69 results about "Wear coefficient" patented technology

The invention relates to the technical field of digital twinning, and discloses a precision casting mold life prediction method based on digital twinning, which comprises a mold data acquisition module, a mold data processing module, a mold coefficient generation module, a prediction model establishment module and a mold life prediction module. Physical data, operation data and maintenance records are synchronously collected through the multi-source sensor, and full-life-cycle real-time monitoring is achieved; establishing comprehensive evaluation of four types of quantization coefficients, thermal fatigue coefficients, comprehensive mechanical coefficients, comprehensive wear coefficients and comprehensive maintenance coefficients to realize multi-field damage coupling analysis; the life prediction index unifies the multi-dimensional damage to be 0-1 standard, outputs a visual life percentage and sets a graded early warning threshold value, so that the prediction precision is improved; all coefficients are calculated through a standardized formula, a full-digital process from data acquisition to index generation to model prediction to decision support is constructed, and the detection requirements of new materials and complex structure molds are met.

The invention provides a wear coefficient correction method for a shield cutter, and relates to the technical field of wear monitoring, and the method comprises the steps: collecting a time sequence magnetic field signal obtained by a magnetic sensor array disposed on a non-rotating part of a shield tunneling machine, and synchronously obtaining a cutter angle coding signal; performing time-frequency conversion and filtering on the magnetic field signal to obtain a noise reduction time sequence signal; determining a geometric position sequence of each shield cutter in combination with the angle coding signals; based on the magnetic sensor pose, the tool position and the magnetic dipole model, theoretical magnetic field mapping between the tool and the sensor is constructed, and a system response matrix is generated; reconstructing an independent magnetic feature vector of each cutter to obtain an optimal feature set; generating a vector difference through comparison with a reference vector, inputting the vector difference into an abrasion identification model, obtaining the abrasion loss and type identification of each cutter, and correcting an abrasion coefficient; the method improves the wear recognition precision and reliability, and is suitable for tunnel construction under complex geological conditions.

The invention relates to a quasi-static straight gear wear numerical analysis method, and belongs to the technical field of mechanical engineering. The method comprises the following steps: calculating a dynamic wear coefficient by using a mixed lubrication model; the contact pressure and the sliding distance are calculated in an integral form, a straight gear quasi-static numerical wear model is established by using matlab software with the help of an Archard formula, and a wear value is calculated; the influence rule of the modulus, the torque and the tooth width on the abrasion loss is obtained, and meanwhile the significance of the influence of the three factors is analyzed through an orthogonal experiment method. Compared with the prior art, the method has the advantages that the problem that the calculation of the contact pressure is greatly influenced by the grid units is researched and solved, so that the obtained contact pressure value is more accurate, and the tooth surface wear is reduced according to the rule and significance analysis of the influence of various factors.

The invention provides a double-speed electric actuating mechanism control system, which relates to the field of electric actuating mechanisms, and comprises a control unit, and the control unit comprises an environment variable conversion module for converting temperature and pressure parameters into an effective viscosity coefficient and a sealing loss factor; the composite wear detection unit calculates a valve wear coefficient in real time; the PID parameter setting module adaptively sets PID control parameters in real time according to the parameters through a feed-forward neural network, and physical constraints and oscillation penalty terms are added; the safety switching module monitors the model output confidence coefficient, the environment variable abrupt change rate and the prediction residual error in real time, and automatically switches to safety parameters when abnormity occurs; the double-speed execution module dynamically adjusts a high-speed continuous driving mode and a low-speed pulse driving mode according to the valve position error; the response speed, stability and control precision of valve control are remarkably improved, and the method is suitable for precise flow control under complex and variable working conditions.

