System health monitoring and prognostics — a review of current paradigms and practices

System health monitoring is a set of activities performed on a system to maintain it in operable condition. Monitoring may be limited to the observation of current system states, with maintenance and repair actions prompted by these observations. Alternatively, monitoring of current system states is being augmented with prediction of future operating states and predictive diagnosis of future failure states. Such predictive diagnosis or prognosis is motivated by the need for manufacturers and other operators of complex systems to optimize equipment performance and reduce costs and unscheduled downtime. Prognosis is a difficult task requiring precise, adaptive and intuitive models to predict future machine health states. Numerous modeling techniques have been proposed in the literature and implemented in practice. This paper reviews the philosophies and techniques that focus on improving reliability and reducing unscheduled downtime by monitoring and predicting machine health.     

自备电厂锅炉检修模式的存在问题及解决办法

通过对锅炉机组非计划停机原因的分析,提出了定期检修与状态检修相结合的检修模式,应是适合自备电厂现状并能有效减少故障频次的办法。     

Integrated approach for diagnostics and prognostics of HP LNG pump based on health state probability estimation

Effective machine fault prognostic technologies can lead to elimination of unscheduled downtime and increase machine useful life and consequently lead to reduction of maintenance costs as well as prevention of human casualties in real engineering asset management. This paper presents a technique for accurate assessment of the remnant life of machines based on health state probability estimation technique and historical failure knowledge embedded in the closed loop diagnostic and prognostic system. To estimate a discrete machine degradation state which can represent the complex nature of machine degradation effectively, the proposed prognostic model employed a classification algorithm which can use a number of damage sensitive features compared to conventional time series analysis techniques for accurate long-term prediction. To validate the feasibility of the proposed model, the five different level data of typical four faults from High Pressure Liquefied Natural Gas (HP-LNG) pumps were used for the comparison of intelligent diagnostic test using five different classification algorithms. In addition, two sets of impeller-rub data were analysed and employed to predict the remnant life of pump based on estimation of health state probability using the Support Vector Machine (SVM) classifier. The results obtained were very encouraging and showed that the proposed prognostics system has the potential to be used as an estimation tool for machine remnant life prediction in real life industrial applications.     

Decoupled tracking and thermal monitoring of non-stationary targets

Fault diagnosis and predictive maintenance address pertinent economic issues relating to production systems as an efficient technique can continuously monitor key health parameters and trigger alerts when critical changes in these variables are detected, before they lead to system failures and production shutdowns. In this paper, we present a decoupled tracking and thermal monitoring system which can be used on non-stationary targets of closed systems such as machine tools. There are three main contributions from the paper. First, a vision component is developed to track moving targets under a monitor. Image processing techniques are used to resolve the target location to be tracked. Thus, the system is decoupled and applicable to closed systems without the need for a physical integration. Second, an infrared temperature sensor with a built-in laser for locating the measurement spot is deployed for non-contact temperature measurement of the moving target. Third, a predictive motion control system holds the thermal sensor and follows the moving target efficiently to enable continuous temperature measurement and monitoring.     

Research on immune genetic algorithm for solving the job-shop scheduling problem

Machine condition monitoring is important to factory efficiency and safety of workers. A variety of vibration signals analysis techniques have long been used to diagnosis machine status. Based on the newest Internet and mobile communication technology we developed a remote fault diagnostic system with many merits. This remote monitoring system takes XML as a core and uses it to encode diagnostic data. The utilization of XML gives this system many advantages including minimum research work on the client side, and simplicity to expand the system. This system publishes the diagnosis data not only by WEB, but also by WAP. Then users can check the machine status including data, image and video, through the Internet and mobile terminals. The automatic alarm part, which is developed based on Microsoft’s Smartphone 2003 operating system, can actively send alerting messages to the engineers’ mobile phones and call these phones to make sure they get an alert when the machine’s status is abnormal.     

