To solve the problem that fault diagnosis accuracy of complex equipment bearings is not high due to the complexity of its structure and the environment, a cooperative algorithm for fault diagnosis of complex equipment bearings based on ensemble empirical mode decomposition (EEMD) and support vector machine (SVM) is proposed. First, the vibration signal of the bearings is decomposed by EEMD. Second, the correlation coefficient and kurtosis value are selected as the evaluation indexes for the intrinsic mode function (IMF) components after decomposition, and the weights of the parameters are set dynamically by the mean-guided weight method. Then, the IMF components are filtered by an improved genetic algorithm to obtain the optimal IMF component combination, which can effectively eliminate redundant components and retain as much fault information as possible. Next, using the orthogonality of IMF components, the energy distribution of the selected IMF components is calculated as the Eigenvector. Finally, using the advantage of accurate classification of SVM in small samples, the fault status of complex equipment bearings can be identified. The effectiveness of the algorithm model is proven by example simulation data, and the model has certain scalability and applicability in engineering.
Considering the complexity and the criticality of the stacker equipment, in order to solve the problem that the stop accuracy of the stacker reduces or even fails to work due to abrasion of the running rail, this paper proposes a cooperative detection method based on Pulse Coupling Neural Network (PCNN) and wavelet transform theory to detect the abnormal points of the stacker running rail in industrial environment by analyzing the variation signals. First of all, considering the fact that the data is mixed up with noises because of the environment at the site and the possibility of the data acquisition equipment breaking down, a noise reduction method for the vibration signal data of stacker is constructed based on PCNN. Then, the basic theory of wavelet transform is introduced and then the rules of judging anomaly points on stackers' running tracks are discussed based on wavelet transform. In addition, a cooperative detection method based on PCNN and wavelet transform theory is carried out based on the spacetime distribution feature of the vibration of the stacker orbits in the industrial environment. Then the rationality of the proposed algorithm is verified by simulation through data provided by State Grid Measuring Center of China. This paper constructs a model of the abnormal point detection of the stackers in an industrial environment. The experimental simulation and example simulation show that the cooperative detection method based on PCNN and wavelet transform theory can effectively detect and locate the anomaly points of the stacker running tracks. The expansibility in engineering applications is promising. Lastly, some conclusions are discussed.
Adaptive dual model predictive control (DMPC) for linear systems with constant parametric uncertainties is investigated in this paper. In particular, chance constraints on output and input are considered. The online set‐membership identification and recursive least squares are utilized for shrinking the uncertain parameter set and getting the estimation point of the parameters. The dual effect represented by the parameters' prediction error is considered in the receding horizon optimization problem for easing the impact of the uncertainties and improving the performance simultaneously. Chance constraints on output are tackled by converting into convex alternatives. The output tracking problem is transformed into a quadratically constrained quadratic‐programming (QCQP) problem, which is computationally tractable. A numerical example is provided to illustrate the effectiveness of the proposed method.
Since the characteristics of the incipient faults for the rolling bearing under the sectional jumping speed are difficult to be extracted, the conventional fault diagnostic approaches usually with poor monitoring performance and low diagnostic accuracy (i.e., the ratio of samples correctly classified to total samples). This paper proposes a novel cooperative diagnostic approach for the incipient faults of the rolling bearing based on the optimized local mean decomposition (LMD) and support vector machine (SVM). First, to resolve the problem of selecting the appropriate number of product function (PF) components, an optimally weighted fusion model of PF components is established by introducing a genetic algorithm, aiming to maximize the correlation with the original incipient fault signal. Besides, in this model, a novel rule is set to calculate the weight coefficients of fusion. Second, considering the sparsity of the incipient fault characteristics caused by the sectional jumping speed, from the perspective of energy distribution, a novel characteristic extraction model is constructed based on the equal interval energy projection. This characteristic extraction model can correctly extract the fault characteristics and effectively eliminate redundant information. Moreover, the SVM has collaborated with the above-mentioned characteristic extraction model to diagnosis incipient faults. Finally, the effectiveness and correctness of the proposed approach are verified by the experimental simulation results. The comparison and analysis show that the proposed algorithm cannot only correctly extract fault characteristics but also have a high accuracy of fault characteristics recognition with good operability and scalability.INDEX TERMS Incipient fault diagnosis, sectional jumping speed, LMD algorithm, genetic algorithm, projection energy, SVM fault characteristics recognition.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.