Abstract:

Abstract: Accurate understanding of the temperature distribution pattern of overhead conductor cross section can effectively predict the maximum ampacity of current line, and provide basis for real-time dynamic capacity-increase.This paper taking the commonly used conductor LGJ300/50 and LGJ400/35 as examples, based on the conductor steady-state heat balance equation and the IEEE 738-2012 standard, considering the air gap within the conductor and the actual contact between the strands, using the ANSYS software, the radial temperature distribution of overhead conductors and the influence of radial temperature difference on the allowable current carrying capacity of conductors are analyzed. The results show that there is a temperature field along the radial direction when the conductor is running. The temperature difference can reach 4℃~10 ℃, and it has a great influence on the allowable ampacity of the conductor.The definition of allowable temperature limit of conductor has a great influence on the allowable ampacity of the conductor. It is suggested that the allowable temperature limit shall be understood as the average temperature of the conductor.

Abstract: The drying process of animal transport vehicle drying room generally includes three stages: a heating period, a high temperature evaporation period, and a high temperature drying period. Be aimed at the phenomenon of high energy consumption in the heating period and undesirable flow field of exiting large-scale truck drying room, the three-dimensional simplified physical model of drying room was established, and the simulation software Airpak was used as the research method to optimize the structure design and process parameters of the drying room. Firstly, the feasibility of simulation research method was tested by field test and theoretical analysis, and the suitable turbulence calculation model was screened out. Then, the influence factors of the flow field were combined into different optimization schemes , and a reasonable structure design pattern was obtained according to the simulation. Finally, the process parameters were optimized, and the theoretical energy consumption calculation shows that the cost of the optimized heating energy consumption by once is decreased by 13.19 yuan

Abstract: In order to improve the steering stability of commercial vehicles, a commercial vehicle simulation model and a double-shift closed-loop test simulation environment were established by Trucksim. The dynamic simulation experiments of the vehicle were carried out by changing the structural parameters of the vehicle. The influence of different structural parameters on the handling stability of the vehicle is analyzed in detail. Combined with the objective quantitative evaluation index of vehicle handling stability, the influence of commercial vehicle structural parameters on vehicle handling stability is quantitatively analyzed. The results show that: Increasing the loading quality, the values of various hazard indicators and comprehensive objective evaluation indicators become higher, indicating that the stability is worse. On the contrary, with the increase of the wheelbase, the indicators and comprehensive evaluation indicators are decreasing, and the steering stability of commercial vehicles is getting better.

Abstract: A new meshfree numerical method, which is known as general particle dynamics (GPD) , is introduced to investigate the process of rock fragmentation by TBM cutter. The effects of inclination angle and length of intermittent joint on the pattern and efficiency of rock fragmentation have been studied. T he conclusions are summarized as follows : ①The initiation patterns of crack at intermittent joint are classified into three types: the crack is initiated at the centre of joint and propagates upward s the crack is initiated from the lower tip of joint and propagates downward s the crack is initiated from the upper tip of joint and propagates upward s ②The length of median cracks and the depth of rock fragmentation are related to the endpoints of intermittent joint. When the location of endpoints is more close to the loading surface and loading point, the madian cracks and the depth of rock fragmentation are more obviously restrain.③The depth of rock fragmentation decreases with increasing the intermittent joint length, and the depth of rock fragmentation remains constant when the length of joint is greater than a critical value.④Relationship between cutter cut rate and the length of joint can be expressed by ，which P75°

Abstract: To evaluate the multiaxial fatigue of U-rib to deck welded joint, the main stress component was defined as the normal stress with maximum amplitude along coordinate axes. The stress state under uniaxial and multiaxial fatigue was compared based on elastic mechanics, and the deviation between the maximum absolute principle stress and the main stress component was proposed as the basis for evaluating the multiaxial fatigue. Then segment model of steel bridge deck and submodel of joint detail were established. The deformation and stress state of welded joint under multiaxial fatigue were evaluated. In order to quantify the difference between uniaxial and multiaxial fatigue life assessment, the fatigue life ratio was defined, and the relationship between and was deduced theoretically, which was verified by experiment and finite element analysis. The result shows that when it’s under uniaxial load, the maximum absolute principal stress is equal to the main stress component. There is a deviation between the two kinds of stresses under multiaxial load and the greater the deviation, the more significant the multiaxial fatigue effect is. The effect of multiaxial fatigue becomes more significant when the load center deviates from the weld position, and the multiaxial stress state of welded joint located at the diaphragm is more obvious. is proportional to , which provides a reference for multiaxial fatigue life assessment based on uniaxial fatigue assessment

