Knowledge-based Fault Diagnosis Research Articles

A knowledge-based fault diagnosis method for rolling bearings without fault sample training

A knowledge-based fault diagnosis method for rolling bearings without fault sample training

Development and demonstration of a method to detect refrigerant charge level for variable refrigerant volume systems

Unlike traditional direct expansion systems, variable refrigerant flow (VRF) systems have longer routing, more complicated setup, and sophisticated controls and require much more refrigerant for proper operation. Proper refrigerant charge becomes more critical to their operations. Intensive studies have investigated refrigerant charge faults for VRF systems. Due to the daunting complexity, few studies use knowledge-based fault detection and diagnosis (FDD) methods. Most of them use data-driven FDD methods to study this fault. Although they seem promising, these methods can only handle single faults and are not scalable or interpretable. This paper proposes a decoupling-based FDD method to detect and diagnose improper refrigerant charge in VRF systems. This method was originally proposed by our previous work for rooftop units (RTUs) and split systems, which has been tested and validated by extensive studies. Due to the differences between VRF and RTU, the original method – virtual refrigerant charge sensor (VRC) for VRF is modified, analyzed, and investigated in detail. Data filter criteria were implemented to eliminate noisy data. The modified VRC, when combined with a data filter, was tested on two systems in the field. The results demonstrated its effectiveness in detecting an undercharged system, specifically a 30 % undercharge.

Knowledge-Based Fault Diagnosis in Industrial Internet of Things: A Survey

Industrial Internet of Things (IIoT) systems connect a plethora of smart devices, such as sensors, actuators, and controllers, to enable efficient industrial productions in manners observable and controllable by human beings. Plain model-based and data-driven diagnosis approaches can be used for fault detection and isolation of specific IIoT components. However, the physical models, signal patterns, and machine learning algorithms need to be carefully designed to describe system faults. Besides, the ever-increasing level of connectivity among devices can induce exponential complexity. Knowledge-based fault diagnosis approaches improve interoperability via ontologies so that high-level reasoning and inquiry response can be provided to nonexpert users. Therefore, knowledge-based fault diagnosis approaches are preferred over plain model-based and data-driven diagnosis approaches in recent IIoT systems. In the context of IIoT systems, this work reviews the recent progress on the construction of knowledge bases via ontologies and deductive/inductive reasoning for knowledge-based fault diagnosis. Besides, general inductive reasoning methods are discussed to shed light on their successful applications in knowledge-based fault diagnosis for IIoT systems. Following the trend of large-system decentralization, future fault diagnosis also requires decentralized implementations. Therefore, we conclude this survey by discussing several interesting open problems for decentralized knowledge-based fault diagnosis for IIoT systems.

Development of a Framework to Aid the Transition from Reactive to Proactive Maintenance Approaches to Enable Energy Reduction

The disparity between public datasets and real industrial datasets is limiting the practical application of advanced data analysis. Therefore, industry is stuck in a reactive mode regarding their maintenance strategy and cannot transition to cost-effective and energy-efficient proactive maintenance approaches. In this paper, an integration-type adaptation of the CRISP-DM data mining process model is proposed to combine domain expertise with data science techniques to address the pervasive data issues in industrial datasets. The development of the Industrial Data Analysis Improvement Cycle (IDAIC) framework led to the novel repurposing of knowledge-based fault detection and diagnosis (FDD) techniques for data quality assessment. Through interdisciplinary collaboration, the proposed framework facilitates a transition from reactive to proactive problem solving by firstly resolving known faults and data issues using domain expertise, and secondly exploring unknown or novel faults using data analysis.

A wind turbine frequent principal fault detection and localization approach with imbalanced data using an improved synthetic oversampling technique

Frequent principal fault detection and localization (FPFDL), as a new problem of fault diagnosis of the wind turbine system in practice, has gained a growing concern in wind power industries. The knowledge-based fault diagnosis method with historical wind buffer data is a feasible way to solve this problem. However, due to the uncertainty of the principal fault and the incompletion of the practical data, the wind buffer data used is imbalanced, inadequate, and unfixed-length, which leads to higher misclassification rates for the minority classes by traditional machine learning methods. To overcome these challenges, a novel FPFDL approach is proposed in this paper. Firstly, we design an improved oversampling algorithm to generate and develop the balanced dataset based on the imbalanced dataset of unfixed-length. This algorithm combines the dependent wild bootstrap oversampling and the modified synthetic minority oversampling technique. So, it can consider the temporal dependence and the relationship between the samples during data oversampling. Secondly, we introduce the one-dimensional convolutional neural networks to achieve automatic high-level local feature extraction and fault identification. Finally, the experimental results of seven cases using the datasets collected from two real wind farms in China validate our proposed approach’s effectiveness and robustness with imbalanced wind buffer data of unfixed-length.