The invention provides a method and a device for measuring a wear coefficient of a roller, electronic equipment and a storage medium, and relates to the technical field of rail transit. A to-be-tested roller and a worn roller are driven to slide relatively; determining the sliding distance of the to-be-tested roller based on the relative sliding rate of the to-be-tested roller relative to the worn roller, the radius of the to-be-tested roller, the number of rotation turns of the to-be-tested roller and the rotation speed of the to-be-tested roller; obtaining the loss weight of the roller to be tested in the wear experiment; and acquiring the vertical force on the contact surface of the worn roller and the to-be-tested roller in the wear experiment and the hardness of the to-be-tested roller so as to acquire the wear coefficient of the to-be-tested roller. According to the invention, the actual wear environment of the roller to be tested on the track is simulated, and the measurement accuracy and authenticity of the wear coefficient of the roller of the track are improved. According to the invention, the actual sliding distance of the to-be-tested roller on the track is accurately calculated, and the measurement accuracy and authenticity of the wear coefficient of the roller of the track are improved.

The application discloses a kind of CNC machine tool tool wear monitoring method and system based on acoustic vibration sensing technology, which comprises: obtaining tool number, processing state from machine tool;Cutting vibration signals in the machining process of machine tool are collected by acoustic vibration sensor;The cutting vibration signals are preprocessed, time domain characteristic indexes and frequency domain characteristic indexes are extracted, and a comprehensive wear coefficient is calculated;According to the interval where the comprehensive wear coefficient is located, the state of the tool is judged;If the tool reaches the failure level, a prompt signal is sent out.The method is suitable for detecting common tool failure states and can be used in machine tools with different tool tooth numbers, different speeds and different machining processes.These indicators can be effectively used to evaluate tool wear in actual manufacturing processes, and play a crucial role in improving production capacity and promoting high-quality production.

The application discloses an intelligent internet-of-things control system and method for plate home, and relates to the technical field of intelligentization, comprising: establishing a repair record of a plate in the intelligent home, extracting a plurality of target records from the repair record; obtaining a repair area of the plate of the target record, analyzing a plurality of corresponding internal defects in the repair area, and obtaining a wear degree corresponding to the target record; intercepting a historical monitoring video of the repair area, obtaining a wear coefficient of the target record, and establishing a scatter plot of the wear degree with the wear coefficient; obtaining a monitoring video of a to-be-detected plate from the last repair to the target time, and judging the timing of a repair prompt for the to-be-detected plate. The application obtains historical repair records, analyzes the living environment and user daily use habits of the intelligent home, reasonably judges the timing of a repair prompt for the to-be-detected plate, and avoids resource waste or safety hazard problems caused by early or late prompts.

The application discloses a kind of based on digital twinning waste incineration grate wear prediction and jam early warning method, belong to solid waste treatment and industrial automation monitoring technical field.The method includes: the displacement, velocity, contact force and acceleration data of grate mechanism are collected in real time by sensor group;Establish the three-dimensional geometric model of grate mechanism and define kinematic pair constraint relationship, material attribute and contact parameter, construct multi-body dynamics digital twinning model, real-time data are mapped to the model to realize virtual and real synchronous;The time-varying contact force and sliding speed signal output by digital twinning model are acquired, and the wear rate is dynamically calculated based on the modified Archard wear model and the remaining useful life is predicted, and when the prediction deviation exceeds the threshold, the dynamic wear coefficient is adaptively corrected;Real-time monitoring of grate motion parameters and comparison with normal working condition benchmark value, according to stroke deviation, speed fluctuation, acceleration peak value, trigger jam early warning signal gradually;The wear amount and remaining life of each grate piece are summarized, and a health assessment report and differentiated repair recommendations are generated.The application time-varying coupling of digital twinning and wear prediction is realized, the wear rate is calculated dynamically step by step, and three-level grading early warning is realized, which can improve the wear prediction accuracy of waste incineration grate and the early warning ability of jam failure.

