A State-of-the-Art Critique Review of the Role of Decision-Making Techniques in NDT for Condition Monitoring

Nondestructive testing (NDT) is a vital tool in maintenance. Each NDT technique has some benefits and hindrances; therefore, the selection is crucial. Generally, the selection of a technique relies on operating personnel experience, and very few research papers shows uses of the decision-making (DM) approach. It was highlighted by various researchers that if a proper DM approach is used, it will save time and increase fault detection reliability. By keeping this fact in mind, this chapter is an attempt to provide a detailed review of research work from the year 2000-2018 that covered the role of DM techniques while making combinations of NDT for effective condition monitoring. It observed from the literature that very few researchers effectively utilized the power of DM tool. The researcher can use the outcome of this work as a beacon and improve it further.

Induction Machine Rotor and Stator Faults Detection by Applying the N-F Network

This chapter focuses on the monitoring and diagnosis of induction machine faults, particularly the broken rotor bars. The design of a system for monitoring, detecting, and locating incipient faults for different loads of the machine is achieved by the use of advanced intelligent techniques based on ANFIS-based neuro-fuzzy network. The knowledge base is based on indicators derived from the stator current spectral analysis of the machine which in addition has to detect and assess the number of faulty bars.

Fault Detection and Isolation in Power Systems Using Unknown Input Observer

Unknown input observers (UIO) find application in many cases for successful fault detection and isolation (FDI). In this chapter, a scenario where the unknown input observer is applied to load frequency control loops in interconnected power systems is analyzed. A UIO was chosen because load demand is not always constant and it can be considered to introduce an unknown disturbance to the system. Mathematical formulations on how to detect and isolate sensor faults are presented which are then implemented in MATLAB Simulink for simulations. Based on this historical survey on the application of UIO, a thesis on UIO application in FDI in distributed generation is done.

A State of Art Critique Review of Role of Optimization in NDTS for Effective Condition Monitoring

Nondestructive testing (NDT) techniques play a pivotal role in a condition-based monitoring system. Generally, using an optimization technique for optimizing the available solution gives added advantage. By keeping this fact in mind, this chapter is an attempt to provide a detailed review of research work from 2000-2018 that covered the role of optimization for effective condition monitoring using NDTs. It was observed from literature that little work found related to NDT process optimization. The researcher and practitioner can use the outcome of this work as a beacon and improve it further.

A Mobile Augmented Reality System for Enhancing Electrical Machine Supervision

Electrical machines are used almost everywhere, and our daily life depends on them. For this reason, it is important to articulate mechanisms to control, supervise, and perform proper maintenance of these machines, especially those used in critical industrial process. The SCADA protocol is one of the technologies that eases the operation and supervision of electrical machines. However, the absence of a spatial connection between the SCADA signals and the machines being supervised suggests the use of augmented reality (AR) to fill this void. This chapter describes SIMARA: A Mobile AR application based on a dual computer-vision system (QR-codes and fiducial markers). SIMARA provides a robust client application for the integration of AR and SCADA signals by means of virtual panels shown on top of real SCADA machines. An authoring tool is also provided in order for users to customize the application to their particular needs, allowing to create, by means of web services, customized virtual panels, and links between SCADA signals and the virtual information shown in the AR application.

Advanced Fault Diagnosis Monitoring Scheme in Asynchronous Motor Using Soft Computing Method

This chapter deals with the implementation of a PC-based monitoring and fault identification scheme for a three-phase induction motor using artificial neural networks (ANNs). To accomplish the task, a hardware system is designed and built to acquire three phase voltages and currents from a 3.3KW squirrel-cage, three-phase induction motor. A software program is written to read the voltages and currents, which are first used to train a feed-forward neural network structure. The trained network is placed in a Lab VIEW-based program formula node that monitors the voltages and currents online and displays the fault conditions and turns the motor. The complete system is successfully tested in real time by creating different faults on the motor.

Sensor and Its Application

Electronic nose systems are used to deliver a pattern response to a listed odor, and pattern recognition software is used to perform odor recognition and discrimination by using a series of sensors. The method of electronic noses generally includes time taking measurements in a non-standard test and error process. The sensory panel problem can be solved by electronic nose. For this purpose, a sensor model is used to design sensor array. The generated signal of these sensor array is used further to classify a mixture of two gases using principle component analysis (PCA)-based classification analysis. During classification, the efficiency of PCA classification has been checked over the different signal preprocessing technique. Continuous real monitoring of odor is done at specific sites in the field over hours, days, weeks, or even months. An electronic machine can also avoid many other troubles linked with the employ of human panels. Each and every variability, adaptation (becoming minimum sensitive during extended exposure), and revelation to hazardous compounds all come to mind.

Identifying Parameters for Nonlinear Degradation-Based Prognostics

Prognostics and health management (PHM) methodologies are increasingly playing active roles in improving the availability, reliability, efficiency, productivity, and safety of systems in many industries. In predicting the remaining useful life (RUL), this chapter introduces a prognostics framework with health index (HI) formulation, with specific emphasis on incorporating and validating nonlinear HI degradations. The key issue to the success of this framework is how to identify appropriate parameters in describing the behavior of the nonlinear HI degradations. Using exponential HI degradation as an example in predicting the RULs of induction motors, this chapter discusses three different explorations in verifying the existence of good parameter values as well as identifying the appropriate parameters automatically. Comprehensive experiments were carried out with degradation process (DP) data from eight induction motors, and it was discovered that good parameters can be automatically determined with the proposed parameter identification method.

Types of Faults and Condition Monitoring Methods of Induction Motors

Induction motors are the electromechanical devices used to convert electrical energy into mechanical energy and work under the principle of mutual inductance. They have stator and rotor as two major parts. They run at constant speed when the supply voltage and frequency are constant and are suited for constant speed drives. They have rugged construction but working environment causes different faults. As per IEEE and EPRI study on induction motor faults, bearing fault and stator faults are 46% and 36%, respectively. The broad categories of the fault are stator winding fault, broken rotor fault, rotor mass unbalance fault, bowed rotor faults, single phasing fault, bearing fault, and crawling. Unbalanced stator voltage and current, oscillations in torque, drop in efficiency and torque, overheating and unwarranted vibration are the effects of these faults. Undetected faults cause complete failure of motor and it is costly in terms of lost production time, maintenance cost, and wasted raw materials.

Vibration Monitoring of Rotating Electrical Machines

Vibration monitoring is applicable to all rotating machines for defect detection and diagnosis. Measurement and analysis of vibration have also been applied to rotating electrical machines with the objective of fault detection and predictive maintenance. The sources of vibration generation in electrical rotating machines, both electrical and mechanical, have been identified in this chapter. The vibratory characteristics associated with these defects have also been discussed in detail. Analyses of vibratory signatures in time domain, frequency domain, and time frequency domain have been dealt with, and different features and indicators associated with each domain have been described. The details of vibration measurement schemes such as transducers, different signal conditioning elements, as well as characteristics of recording and display devices and their applicability to electrical machines have also been included in the chapter.