Computing large deviation prefactors of stochastic dynamical systems based on machine learning

We present a large deviation theory that characterizes the exponential estimate for rare events in stochastic dynamical systems in the limit of weak noise.We aim to consider a next-to-leading-order approximation for more accurate calculation of the mean exit time by computing large deviation prefactors with the aid of machine learning.More specifically,we design a neural network framework to compute quasipotential,most probable paths and prefactors based on the orthogonal decomposition of a vector field.We corroborate the higher effectiveness and accuracy of our algorithm with two toy models.Numerical experiments demonstrate its powerful functionality in exploring the internal mechanism of rare events triggered by weak random fluctuations.

Self-adaptive large neighborhood search algorithm for parallel machine scheduling problems

A self-adaptive large neighborhood search method for scheduling n jobs on m non-identical parallel machines with mul- tiple time windows is presented. The problems＇ another feature lies in oversubscription, namely not all jobs can be scheduled within specified scheduling horizons due to the limited machine capacity. The objective is thus to maximize the overall profits of processed jobs while respecting machine constraints. A first-in- first-out heuristic is applied to find an initial solution, and then a large neighborhood search procedure is employed to relax and re- optimize cumbersome solutions. A machine learning mechanism is also introduced to converge on the most efficient neighborhoods for the problem. Extensive computational results are presented based on data from an application involving the daily observation scheduling of a fleet of earth observing satellites. The method rapidly solves most problem instances to optimal or near optimal and shows a robust performance in sensitive analysis.

Trend Prediction Method Based on the Largest Lyapunov Exponent for Large Rotating Machine Equipments

In order to predict electromechanical equipments＇ nonlinear and non-stationary condition effectively, max Lyapunov exponent is introduced to the fault trend prediction of large rotating mechanical equipments based on chaos theory. The predict method of chaos time series and two methods of proposing f and F are dis- cussed. The arithmetic of max prediction time of chaos time series is provided. Aiming at the key part of large rotating mechanical equipments-bearing, used this prediction method the simulation experiment is carried out. The result shows that this method has excellent performance for condition trend prediction.

Research on the floating performance of a novel large caliber machine gun based on the floating principle with complicated boundary conditions

In this paper,a novel large caliber machine gun was taken as the research object to analyze the floating technique based on the principle of fixed-point constraint and secondary counter-recoil.A rigid-flexible coupling multi-body dynamic model of the large caliber machine gun with muzzle brake based on floating principle was established,in which the influence of soil and human body was taken into account.The dynamic simulation was conducted and then the results were compared with the corresponding experimental data The dynamic characteristics of the machine gun with or without floating technique were analyzed to indicate the influence of floating technique upon the performance of the gun.Furthermore,the rigid-flexible coupling dynamic models with five different firing angles was constructed to study the influence caused by the angles.The results indicated that the floating mechanism could reduce the recoil effectively and improve the operational performance of this novel large caliber machine gun.

An automatic arc welding machine for saddle joint seams on large diameter cylinders

This paper deals with the structure, components, characteristics and work principle of a newly developed automatic arc welding machine for saddle joint seams on large diameter cylinders. The equations for designing the geometry and dimensions of the cam controlling the moving locus of the welding torch have been derived. This welding machine has successfully been used in automatic welding saddle joint seams on boiler drums with good results and low cost.

A Hierarchical Clustering and Fixed-Layer Local Learning Based Support Vector Machine Algorithm for Large Scale Classification Problems

It is a challenging topic to develop an efficient algorithm for large scale classification problems in many applications of machine learning. In this paper, a hierarchical clustering and fixed- layer local learning （HCFLL） based support vector machine（SVM） algorithm is proposed to deal with this problem. Firstly, HCFLL hierarchically dusters a given dataset into a modified clustering feature tree based on the ideas of unsupervised clustering and supervised clustering. Then it locally trains SVM on each labeled subtree at a fixed-layer of the tree. The experimental results show that compared with the existing popular algorithms such as core vector machine and decision.tree support vector machine, HCFLL can significantly improve the training and testing speeds with comparable testing accuracy.

A Multilevel Design Method of Large-scale Machine System Oriented Network Environment

The design of large-scale machine system is a very complex problem.These design problems usually have a lot of design variables and constraints so that they are difficult to be solved rapidly and efficiently by using conventional methods.In this paper,a new multilevel design method oriented network environment is proposed,which maps the design problem of large-scale machine system into a hypergraph with degree of linking strength (DLS) between vertices.By decomposition of hypergraph,this method can divide the complex design problem into some small and simple subproblems that can be solved concurrently in a network.