The invention relates to the technical field of electrical performance fault detection, in particular to a power transmission line fault prediction system and method. The method comprises the following steps: acquiring along-line meteorological monitoring data of a power transmission line hardware fitting operation area, and collecting hardware fitting vibration displacement data; shooting a fitting surface image of a power transmission line operation area through an unmanned aerial vehicle, identifying the size of a fitting wear area, and determining the fitting wear degree; the meteorological action intensity of the hardware fitting is determined according to the meteorological monitoring data along the line, and the wear coefficient of the hardware fitting is set according to the meteorological action intensity and the wear degree of the hardware fitting. According to the method, the wear area of the power transmission line fitting is identified, and the wear coefficient is adapted by combining the meteorological factor data, so that the wear loss of the power transmission line fitting is calculated, and the accuracy of power transmission line fault prediction is improved.

The invention discloses a material surface fretting wear prediction method and system based on transfer learning, and the method comprises the steps: constructing a fretting wear simulation model, and achieving the precise simulation of the motion form of a workpiece; meanwhile, aiming at a wear coefficient in the fretting wear simulation model, an attention mechanism is used for solving an influence weight of multi-source data on the wear coefficient to serve as an initial value, and the prediction of the fretting wear performance under a new working condition is quickly adapted by setting the weight and an offset, so that the high robustness of the model is realized; besides, a fretting wear simulation model is used for physical simulation to obtain a data set, a simulation fretting wear prediction model is trained in advance, and after general knowledge of fretting wear behaviors is learned by the model, a hidden layer in the model is divided into a freezing layer and a self-adaptive fine tuning layer according to the universality of wear knowledge, so that the fretting wear behavior is predicted. And a real data set is used to carry out fine tuning operation on the adaptive fine tuning layer, so that the model is closer to a real prediction result.

The application discloses a compatible type wave division equipment optical module plugging and wearing analysis method and system, and relates to the technical field of optical communication equipment operation and maintenance. The method comprises the following steps: performing optical module plugging operation by an automatic plugging device and synchronously collecting multi-dimensional force feedback data and interface positioning information; converting the force feedback data into multi-direction wearing coefficient distribution by using a pre-trained wearing coefficient mapping model; based on the wearing coefficient distribution data, calculating the total wearing distribution and the total wearing amount of each interface by path segmentation integration and direction accumulation; according to a preset wearing discrimination threshold, combining the dimension total wearing amount and the most unfavorable eccentric wearing amount to perform wearing discrimination, and generating early warning information containing the wearing category and the position; when the early warning is eccentric wearing, driving the automatic device to perform targeted correction. The application realizes quantitative monitoring, accurate prediction and active maintenance of optical module interface wearing, and significantly improves the intelligent level of operation and maintenance and the reliability of equipment.

The present application relates to the technical field of data processing, in particular to a kind of tire carcass life prediction method and system based on intelligent tire technology, the method comprises: obtaining tire vibration data and other multiple dimensions under tire wear related data;Based on tire vibration data, data segmentation is carried out to the distance traveled;For each segmented mileage, the wear coefficient of the segmented mileage is calculated;Based on the wear coefficient of each segmented mileage, a prediction model is constructed, and the remaining life of the tire carcass is predicted based on the prediction model.The present application embeds high-precision sensors in the tire, collects vibration and temperature data in real time, quantifies the influence of each different road section on tire wear through the vibration and temperature changes of the vehicle on different road sections, thereby achieving accurate prediction of tire wear;Solve the problem that the influence of the road conditions of different road sections on tire wear is not considered in the prior art, which leads to inaccurate prediction results.

This invention discloses a method, apparatus, storage medium, and computer equipment for predicting heat transfer tube wear. The method includes: acquiring heat transfer tube attribute information, support attribute information of the supporting component, flow field attribute information of the internal and external flow fields, constraint boundary information, and working environment information of the heat transfer tube to be predicted; constructing a nonlinear dynamic analysis nominal model of the target heat transfer tube structure based on the structural attribute information, flow field attribute information, constraint boundary information, and working environment information; determining the nonlinear contact state parameters and wear coefficient between the heat transfer tube to be predicted and the supporting component, and determining the turbulent excitation force time history of the heat transfer tube to be predicted; applying the nonlinear contact state parameters and turbulent excitation force time history to the nonlinear dynamic analysis nominal model to perform numerical simulation of dynamic analysis, and determining the interaction information between the heat transfer tube to be predicted and the supporting component based on the simulation results; and determining the degree of wear of the heat transfer tube to be predicted based on the interaction information and the wear coefficient.

