1136 results about "Torque sensor" patented technology

The invention discloses a face gear planetary transmission system dynamic uniform load test platform and test method, and belongs to the field of gear transmission, and the test platform comprises a rack, a drive motor, a step-up gear box, a face gear planetary transmission system, a magnetic powder brake, a torque sensor, a slip ring, a stress strain test system and the like. The face gear planetary transmission system comprises an input face gear, a planet wheel, a planet carrier, a fixed face gear and the like. According to the dynamic uniform load test, stress values at the tooth root of the face gear and the tooth root of the planetary gear are measured mainly through strain gauges, and the corresponding relation between the tooth root stress and the meshing force at the gear meshing point is obtained through finite element simulation. And calculating the dynamic uniform load coefficient according to the dynamic meshing force root-mean-square values and the average values obtained at the tooth roots of the face gear and the planetary gear. By testing and analyzing the dynamic uniform load coefficient, the load distribution characteristic of the face gear planetary transmission system can be accurately revealed, a scientific basis is provided for structural parameter optimization, meshing performance improvement and reliability design of the face gear planetary transmission system, and then accurate and high-performance design of the transmission system is achieved.

The utility model provides a double-rigid-gear harmonic speed reducer with a torque sensing function, which relates to the technical field of speed reducers and comprises a wave generator, a flexible bearing, a flexible gear, an output end rigid gear, a crossed roller bearing and a fixed end rigid gear. The crossed roller is arranged between the bearing outer ring and the output end rigid wheel, the output end rigid wheel serves as an inner ring of the crossed roller bearing, and the fixed end rigid wheel is detachably and fixedly connected with the bearing outer ring; the two end faces of the fixed end rigid wheel are each provided with a receding groove coaxial with the fixed end rigid wheel, a connecting wall is formed between the bottoms of the two receding grooves, and a plurality of strain gauges arranged in a circumferential array mode are installed at the position, close to one side of the output end rigid wheel, of the bottom of the receding groove. The elastic strain gauge is embedded in the rigid fixed end rigid wheel, so that the fixed end rigid wheel has a torque sensing function, the axial thickness of the harmonic speed reducer is not increased, and the use requirements of more occasions are met.

The utility model discloses a device for testing the service life of a gear motor, and particularly relates to the technical field of detection equipment, which comprises a torque sensor and an input transition seat. The torque sensor, the input transition seat and the load gear motor are all arranged on the workbench, the tested gear motor is fixedly installed at one end of the input transition seat, and an output shaft of the tested gear motor is fixedly connected with the input end of the input transition seat. The output end of the input transition seat is fixedly connected with the input end of a torque sensor through a first coupler, and the output end of the torque sensor is fixedly connected with a rotating shaft of a load gear motor through a second coupler. According to the utility model, the load gear motor and the input transition seat are arranged, the tested gear motor is fixed on the input transition seat and is powered by the tested gear motor, and the load gear motor is arranged at the tail end to serve as a load, so that the working environment of a conventional gear motor is simulated, and the service life of the gear motor can be conveniently tested after long-time operation of the gear motor.

The invention discloses a method for testing an electric power steering system assembly, and belongs to the technical field of automobile part testing. The technical problems that in an existing testing method, static and dynamic testing processes are separated, testing efficiency is low, and quantitative evaluation on key dynamic performance parameters is difficult are solved. According to the invention, a test tool comprising a simulation rack, a driving device, an encoder, a torque sensor and a data acquisition card is adopted, and a control and processing module automatically executes a continuous test process: firstly, performing a static assistance test on an assembly, and judging qualification; and if the test is qualified, the test is automatically switched to dynamic test, a torque command signal is sent to the assembly, an output shaft is driven to rotate forwards and backwards, a position and a feedback torque signal are collected, and dynamic response parameters such as a position dispersion error, power-assisted delay time and overshoot are calculated. The method is mainly used for comprehensive performance testing and quality evaluation of the electric power steering system assembly in the production manufacturing or maintenance after-sales link.

