Given their flexibility and encouraging performance, deep-learning models are becoming standard for motion prediction in autonomous driving. However, with great flexibility comes a lack of interpretability and possible violations of physical constraints. Accompanying these data-driven methods with differentially-constrained motion models to provide physically feasible trajectories is a promising future direction. The foundation for this work is a previously introduced graph-neural-network-based model, MTP-GO. The neural network learns to compute the inputs to an underlying motion model to provide physically feasible trajectories. This research investigates the performance of various motion models in combination with numerical solvers for the prediction task. The study shows that simpler models, such as low-order integrator models, are preferred over more complex, e.g., kinematic models, to achieve accurate predictions. Further, the numerical solver can have a substantial impact on performance, advising against commonly used first-order methods like Euler forward. Instead, a second-order method like Heuns can greatly improve predictions.

A methodology for the generation of representative driving cycles is proposed and evaluated. The proposed method combines traffic simulation and driving behavior modeling to generate mission-based driving cycles. Extensions to the existing behavioral model in a traffic simulation tool are suggested and parameterized for different driver categories to capture the effects of road geometry and variances between drivers. The evaluation results illustrate that the developed extensions significantly improve the match between driving data and the driving cycles generated by traffic simulation. Using model extensions parameterized for different driver categories, instead of only one average driver, provides the possibility to represent different driving behaviors and further improve the realism of the resulting driving cycles.

With trends as IoT and increased connectivity, the availability of data is consistently increasing and its automated processing with, e.g., machine learning becomes more important. This is certainly true for the area of fault diagnostics and prognostics. However, for rare events like faults, the availability of meaningful data will stay inherently sparse making a pure data-driven approach more difficult. In this paper, the question when to use model-based, data-driven techniques, or a combined approach for fault diagnosis is discussed using real-world data of a permanent magnet synchronous machine. Key properties of the different approaches are discussed in a diagnosis context, performance quantified, and benefits of a combined approach are demonstrated.

This paper investigates an integrated traffic environment modeling and model predictive control (MPC) system to realize interaction-aware dynamic motion planning of an autonomous vehicle with multiple surrounding vehicles. The interaction-aware interacting multiple model Kalman filter (IAIMM-KF) from the literature is used to hierarchically predict maneuvers and trajectories of surrounding vehicles and to compute safe targets for the ego vehicle. The targets are terminal speed and reference lane, which are moving targets as they are updated at each time step. Then, an MPC controller is designed for the ego vehicle to generate an optimal trajectory by following the moving targets and including the prediction results to formulate collision-free constraints. The proposed interaction-aware planning method has a proactive planning ability and can avoid collisions by non-local replanning. The strengths and effectiveness of the approach are verified in challenging highway lane-change simulation scenarios.

An approach to resilient planning and control of autonomous vehicles in multi-vehicle traffic scenarios is proposed. The proposed method is based on model predictive control (MPC), where alternative predictions of the surrounding traffic are determined automatically such that they are intentionally adversarial to the ego vehicle. This provides robustness against the inherent uncertainty in traffic predictions. To reduce conservatism, an assumption that other agents are of no ill intent is formalized. Simulation results from highway driving scenarios show that the proposed method in real-time negotiates traffic situations out of scope for a nominal MPC approach and performs favorably to state-of-the-art reinforcement-learning approaches without requiring prior training. The results also show that the proposed method performs effectively, with the ability to prune disturbance sequences with a lower risk for the ego vehicle.

To study the effects of uncertainty in autonomous motion planning and control, an 8-DOF model of a tractor-semitrailer is implemented and analyzed. The implications of uncertainties in the model are then quantified and presented using sensitivity analysis and closed-loop simulations. The study shows that different model parameters are more or less critical depending on the investigated scenario.- Using sampling-based closed-loop predictions, uncertainty bounds on state variable trajectories are determined. Our findings suggest the potential for the inclusion of our method within a robust predictive controller or as a driver-assistance system for rollover or lane departure warning.

Predictive maintenance of systems and their components in technical systems is a promising approach to optimize system usage and reduce system downtime. Various sensor data are logged during system operation for different purposes, but sometimes not directly related to the degradation of a specific component. Variable selection algorithms are necessary to reduce model complexity and improve interpretability of diagnostic and prognostic algorithms. This paper presents a forest-based variable selection algorithm that analyzes the distribution of a variable in the decision tree structure, called Variable Depth Distribution, to measure its importance. The proposed variable selection algorithm is developed for datasets with correlated variables that pose problems for existing forest-based variable selection methods. The proposed variable selection method is evaluated and analyzed using three case studies: survival analysis of lead-acid batteries in heavy-duty vehicles, engine misfire detection, and a simulated prognostics dataset. The results show the usefulness of the proposed algorithm, with respect to existing forest-based methods, and its ability to identify important variables in different applications. As an example, the battery prognostics case study shows that similar predictive performance is achieved when only 17% percent of the variables are used compared to all measured signals.

