Condition monitoring and fault diagnosis of electric machinery Research Papers (original) (raw)

The reliable condition monitoring of machines and the early detection of faults play an important role in condition-based maintenance. Information on the condition of machines is needed in different forms but finally it has to be in as simple form as possible so that it can be utilised in the decision-making by the maintenance and management personnel. In the field of machine condition monitoring, there is a wide range of signal processing methods, which are used in feature extraction and fault diagnosis. Differentiation and integration are very common and important operations in vibration signal processing. The order of derivative is typically an integer number but it can also be any fractional number. Especially in the challenging fault and process cases, signals whose order of derivative is a real or complex number could be clearly more sensitive in fault detection than the commonly used signals: displacement, velocity and acceleration. In this paper, the application of complex o...

In this paper, we propose a simulation-before-test (SBT) fault diagnosis methodology based on the use of a fault dictionary approach. This technique allows the detection and localization of the most likely defects of open-circuit type occurring in Complementary Metal–Oxide–Semiconductor (CMOS) analog integrated circuits (ICs) interconnects. The fault dictionary is built by simulating the most likely defects causing the faults to be detected at the layout level. Then, for each injected fault, the spectre's frequency responses and the power consumption obtained by simulation are stored in a table which constitutes the fault dictionary. In fact, each line in the fault dictionary constitutes a fault signature used to identify and locate a considered defect. When testing, the circuit under test is excited with the same stimulus, and the responses obtained are compared to the stored ones. To prove the efficiency of the proposed technique, a full custom CMOS operational amplifier is implemented in 0.25 µm technology and the most likely faults of open-circuit type are deliberately injected and simulated at the layout level.

Integrated System Health Management (ISHM) is a promising technology that fuses sensor data and historical state-of-health information of components and subsystems to provide actionable information and enable intelligent decision-making regarding the operation and maintenance of aerospace systems. ISHM fundamentally relies on assessments and predictions of system health, including the early detection of failures and estimation of Remaining Useful Life (RUL). Model-based, data-driven or hybrid reasoning techniques can be utilized to maximise the timeliness and reliability of diagnosis and prognosis information. The benefits of ISHM include enhancing the maintainability, reliability, safety and performance of systems. The next evolution of the ISHM concept, Intelligent Health and Mission Management (IHMM), delves deeper into the utilization of on-line system health predictions to modify mission profiles to ensure safety and reliability, as well as efficiency through predictive integ...

The reliability and performance of a system with minimum life-cycle cost have become quite prominent in engineering systems. With increasing industrial applications, machines are operating in intricate conditions with higher uncertainty, causing greater vulnerability of system failure. This paper reports fault-related information of Brushless DC Motor (BLDC motor) in non-stationary operating conditions and presents several analyses to diagnose the faults. Fault diagnosis is the most crucial and important part of system prognostics which helps to increase the remaining useful life (RUL) and prevent catastrophic failures. Having both electrical and mechanical characteristics present in a BLDC motor, it shows several faults in different operating conditions. These faults cause a significant change in the vibration of the Motor. This paper deals with the anomaly detection of BLDC motor in non-stationary speed conditions using vibration signal analysis as well as extraction of several Condition Indicators (CI).

In this article, we are trying to exploit the cyclostationary characteristics of electrical signals in order to detect the rotor faults of an asynchronous machine. These defects are the most complex in terms of detection since they interact with the 50 Hz carrier with a weak band occupied in frequency. The test bench used includes an industrial three-phase wound rotor asynchronous motor of 400V, 6.2A, 50Hz, 3kW, 1385rpm characteristics (Fig. 15). The rotor fault has been carried out by adding an extra 40m resistance on one of the rotor phases (i.e. 10% of the rotor resistance value per phase, Rr=0,4). From the stator voltage and current acquisition, and by application of the Time Synchronous Averaging (TSA) method to the stator current, we condition the electrical signal in order to obtain a sensitive indicator allowing to easily distinguish the healthy cases from defective ones; this indicator will allow the motor monitoring. In a second step, we will apply the Motor Current Signature Analysis (MCSA) technique to the stator current, in order to identify the type of the detected fault. This will allow to go further and diagnose the motor defect.