The invention discloses a robot joint torque control system and method, and the system comprises a joint torque sensor which is used for detecting the actual output torque of a joint; the joint driver is used for driving robot joints to move according to the control instruction; the bearing pre-tightening mechanism is used for applying pre-tightening force to the joint bearing; the multi-source environment sensing module comprises a temperature sensor used for detecting the temperature of the bearing, a vibration sensor used for detecting the mechanical vibration frequency and amplitude, and an electromagnetic interference detector used for detecting the electromagnetic interference intensity; the intelligent compensation module is integrated in the controller and comprises a thermal deformation compensation unit, the input end of the thermal deformation compensation unit is connected with the temperature sensor, and the thermal deformation compensation unit is used for generating the first torque compensation amount. According to the method, high-stability control over the robot joint torque is achieved, the influence of various kinds of interference and uncertainty on the torque control effect is reduced, the reliability under the complex working condition is remarkably improved, and the higher-precision robot joint torque control requirement is met.

The invention provides a flying robot control method and device based on force feedback and a medium, and the method comprises the steps: deploying a six-dimensional force torque sensor at an operation end effector of a flying robot, and obtaining and screening effective torque data in real time to obtain a force error signal; a compensation layer based on the Lyapunov self-adaptive law is utilized, the total disturbance is cooperatively estimated in combination with double observers, and the disturbance serves as a feed-forward quantity to be injected into an attitude controller; and calculating the adjustment amount according to the target impedance model and the force error, and generating an execution mechanism control instruction. According to the technical scheme provided by the invention, stable control of air interaction operation can be realized, and the anti-disturbance capability and interaction force control precision of the flying robot are effectively improved.

The invention discloses a suspension bridge pin shaft fork ear connecting piece load-wear fatigue test device, which comprises a lever prying force application device, a fatigue test device and a fatigue test device, comprising a lever prying support, a fork-shaped lug plate force application plate arranged at the top end of the lever prying support, and a force transmission lever arranged below the fork-shaped lug plate force application plate to drive the fork-shaped lug plate force application plate to move up and down. The torque force application device is used for providing torque, enabling the fork-shaped lug plate to be in close contact with the box girder lug plate and simulating an actual back-twist phenomenon, and comprises an upper layer mechanism and a lower layer mechanism which rotate relatively, and a high-strength torsion spring and a torque sensor which are buckled inside by the upper layer mechanism and the lower layer mechanism; the abrasion sliding device is arranged at the bottom of the lever prying support and connected with the bottom of the torque force application device, and the operation state of the fork-shaped lug plate in an actual structure is simulated, so that the fork-shaped lug plate generates back-twist abrasion damage. According to the invention, a large tonnage, namely the stress state of the connecting piece under an actual bridge load, can be fully simulated through a test, and fatigue test evaluation after wear damage is carried out on the connecting piece.

The invention relates to a multi-modal sensing fusion-based automatic correction method and system for a welding robot body, the system comprises a three-level distributed architecture of a sensing layer, an edge layer and a control layer, the sensing layer is integrated with a millimeter wave radar, a camera, a six-dimensional force / torque sensor, a welding power supply data acquisition module and an acoustic emission sensor, and multi-modal data acquisition is realized; the edge layer runs a fusion algorithm through an embedded AI computing platform carrying a GPU to complete data processing and decision making; and the control layer receives the deviation correction instruction to drive the robot to execute motion correction. The method comprises the steps of multi-modal data real-time acquisition and synchronization, data preprocessing and feature extraction, multi-source information fusion and decision making, and real-time control and execution. The problems of single sensing dimension, response delay, weak anti-interference capability and the like in the prior art are solved, the robustness, the real-time performance and the deviation correction precision of the system are improved, full-automatic intelligent welding is realized, and the method is suitable for high-precision scenes such as shipbuilding and pressure vessel welding.

