Multiple fault diagnosis using mathematical models

Aiming at solving the multiple fault diagnosis problem as well as the sequence of all the potential multiple faults simultaneously, a new multiple fault diagnosis method based on the dependency model method as well as the knowledge in test results and the prior probability of each fault type is proposed. Firstly, the dependency model of the system can be built and used to formulate the fault-test dependency matrix. Then, the dependency matrix is simplified according to the knowledge in the test results of the system. After that, the logic ‘OR’ operation is performed on the feature vectors of the fault status in the simplified dependency matrix to formulate the multiple fault dependency matrix. Finally, fault diagnosis is based on the multiple fault dependency matrix and the ranking of each fault type calculated basing on the prior probability of each fault status. An illustrative numerical example and a case study are presented to verify the effectiveness and superiority of the proposed method.

Fault diagnosis of rotating machines is an important task to prevent machinery downtime, and provide verifiable support for condition-based maintenance (CBM) decision-making. Deep learning-enabled fault diagnosis operations have become increasingly popular because features are extracted and selected automatically. However, it is challenging for these models to give superior results with rotating machine components of different scales, single and multiple faults across different rotating components, diverse operating speeds, and diverse load conditions. To address these challenges, this paper proposes a comprehensive learning approach with optimized signal processing transforms for single as well as multiple faults diagnosis across dissimilar rotating machine components: gearbox, bearing, and shaft. The optimized bicoherence, spectral kurtosis and cyclic spectral coherence feature spaces, and deep blending ensemble learning are explored for multiple faults diagnosis of these components. The performance analysis of the proposed approach has been demonstrated through a single joint training of the entire framework on a compound dataset containing multiple faults derived from three public repositories. A comparison with the state-of-the-art approaches that used these datasets, shows that our method gives improved results with different components and faults with nominal retraining.

A formal specification for analysing and implementing multiple fault diagnosis software is proposed in this paper. The specification computes all potential fault sources that correspond to a set of triggered alarms for a safety-related system, or part of a system. The detection of faults occurring in a safety-related system is a fundamental function that needs to be addressed efficiently. Safety monitors for fault diagnosis have been extensively studied in areas such as aircraft systems and chemical industries. With the introduction of intelligent sensors, diagnosis results are made available to monitoring systems and operators. For complex systems composed of thousands of components and sensors, the diagnosis of multiple faults and the computational burden of processing test results are substantial. This paper addresses the multiple fault diagnosis problem for zero-time propagation using a fault propagation graph. Components represented as nodes in a fault propagation graph are allocated with alarms. When faults occur and are propagated some of these alarms are triggered. The allocation of alarms to nodes is based on a severity analysis performed using a form of failure mode and effect analysis on components in the system.

Improving Multiple Fault Diagnosability using Possible Conflicts

In a chiller plant, primary or critical sensors are used to control the system operation while secondary sensors are installed to monitor the performance/health of individual equipment. Current sensor fault detection and diagnosis (SFDD) approaches are not applicable to secondary sensors which usually are not involved in the system control. Consequently, a hybrid multiple sensor fault detection, diagnosis and reconstruction (HMSFDDR) algorithm for chiller plants was developed. Machine learning and pattern recognition were used to predict the primary sensor faults through the comparison of the weekly performance curves. With the primary sensor signals reconstructed, the secondary sensor faults were estimated based on mass and energy balance. By applying the algorithm with various logged plant data and comparison with site checking results, a maximum of 75% effectiveness could be achieved. The merits of the present approach were further justified through off-site sensor testing which reinforced the usefulness of proposed HMSFDDR algorithm.

Multiple faults are easily confused with single faults. In order to identify multiple faults more accurately, a highly efficient learning method is proposed based on a double parallel two-hidden-layer extreme learning machine, called DPT-ELM. The DPT-ELM method is a variant of an extreme learning machine (ELM). There are some issues with ELM. First, achieving a high accuracy requires too many hidden nodes; second, the direct connection between the input layer and the output layer is ignored. Accordingly, to deal with the above-mentioned problems, DPT-ELM extends the single-hidden-layer ELM to a two-hidden-layer ELM, which can achieve a desired performance with fewer hidden nodes. In addition, a direct connection is built between the input layer and the output layer. Since the input layer weights and the thresholds of the two hidden layers are determined randomly, this simplifies the improved model and shortens the calculation time. Additionally, to improve the signal to noise ratio (SNR), an adaptive waveform decomposition (AWD) algorithm is used to denoise the vibration signal. Then, the denoised signal is used to extract the eigenvalues by the time-domain and frequency-domain methods. Finally, the eigenvalues are input to the DPT-ELM classifier. In this paper, two groups of rolling bearing data at different speeds, which were collected from a real experimental platform, are used to test the method. Each set of data includes three single fault states, two complex fault states and a healthy state. The experimental results demonstrate that the DPT-ELM method achieves fast learning speed and a high accuracy. Moreover, based on 10-fold cross-validation, it proves to be an effective method to improve the accuracy with fewer hidden nodes.