A cooperative control approach for autonomous vehicles is developed in order to perform different complex traffic maneuvers, e.g., double lane-switching or intersection situations. The problem is formulated as a distributed optimal control problem for a system of multiple autonomous vehicles and then solved using a nonlinear Model Predictive Control (MPC) technique, where the distributed approach is used to make the problem computationally feasible in real-time. To provide safety, a collision avoidance constraint is introduced, also in a distributed way. In the proposed method, each vehicle computes its own control inputs using estimated states of neighboring vehicles. In addition, a compatibility constraint is defined that takes collision avoidance into account but also ensures that each vehicle does not deviate significantly from what is expected by neighboring vehicles. The method allows us to construct a cost function for several different traffic scenarios. The asymptotic convergence of the system to the desired destination is proven, in the absence of uncertainty and disturbances, for a sufficiently small MPC control horizon. Simulation results show that the distributed algorithm scales well with increasing number of vehicles.

This work presents a method for on-line condition monitoring of a hydraulic rock drill, though some of the findings can likely be applied in other applications. A fundamental difficulty for the rock drill application is discussed, namely the similarity between frequencies of internal standing waves and rock drill operation. This results in unpredictable pressure oscillations and superposition, which makes synchronization between measurement and model difficult. To overcome this, a data driven approach is proposed. The number and types of sensors are restricted due to harsh environmental conditions, and only operational data is available. Some faults are shown to be detectable using hand-crafted engineering features, with a direct physical connection to the fault of interest. Such features are easily interpreted and are shown to be robust against disturbances. Other faults are detected by classifying measured signals against a known reference. Dynamic Time Warping is shown to be an efficient way to measure similarity for cyclic signals with stochastic elements from disturbances, wave propagation and different durations, and also for cases with very small differences in measured pressure signals. Together, the two methods enables a step towards condition monitoring of a rock drill, robustly detecting very small changes in behaviour using a minimum amount of sensors. Copyright (C) 2021 The Authors.

A computationally cheap method for computing collision-free trajectories with multiple moving obstacles is proposed here while meeting comfort and safety criteria. By avoiding search in the trajectory calculation and instead using a geometrical set to calculate the trajectory, the calculation time is significantly reduced. The geometrical set is calculated by solving a support vector machine problem and solving the SVM problem characterizes maximum separating surfaces between obstacles and the ego vehicle in the time-space domain. The trajectory on the separating surface might not be kinematically feasible. Therefore, a vehicle model and a Newton-Raphson based procedure is proposed to obtain a safe, kinematically feasible trajectory on the separating surface. A roundabout scenario and two take-over scenarios with different configurations are used to investigate the properties of the proposed algorithm. Robustness properties of the proposed algorithm is investigated by a large number of randomly initiated simulation scenarios.

Simultaneous optimization of fuel consumption and battery lifetime is addressed in this work. A differential capacity degradation model is used to predict capacity loss, and linear time-varying and nonlinear MPC techniques are used to solve the energy management problem. It is shown that penalizing battery power in the MPC cost function can prolong battery lifetime by about 50 percent while achieving small gains in fuel economy compared to when the cost function only aims to minimize fuel consumption. An analysis of robustness against uncertainties in drive-cycle information shows that the controller is well-behaved and has good performance under uncertainty.

Efficient trajectory planning of autonomous vehiclesin complex traffic scenarios is of interest both academically andin automotive industry. Time efficiency and safety are of keyimportance and here a two-step procedure is proposed. First, aconvex optimization problem is solved, formulated as a supportvector machine (SVM), in order to represent the surroundingenvironment of the ego vehicle and classify the search spaceas obstacles or obstacle free. This gives a reduced complexitysearch space and an A* algorithm is used in a state space latticein 4 dimensions including position, heading angle and velocityfor simultaneous path and velocity planning. Further, a heuristicderived from the SVM formulation is used in the A* search anda pruning technique is introduced to significantly improve searchefficiency. Solutions from the proposed planner is compared tooptimal solutions computed using optimal control techniques.Three traffic scenarios, a roundabout scenario and two complextakeover maneuvers, with multiple moving obstacles, are used toillustrate the general applicability of the proposed method.

The use of learning-based methods for vehicle behavior prediction is a promising research topic. However, many publicly available data sets suffer from class distribution skews which limits learning performance if not addressed. This paper proposes an interaction-aware prediction model consisting of an LSTM autoencoder and SVM classifier. Additionally, an imbalanced learning technique, the multiclass balancing ensemble is proposed. Evaluations show that the method enhances model performance, resulting in improved classification accuracy. Good generalization properties of learned models are important and therefore a generalization study is done where models are evaluated on unseen traffic data with dissimilar traffic behavior stemming from different road configurations. This is realized by using two distinct highway traffic recordings, the publicly available NGSIM US-101 and I80 data sets. Moreover, methods for encoding structural and static features into the learning process for improved generalization are evaluated. The resulting methods show substantial improvements in classification as well as generalization performance.

