Intelligent Fault Recognition and Diagnosis for Rotating Machines using Neural Networks

2013 ◽  
pp. 158-172 ◽  
Author(s):  
Cyprian F. Ngolah ◽  
Ed Morden ◽  
Yingxu Wang
Keyword(s):  
Machine Condition ◽  
Vibration Signals ◽  
Rotating Machine ◽  
Fault Recognition ◽  
Machine Operators ◽  
System Vibration ◽  
Machine Health ◽  
Condition Based Monitoring ◽  
Industrial Machine ◽  
Previous Training

Monitoring industrial machine health in real-time is not only in high demand, it is also complicated and difficult. Possible reasons for this include: (a) access to the machines on site is sometimes impracticable, and (b) the environment in which they operate is usually not human-friendly due to pollution, noise, hazardous wastes, etc. Despite theoretically sound findings on developing intelligent solutions for machine condition-based monitoring, few commercial tools exist in the market that can be readily used. This paper examines the development of an intelligent fault recognition and monitoring system (Melvin I), which detects and diagnoses rotating machine conditions according to changes in fault frequency indicators. The signals and data are remotely collected from designated sections of machines via data acquisition cards. They are processed by a signal processor to extract characteristic vibration signals of ten key performance indicators (KPIs). A 3-layer neural network is designed to recognize and classify faults based on a pre-determined set of KPIs. The system implemented in the laboratory and applied in the field can also incorporate new experiences into the knowledge base without overwriting previous training. Results show that Melvin I is a smart tool for both system vibration analysts and industrial machine operators.

Intelligent Fault Recognition and Diagnosis for Rotating Machines using Neural Networks

2011 ◽  
Vol 3 (4) ◽  
pp. 67-83 ◽  
Author(s):  
Cyprian F. Ngolah ◽  
Ed Morden ◽  
Yingxu Wang
Keyword(s):  
Performance Indicators ◽  
High Demand ◽  
Rotating Machine ◽  
Fault Recognition ◽  
Machine Operators ◽  
System Vibration ◽  
Machine Health ◽  
Condition Based Monitoring ◽  
Industrial Machine ◽  
Previous Training

Monitoring industrial machine health in real-time is not only in high demand, it is also complicated and difficult. Possible reasons for this include: (a) access to the machines on site is sometimes impracticable, and (b) the environment in which they operate is usually not human-friendly due to pollution, noise, hazardous wastes, etc. Despite theoretically sound findings on developing intelligent solutions for machine condition-based monitoring, few commercial tools exist in the market that can be readily used. This paper examines the development of an intelligent fault recognition and monitoring system (Melvin I), which detects and diagnoses rotating machine conditions according to changes in fault frequency indicators. The signals and data are remotely collected from designated sections of machines via data acquisition cards. They are processed by a signal processor to extract characteristic vibration signals of ten key performance indicators (KPIs). A 3-layer neural network is designed to recognize and classify faults based on a pre-determined set of KPIs. The system implemented in the laboratory and applied in the field can also incorporate new experiences into the knowledge base without overwriting previous training. Results show that Melvin I is a smart tool for both system vibration analysts and industrial machine operators.

scholarly journals Intelligent Condition Monitoring Models For Rotating

2021 ◽  
Author(s):  
Kamyar Rashidi
Keyword(s):  
Condition Monitoring ◽  
Risk Function ◽  
Maintenance Cost ◽  
Machine Condition ◽  
Bayesian Decision ◽  
Noise Levels ◽  
Vibration Signals ◽  
Conditional Risk ◽  
Rotating Machine ◽  
Monitoring Model

Condition-based maintenance (CBM) is a maintenance strategy that reduces equipment downtime, production loss, and maintenance cost based on the changes in machine condition (e.g., changes in vibration, power usage, operating performance, temperatures, noise levels, chemical composition, and debris content). A newly developed condition monitoring model (CMM) is developed based on Bayesian decision theory, which takes vibration signals from a rotating machine and classifies them to either the normal or abnormal state. A conditional risk function is defined, which is calculated based on a loss table and the posterior probabilities. Using the conditional risk funciton, the machine condition can be classified to either the normal or abnormal condition. The developed model can efficiently avoid unnecessary maintenance and take timely actions through analyzing the received vibration signals from the machine. However, the vibration signals sometimes may not be sensed, transmitted, or received precisely due to unexpected situations. Therefore, a fuzzy Bayesian model for condition monitoring of a system is proposed. A program is coded in visual basic to run the models. Illustrative examples are demonstrated to present the application of both models.

scholarly journals Intelligent Condition Monitoring Models For Rotating

2021 ◽  
Author(s):  
Kamyar Rashidi
Keyword(s):  
Condition Monitoring ◽  
Risk Function ◽  
Maintenance Cost ◽  
Machine Condition ◽  
Bayesian Decision ◽  
Noise Levels ◽  
Vibration Signals ◽  
Conditional Risk ◽  
Rotating Machine ◽  
Monitoring Model