The invention relates to the technical field of water pump performance testing, and particularly discloses an intelligent testing system and method for water pump performance, and the method comprises the following steps: S1, setting a monitoring point at a pump shell, collecting a vibration signal under the condition of sand-containing water quality, and carrying out the preprocessing to extract a high-frequency conduction vibration signal; s2, collecting sample data including conduction vibration signals and wear intensity in an operation period, obtaining an amplitude distribution curve according to the sample data, and calculating an amplitude wear coefficient; s3, a wear strength threshold value is set, and the wear rate of the water pump in the current sand-containing water quality environment is calculated in combination with the amplitude distribution curve and the amplitude wear coefficient; according to the invention, the accuracy of wear monitoring is improved, the conversion from passive maintenance to active prediction is realized, the operation reliability of the water pump system is obviously improved, and the service life of the water pump system is obviously prolonged.

The abrasion prediction method for the brake pad of the elevator drum brake comprises the steps that a brake test bed is built, the brake duration and the brake distance under different brake pressure and brake rotating speed working conditions are obtained through a brake test, and the average friction coefficient and the average abrasion coefficient are calculated; least square polynomial fitting is carried out on the average friction coefficient and the average wear coefficient, Latin hypercube sampling is carried out on the braking parameters, and simulation working condition data are generated; establishing a brake finite element model to carry out heat-stress-wear coupling simulation analysis on each simulation working condition to obtain the maximum wear depth of the surface of the brake pad under each simulation working condition; constructing a brake pad surface maximum wear depth prediction model based on a PSO-BP neural network, and training the prediction model by adopting the simulation working condition data and the brake pad surface maximum wear depth; and adopting the trained PSO-BP neural network-based brake pad surface maximum wear depth prediction model to predict the brake pad surface maximum wear depth under a specific working condition.

The invention relates to the technical field of ship propulsion systems, and particularly discloses a texturing-self-lubricating synergistically reinforced hub joint surface structure and a wear depth prediction method. The joint surface structure comprises a propeller hub and a crank pin disc, and the joint surface of the propeller hub adopts a partition micro-texture design: the periphery is a groove type micro-texture for guiding oil and discharging chips; and the inner side is a pit-shaped micro-texture and is used for storing oil and lubricating. A gradient nanocrystalline strengthening layer is formed on the combined surface of the crank pin disc through ultrasonic rolling treatment, and a self-lubricating material column is embedded in the combined surface in an interference pressing mode, so that solid lubrication and high bearing capacity are achieved. The wear prediction method comprises the following steps: calibrating a wear coefficient K through a fretting wear experiment; establishing a finite element model to simulate and obtain the distribution of the contact pressure P and the inching slip amplitude S; and substituting the P and S field data and the K value into an Archard model to calculate the wear depth, and generating a visual prediction cloud picture. Through the synergistic effect of the texture and the self-lubricating material, the boundary lubricating state is remarkably improved, the wear rate is reduced, wear distribution can be accurately predicted, a basis is provided for condition-based maintenance, and the service life of the controllable-pitch propeller is prolonged.

The invention belongs to the technical field of wear prediction, and discloses a wear depth prediction method, device and system in a high-temperature environment and a storage medium, and the method comprises the steps: building a fitting expression of a wear coefficient; wherein the fitting expression of the wear coefficient is obtained by fitting test working condition data; substituting the wear coefficient into an Archard model to obtain a wear model; based on the wear coefficient, a wear depth prediction formula is established; and based on the wear model and a wear depth prediction formula, predicting wear volumes and wear depths under different test working conditions. Compared with a traditional prediction method, the wear coefficient K only needs to be fitted once, fitting does not need to be conducted every time, multivariable fitting is adopted, and coupling among parameters is guaranteed.