The utility model discloses a brushless motor load detection device, and specifically relates to the motor load detection device technology field, the brushless motor load detection device comprises a control panel, a load assembly, a torque sensor and a limiting mechanism, the side surface of the control panel is provided with the load assembly, and one side of the load assembly far away from the control panel is provided with the torque sensor; a torque sensor is arranged on the load assembly, a limiting mechanism is placed on the side, away from the load assembly, of the torque sensor and comprises a clamping assembly, a moving assembly and a sliding assembly, the moving assembly is installed above the sliding assembly, the clamping assembly is installed above the moving assembly, and all the assemblies can be controlled and monitored in a centralized mode through a control panel; the automatic detection process and data recording are realized, and the working efficiency and the accuracy of measured data are improved.

The invention discloses a cylindrical thin-wall part thread assembly device and method, and aims to solve the problems of low efficiency, high labor intensity and uncontrollable quality of traditional manual assembly. The device comprises an enclasping and screwing mechanism, a screwing control mechanism, a size rechecking mechanism and a horizontal carrying mechanism. The enclasping and screwing mechanism is used for enclasping a first thin-wall part, driving the first thin-wall part to rotate and temporarily bearing a second thin-wall part at the same time. The tightening control mechanism achieves grabbing of the second thin-wall part, thread pre-tightening / tightening of the first thin-wall part and process parameter monitoring through a static torsion sensor, a displacement sensor and an elastic floating structure. The dimension rechecking mechanism adapts to the levelness error of the reference surface by means of an integrated floating structure of a floating conical block, and accurately detects the dimension of the relative end surface after assembly; and the horizontal carrying mechanism drives the holding and screwing mechanism to accurately move among the stations. Full-automatic assembly of the thin-wall parts is achieved, efficiency is high, quality is good, and the automatic assembly machine is suitable for automatic production of the thin-wall parts in the aerospace and aviation fields.

The high-altitude operation bolt and nut synchronous disassembling and assembling tool comprises a connecting plate, a display panel and a handle are installed on one side of the connecting plate, a disassembling and assembling mechanism is arranged on the other side of the connecting plate, and the disassembling and assembling mechanism comprises a nut disassembling and assembling assembly and a bolt disassembling and assembling assembly; according to the invention, the whole process only needs single-hand control, no additional tool assistance is needed, the risk of easy unbalance of double-hand operation during high-altitude operation is solved, and rapid disassembly and assembly of bolts and nuts are realized; the nut sleeve and the bolt sleeve both adopt detachable design and can be quickly replaced according to the specifications of bolts and nuts, so that the requirements of multi-scene operation are met; the magnetic piece in the nut sleeve can achieve auxiliary positioning, the torque sensor between the driving motor and the first gear can monitor the dismounting torque in real time, and by cutting off output of the driving motor, the risk of tool damage or bolt slipping caused by continuous overload work of equipment when the nut is aged and rusted is effectively prevented.

The invention provides an industrial robot anti-collision early warning method and system. The method comprises the following steps: environment perception and multi-source data fusion; predicting a dynamic obstacle track; robot posture real-time modeling is carried out; carrying out collision risk joint assessment; dynamically dividing early warning levels; intelligent planning of an obstacle avoidance path; dynamically compensating joint torque; multi-stage early warning collaborative response is carried out; performing iterative evaluation on the early warning effect; and self-evolving the anti-collision knowledge base. The three key technical problems in the industrial robot anti-collision field are solved, dependence on high-cost physical sensors (such as a torque sensor and a laser radar) is eliminated, collision detection of any position of the whole robot is achieved, and the cost is reduced by 60% or above. The limitation of a static obstacle model is overcome, and real-time track prediction and risk grading of dynamic targets such as moving personnel and conveying belt materials are achieved. Through multi-source data fusion and a risk probability model, the false alarm rate is reduced to 5% or below, and meanwhile it is guaranteed that the missing report rate is 0.

