Bearing Fault Diagnosis Method Based on Multidomain Heterogeneous Information Entropy Fusion and Model Self-Optimisation

Abstract

Incomplete diagnostic information, inadequate multisource sensor information, weak diagnosis models, and subjective experience result in difficulty in predicting rotating machinery faults. To overcome these limitations, we proposed a multiple domain and heterogeneous information entropy fusion model based on an optimisation of bearing fault diagnosis. The spatiotemporal approach uses a multiscene domain fusion strategy based on heterogeneous sensors (HSMSF) to extract feature fusion strategies and analyses the characteristics of the bearing fault features by multichannel processes with convolutional neural networks to vibration signals. After the mapping of multiple quality characteristics, the high-quality features are combined with each other, and the adaptive entropy weighted fusion method is used to analyse and make decisions on sensor information from different detection points. Nineteen key model parameters that were required for HSMSF construction were selected by adaptive optimisation using the chaos elitist modified sparrow search algorithm (CEI-SSA), and a self-learning diagnostic model that is suitable for multiple detection points was constructed. The validity and feasibility of the proposed fault diagnosis method were verified experimentally on two common reference-bearing datasets, CWRU and IMS, and compared with other fault diagnosis methods.

Application of Swarm Intelligence Optimization Algorithms in Image Processing: A Comprehensive Review of Analysis, Synthesis, and Optimization

“…[ 97 ] proposed a sparrow search algorithm based on the elite reverse learning-Levy flight strategy to address the drawbacks of large calculation amounts, long running times, and inaccurate selection of thresholds, resulting in low segmentation accuracy of the fire image Otsu method segmentation algorithm. To improve the performance of maximum two-dimensional entropy segmentation, the literature [ 98 ] proposed a maximum two-dimensional entropy segmentation method based on the improved sparrow search algorithm, and the segmented image with the optimal threshold was obtained by finding the maximum two-dimensional entropy of the image with the improved sparrow search algorithm. Second, the sparrow search algorithm combined with other algorithms to optimize image segmentation is also an effective solution.…”

Civil aviation safety risk intelligent early warning model based on text mining and multi-model fusion

“…Step 5: Calculate the information entropy of the predicted probability of each model 26 as follows: LGBM(Light Gradient Boosting Machine)…”

“…The process of the improved Stacking multimodel fusion algorithm is shown in Figure 4. The specific steps to improve the stacking multi-model fusion algorithm are as follows: Use sample x1 ¼ ½ f 1, f 2, f 3, /, fn to train the first layer XGB1 to obtain the prediction result P1 of XGB1; Step 2: Add P1 as a new feature to the sample x1 to construct an input sample x2 ¼ ½ f 1, f 2, f 3, /, fn, P1, use the input sample x2 to train the second layer LGBM1, and obtain the prediction result P2 of LGBM1; Step 3: Add P2 as a new feature to the sample x1 ¼ ½ f 1, f 2, f 3, /, fn to construct an input sample x3 ¼ ½ f 1, f 2, f 3, /fn, P2, use the input sample x1 to train the third layer GBDT, use the input sample x2 to train the third layer LGBM2, and use the input sample x3 to train the third layer XGB2;Step 4: The predicted probability values of the output three models26 are as follows:…”