A self-learning and self-optimizing framework for the fault diagnosis knowledge base in a workshop

Abstract The knowledge base is an essential part of the fault diagnosis system, which is crucial to the performance of fault recognition. As the intelligence of the fault diagnosis system has made persistent advance, the increasing demands for diversity and dynamic update have posed challenges to the knowledge base. In this paper, a framework for the fault diagnosis knowledge base is proposed to address the challenges mentioned above. Firstly, a dynamic clustering model is designed using the proposed semi-supervised multi-spatial manifold clustering method to recognize attribute clusters and aggregate new types. When new types are added to this model, it is constantly updated to achieve the automatic evolution of the knowledge base for the diversity of fault. Then, a knowledge evolution model is established by the generative adversarial network algorithm to achieve self-learning and self-optimizing capabilities of the knowledge base. This method learns the distribution of knowledge elements and generates new knowledge elements to optimize the clustering model. Finally, a series of comparative experiments are carried out on bearing datasets to verify the validity of the mentioned framework and models. The comparison results indicate that the proposed method has better performance in fault diagnosis. This research can not only update the knowledge base, but also provide a feasible approach for designing an autonomous knowledge base with self-optimizing and self-learning capabilities.

Coal mill fault diagnosis based on Gaussian process regression

A typical operating set of equipment can be obtained through cluster analysis of historical data. Two state monitoring models for HP medium speed coal mill are established based on Gaussian process regression and the similarity index calculated by this model can be used for measuring the operating status of HP mills. Finally a method for fault diagnosis of HP mill based on Gaussian regression modelling is proposed combined with fault diagnosis knowledge base of this HP mill. Taking the HP medium speed mill of a 660MW thermal power unit as an example, the real operating data is collected and used for modelling and analysis. Results shows that the equipment parameter estimation calculated by Gaussian process regression is accurate. It can be used for early-warning and diagnosed of equipment fault and also for practical engineering application.

Application of Fault Diagnosis Expert System for Unmanned Vehicle Safety

In order to ensure the safety of the underwater unmanned vehicle (UUV) and reduce the risk of damage or loss during operation, the safety system will be equipped on the UUV. It can accurately locate the fault when the submersible encounters dangerous situations, such as equipment failure and cabin flooding, assess the dangerous situation and make emergency measures, so as to help the underwater unmanned submersible realize self-rescue. Fault diagnosis expert system is a knowledge-based fault diagnosis method, which is suitable for complex systems with incomplete knowledge. However, because the working environment of the underwater unmanned underwater vehicle is very complex and the fault types are diverse and change in real time, the traditional fault diagnosis expert system may not meet the response time requirements of the safety system due to the long response time required. Therefore, the finite state machine technology is applied to the diagnostic expert system to improve the response speed of the diagnostic expert system, and at the same time make the system more flexible and convenient to expand its functions. In addition, the model-based design method was applied to establish the model of the security system in stateflow, and the model verification was carried out. With the help of PLC Coder tool, the code of the target controller was generated and the algorithm was deployed.

Fault Diagnosis of Planetary Gear Carrier Packs: A Class Imbalance and Multiclass Classification Problem

Fault diagnosis plays a key role in monitoring manufactured products for the purpose of quality control. Among the several fault diagnosis approaches, knowledge-based fault diagnosis, which uses signals from sensors and machine learning algorithms instead of a priori information, is widely employed to diagnose the status of products. In this paper, we propose a knowledge-based procedure to establish a fault diagnosis model. The model is aimed to diagnose planetary gear carrier packs, which have many fault types and an unbalanced number of samples in the sample classes, using transmission error. In the procedure, the best feature subset that contains the most important features is selected using two different feature selection processes. Several ensemble algorithms are used during the model training process. The imbalance ratio between classes of samples is addressed. The number of weak learners is automatically determined by a genetic algorithm. Finally, the performance of the proposed procedure is validated by comparison with other models trained without applying the proposed procedure. We observed that it is important to incorporate the class imbalance technique in the training process as it reduces the misclassification of faulty products as normal ones. This reduction is important in production quality control.