The invention provides an electronic control hydraulic steering system driving mode switching method, system and device and a medium, and belongs to the technical field of automatic driving control. The method comprises the following steps: constructing a kinetic model of an EHPS system corner torque sensor, constructing a sliding mode observer based on the model, and accurately calculating an estimated value of a driver hand torque by compensating rotational inertia and a damping component of a steering wheel in real time; determining an adjustment factor by using a fuzzy rule according to the vehicle speed and the corner speed, and setting a dynamic threshold by combining the maximum hand torque; judging the hand intervention state of the driver in a self-adaptive time window by comparing the estimated value of the hand torque with a dynamic threshold value; after the manual intervention is confirmed, the target current value of the power-assisted motor and the road curvature in the manual driving mode and the automatic driving mode are fused, a comprehensive target current value in smooth transition is calculated, and finally the comprehensive target current value is converted into electromagnetic torque to complete the driving mode switching. According to the invention, accurate identification of driver intervention intentions and smooth control of a mode switching process are realized.

The invention provides a mechanical arm autonomous ultrasonic scanning method for kidney examination. The method comprises the steps that a mechanical arm, an ultrasonic probe and a torque sensor are configured, a coordinate system is calibrated, and pixel scale parameters of a kidney ultrasonic image and probe contact force are obtained; based on the calibrated coordinate system, kidney region segmentation is carried out on the kidney ultrasonic image collected in real time, the kidney standard section is autonomously positioned, and kidney standard section information is generated; in combination with the kidney standard section information, the pixel scale parameters and the probe contact force, scanning paths in at least two orthogonal directions are planned, autonomous scanning is executed, and an ultrasonic image segmentation sequence covering the kidney structure is obtained; and calculating the volume and symmetry index of the kidney through image preprocessing, kidney region segmentation and three-dimensional reconstruction by using the ultrasonic image segmentation sequence. According to the method, the autonomy and accuracy of kidney ultrasonic scanning are improved.

The utility model relates to the field of tightening and locking, in particular to a tightening tool internally provided with two groups of torque sensors and a verification-free method, the tightening tool further comprises a dynamic torque sensor and a static torque sensor, a power device is arranged on the static torque sensor, and counter-acting force provided by an external source is transmitted to the power device through the static torque sensor. The power device provides torsion for the output end through the dynamic torque sensor; in order to solve the problem that the torsion is abnormal but not known, a novel detection mode is used, the detection mode is that more than two torque sensors are utilized to respectively measure the torque on the power device and the torque on the output end, and then the two torque values are compared, so that the torque on the power device and the torque on the output end are detected. If the torque is outside the threshold value range, the problem that the torque accuracy is reduced exists on the power device or the output end, and according to the mode, the effect of real-time monitoring is achieved, and therefore the problem that the torque is abnormal and not known is solved.

Disclosed herein are slew drive components and systems. In some cases, a slew drive system can comprise a sensor configured to measure deformation in a deformation element of a sensor carrier component, which can result from axial displacement of a worm gear of the slew drive system. In some cases, measured deformation of a deformation element can be used to determine torque applied to a worm gear by a slew drive worm wheel, as described herein. As such, the sensor can be a torque sensor.

The invention discloses a gate groove sill foreign matter cleaning method and system based on intelligent sensing. The method comprises the following steps that the cleaning system is fixed to a gate through a self-adaptive hook beam; the multi-source sensing module collects underwater foreign matter and environment data and constructs a sill three-dimensional environment map; the decision processing unit analyzes and processes the preprocessed data to generate a high-quality foreign matter feature map, and fuses the high-quality foreign matter feature map with a three-dimensional environment map constructed in the earlier stage to generate a sill foreign matter distribution map; the decision processing unit identifies the foreign matter type and marks the cleaning priority, and meanwhile, the decision processing unit plans an optimal cleaning path; according to the dirt type, the decision processing unit sends a cleaning device conversion instruction to the dirt cleaning device, and the dirt cleaning device executes cleaning operation according to the instruction; a high-precision torque sensor arranged in each joint of the mechanical arm collects joint force application data in real time and transmits the joint force application data to the decision processing unit; the collecting device synchronously recovers chippings generated in the cleaning process, and the communication module achieves two-way data transmission. And after the cleaning operation is completed, the multi-source sensing module scans the sill again, and the cleanliness is verified through secondary scanning. According to the cleaning method and system, efficient and automatic cleaning of the gate groove sill of the hydropower station gate can be achieved.