Increase in use of power electronics in power system addressed power quality problems. Converters are widely used in industrial area for different application. They are non-linear devices and degrade power quality of system. In this paper, 12 – pulse ac – dc power supply is taken as non-linear load example. Power supply, here discuss is use in low voltage, high dc current application. High dc current is generated by connecting four M3 converters in parallel. Phase-shifting transformer is also introduce for require phase displacement. Converter can affect power quality in terms of inject harmonics and decrease power factor. It can be used as dynamic load; therefore, it is necessary to evaluate active and reactive power for different loading condition. This paper represents assessment of power quality for such system.

The present paper describes the development of a
monitoring, analysis and diagnosis system of power plant
equipments based on strain measurements. The objective
is to help companies increase availability and reduce
maintenance costs. The aim is the integrity evaluation of
a main steam and a hot reheat steam piping through
inspection, strain monitoring and computational
diagnosis.
The benefits are, among others, reduction in the
uncertainty of the remaining life prediction and reduction
of work, through process automation and integration and
real time monitoring (through the Internet) of the
operational condition of the equipment. Thus, greater
confidence and availability of the monitored generating
unit is sought as well as cost reduction as a consequence
of reduced frequency of unnecessary unit stops and
greater speed in decision making due to more precise
follow up of the operational condition of the targetequipment
and of its remaining life.

We would like to invite you to join this exciting new project as a chapter contributor. Since this is a textbook, a great deal of this chapter entails a survey on the topic under the paradigm of cyber-physical systems, what can be done onboard and remotely, the distributed nature of the system and some exercises on futurology (anticipating trends can shed some light on upcoming designs). IET will bring great visibility to your work. You are welcome to suggest another topic/chapter title if you feel it would be more suitable. Each chapter should be around 20-25 pages each and can be submitted as a Word or Latex File. The IET will send you additional information (formatting, permission form, etc.) with the contributor's agreement once you have agreed to contribute to the book. Visit http:// www.theiet.org/resources/author-hub/books/index.cfm to get all information you need as a contributor to an IET research-level book. Each book is expected to have a total number of 500 printed pages (based on approximately 550 words per page with a 20% allowance for figures and tables). We have included a tentative schedule and list of topics below. If this is something you would consider, please send me the title of your chapter, a short description/abstract of the chapter content, and your full contact details. We will expect original content and new results for this book. You can, of course, reuse published material but the percentage of material reuse for the chapter should be less than 40%. The IET will run a piracy software on the full manuscript to control that you are including original material and will reject chapters who contain a large amount of already-published material so please do take this into consideration.

- by Vania V Estrela
- •
- Robotics, Computer Science, Computer Graphics, Robotics (Computer Science)

Objective: This study was done to assess the accuracy of Accutrend GCT meter in determining blood cholesterol levels in our setup, with an aim to recommend its use in clinical practice
Methods: This cross sectional study was conducted on 251 healthy volunteers from April to May 2013. Capillary whole blood samples were obtained using sterile lancets and cholesterol levels were measured using Accutrend GCT meter (Roche Diagnostics, Mannheim, Germany) using the standard technique. Three ml whole blood was also collected in plain tubes by the same operator without applying a tourniquet. Serum cholesterol levels were determined using Merck Microlab 300 Automated Clinical Chemistry Analyser the same day. The laboratory technician performing this test was blinded to results obtained with Accutrend GCT meter. The seven patients with readings beyond the analytic range of the Accutrend GCT meter were excluded, meaning that data analysis was performed on 244 results only.
Results: Results of 182 males and 62 females having a mean age of 38.54± 15.25 years were analysed. There was a significant difference in mean cholesterol levels measured by Accutrend GCT and Microlab-300 (4.73± 0.74mmol/l and 4.67± 0.86 mmol/l; p=0.021), producing a measurement bias of 1.43% with Accutrend GCT meter. A strong positive correlation was found between the results of the two techniques (r=0.852 ,p<0.001).
Conclusions: Accutrend GCT meter provides accurate measurement of blood cholesterol levels and its use should be encouraged for point-of-care measurements.

This paper investigates the development and implementation of a real-time thermal ageing model for polymer-based electrical wire insulation using the classical Arrhenius relationship for chemical reaction rates. The paper presents the theoretical development and implementation of the method for predicting the insulation lifetime based on real-time temperature measurements using fibre-optic sensors embedded inside copper-wound coils. The performance of the presented lifetime model in delivering consistent results for winding insulation lifetime predictions is then assessed and validated using real-time steady-state and transient thermal experiments on a wound test coil mounted into a purpose built motorette test rig.

