Fault diagnosis support system for complex chemical plants

This work approaches relative aspects to the alarm processing problem and fault diagnosis in system level, having as purpose filter the alarms generated during a outage and identify the equipment under fault. A methodology was developed using Artificial Neural Networks (ANN) and Genetic Algorithms (GA) in order to resolve the problem. This procedure had as initiative explore the GA capacity to deal with combinatory problems, as well as the ANN processing speed and generalization capacity. Such strategy favors a fast and robust solution.

Fault Detection and Diagnosis (FDD) in complex industrial systems requires methods that can handle uncertain operating conditions, soft thresholds, evolving sensor behavior, and increasing volumes of heterogeneous data. Traditional model-based or rule-driven approaches offer interpretability but lack adaptability, while purely data-driven and Large Language Model (LLM)-based methods often struggle with consistency, traceability, and causal grounding. Dynamic Master Logic (DML) provides a causal and temporal reasoning structure with fuzzy rules that capture gradual drift, soft limits, and asynchronous sensor signals while preserving traceability and deterministic evidence propagation. Building on this foundation, this paper presents a DML-LLM hybrid architecture that integrates targeted LLM inference to interpret unstructured information such as logs, notes, or retrieved documents under controlled prompts that maintain domain constraints. The combined system integrates Bayesian updating, deterministic routing, and semantic interpretation into a unified FDD pipeline. In a semiconductor manufacturing case study, the proposed framework reduced time to detection (TTD) from 7.4 h to 1.2 h and improved the F1 score from 0.59 to 0.83 when compared with conventional Statistical Process Control (SPC) and Fault Detection and Classification (FDC) workflows. Provenance completeness increased from 18% to 96%, while engineer triage time was reduced from 72 min to 18 min per event. These results demonstrate that the hybrid framework provides a scalable and explainable approach to anomaly detection and fault diagnosis in sensor-rich industrial environments.

The traditional fault diagnosis expert system is dependent on knowledge acquisition of the experts. Knowledge acquisition is recognized as the problem of expert system. In addition, there are also some limitations of adaptive capacity, learning ability and real-time. And artificial neural network with good fault-tolerance and associative memory function, as well as very strong self-adaptive, self-learning ability, just can make up for the limitations of traditional expert system. This paper will construct a new expert system with the artificial neural network into and fault tree. Besides fault tree and neural network, this article mainly introduces the system model of fault diagnosis of the fire control computer and sensor subsystem, the method and process of fault diagnosis. In this expert system, we use the object-oriented production rule to represent the knowledge, which solves the bottleneck problem of the diagnostic knowledge acquisition effectively. The inferential process begins with the abnormal event and finally finds all of the possible faults and the faulty component. For some possible faulty components, which have large number of fault samples, the neural network model can be used to diagnose. The training network of fault samples employs the BP neural network. Finally, simulation training results show that the fault diagnosis expert system based on the combination of fault tree and neural network is rational and effective in fault diagnosis of the fire control system, realizes perfectly the combination of new knowledge and old one, and can grasp the state of systems dynamically.

The electrical system fault testing and diagnosis system based on I2C-bus and embedded equipment is proposed. This system is accomplished with the integration of PXI-based computer, field fault testing platform, dedicated interface adapter unit and accessories with software program of virtual instrument and database management and fault guidance system. It can obtain various state parameters of the heavy mechanized bridge by interface adapter unit and corresponding sensors. The dedicated interface adapter unit, that is the core of the hardware platform is composed of chassis, embedded microcomputer controller, I2C-bus data acquisition modules, VPC connection package and military aviation sockets. Because of its flexibility and modular design, it can support different data conversion, for example, analog, digital, and serial, while functioning as an intelligent conversion bridge between field fault testing platform or PXI computer and electrical system of heavy mechanized bridge electrical system. The fault diagnosis software is of hierarchical modular structure with integration of system management control, fault detection and circuit hardware driver modules together with fault repair and diagnosis database. Therefore it provides functions of human-machine interaction, equipment fault detection, fault diagnosis and analysis, as well as repair and maintenance guidance The fault testing and diagnosis system in this work is also featured with handy structure, lightweight, low consumption, large storage capacity, excellent expandability and intelligent inference capability. The system can be used in the online fault testing and diagnosis of similar engineering equipments. So it has important engineering and military application value to the rapid fault testing and fault diagnosis of engineering equipments.