Abstract: Dynamic matrix predictive control (DMC) is a common method for process control of linear systems. Its control effect is greatly affected by the parameters of its control weighting matrix. Aiming at the off-line parameter adjustment of parameter of control weighting matrix of DMC algorithm, a method of optimizing DMC is presented in this paper and fitness function based on input and output parameters of control system is designed . With a single-joint manipulator as the controlled object, a DMC control system is designed to sample the unit step response of the controlled object and adjust the parameters offline by genetic algorithm. The parameters of the system and the genetic algorithm are verified by simulation then . The results show that the parameters of control weighting matrix of DMC algorithm with better output can be obtained quickly and accurately after optimized using genetic algorithm, which is convenient to use DMC for manipulator control

Abstract: Non-dominated Sorting Genetic Algorithm II （NSGA-II） is a classical multi-objective optimization algorithm. The strategy of tournament selection employed in NSGA-II may produce a large amount of repeated individuals, and thus decreases the diversity of population and the overall performance. To tackle this problem, this paper proposed NSGA-II based on Dimensionality Perturbation. Firstly, perturbation parameter is introduced, and then it is further used to modify each dimensionality of the parent individuals to do crossover operator. After that, the modified parent individuals do the crossover operator as usual to avoid generⅡating the repeated offspring individuals. To verify the proposed algorithm, ZDT test suit is employed as benchmark problems. Compared to the state-of-art algorithms, the proposed algorithm is capable of effectively improving the performance of NSGA-II, thus demonstrating the effectiveness of the proposed strategy.

Abstract: When Principal Component Analysis (PCA) is applied to process monitoring, improper component selection method will cause variation characteristics to be dispersed or submerged, thus affecting monitoring performance. In order to solve this problem, this paper proposes an adaptive selection method of components and applies it to process monitoring, called Adaptive Principal Component Analysis (APCA). The application of adaptive principal components to process monitoring mainly includes three steps: 1 ) firstly, calculating the similarity of each component based on the load matrix through Euclidean distance during offline modeling, and selecting components with high similarity to each component to form multiple molecular spaces 2 ) Secondly, during on-line monitoring, the variation probability of each component is calculated by kernel density estimation based on each component of the on-line sample, and the component with the highest variation probability is selected as the characteristic component (CC) 3 ) Finally, the molecular space corresponding to CC is selected and statistics are constructed. Numerical simulation and Tennessee Eastman (TE) process prove the effectiveness of the proposed APCA

Abstract: Feature selection is a key issue in data mining and machine learning . The accuracy and generalization performance of a classifier are affected by the result of feature selection significantly. However, feature selection is a challenging task due mainly to the large search space. A variety of methods have been applied to solve feature selection problems, where evolutionary computation (EC) techniques have recently gained much attention and shown some success. This paper first introduces the basic framework of feature selection. Then the search mechanism, subset evaluation strategy and objective number of feature selection methods based on evolutionary computation are analyzed and summarized. Finally, current issues and challenges are also discussed to identify promising areas for future research

Abstract: Sentiment analysis is a research hotspot in the field of natural language processing in recent years. However, the current deep learning model lacks the importance of studying the position of emotional words for the whole sentiment analysis in the emotional analysis of text sentences. In the sentiment semantic analysis of e-commerce commodity review data, CNN has certain advantages in extracting the structural features of the target, and can extract a variety of local features. RNN has memory function and has certain advantages in sequence feature extraction. Bidirectional Long Short-Term Memory (BLSTM) can achieve good results in extracting remote-dependent sequence semantic features. Based on BLSTM, this paper introduces a positional attention mechanism based on the combination of semantic role labeling and location in the food field. The distance-related sequence semantic feature extraction is realized, and the sentiment semantic classification of sequence semantic features is realized by CNN, and a food comment sentiment analysis model based on BLSTM and positional attention mechanism is constructed. Experimental results show that the model designed in this paper It has achieved good results in emotional classification, and has improved the accuracy rate results compared with the previous sentiment classification model

