This paper presents a benchmark problem for fault diagnosis of an internal combustion engine that has been formulated and solved. The objective is to design a diagnosis system using and incomplete model information training data that only contains a limited set of fault realizations. Six different solutions to the benchmark, that were presented at the IFAC Safeprocess symposium 2024, are described and evaluated. The contribution of this paper is the benchmark and the presentation of six different solutions in one paper. The paper is intended to provide a starting point for engineers and researchers who work with fault diagnosis and monitoring of technical systems.

Hybrid diagnosis systems combine model-based and data-driven methods to leverage their respective strengths and mitigate individual weaknesses in fault diagnosis. This paper proposes a unified framework for analyzing and designing hybrid diagnosis systems, focusing on the principles underlying the computation of diagnoses from observations. The framework emphasizes the importance of assumptions about fault modes and their manifestations in the system. The proposed architecture supports both fault decoupling and classification techniques, allowing for the flexible integration of model-based residuals and data-driven classifiers. Comparative analysis highlights how classical model-based and pure data-driven systems are special cases within the proposed hybrid framework. The proposed framework emphasizes that the key factor in categorizing fault diagnosis methods is not whether they are model-based or data-driven, but rather their ability to decuple faults which is crucial for rejecting diagnoses when fault training data is limited. Future research directions are suggested to further enhance hybrid fault diagnosis systems.

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.

Online acoustic emission (AE) sensing is a nondestructive method that has the potential to be an indicator of battery health and performance. Rechargeable batteries exhibit complex mechano-electrochemical behaviors during operation, such as electrode expansion/contraction, phase transition, gas evolution, film formation, and crack propagation. These events emit transient elastic waves, which may be detected by a piezoelectric-based sensor attached to the battery cell casing. Research in this field is active and new findings are generated continuously, highlighting its potential and importance of further research and development. This Review provides a comprehensive analysis of AE sensing in rechargeable batteries, aiming to describe the underlying mechanisms and potential applications in battery monitoring and diagnostics. This Review summarizes recent progress and discusses future perspectives in applying online acoustic emission sensing as a non-destructive method for monitoring rechargeable batteries.

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.

This work considers the problem of selecting residuals for consistency-based diagnosis of multimode systems. The system operation mode is assumed to be given by a set of known discrete variables. The number of operation modes grows exponentially with the number of binary variables, thus methods enumerating the modes are not feasible. Here a method is proposed to select a small subset of residuals for diagnosing multimode systems. The selection is based on the fault signature of the residuals for the different modes of operation. To avoid the exponential growth of the number of modes, the multimode fault signature matrix is used to compute the diagnosability of the residuals. The approach is inspired and exemplified by a dynamically configurable battery pack. The result is a small set of residuals with the maximum diagnosability in all operation modes.

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.

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.