Most deep-learning models, especially stacked auto-encoders (SAEs), have been used in recent years for the diagnosis of faults in rotating machinery. However, very few studies have reported on health indicator (HI) construction by using SAEs in deep learning. SAEs have a good feature-extraction ability when several hidden layers are used to reconstruct the original input. In this study, we first introduce a method to reduce dependence on prior knowledge that is based on SAEs and enables extraction of the preliminary degradation trend from the bearing's frequency domain directly. Second, to construct the final HI and improve the monotonicity of the indicators, an exponential function is used to eliminate global severe vibration after an SAE has extracted the preliminary degradation trend. To prove the effect of our presented method, some other HI construction models, such as root mean square, kurtosis, approximate entropy, permutations entropy, empirical mode decomposition-singular value decomposition, K-means/K-medoids, and various time-frequency fusion indicators are used for comparison. Moreover, to prove that the exponential-function effect exceeds other severe vibration-eliminating methods, examples of the latter methods such as exponentially weighted moving-average and outlier detection are used for comparative analysis. Finally, the results shows that our proposed model is better than the above-mentioned existing models.

This paper addresses fault diagnosis in dynamic systems represented by discrete state-space models. The main idea of the paper is to propose a systematic way to implement a Petri net-based fault diagnosis system. This procedure consists of three main steps. In the first step, a fault diagnosis system is built based on the Luenberger observer. In the second step, the obtained fault diagnoser equations are transformed to a suitable format. Finally, in the third step, the obtained equations are implemented by a Petri net called continuous-time delay Petri net (CTDPN) that can realize difference equations. Based on this method, a systematic approach is proposed for realizing a classical fault diagnoser by CTDPN. By integrating the concept of state-space observers and PNs in this paper, new and effective methods are developed for the analysis and fault diagnosis of systemsknown as hybrid systems-that have both continuous and discrete variables. The performance of the proposed method is thoroughly investigated, and the obtained results show that the proposed CTDPN can precisely detect the occurred faults, their types and their occurrence time instances.

The advent of CBCT has made it possible to visualize the
dentition, the maxillofacial skeleton and the relationship of
anatomic structures in 3D. CBCT represents a valuable resource in
dental practice because it allows the establishment of a precise
treatment plan by means of diagnostic imaging. In cases of
increased difficulty or intra operative complications, root
resorptions, perforations and root fracture it is prudent to consider
the use of CBCT with its diagnostic value and limited radiation
exposure. Analyzing the morphology of the root canals in human
dentition conclude that the 3D image provided by CBCT is a great
advancement as an auxiliary method to establish the endodontic
diagnosis.

Real-time vibration monitoring and diagnostics system is developed and supplied for the 5 stand 4-h tandem cold rolling mill 2030 NLMC. Mechanism of chatter regeneration due to high frequency strip thickness variation and stands synchronization in the tandem rolling mills are considered. Methods for chatter passive damping and active suppression are considered. Work rolls hydraulic bending system influence on bearings vibration and chatter is discussed. The new methods are used for the 3rd octave chatter early diagnostics and model based mill control.

The monitoring systems presently available for vibration observation of civil engineering struc-tures are normally based on networks of accelerometers and strain gages distributed along the structure connected to one or more central computer. 1, 2 This computer launches the acquisition and stores and transmits the collected data. Depending on the dimensions of the structure and the extensiveness of the monitoring system, one common issue with most widely used monitoring systems is the use of electrical cables to power sensors and ...

Machine condition monitoring enables reliable and economical way of action for maintenance operations in modern industrial plants. Increasing number of measurement points and more demanding problems require automatic fault detection. Advanced signal processing methods exposed failures earlier and then it's possible to plan more operating time and less shutdowns. Intelligent methods have been increasingly used in model based fault diagnosis and intelligent analysers. Intelligent methods provide various techniques for combining a large number of features. A test rig was used to simulate different fault types and changes in operating conditions. Linguistic equation (LE) models were developed for the normal operation and nine fault cases including rotor unbalance, bent shaft, misalignment and bearing faults. Classification is based on the degrees of membership developed for each case from the fuzziness of the LE models. The classification results of the experimental cases are very good and logical. As even very small faults are detected by a slight increase of membership, the results are very promising for early detection of faults. Together with the compact implementation and the operability of the normal model, this makes the extension to real world problems feasible.