The study of fault diagnosis on automotive engine systems has been an interesting and ongoing topic for many years. Numerous research projects were conducted by automakers and research institutions to discover new and more advanced methods to perform diagnosis for better fault isolation (FI). Some of the research in this field has been reported in.

The life of a vehicle is heavily influenced by how it is used, and usage information is critical to predict the future condition of the machine. In this work we present a method to categorize what task an earthmoving vehicle is performing, based on a data driven model and a single standalone accelerometer. By training a convolutional neural network using a couple of weeks of labeled data, we show that a three axis accelerometer is sufficient to correctly classify between 5 different classes with an accuracy over 96% for a balanced dataset with no manual feature generation. The results are also compared against some other machine learning techniques, showing that the convolutional neural network has the highest performance, although other techniques are not far behind. An important conclusion is that methods and ideas from the area of Human Activity Recognition (HAR) are applicable also for vehicles. Copyright (C) 2020 The Authors.

This paper presents a method to enhance fault isolation without adding physical sensors on a turbocharged spark ignited petrol engine system by designing additional residuals from an initial observer-based residuals setup. The best candidates from all potential additional residuals are selected using the concept of sequential residual generation to ensure best fault isolation performance for the least number of additional residuals required. A simulation testbed is used to generate realistic engine data for the design of the additional residuals and the fault isolation performance is verified using structural analysis method.

The life and condition of a mine truck frame are related to how the machine is used. Damage from stress cycles is accumulated over time, and measurements throughout the life of the machine are needed to monitor the condition. This results in high demands on the durability of sensors, especially in a harsh mining application. To make a monitoring system cheap and robust, sensors already available on the vehicles are preferred rather than additional strain gauges. The main question in this work is whether the existing on-board sensors can give the required information to estimate stress signals and calculate accumulated damage of the frame. Model complexity requirements and sensors selection are also considered. A final question is whether the accumulated damage can be used for prognostics and to increase reliability. The investigation is performed using a large data set from two vehicles operating in real mine applications. Coherence analysis, ARX-models, and rain flow counting are techniques used. The results show that a low number of available on-board sensors like load cells, damper cylinder positions, and angle transducers can give enough information to recreate some of the stress signals measured. The models are also used to show significant differences in usage by different operators, and its effect on the accumulated damage.

Predictive maintenance aims to predict failures in components of a system, a heavy-duty vehicle in this work, and do maintenance before any actual fault occurs. Predictive maintenance is increasingly important in the automotive industry due to the development of new services and autonomous vehicles with no driver who can notice first signs of a component problem. The lead-acid battery in a heavy vehicle is mostly used during engine starts, but also for heating and cooling the cockpit, and is an important part of the electrical system that is essential for reliable operation. This paper develops and evaluates two machine-learning based methods for battery prognostics, one based on Long Short-Term Memory (LSTM) neural networks and one on Random Survival Forest (RSF). The objective is to estimate time of battery failure based on sparse and non-equidistant vehicle operational data, obtained from workshop visits or over-the-air readouts. The dataset has three characteristics: 1) no sensor measurements are directly related to battery health, 2) the number of data readouts vary from one vehicle to another, and 3) readouts are collected at different time periods. Missing data is common and is addressed by comparing different imputation techniques. RSF- and LSTM-based models are proposed and evaluated for the case of sparse multiple-readouts. How to measure model performance is discussed and how the amount of vehicle information influences performance.

Finding the cheapest, or smallest, set of sensors such that a specified level of diagnosis performance is maintained is important to decrease cost while controlling performance. Algorithms have been developed to find sets of sensors that make faults detectable and isolable under ideal circumstances. However, due to model uncertainties and measurement noise, different sets of sensors result in different achievable diagnosability performance in practice. In this paper, the sensor selection problem is formulated to ensure that the set of sensors fulfils required performance specifications when model uncertainties and measurement noise are taken into consideration. However, the algorithms for finding the guaranteed global optimal solution are intractable without exhaustive search. To overcome this problem, a greedy stochastic search algorithm is proposed to solve the sensor selection problem. A case study demonstrates the effectiveness of the greedy stochastic search in finding sets close to the global optimum in short computational time.

Fault detection and fault isolation performance of a model based diagnosis system mainly depends on the level of model uncertainty and the time allowed for detection. The longer time for detection that can be accepted, the more certain detection can be achieved and the main objective of this paper is to show how the window length relates to a diagnosis performance measure. A key result is an explicit expression for asymptotic performance with respect to window length and it is shown that there exists a linear asymptote as the window length tends to infinity. The gradient of the asymptote is a system property that can be used in the evaluation of diagnosis performance when designing a system. A key property of the approach is that the model of the system is analyzed directly, which makes the approach independent of detection filter design. (C) 2019 Elsevier Ltd. All rights reserved.