This paper addresses the problems of diagnosing multiple faults occuring in the non-boundary-scan parts of a printed circuit board. The paper details a diagnostic algorithm based upon combining the fault signatures of single faults in order to produce a pattern which best matches the signature of a multiple fault. In addition, a graphical routine is presented which allows the tester to analyze a given set of test vectors. This analysis provides an implicit fault-simulation process for stuck-at and bridging faults. Furthermore, the process informs the tester of any faults which mask other previously detectable faults within the given test set. >

This paper deals with multiple soft fault diagnosis of nonlinear analog circuits and offers a method that allows locating the faulty parameters and evaluating their values. The method works with a system of nonlinear algebraic test equations, which are not given in explicit analytical form, and actually may possess multiple solutions. The solutions are specified by one or several sets of the diagnostic parameter values that meet the test. To find the multiple solutions, an extended systematic search method has been developed. The diagnostic algorithm proposed in this paper exploits this method and brings a new concept for finding the actual solution. As a result, the diagnostic process is considerably improved. It can be applied to bipolar junction transistor and CMOS circuits manufactured in micrometer and nanometer technologies. In the last case, however, the transistors are characterized by intricate models (PSP 103 or BSIM 4). In consequence, the CPU time increases due to very complex sensitivity analyses of the circuits required by the diagnostic method. In such a case, the proposed approach is useful at the preproduction stage, where the CPU time is offline and not crucial. For illustration, two numerical examples are given.

With the development of the processing capacity of the embedded chip, it is possible to implement a machine learning algorithm in the embedded system. To achieve the fault status without poor portability, tricky threshold selection, and complex rulemaking, this article proposes a multimodal deep residual filter network (DRFN) for online multiple open-switch fault diagnosis of T-type three-level inverters. It contains low-rank matrix fusion (LMF), a DRFN, and a cross-transformer mechanism. The LMF fuses the voltage signal and the current signal for obtaining the unified representation. Then, the DRFN filters noise adaptively and extracts information effectively. Finally, the cross-transformer mechanism outputs the fault state of the T-type three-level inverter. The datasets consist of the dc-link voltage and load side current of the inverter control system. The data time window is selected as 20 ms. Through the real-time calculation of online monitored data, the experimental results show the effectiveness of the proposed fault diagnosis approach. Moreover, the accuracy of fault diagnosis is 99.18%, and the average open-circuit fault diagnosis time is 21 ms.

In this paper we present a new approach to multiple fault diagnosis in combinational circuits based on an effect-cause analysis. The main vehicle of our approach is the deduction of internal line values in a circuit under test N*. The knowledge of these values allows us to identify fault situations in N* (causes) which are compatible with the applied test and the obtained response (the effect). A fault situation specifies faulty as well as fault-free lines. Other applications include identifying the existence of nonstuck faults in N* and determination of faults not detected by a given test, including redundant faults. The latter application allows for the generation of tests for multiple faults without performing fault enumeration.

Multiple fault diagnosis is a challenging problem, especially for complex high-risk systems such as nuclear power plants. Multilevel Flow Models (MFM) is a powerful tool for identifying functional failures of complex process systems composing of mass, energy and information flows. The method of fault diagnosis based on MFM is generally based on the assumption that only a single fault occurs, and based on this, the Depth First Search (DFS) is adopted to identify the abnormal functions at the lower level of an MFM. This paper presents a method based on Multilevel Flow Models (MFM) for diagnosing multiple functionally related and coupled faults. An MFM model is firstly transformed into a reasoning Causal Dependency Graph (CDG) model according to a group of alarm events. The CDG model is further decoupled to generate causal trees by a DFS algorithm, each of which represents an overall explanation of a cause of alarm events. The paper presents a comparative analysis of cases. It proves that the method proposed in the paper can give more comprehensive diagnostic results than the existing method.

A method for diagnosis of multiple incipient faults on a 2-pole synchronous generator is presented. Simulation of the generator on a finite element analysis (FEA) software package is used to predict the effects of these faults. Experimental analysis of the generator under fault conditions is then conducted and confirms the predicted behaviour. The investigation utilises shaft brushes as a non-invasive condition monitoring tool and search coils are used to validate findings from the shaft signal analysis. Results of the investigation indicate definitive relationships between the faults and specific harmonics of the output signals from the condition monitoring tools.

Deep model integrated with data correlation analysis for multiple intermittent faults diagnosis

In this paper, a new approach to alarm processing in power systems is proposed based on the set covering theory and a refined genetic algorithm (RGA). Although alarm processing and fault diagnosis have different explanations in power system community, from the viewpoint of artificial intelligence community, the alarm processing problem is a typical Multiple Fault Diagnosis (MFD) problem. Thus, we first attribute the alarm processing problem to a MFD problem, and discuss the MFD problem in general with special emphasis on the evaluation criteria. And then, a probabilistic criterion is introduced to describe the alarm processing problem, and this criterion is more reasonable man the currently used criteria. Thirdly, a new method is presented to solve the alarm processing problem using a RAG. Finally, two sample examples are used to demonstrate the feasibility and efficiency of the developed method. Test results suggest that the developed RAG-based probabilistic method to the alarm processing problem is promising.

Graph-based systems are models wherein the nodes represent the components and the edges represent the fault propagation between the components. For critical systems, some components are equipped with smart sensors for on-board system health management. When an abnormal situation occurs, alarms will be triggered from these sensors. This paper considers the problem of identifying the set of potential failure sources from the set of ringing alarms in graph-based systems. However, the computational complexity of solving the optimal multiple fault diagnosis (MFD) problem is exponential. Based on Lagrangian relaxation and subgradient optimization, we present a heuristic algorithm to find approximately the most likely candidate fault set. A computationally cheaper heuristic algorithm - primal heuristic - has also been applied to the problem so that real-time MFD in systems with several thousand failure sources becomes feasible in a fraction of a second. This paper also considers systems with asymmetric and multivalued alarms (tests).