Implementation of Digital Classroom State System for Teachers and Students Based on Large Models

Deep learning has become a hot field of artificial intelligence,and the deep learning large model framework has become a bridgehead for the active layout of Chinese and foreign technology companies.Large models play a significant role in the application field,greatly improving the efficiency of training and optimization,and contributing to the landing of many innovative artificial intelligence tools.Based on the Chinese PaddlePaddle large model framework,an application system is designed in combination with the intelligent classroom teaching scenario,which uses machine vision algorithms to distinguish and present teachers’and students’behaviors,that is,the digitization and multi-classification scheme of class character states.After having digital data,data analysis can be carried out to evaluate the class status of teachers and students,and the traditional subjective judgment such as peacetime grades and teaching ability can be upgraded to the objective judgment of artificial intelligence.

Large scale classification with local diversity AdaBoost SVM algorithm

Local diversity AdaBoost support vector machine（LDAB-SVM） is proposed for large scale dataset classification problems.The training dataset is split into several blocks firstly, and some models based on these dataset blocks are built.In order to obtain a better performance, AdaBoost is used in each model building.In the boosting iteration step, the component learners which have higher diversity and accuracy are collected via the kernel parameters adjusting.Then the local models via voting method are integrated.The experimental study shows that LDAB-SVM can deal with large scale dataset efficiently without reducing the performance of the classifier.

RandWPSO-LSSVM optimization feedback method for large underground cavern and its engineering applications

According to the characteristics of large underground caverns, by using the safety factor of surrounding rock mass point as the control standard of cavern stability, RandWPSO-LSSVM optimization feedback method and flow process of large underground cavern anchor parameters were established. By applying the optimization feedback method to actual project, the best anchor parameters of large surge shaft five-tunnel area underground cavern of the Nuozhadu hydropower station were obtained through optimization. The results show that the predicted effect of LSSVM prediction model obtained through RandWPSO optimization is good, reasonable and reliable. Combination of the best anchor parameters obtained is 114131312, that is, the locked anchor bar spacing is 1 m x 1 m, pre-stress is 100 kN, elevation 580.45-586.50 m section anchor bar diameter is 36.00 mm, length is 4.50 m, spacing is 1.5 m × 2.5 m; anchor bar diameter at the five-tunnel area side wall is 25.00 mm, length is 7.50 m, spacing is 1 m× 1.5 m, and the shotcrete thickness is 0.15 m. The feedback analyses show that the optimization feedback method of large underground cavern anchor parameters is reasonable and reliable, which has important guiding significance for ensuring the stability of large underground caverns and for saving project investment.

Boundary fluid constraints during electrochemical jet machining of large size emerging titanium alloy aerospace parts in gas–liquid flows:Experimental and numerical simulation

Large size titanium alloy parts are widely used in aerospace.However,they are difficult to manufacture using mechanical cutting technology because of severe tool wear.Electrochemical jet machining is a promising technology to achieve high efficiency,because it has high machining flexibility and no machining tool wear.However,reports on the macro electrochemical jet machining of large size titanium alloy parts are very scarce,because it is difficult to achieve effective constraint of the flow field in macro electrochemical jet machining.In addition,titanium alloy is very sensitive to fluctuation of the flow field,and a turbulent flow field would lead to serious stray corrosion.This paper reports a series of investigations of the electrochemical jet machining of titanium alloy parts.Based on the flow analysis and experiments,the machining flow field was effectively constrained.TB6 titanium alloy part with a perimeter of one meter was machined.The machined surface was smooth with no obvious machining defects.The machining process was particularly stable with no obvious spark discharge.The research provides a reference for the application of electrochemical jet machining technology to achieve large allowance material removal in the machining of large titanium alloy parts.

Key Techniques of High-voltage and Large-capacity Series Hybrid Active Power Filters

基于基波磁通补偿的串联混合型有源电力滤波器（active power filter,APF）应用于高电压、大容量的谐波抑制场合时,受变压器励磁支路谐波电压的影响,逆变器不能等效为基波电流源,其输出电流将含有大量的谐波,从而影响滤波效果。以逆变器为核心,推导出在励磁支路谐波压降影响下的串联变压器的谐波等效阻抗。并以此为基础,从理论上分析励磁电感和变比对串联变压器谐波等效阻抗和APF滤波效果的影响。仿真结果验证了理论分析的正确性。最后,针对广东某厂10kV、1MVA电力负荷,研制一套基于基波磁通补偿的串联混合型有源滤波器工程样机,取得非常好的滤波效果。

Error Analysis for High-precision 7m Laser Measuring Machine

This paper introduces a high precision 7m laser measuring instrument developedby the anthors and its operating principle,and systematically analyses the errors havinginfluence on the performance of the measuring instrument.Error analysis and actualverification indicate that all the characteristics reached or exceeded the original designspecifications.

Study on intelligent digital welding machine with a self-learning function

A design idea was proposed that it was about intelligent digital welding machine with self-learning and self- regulation functions. The overall design scheme of software and hardware was provided. It was introduced that a parameter self-learning algorithm was based on large-step calibration and partial Newton interpolation. Furthermore, experimental verification was carried out with different welding technologies. The results show that weld bead is pegrect. Therefore, good welding quality and stability are obtained, and intelligent regulation is realized by parameters self-learning.