Deterministic and real time calculation of safe and comfortable speed profiles is the main topic of this paper. Using vehicle properties and road characteristics, such as friction and road banking, safety limits for rollover and skidding are calculated and applied in the trajectory planning. To satisfy comfort criteria and obtain smooth speed profiles, jerk and acceleration of the vehicle are limited in the speed planning algorithm. For speed planner, an A* based search method is used to calculate a speed profile corresponding to shortest traveling time. In order to avoid stationary and moving obstacles, decoupled prioritized planning is used. A physical model is used to define the behavior of the vehicle in the speed planner, where jerk is main parameter for speed planner. The physical model enables the algorithm to take into account the safety and comfort limitations. The results attained from the search method are compared with optimal solutions in different test scenarios and the comparisons show the properties of the algorithm. (C) 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

The concept of mission-based driving cycles has been introduced as an efficient way of generating driving cycles with desired characteristics for data-driven development of vehicle powertrains. Mission-based driving cycles can be generated using traffic simulation tools with improved behavioral models that match simulation outputs and naturalistic driving data. Here, driving behavior categorization and how it can be used to create a set of differently parameterized behavioral models corresponding to various types of drivers, are studied. The focus is on curvy road driving, and two different categorization features are used, speed through the curves and the braking behavior.

Driving cycles are nowadays, to an increasing extent, used as input to model-based vehicle design and as training data for development of vehicle models and functions with machine learning algorithms. Recorded real driving data may underrepresent or even lack important characteristics, and therefore there is a need to complement driving cycles obtained from real driving data with synthetic data that exhibit various desired characteristics. In this paper, an efficient method for generation of mission-based driving cycles is developed for this purpose. It is based on available effective methods for traffic simulation and available maps to define driving missions. By comparing the traffic simulation results with real driving data, insufficiencies in the existing behavioral model in the utilized traffic simulation tool are identified. Based on these findings, four extensions to the behavioral model are suggested, staying within the same class of computational complexity so that it can still be used in a large scale. The evaluation results show significant improvements in the match between the data measured on the road and the outputs of the traffic simulation with the suggested extensions of the behavioral model. The achieved improvements can be observed with both visual inspection and objective measures. For instance, the 40% difference in the relative positive acceleration of the originally simulated driving cycle compared to real driving data was eliminated using the suggested model.

Finding safe and collision free trajectories in an environment with moving obstacles is central for autonomous vehicles but at the same time a complex task. A reason is that the search space in space-time domain is very complex. This paper proposes a two-step approach where in first step, the search space for trajectory planning is simplified by solving a convex optimization problem formulated as a Support Vector Machine resulting in an obstacle free corridor that is suitable for a trajectory planner. Then, in a second step, a basic A* search strategy is used in the obstacle free search space. Due to the physical model used, the comfort and safety criteria are applied while searching the trajectory. The vehicle rollover prevention is used as a safety criterion and the acceleration, jerk and steering angle limits are used as comfort criteria. For simulations, urban environments with intersections and vehicles as moving obstacles are constructed. The properties of the approach are examined by the simulation results. (C) 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

Machine learning can be used to automatically process sensor data and create data-driven models for prediction and classification. However, in applications such as fault diagnosis, faults are rare events and learning models for fault classification is complicated because of lack of relevant training data. This paper proposes a hybrid diagnosis system design which combines model-based residuals with incremental anomaly classifiers. The proposed method is able to identify unknown faults and also classify multiple-faults using only single-fault training data. The proposed method is verified using a physical model and data collected from an internal combustion engine.

Maintenance planning is important in the automotive industry as it allows fleet owners or regular customers to avoid unexpected failures of the components. One cause of unplanned stops of heavy-duty trucks is failure in the lead-acid starter battery. High availability of the vehicles can be achieved by changing the battery frequently, but such an approach is expensive both due to the frequent visits to a workshop and also due to the component cost. Here, a data-driven method based on random survival forest (RSF) is proposed for predicting the reliability of the batteries. The dataset available for the study, covering more than 50 000 trucks, has two important properties. First, it does not contain measurements related directly to the battery health; second, there are no time series of measurements for every vehicle. In this paper, the RSF method is used to predict the reliability function for a particular vehicle using data from the fleet of vehicles given that only one set of measurements per vehicle is available. A theory for confidence bands for the RSF method is developed, which is an extension of an existing technique for variance estimation in the random forest method. Adding confidence bands to the RSF method gives an opportunity for an engineer to evaluate the confidence of the model prediction. Some aspects of the confidence bands are considered: their asymptotic behavior and usefulness in model selection. A problem of including time-related variables is addressed in this paper with the argument that why it is a good choice not to add them into the model. Metrics for performance evaluation are suggested, which show that the model can be used to schedule and optimize the cost of the battery replacement. The approach is illustrated extensively using the real-life truck data case study.

