Search

The problems of insufficient recognition accuracy, poor real‐time performance and lack of consideration of actual working conditions in the process of intelligent construction of coal mines make this technology still in the research stage and not applied in practical engineering. The purpose of this paper is to establish an accurate and real‐time recognition model, which can quickly distinguish the vibration acceleration signals of coal and gangue under the influence of external factors such as impact position, velocity, and direction by using the different physical properties of coal and gangue particles. Therefore, the accuracy and real‐time of coal gangue recognition model established by different convolutional neural networks (CNN) structures and different position signal input are studied. First, to meet the real‐time requirements, an original CNN recognition model composed of single convolution layer and single pooling layer is established, and the data collected by seven sensors are input in the form of two‐dimensional matrix. However, the stability of the training and test results is insufficient. To solve this problem, once improved CNN (OI‐CNN) recognition model with multiconvolution layers and multipooling layers is built by deepening the network. The experimental results show that the stability and accuracy are improved, but the real‐time performance is poor. Furthermore, through parameter adjustment, the OI‐CNN is changed to the twice improved CNN (TI‐CNN), and the sensor data at different positions are input in the form of one‐dimensional vectors. The results show that the accuracy and real‐time performance of the TI‐CNN coal gangue recognition model are further improved. Finally, according to the research purpose of this paper, the weights of CNN indexes are given, and a multi‐index comprehensive evaluation system (MICES) is established. With the original CNN recognition model as the control, the OI‐CNN recognition model and the TI‐CNN recognition model at different positions are quantitatively compared to obtain the comprehensive evaluation scores of each model. The results show that the MICES of the coal gangue recognition model established based on the TI‐CNN structure and the data input of a single position sensor is the highest, while the sensor position has little effect on the recognition results. [ABSTRACT FROM AUTHOR]

Compared with the forward design method through the control of geometric parameters and material types, the inverse design method based on the target stress‐strain curve is helpful for the discovery of new structures. This study proposes an optimization strategy for mechanical metamaterials based on a genetic algorithm and establishes a topology optimization method for energy‐absorbing structures with the desired stress‐strain curves. A series of structural mutation algorithms and design‐domain‐independent mesh generation method are developed to improve the efficiency of finite element analysis and optimization iteration. The algorithm realizes the design of ideal energy‐absorbing structures, which are verified by additive manufacturing and experimental characterization. The error between the stress‐strain curve of the designed structure and the target curve is less than 5%, and the densification strain reaches 0.6. Furthermore, special attention is paid to passive pedestrian protection and occupant protection, and a reasonable solution is given through the design of a multiplatform energy‐absorbing structure. The proposed topology optimization framework provides a new solution path for the elastic‐plastic large deformation problem that is unable to be resolved by using classical gradient algorithms or genetic algorithms, and simplifies the design process of energy‐absorbing mechanical metamaterials. [ABSTRACT FROM AUTHOR]

In the process of rock bolt support for the roadway with floor heave, the rock bolt cannot reach the bottom of the borehole smoothly due to the influence of the collapse gravels around the borehole. In order to solve the problem of difficult rock bolt installation, the auxiliary installation device of rock bolt drilling was innovatively designed. At the same time, a new method of auxiliary bolt installation was put forward, in which a bit was installed at the bottom of the bolt to assist the bolt drilling. The drilling process of the bit was simulated by the co‐simulation of discrete element method (DEM) and multibody dynamics method (MBD). The axial resistance of the bit and the change law of the particles movement were studied under different motion parameters and structural parameters. It was found that the drilling performance of bit was directly related to the motion parameters and structure of bit. And the selection of gravel parameters in DEM was verified by experiments. The research results can provide technical guidance for bit structure design and the selection of motion parameters of bolt drilling auxiliary installation device, and can effectively improve the rock bolt installation efficiency. [ABSTRACT FROM AUTHOR]

Due to its high thermal sensitivity, a power lithium‐ion battery for vehicles requires an efficient cooling system to ensure safety and good performance. Excellent heat dissipation capacity enables the liquid cold plate cooling system to have better application prospects. However, all existing cold plates improve their cooling capacity by increasing the complexity of their structure. Therefore, directly opposite inlet and outlet cavity cold plate cooling systems with simple structures are established. Two kinds of cavity cold plates (Model I and Model L) with different inlet and outlet positions are analyzed using the numerical simulation method. The effects of inlet and outlet sizes, coolant mass flow rate (qm), and inlet and outlet positions on the temperature field as well as the cold plate pressure drop are studied. According to the results, maximum temperatures of batteries appear at four corners of cavity cold plates, which are lower than 35 °C. The cooling capacity and temperature uniformity of Model I cooling systems are better than those of Model L. However, the heat dissipation capacity of Model L is more sensitive to qm than that of Model I. Pressure drop of Model L is smaller. This method meets the heat dissipation of vehicle pouch lithium‐ion batteries. [ABSTRACT FROM AUTHOR]

The cold plate cooling system has become one of the most practical and promising Li‐ion battery thermal management systems for electric vehicles. The existing cold plate has complex structure with high production cost, and the energy consumption is relatively high. In this paper, a detailed optimization study of cavity cold plate is carried out. The heat generation data of the pouch Li‐ion batteries were obtained through experiments, and the data were applied to the finite element method simulation of the cavity cold plate thermal management system. The effects of cavity cold plate thickness (d1), cold plate inlet and outlet width (d2), and inlet coolant mass flow rate on battery temperature and cold plate pressure drop were discussed. The results showed that the optimization allowed the cavity cold plate to control the battery maximum temperature within 40°C and temperature difference within 5°C. Under the same volume of cold plates, the average pressure drop reduction rates of models where Δd (the difference between d1 and d2) is 1 mm are 65% higher than that of the models where d2 is 1 mm. This study has practical significance for improving the design efficiency of cavity cold plate. [ABSTRACT FROM AUTHOR]

This paper is written to show a new detection method for integrity attack on the measurements. It is proved that the normality of the residual error from Kalman filter is equivalent to that of the measurement. Our method utilizes this property and it could not only detect the distribution changes at current time, but also detect the its time correlations. Overall, it is an improved detection method for a wider range of attacks. [ABSTRACT FROM AUTHOR]