Ning Li

To adapt to the characteristics of high load and long-term operation of heavy-duty escalators, traditional trusses often adopt redundant structural designs to meet higher safety and reliability requirements, resulting in increased self-weight and higher manufacturing costs. Therefore, achieving the redesign of truss structures without compromising mechanical performance is necessary. In this work, static analysis of the heavy-duty escalator truss was conducted using Abaqus finite element simulation software. The influencing factors of truss deflection and weight were analyzed, as well as the effect of truss structure composition, distribution, and dimensions on truss performance, in order to obtain an optimized truss structure with the best mechanical performance. Subsequently, a three-dimensional model of the truss was established and modified based on the actual truss structure. The correctness of the model was verified through experimental results of an actual heavy-duty escalator truss project. Utilizing this model, the goal of reducing deflection and weight under the most economical conditions was pursued, and an economic analysis of the chords was conducted to propose the strengthening and weakening strategies. This work can serve as a guide for the design of heavy-duty escalator truss structures, helping to enhance the rationality and reliability of truss structures, reduce development costs, and improve economic benefits.

Accurate identification of the tool wear states in machining of titanium alloys continues to be a thorny problem. Rapid construction of accurate and effective tool wear predictive models with regard to various titanium alloys is indispensable for promoting the development of intelligent manufacturing. This paper presents a novel WOA-SVM model that integrates Support Vector Machines (SVM) and Whale Optimization Algorithm (WOA), which is utilized for accurate estimation of the tool wear in end-milling of titanium alloy Ti-6Al-4V under variable cutting conditions. The signal features in three domains are extracted from the original cutting forces and constitute the "Complete features" which are adopted as the monitoring features. Besides, Neighborhood Preserving Embedding (NPE) is utilized to fuse the monitoring features and realize dimension reduction, which aims at improving the modeling efficiency of the novel WOA-SVM model. The experimental results show that, under the premise of guaranteeing prediction accuracy, the utilization of NPE reduces the modeling time-consumption of WOA-SVM by more than 90%. In comparison with PSO-SVM and GSA-SVM, WOA-SVM takes on comparable prediction accuracy and can reduce the modeling time-consumption by more than 30% in most cases. Moreover, the WOA-SVM model has better prediction accuracy and stability than other classical methods, such as k-NN, FFNN, LDA, QDA and CART. Therefore, the combination of NPE and WOA-SVM provides a guarantee for rapidly constructing accurate tool wear predictive models in machining of titanium alloys.

Deep Neural Networks (DNNs) have progressed significantly in recent years. Novel DNN methods allow tasks such as image and speech recognition to be conducted easily and efficiently, compared with previous methods that needed to search for valid feature values or algorithms. However, DNN computations typically consume a significant amount of time and high-performance computing resources. To facilitate high-speed object recognition, this article introduces a Deep Convolutional Neural Network (DCNN) accelerator based on a field-programmable gate array (FPGA). Our hardware takes full advantage of the characteristics of convolutional calculation; this allowed us to implement all DCNN layers, from image input to classification, in a single chip. In particular, the dateflow from input to classification is uninterrupted and paralleled. As a result, our implementation achieved a speed of 409.62 giga-operations per second (GOPS), which is approximately twice as fast as the latest reported result. Furthermore, we used the same architecture to implement a Recurrent Convolutional Neural Network (RCNN), which can, in theory, provide better recognition accuracy.