The literature study of existing research, related to feature extraction methods or. Condition monitoring and assessment of power transformers using computational intelligence applies a broad range of computational intelligence techniques to deal with practical problems of transformer cma. There are numerous practical applications of computational intelligence techniques in modelling, control, automation, prediction, image processing and data mining. In addition to economic modeling using artificial intelligence methods, he has previously published 3 books with springer. Condition monitoring has a number of important benefits such as. Computational intelligence, neural networks, fuzzy systems.
Accurate estimation of state of charge and state of health is achieved at low computational cost. Finally, the predictive maintenance methods using computational intelligence techniques are very important for improving production and manufacturing and product quality. It brings together many different aspects of the current research on intelligence technologies. In this study, moisture level in oil is estimated and its status classification is proposed by using fuzzy logic techniques for the power transformer monitoring and condition assessment. Using the nslkdd dataset, detection rates achieved by the two techniques for six cyber attacks were recorded. Transfer learning using computational intelligence. Although computational intelligence and soft computing are established fields, the new applications of using computational intelligence and soft computing can be regarded as an emerging field, better alternativeto traditional hard computing scenario. What is computational intelligence ci and what are its relations with arti. A recently developed method is by using artificial intelligence techniques as tools for routine maintenance.
The platform utilizes tool set for rapid prototyping of intelligent condition monitoring systems and advanced computational intelligence methods for novelty. The application of computational intelligence techniques 11 and available advanced telecommunication technology provided the capability to monitor what is happening inside the transformer and to. Ci computational intelligence dai distributed arti. Computer visionbased tracking and fault detection methods are increasingly growing method for use on railway systems. Genetic algorithm ga, one of the computational intelligence methods, employs a highly parallel, massive, and adaptive computational environment to accomplish the mathematically difficult tasks in the structural condition monitoring. In this thesis, artificial intelligence ai techniques are used to build a condition monitoring system that has incremental learning capabilities. Regarding the researches we can say two type of ehealth systems use mobile devices for chronic diseases management, agent.
This book explores applications of computational intelligence in key and emerging fields of engineering, especially with regard to condition monitoring and fault diagnosis, inverse problems, decision support systems and optimization. The diagnostic gases in the bushings are analyzed using the dissolve gas analysis. Tool condition monitoring using artificial intelligence methods. Artificial intelligence is a computational technique which is inspired by natural intelligence such as the swarming of birds, the working of the brain and the pathfinding of the ants. Pdf introduction to condition monitoring in mechanical and electrical systems. Condition monitoring using computational intelligence methods promotes. By definition, condition monitoring is performed when it is necessary to access the state of a machine and to determine whether it is malfunctioning through reason and observation william et al. Ebook condition monitoring using computational intelligence.
Applications in mechanical and electrical systems condition monitoring using. Modelbased condition monitoring for lithiumion batteries taesic kima, yebin wangb, huazhen fangc, zafer sahinoglub, toshihiro wadad, satoshi harad, wei qiaoe adepartment of computer science and computer engineering, university of nebraskalincoln, lincoln, ne. In this work, we investigated two computational intelligence techniques for wsn intrusion detection. Pdf online condition monitoring using computational. A long section presenting various applications not only illustrates the usefulness of some methods, but also provides a gauge to evaluate progress in this field. These are the finite element models, correlation based methods and computational intelligence. The incremental learning and multiagent system approach christina busisiwe vilakazi. To comply with this requirements, condition monitoring and diagnosis of machinery have become established industry tools 3. With the investigation of fault diagnosis system based on the virtual instrument technol. Condition monitoring and assessment of power transformers. Computational intelligence in emerging technologies for. The use of the stator current to monitor induction motors has been validated as a very advantageous and practical way to detect several types of faults. This paper presents an empirical study of feature extraction methods for the application of lowspeed slew bearing condition monitoring.
The gentlemans udrls is attractive to embedded applications due to its parallel implementation and the resultant fast computational speed. Though, there is good understanding of the importance healthcare systems by various authors, their focus was limited to a single aspect of the whole system and without integrated the analysis and decision. This presentation will focus on several methods of developing close to optimal architectures and on finding efficient learning algorithms. Condition monitoring using computational intelligence methods. Wilamowski, fellow member, ieee auburn university, usa abstract comparison of various methods of computational intelligence are presented and illustrated with exampies. Feature extraction and diagnosis system using virtual. An idea of prototyping these methods has triggered in using micro electro mechanical system mems sensor for data acquisition and real time condition monitoring. The modelbased monitoring algorithm is validated by simulation and experiments.
A back propagation neural network was compared with a support vector machine classifier. Researchers studying computational intelligence and its applications will find condition monitoring using computational intelligence methods to be an excellent source of examples. Methods of computational intelligence auburn university. The text introduces various signalprocessing and preprocessing techniques, wavelets and principal component analysis, for example, together with their uses in condition monitoring and details. In the next two sections, types of propositional logical. Study of condition monitoring of bridges using genetic algorithms. The search and selection of these articles were performed according to the following five steps. Methods of computational intelligence for nonlinear. Condition monitoring using computational intelligence methods promotes the various approaches gathered under the umbrella of computational intelligence to show how condition monitoring can be used to avoid equipment failures and lengthen its useful life, minimize downtime and reduce maintenance costs. Tool condition monitoring using artificial intelligence. The vibration monitoring methods and signal processing techniques for structural health monitoring. A new approach for condition monitoring and detection of. Pdf artificial intelligence application in machine condition. The text introduces various signalprocessing and preprocessing techniques.
Condition monitoring of bearing faults using the stator. Modelbased condition monitoring for lithiumion batteries. Methods in predictive techniques for mental health status. May 15, 2017 computational intelligence is one of the most powerful data processing tools to solve complex nonlinear problems, and thus plays a significant role in intelligent fault diagnosis and prediction. Ambient intelligence healthcare monitoring management.