The invention provides a water-lubricated bearing performance testing device and method, relates to the field of bearing testing, and aims to solve the problem that a current water-lubricated bearing testing machine is difficult to realize real-time parameter acquisition during loading, a radial loading assembly is arranged corresponding to a stressed bearing, and an axial loading assembly acts on the tail end of a main shaft; a loading position avoids a sensor mounting area, interference of loading action on sensor acquisition precision is avoided, the water tank wraps the second bearing and the stress bearing, and the first bearing and the torque sensor are located outside the water tank, so that water lubrication environment simulation is guaranteed, and torque and temperature signal acquisition is prevented from being affected by water. When the radial loading assembly applies a radial load to the stress bearing, the load is uniformly transmitted to the first bearing and the second bearing on the two sides through the sleeve, at the moment, the temperature sensor collects the temperature rise of the first bearing, the acceleration sensor collects the vibration of the second bearing, and the torque sensor synchronously collects the friction torque. And radial loading and synchronous acquisition of multiple parameters are realized.

The invention discloses a robot joint dynamic precision control method. The method comprises the following steps that the interaction torque, the angle and the angular speed of a robot joint are obtained; based on the interaction torque, the angle and the angular velocity of the robot joint, a robot joint dynamic model containing friction and external disturbance is constructed; designing a super-spiral sliding mode control law based on the robot joint kinetic model; optimizing a sliding mode gain parameter in the super-spiral sliding mode control law based on a PPO algorithm to obtain an optimized super-spiral sliding mode control law; and controlling the dynamic precision of the robot joint based on the optimized super-spiral sliding mode control law. According to the method, the MEMS torque sensor and deep reinforcement learning are combined, and a new effective method is provided for robot joint dynamic precision control.

The invention discloses a cooking machine heating and stir-frying structure based on intelligent sensing monitoring, and relates to the technical field of intelligent kitchen equipment.The cooking machine heating and stir-frying structure comprises a machine table, a frying pan installed on the machine table, a heating layer, a mechanical cooking assembly, a non-contact infrared thermal imaging device and a controller, and the heating layer is attached to the outer wall of the frying pan; electric heating wires and variable-frequency vibrators which are uniformly distributed are arranged in the mechanical cooking assembly, and the mechanical cooking assembly comprises a mechanical arm with a humidity sensor and a spatula with a contact type temperature sensor. By integrating contact type and non-contact type temperature sensing, humidity sensing and torque sensing, the controller can comprehensively sense the temperature, humidity distribution and stir-frying resistance of food materials in the pot in real time and control the electric heating wire, the variable-frequency vibrator and the mechanical arm in a linkage mode. According to the structure, the problems that an existing cooker is uneven in heating, insufficient in stir-frying and incapable of adapting to real-time state changes of food materials depending on a preset program are solved, accurate temperature control, self-adaptive stir-frying and intelligent cooking are achieved, and the taste and consistency of dishes are improved.

The invention relates to the technical field of machining, and discloses an intelligent cutter handle capable of monitoring cutter wear in real time and triggering replacement reminding, which comprises a cutter handle main body, a sensor module, a control module, a wireless transmission module, a power supply module and an upper computer system in communication connection with the wireless transmission module, a connecting structure matched with a mainstream machine tool connector is arranged at one end of the cutter handle body, and a clamping part for clamping a cutting tool is arranged at the other end of the cutter handle body. According to the intelligent cutter handle capable of monitoring cutter abrasion in real time and triggering reminding of cutter replacement, the vibration sensor, the cutting force sensor, the torque sensor, the temperature sensor and the acoustic emission sensor are integrated in the cutter handle body, and the cutter abrasion state is accurately judged in combination with a trained and tested machine learning model based on historical abrasion data of the cutter; a plurality of wear judgment threshold sets are stored in a convolutional neural network model analysis algorithm unit in a machine learning model, and each threshold set corresponds to different cutter materials, workpiece materials and cutting parameter combinations respectively; if yes, calling a threshold set matched with the current machining condition information for judgment, and outputting a corresponding result by the model, so that real-time and automatic judgment on the tool wear state is realized, manual experience analysis is not needed, the accuracy and timeliness of judgment are remarkably improved, and the working efficiency is improved. And reduction of machining quality or cutter breakage caused by misjudgment of sudden wear as normal wear or delayed response is effectively avoided.

