Enhance Equipment Reliability Research Articles

Research on maintenance decision-making approach based on dynamic opportunistic window

We have developed a maintenance decision-making approach based on the dynamic opportunistic window, utilizing algorithms such as k-mean clustering, expected maximum, and parameter estimation to address the lack of a reasonable basis for the duration and divided number of opportunistic windows in current maintenance decision-making. Firstly, we have comprehensively summarized the multi-stage opportunistic maintenance decision-making approach, focusing on its current strengths and limitations. Secondly, the modeling concept of the dynamic opportunistic window is analyzed, and the underlying assumptions are established. Furthermore, it elaborates on the theoretical foundation of the proposed approach through a detailed modeling process. Finally, we validate the proposed model by conducting experiments on tandem components from the main combustion chamber in an aero engine. The experimental results demonstrate the significant value of the proposed approach in enhancing equipment reliability and optimizing maintenance support resources.

Small data challenges for intelligent prognostics and health management: a review

Prognostics and health management (PHM) is critical for enhancing equipment reliability and reducing maintenance costs, and research on intelligent PHM has made significant progress driven by big data and deep learning techniques in recent years. However, complex working conditions and high-cost data collection inherent in real-world scenarios pose small-data challenges for the application of these methods. Given the urgent need for data-efficient PHM techniques in academia and industry, this paper aims to explore the fundamental concepts, ongoing research, and future trajectories of small data challenges in the PHM domain. This survey first elucidates the definition, causes, and impacts of small data on PHM tasks, and then analyzes the current mainstream approaches to solving small data problems, including data augmentation, transfer learning, and few-shot learning techniques, each of which has its advantages and disadvantages. In addition, this survey summarizes benchmark datasets and experimental paradigms to facilitate fair evaluations of diverse methodologies under small data conditions. Finally, some promising directions are pointed out to inspire future research.

Bearing fault detection by using graph autoencoder and ensemble learning

The research and application of bearing fault diagnosis techniques are crucial for enhancing equipment reliability, extending bearing lifespan, and reducing maintenance expenses. Nevertheless, most existing methods encounter challenges in discriminating between signals from machines operating under normal and faulty conditions, leading to unstable detection results. To tackle this issue, the present study proposes a novel approach for bearing fault detection based on graph neural networks and ensemble learning. Our key contribution is a novel stochasticity-based compositional method that transforms Euclidean-structured data into a graph format for processing by graph neural networks, with feature fusion and a newly proposed ensemble learning strategy for outlier detection specifically designed for bearing fault diagnosis. This approach marks a significant advancement in accurately identifying bearing faults, highlighting our study's pivotal role in enhancing diagnostic methodologies.

Proactive Fault Detection in Rotating Machinery using Machine Learning- A Survey

This study presents a survey of approaches for proactive fault detection in rotating machinery, with a focus on the early identification of bearing faults to enhance equipment reliability and operational efficiency. Traditional methods, relying on physical sensors and manual inspections, often lack the ability to provide timely insights into emerging faults. In contrast, the surveyed approaches integrate non-contact vibration sensors with advanced machine learning techniques, revolutionizing fault detection capabilities. The study presents a brief overview of the methods used in classification of the rotating machinery defects using the machine learning and recommends a combination of machine learning methods at different stages to overcome the challenges of the traditional methods. The collected vibration signals undergo noise reduction via the Hilbert transform, followed by dimensionality reduction and feature selection using Independent Component Analysis (ICA) and Genetic Algorithms (GA), respectively. The selected features are then employed for fault detection and categorization using Random Forest (RF) and Deep Belief Networks (DBN). The Future work will involve the implementation and evaluation of these approaches in real-world industrial settings to validate their effectiveness and reliability.

Enhancing Equipment Reliability and Reducing Maintenance Costs with MSET2: A Predictive Maintenance Approach Using IoT Sensor Data

Enhancing Equipment Reliability and Reducing Maintenance Costs with MSET2: A Predictive Maintenance Approach Using IoT Sensor Data

Advanced Data Analytics for Prognostics and Health Management (PHM) in Industrial Engineering: A Comprehensive Review

Prognostics and Health Management (PHM) is a crucial aspect of industrial engineering, aiming to enhance equipment reliability, reduce downtime, and optimize maintenance strategies. Advanced data analytics plays a pivotal role in PHM, enabling the analysis of equipment condition and performance to predict failures and prescribe proactive maintenance actions. This review article provides a comprehensive overview of advanced data analytics techniques used in PHM, including machine learning, statistical analysis, and predictive modeling. The article also discusses the application of these techniques in various industrial sectors, highlighting their benefits and challenges. Furthermore, the review identifies current trends and future directions in the field of PHM, emphasizing the importance of integrating advanced data analytics for improved industrial engineering practices.

Multi-source partial domain adaptation method based on pseudo-balanced target domain for fault diagnosis

Multisource domain adaptation (MSDA) for fault diagnosis enables knowledge transfer from multisource domains to unknown target domains, which is crucial for enhancing equipment reliability and safety. However, current MSDA methods face two major challenges: (1) they face serious domain-shift problems not only between the target and source domains, but also between different source domains, and (2) in practical applications, class labels in the target domain are likely to be subsets of class labels in the source domain. Therefore, this study considers a setting called multisource partial domain adaptation (MSPDA). A two-stage intelligent fault diagnosis method for MSPDA based on pseudo-balanced target domains (PBTD) is proposed. In the first stage, we propose a weighted adversarial partial domain adaptation method based on a dual progressive strategy that aligns each source domain with the target domain to construct a series of PBTD. In the second stage, an alternating learning scheme is utilized to align the remaining source domains with the PBTDs, which makes full use of multisource information to bridge the discrepancies between different domains. Additionally, this study proposes a multiscale convolutional neural network based on a three-branch attention mechanism that captures the cross-dimensional interactions of scale, channel, and space to enhance the algorithmic characterization capability. Finally, extensive experiments with gear and bearing datasets are conducted to validate the effectiveness of the proposed method.

Mechanisms underlying temperature uniformity in electrostatic chucks through experimental and simulation methods

Electrostatic chucks (ESCs) play a crucial role in securing and holding wafers during processing or testing in the semiconductor industry. ESCs are favored for their superior clamping performance, ensuring high-quality and consistent semiconductor products. Nevertheless, the temperature uniformity in ESCs is paramount to achieving these goals. In this study, the surface temperature distribution of a 12-inch four-zone ESC was investigated based on thermodynamics and hydromechanics theories. A numerical model has been constructed and validated via relevant experiments. Both results show that the surface temperature uniformity of the ESC can be improved by appropriately increasing the coolant flow rate. The impact of the distance from cooling channel to the pedestal and the height of cooling channel on the temperature uniformity of the ESC was studied particularly. The findings indicate that an extended distance yields a heightened surface temperature while simultaneously reducing temperature differences. Moreover, increasing the height leads to a reduction in ESC surface temperature but degradation in temperature uniformity. This work has the potential to significantly reduce experimental costs, enhance equipment reliability and provide valuable insights for investigating temperature uniformity mechanisms in ESCs, as well as for modeling and designing such systems.

Failure analysis and factors influencing spline wear in hydraulic motors of charging pumps in nuclear power plants

Metallographic analysis techniques such as optical microscopy and scanning electron microscopy were used to observe the morphology of spline wear, confirming the presence of fretting wear characteristics. Microstructural analysis of spline cross sections using a metallographic microscope revealed surface carburization treatment on the splines. Hardness tests conducted from the surface to the core of the splines showed a gradual decrease in hardness, consistent with the observed microstructural features. The chemical composition of the spline was analyzed using a spectrometer, and the main component content was analyzed.By combining finite element analysis techniques, this study analyzed the effects of factors such as forces, eccentricity, and lubrication on spline wear. The results indicated that the varying degrees of spline wear in the hydraulic motors of charging pumps in the on-site conditions of the nuclear power plant were primarily attributed to differences in spline eccentricity after manufacture and assembly. Further investigation revealed that the fundamental cause of spline wear in hydraulic motors was the operation of the equipment under conditions deviating from the rated operating points, resulting in poor circulation of oil within the motors and insufficient spline lubrication. Specifically, operating the equipment at lower pressures and away from the rated operating points resulted in reduced oil flow velocity, increasing the friction between the spline mating surfaces. The poor lubrication of the spline and eccentricity are the primary reasons for spline wear, and the combination of these two factors exacerbates spline wear. To address the wear issue of the hydraulic motor, we replaced it with a linear-axis hydraulic motor and conducted a comprehensive analysis of the linear-axis hydraulic motor. The results indicate that the linear-axis hydraulic motor can effectively reduce wear, and after testing at the nuclear power plant, it meets the operational time requirements on-site.These findings offer valuable guidance for the maintenance and operation of charging pumps in nuclear power plants, facilitating the prevention of similar issues and enhancing equipment reliability and operational efficiency.

Multiscale global and local self-attention-based network for remaining useful life prediction

Remaining useful life (RUL) prediction plays an important role in prognostics and health management (PHM) and can significantly enhance equipment reliability and safety in various engineering applications. Accurate RUL prediction enables proactive maintenance planning, helping prevent potential hazards and economic losses caused by equipment failures. Recently, while deep learning-based methods have swept the RUL prediction field, most existing methods still have difficulties in simultaneously extracting multiscale global and local degradation feature information from raw multi-sensor monitoring data. To address these issues, we propose a novel multiscale global and local self-attention-based network (MGLSN) for RUL prediction. MGLSN consists of global and local feature extraction subnetworks based on self-attention, which work in parallel to simultaneously extract the global and local degradation features of equipment and can adaptively focus on more important parts. While the global network captures long-term dependencies between time steps, the local network focuses on modeling local temporal dynamics. The design of parallel feature extraction can avoid the mutual influence of information from global and local aspects. Moreover, MGLSN adopts a multiscale feature extraction design (multiscale self-attention and convolution) to capture the global and local degradation patterns at different scales, which can be combined to better reflect the degradation trend. Experiments on the widely used Commercial Modular Aero-Propulsion System Simulation (CMAPSS), New CMAPSS (N-CMAPSS), and International Conference on Prognostics and Health Management 2008 challenge datasets provided by NASA show that MGLSN significantly outperforms state-of-the-art RUL prediction methods and has great application prospects in the field of PHM.

A Fault Warning Approach Using an Enhanced Sand Cat Swarm Optimization Algorithm and a Generalized Neural Network

With the continuous development and complexity of industrial systems, various types of industrial equipment and systems face increasing risks of failure during operation. Important to these systems is fault warning technology, which can timely detect anomalies before failures and take corresponding preventive measures, thereby reducing production interruptions and maintenance costs, improving production efficiency, and enhancing equipment reliability. Machine learning techniques have proven highly effective for fault detection in modern production processes. Among numerous machine learning algorithms, the generalized neural network stands out due to its simplicity, effectiveness, and applicability to various fault warning scenarios. However, the increasing complexity of systems and equipment presents significant challenges to the generalized neural network. In real-world scenarios, it suffers from drawbacks such as difficulties in determining parameters and getting trapped in local optima, which affect its ability to meet the requirements of high efficiency and accuracy. To overcome these issues, this paper proposes a fault warning method based on an enhanced sand cat swarm optimization algorithm combined with a generalized neural network. First, we develop an enhanced sand cat swarm optimization algorithm that incorporates an improved chaotic mapping initialization strategy, as well as Cauchy mutation and reverse elite strategies based on adaptive selection. Subsequently, we utilize this algorithm to optimize the generalized neural network and determine its optimal parameters, effectively improving the accuracy and reliability of system fault warnings. The proposed method is validated using actual industrial system data, specifically for generator fault warning, and is demonstrated to outperform other advanced fault warning techniques. This research provides valuable insights and promising directions for enhancing industrial fault warning capabilities.

A transformer-based approach for novel fault detection and fault classification/diagnosis in manufacturing: A rotary system application

Owing to the rapid development of Industry 4.0, new sensing and communication technologies have made vast amounts of untapped process data available. In order to transform such data assets into strong insights and knowledge that support manufacturing decisions, condition-based maintenance (CBM) and fault detection and diagnosis (FDD) have become effective ways to enhance equipment reliability and reduce costs. A successful data-driven FDD method must not only be capable of identifying the types of known faults, but also in detecting unseen or uncharacterized events during manufacturing system operation. To this end, this paper presents a Transformer-based classifier that can efficiently identify different known types and severity levels of fault conditions, in addition to novel fault detection. In this method, time-frequency spectrograms transformed from raw vibration signals are input to the classifier for known fault classification. Utilizing the advanced feature extracting performance of the classifier, a simple yet effective technique based on Mahalanobis distance is adopted to detect whether the fault comes from a previously unseen fault condition. When a novel condition is detected, the model is subsequently retrained using the novel data in an incremental learning manner. The proposed method is verified by an experimental case study with data collected from a testbed that has many features representative of common manufacturing equipment. The results demonstrated that the proposed method has superior performance in both fault diagnosis and novelty identification when compared with the baseline models and a cutting-edge model.

Condition-Based Monitoring and Novel Fault Detection Based on Incremental Learning Applied to Rotary Systems

Thanks to the development of new technologies such as sensor networks and advanced computational power, the research field of condition-based monitoring (CBM) has drawn increasing attention in manufacturing. With the aim of enhancing equipment reliability, leading to a reduction in maintenance costs, one of the most crucial challenges dealing with CBM is the detection or prediction of unseen/uncharacterized event during manufacturing system operation. Therefore, the identification of novel fault conditions and learning of new patterns are believed to be an important and mandatory thrust in CBM research. In this work, a convolutional neural networks and autoencoder (CNN-AE) based incremental learning method is presented. It applies CNN-AE to identify various types and severities of faults under scenarios of previously unseen fault conditions. In this method, the spectrograms generated from raw sensory signals are acquired and labelled along with working condition information via inspection. A model composed of two sub-models for novel fault identification is then constructed and trained using the time-frequency spectrograms of available conditions of operation from a rotary system. One sub-model based on CNN is for known fault classification and the other sub-model based on AE is for novelty detection, where the two sub-models share an architecture for improving efficiency and accuracy. Finally, incremental learning is performed to retrain the model with the data identified as a novel fault condition. The performance of this method is validated via an experimental case study conducted on a fault machinery simulator.

A big data driven sustainable manufacturing framework for condition-based maintenance prediction

Smart manufacturing refers to a future-state of manufacturing and it can lead to remarkable changes in all aspects of operations through minimizing energy and material usage while simultaneously maximizing sustainability enabling a futuristic more digitalized scenario of manufacturing. This research develops a big data analytics framework that optimizes the maintenance schedule through condition-based maintenance (CBM) optimization and also improves the prediction accuracy to quantify the remaining life prediction uncertainty. Through effective utilization of condition monitoring and prediction information, CBM would enhance equipment reliability leading to reduction in maintenance cost. The proposed framework uses a CBM optimization method that utilizes a new linguistic interval-valued fuzzy reasoning method for predicting the information. The proposed big data analytics framework in our study for estimating the uncertainty based on backward feature elimination and fuzzy unordered rule induction algorithm prediction errors, is an innovative contribution to the remaining life prediction field. Our paper elaborates on the basic underlying structure of CBM system that is defined by transaction matrix and the threshold value of failure probability. We developed this framework for analysing the CBM policy cost more accurately and to find the probabilistic threshold values of covariate that corresponds to the lowest price of predictive maintenance cost. The experimental results are performed on a big dataset which is generated from a sophisticated simulator of a gas turbine propulsion plant. A comparative analysis confirms that the method used in the proposed framework outpaces the classical methods in terms of classification accuracy and other statistical performance evaluation metrics.

