Showing papers in "Recent Patents on Mechanical Engineering in 2022"

Effects of strain Rate on Cutting of Duplex Stainless Steel S32760

Abstract: The essence of plastic deformation in cutting processing is the movement and proliferation of dislocations. By increasing the density of dislocations, the material’s flow stress will inevitably increase by rising the strain rate. The three regions are divided quantitatively as thermal activation stage (101-3×103), non-thermal stage (10-3-101), and dislocation damping stage (above 3×103). Analyzing the chip metallographic diagram of the cutting process, it is believed that the strain rate effect is caused by two reasons. It is divided into three areas based on the speed of growth and the control mechanism presenting a more de-tailed and vivid explanation of these three areas. Using Hopkinson pressure bar (SHPB), the strain rate effect of duplex stainless steel S32760 is studied. T The first is the greater austenite deformation caused by the austenite deformation in S32760 compared to the ferrite softening effect and the insufficient softening effect in the plastic deformation of the material. The second is the grain refinement caused by the adiabatic shear zone from the deformation zone to the transi-tion zone making it difficult for dislocations to start slipping and increasing the flow stress.

Structure Design and Performance Test of Wheat Combine Harvester Based on Numerical Modeling

Abstract: In response to the current needs for the development of large-scale wheat combine harvesters, this paper carried out the structure design and performance test of a large feed volume wheeled wheat combine harvester. Based on the characteristics of wheat plants, this paper designed a wheeled wheat combine harvester with a feed rate of 10kg/s. Subsequently, the structural parameters and design process of the main working components such as the header feeding device, the conveying device, the threshing device, the separation and cleaning device, the walking device, the cab, and the straw crushing device are elaborated. The strength of the key parts was checked by finite element simulation, and the structural parameters were optimized. The results show that the large feed volume combine harvester which designed in this paper can achieve entrainment loss rate of less than 2.39% and cleaning loss rate of less than 0.26%, significantly lower than the current 3% loss rate and there is almost no unclean and broken situation. This research provides reference for the design of large feed volume combine harvester.

Influence of tooth surface wear and nonlinear contact stiffness on dynamic responses of helical gears

Abstract: Tooth surface wear is inevitable in helical geared transmission. Consequently, the worn profile deviates from ideal involute one. As a result, the structural stiffness of worn tooth and contact stiffness of tooth-pair are both changed. This work presents an improved calculation method for structural stiffness of worn teeth by combining slicing and potential energy method, considering non-uniform distribution of wear amount along tooth surface. Then a nonlinear contact stiffness model is employed to investigate the influence of wear on contact stiffness. Meanwhile, taking wear as one kind of profile deviation, the analytical model of time-varying mesh stiffness (TVMS) of helical gear pair is derived. Furthermore, governing equations with 6 degree-of-freedom is established and influences of wear on dynamic responses are revealed. Results indicate that structural stiffness of worn teeth decreases but contact stiffness does not always keep increasing or decreasing. The fluctuation of dynamic transmission error with the nonlinear contact model is not as significant as that from constant contact stiffness model. The approach presented in this work is suitable for condition monitoring of helical gears in view of long-term service.

Fault Diagnosis of Oil -Immersed Transformer based on TSNE and IBASA-SVM

Abstract: With the rapid development of power system, oil-immersed transformers are widely used in the substation and distribution system. The faults of oil-immersed transformers are large threat to the power system. Therefore, it is significant that the faults of oil-immersed transformers can be diagnosed accurately. To accurately diagnose the faults of oil-immersed transformers through machine learning methods and swarm intelligent algorithms. To accurately diagnose the faults of oil-immersed transformers, a fault diagnosis method based on T-distributed stochastic neighbor embedding and support vector machine is proposed. The improved beetle antennae search algorithm is used to optimize the parameters of support vector machine. Firstly, the non-coding ratio method is used to obtain nine-dimensional characteristic indices. Secondly, the original nine-dimensional data are reduced to three-dimensional by T-distributed stochastic neighbor embedding. Lastly, the data after dimensionality reduction are used as the input of the support vector machine optimized by improved beetle antennae search algorithm and the fault types of transformers can be diagnosed. The accuracy rate is 94.53% and the operation time is about 1.88s. The results indicate that the method proposed by this paper is reasonable. The experimental results show that the method proposed by this paper has a high accuracy rate and low operation time. Mixed faults that are difficult to diagnose also can be diagnosed by this paper's method. In the era of big data, there is a lot of data of transformer, so the method proposed in this paper has certain engineering significance.

