To solve the problems of low measurement efficiency and measurement accuracy error in the balance correction of the mill before delivery. The measurement method of measuring a single chip instead of the whole chip group is adopted. And based on that, an improved adaptive quantum genetic algorithm based on Bloch spherical coordinates is proposed. Three layers of quantum coding are used for the grinding group, the first layer adopts three-strand gene coding, the second and third layers adopt double-strand gene coding, and the adaptive step coefficient is introduced on this basis. The improved algorithm not only has the global search ability of a genetic algorithm but also has the coding ability of quantum bit, which can avoid the premature algorithm and improve the convergence performance of the algorithm. The results show that the proposed method enhances the correction accuracy compared with the traditional correction method. The residual unbalance is less than 0.005kg; Work efficiency increased by 92%. It can improve the calibration efficiency and accuracy of grinding disc installation balance measurement.

The safe operation of high-speed rail running gear is crucial, as fault diagnosis can effectively prevent potential risks and ensure the smooth operation of the train. The Belief Rule Base (BRB) method has demonstrated excellent performance in complex system modeling. However, during the optimization process, BRB may lead to a "combinatorial explosion" of rules within the model, resulting in a loss of model interpretability and an increase in complexity. To address this, a Multidimensional Belief Rule Base (MBRB) fault diagnosis method is proposed. By optimizing the structure and parameters, the interpretability of the model is enhanced, and its complexity is reduced. Specifically, the model inputs are decomposed into multiple dimensions for analysis, and then the MBRB rules are updated using the Projection Covariance Matrix Adaption Evolution Strategy (P-CMA-ES), increasing the model’s interpretability and accuracy. Finally, the effectiveness of this method is validated through an example of high-speed rail running gear.

For final-state quality inspection of three-dimensional stamped hairpin windings, existing studies still lack multimodal methods that integrate mechanical geometric constraints, prior-guided fusion, and decision interpretability. This study proposes a span-prior-guided explainable multimodal neural network method and develops SPIMA-Net. The final-state images were acquired at a fixed inspection station with a fixed camera position and imaging angle under a CCD vision light source. Final-state images are used as visual inputs, while geometric priors are constructed from span measurements and model-type information. A visual branch and a span branch extract image and prior features, and a span-prior-assisted gating mechanism modulates visual features to enable collaborative fusion. Experimental results show that SPIMA-Net achieves an accuracy of 98.14%, an F1-score of 96.55%, and an AUC of 0.9983 on the test set. Its nonconforming-class F1-score is improved by 10.44, 3.04, 6.27, 1.38, and 0.66 percentage points over the image-only, span-only, direct-fusion, SE-fusion, and CBAM-fusion models, respectively, while the total number of misclassifications decreases to five. Interpretability analysis shows that the model mainly focuses on span openings, end profiles, and local abnormal regions. Relative and absolute span deviations are identified as the main mechanical geometric factors affecting final-state quality classification. The proposed method provides a neuro-mechanical fusion approach that demonstrates high discriminative performance and engineering interpretability for hairpin winding quality inspection on the investigated industrial dataset.