- by Sulo Lahdelma and +1
- •
- Mechanical Engineering, Signal Processing, Digital Signal Processing, Fault Detection

–Equipments are deteriorating with respect to time. If the timing and causes of the equipment deterioration are known ,proper preventive measures can be taken and hence the life time of the equipment can be increased. In this context, several parameters can be analysed, e.g-pressure ,temperature, vibration ,flow etc by collecting data and following certain methodologies to indicate the status of condition of the equipment. In this way the reliability of the equipment can remain high and longevity also can be increased. This paper presents a survey on various condition monitoring approaches of transformer along with various practical case studies based on various site visits. It discusses the minute details about how the condition of a transformer can be assessed after several years of usage and operation. It also discusses what are the methodologies used for assessment of transformer's condition and necessary precautions to be taken to avoid errors in assessment of condition. Some practical case studies based on various site visits are also shown to emphasize the importance of the work.

Oil analysis is a long-term program that, where relevant, can eventually be more predictive than any of the other technologies. It can take years for a plant's oil program to reach this level of sophistication and effectiveness. This book includes what all practitioners need to know to build an oil analysis program for their machine inspection. This book includes three real case studies and numerous industrial examples to improve machine reliability and enhance the condition monitoring program.

Induction motors are widely used in transportation, mining, petrochemical, manufacturing and in almost every other field dealing with electrical power. These motors are simple, efficient, highly robust and rugged thus offering a very high degree of reliability. But like any other machine, they are vulnerable to faults, which if left unmonitored, might lead to catastrophic failure of the machine in the long run. On-line
condition monitoring of the induction motors has been widely used in the detection of faults. This paper delves into the various faults and study of conventional and innovative techniques for induction motor faults with an identification of future research areas.

- by SOURAV PRADHAN
- •
- Fuzzy Logic, Matlab, Parameter estimation, Artificial Neural Networks

Monitoring and Evaluation Systems require twelve main components in order to function effectively and efficiently to achieve the desired results. These twelve M&E components are discussed in detail below: 1. Organizational Structures with M&E Functions The adequate implementation of M&E at any level requires that there is a unit whose main purpose is to coordinate all the M&E functions at its level. While some entities prefer to have an internal organ to oversee its M&E functions, others prefer to outsource such services. This component of M&E emphasizes the need for M&E unit within the organization, how elaborate its roles are defined, how adequately its roles are supported by the organizations hierarchy and how other units within the organization are aligned to support the M&E functions within the organization. 2. Human Capacity for M&E An effective M&E implementation requires that there is only adequate staff employed in the M&E unit, but also that the staff within this unit have the necessary M&E technical know-how and experience. As such, this component emphasizes the need to have the necessary human resource that can run the M&E function by hiring employees who have adequate knowledge and experience in M&E implementation, while at the same time ensuring that the M&E capacity of these employees are continuously developed through training and other capacity building initiatives to ensure that they keep up with current and emerging trends in the field. 3. Partnerships for Planning, Coordinating and Managing the M&E System A prerequisite for successful M&E systems whether at organizational or national levels is the existence of M&E partnerships. Partnerships for M&E systems are for organizations because they complement the organization's M&E efforts in the M&E process and they act as a source of verification for whether M&E functions align to intended objectives. They also serve auditing purposes where line ministries, technical working groups, communities and other stakeholders are able to compare M&E outputs with reported outputs. 4. M&E frameworks/Logical Framework The M&E framework outlines the objectives, inputs, outputs and outcomes of the intended project and the indicators that will be used to measure all these. It also outlines the assumptions that the M&E system will adopt. The M&E framework is essential as it links the objectives with the process and enables the M&E expert know what to measure and how to measure it. REPORT THIS AD 5. M&E Work Plan and costs Closely related to the M&E frameworks is the M&E Work plan and costs. While the framework outlines objectives, inputs, outputs and outcomes of the intended project, the work plan outlines how the resources that have been allocated for the M&E functions will be used to achieve the goals of M&E. The work plan shows how personnel, time, materials and money will be used to achieve the set M&E functions. 6. Communication, Advocacy and Culture for M&E This refers to the presence of policies and strategies within the organization to promote M&E functions. Without continuous communication and advocacy initiatives Page2 Page2Cite as Otundo M. (2019) The 12 Key Components Of M&E Systems Martin Otundo +254721246744 (whatsapp); email;