냉동기 고장경향분석을 통한 설비신뢰도향상 방안 제시

Chiller system plays an important role of maintaining room temperature constantly by supplying chilled water to Heating, Ventilating and Air Conditioning(HVAC)or area room cooler equipment during plant normal operation or accident condition. Chiller failures are one of the most frequently occurring equipment failures. If the types of chiller failures are analyzed and grouped thoroughly, it would be helpful to make chiller maintenance strategy at the plants. That would enhance equipment reliability of chiller in the end. In this paper, chiller failure data during three years were analyzed and categorized by specific failure code. In addition, the various proposals to improve equipment reliability of chiller were suggested such as Preventive Maintenance Optimization(PMO) strategy and performance monitoring reinforcement and so on.

Combined bispectrum and trispectrum for faults diagnosis in rotating machines

Over the years, condition monitoring of rotating machines has been extensively applied for enhancing equipment reliability and maintenance cost-effectiveness, through the early detection and reliable diagnosis of incipient machine faults. Earlier studies suggest that bispectrum analysis is a good tool for detecting and distinguishing rotor-related faults in rotating machines, with a significantly reduced number of vibration sensors. Now, the trispectrum analysis is also applied to the measured vibration data, so as to explore the usefulness of this analysis in the diagnosis. It is observed that the trispectrum further improves the reliability of rotating machines’ faults diagnosis. This article presents the results and observations related to the bispectrum and trispectrum analyses for fault(s) diagnosis, through an experimental rig with different faults simulation.

신규원전의 기기별 고장분석을 통한 발전정지유발기기 선정

For decreasing an unexpected shutdown of Nuclear Power Plants, Korea Hydro & Nuclear Power co.(KHNP) has developed Single Point Vulnerability(SPV) of NPPs since 2008. SPV is the equipment that cause reactor shutdown & turbine trip or more than 50% power rundown due to its malfunction. Newly built Nuclear Power Plants need to develop the SPV list, so performed the job which analyse equipment failure effect for SPV selection for 1 year. To develop this, Failure Mode Effect Analysis(FMEA) and Fault Tree Analysis(FTA) methods are used. As results of this analysis, about 900 equipment are selected as SPV. Thereafter those are going to be applied to Nuclear Power Plants to enhance equipment reliability..

Intelligent Prognostics System Design and Implementation

This paper proposes an intelligent prognostics system JPS) for semiconductor and TFT-LCD manufacturing. The IPS comprises several generic embedded devices (GEDs) and remote clients. The GED can be easily embedded into various types of equipment to acquire equipment engineering data and meet the specification requirements of Interface A for supporting semiconductor industry equipment engineering capabilities. Furthermore, the GED has an open-standard application interface offering pluggable and customized intelligent applications. With this feature, the intelligent applications can be distributed and localized, releasing the factory network burden and enhancing equipment reliability and processing quality. This paper also develops two typical pluggable applications: the predictive maintenance scheme (PMS) for detecting equipment faults and the virtual metrology scheme (VMS) for conjecturing equipment-processing quality. Integrating the PMS into the IPS and the VMS into the IPS are, respectively, accomplished using the conveyor equipment and the sputtering equipment in a TFT-LCD factory. These two illustrative examples clearly demonstrate that IPS is versatile, configurable, and effective.

IMPROVING THE RELIABILITY OF BODY ASSEMBLY LINE EQUIPMENT

It is necessary to establish higher levels of equipment reliability in a short time, the market demands ever shorter lead times for the release of new models. Also, the demand for new-model cars is very strong immediately after their introduction. The conventional method for enhancing equipment reliability is by screening alone. However, this requires screening operations on production lines and so has been an obstacle to line production and prevented shortening of lead times. We are now able to dramatically enhance equipment reliability in a very short time by detecting failure modes and forecasting the number of occurrences using a scientific technique based on reliability engineering.

Human Factors and Safety at Electricite de France

This article describes the changes in the ideas that have occurred in the human factors approach at Electricite de France, the publicly owned French utility, which is the largest operator of nuclear power plants in the world. Initially, the approach to human factors was based almost exclusively on enhancing equipment reliability. Recently, problems of teamwork, interface and interaction, and interdepartmental relations have come to the surface, and the initial approach is being supplanted by a new approach based on strengthening professionalism and devel oping a safety quality culture.