Hoisting-rope continuous retracting and releasing device with constant locking force and small impact

Abstract: With the continuous exploitation of shallow mineral resources, the shallow resources are increasingly exhausted. Therefore, the application of multi-rope friction machine in ultra-deep, high speed, heavy load mine will be more and more widely. The diameter and dead weight of the hoisting-rope in this heavy-duty deep well are larger, and the internal torsion and bending load are more complex, which makes the replacement of the hoisting-rope more difficult. According to the "coal mine safety regulations", the working life of hoisting-rope is not more than two years, and the hoisting-rope of friction hoist is not more than eight months in harsh environment. Although the existing hoisting-rope replacing methods are mature, there are some problems such as high labor intensity, long replacement time and low safety, which affect the mine production and are not suitable for deep mine hoisting-rope replacement operation. The purpose of this patent is to provide a new mechanism for safely and efficiently replacing the hoisting-ropes of multi-rope friction hoist. In addition, the dynamic simulation analysis of the key parameters of the mechanism is carried out, and the reasonable design suggestions are given. A new device is designed to achieve continuous retracting and releasing ropes with constant locking force and small impact, which is mainly composed by sprocket, chain, friction block, mechanism of clamping hoisting-rope and so on. The designed new mechanism can efficiently and safely replace the hoisting-rope of various hoisting equipment, and realize the continuous hoisting-rope replacement, which limits the load impact to a great extent. The mechanism is responsible for clamping and releasing the new hoisting-rope and retracting the old hoisting-rope during the whole hoisting-rope replacement process. In the condition of some hoisting-rope with large dead weight, it can also provide enough clamping force, and there will be no phenomenon of hoisting-rope sliding. The device not only realizes the synchronous replacement of the old and new hoisting-rope, but also greatly improves the replacement efficiency and safety of the hoisting-rope. The patent effectively solves the existing problems in the process of hoisting-rope replacement and greatly improves the work efficiency.

Hemispherical Surface Defect Classification of Valve Core with a Noval Semi-supervised Learning

Abstract: Background: In the industrial manufacturing process, manually labeling enough datasets is a time-consuming thing , which makes the training and deployment of defect detection models seriously hindered. Therefore, automatic defect detection and its classification is the premise of the industrial production quality. Objectives: The study is mainly talk about the detection of the Hemispherical Surface of the valve core by machine vision method. Methods: The paper put forward a noval semi-supervised algorithm to detect the Hemispherical Surface of the Valve Core. Under the condition of the lack of labeled datasets, the paper used labeled and unlabeled samples for model training. This thesis proposed, for the first time, used the Mean Teacher semi-supervised learning framework and then make changes to the model; Firstly, this paper proposed to use the Stochastic Weight Average(SWA) algorithm to update the weight of the teacher model to enhance this model’s generalization ability. Furthermore, in order to select reliable datasets and calculate the consistency loss, this study also proposed an Uncertainty Filter(UF) method. Thirdly, in the aspect of the selection hard-ware equipment, since the hemispherical surface is anisotropic, it uses a ring light source, which can light the surface from top to bottom. Results: Experimental results show that in two different conditions, the classification accuracy can both raise. For the one hand, under the condition of trainning with a small amount of labeled datasets, the proposed semi-supervised learning model can achieve a classification accuracy of 90.51% ; For another, under the condition of the semi-supervised learning mechanism and a large amount of unlabeled datasets, the accuracy raises from 93.7% to 98.1%. Conclusion: This paper uses hemispherical metal surface as the dataset for the first time, and also innovatively optimizes the semi-supervised model. On the other hand, experimental comparative analysis indicates that the model proposed in this paper is significantly better than the comparison model, which lays the basic position for the defect detection of the hemispherical surface’s metal. At the same time, the novel semi-supervised algorithm can also be used to detect other metal part’s hemispherical surfaces.