对远程监测系统应用于采煤机维修的探究

采煤机正常运行直接关系到综采工作面的效率,影响到煤炭企业的发展速度、经济效益和安全生产。简单介绍了当前采煤机维修存在的不足,提出了采用先进的远程监控系统对煤矿设备进行远程监测的重要性。重点阐明了基于GPRS的采煤机远程监控系统的设计方案,介绍了采煤机运行状态监控的主要内容,并提出了为保证采煤机高效运行能采取措施的思路。     

A wavelet packet spectral subtraction and convolutional neural network based method for diagnosis of system health

Health monitoring systems play a key role inside smart factories. To enhance the real-time capability and reliability of health monitoring systems, we propose a fully automatic method for machine diagnosis. Firstly, acquired vibration signals are converted into high-resolution images by wavelet packet spectral subtraction. Next, a trained convolutional neural network (CNN) automatically extracts important features and determines the current health of the machine. The performance of the proposed method is demonstrated by employing a diagnosis problem of a bearing system. The result shows an outstanding classification accuracy of 99.64 % even with a small amount of training data (5 % of the data).

     

Reliability-based maintenance optimization under imperfect predictive maintenance

The reliability-based maintenance optimization model has been focused by the engineers and scholars but it has never been solved effectively to formulate the effect of a maintenance action on the optimization model.In existing works,the system reliability was assumed to be increased to 1 after a predictive maintenance.However,it is very difficult in the most practical systems.Therefore,a new reliability-based maintenance optimization model under imperfect predictive maintenance (PM) is proposed in this paper.In the model,the system reliability is only restored to Ri (0相似文献   

Support vector machine in machine condition monitoring and fault diagnosis

Recently, the issue of machine condition monitoring and fault diagnosis as a part of maintenance system became global due to the potential advantages to be gained from reduced maintenance costs, improved productivity and increased machine availability. This paper presents a survey of machine condition monitoring and fault diagnosis using support vector machine (SVM). It attempts to summarize and review the recent research and developments of SVM in machine condition monitoring and diagnosis. Numerous methods have been developed based on intelligent systems such as artificial neural network, fuzzy expert system, condition-based reasoning, random forest, etc. However, the use of SVM for machine condition monitoring and fault diagnosis is still rare. SVM has excellent performance in generalization so it can produce high accuracy in classification for machine condition monitoring and diagnosis. Until 2006, the use of SVM in machine condition monitoring and fault diagnosis is tending to develop towards expertise orientation and problem-oriented domain. Finally, the ability to continually change and obtain a novel idea for machine condition monitoring and fault diagnosis using SVM will be future works.     

An intelligent approach to machine component health prognostics by utilizing only truncated histories

Numerous techniques and methods have been proposed to reduce the production downtime, spare-part inventory, maintenance cost, and safety hazards of machineries and equipment. Prognostics are regarded as a significant and promising tool for achieving these benefits for machine maintenance. However, prognostic models, particularly probabilistic-based methods, require a large number of failure instances. In practice, engineering assets are rarely being permitted to run to failure. Many studies have reported valuable models and methods that engage in maximizing both truncated and failure data. However, limited studies have focused on cases where only truncated data are available, which is common in machine condition monitoring. Therefore, this study develops an intelligent machine component prognostics system by utilizing only truncated histories. First, the truncated Minimum Quantization Error (MQE) histories were obtained by Self-organizing Map network after feature extraction. The chaos-based parallel multilayer perceptron network and polynomial fitting for residual errors were adopted to generate the predicted MQEs and failure times following the truncation times. The feed-forward neural network (FFNN) was trained with inputs both from the truncated MQE histories and from the predicted MQEs. The target vectors of survival probabilities were estimated by intelligent product limit estimator using the truncation times and generated failure times. After validation, the FFNN was applied to predict the machine component health of individual units. To validate the proposed method, two cases were considered by using the degradation data generated by bearing testing rig. Results demonstrate that the proposed method is a promising intelligent prognostics approach for machine component health.