The purpose of this article is to develop a new method to diagnose faults in pitch-controlledsystem of wind turbine. To do this, Fuzzyinference techniques combining the actual performance of wind turbine generating units and the spot workers' as well as the experts' experiences were used and a model is developed to diagnose faults in pitch- controlledsystem. The fuzzy theory is used to solve uncertainty inference problem through the establishment of the fault tree. The diagnostic accuracy is raised and the confirmation time of fault is improved at the same time by this method.
ABSTRACT: Rotating machinery is widely used in today’s industry some of which are complex, often with extremely demanding performance criteria. Machine failures can be catastrophic resulting in costly downtime. Faultdiagnosis has become increasingly more important for industrial automation. This work demonstrates the use of hybrid intelligentsystem in detection of vibration faults in Feed Pump. Prediction of failure in Feed Pump is based on Adaptive Neuro FuzzyInferenceSystem. The performance of this technique is investigated through experimental study of real online vibration signals. The results reveal that complexity analysis and velocity parameters in combination with ANFIS enable predictive maintenance and provide an effective measure for machine condition evaluation .
An architecture of a fuzzysystem with the aid of neural networks was used to make an intelligent decision for gearbox faults. The neuro-fuzzysystem combines the learning capabilities of neural networks with the linguistic rule interpretation of a fuzzyinferencesystem. Fuzzy systems are suitable for uncertain knowledge representation, while neural networks are efficient structures capable of learning from examples. The hybrid technique brings the learning capability of neural networks to the fuzzyinferencesystem. The parameters associated with the membership functions of a Sugeno-type FIS will change through the learning algorithm of the neural network. The computation and adjustment of these parameters are facilitated by a gradient vector, which provides a measure of how well the FIS is modelling the input/output data for a given set of parameters. From the topology point of view, ANFIS is an implementation of a representative fuzzyinferencesystem using a back propagation (BP) neural network-like structure. Figure 3 shows the topology of ANFIS with q node for each input, which consists of five layers. A description of each layer follows (Alavandar & Nigam., 2008):
This paper discusses the extended version of rFRSN P systems, i.e., fuzzy reasoning spiking neural P systems with trapezoidal fuzzy numbers (tFRSN P systems), and its application to faultdiagnosis of power systems. To adapt tFRSN P systems to solve faultdiagnosis problems, a matrix-based fuzzy reasoning algorithm (MBFRA) is used inspired by the dynamic ﬁring mechanism of neurons. Given initial pulse values of all input neurons of a tFRSN P system, MBFRA can perform fuzzyinference to obtain the pulse values contained in other neurons and export reasoning results represented by trapezoidal fuzzy numbers. To make MBFRA suitable for multiple faults diagnosis of power systems, a defuzziﬁcation method is applied for processing the reasoning results in order to obtain crisp numbers corresponding to them. Some case studies show the eﬀectiveness of the presented method. We also brieﬂy draw comparisons between tFRSN P systems and several other faultdiagnosis approaches.
Data-driven prognosis techniques utilize and require a large amount of historical failure data to build a prognostic model that learns the system behavior. Among these techniques, artificial intelligence is regularly used because of its flexibility in generating appropriate models. Reference  gives a survey on artificial intelligent techniques used in prognosis. Other outstanding data-driven prognosis techniques can be found in references [32-35] . In comparison with other prognosis techniques, data-driven prognosis techniques are the most promising and effective techniques in machine condition prognosis. They frequently use vibration signals for temporal pattern identifications since it is relatively easy to measure and record machine vibration data. Accordingly, data-driven prognosis technique with vibration-based measurement are developed and used for machine condition prognosis in this study.