Analysis and evaluation of fatigue strength for engine bracketconsidering load characteristics

Abstract: In order to explore the load characteristics and fatigue characteristics of the engine bracket during the working process, the automobile engine bracket is taken as the research object and the force characteristics are analyzed. This paper provides a theoretical basis for the research and design of the engine support, thereby improving the reliability and durability of the engine bracket. Under cyclic loading, the fatigue characteristics are analyzed through the bench test. According to the experimental results, the dangerous points of the engine bracket are judged. According to the S-N curve cluster, the estimated range fatigue life of the engine bracket is 34236 times to 127219 times. When the load level is low, the life span changes significantly with the stress. As the load increases, when the stress level reaches a certain level, the fatigue life is less affected by the load. As the load increases, the fatigue life shows a slow decreasing trend. When the stress level is lower than the equivalent stress threshold value, the stress will not cause fatigue failure on the specimen, and the specimen has an infinite life. This paper lays a foundation for the prediction of fatigue life and the bench test of fatigue durability of the engine bracket subjected to complex and variable random loads. At the same time, the research method can also be used to estimate the fatigue life of other bearing parts.

A new design for low flange-wear railroad wheelset

Abstract: Wear of wheelsets on curves has always been a problem for rail vehicles, it is of great significance to research and develop radial components with excellent curve negotiating performance. The purpose of this paper is to study and design a wheelset with excellent curve negotiating performance to reduce wear on the flange. In addition, the dynamic simulation performance of the wheelset is studied. The wheel is divided into the flange part and the tread part, bearings are mounted between the two, allowing them to rotate at differential speeds, while the tread part maintains a rigid connection with the axle. Modeling and dynamics simulation of the wheelset are carried out by SOLIDWORKS and SIMPACK. Based on the Archard wear model, it is found that the flange wear amount of the designed wheelset is significantly reduced compared with the traditional wheelset. The results show that the structural design of the wheelset is reasonable, has good curve negotiating performance, and can greatly reduce the wear of the flange, however, there is still room for further optimization of the structural design.

Research on Vibration Damping of Tuned Mass Damper for Wheeled Ex-cavator

Abstract: When driving and working, the engine, working equipment and uneven road sur-face will cause severe vibrations to the wheeled excavator, 1which can affect efficiency and comfort. This paper discusses various patents and presents a new method of vibration reduction for excavators. The purpose of the research is to design the counterweight of the excavator as tuned mass of tuned mass damper (TMD) to reduce body vibration. The recent patents of TMD were investigated in this research. In this paper, the coun-terweight of the excavator is designed as a non-linear TMD system. The vibration models were established under driving and crushing conditions, respectively. The vibration response of the vehicle body was calculated and analyzed through MATLAB/Simulink under driving and crush-ing conditions. Finally, the damping characteristics of the TMD system were discussed. The vibration of the car body can be reduced by TMD. 2The improvement rates in ver-tical acceleration were 8.05%, 11.85% and 11.15% for the three classes of road surfaces for the driving conditions. The improvement rates of 3vertical acceleration for the three powers of crushing conditions are 16.18%, 18.32% and 23.48%, respectively. The vibration damping performance of the excavator was effectively improved by TMD in the main working conditions. The variation of body vertical acceleration with TMD parameters indicates the existence of optimal damping characteristics parameters for the TMD system at a fixed road surface and vehicle speed.