The application relates to the technical field of ball mill control, and discloses a composite mineral admixture ball mill control method and system, which comprises the following steps: collecting driving current data, mill sound data and vibration data, and constructing current sequences, mill sound sequences and vibration sequences of a collection period; marking a target collection period, determining a mill sound first slope, a mill sound wear confidence, a current first slope, a current wear confidence, a vibration first slope and a vibration wear confidence of the target collection period, and determining a steel ball wear coefficient of the target collection period; determining a wear difference coefficient of the target collection period; and controlling the rotating speed of the ball mill of the composite mineral admixture according to the wear difference coefficient of the target collection period and the rotating speed. The application can realize self-adaptive control of the rotating speed of the ball mill of the composite mineral admixture.

The invention discloses an intelligent Internet of Things control system and method for a panel home, and relates to the technical field of intellectualization, and the method comprises the steps: building a repairing record of a panel in the smart home, and extracting a plurality of target records from the repairing record; obtaining a repairing area of the plate of the target record, and analyzing a plurality of corresponding internal defects in the repairing area to obtain a wear degree corresponding to the target record; intercepting a historical monitoring video of the repairing area to obtain a wear coefficient of the target record, and establishing a scatter diagram of the wear degree along with the wear coefficient; and acquiring a monitoring video of the to-be-detected plate from the last repair to the target moment, and judging the opportunity of performing repair prompt on the to-be-detected plate. According to the method, the historical repair record is obtained, analysis is performed in combination with the living environment of the smart home and the daily use habits of the user, the repair prompt time of the to-be-detected plate is reasonably judged, and the problem of resource waste or potential safety hazards caused by too early or too late prompt is avoided.

The invention relates to the technical field of control systems, and particularly discloses a PLC-based automatic wire threading control method and system for a medium-speed wire cutting machine tool, and the method comprises the steps: collecting the accumulated use time, the accumulated wire threading frequency and the real-time tension fluctuation standard deviation of a molybdenum wire; based on the sum, calculating a wear coefficient representing the current wear state of the molybdenum wire; according to the wear coefficient, dynamic control parameters used for controlling the tension of the molybdenum wire are determined from a preset dynamic compensation model, and the dynamic control parameters at least comprise static gain and a time constant. Molybdenum wire tension can be adjusted in real time in a dynamic environment, and the problem that molybdenum wire abrasion cannot be monitored and adjusted in real time in the prior art is solved; the wear coefficient is calculated by collecting the use time, the threading frequency and the real-time tension fluctuation of the molybdenum wire, and dynamic control is performed based on the wear coefficient, so that the system can automatically adjust control parameters to ensure that the tension of the molybdenum wire is always kept in the optimal state.

The invention relates to the technical field of marketing management, and discloses a multi-modal data fusion marketing effect prediction method and device, and the method comprises the following steps: 1, obtaining the management data of all users, the sales data of all material artificial limbs and the marketing data of all regions, and classifying the management data, the sales data and the marketing data to form a data set; 2, according to the user data set, the abrasion degree of each user artificial limb is analyzed, and an abrasion coefficient is generated; 3, according to the artificial limb data set, the user acceptance degree of the artificial limb of each material is analyzed, and an acceptance index is generated; 4, according to the regional data set, the marketing effect of each regional market is analyzed, a marketing data set is generated, and the multi-dimensional analysis precision is high; and 5, setting a wear threshold value and an acceptance threshold value with fixed numerical values, screening out artificial limb materials which are highly accepted by a target customer and a user in combination with the wear coefficient, the acceptance index and the marketing data set, and outputting corresponding marketing strategy suggestions, so that the dynamic management marketing effect is good.