The invention relates to the technical field of mechanical manufacturing detection, and particularly discloses an online detection method for an integrated thread go-no go gauge of a multi-axis machining center. The method aims to solve the problems of low efficiency and secondary clamping errors caused by off-line detection after thread machining. The method is characterized in that on a multi-axis machining center, a thread detection unit integrated with a torque sensor and a linear driver serves as a standard tool to be managed; after machining, the main shaft automatically grabs the unit and positions the unit to a threaded hole, and constant-force propelling of a driver is cooperated with rotary feeding of the main shaft; in the process, the system collects torque-screwing depth data in real time, a process curve is generated, the process curve is compared with a standard curve template in form, and the non-go gauge screwing torque gradient is analyzed, so that authority judgment and quality analysis of the thread function are completed online, and a result is fed back to a numerical control system to form a process closed loop. The technical problems of thread on-machine authoritative detection and process closed-loop control are solved.

This sensor device comprises a sensor body (13 to 16, 21, 22), a sensor housing (30), a connector housing (50), and a flange 51. The sensor body (13 to 16, 21, 22) captures changes in a physical quantity, and the sensor housing (30) accommodates at least a portion of the sensor body. The connector housing (50) is provided with a detecting element (40) that outputs a signal corresponding to a change in the physical quantity, and the part in which the detecting element (40) is provided is inserted inside the sensor housing (30). The flange (51) extends outward from the connector housing (50), and a joining surface (53) facing the sensor housing (30) side is joined to the sensor housing (30). The joint surface (53) of the flange (51) is inclined with respect to a virtual plane (VS) that is perpendicular to a direction (ID) in which the part of the connector housing (50) in which the detecting element (40) is provided is inserted into the sensor housing (30).

The invention provides a six-dimensional force / torque sensor calibration device and a calibration method thereof. The six-dimensional force / torque sensor calibration device comprises a fixed base; the upper mounting plate is movably arranged on the fixed base, the height of the upper mounting plate can be adjusted relative to the fixed base, and the upper mounting plate is used for fixing a fixed surface of a calibrated sensor; the upper surface of the lower mounting plate is attached to the execution surface of the calibrated sensor, and the lower mounting plate is fixedly connected with the calibrated sensor; the six-dimensional loading plate is fixedly connected with the lower mounting plate, and the lower mounting plate is located in the middle of the six-dimensional loading plate; the number of the push-pull rods is multiple, and one end of each push-pull rod is hinged to the six-dimensional loading plate; according to the invention, automatic loading and unloading of the three-dimensional force and the three-dimensional torque under the unidirection or multi-direction combined action can be realized, the calibration process can be continuously executed, manual intervention is not needed, the labor intensity of operators is greatly reduced, and the stability and repeatability of calibration are improved at the same time.

A straddled vehicle with electric power steering including: a front fork including a left leg and a right leg extending in an up-down direction; an upper bracket supporting the front fork; a steering shaft disposed between the left and right legs, and extending in the up-down direction, the upper bracket rotating together with the front fork about an axis line of the steering shaft; a handlebar holder attached to the upper bracket and supporting the handlebar; and a torque sensor detecting a steering torque, the torque sensor including an input shaft extending in the up-down direction. The handlebar holder includes: a torque sensor support holder attached to the upper bracket, and a handlebar support holder rigidly fixed to the torque sensor support holder with a relative position therebetween changeable.

The invention relates to the field of pharmaceutical engineering and automatic control, in particular to a reaction kettle for synthesizing a medical intermediate and an intelligent control method of the reaction kettle. The reaction kettle comprises a reaction kettle main body, a stirring assembly integrated with a dynamic torque sensor and a thermotechnical pipeline assembly, the system firstly executes no-load calibration to draw a mechanical friction loss curve and a heat transfer coefficient map; deducting friction reference inversion apparent viscosity by using real-time torque during operation, and judging a reaction stage in combination with a reaction heat rate; then dynamic heat balance control is executed, and a medium temperature change compensation strategy or a rotating speed shearing strategy is selected to be executed according to the heat transfer deviation; the method is characterized in that high-precision viscosity inversion is achieved by eliminating mechanical friction interference, the polymerization degree or the crystallization state is visually monitored on the premise that the closed environment is not damaged, and the problem that the reaction process is invisible in the prior art is solved.