Short-term power load forecasting based on orthogonal PCA-LPP dimension reduction and IGWO-BiLSTM

Abstract: Accurate power load forecasting is of great significance in ensuring power load planning, reliability and economic operation. The traditional power load is easy to be affected by climate, environment, date type and other factors, resulting in the problem of poor forecasting accuracy. Therefore, it is necessary to study power load forecasting. Through machine learning, dimension reduction method and intelligent optimization algorithm, the accuracy of load forecasting is improved In order to fully extract load information and improve the accuracy of short-term load forecasting for campus electricity, an improved combination of orthogonal dimensionality reduction and Bilstm is proposed to optimize the hyperparameters in BiLSTM using an improved gray wolf algorithm. Firstly, using the advantages of principal component analysis (PCA) and Locality Preserving Projection (LPP) to maintain the global and local structure of the data, respectively, the Orthogonal PCA-LPP（OPCA-LPP） dimensionality reduction method is proposed to reduce the dimensionality of the original multidimensional data. Finally, the dimensionality-reduced data is used as the input of BiLSTM and optimized by the improved Gray Wolf algorithm, which can enhance the prediction capability of the model and thus achieve accurate prediction of short-term electric load. The Mae and RMSE of this paper are 1.6585 and 1.7602 respectively. The results show that the method proposed in this paper is reasonable This method is applied to power load forecasting. The comparative experimental results show that this method reduces the dimension of data input, simplifies the complexity of network input data, and improves the accuracy of load forecasting. Compared with other methods, it can effectively improve the accuracy of load forecasting, and provide a basis for formulating reasonable power grid operation mode and balanced dispatching of power grid.

Design and Analysis of an Inverted XY-3RPS Hybrid Mechanism for Polishing of Complex Surface

Abstract: An inverted XY-3-RPS hybrid mechanism was designed for applying ultraviolet-induced nano-particle colloid jet machining to polish complex surface. The hybrid mechanism has been widely used in ultraprecision polishing field for in-stalling different polishing tools on the moving platform to meet different machining requirements because of its wide working space, good dynamic performance and large bearing capacity. The main objective of this study is to establish an inverted XY-3-RPS hybrid mechanism for UV-induced nanoparticle colloid jet machining, to realize the ultra precision polishing of complex surfaces by UV-induced nanoparticle colloid jet machining. The three-dimensional model of the inverted XY-3-RPS hybrid mechanism was established, and the kinematics and dynamics were analyzed. The velocity Jacobian matrix of the inverted XY-3-RPS hybrid mechanism is derived by vector construction method and differential method, and the dexterity index under different proportional parameters is optimized and simulated. The output Jacobian matrix and stiffness matrix are obtained by using the virtual work principle, and their static analysis is carried out. Based on Lagrange dynamics theory, the dynamic mathematical model of inverted XY-3-RPS hybrid mechanism is established, and its kinematics is verified by software joint simulation. Through dynamic simulation, the variation curves of motion, force and kinetic energy of the mechanism are obtained, which provides a theoretical basis for the application of the hybrid mechanism in complex curved surface polishing. The analysis results show that it has the best dexterity index when the ratio of moving and fixed platform is 2:1. The kinematic simulation results show that the hybrid mechanism moves reliably under the given trajectory. The dynamic simulation results show that the force analysis of each kinematic pair and the kinetic energy change curve of each part change smoothly and the dynamic performance is stable under different trajectories. The parameter design and structural design of the inverted XY-3-RPS hybrid mechanism meets the requirements of ultra precision polishing of complex surfaces

A Bibliometric Analysis of the Reliability Assessment Technology Based on Accelerated Degradation

Abstract: In face of the development trend of high-end manufacturing servitization, the reliability standard of manufacturing products gradually increases. In order to accurately predict the product life cycle, the accelerated degradation evaluation technology could be applied to significantly shorten the experiment duration. As the technologies of the intelligent manufacturing and industrial big data develop, the theory of accelerated degradation evolves as well. Based on the scientific knowledge mapping, co-author network and co-existence network, 22283 pertinent articles since the year 2010 have been collected to conduct a bibliometric study. The results show that the accelerated degradation reliability assessment spans over many research fields, and achieves great development in the mathematical modeling and experiment verification. To further the study, more efforts are expected in the areas such as building effective evaluation systems and enhancing the credibility of the assessment outcomes, as more advanced sensory data and wireless communication technologies become available.