The invention relates to a valve moving type material selecting device based on a database and a control method, the material selecting device comprises a driving system, a shell part, a rotating part, a butt joint part, a material injection part and a database management system; the database management system stores raw material data; the driving system comprises a servo motor and a speed reducer; the shell part comprises a rack and an index plate, and the index plate is mounted on the rack; the rotating part comprises a rotating shaft and a nylon disc; and the butt joint part is used for butt joint of the rotating part and the injection part. The method has the beneficial effects that the environment parameters and the equipment wear coefficient are fused through the database to generate the composite target angle, so that the problem of large indexing angle positioning error caused by environment fluctuation and equipment aging in the prior art is solved.

The invention provides a steam generator heat transfer tube wear prediction and intelligent tube blocking method and system. The method comprises the steps that flow fields, vibration fields and wear databases of a heat transfer tube under different working conditions and positions are constructed through analogue simulation and real overhaul data of a nuclear power plant; constructing a training sample based on the constructed flow fields, vibration fields and wear databases of the heat transfer tube under different working conditions and positions; respectively training the flow field prediction model, the vibration field prediction model and the wear coefficient prediction model; during the unit overhaul period, operation data of a steam generator, position information of each heat transfer pipe and a supporting plate and corresponding abrasion data are obtained; respectively carrying out pretreatment; utilizing the trained flow field prediction model, vibration field prediction model and wear coefficient prediction model to predict the wear depth during the next overhaul; and judging whether the predicted wear depth during the next overhaul reaches or exceeds a set threshold value, and triggering and controlling the automatic pipe plugging operation when the wear depth reaches or exceeds the threshold value.

The invention discloses a project progress deviation dynamic early warning method oriented to whole process consultation, relates to the technical field of project early warning, and is used for solving the problems of unbalanced working face advancing rhythm and uneven resource distribution. The method comprises the following steps: calling classification data of working surfaces of all areas, detecting ring number propulsion rates and tool changing frequencies, calculating engineering propulsion indexes and shield wear coefficients according to the classification data, further evaluating area propulsion synchronization fluctuation rates, judging whether to enter a resource analysis mechanism or not according to the fluctuation rates, and collecting grouting material consumption of the working surfaces in the mechanism; the method comprises the following steps: counting arrival intervals of muck transport vehicles, identifying a vehicle accumulation state, detecting stratum hardness when accumulation is abnormal, predicting a resource consumption trend based on grouting consumption, generating a resource consumption level after correction in combination with the stratum hardness, judging whether areas are synchronously unbalanced or not according to the level, selecting corresponding pre-control measures, and improving the overall propulsion efficiency of a tunnel.

This invention discloses an adaptive wear calculation method and system for heavy-duty sliding bearings. The method includes: reading input parameters (bearing properties, initial state, current wear parameters); initializing relevant variables (roughness, wear depth array, time step array); calculating combined roughness; calculating contact pressure; adaptively calculating the maximum sliding distance; adaptively calculating the maximum time step; calculating the real-time wear coefficient; calculating the current wear depth based on the Archard model; determining whether the maximum wear depth or time step is greater than the planned depth or time step; determining the final wear depth, film thickness, contact pressure, temperature, and roughness; and outputting the results. The system includes a reading module, an initialization module, a calculation module, a judgment module, an update module, and an output module. This invention has the advantages of simplicity and efficiency, eliminating tedious calculation steps and making it more efficient.

The present application provides a straddle-type monorail car pantograph copper slider thickness detection method, storage medium and system, belongs to the straddle-type monorail car technical field. Including step one, the pantograph copper slider image is collected, step two, based on the pantograph copper slider image collected, the image is pretreated;Step three, the wear coefficient is constructed, the pantograph copper slider wear threshold is preset, the wear coefficient is compared with the pantograph copper slider wear threshold, whether the pantograph copper slider meets the safety use requirement is identified;Step four, the wear trend index and the defect evaluation index are obtained;Step five, finally, the wear trend index and the defect evaluation index are associated, and the comprehensive influence coefficient is constructed. Through the pantograph copper slider image collection, processing, and based on the pantograph copper slider data atlas extraction of the thinnest and thickest thickness information, the wear coefficient is constructed, and whether it meets the safety use requirement is identified in time, so as to avoid the operation risk caused by excessive wear.

