Predict industrial equipment failure with time windows and transfer learning

2021 ◽  
Author(s):  
Hongzhi Wang ◽  
Wenbo Lu ◽  
Shihan Tang ◽  
Yang Song
Keyword(s):  
Transfer Learning ◽  
Time Windows ◽  
Equipment Failure ◽  
Industrial Equipment

scholarly journals AN INTELLIGENT MODEL BASED ON DEEP TRANSFER LEARNING FOR DETECTING ANOMALIES IN CYBER-PHYSICAL SYSTEMS

2021 ◽  
pp. 124-132
Author(s):  
L. V. Sukhostat
Keyword(s):  
Anomaly Detection ◽  
Transfer Learning ◽  
Neural Model ◽  
Acoustic Signals ◽  
Cyber Physical Systems ◽  
Gradient Boosting ◽  
Industrial Equipment ◽  
Physical Systems ◽  
Extreme Gradient Boosting ◽  
Boosting Algorithm

Context. The problem of detecting anomalies from signals of cyber-physical systems based on spectrogram and scalogram images is considered. The object of the research is complex industrial equipment with heterogeneous sensory systems of different nature.  Objective. The goal of the work is the development of a method for signal anomalies detection based on transfer learning with the extreme gradient boosting algorithm. Method. An approach based on transfer learning and the extreme gradient boosting algorithm, developed for detecting anomalies in acoustic signals of cyber-physical systems, is proposed. Little research has been done in this area, and therefore various pre-trained deep neural model architectures have been studied to improve anomaly detection. Transfer learning uses weights from a deep neural model, pre-trained on a large dataset, and can be applied to a small dataset to provide convergence without overfitting. The classic approach to this problem usually involves signal processing techniques that extract valuable information from sensor data. This paper performs an anomaly detection task using a deep learning architecture to work with acoustic signals that are preprocessed to produce a spectrogram and scalogram. The SPOCU activation function was considered to improve the accuracy of the proposed approach. The extreme gradient boosting algorithm was used because it has high performance and requires little computational resources during the training phase. This algorithm can significantly improve the detection of anomalies in industrial equipment signals. Results. The developed approach is implemented in software and evaluated for the anomaly detection task in acoustic signals of cyber-physical systems on the MIMII dataset. Conclusions. The conducted experiments have confirmed the efficiency of the proposed approach and allow recommending it for practical use in diagnosing the state of industrial equipment. Prospects for further research may lie in the application of ensemble approaches based on transfer learning to various real datasets to improve the performance and fault-tolerance of cyber-physical systems.

scholarly journals Prognostics and Health Management of Industrial Equipment

2013 ◽  
pp. 333-356 ◽  
Author(s):  
E. Zio
Keyword(s):  
Health Management ◽  
The State ◽  
Equipment Failure ◽  
Prognostics And Health Management ◽  
Industrial Equipment ◽  
Useful Life ◽  
Future Information ◽  
Open Issues

Prognostics and health management (PHM) is a field of research and application which aims at making use of past, present, and future information on the environmental, operational, and usage conditions of an equipment in order to detect its degradation, diagnose its faults, and predict and proactively manage its failures. This chapter reviews the state of knowledge on the methods for PHM, placing these in context with the different information and data which may be available for performing the task and identifying the current challenges and open issues which must be addressed for achieving reliable deployment in practice. The focus is predominantly on the prognostic part of PHM, which addresses the prediction of equipment failure occurrence and associated residual useful life (RUL).

scholarly journals Forensic Engineering Investigation of Electrical and Electronic Causes of an Industrial Equipment Failure

2022 ◽  
Vol 38 (2) ◽  
Author(s):  
Robert Peruzzi
Keyword(s):  
Electrostatic Discharge ◽  
Equipment Failure ◽  
Industrial Equipment ◽  
Root Cause ◽  
Three Phase ◽  
Forensic Engineering ◽  
Engineering Investigation ◽  
Electrical Contractors ◽  
Random Failures ◽  
Secondary Power

This case involved industrial equipment whose repeated, seemingly random failures resulted in the buyer of that equipment suing the seller. The failures had been isolated to a group of several transistors within electro-mechanical modules within the equipment, but the root cause of those transistors failing had not been determined. The equipment seller had more than 1,000 units in the field with no similar failures. And the electro-mechanical module manufacturer had more than 20,000 units in the field with no similar failures. Electrical contractors hired by the buyer had measured power quality, and reported no faults found in the three-phase power at the equipment terminals. This paper presents circuit analyses of the failing electro-mechanical module, basics of electrostatic discharge damage and protection, and the root cause of these failures — an electrical code-violating extraneous neutral-to-ground bond in a secondary power cabinet.

Project Scheduling with Time Windows and Scarce Resources

2002 ◽  
Author(s):  
Klaus Neumann ◽  
Christoph Schwindt ◽  
Jürgen Zimmermann
Keyword(s):  
Project Scheduling ◽  
Time Windows ◽  
Scarce Resources

Improving Production System Performance Using Overall Equipment Effectiveness

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Lance Clarence ◽  
Wan Muhammad Noor Sarbani Mat Daud
Keyword(s):  
Production System ◽  
System Performance ◽  
Intelligent System ◽  
Global Market ◽  
Equipment Failure ◽  
Intuitive Knowledge ◽  
Analysis Tools ◽  
New Process ◽  
Knowledge Delivery

In the competition among organization on the global market, no organization will tolerate losses. Overall Equipment Effectiveness (OEE) overall is a new process in which the efficiency of a system is calculated and complicated manufacturing issues are truly simplified to simple and intuitive knowledge delivery. It thinks about the exceptionally important measures of productivity. An endeavour has been done to measure and analyse existing Overall Equipment Effectiveness (OEE) at company Kirino in hope to reduce unplanned downtime losses on equipment failure and tooling damage to maximize the productivity. The methods used to analyse these various causes were analysis tools and Intelligence Systems. After knowing the causes of various activities that leads to high rates of defects, then recommendations for improvements that could be used by company Kirino were ready to be made using intelligent system as a medium of solution

Qualitative assessment of equipment failure cause finding and removal

2018 ◽  
pp. 116-126
Author(s):  
E. A. Vakulin ◽  
A. I. Zayats ◽  
V. A. Beklemeshev ◽  
V. A. Ivashkevich ◽  
V. A. Khazhiev ◽  
...  
Keyword(s):  
Production Condition ◽  
Real Life ◽  
Open Pit Mine ◽  
Qualitative Assessment ◽  
Open Pit ◽  
Quality Level ◽  
Equipment Failure ◽  
Operation Conditions ◽  
Failure Investigation

Investigation of failures is one of the critical activities of mining and haulage equipment operability assurance in mining. Maintaining failure investigation at the required quality level, it is possible to identify provisions, rules and procedures that should be revised or changed, operation conditions that should be improved, additional personnel training, if required, etc. Investigation of failures in mines is under responsibility of machine men and electricians of maintenance and operation services. In reality, factory management and setup for production condition weak concernment of these workers in quality investigation aimed at finding of sources of equipment failures. This article describes real-life results achieved in development and use of maintenance service operation, technology and management monitoring. The requirements are substantiated for quality improvement in failure cause finding and removal in mining and haulage equipment at Chernogorsky open pit mine, SUEK-Khakassia. Causes of the present quality of failure investigation by machine men of Chernogorsky Repair and Engineering Works and Chernogorsky open pit mine are revealed. The proposed recommended practices will improve quality of mining and haulage equipment failure investigation.

Sign in / Sign up

Export Citation Format

Share Document