Performance Analysis of Low GWP Refrigerants R1234yf and R448A in a Small High and Low-Temperature Test Equipment

Abstract: The article presents an analysis of the feasibility of R1234yf and R448A, two new low GWP refrigerants, as alternatives to R404A in the refrigeration system of small high and lowtemperature test equipment. The physical properties of R448A and R404A are similar. Compared with R404A, the GWP of R1234yf and R448A reduced by 99.9% and 67.7%, respectively. The analysis is based on an experimental comparison of R404A with R448A and R1234yf, comparing the compressor discharge temperature, COP, cooling capacity, and the cooling rate of three refrigeration systems at different ambient temperatures. The experimental results show that the cooling capacity of R448A is better than R404A at a higher condensing temperature. When the charging volume is 230g, and the ambient temperature is 25℃, the COP of the R448A system is increased by about 24.63% compared with the R404A system.

Heat treatment of high manganese austenitic steel: STRUCTURAL AND MECHANICAL PROPERTIES

Abstract: Technological progress is based on the development of different types of materials. Among the materials most solicited, we mention metals and alloys. The development of these materials has been initiated and resulted in a wide range of metallic materials, including austenitic manganese constituting, until today, a center of interest of several research works given their wide use in the industry as well as the recent progress by observation and characterization instruments. The aim of the paper is to investigate the heat treatment conditions of high manganese austenitic steel and to determine their influence on the structure and mechanical properties. The samples were subjected to an austenitization treatment at five different temperatures: 980 °C, 1000 °C, 1020 °C, 1040 °C, and 1060 °C for 1 hour. The experimental techniques used are hardness, nanoindentation tests, optical microscopy and X-ray diffraction. Hardness and microhardness measurements were performed to determine the wear behavior of the studied steels. The results indicated that the temperature affects the microstructure, by increasing the austenitizing temperature with pronounced growth of the austenite as well as the dissolution of carbides M7C3, the nanohardness and the modulus of elasticity decreases considerably. The heat treatment of materials modifying the microstructure is closely related to the mechanical behavior of the austenitic manganese steel. Therefore, the control of structural changes by heat treatment is essential to obtain the desired properties. The established heat treatment conditions of the obtained steel can be suitable for several industrial applications.

Application of Functional Bionic Technologies on Micropumps

Abstract: Bionics applied to micropumps is the most advanced technology currently accessible. The widespread use of microfluidic transport technology in fields like drug delivery and chemical analysis has made it a current research hotspot. As a core component in the microfluidic transport process, the micropump is a key part of the breakthrough. The study aims to summarize the engineering applications of various bionic micropumps in order to serve as a resource for future research in related fields. Study the application of bionic technologies that mimic fish tail fin oscillation, female mosquito blood sucking, honeybee nectar ingestion, and plant stomatal transpiration in various micropumps by sorting out typical research results. This study examines the current state of bionic micropumps research and problems, as well as anticipates the future direction of functional bionic technology in micropumps. In this paper, we review the functional bionic technology used in micropumps and study some of the physiological processes of specific creatures from a biological perspective. We also show how effectively using bionic design can enhance the overall functionality of micropumps. However, man's knowledge of the natural world is still very limited. Functional bionics technology will shine in the area of engineering application as a result of the investigation of materials, processing technology, and biological principles.

