This study proposes a new uncertain optimization algorithm to suppress vibration of the crankshaft system. In this new algorithm, the interval expression with random-interval hybrid variables is obtained by the confidence level. In addition, the interval order relation, interval probability, radial basis function neural network technology, and multi-objective genetic algorithm are applied to construct uncertain optimization algorithm with random-interval hybrid variables. Moreover, typical examples are used to demonstrate the effectiveness of the proposed algorithm. To suppress vibration of the crankshaft system, the optimization-Latin hypercube sampling design is used to obtain the experimental scheme and the data sampling is performed by multi-body system simulation of the vibration performance. Then, the radial basis function neural network is built considering the torsional displacement and transient stress of the crankshaft. Finally, the uncertain optimization algorithm is operated on the crankshaft structure design of the high-power reciprocating compressor. The results demonstrate that the robustness of the vibration performance and strength property is improved through the uncertain optimization algorithm, compared with that through deterministic optimization. The uncertain optimization algorithm to suppress vibration of the crankshaft system with random-interval hybrid variables is an efficient and effective approach, which is finally proved by the prototype test.

Obtaining the complete wear state of the milling cutter during processing can help predict tool life and avoid the impact of tool breakage. A cylindrical model of tool collection is proposed, which uses the collected partial pictures of the side edge to construct a panoramic picture of tool wear. After evaluating the splicing accuracy, the fully convolutional neural network (FCN) segmentation algorithm of the VGG16 structure is used to segment the panorama of the side edge of the end mill after splicing. The FCN model is built using Tensorflow to complete the image segmentation training and testing of the side edge wear area. Experimental results show that the FCN model can segment the side wear image and effectively solve the illumination change problem and different tool wear differences. Compared with the Otsu threshold adaptive segmentation algorithm and K-means clustering algorithm, the error of the extracted wear value is 1.34% to 8.93%, and the average error rate is 5.23%. This method can obtain a more intuitive panorama of the cutter side edge wear of the end milling and provide technical support for improving tool utilization rate, machining quality, and tool selection and optimization.