The Inference System for Fault Diagnosis

A knowledge-based fault diagnosis system uses prior knowledge and context knowledge for prediction to improve fault diagnosis performance. The proposed representative fault diagnosis system consists of three levels. With this structure, fault diagnosis can be flexibly performed even in a complicated environment. The three-level consists of the fault diagnosis level, the learning level, and the information processing level. The Fault diagnosis level is able to express the correlation by using the data obtained from the controller and diagnose the fault by logically inferring it. The learning level links the logical language perceived by humans and the numerical data processed by the computer, and keeps it consistent with the situation. The information processing level acquires the feature value required by the higher level in the candidate region among the numerous data obtained from the controller and sends it to the higher level. The proposed algorithm can effectively diagnosis faults by using additional prior knowledge and situation data.

Bayesian and Dempster–Shafer reasoning for knowledge-based fault diagnosis–A comparative study

Even though various frameworks exist for reasoning under uncertainty, a realistic fault diagnosis task does not fit into any of them in a straightforward way. For each framework, only part of the available data and knowledge is in the desired format. Moreover, additional criteria, like clarity of inference and computational efficiency, require trade-offs to be made. Finally, fault diagnosis is usually just a subpart of a larger process, e.g. condition-based maintenance. Consequently, the final goal of fault diagnosis is not (just) decision making, and the outcome of the diagnosis process should be a suitable input for the subsequent reasoning process. In this paper, we analyze how a knowledge-based diagnosis task is influenced by uncertainty, investigate which additional objectives are of relevance, and compare how these characteristics and objectives are handled in two well-known frameworks, namely the Bayesian and the Dempster-Shafer reasoning framework. In contrast to previous works, which take the reasoning method as the starting point, we start from the application, knowledge-based fault diagnosis, and examine the effectiveness of different reasoning methods for this specific application. It is concluded that the suitability of each reasoning method highly depends on the problem under consideration and on the requirements of the user. The best framework can only be assigned given that the problem (including uncertainty characteristics) and the user requirements are completely known.

Reasoning under Uncertainty for Knowledge-Based Fault Diagnosis: A Comparative Study

This paper addresses reasoning under uncertainty for knowledge-based fault diagnosis. We illustrate how the fault diagnosis task is influenced by uncertainty. Furthermore, we compare how the diagnosis task is solved in the Bayesian and the Dempster-Shafer reasoning framework, in terms of both diagnostic performance and additional objectives, like transparency, adaptability, and computational efficiency. Since the diagnosis problem is influenced by different kinds of uncertainty, it is not straightforward to determine the optimal reasoning method. First, the different uncertain influences all have their own characteristics, asking for different reasoning approaches. So, to solve the whole problem in one reasoning framework, approximations and trade-offs need to be made. Second, which types of uncertainty are present and to what extent, is highly application-specific. Therefore, the best framework can only be assigned after the problem, the uncertainty characteristics, and the user requirements are known.

Wavelet Analysis of Fault Diagnosis Technology

In recent years, the development of computer technology, signal processing, artificial intelligence, pattern recognition technology; and promote the continuous development of fault diagnosis technology, especially knowledge-based fault diagnosis method has been widely studied. Which, along with the increasingly improved neural network technology, the fault diagnosis method based on neural network has been widespread concern. Since one of the main steps of fault diagnosis is signal processing, while wavelet analysis is an effective tool to process signals and wavelet function has many good characteristics, so the combination of wavelet and neural network, so called wavelet neural network, has become a focus in fault diagnosis field recently.

Application Research of the Pro/3 Inference Information Report and Transformer Fault Diagnosis Based on Forward Reasoning

The paper work had improved some inference information report show functions of the expert system shell Pro/3 by using graph in combination with text . By analyzing some forward reasoning application mechanisms of the Pro/3, this work had also created a transformer fault diagnosis knowledge base rule model based on dissolved gas analysis in transformers such that using the rules of sentence in model had implemented an expert system of transformer fault diagnosis. The basic application shows the effectiveness of the system.The modeling approach created by the Pro/3 can be also applied to some diagnosis or analysis of other equipments. Exploring the Pro/3 has certain practical significance for establishing some expert systems or assistance decision support systems.