What is computational intelligence and what could it become. Various systems are used to monitor the condition of patients with chronic disease. Condition monitoring using computational intelligence. If the faulty condition in a system can be determined with the detection, the diagnosis, or the prognosis in early stage, most problems can be repaired at this time. Methods in predictive techniques for mental health status on. Section 5 presents a discussion on the application situations. This textbook provides a clear and logical introduction to the field, covering the fundamental concepts, algorithms and practical implementations behind efforts to develop systems that exhibit intelligent behavior in complex environments. Type 3 articles on related computational intelligence techniques. Pdf condition monitoring techniques are described in this chapter. In addition, an online bushing condition monitoring approach, which is able to adapt to newly acquired data are introduced.
This book focuses on computational intelligence techniques and their applications fastgrowing and promising research topics that have drawn a great deal of attention from researchers over the years. Economic modeling using artificial intelligence methods. Computational intelligence is one of the most powerful data processing tools to solve complex nonlinear problems, and thus plays a significant role in intelligent fault diagnosis and prediction. Computational intelligence methods can be used in conjunction with the abovementioned methods for bushing condition monitoring. Pdf computational intelligence for condition monitoring. Machine condition monitoring using artificial intelligence core. Lis3dh accelerometer sensor is used for the data acquisition of spindle for capturing high frequency fault signals. Graduate students studying condition monitoring and diagnosis will find this alternative approach to the problem of interest and practitioners involved in fault. The problem becomes even more complex if the methods of computational intelligence have to be implemented in hardware. Condition monitoring using computational intelligence methods 2012, militarized conflict modeling using computational intelligence techniques 2011. Condition monitoring uses the observed operating characteristics of a machine or structure. Generally, heavy and timeconsuming computational tasks must be performed due to the complexity of the applied analytical models and the large number of required parameters 2. These methods include neural networks, fuzzy systems, and evolutionary computation.
The estimation algorithm with a small forgetting factor may track time. He became professor at the university of the witwatersrand in 2003 and also chairperson of system and control engineering in south africa. The rlsbased methods can be improved by using the forgetting factor. A methodological introduction texts in computer science currently unavailable. In this study, methods are proposed for fault detection. Mlp gives superior performance in terms of accuracy and training time than svm and rbf. Transformers are the most critical assets of electrical transmission and distribution system. The generalized condition monitoring framework which includes the data acquisition device, data analysis device, feature selection device and decisionmaking device is also presented. A modelbased monitoring algorithm is proposed to estimate model parameters and state of charge for lithiumion batteries. The emphasis in using the genetic algorithm for feature selection is to reduce the\ud computational load on the training system while still allowing near optimal results to be found\ud relatively quickly. Classification methods described and implemented are support. Section 6 describes challenges and prospects in this area. A new approach for condition monitoring and detection of rail.
Moreover, the goal of the study is to find methods and techniques for the condition assessment of power transformers status based on the state of moisture in. This is done by observing the deviation of the transformer parameters from their expected values. Dl methods 12, the rnn scheme for machine health monitoring. Computational intelligence for condition monitoring. The third is a new artificial neural network basedfuzzy inference system with moving consequents in ifthen rules. Condition monitoring using computational intelligence methods tshilidzi marwalacondition monitoring using computati. Nevertheless, for bearing faults, the use of vibrations or sound generally offers better results in the accuracy of the detection, although with some disadvantages related to the sensors used. Two aspects of condition monitoring process are considered. This paper describes an application of three artificial intelligence ai methods to estimate tool wear in lathe turning. Techniques for using these decisionmaking devices are introduced. The book is intended for use in graduate courses on applied computation, applied mathematics, and engineering, where tools like computational intelligence and numerical methods are applied to the solution of realworld problems in emerging areas of engineering. The first two are conventional ai methodsthe feed forward back propagation neural network and the fuzzy decision support system. Artificial intelligence ai is a successful method of machine condition monitoring and fault diagnosis since these techniques are used as tools for routine. A brief survey of the scope of ci journals and books with computational intelligence in their title shows that at present it is an umbrella for three core technologies neural, fuzzy and evolutionary, their appli.
The aim of the study is to find the proper features that represent the degradation condition of slew bearing rotating at very low speed. Study of condition monitoring of bridges using genetic. Conventional methods of fault diagnosis and condition monitoring are based on welltested mathematical models incorporating various machine faults. Condition monitoring using computational intelligence methods promotes the various approaches gathered under the umbrella of computational intelligence to show how condition monitoring can be used to avoid equipment failures and lengthen its useful life, minimize downtime and reduce maintenance. Results have shown that rbf radial bias function kernel, which is commonly known as gauss kernel has good performance in identifying faults with less computation time. Pdf the vibration monitoring methods and signal processing.
The advent of artificial intelligence has changed many disciplines such as engineering, social science and economics. Request pdf condition monitoring using computational intelligence methods. Ebook condition monitoring using computational intelligence methods. These methods make detection of components of the railways and fault detection and condition monitoring process can be performed using data obtained by means of computers. Online condition monitoring using computational intelligence. Comprehensive overview on computational intelligence. Many computational intelligences and statistical techniques have been proposed to develop a forecasting model to predict the future condition of a transformer in transmission system using dg analysis. Acoustic emission signal analysis and artificial intelligence. Research and development work in the area of computational intelligence is.
1401 826 1636 178 232 549 201 1593 1557 338 1121 630 499 695 575 1108 458 1390 42 1196 9 1265 539 236 1320 396 954 797 1192 1091 1219 221 275 520 1080 555 93 178 1175