As rotating machines play an important role in industrial applications such as aeronautical, naval and automotive industries, many researchers have developed various condition monitoring system and fault diagnosis system by applying various techniques such as signal processing and pattern recognition. Recently, fault diagnosis systems using artificial neural network have been proposed. For effective fault diagnosis, this paper used MLP(multi-layer perceptron) network which is widely used in pattern classification. Since using obtained signals without preprocessing as inputs of neural network can decrease performance of fault classification, it is very important to extract significant features of captured signals and to apply suitable features into diagnosis system according to the kinds of obtained signals. Therefore, this paper proposes the decision method of the proper feature vectors about each fault signal for neural-network-based fault diagnosis system. We applied LPC coefficients, maximum magnitudes of each spectral section in FFT and RMS(root mean square) and variance of wavelet coefficients as feature vectors and selected appropriate feature vectors as comparing error ratios of fault diagnosis for sound, vibration and current fault signals. From experiment results, LPC coefficients and maximum magnitudes of each spectral section showed 100 % diagnosis ratios for each fault and the method using wavelet coefficients had noise-robust characteristic.

Fault Detection and Diagnosis for Nonlinear Systems: A Support Vector Machine Approach

The paper introduces the modeling method and modeling tool for the fault diagnosis of manned spacecraft, the multi-signal flow graph model of a manned space equipment was established using this method; the framework of the fault detection and diagnosis system of manned spacecraft is proposed, the function of ground system and function of the spacecraft are clearly defined. The structure of the functional module is given separately; finally, the tool builds the fault detection and diagnosis system, the application of fault diagnosis method for manned spacecraft is used for reference.

A stylized trend analysis was developed to identify recurring or standard operating procedures (SOP) such as equipment switching or maintenance from plant process history data to detect faults and near misses due to operator errors or equipment failures. Trend based fault detection and diagnosis systems have not been implemented widely in the chemical process industries because known fault scenarios are typically required. Known fault scenarios were not required for the stylized trend analysis because faults and near misses were identified by comparing trends with normal SOP transition responses. Large volumes of historical data were processed automatically allowing corrective action to be taken prior to an incident. The stylized trend analysis was demonstrated to detect unsteady‐state transition faults on historical distributed control system data simulated for a continuous process ethylene plant dryer switching operation. © 2017 American Institute of Chemical Engineers Process Process Saf Prog 37:411–418, 2018

Automated Fault Detection and Diagnosis (AFDD) systems are critical to safe and efficient operation of smart buildings. A significant amount of building data can be collected and analyzed to detect building compo-nent failures. Attacks against such data that are contami-nated with small additive disturbances (i.e., adversarial per-turbation attacks) could dreadfully impact the performance of such systems while maintaining a high level of imper-ceptibility. The vulnerability studies of such data attacks is lacking. Specifically, most existing detection and clas-sification models have flat structures, regarded as Single-Stage Classifiers (SSCs), are prone to adversarial data perturbation attacks. In this paper, we present a coarse-to-fine Hierarchical Fault Detection and multi-level Diagnosis (HFDD) model, and formulate a mathematical program to derive targeted attacks on the model with respect to a pre-specified target diagnosis level. Two algorithms are developed based on convex relaxations of the formulated program for non-targeted attacks. An Alternating Direction Method of Multipliers (ADMM)-based solver is developed for the convex programs. Extensive experiments are con-ducted using two real-world datasets of measurements from air handling units and chillers, demonstrating the fea-sibility of the proposed attacks with regard to misclassifi-cation rate and imperceptibility of the attack. We also show that the HFDD is more robust to disturbances than SSC-based fault detection and multi-level diagnosis systems.