A dynamic obstacle avoidance Model Predictive Control (MPC) method is introduced for autonomous driving that uses deep learning technique for velocity-dependent collision avoidance in unknown environments. The objective of the method is to control an autonomous vehicle in order to perform different traffic maneuvers in a safe way with maximum comfort of passengers, and in minimum possible time, accounting for maneuvering capabilities, vehicle dynamics, and in the presence of traffic rules, road boundaries and static and dynamic unknown obstacles. Here, by defining local coordinates and collision regions, the dynamic collision avoidance problem is translated into a static collision avoidance problem which makes the method easier and faster to be solved in dynamical environments. In order to provide safety, an ensemble of deep neural networks is used to estimate the probability of collision and to form an uncertainty-dependent collision cost which prioritizes between mission and safety. The collision cost is a product of the probability of collision and vehicle’s velocity in the directions with high collision-risk. The dynamic obstacle avoidance optimization method minimizes the velocity in the obstacle cones where the probability of collision is high or in unfamiliar environments, and increases the velocity when probability and variation in predicted values of the ensemble are low. The predicted trajectory from MPC is used in learning procedure in order to assign labels that makes it possible to predict the collision in advance. Simulation results show that the proposed method has good adaptability to unknown environments.

Representative driving cycles are of key importance for design and dimensioning of powertrains. One approach for generation of representatives driving cycles is to define relevant driving missions which include different street types, obstacles and traffic conditions, and simulate them in a traffic simulation tool. Such a simulation approach will also require representative driver models to generate the speed profiles for the defined driving missions. Feasibility of this approach is investigated in this paper.

To leverage on model based engineering for fault diagnosis, it is useful to be able to do direct analysis of general purpose modelling languages for engineering systems. In this work, it is demonstrated how non-trivial Modelica models, for example utilizing the Modelica standard library, can be automatically transformed into a format where existing fault diagnosis analysis techniques are applicable. The procedure is demonstrated on a model of an air cooling system in the Gripen fighter aircraft developed by Saab, Sweden. It is discussed why the Modelica language is well suited for diagnosability analysis, and a number of non-trivial diagnosability analysis shows the efficacy of the approach. The methods extract the model structure, which gives additional insight into the system, e.g., highlighting model connections and possible model decompositions. (C) 2018, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

Predictive maintenance of components has the potential to significantly reduce costs for maintenance and to reduce unexpected failures. Failure prognostics for heavy-duty truck lead-acid batteries is considered with a multilayer perceptron (MLP) predictive model. Data used in the study contains information about how approximately 46,000 vehicles have been operated starting from the delivery date until the date when they come to the workshop. The model estimates a reliability and lifetime probability function for a vehicle entering a workshop. First, this work demonstrates how heterogeneous data is handled, then the architectures of the MLP models are discussed. Main contributions are a battery maintenance planning method and predictive performance evaluation based on reliability and lifetime functions, a new model for reliability function when its true shape is unknown, the improved objective function for training MLP models, and handling of imbalanced data and comparison of performance of different neural network architectures. Evaluation shows significant improvements of the model compared to more simple, time-based maintenance plans.

Computation and sampling time requirements for real-time implementation of observers is studied. A common procedure for state estimation and observer design is to have a system model in continuous time that is converted to sampled time with Euler forward method and then the observer is designed and implemented in sampled time in the real time system. When considering state estimation in real time control systems for production there are often limited computational resources. This becomes especially apparent when designing observers for stiff systems since the discretized implementation requires small step lengths to ensure stability. One way to reduce the computational burden, is to reduce the model stiffness by approximating the fast dynamics with instantaneous relations, transforming an ordinary differential equations (ODE) model into a differential algebraic equation (DAE) model. Performance and sampling frequency limitations for extended Kalman filter (EKF)s based on both the original ODE model and the reduced DAE model are here analyzed and compared for an industrial system. Furthermore, the effect of using backward Euler instead of forward Euler when discretizing the continuous time model is also analyzed. The ideas are evaluated using measurement data from a diesel engine. The engine is equipped with throttle, exhaust gas recirculation (EGR), and variable geometry turbines (VGT) and the stiff model dynamics arise as a consequence of the throttle between two control volumes in the air intake system. The process of simplifying and modifying the stiff ODE model to a DAE model is also discussed. The analysis of the computational effort shows that even though the ODE, for each time-update, is less computationally demanding than the resulting DAE, an EKF based on the DAE model achieves better estimation performance than one based on the ODE with less computational effort. The main gain with the DAE based EKF is that it allows increased step lengths without degrading the estimation performance compared to the ODE based EKF.