ABSTRACT: Faultdiagnosis is an ongoing significant research field due to the constantly increasing need for maintain ability, reliability and safety of industrial plants. The pneumatic actuators are installed in harsh environment: high temperature, pressure, aggressive media and vibration, etc. This influenced the pneumatic actuator predicted life time. The failures in pneumatic actuator cause forces the installation shut down and may also determine the final quality of the product. A fuzzy logic based approach is implemented to detect the external faults such as Actuator vent blockage, Diaphragm leakage and in correct supply pressure. The fuzzysystem is able to identify the actuator condition with high accuracy by monitoring five parameters. The parameter selection is based on the committee of DAMADICS (Development and Application of Methods for Actuator Diagnosis in Industrial Control Systems). The FuzzyInference Systems were implemented in real time using MATLAB and the results prove that the system can effectively classify all the types of external faults.
This paper has described and illustrated the application of two popular NN/FZ systems, the AFD and the FFD, for motor fault detection/diagnosis. Both structures can provide good fault detection/diagnosis under varying load torque, with the results of the AFD being slightly more accurate. Yet, from the FFD, consistent heuristic information can be extracted in terms of fuzzy if–then rules, which is probably one of the main advantages of the structure. However, for the specific case considered, the fault detection scheme is slower in convergence when compared to the AFD. Furthermore, the initial unsupervised pretraining is mandatory for the prelim- inary structuring of the fuzzyinferencesystem. The AFD, on the other hand, is faster in convergence. Furthermore, it provides better results when applied without any pretraining. However, the extracted knowledge in the AFD is not as
quality. Two date parameters including the length and freshness were measured for 500 date fruits. These dates were graded by both a human expert and MFIS (N. Alavi 2013); Based on the evaluation criteria, they can be categorized based on the grading into dryness (Wulfsohn et al., 1993), firmness (Schmilovitch et al., 1995), moisture (Dull et al., 1991; Schmilovitch et al., 2003, 2006), and automatic date grading (Lee et al., 2008). AL-Janobi (1998) applied the line-scan based vision for inspecting fast moving date fruits on a grading conveyor belt, where it is capable of determining the color/quality of date fruits. Self-learning techniques such as neural networks and fuzzy logic (Zadeh, 1965) seem to represent a good approach. In recent years, more and more applications of fuzzy theory to agriculture have been reported: Chao et al. (1999). In this research Mamdani fuzzyinferencesystem (MFIS) was applied as a decision making technique to classify the Mozafati dates based on quality (N.Alavi, 2012), Taner et al., (2015) in the paper, proposes a novel gender recognition framework based on a fuzzyinferencesystem (FIS). Fuzzy Logic (FL) is believed to be capable of addressing the uncertainty lying in the travellers behaviour and has been sought to develop realistic behavioural models in the recent years(Salini P.S. et al., 2017), Mohd in this paper presents the development of a Final Year Project (FYP) matching system using Fuzzy Logic (FL), (Mohd Fuad Abdul Latip et al., 2017) explains under partly covered conditions, the fuzzyinferencesystem decides which of the previous positions is more efficient. The proposed approach is implemented using experimental prototype located in Perpignan , France (A Zaher et al., 2017) explains based on the results, companies can develop their business strategies to meet the needs and expectations of potential customers from this perspective as well (Leon Oblak et al., 2017).
Faruk Arar et.al implemented Artificial Neural Community (ANN) for building a model for software program illness Prediction. He applied Artificial Bee Colony (ABC) for optimizing connection weights in ANN. This version changed into implemented to five publicly to be had datasets from the NASA repository. Jun Zheng et al studied 3 fee-sensitive algorithms for software illness prediction. The performances of the 3 algorithms are evaluated by means of the usage of four datasets from NASA projects. A comparison of soft computing algorithms for software program illness prediction is performed through Ertruk. E Erturk applied Adaptive Neuro-fuzzyinferencesystem for software disorder prediction. Rodriguez used datasets from PROMISE repository and implemented feature selection and genetic algorithms for predicting defective modules. Guo
Recently, AI techniques have become increasingly applied in vehicles faultdiagnosis due to the significant impact . In this regard, the authors in  proposed a self-diagnosissystem for autonomous vehicles that aims to improve the self-diagnosis speed and reduce the overhead. The proposed system consists of three modules where the first module is responsible for data gathering from autonomous vehicles using the Internet of Things, IoT, the second module is an optimised deep learning to initiate a training dataset based on the collected data of first module and finally, the third module is an edge computing based self-diagnosis service. Also, the authors presented the Lightweight In-Vehicle Edge Gateway (LI-VEG)  for the self-diagnosissystem, which provides rapid and accurate communication between vehicle and self- diagnosis module.