The invention discloses an intelligent torque gun with a miniature camera and an edge computing interface and a method, the intelligent torque gun comprises an integrated functional assembly and a cooperative control unit, the integrated functional assembly comprises a torque gun body, an operation control module, a power execution module, a sensing acquisition module, a display module and a power supply module, the cooperative control unit is composed of an edge computing interface and an adaptive edge computing device, a torque sensor in the sensing and collecting module collects torque parameters in real time, and a zoom type miniature camera is matched with LED supplementary lighting to collect assembly visual information; the edge computing interface adapts to multiple industrial protocols to realize high-speed data transmission, the edge computing device fuses and analyzes torque and visual data through a YOLO algorithm, accurately judges neglected loading, mistaken loading and floating lock abnormity, and outputs a control instruction in real time to adjust parameters of a motor driving mechanism to form closed-loop control, so that the reliability of the system is improved. According to the method, the defect that a traditional torque tool depends on manual judgment is overcome, and the accuracy and traceability of precise assembly are improved.

The invention discloses a self-adaptive precision polishing control system and method based on multi-modal perception and artificial intelligence decision. According to the system, a multi-mode sensing network is constructed through an acoustic emission sensor, a force / torque sensor, a vibration sensor, a visual sensor and a temperature sensor, and physical signals in the polishing process are collected in real time. The system adopts a deep learning model to carry out feature fusion and space-time analysis on multi-source sensing data, realizes accurate estimation of the material removal rate and comprehensive scoring of the surface quality, further integrates a reinforcement learning optimization engine, takes a process state as input, takes control parameter adjustment as action, and takes a multi-target reward function as guidance, and realizes comprehensive evaluation of the surface quality. And the autonomous optimization decision of the polishing parameters is realized. The invention further comprises a digital twinning system for offline training and online verification, and a transfer learning-based small sample rapid adaptation mechanism, so that the polishing quality consistency, the processing efficiency and the process autonomy can be remarkably improved.

The invention discloses a safe takeover and man-machine cooperation automatic driving control method. The method comprises the following steps: acquiring a face image, eye movement data, a head posture, a sight direction, a blinking frequency and a steering wheel holding state of a driver in real time through a vehicle-mounted camera and a steering wheel torque sensor; the collected driver state information is input into a driver ability evaluation module constructed based on a time sequence model, a driver ability level C is output, and the ability level C is divided into four levels of C0 to C3; and acquiring current driving scene information through an environment sensing sensor carried by the vehicle. According to the invention, all-weather and full-scene environment understanding is realized, the camera provides semantic information of lane lines and traffic signs, the millimeter-wave radar can still accurately measure distance at rainy and foggy nights, the laser radar generates high-precision three-dimensional point cloud, depicts the contour of an obstacle, and injects prior knowledge into a high-precision map.

This invention discloses a metal waste recycling and processing device and its usage method, relating to the field of metal recycling technology. It includes a machine base, an installation box mounted on top of the machine base, a feeding hopper mounted on top of the installation box, a crusher installed inside the installation box, and two rollers rotatably mounted inside the crusher. A torque sensor is rotatably connected to the outer right end of the rear roller, and a high-torque motor is installed at the right end of the rear roller. An abutment block is installed on the outer side of both the front and rear rollers. This invention features an abutment block; when the hardness of the metal material is high, leading to increased roller torque and bearing friction, a pusher block drives the abutment block to press against the roller along a slide block, cooperating with the inner rollers to provide support force compensation for the roller, reducing relative bearing friction. When the pusher block moves upward, it simultaneously contacts the oil pusher plug, squeezing lubricating oil which is then delivered to the oil tank via a hose, achieving simultaneous support force compensation and lubrication protection.