Efficient machine learning model for settlement prediction of large diameter helical pile in c—Φsoil

Machine learning is frequently used in various geotechnical applications nowadays.This study presents a statistics and machine learning model for settlement prediction of helical piles that relates compressive service load and soil parameters as a group with the pile parameters.Machine learning algorithms such as Decision Trees,Random Forests,AdaBoost,and Artificial Neural Networks(ANN)were used to develop the predictive models.The models were validated using cross-validation techniques and tested on an independent dataset to assess their accuracy and generalizability.Numerical investigation is used here to supplement the field data by simulating various soil conditions and pile geometries that have not been tested in the field.This study compiled numerical results of 3600 models.As the models are well-calibrated and validated,the data from these models can be reasonably assumed to simulate the ground situation.At the end of this study,a comparative analysis of statistic learning and machine learning(ML)was done using the field axial load tests database and numerical investigation on helical piles.It is observed that ML models like Decision Trees and Random Forests provided the better model with R-squared values of 0.92 and 0.96,respectively,for large diameters.The authors believe this study will permit engineers and state agencies to understand this prediction model’s efficacy better,resulting in a more resilient approach to designing large-diameter helical piles for the compressive load.

Prediction of dynamic recrystallization behavior of SAE52100 large section bearing steel based on machine learning

This paper investigates the dynamic recrystallization characteristics of SAE52100 large section bearing steel under hot compression,focusing on both the center and surface.Using data from thermal simulation experiments the physical models were developed.Four machine learning algorithms including support vector regression,knearest neighbors,random forest,and extreme gradient boosting were then employed to develop dynamic recrystallization prediction models based on the experimental data and inferred values from the physical model.The results show that the machine learning methods provide a better numerical description of the model,provided these are fed with extensive data.To enhance the scope of application,we obtained data from the dynamic recrystallization models for both the center and surface of SAE52100 steel in the as-cast state,as well as extrapolated values from the literature regarding the hot-rolled condition.When the SHAP method was introduced to reveal the mechanism of the influence of each input feature on the prediction results of the machine learning model,it was found that the test results of the Cr element did not match the theory,mainly because of the small scale of Cr elemental data and the strong dependence on grain size and secondary dendrite spacing.

Research on Safety Risk Assessment Method for Large Scale Field Operation Project

By applying man-machine-environment system engineering theory, safety risks on large scale field operation project have been evaluated in this article. The factors concerning with the man, machine and environment in system were proposed separately. The value for lowest indexs was determined by decision-making of expert group. The weights were calculated based on AHP, and then safety risk assessment in different layers was made. The results show that the assessment method is reasonable, and it is significant for large scale field operation project safety managerment.

超大规模集成电路布图规划方法研究综述

综述超大规模集成电路(VLSI)布图规划方法,探讨布图规划在集成电路设计中的重要性,以及其对芯片面积、互连线长和设计周期的影响.首先,回顾集成电路技术的发展历程,强调布图规划在确定模块位置、尺寸和旋转角度中的作用.其次,详细介绍4类主要的VLSI布图规划方法:直观构造方法、分析法、迭代法和基于机器学习的方法.再次,讨论两个VLSI设计领域中常用的基准数据集MCNC和GSRC对测试和评估布图设计方法的重要性.最后,总结布图规划领域的研究进展,并指出未来的研究方向.

大模型时代下的汉语自然语言处理研究与探索

自然语言处理是实现人机交互的关键步骤,而汉语自然语言处理(Chinese natural language processing,CNLP)是其中的重要组成部分。随着大模型技术的发展,CNLP进入了一个新的阶段,这些汉语大模型具备更强的泛化能力和更快的任务适应性。然而,相较于英语大模型,汉语大模型在逻辑推理和文本理解能力方面仍存在不足。介绍了图神经网络在特定CNLP任务中的优势,进行了量子机器学习在CNLP发展潜力的调查。总结了大模型的基本原理和技术架构,详细整理了大模型评测任务的典型数据集和模型评价指标,评估比较了当前主流的大模型在CNLP任务中的效果。分析了当前CNLP存在的挑战,并对CNLP任务的未来研究方向进行了展望,希望能帮助解决当前CNLP存在的挑战,同时为新方法的提出提供了一定的参考。

大规格滚齿工件安装误差分析与补偿策略研究

大规格滚齿加工精度在齿轮制造领域仍是薄弱部分,工件作为成型齿轮载体,在加工过程中的安装精度直接影响齿轮精度。针对大规格滚齿工件安装误差对齿轮齿面映射关系,基于齿面拓扑结构,对工件偏心误差、倾斜误差及工件椭圆度误差进行定值分析,通过实际加工齿轮精度进行验证,对实际加工中做出有效的指导。结合实际工件安装过程,提出对偏心误差在X方向补偿策略,基于Vericut软件进行仿真加工验证,证明提出的补偿策略可行,为实际加工奠定了理论基础,可有效地减少工件安装调整时间,提高滚齿加工效率。