ANFIS model based on fuzzy C‐mean , grid partitioning and subtractive clustering to detection of stator winding inter‐turn fault for PM synchronous motor

Abstract

Summary In this paper, one‐of‐a‐kind hybrid intelligence models based on the adaptive neuro‐fuzzy inference system (ANFIS) the use of C‐mean fuzzy clustering (FCM), grid partitioning (GP), and subtractive clustering (SC) fashions are used. Three extraordinary gaining knowledge of algorithms that were incorporated with the ANFIS version are used to locate fault prevalence within the permanent magnet synchronous motor (PMSM). Due to the fact it may both stumble on any inconvenience with any force and is flexible enough, and it can be used in offline and online identification of this method. In the beginning, the dynamic model of the PMSM along with its positive fault could be delivered. On the grounds that fault detection in these engines could be very critical, one‐of‐a‐kind strategies have been proposed for detecting stator deflection in electric machines. On the way to determine the fault percentage in the PMSM, hybrid intelligence fashions are used to identify the fault. The advantages of the proposed algorithm are the potential to stumble on faults with one‐of‐a‐kind domain names. The inputs of the proposed set of rules are PMSM current and torque alerts in normal and defective conditions. Inside the proposed set of rules, the club function structure turned into created with the FCM, SC, and GP methods. The outcomes show that the proposed approach can follow the fault in a brief time.

Research on fault early warning of power transmission line crossing and collision based on multi-source data

“…The line fault early warning model is mainly divided into seven links, such as information collection and data preprocessing [17]. The multi-source data algorithm is used to mine massive data, so as to obtain the occurrence index of fault factors of different fault types On this basis, using the feature items in the fault identification feature library and the time series data composed of time series data with standard time, the corresponding time series model is established, the time series spacing is set, the method and method of optimal diagnosis are determined, and the fault alarm is carried out for the transmission system that meets a certain critical point [18]. By filtering the data, it is found that some characteristics have a certain correlation with the fault.…”

Deep Neural Fuzzy System Oriented toward High-Dimensional Data and Interpretable Artificial Intelligence

“…The input space can be divided appropriately, and the number of membership functions (MFs) and the parameters for each input domain can be reasonably determined [28]. There are two other well-known methods to construct fuzzy inference systems: (1) grid partitioning; (2) fuzzy c-means clustering [29]. It has been proven that SC is better than other algorithms [30,31], and it was adopted as the method to generate the fuzzy inference system in the ANFIS.…”

Diagnostic Modelling for Induction Motor Faults via ANFIS Algorithm and DWT-Based Feature Extraction

“…ANFIS is a hybrid of ANN and fuzzy logic that can incorporate important features of both techniques [13]. The ANN's learning ability and the fuzzy system's logical reasoning ability have been combined in ANFIS [14]. ANFIS takes into account the positive features of ANN and fuzzy logic techniques for classifying and detecting different rotating machinery faults [15].…”