In face milling process, the quality of surface texture is vital for mechanical performance of workpieces. The quality of surface texture, especially for waviness, is directly affected by tool marks, a commonly observed phenomenon in face milling. However, appropriate approaches for evaluation and modeling of tool marks are absent to date. Limited to the resolution as well as the efficiency of conventional measurement instruments, the height data of tool marks is hard to be entirely obtained, leading to valuable information omission. Besides, most existing models of tool marks are established for general workpieces with regular geometry and continuous surfaces. Since the cutter-workpiece engagement mode has a significant impact on the generation of tool marks, current models could be inaccurate or invalid when dealing with workpieces with discontinuous surfaces. To overcome this shortage, a novel approach is proposed in this research, aimed at quality improvement of surface texture in face milling of workpieces with discontinuous surfaces. First, the evaluation indexes for tool marks are defined based on the recently developed high definition metrology (HDM). Second, the physical modeling of tool marks is presented, taking the face milling mechanism into account. Third, the physical-informed optimization model is developed to search for the optimal processing parameters for surface quality improvement. At last, the effectiveness of the proposed approach is verified by a face milling experiment on the engine blocks.

Aiming at the problems of low efficiency and poor accuracy in the product surface defect detection. In this paper, an online surface defects detection method based on YOLOV3 is proposed. Firstly, using lightweight network MobileNetV2 to replace the original backbone as the feature extractor to improve network speed. Then, we propose an extended feature pyramid network (EFPN) to extend the detection layer for multi-size object detection and design a novel feature fusing module (FFM) embedded in the extend layer to super-resolve features and capture more regional details. In addition, we add an IoU loss function to solve the mismatch between classification and bounding box regression. The proposed method is used to train and test on the hot rolled steel open dataset NEU-DET, which contains six typical defects of a steel surface, namely rolled-in scale, patches, crazing, pitted surface, inclusion and scratches. The experimental results show that our method achieves a satisfactory balance between performance and consumption and reaches 86.96% mAP with a speed of 80.96 FPS, which is more accurate and faster than many other algorithms and can realize real-time and high-precision inspection of product surface defects.

The increasingly serious problem of consumers returning goods on e-commerce platforms has brought high costs to the Internet economy, carbon pollution to the environment, and waste of social resources. E-commerce platforms can provide useful information to assist consumers to make rational decisions, but they are often filled with useless, repetitive, and even false excessive information, which will lead to information overload and impulsive decision-making of consumers. Most of the previous literature focuses on reverse logistics, return policy, and consumer behavior tendency, etc. From the perspective of consumers’ perception of information displayed on e-commerce platforms, there are few research endeavors on the formation mechanism of perceived information overload on consumers’ return intention. Taking perceived information overload as an independent variable and consumers’ perceived environmental effectiveness as a moderation variable, this study constructs a chain mediation model that affects consumers’ online return intention. Based on the analysis of the mediating effects of impulsive buying behavior and cognitive dissonance, this study explored the moderating mechanism of consumers’ perceived environmental effectiveness on the chain mediation model. The results show that perceived information overload has a positive influence on online return intention through impulsive buying behavior, and perceived information overload has a positive influence on online return intention through cognitive dissonance. Perceived information overload also positively affects cognitive dissonance through impulsive buying behavior and thus has a significant positive chain mediating effect on consumers’ online return intention. More importantly, this research shows that consumers’ perceived environmental effectiveness can significantly moderate the chain mediation path by reducing the positive effect of the cognitive dissonance on online return intention. On this basis, this study put forward the corresponding managerial implications from the perspectives of consumers and e-commerce platforms.

Remaining Useful Life (RUL) prediction is significant in indicating the health status of the sophisticated equipment, and it requires historical data because of its complexity. The number and complexity of such environmental parameters as vibration and temperature can cause non-linear states of data, making prediction tremendously difficult. Conventional machine learning models such as support vector machine (SVM), random forest, and back propagation neural network (BPNN), however, have limited capacity to predict accurately. In this paper, a two-phase deep-learning-model attention-convolutional forget-gate recurrent network (AM-ConvFGRNET) for RUL prediction is proposed. The first phase, forget-gate convolutional recurrent network (ConvFGRNET) is proposed based on a one-dimensional analog long short-term memory (LSTM), which removes all the gates except the forget gate and uses chrono-initialized biases. The second phase is the attention mechanism, which ensures the model to extract more specific features for generating an output, compensating the drawbacks of the FGRNET that it is a black box model and improving the interpretability. The performance and effectiveness of AM-ConvFGRNET for RUL prediction is validated by comparing it with other machine learning methods and deep learning methods on the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset and a dataset of ball screw experiment.