Influence of Pitting Failure on Dynamic Performance of Herringbone Gear Transmission System Considering Friction Coefficient

Abstract: Gearboxes are used in many industrial fields. Due to uncontrollable external factors and inevitable fa-tigue damage, gearboxes are likely to fail. It has become a major research trend to collect dynamic sig-nals of gearboxes and develop effective fault diagnosis methods for gearboxes. The purpose of this paper is to study the dynamic characteristics of herringbone gear trans-mission(HGT) under different friction coefficients and pitting faults. A virtual prototype model of the system with different friction coefficients and pitting faults was established jointly with KISSsoft, SolidWorks, and ADAMS. The contact stiffness, penetration co-efficient, damping, and other factors were considered in the model. The contact force and angular accel-eration signals of the Driven gear are collected and analyzed by simulation. The increase of friction coefficient results in the increase of contact force and instantaneous angular acceleration. The modulation side frequency band on both sides of the frequency becomes dense, and the side frequency band in the frequency domain of angular acceleration becomes sparse. When pitting failure exists, all dynamic signals show fault characteristics. This work provided a theoretical basis for fault diagnosis and gear dynamics research, Due to many nonlinear factors, the fault diagnosis of the HGT system is relatively difficult. The research results can quickly diagnose the fault of the HGT system, which makes up for the shortcomings in the study of the fault diagnosis of the HGT system.

Modeling of Austenite Grain Growth Behavior for AISI 302 Stainless Steel

Abstract: Among the metals used in foundry, we find the austenitic stainless steels, which are used in several fields because of their mechanical properties, which can change during the heat treatments; for that, it is important to understand and control the growth of the austenite grains. Modeling austenite grain growth by considering the effects of heating temperature, holding time, and initial austenite grain size on austenite grain growth. In this paper, the austenite grain growth process of AISI 302 steel was studied in a temperature range of 900 to 1000 °C and a holding time of up to 360 minutes. Based on the experimental results and a combination of Arrhenius and Sellars type equations, a mathematical model of austenite grain growth was developed. From the experimental part, it was found that the increase in heating temperature caused the dissolution of carbides; therefore, the size of austenite grains grew faster, implying a higher growth rate. The prolongation of the holding time also led to the increase in the size of the austenite grains. Based on statistical indicators and a comparison between experimental and predicted results, the ability of the model to predict austenite grain growth was confirmed.

Study on Decoupling Control Strategy of Redundant Parallel Hybrid Vibration Isolation Platform

Abstract: Background:The vibration isolation platform (VIP) can greatly reduce the risk of damaging to dynamic equipment caused by external vibration interference, and provide the most stable and reliable working environment for dynamic equipment. Objective:Aiming at the problems of small vibration isolation dimension, low bearing capacity, serious motion coupling, and narrow vibration isolation bandwidth in the field of vibration isolation of dynamic load equipment, a hydraulic redundant six degrees of freedom parallel vibration isolation platform (PVIP) with active and passive composite vibration isolation support is proposed. Methods:The dynamic coupling model of active and passive hybrid vibration isolation (APHVI) of redundant PVIP is established, and the matrix diagonal decoupling control strategy and fuzzy PI control theory are combined. Analysis on passive vibration isolation performance and APHVI performance of VIP. Results:The simulation results show that the effect of APHVI based on fuzzy PI decoupling control is better than that of passive vibration isolation and matrix diagonal decoupling control. Conclusion:Fuzzy PI control can effectively attenuate more than 98 % of the disturbance, significantly improve the vibration isolation performance and decoupling effect of the platform, and expand the effective vibration isolation bandwidth.

Investigations on Force Characteristics of Orbiting Scroll in Asymmetric-suction Scroll Compressors

Abstract: Scroll refrigeration compressors are the critical equipment for the refrigeration system in air conditioners and vehicles. The asymmetric suction structure can be applied to reduce the scroll compressors' size. However, the pressure difference between the symmetric working chambers becomes larger and leads to the special force characteristics of the orbiting scroll. This paper illustrates the force characteristics of the orbiting scroll in an Asymmetric-suction Scroll Compressor (ASC) to improve its stability and reliability. The theoretical model has been established to calculate the force and moment acting on the orbiting scroll of ASC and the Symmetric-suction Scroll Compressor (SSC) based on the transient numerical simulation results. The variations of gas force and moment in ASC and SSC are displayed and compared. Their pulsation intensities are calculated and discussed. The pressure in the outer compression chamber of ASC was always higher than that in the inner compression chamber, which caused significant discharge loss. Affected by the tangential leakage flow, the radial force of the compressor fluctuated sharply. As the tangential force on the orbiting scroll segments of symmetrical working chambers in ASC led to the negative spin moment, the total average spin torque decreased by 71.3%. Still, the pulsation intensity increased by ten times. Furthermore, the direction of the spin moment reversed at 275°~355°, which indicated that the orbiting scroll impacted the Oldham ring every rotation. The noise and vibration would happen, and the Oldham ring would be damaged easily.