Design and Implementation of Power Grid Dispatching Fault Diagnosis Knowledge Base

The paper designs the urban-rural power grid dispatching fault diagnosis expert system which acquires fault information by SCADA system of automatic system of urban-rural power grid, and uses artificial intellegence method to analyze fault information and make fault diagnosis. The paper implements the core part of the fault expert system—the design of knowledge base and fault inference engine.

Research on Key Technology of Knowledge-Based Intelligent Fault Diagnosis of Hydraulic System

A general framework of hydraulic fault diagnosis system was studied. It consisted of equipment knowledge bases, databases, fusion reasoning, knowledge acquisition and so on. The tree-structure model of the fault knowledge was established based on fault hierarchy and logicality. Fault nodes knowledge was encapsulated by object-oriented technique. Complete knowledge bases were made including fault bases and diagnosis bases. It could describe the fault positions, system structure, cause-symptom relationships, diagnosis principles and other knowledge. The results show that the methods are effective.

The Research and Development of Mine Main Fan’s On-Line Fault Diagnosis Expert System

In order to diagnose mine fan fault timely, to enhance and improve the level of safety of coal mining enterprises, construct fuzzy expert system based on multiple symptom. The system presents a inference model based on rules and cases, establish fault diagnosis knowledge base of the rules and cases.Using pros and cons mixed reasoning strategy, according to the fault symptom obtained from man-machine conversation, dialogue diagnosis was carried out on the equipment fault.Use the calculation of symptom and rules confidence to produce fault result confidence to screen and order the faults,and export supporting information such as the diagnostic process explanation and maintenance plan and so on,which is convenient for users to understand and carry out various processing.

Application of advanced fault diagnosis technology in electric locomotives

As the continuous development of intelligent mechatronic systems and robots, the fault diagnosis technology is making full advances in many practical applications. In this paper, an advanced fault diagnosis system, which consists of logical control units, microcontrollers, colour display screens and an industry PC, is developed for SS7E locomotives in China. Based on thoroughly analysing the structures and control principles, a full set of digital checkpoints and fault points of SS7E are presented. The method to obtain diagnosis rules from the fault tree is described and the high-efficiency reasoning mechanism is deduced. The intelligent fault diagnosis knowledge base of SS7E is constructed and the data structure is explained. Finally, an online instance of the SS7E locomotive fault diagnosis system interface is shown.

Real-time fault diagnosis using knowledge-based expert system

Abnormal operating conditions (faults) cost process industry billons of dollars per year and can be prevented if they are predicted and controlled in advance. Advanced software applications, based on the expert system, has the potential to assist engineers in monitoring, detecting, and diagnosing abnormal conditions and thus providing safe guards against these unexpected process conditions. Abnormal operating conditions (faults) could be modeled and predicted with high confidence using software applications. A wide range of fault diagnosis methods exist which may be used to design safety systems. Due to the increased process complexity and possible instability in the operating conditions, the existing control systems have limited ability to provide practical assistance to both operators and engineers. This paper proposes a knowledge-based fault diagnosis method, which uses the valuable knowledge from the experts and operators, as well as real-time data from a variety of sensors. Fuzzy logic is also used to make inferences based on the acquired information (real-time data) and the knowledge. A computer-aided tool based on proposed methodology is developed on the platform of G2 expert shell using GDA ( G2 Diagnostic Assistant) components. Performance of the methodology is verified using both industrial and simulated data.

An integration mechanism for multivariate knowledge-based fault diagnosis

A design of a multivariate knowledge-based fault diagnosis system is described in this paper. The proposed design is based on a novel strategy, which integrates multivariate statistical process control (MSPC) monitoring into knowledge-based (KB) fault diagnosis both qualitatively and quantitatively using expert system technology. The integration mechanism mimics how process engineers combine their process knowledge with Principal Component (PC) score contribution, PC score deviation contribution and square predicted error (SPE) contribution of principal component analysis (PCA) projection in diagnosing anomaly. The system has been successfully implemented in G2 environment. A dynamic simulation of a continuous stirred tank reactor (CSTR) running a second order exothermic reaction was used to test the proposed system. Testing results clearly indicated that the system produces more contrasting probabilities between all possible exogenous causes and it can give accurate diagnosis when the process upsets were undetected by univariate monitoring.