A fault diagnosis system is developed by integrating principal component analysis (PCA) with fuzzy logic knowledge-based (FLKB) systems. A PCA model is created using normal state data. Then it is used to project normal and faulty data during the training stage. It evaluates the process variables values and their correlation, allowing fast and reliable fault detection. Once detection is performed, a FLKB system is used to evaluate the contributions of each variable to changes in the process, finding the root causes of the abnormal event detected. A simple methodology to automatically extract compact process information is presented. Then, an optimization algorithm is implemented to improve the isolation performance. The methodology is demonstrated in an academic case study and in the Tennessee Eastman process benchmark.

Long term exposure of photovoltaic (PV) systems under relatively harsh and changing environmental conditions can result in fault conditions developing during the operational lifetime. The present solution is for system operators to manually perform condition monitoring of the PV system. However, it is time-consuming, inaccurate and dangerous. Thus, automatic fault detection and diagnosis is a critical task to ensure the reliability and safety in PV systems. The current state-of-the-art techniques either cannot provide enough detailed fault information with high accuracy or have too much complexity. This work presents an automatic fault detection and diagnosis method for string based PV systems. It combines an artificial neural network (ANN) with the conventional analytical method to conduct the fault detection and diagnosis tasks. A two-layered ANN is applied to predict the expected power which is then compared with the measured power from the real PV system. Based on the difference between the ANN estimated power and the measured power, the open circuit voltage and short circuit current of the PV string determined using analytical equations are used to identify any of the six defined fault types. The proposed method has a fast detection, compact structure and good accuracy. Simulation results show the effective fault detection and diagnosis capability of the proposed method.

Fault is defined as degradation between 100% performance and complete failure. The authors demonstrate how an artificial neural network can detect and diagnose faults from online process data. A wide range of input patterns can be learned by artificial neural networks in the presence of noise by changing the interconnections of the nodes, their thresholds for activation, and their individual weights. Artificial neural networks are able to take inputs from the processes without knowing the process model, allowing representation of complex engineering systems which are difficult to model either with traditional model-based engineering or knowledge-based expert systems. A description is given of some of the characters of a neural network that are useful for fault discrimination in a chemical plant. It is shown that even when using noisy sensor data, the misclassification rate is nil

A fusion-based fault detection and diagnosis system is introduced for a multisensor system where the fault detection process is divided into three stages and the uncertainty-reductive-fusion technique is used to detect possible sensor failures. A fuzzy rule-based diagnosis is performed in order to analyze and to try to correct for the signaled faults.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Two neural network models are compared using a process fault detection and diagnosis problem. Process fault detection and diagnosis using steady-state information is a nonlinear pattern recognition problem. In such problems the measurement pattern vectors are noisy and collection of a complete training data set is time consuming and in some cases impossible. The training data were obtained from a simulated chemical process. The process consists of a reactor and a distillation column. The dynamically capacity allocating network models were found to have the best performance as compared to backpropagation-type network models. These networks can also be used for continuously learning systems and therefore the difficulties of training data collection are avoided. >

The technology of integrated health management (IHVM) is an important approach to improve the security, reliability and maintainability of airplanes and spacecrafts, and to reduce their cost significantly. Taken aircraft electric power system into consideration, it is one of the important equipment that provides electric energy for all electro-equipments in airplane. Its working state is a crucial to ensure airplane normal and secure flight, so the research of condition detection, fault diagnosis and prognosis is a great concern in the field of IHVM system. Aiming at interoperability and complexity of data exchanging for aircraft electric power diagnosis and prognostic system, a method of using ATML (automatic test markup language) based on XML (extensible markup language) is proposed in order to describe the information of devices and conditions for fault diagnosis and prognostic in the system. First, based on reference frame of integrated health management system, a distributed multi-level fault diagnosis and prognosis system structure that exchange data through ATML is designed. Secondly, condition monitor is a foundation of fault diagnosis and prognosis, and a schema of test information for aircraft electric power parameters is designed by using ATML after data of crucial fault is analyzed. The result shows that the method can implement seamless interaction among test, diagnosis and prognosis. At same time, sharing and transplant of test information and diagnostic knowledge is improved and the process of fault diagnosis is accelerated.