Condition-based maintenance (CBM) is a maintenance strategy that reduces equipment downtime, production loss, and maintenance cost based on the changes in machine condition (e.g., changes in vibration, power usage, operating performance, temperatures, noise levels, chemical composition, and debris content). A newly developed condition monitoring model (CMM) is developed based on Bayesian decision theory, which takes vibration signals from a rotating machine and classifies them to either the normal or abnormal state. A conditional risk function is defined, which is calculated based on a loss table and the posterior probabilities. Using the conditional risk funciton, the machine condition can be classified to either the normal or abnormal condition. The developed model can efficiently avoid unnecessary maintenance and take timely actions through analyzing the received vibration signals from the machine. However, the vibration signals sometimes may not be sensed, transmitted, or received precisely due to unexpected situations. Therefore, a fuzzy Bayesian model for condition monitoring of a system is proposed. A program is coded in visual basic to run the models. Illustrative examples are demonstrated to present the application of both models.

Machine Fault Detection Using Genetic Programming

2005 ◽  
Author(s):  
B. Samanta
Keyword(s):  
Fault Detection ◽  
Genetic Programming ◽  
Vibration Data ◽  
Rotating Machine ◽  
Fault Recognition ◽  
Machine Fault ◽  
Artificial Neural Network Ann ◽  
Monitoring And Diagnostics ◽  
The Time Domain ◽  
Selection Of

Applications of genetic programming (GP) include many areas. However applications of GP in the area of machine condition monitoring and diagnostics is very recent and yet to be fully exploited. In this paper, a study is presented to show the performance of machine fault detection using GP. The time domain vibration signals of a rotating machine with normal and defective gears are processed for feature extraction. The extracted features from original and preprocessed signals are used as inputs to GP for two class (normal or fault) recognition. The number of features and the features are automatically selected in GP maximizing the classification success. The results of fault detection are compared with genetic algorithm (GA) based artificial neural network (ANN)- termed here as GA-ANN. The number of hidden nodes in the ANN and the selection of input features are optimized using GAs. Two different normalization schemes for the features have been used. For each trial, the GP and GA-ANN are trained with a subset of the experimental data for known machine conditions. The trained GP and GA-ANN are tested using the remaining set of data. The procedure is illustrated using the experimental vibration data of a gearbox. The results compare the effectiveness of both types of classifiers with GP and GA based selection of features.

Diagnosis of Machinery Fault Status using Transient Vibration Signal Parameters

2002 ◽  
Vol 8 (3) ◽  
pp. 321-335 ◽  
Author(s):  
Zhidong Chen ◽  
Chris K. Mechefske
Keyword(s):  
Vibration Signal ◽  
Rolling Element Bearings ◽  
Machine Condition ◽  
Transient Vibration ◽  
Vibration Signals ◽  
Model Based ◽  
Machine Condition Monitoring ◽  
Signal Parameters ◽  
Rolling Element ◽  
Efficient Machine

This paper reports the results of an investigation in which a Prony model based method is developed. The method shows potential for analysing transient vibration signals. An example is included that shows how the procedure was employed to analyse the transient vibration signals created from faulty low speed rolling element bearings. Spectral plots generated by applying the procedure to very short data samples, as well as trending parameters based on these spectral estimations and Prony parameters, are presented. An equation was also derived to quantitatively determine the fault status. It is shown that application of the Prony model based method has the potential to be an effective as well as efficient machine condition monitoring and diagnostic tool where short duration transient vibration signals are being generated.

scholarly journals Condition Monitoring of Forward Curved Centrifugal Blower Using Coast Down Time Analysis

2010 ◽  
Vol 2010 ◽  
pp. 1-12
Author(s):  
G. R. Rameshkumar ◽  
B. V. A. Rao ◽  
K. P. Ramachandran
Keyword(s):  
Condition Monitoring ◽  
Health Condition ◽  
Centrifugal Blower ◽  
Rotating Machine ◽  
Monitoring Parameter ◽  
Shaft Misalignment ◽  
Sustained Operation ◽  
Mechanical Faults ◽  
Machine Health ◽  
Reduction Percentage

Mechanical malfunctions such as, rotor unbalance and shaft misalignment are the most common causes of vibration in rotating machineries. Vibration is the most widely used parameter to monitor and asses the machine health condition. In this work, the Coast Down Time (CDT), which is an indicator of faults, is used to assess the condition of the rotating machine as a condition monitoring parameter. CDT is the total time taken by the system to dissipate the momentum acquired during sustained operation. Extensive experiments were conducted on Forward Curved Centrifugal Blower Test Rig at selected cutoff speeds for several combinations of combined horizontal and vertical parallel misalignment, combined parallel and angular misalignment, as well as for various unbalance conditions. As mechanical faults increase, a drastic decrease in CDT is found and this is represented as CDT reduction percentage. A specific correlation between the CDT reduction percentage, level of mechanical faults, and rotational cutoff speeds is observed. The results are analyzed and compared with vibration analysis for potential use of CDT as one of the condition monitoring parameter.

Sign in / Sign up

Export Citation Format

Share Document