This invention relates to a database-based valve-operated material selection device and control method. The material selection device includes: a drive system, a housing component, a rotating component, a docking component, a material injection component, and a database management system. The database management system stores raw material data. The drive system includes a servo motor and a reducer. The housing component includes a frame and an indexing plate, with the indexing plate mounted on the frame. The rotating component includes a rotating shaft and a nylon disc. The docking component is used to dock the rotating component and the material injection component. The beneficial effect of this invention is that it generates a composite target angle by fusing environmental parameters and equipment wear coefficients from a database, thus overcoming the problem of large positioning errors in the indexing angle caused by environmental fluctuations and equipment aging in the prior art.

The invention discloses a dynamic identification method for dynamic seal abrasion loss of an aviation flight control actuator, which belongs to the field of reliability simulation of mechanical and electrical products and comprises the following steps of: constructing a dynamic seal abrasion model of the abrasion loss of a sealing material of the aviation flight control actuator along with time change; coupling the dynamic seal wear model with a hydraulic transmission model and a control system model, and establishing a complete machine simulation model for simulating the macro performance change of the actuator at different time points; according to the whole machine simulation model, an order reduction agent model with the abrasion loss and time as input and key performance response indexes as output is constructed; and on the basis of the reduced-order agent model and the actually measured key performance response index, a dynamic seal wear coefficient is obtained through a reverse optimization algorithm, and the dynamic seal wear amount of the aviation flight control actuator is dynamically identified. On the premise of not depending on frequent disassembly and assembly, online acquisition and identification of the abrasion loss at different time nodes can be achieved, and technical support is provided for reliability prediction and service life evaluation of the aviation flight control actuator.

The embodiment of the invention provides a method and system for predicting the abrasion loss of a grinding roller of a medium-speed coal mill, and the method comprises the steps: collecting the configuration parameters of the medium-speed coal mill and the periodic operation parameters of the grinding roller based on the microcosmic cutting mechanism of the grinding roller and coal particles, and enabling the periodic operation parameters to be collected in the periodic discontinuous contact process of the grinding roller and the coal particles; on the basis of configuration parameters and the periodic operation parameters of the medium-speed coal mill, the normal load, the slippage distance and the wear coefficient of the grinding roller are calculated, and the slippage distance is obtained through calculation on the basis of the periodic wear conditions of the multiple continuous wear points; based on the configuration parameters of the medium-speed coal mill, the normal load, the slippage distance and the wear coefficient, establishing a wear loss calculation model; and inputting the current running parameters, collected in real time, of the grinding roller into the abrasion loss calculation model, and outputting an abrasion loss prediction result of the grinding roller. According to the invention, continuous prediction of the abrasion loss of the grinding roller can be realized, and the hysteresis defect of traditional manual measurement is overcome.

The invention discloses a method for predicting abrasion parameters based on a physical information tandem type artificial neural network, and the method comprises the steps: S1, collecting abrasion coefficient data, abrasion volume data and working condition data generated by the fretting abrasion of a winding wire and a fuel cladding under different test working conditions through tests, and carrying out the preprocessing; s2, constructing a physical information tandem type artificial neural network, constructing a physical information constraint loss function based on an Archard wear model, and jointly training the physical information tandem type artificial neural network based on the preprocessed wear coefficient data, wear volume data and working condition data constraint loss function; s3, utilizing the trained physical information tandem type artificial neural network to predict the abrasion coefficient and the abrasion volume of the fuel cladding; according to the method, the Archard wear physical model and the experimental data are fused to jointly train the physical information neural network, so that accurate prediction of the fretting wear coefficient and the wear volume of the fuel cladding is realized.