Influence of Solid Particles on Wellbore Parameters in Solid Fluidization Production Process

Abstract: In order to efficiently exploit the hydrate reservoir, based on the problem of large amount of sand production in the current hydrate reservoir exploration process, combined with the solid fluidization well testing and production method. A gas-liquid-solid three-phase flow model is established and hydrate decomposition is taken into consideration. The changes in parameters of wellbore pressure, gas volume fraction, liquid volume fraction, temperature and the decomposition rates of wellbore hydrate under the conditions of different rates of sand production are analyzed. The results show that with the increasing rate of sand production during the solid fluidization well testing and production, pressure of the wellbore is lifted, gas volume fraction declines, liquid volume fraction declines, and temperature of the wellbore does not change. Moreover, increasing rate of sand production also leads to the delay of the position where hydrate begins to decompose. With the decrease of hydrate saturation, pressure of the wellbore goes up, gas volume fraction is lifted, solid volume fraction rises, and decomposition rate of hydrate declines.

Design, Stress Analysis and FEA Prediction of Nutation Drive with Face Gear

Abstract: Nutation face gear transmission is a patent about a new type of transmission based on meshing between two face gears. It replaces spur gear with internal face gear to form a “face-face” meshing gear pair, and actualizes its deceleration function by combining the nutation principle, which has the advantages of both face gear and nutation drive. The purpose of this paper is to study design and manufacture of a nutation face gear reducer, so as to derive the force calculation formulas of the face gear, input shaft and bearings, calculate the contact stress of tooth surface and bending stress of tooth root, determine the basic parameters of the prototype, and analyze the processing points for the core parts of the prototype. Using the dynamic meshing force analysis method, combined with modern digital design and manufacturing methods, the design and manufacture of a nutation face gear reducer is studied. In the theoretical calculation, the maximum contact stress of the fixed side tooth surface is about 433MPa, and the average contact stress is about 345MPa; the maximum contact stress of the tooth surface on the rotating side is about 579MPa, with an average of about 502MPa, the comparison of which with the finite element analysis results verifies the theoretical calculation results. The dynamic meshing force analysis method of nutation face gear transmission is deduced and given. On the basis, the calculation of gear tooth surface transient contact stress and tooth root bending stress is completed.

Research Progress on the Human Behavior Recognition Based on Machine Learning Methods

Abstract: Machine vision has been used in the industrial automation system for a long time. It also plays a significant role in the field of human behavior recognition. Behavior recognition based on machine vision, such as object tracking, motion detection and crime recognition, greatly broadens the application field of artificial intelligence and has a good application prospect. We summarize the latest applications of various machine learning algorithms in human behavior recognition, and analyze the accuracy of various algorithms combined with data sets, so as to provide reference for researchers in related fields. By sorting out the typical research results, briefly expound on the application of machine learning in the field of behavior recognition in recent years. This review focuses on the Two Stream Network structure, TSN structure, LSTM network and C3D network. This paper analyzes the principles, advantages and disadvantages of various human behavior recognition methods, and briefly discusses the future development direction. The wide application prospect of behavior recognition and detection makes it a hot research direction in the field of computer vision, and greatly improves the accuracy of complex human motion recognition combined with deep learning. However, it still faces many difficulties, such as insufficient discrimination of violence attributes, difficult collection, verification of special action data and insufficient hardware computing resources, etc.