A common architecture of model-based diagnosis systems is to use a set of residuals to detect and isolate faults. In the paper it is motivated that in many cases there are more possible candidate residuals than needed for detection and single fault isolation and key sources of varying performance in the candidate residuals are model errors and noise. This paper formulates a systematic method of how to select, from a set of candidate residuals, a subset with good diagnosis performance. A key contribution is the combination of a machine learning model, here a random forest model, with diagnosis specific performance specifications to select a high performing subset of residuals. The approach is applied to an industrial use case, an automotive engine, and it is shown how the trade-off between diagnosis performance and the number of residuals easily can be controlled. The number of residuals used are reduced from original 42 to only 12 without losing significant diagnosis performance. (C) 2018, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

In model-based diagnosis there are often more candidate residual generators than what is needed and residual selection is therefore an important step in the design of model-based diagnosis systems. The availability of computer-aided tools for automatic generation of residual generators have made it easier to generate a large set of candidate residual generators for fault detection and isolation. Fault detection performance varies significantly between different candidates due to the impact of model uncertainties and measurement noise. Thus, to achieve satisfactory fault detection and isolation performance, these factors must be taken into consideration when formulating the residual selection problem. Here, a convex optimization problem is formulated as a residual selection approach, utilizing both structural information about the different residuals and training data from different fault scenarios. The optimal solution corresponds to a minimal set of residual generators with guaranteed performance. Measurement data and residual generators from an internal combustion engine test-bed is used as a case study to illustrate the usefulness of the proposed method.

A novel trajectory planning method is proposedin time varying environments for highway driving scenarios.The main objective is to ensure computational efficiency in theapproach, while still ensuring collision avoidance with movingobstacles and respecting vehicle constraints such as comfortcriteria and roll-over limits. The trajectory planning problemis separated into finding a collision free corridor in space-time domain using a support vector machine (SVM), whichmeans solving a convex optimization problem. After that atime-monotonic path is found in the collision free corridor bysolving a simple search problem that can be solved efficiently.The resulting path in space-time domain corresponds to theresulting planned trajectory of the vehicle. The planner is adeterministic search method associated with a cost functionthat keeps the trajectory kinematically feasible and close to themaximum separating surface, given by the SVM. A kinematicmotion model is used to construct motion primitives in thespace-time domain representing the non-holonomic behavior ofthe vehicle and is used to ensure physical constraints on thestates of the vehicle such as acceleration, speed, jerk, steer andsteer rate. The speed limits include limitations by law and alsorollover speed limits. Two highway maneuvers have been usedas test scenarios to illustrate the performance of the proposedalgorithm.

To facilitate the use of advanced fault diagnosis analysis and design techniques to industrial sized systems, there is a need for computer support. This paper describes a Matlab toolbox and evaluates the software on a challenging industrial problem, air-path diagnosis in an automotive engine. The toolbox includes tools for analysis and design of model based diagnosis systems for large-scale differential algebraic models. The software package supports a complete tool-chain from modeling a system to generating C-code for residual generators. Major design steps supported by the tool are modeling, fault diagnosability analysis, sensor selection, residual generator analysis, test selection, and code generation. Structural methods based on efficient graph theoretical algorithms are used in several steps. In the automotive diagnosis example, a diagnosis system is generated and evaluated using measurement data, both in fault-free operation and with faults injected in the control-loop. The results clearly show the benefit of the toolbox in a model-based design of a diagnosis system. Latest version of the toolbox can be downloaded at faultdiagnosistoolbox.github.io. (C) 2017, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

Structural approaches have shown to be useful for analyzing and designing diagnosis systems for industrial systems. In simulation and estimation literature, related theories about differential index have been developed and, also there, structural methods have been successfully applied for simulating large-scale differential algebraic models. A main contribution of this paper is to connect those theories and thus making the tools from simulation and estimation literature available for model based diagnosis design. A key step in the unification is an extension of the notion of differential index of exactly determined systems of equations to overdetermined systems of equations. A second main contribution is how differential-index can be used in diagnosability analysis and also in the design stage where an exponentially sized search space is significantly reduced. This allows focusing on residual generators where basic design techniques, such as standard state-observation techniques and sequential residual generation are directly applicable. The developed theory has a direct industrial relevance, which is illustrated with discussions on an automotive engine example. (C) 2017, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

The life and condition of a MT65 mine truck frame is to a large extent related to how the machine is used. Damage from different stress cycles in the frame are accumulated over time, and measurements throughout the life of the machine are needed to monitor the condition. This results in high demands on the durability of sensors used. To make a monitoring system cheap and robust enough for a mining application, a small number of robust sensors are preferred rather than a multitude of local sensors such as strain gauges. The main question to be answered is whether a low number of robust on-board sensors can give the required information to recreate stress signals at various locations of the frame. Also the choice of sensors among many different locations and kinds are considered. A final question is whether the data could also be used to estimate road condition. By using accelerometer, gyroscope and strain gauge data from field tests of an Atlas Copco MT65 mine truck, coherence and Lasso-regression were evaluated as means to select which signals to use. ARX-models for stress estimation were created using the same data. By simulating stress signals using the models, rain flow counting and damage accumulation calculations were performed. The results showed that a low number of on-board sensors like accelerometers and gyroscopes could give enough information to recreate some of the stress signals measured. Together with a linear model, the estimated stress was accurate enough to evaluate the accumulated fatigue damage in a mining truck. The accumulated damage was also used to estimate the condition of the road on which the truck was traveling. To make a useful road monitoring system some more work is required, in particular regarding how vehicle speed influences damage accumulation.