Sugeno FIS lends itself to the use of optimization and adaptive techniques for constructing fuzzy models and works well with linear techniques (e.g., Proportional-Integral- Derivative (PID) control). These adaptive techniques can be used to customize the MFs so that the fuzzysystem best models the data. It also has guaranteed continuity of the output surface . Therefore considering these abilities and advantages of Sugeno FIS especially in mathematical and design systems, all models in this study are developed based on the Sugeno FIS system.
In FTA the basic events have different importance and improving failure possibility of a basic event having highest importance will improve the reliability of system. H. Furuta and N. Shiraishi  proposed the concept of fuzzy importance using max-min fuzzy operator and fuzzy integral. Monte-Carlo simulation is generally used in the determination of importance measure, even though computing process is time consuming. Thus for a very complex system having large number of components, the whole procedure has to be repeated again and again, thus not suitable for the fuzzy approach. P. V. Suresh, A. K. Baber and V. Venkat Raj  proposed another method to evaluate an importance measure called fuzzy impor- tance measure (FIM). For effective evaluation of the im- portance index of each basic events, we have introduced a comparatively easier method to calculate fuzzy impor- tance index (FII), based Euclidean distance between two fuzzy numbers. The FII of different basic events leading Cannula Fault are obtained from the proposed method.
Recently, the new group of oil production modeling methods which are based on Artificial Intelligence (AI) approaches has enormously been used by experts. Fuzzy Logic (FL), was introduced by Lotfi A. Zadeh , and has advantages as one of the most popular methods to model the imprecise, vague and unclear problems [5, 19]. Their related procedures areas like oil production have recently become very noticeable. It is because of its strong abilities to deal with imprecise, vague and unclear problems that made it applicable in complex operations. The determination of the most suitable model involves finding the best relationship, called fuzzy rules, between pertinent parameters such as THP, GLR, Production rate in this specific case and the target, choke size. It is therefore extremely vital, critical and crucial to search for the most compatible rules. In order to generate fuzzy rule there are 3 possible rules which are (1) Through literature Survey (2) From Human Experts (3) Automatic Rule Generation . Furthermore, there are some techniques used to produce automatically these rules gaining from some evolutionary method like Genetic Algorithm (GA) and also, decision tree as a conventional one [7,13, 20]. In the present paper, an attempt is made to extract exact and useful rules out of the trained part of the
JT2FISPanel and JT2FISClusteringPanel are Java visual components to Build Java Intelligent Applications using Java Interval Type-2 FuzzyInferenceSystem and clustering method for fuzzy sets discovered from data mining process. We present an object oriented design of a JT2FISPanel and JT2FISClusteringPanel visual components based on SWING JPanel. We provide an example of how to use the JT2FISPanel and JT2FISClustering Panel for FIS easy configurations.
Hyper-convergence is a new innovation in data center technology, it changes the way clouds manage and maintain enterprise IT infrastructure. Hyper-convergence is more efficient and basically agile technology environment. Cloud computing is a latest technology due to provision of latest cloud services over the internet. The cloud service providers cannot promise accurate reliability of their services i.e. problem in provisioning of software or hardware failure etc. Reliability of cloud computing services depends on the ability of fault tolerance during the execution of services. There are so many factors can cause faults, such as network failure, browser crash, request time out or hacker attacks. When users are facing these types of faults, they usually resubmit their requests. However, if there is any key element involved in faults or errors, additional action may be needed to deal with system logs. If there is anomaly behavior occurred in faulted virtual machine, these VMs may need extra attention from cloud system protection and security point of view. In this paper, provision of reliability management in hyper-convergence cloud infrastructure is proposed and self-healing techniques in software as a service on the basis of failure in cloud services. Intelligent cloud service reliability framework will increase the reliability during execution of cloud service.
