Multi-mode systems can operate in different modes, leading to large numbers of different dynamics. Consequently, applying traditional structural diagnostics to such systems is often untractable. To address this challenge, we present a multi-mode diagnostics algorithm that relies on a multi-mode extension of the Dulmage-Mendelsohn decomposition. We introduce two methodologies for modeling faults, either as signals or as Boolean variables, and apply them to a modular switched battery system in order to demonstrate their effectiveness and discuss their respective advantages.

Safety, reliability, and durability are targets of all engineering systems, including Li-ion batteries in electric vehicles. This paper focuses on sensor setup exploration for a battery-integrated modular multilevel converter (BI-MMC) that can be part of a solution to sustainable electrification of vehicles. BI-MMC contains switches to convert DC to AC to drive an electric machine. The various configurations of switches result in different operation modes, which in turn, pose great challenges for diagnostics. The study explores diverse sensor arrangements and system configurations for detecting and isolating faults in modular battery packs. Configurations involving a minimum of two modules integrated into the pack are essential to successfully isolate all faults. The findings indicate that the default sensor setup is insufficient for achieving complete fault isolability. Additionally, the investigation also demonstrates that current sensors in the submodules do not contribute significantly to fault isolability. Further, the results on switch positions show that the system configuration has a significant impact on fault isolability. A combination of appropriate sensor data and system configuration is important in achieving optimal diagnosability, which is a paramount objective in ensuring system safety.

Data-driven fault diagnosis requires training data that is representative of the different operating conditions of the system to capture its behavior. If training data is limited, one solution is to incorporate physical insights into machine learning models to improve their effectiveness. However, while previous works show the usefulness of hybrid approaches for isolation of faults, the impact of training data must be taken into consideration when drawing conclusions from data-driven residuals in a consistency-based diagnosis framework. By giving an understanding of the physical interaction between the signals, a hybrid fault diagnosis approach, can enforce model properties of residual generators to isolate faults that are not represented in training data. The objective of this work is to analyze the impact of limited training data when training neural network-based residual generators. It is also investigated how the use of structural information when selecting the network structure is a solution to limited training data and how to ameliorate the performance of hybrid approaches in face of this challenge.

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.

User activity detection in grant-free random access massive machine type communication (mMTC) using pilot-hopping sequences can be formulated as solving a non-negative least squares (NNLS) problem. In this work, two architectures using different algorithms to solve the NNLS problem is proposed. The algorithms are implemented using a fully parallel approach and fixed-point arithmetic, leading to high detection rates and low power consumption. The first algorithm, fast projected gradients, converges faster to the optimal value. The second algorithm, multiplicative updates, is partially implemented in the logarithmic domain, and provides a smaller chip area and lower power consumption. For a detection rate of about one million detections per second, the chip area for the fast algorithm is about 0.7 mm 2 compared to about 0.5 mm 2 for the multiplicative algorithm when implemented in a 28 nm FD-SOI standard cell process at 1 V power supply voltage. The energy consumption is about 300 nJ/detection for the fast projected gradient algorithm using 256 iterations, leading to a convergence close to the theoretical. With 128 iterations, about 250 nJ/detection is required, with a detection performance on par with 192 iterations of the multiplicative algorithm for which about 100 nJ/detection is required.

By running simulation models on FPGAs, their execution speed can be significantly improved, at the cost of increased development effort. This paper describes a project to develop a tool which converts simulation models written in high level languages into fast FPGA hardware. The tool currently converts code written using custom C++ data types into Verilog. A model of a hybrid electric vehicle is used as a case study, and the resulting hardware runs significantly faster than on a general purpose CPU.

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.

In this work, an implementation of a pilot-hopping sequence detector for massive machine type communication is presented. The architecture is based on solution a non-negative least squares problem. The results show that the architecture supporting 1024 users can perform more than one million detections per second with a power consumption of less than 70 mW when implemented in a 28 nm FD-SOI process.

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.

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.