Path planning algorithms have evolved during decades to become computationally less expensive and optimal. In this paper a deterministic approach is used to find a path near to the shortest path using motion primitives. The motion primitives are constructed using a non-holonomic vehicle model. The physical model enables the algorithm to use a friction map and calculate paths with lower lateral slip forces. Furthermore the algorithm takes into account the steer rate using steer angles assigned for motion primitives. The algorithm is an A* based search method along with a heuristic to find a near optimal solution. The performance and calculation time of the algorithm is tunable by adjusting motion primitive size and discretization steps. In order to compare the algorithm output to optimal solution a direct multiple shooting method is used. The algorithm is simulated in different scenarios that shows the properties of the algorithm. The results attained from search method is compared with optimal solution in two different test scenarios and the comparison shows consistency of search method to the optimal solution.

This paper describes a cooperative control method for autonomous vehicles, in order to perform different traffic maneuvers. The problem is formulated as a distributed optimal control problem for a system of multiple autonomous vehicles with an identified model and then solved using nonlinear Model Predictive Control (MPC). The distributed approach has been used in order to make the problem computationally feasible to be solved in real-time. In the proposed method, each vehicle computes its own control inputs using estimated states of neighboring vehicles. The constraints on the control inputs ensure the comfort of passengers. The method allows us to construct a cost function for several different scenarios in which safety and performing the maneuver constitute two terms of the integrated cost of the finite horizon optimization problem. To provide safety, a potential function is introduced for collision avoidance. Simulation results show that the distributed algorithm scales well with increasing number of vehicles. (C) 2017, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

There is a current strong trend where driving cycles are used extensively in vehicle design, especially for calibration and tuning of all powertrain systems for control and diagnosis. In such situations it is essential to capture real driving, and therefore using only a few driving cycles would lead to the risk that a test or a design would be tailored to details in a specific driving cycle. Consequently there are now widespread activities using techniques from statistics, big data and mission modeling to address these issues. For all such methods there is an important final step to calibrate a representative cycle to adhere to fair propulsion requirements on the driven wheels over a cycle. For this a general methodology has been developed, applicable to a wide range of problems involving driving cycle transformations. It is based on a definition of equivalence for driving cycles that loosely speaking defines being similar without being the same. Based on this, a set of algorithms are developed to transform a given driving cycle into an equivalent one, or into a cycle with given equivalence measure. The transformations are effectively handled as a nonlinear program that is solved using general purpose optimization techniques. The proposed method is general and a wide range of constraints can be used.

In this paper, a cooperative fuel and comfort efficient control for autonomous vehicles is presented in order to perform different traffic maneuvers. The problem is formulated as an optimal control problem in which the cost function takes into account the fuel consumption and passengers comfort, subject to safety and speed constraints. The optimal solution takes into account the comfort and fuel consumption, which is obtained by minimizing a jerk, an acceleration, and a fuel criterion. It is shown that the method can be applied to control different groups of vehicles in different traffic scenarios. Simulation results are used to illustrate the generality property and performance of the proposed approach.

Path planning and path following are core components in safe autonomous driving. Typically, a path planner provides a path with some tolerance on how tightly the path should be followed. Based on that, and other path characteristics, for example, sharpness of curves, a speed profile needs to be assigned so that the vehicle can stay within the given tolerance without going unnecessarily slow. Here, such trajectory planning is based on optimal control formulations where critical cases arise as on-the-limit solutions. The study focuses on heavy commercial vehicles, causing rollover to be of a major concern, due to the relatively high centre of gravity. Several results are obtained on required model complexity depending on path characteristics, for example, quantification of required path tolerance for a simple model to be sufficient, quantification of when yaw inertia needs to be considered in more detail, and how the curvature rate of change interplays with available friction. Overall, in situations where the vehicle is subject to a wide range of driving conditions, from good transport roads to more tricky avoidance manoeuvres, the requirements on the path following will vary. For this, the provided results form a basis for real-time path following.

The present paper proposes an advanced approach for Polymer Electrolyte Membrane Fuel Cell (PEMFC) systems fault detection and isolation through a model-based diagnostic algorithm. The considered algorithm is developed upon a lumped parameter model simulating a whole PEMFC system oriented towards automotive applications. This model is inspired by other models available in the literature, with further attention to stack thermal dynamics and water management. The developed model is analysed by means of Structural Analysis, to identify the correlations among involved physical variables, defined equations and a set of faults which may occur in the system (related to both auxiliary components malfunctions and stack degradation phenomena). Residual generators are designed by means of Causal Computation analysis and the maximum theoretical fault isolability, achievable with a minimal number of installed sensors, is investigated. The achieved results proved the capability of the algorithm to theoretically detect and isolate almost all faults with the only use of stack voltage and temperature sensors, with significant advantages from an industrial point of view. The effective fault isolability is proved through fault simulations at a specific fault magnitude with an advanced residual evaluation technique, to consider quantitative residual deviations from normal conditions and achieve univocal fault isolation.