Faultdiagnosis is an ongoing significant research field, due to the constant increasing need for maintainability, reliability and safety of industrial plants. The pneumatic actuators are installed mainly in harsh environment: high temperature, pressure, aggressive media, vibration, etc. This influenced on the Pneumatic actuator predicted lifetime. The failures in pneumatic actuator cause forces the installation shut down and may also influence the final product quality. A fuzzy logic based approach is implemented to detect the external faults such as Actuator vent blockage, Diaphragm leakage and incorrect supply pressure. The fuzzysystem is able to identify the actuator condition with high accuracy by monitoring five parameters. The parameter selection is based on the committee of DAMADICS. The FuzzyInference Systems was implemented using MATLAB® and the simulation result show that the scheme can effectively classify all the types of external faults.
[1, 2]. For this objective, structural controllers are one of the novel solutions, which could be expressed as passive, active, semi-active, and hybrid control systems [3, 4]. However, active structural controller has been manufactured and utilized in full-scale structures, but it requires to develop in solving the reliability and robustness obstacles. Although passive control devices demonstrate suitable outcome in attenuating the undesired vibration magnitudes, but the deficiency of adaptability with online conditions of structural system is one of the main obstacles in robustness and reliability in passive controllers. On the other hand, the idea came up that resistance effort could be inserted by applying smart materials in semi- active dampers. A semi-active damper is a controller device that cannot incorporate external energy into the structural building . Magnetorheological (MR) damper was a novel semi-active device that has a great impact to enhance the seismic vibration controllers. The MR dampers have the reliability of passive control devices beside of preserving the versatility and adaptability of active control devices[7, 8].
According to Juliansyah  conducted a study entitled "Application of the Fuzzy Tsukamoto Method to Predict Palm Oil Results (Case Study: PT. Amal Tani Tanjung Putri-Bahorok Plantation)". In this study a system that can help predict the results of oil palm in the company is built by using the Tsukamoto method by using two variables as input, namely demand and supply and the results of the output in the form of the amount of palm oil production in a monthly period.
Abstrak: Beasiswa merupakan pemberian berupa bantuan keuangan yang diberikan kepada perorangan. Beasiswa bertujuan untuk digunakan demi keberlangsungan pendidikan yang ditempuh. SMAN 1 Parung merupakan lembaga formal milik pemerintah yang bergerak pada bidang pendidikan. SMAN 1 Parung mempunyai program beasiswa untuk siswa berprestasi yang kurang mampu. Masalah yang kerap kali terjadi yaitu tidak tepatnya pemberian beasiswa karena hanya menggunakan rata-rata nilai rapor. Berdasarkan masalah tersebut, penulis melakukan penelitian untuk menentukan penerima beasiswa menggunakan fuzzyinferencesystem metode Mamdani, dengan kriteria rata-rata nilai rapor, pendapatan orang tua, dan jumlah tanggungan orang tua. Pendekatan yang digunakan untuk menyelesaikan permasalahan penelitian melalui studi pustaka dari penelitian terdahulu tentang penentuan penerima beasiswa, teori tentang logika fuzzy metode Mamdani, kemudian menyusun tahap- tahap yang harus dilakukan dalam penelitian. Penerapan metode dan kriteri diharapkan dapat diperoleh perhitungan yang akurat sehingga menghasilkan penilaian yang akurat terhadap siswa-siswi yang berhak mendapatkan beasiswa.
The first step is to solve the problem of woven fabric production using the Tsukamoto method which is to determine the input variables and output variables which are firm sets, the second step is to change the input variable into a fuzzy set with the fuzzification process, then the third step is processing the fuzzy set data with the maximum method. And the last or fourth step is to change the output into a firm set with the defuzzification process with a weighted average method, so that the desired results will be obtained in the output variable. The solution to the production problem using the Sugeno method is almost the same as using the Tsukamoto method, it's just that the system output is not a fuzzy set, but rather a constant or a linear equation. The difference between the Tsukamoto Method and the Sugeno Method is in consequence. The Sugeno method uses constants or mathematical functions of the input variables.