Rotating machines represent a class of nonlinear, uncertain, and multiple-degrees-of-freedom systems that are used in various applications. The complexity of the system's dynamic behavior and uncertainty result in substantial challenges for fault estimation, detection, and identification in rotating machines. To address the aforementioned challenges, this paper proposes a novel technique for fault diagnosis of a rolling-element bearing (REB), founded on a machine-learning-based advanced fuzzy sliding mode observer. First, an ARX-Laguerre algorithm is presented to model the bearing in the presence of noise and uncertainty. In addition, a fuzzy algorithm is applied to the ARX-Laguerre technique to increase the system's modeling accuracy. Next, the conventional sliding mode observer is applied to resolve the problems of fault estimation in a complex system with a high degree of uncertainty, such as rotating machinery. To address the problem of chattering that is inherent in the conventional sliding mode observer, the higher-order super-twisting (advanced) technique is introduced in this study. In addition, the fuzzy method is applied to the advanced sliding mode observer to improve the accuracy of fault estimation in uncertain conditions. As a result, the advanced fuzzy sliding mode observer adaptively improves the reliability, robustness, and estimation accuracy of rolling-element bearing fault estimation. Then, the residual signal delivered by the proposed methodology is split in the windows and each window is characterized by a numerical parameter. Finally, a machine learning technique, called a decision tree, adaptively derives the threshold values that are used for problems of fault detection and fault identification in this study. The effectiveness of the proposed algorithm is validated using a publicly available vibration dataset of Case Western Reverse University. The experimental results show that the machine learning-based advanced fuzzy sliding mode observation methodology significantly improves the reliability and accuracy of the fault estimation, detection, and identification of rolling element bearing faults under variable crack sizes and load conditions.

Predictive Maintenance strategy employs vibration analysis, thermography analysis, ultrasound analysis, oil analysis and other techniques to improve machine reliability. The goal of the strategy is to provide the stated function of the... more

The bleaching of palm oil using acid activated local bentonite clay, charcoal and periwinkle shell was studied. The raw oil was characterized to determine its properties .Chemical activation of the bleaching agent was done using Phosphoric acid (H3PO4) .the activated samples were used to adsorb color pigment from palm oil. The absorbance was measured using a spectrophotometer and the opacity and percentage color reduction were obtained in each case. To study the adsorption capacity of the three bleaching agent, the effect of temperature ,adsorbent dosage and contact time were studied. The bleaching performance increase with temperature, contact time and dosage for the three adsorbent. The activated charcoal produced the best bleaching performance at varying bleaching temperature and contact time while the activated bentonite produced the best bleaching performance at varying dosage concentration. The Experimental data conformed to the Othorder rate equation for the three adsorbent. The rate constant for activated bentonite clay,charcoal and periwinkle shell are:0.01min-1,0.023min-1 and 0.064min-1. Langmuir and Freundlich models were used to study the adsorption mechanism. the adsorption data conformed to the Freundlich isotherm for the three different adsorbent. The heat of adsorption of the acid activated bentonite clay was observed to be endothermic and most spontaneous with enthropy of -5.511Jmol-1, while the activated charcoal and Periwinkle shell is Exothermic.

Condition monitoring of gear-based mechanical systems in non-stationary operation conditions is in general very challenging. This issue is particularly important for wind energy technology because most of the modern wind turbines are geared and gearbox damages account for at least the 20% of their unavailability time. In this work, a new method for the diagnosis of drive-train bearings damages is proposed: the general idea is that vibrations are measured at the tower instead of at the gearbox. This implies that measurements can be performed without impacting the wind turbine operation. The test case considered in this work is a wind farm owned by the Renvico company, featuring six wind turbines with 2 MW of rated power each. A measurement campaign has been conducted in winter 2019 and vibration measurements have been acquired at five wind turbines in the farm. The rationale for this choice is that, when the measurements have been acquired, three wind turbines were healthy, one wind ...

- by Alessandro Daga
- •
- Engineering, Mechanical Engineering, Computer Science, Signal Processing

Fault diagnosis of electric motors is a fundamental task for production line testing, and it is usually performed by experienced human operators. In the recent years, several methods have been proposed in the literature for detecting faults automatically. Deep neural networks have been successfully employed for this task, but, up to the authors' knowledge, they have never been used in an unsupervised scenario. This paper proposes an unsupervised method for diagnosing faults of electric motors by using a novelty detection approach based on deep autoencoders. In the proposed method, vibration signals are acquired by using accelerometers and processed to extract Log-Mel coefficients as features. Autoencoders are trained by using normal data only, i.e., data that do not contain faults. Three different autoencoders architectures have been evaluated: the Multi-layer Perceptron (MLP) autoencoder, the Convolu-tional Neural Network autoencoder (LSTM), and the recurrent autoencoder composed of Long Short-Term Memory (LSTM) units. The experiments have been conducted by using a dataset created by the authors, and the proposed approaches have been compared to the One-Class Support Vector Machine (OC-SVM) algorithm. The performance has been evaluated in terms Area Under Curve (AUC) of the Receiver Operating Characteristic curve, and the results showed that all the autoencoder-based approaches outperform the OC-SVM algorithm. Moreover, the MLP autoencoder is the most performing architecture, achieving an AUC equal to 99.11%.