A model predictive controller (MPC) including velocity and path planner is designed for real time calculation of a safe and comfortable velocity and steer angle in a heavy duty vehicle. The calculation time is reduced by finding, based on measurement data, simple roll and motion model. The roll dynamics of the truck is constructed using identification of proposed roll model and it is validated by measurements logged by a heavy duty truck and the suggested model shows good agreement with the measurement data. The safety issues such as rollover prevention and moving obstacle avoidance are taken into account. To increase comfort, acceleration, jerk, steer angle and steer angle rate are limited. The simulation and control algorithm is tested in different scenarios, where the test results show the properties of the algorithm.

Detecting changes in residuals is important for fault detection and is commonly performed by thresholding the residual using, for example, a CUSUM test. However, detecting variations in the residual distribution, not causing a change of bias or increased variance, is difficult using these methods. A plug-and-play residual change detection approach is proposed based on sequential quantile estimation to detect changes in the residual cumulative density function. An advantage of the proposed algorithm is that it is non-parametric and has low computational cost and memory usage which makes it suitable for on-line implementations where computational power is limited.

The charge sustaining mode of a hybrid electric vehicle maintains the state of charge of the battery within a predetermined narrow band. Due to the poor system observability in this range, the state of charge estimation is tricky, and inadequate prior knowledge of the system uncertainties could lead to deterioration and divergence of estimates. In this paper, a comparative study of three estimators tuned based on the noise covariance matching technique is established in order to analyze their robustness in the state of charge estimation. Simulation results show a significant enhancement of filter accuracy using this adaptation. The adaptive particle filter has the best estimation results but it is vulnerable to model parameter uncertainties, further it is time consuming. On the other hand, the adaptive Unscented Kalman filter and the adaptive Extended Kalman filter show enough estimation accuracy, robustness for model uncertainty, and simplicity of implementation. (C) 2017, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

A hybrid diagnosis system design is proposed that combines model-based and data-driven diagnosis methods for fault isolation. A set of residuals are used to detect if there is a fault in the system and a consistency-based fault isolation algorithm is used to compute all diagnosis candidates that can explain the triggered residuals. To improve fault isolation, diagnosis candidates are ranked by evaluating the residuals using a set of one-class support vector machines trained using data from different faults. The proposed diagnosis system design is evaluated using simulations of a model describing the air-flow in an internal combustion engine.

A commonly used signal for engine misfire detection is the crankshaft angular velocity measured at the flywheel. However, flywheel manufacturing errors result in vehicle-to-vehicle variations in the measurements and have a negative impact on the misfire detection performance, where the negative impact is quantified for a number of vehicles. A misfire detection algorithm is proposed with flywheel error adaptation in order to increase robustness and reduce the number of mis-classifications. Since the available computational power is limited in a vehicle, a filter with low computational load, a Constant Gain Extended Kalman Filter, is proposed to estimate the flywheel errors. Evaluations using measurements from vehicles on the road show that the number of mis-classifications is significantly reduced when taking the estimated flywheel errors into consideration.

A common situation in industry is to store measurements for different operating points in the lookup tables, often called maps. They are used in many tasks, e.g., in control and estimation, and therefore considerable investments in engineering time are spent in measuring them which usually make them accurate descriptions of the fault-free system. They are thus well suited for fault detection, but, however, such a model cannot give fault isolation since only the fault free behavior is modeled. One way to handle this situation would be also to map all fault cases but that would require measurements for all faulty cases, which would be costly if at all possible. Instead, the main contribution here is a method to combine the lookup model with analytical fault models. This makes good use of all modeling efforts of the lookup model for the fault-free case, and combines it with fault models with reasonable modeling and calibration efforts, thus decreasing the engineering effort in the diagnosis design. The approach is exemplified by designing a diagnosis system monitoring the power electronics and the electric machine in a hybrid electric vehicle. An extensive simulation study clearly shows that the approach achieves both good fault detectability and isolability performance. A main point is that this is achieved without the need for neither measurements of a faulty system nor detailed physical modeling, thus saving considerable amounts of development time.

Predicting lead-acid battery failure is important for heavy-duty trucks to avoid unplanned stops by the road. There are large amount of data from trucks in operation, however, data is not closely related to battery health which makes battery prognostic challenging. A new method for identifying important variables for battery failure prognosis using random survival forests is proposed. Important variables are identified and the results of the proposed method are compared to existing variable selection methods. This approach is applied to generate a prognosis model for lead-acid battery failure in trucks and the results are analyzed. (C) 2016, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.