It has been proved that surface integrity alteration induced by machining process has a profound influence on the performance of a component. As a widely used processing technology, milling technology can process parts of different quality grades according to the processing conditions. The different cutting conditions will directly affect the surface state of the machined parts (surface texture, surface morphology, surface residual stress, etc.) and affect the final performance of the workpiece. Therefore, it is of great significance to reveal the mapping relationship between working conditions, surface integrity, and parts performance in milling process for the rational selection of cutting conditions. The effects of cutting parameters such as cutting speed, feed speed, cutting depth, and tool wear on the machined surface integrity during milling are emphatically reviewed. At the same time, the relationship between the machined surface integrity and the performance of parts is also revealed. Furthermore, problems that exist in the study of surface integrity and workpiece performance in milling process are pointed out and we also suggest that more research should be conducted in this area in future.

The occurrence of chatter in the machining process accelerates tool wear and breakage, reduces the service life of tools and machine tools and the surface accuracy of workpieces. Therefore, how to quickly and accurately detect chatter and adjust process parameters to prevent chatter has become a research hotspot today. This article proposes a new method to detect the machining state in the milling process by using the sensor signal sensitive feature data set and the Mahalanobis-Taguchi System. First, a method for extracting the comprehensive characteristics of nonlinear time-domain signals in the cutting process is proposed. This method can realize the dimensionality reduction of the time-domain data features. Then, time-frequency domain methods such as variable mode decomposition energy entropy, multi-scale power spectrum entropy and multi-scale displacement entropy are used to process the processed signals collected by multiple sensors to obtain the characteristic data set related to flutter. Take the feature data set as the measurement scale to participate in the construction of the Mahalanobis-Taguchi System classifier. Using the experimental data of milling titanium alloy thin-walled parts with end mills, the Mahalanobis space of cutting chatter was constructed, and the chatter detection system was verified. It is found that this method can accurately detect the cutting processing state. The research results can lay the foundation for advancing the industrialization of intelligent cutting processing.

Milling is a kind of interrupted cutting. When the tool cuts into the workpiece, it is often accompanied by instantaneous impact, which results in impact vibration of the milling system. Meanwhile, tool wear will occur gradually on flank face with the cutting progress. The impact vibration and tool wear affect the morphological characteristics of machined surfaces. In the present work, the instantaneous impact force is obtained by introducing the italic impact model of single degree of freedom, and the free vibration in the x and y directions under the impact force is obtained by combining the damped vibration equation. The cutting vibration in the x and y directions is obtained by solving the dynamic equation of the milling system with the fourth-order Runge–Kutta method. The equation of the cutting edge is modified according to the tool flank wear, and the machined surface topography considering the dynamic characteristics of cutting system and tool flank wear is obtained by combining the Z-MAP algorithm. The verification milling experiment was carried out on the hardened steel Cr12MoV workpiece. The simulation results are in good agreement with the experimental results. The research results have important guiding significance for the reasonable selection of processing parameters in actual production.

Internet of Things (IoT) has brought changes in many fields by joining physical space with the cyber space. The IoT devices are becoming increasingly complex. With the rapid deployment of cameras, tasks in IoT like visual information are more important, but IoT devices have limited computing resources, including power, computing ability, storage, etc. Some tasks that might be perfectly normal to perform on a computer would be rather challenging on an IoT device. Therefore, how to maintain acceptable performance while minimizing resources is becoming a more consequential part in IoT. In this article, we aim to solve the problem of object detection and tracking in IoT while minimizing resources. The traditional algorithms need to use a convolutional neural network (CNN) to identify different objects in each frame, and then determine the tracking target from identified objects, which typically requires a lot of computing resources. By incorporating spatial attention, and multidomain network, we proposed a novel algorithm named as spatial attention powered multidomain network (SA-MDNet). By adding the spatial attention mechanism to the original MDNet model, and using multiclass cross-entropy loss, we are able to distinguish the background and the target in different video sequences effectively and efficiently. This novel algorithm achieves similar performance on the OTB 50/100/2013 data sets compared to several state-of-art models, while uses only a fraction of the memory compared to MDNet.