- by stefano squartini and +1
- •
- Machine Learning, Electrical Motors, Condition monitoring and fault diagnosis of electric machinery, Novelty Detection
- by Mohammad Rifky
- •
- Hematology, Veterinary Medicine, Animal Science, Molecular Biology

El estándar ISO 13379-1 presenta una serie de métodos de diagnóstico y lineamientos generales para ejecutarlos. En particular este articulo se refiere a una figura de mérito propuesta como ejemplo, por ISO 13379-1 para evaluar el nivel de confianza de un proceso de diagnóstico efectuado sobre un fallo potencial. El propósito de esta evaluación es determinar cuanta certeza se tiene sobre el resultado final del proceso de diagnóstico como una forma de validar si procede o no la acción correctiva recomendad en el diagnóstico mismo.

Even though prognostics has been defined to be one of the most difficult tasks in Condition Based Maintenance (CBM), many studies have reported promising results in recent years. The nature of the prognostics problem is different from diagnostics with its own challenges. There exist two major approaches to prognostics: data-driven and physics-based models. This paper aims to present the major challenges in both of these approaches by examining a number of published datasets for their suitability for analysis. Data-driven methods require sufficient samples that were run until failure whereas physics-based methods need physics of failure progression.

Prognostics and health management is an emerging discipline to scientifically manage the health condition of engineering systems and their critical components. It mainly consists of three main aspects: construction of health indicators, remaining useful life prediction and health management. Construction of health indicators aims to evaluate the system’s current health condition and its critical components. Given the observations of a health indicator, prediction of the remaining useful life is used to infer the time when an engineering systems or a critical component will no longer perform its intended function. Health management involves planning the optimal maintenance schedule according to the system’s current and future health condition, its critical components and the replacement costs. Construction of health indicators is the key to predicting the remaining useful life. Bearings and gears are the most common mechanical components in rotating machines, and their health conditions are of great concern in practice. Because it is difficult to measure and quantify the health conditions of bearings and gears in many cases, numerous vibration based methods have been proposed to construct bearing and gear health indicators. This paper presents a thorough review of vibration based bearing and gear health indicators constructed from mechanical signal processing, modelling and machine learning. This review article will be helpful for designing further advanced bearing and gear health indicators and provides a basis for predicting the remaining useful life of bearings and gears. Most of the bearing and gear health indicators reviewed in this paper are highly relevant to simulated and experimental run-to-failure data rather than artificially seeded bearing and gear fault data. Finally, some problems in the literature are highlighted and areas for future study are identified.

This project evaluated underground cable failure and researched innovative techniques for diagnosing failing underground power distribution cables. The aging of installed underground distribution cables is a looming issue facing electric utilities in India. A variety of technologies and tests are available for evaluating underground Cables, but there is often little correlation between what is diagnosed and what is found when the cable is pulled out and examined. The project team studied various cable failure mechanisms to better understand failure causes and to identify improved failure detection methods. Researchers investigated novel online techniques for detecting the degradation of concentric neutrals and insulation in the cable. Water trees are defects in high voltage cables that are the result of moisture content or the permeability of water within the insulation. The results suggested that both chemical and mechanical forces drive water tree creation. The injection of charges from electrolytes that form around a submerged cable can also contribute to water trees formation. Researchers concluded that two proposed diagnostic techniques were most promising: magnetic amorphous magneto resistive concentric neutral probing and radio frequency test point injection techniques.

Early detection of faults occurring in three-phase induction motors can appreciably reduce the costs of maintenance, which could otherwise be too much costly to repair. Internal faults in three phase induction motors can result in significant performance degradation and eventual system failures. Artificial intelligence techniques have numerous advantages over conventional Model-based and Signal Processing fault diagnostic approaches; therefore, in this paper, a soft-computing system was studied through Neural Network Analysis to detect and diagnose the stator and rotor faults. The fault diagnostic system for three-phase induction motors samples the fault symptoms and then uses a Neural Network model to first train and then identify the fault which gives fast accurate diagnostics. This approach can also be extended to other applications.