Abstract: When single-phase grounding fault occurs in distribution network, the non-power frequency components of zero-sequence current between fault line and sound line are obviously different. In order to solve the problem that the success rate of line selection is not high when the modulus maxima polarity is used as criterion in high resistance grounding, a method of line selection based on zero sequence current non-power frequency component and support vector machine is presented in this paper. This method decomposes the zero sequence current of each line by wavelet packet transform, chooses the characteristic frequency band according to the principle of maximum energy, takes the energy and modulus maxima of different lines in the characteristic frequency band as the characteristic vector, takes the fault line label as the classification target, transforms the fault line selection int o multi-classification, and uses support vector machine to predict the fault line. A large number of training samples are obtained through simulation. K-fold cross-validation and grid search are used to optimize the param eters of support vector machine. The results on the test dataset show that the method is accurate and reliable. The correct line selection can be achieved at different grounding distances, grounding resistances and initial phase angles of faults.

Abstract: Ultra-wideband positioning has been widely used as a high-precision indoor moving object positioning tracking or navigation technology. The traditional UWB positioning model usually uses the Taylor series iterative algorithm to achieve positional solution. However, the Taylor series positioning solution has strongly dependence on the initial value. To improve the robustness and positioning accuracy of the positioning solution method, a novel ultra-wideband localization solution based on differential evolution algorithm and Taylor series iteration is proposed. Calculation method. Taking the positioning error as the optimization target, the differential evolution algorithm is used to achieve the global position of the target point. Furthermore, the optimal positioning point obtained by the differential evolution algorithm is used as the initial value, and the Taylor series iterative algorithm is used to locally optimize the positioning point to obtain more precise target positioning. Aiming at the complex indoor scene of coal mine roadway, the proposed method is used to realize the UWB positioning calculation of the excavation support mobile bracket. The experimental results show that the proposed method has higher positioning resolution accuracy than the existing positioning solution method.

Abstract: In the optimization of the operation mode of active distribution network, node power data usually comes from power prediction, and there are prediction errors and corresponding distribution characteristics, which can be described by probabilistic expression. Considering the distribution characteristics of power prediction error, taking the average of comprehensive operating costs as the objective function, the node power balance equation as an equality constraint, and the operating range of variables such as node voltage and branch power constituting inequality constraints, the operating mode of active distribution network is established. Probabilistic optimization model. By analyzing the characteristics of the optimization formula, the probability description of the second-order power flow expression is adopted, and the variance correction is taken into account in the calculation of the mean value of random variables to improve the accuracy of the mean value calculation. In solving the optimization model, according to the actual characteristics of variables, different processing methods are used for discrete variables and continuous variables, and trust region management technology is used to process continuous variables. The feasibility and practicability of the algorithm are illustrated through the calculation and analysis of a 118-node example.

Abstract: Traffic simulation was an important part of crowd simulations.It was a key point to model drivers’ psychological cognitive decision-making processes to realize a realistic traffic simulation.This paper provided a survey of traffic simulation based on traffic psychology.A detailed description of the traffic psychology and traffic simulation was presented.The traffic simulation based on traffic psychology introduced the principles, advantages and drawbacks were examined.Finally, some open research areas and possible future directions were pointed out.

Abstract: The surface modification process of 18CrNiMo7-6 gear carburized steel round bar samples by post-mixed water jet peening was studied. Under the condition of satisfying the full coverage of water jet blasting on the circumferential surface of the sample, the single factor experiment was used to study t he effect of sample rotation speed, nozzle moving speed, high pressure water jet pump pressure and number of treatments on the surface topography, surface roughness, surface residual stress and hardness of the sample material, and use super depth of field three-dimensional microscope, three-dimensional surface topography , X-ray residual stress analyzer, HV-1000 microhardness tester and so on to measure t he above results .The experimental results show that after the post-mix ed water jet, the projectile and water will bring certain erosion and wear on the surface of the sample, and the surface morphology of the sample will be changed. The surface roughness, surface residual stress and hardness of the sample decrease with the increase of the sample rotation speed and the nozzle movement speed, and increase with the increase of the pump pressure and the number of treatments when the sample rotation speed n=100r/m in, the nozzle movement speed v=50mm/min, the pump pressure P=300MPa, the number of trea tments N=1, the maximum residual stress is about -1176.25 MPa, and the maximum hardness is 64HRC, which is 6.7% higher than the original sample.

Abstract: