Equipment management and process quality collaborative optimization method and device based on digital twin base, equipment and storage medium

Abstract

The invention discloses an equipment management and process quality collaborative optimization method and device based on a digital twin base, equipment and a storage medium, and relates to the technical field of intelligent manufacturing, and the method comprises the steps: obtaining equipment operation data from a programmable logic controller, and inputting the equipment operation data into a physical engine; driving a virtual device model in the physical engine and the physical device to run synchronously to obtain synchronous state data; the synchronous state data are input into a machine learning model for prediction, and the tool abrasion loss and the equipment fault probability value are obtained; obtaining quality deviation data, and inputting the quality deviation data and the tool abrasion loss into the virtual equipment model for simulation iteration to obtain optimized process parameters; and the optimized process parameters are input into the programmable logic controller, so that the programmable logic controller controls the physical equipment to execute machining operation according to the optimized process parameters, collaborative optimization of the equipment state and the process quality is completed, the equipment utilization rate is remarkably improved, and the maintenance cost and the quality rework rate are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent manufacturing, and particularly relates to a device management and process quality collaborative optimization method and device based on a digital twin base, equipment and a storage medium. BACKGROUND

[0002] The digital transformation of manufacturing requires deep collaboration between equipment utilization and process quality to address bottlenecks in production capacity loss and quality fluctuations, and to upgrade the production mode from passive response to active prediction.

[0003] In the prior art, device management, production execution and quality control systems operate independently, maintenance relies on fixed cycles or after-the-fact maintenance, process parameter adjustment lags behind offline detection, digital twin applications are mostly limited to visualization, virtual models and physical devices lack real-time driven deep interaction, and it is difficult to dynamically optimize production rhythm and resource allocation, resulting in low equipment comprehensive efficiency and high quality cost.

[0004] The above content is only used to assist in understanding the technical solutions of the present application, and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0005] The main purpose of the present application is to provide a device management and process quality collaborative optimization method, device and storage medium based on a digital twin base, aiming to solve the technical problem that device state monitoring and process quality control are mutually isolated and cannot be optimized in real time.

[0006] To achieve the above purpose, the present application provides a device management and process quality collaborative optimization method based on a digital twin base, which comprises the following steps: Inputting device running data obtained from a programmable logic controller into a physical engine to drive virtual device models in the physical engine to run synchronously with physical devices, and obtaining synchronous state data; Inputting the synchronous state data into a machine learning model for prediction to obtain tool wear and device failure probability values; Obtaining quality deviation data, inputting the quality deviation data and the tool wear into the virtual device model for simulation iteration to obtain optimized process parameters; Inputting the optimized process parameters into the programmable logic controller to enable the programmable logic controller to control physical devices to perform machining operations according to the optimized process parameters, and to complete the collaborative optimization of device state and process quality.

[0007] In an embodiment, the step of inputting the device running data obtained from the programmable logic controller into the physics engine to drive the virtual device model in the physics engine to run synchronously with the physical device and obtain synchronous state data comprises: device running data read from the programmable logic controller; timestamp alignment and filtering preprocessing of the device running data to obtain preprocessed data; transmission of the preprocessed data to the physics engine through the Open Platform Communication Unified Architecture protocol; updating the spatial pose and motion logic of the virtual device model based on the preprocessed data to trigger the physics engine to perform physical simulation calculation and obtain synchronous state data.

[0008] In an embodiment, the step of inputting the synchronous state data into the machine learning model for prediction to obtain tool wear and device failure probability values comprises: extracting multi-source sensor time series features from the synchronous state data, wherein the multi-source sensor time series features include vibration features, temperature features, and rotation speed features; inputting the multi-source sensor time series features into the machine learning model for encoding to obtain a time series feature vector; performing tool wear regression calculation on the time series feature vector to obtain tool wear; performing device failure classification judgment on the time series feature vector to obtain device failure probability values.

[0009] In an embodiment, the step of inputting the quality deviation data and the tool wear into the virtual device model for simulation iteration to obtain optimized process parameters comprises: constructing a multi-objective quality loss function based on the quality deviation data and the tool wear; inputting the multi-objective quality loss function into the virtual device model to trigger an adaptive control algorithm to iteratively calculate compensated process parameters; when the multi-objective quality loss function value meets a preset convergence condition, outputting the compensated process parameters as optimized process parameters.

[0010] In an embodiment, the step of inputting the optimized process parameters into the programmable logic controller to enable the programmable logic controller to control the physical device to perform machining operations according to the optimized process parameters to complete the collaborative optimization of device state and process quality comprises: packaging the optimized process parameters into control instruction frames; sending the control instruction frames to the programmable logic controller; verifying a response message returned by the programmable logic controller to obtain a verification result; when the verification result is a verification failure or no response message is received, re-sending the control instruction frame; when the verification result is a verification success, completing the issuance of the optimized process parameters, so that the programmable logic controller controls the physical device to perform a processing operation according to the optimized process parameters, and uses the device failure probability value to generate a maintenance work order, to complete the collaborative optimization of device state and process quality.

[0011] In an embodiment, the method further comprises: obtaining production plan data and device available state data; inputting the production plan data, the device available state data and the synchronization state data into a multi-objective optimization model, the multi-objective optimization model taking production efficiency, product quality and device energy consumption as optimization objectives; allocating a dynamic weight coefficient to the multi-objective optimization model; running a multi-objective intelligent optimization algorithm to solve the multi-objective optimization model, to generate a candidate production scheduling scheme; inputting the candidate production scheduling scheme into the virtual device model for simulation verification; using the candidate production scheduling scheme that passes simulation verification as a final production rhythm and resource scheduling instruction to guide actual production.

[0012] In an embodiment, the method further comprises: obtaining tool identification data and historical tool life records; generating tool life records from the tool identification data and tool wear; uploading the tool life records to a blockchain network, so that the blockchain network performs verification and stores the tool life records that pass verification on the chain.

[0013] In addition, to achieve the above-mentioned purpose, the application further provides a device management and process quality collaborative optimization device based on a digital twin base, which comprises: a virtual-real synchronization module for inputting device running data obtained from a programmable logic controller into a physical engine, driving a virtual device model in the physical engine to run synchronously with a physical device, to obtain synchronization state data; a prediction analysis module for inputting the synchronization state data into a machine learning model for prediction, to obtain tool wear and device failure probability values; a simulation module for obtaining quality deviation data, inputting the quality deviation data and the tool wear into the virtual device model for simulation iteration, to obtain optimized process parameters; An optimization module is configured to input the optimized process parameters into the programmable logic controller, so that the programmable logic controller controls the physical device to perform the processing operation according to the optimized process parameters, and completes the collaborative optimization of the device state and the process quality.

[0014] In addition, to achieve the above-mentioned purpose, the present application also provides a device management and process quality collaborative optimization device based on a digital twin base, which comprises a memory, a processor and a device management and process quality collaborative optimization program based on a digital twin base stored in the memory and executable on the processor, and the device management and process quality collaborative optimization program based on a digital twin base is configured to implement the steps of the device management and process quality collaborative optimization method based on a digital twin base as described above.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a storage medium, which stores a device management and process quality collaborative optimization program based on a digital twin base, and the device management and process quality collaborative optimization program based on a digital twin base implements the steps of the device management and process quality collaborative optimization method based on a digital twin base as described above when executed by a processor.

[0016] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which comprises a computer program, and the computer program implements the steps of the device management and process quality collaborative optimization method based on a digital twin base as described above when executed by a processor.

[0017] The one or more technical solutions provided by the present application have at least the following technical effects: The physical engine is used to realize millisecond-level synchronous mapping of device running data and virtual models, the machine learning model is used to complete parallel regression calculation of tool wear and classification judgment of device failure after encoding of time sequence features of multiple source sensors, the device health state is accurately predicted, then the quality deviation data and the wear prediction value are fused to construct a multi-objective loss function, the process parameters are iteratively optimized in a virtual environment through an adaptive control algorithm, the instructions are encapsulated and reliably issued to the controller for execution after bidirectional verification, a closed-loop feedback of process quality is formed, multi-objective intelligent optimization and virtual simulation verification are performed in combination with production plans and device states, global optimal scheduling instructions are generated to guide production, and tool life data is stored in a blockchain to trigger intelligent procurement management, and finally the whole chain of device monitoring, process optimization, production decision and spare parts management is connected, and deep collaborative optimization of physical and virtual spaces is realized. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the application.

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, those skilled in the art can obtain other drawings according to these drawings without any creative effort.

[0020] Figure 1 A flowchart provided by the embodiment one of the method for collaborative optimization of equipment management and process quality based on digital twin base of the present application; Figure 2 A system architecture diagram provided by the embodiment one of the method for collaborative optimization of equipment management and process quality based on digital twin base of the present application; Figure 3 A principle diagram provided by the embodiment one of the method for collaborative optimization of equipment management and process quality based on digital twin base of the present application; Figure 4 A flowchart provided by the embodiment two of the method for collaborative optimization of equipment management and process quality based on digital twin base of the present application; Figure 5 A module structure diagram of the device for collaborative optimization of equipment management and process quality based on digital twin base of the embodiment of the present application; Figure 6 A device structure diagram of the hardware running environment involved in the method for collaborative optimization of equipment management and process quality based on digital twin base of the embodiment of the present application.

[0021] The object implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application, and are not used to limit the present application.

[0023] In order to better understand the technical solutions of the present application, the following will be described in detail with reference to the drawings and specific embodiments of the specification.

[0024] It should be noted that the execution subject of the present embodiment can be a computing service device with data processing, network communication and program running functions, such as tablet computers, personal computers, mobile phones, etc., or an electronic device capable of realizing the above functions, a device for collaborative optimization of equipment management and process quality based on digital twin base, etc. The following will take the device for collaborative optimization of equipment management and process quality based on digital twin base as an example to describe the present embodiment and each of the following embodiments.

[0025] Based on this, the embodiment of the present application provides a device management and process quality collaborative optimization method based on a digital twin base, referring to Figure 1 , Figure 1 is the flowchart of the first embodiment of the device management and process quality collaborative optimization method based on the digital twin base of the present application.

[0026] In this embodiment, the device management and process quality collaborative optimization method based on the digital twin base comprises steps S10-S40: Step S10, inputting the device running data obtained from the programmable logic controller into the physical engine, driving the virtual device model in the physical engine to run synchronously with the physical device, and obtaining synchronous state data; It should be noted that the purpose of this step is to establish a real-time mapping channel between the physical device and the virtual model, and realize high-fidelity digitalization of the device running state.

[0027] The device running data obtained from the programmable logic controller refers to a set of original sensing data collected from the control layer through the industrial field bus, including vibration, temperature, rotating speed, and position encoder electrical signal sampling values; the physical engine refers to a real-time simulation computing platform integrating rigid body dynamics, collision detection, and multi-body kinematics solver; the virtual device model refers to a digital twin based on three-dimensional geometric modeling and physical property definition, having consistent structure, kinematics, and quality distribution characteristics with the physical device.

[0028] It can be understood that the digital twin base system reads the original sensing data packet from the input and output registers of the programmable logic controller at regular intervals, eliminates the clock source deviation of multiple sensors through timestamp alignment, removes measurement noise through Kalman filtering, obtains preprocessed data unified in time and space reference, and then transmits to the physical engine in real time through the Open Platform Communication Unified Architecture protocol in real-time subscription mode. The physical engine drives the spatial pose update of the virtual device model according to the position encoder value, drives the model motion logic according to the vibration and temperature data, and then triggers the physical engine to perform rigid body dynamics and collision contact physical simulation calculation, generating synchronous state data containing device geometry, physics, and behavior state.

[0029] The purpose of this scheme is to realize device lifecycle management through the digital twin base, integrate account, plan, and maintenance functions, and dynamically optimize device utilization; at the same time, build predictive maintenance capability, accurately predict tool life and device failure based on sensor data and digital twin model; in addition, through real-time collection of process parameters and quality data, realize closed-loop process quality control, and automatically feedback and adjust production parameters; finally, realize real-time mapping of device state through the digital twin base, drive dynamic optimization of production rhythm and resource scheduling.

[0030] As Figure 2As shown, the system architecture of the present scheme includes a digital twin base layer, a device management module, a process quality module, and a collaborative optimization engine: The digital twin base layer includes: based on high-precision three-dimensional modeling and physical engine (such as Unity3D, UE5), constructing device geometric model and motion logic, integrating sensor data to realize virtual-real synchronization; connecting PLC and motion controller through OPC UA protocol, and mapping device running state to virtual model in real time.

[0031] The device management module includes: account management, dynamically updating device attributes, maintenance records, and spare parts inventory, supporting two-dimensional code / RFID quick retrieval.

[0032] Planning and scheduling, combined with digital twin simulation results, automatically generating production plans and optimizing device scheduling.

[0033] Predictive maintenance, based on machine learning algorithms (such as LSTM) to analyze vibration, temperature, and other sensor data to predict tool wear and equipment failure and trigger maintenance work orders.

[0034] The process quality module includes: process route optimization, adjusting process parameters according to real-time processing data (such as cutting force, speed), and reducing quality fluctuations. Quality traceability system, recording process parameters and test results of each batch of products through blockchain technology, supporting full-process traceability.

[0035] The collaborative optimization engine includes: inputting device status, process parameters, and quality data into the digital twin model, simulating different production scenarios, and outputting the optimal cycle and resource allocation scheme.

[0036] As shown, Figure 3 The working principle diagram of the present scheme includes: real-time transmission of physical device data to digital twin, driving virtual model to run synchronously; the device management module generates maintenance recommendations based on twin data, and the process module adjusts processing parameters in real time; quality detection data is fed back to the digital twin model, triggering a self-optimization cycle of process parameters; the collaborative optimization engine simulates multiple production plans and selects the optimal scheme to guide actual production.

[0037] In a feasible implementation, step S10 includes steps A11-A14: Step A11: reading device running data from the programmable logic controller; It should be noted that the purpose of this step is to obtain raw device sensor signals that have not been processed. Device running data refers to process image data stored in the memory mapping area of the programmable logic controller, including instantaneous values collected from field-installed acceleration sensors, temperature sensors, and rotary encoders.

[0038] It can be understood that the digital twin base system, as an OPC UA client, accesses the programmable logic controller preset variable node through periodic reading service, extracts the analog / digital signals of vibration, temperature, rotating speed and position encoder in the form of data packets, and forms the original data basis for subsequent processing.

[0039] Step A12: time stamp alignment and filtering preprocessing of the device operation data of the pair to obtain preprocessed data; It should be noted that the purpose of this step is to improve the data quality to meet the requirements of real-time simulation on time and space consistency and signal-to-noise ratio.

[0040] Time stamp alignment refers to time delay compensation according to the offset of each sensor sampling clock, and unification to global synchronous clock reference; filtering preprocessing refers to fusing multi-sensor observation values by using Kalman filtering algorithm, estimating the real physical state and filtering out high-frequency measurement noise.

[0041] It can be understood that the system reads the acquisition time stamp of each data packet, calculates the deviation relative to the master clock and performs spline interpolation resampling, to ensure that the multi-source data is strictly aligned in time dimension; then the system state equation and observation equation are constructed, and the state estimation value is recursively updated, to output preprocessed data that is smooth and suppresses noise interference.

[0042] Step A13: transmitting the preprocessed data to the physical engine through the open platform communication unified architecture protocol; It should be noted that the purpose of this step is to realize standardized real-time data communication between the industrial field and the simulation platform. The open platform communication unified architecture protocol refers to the standard cross-platform industrial communication specification, which supports the publish / subscribe mechanism and security encryption; the physical engine refers to the real-time simulation kernel deployed in the edge computing node or the cloud. It can be understood that the system encapsulates the preprocessed data as an OPC UA data variant type, pushes it to the data receiving interface of the physical engine through the establishment of a subscription channel with a millisecond-level period, and the physical engine parses the protocol message and extracts the payload to provide data input for model driving.

[0043] Step A14: updating the spatial pose and motion logic of the virtual device model based on the preprocessed data to trigger the physical engine to perform physical simulation calculation, to obtain synchronization state data.

[0044] It should be noted that the purpose of this step is to convert the preprocessed data into the physical behavior of the virtual model.

[0045] Spatial pose refers to the position and attitude homogeneous transformation matrix of the virtual device model in the three-dimensional coordinate system; motion logic refers to the driving constraint relationship of each motion pair of the model; physical simulation calculation refers to numerical integration solution based on Newton-Euler dynamics equation.

[0046] It can be understood that the system updates the model joint angle according to the position encoder value, calculates the end effector pose according to the forward kinematics, maps the vibration amplitude to the excitation force suffered by the model, maps the temperature data to the material thermal expansion coefficient, triggers the physics engine to perform collision detection, contact force calculation and dynamics integration every simulation step, and generates synchronous state data.

[0047] Step S20, input the synchronous state data into the machine learning model for prediction to obtain the tool wear and equipment failure probability value; It should be noted that the purpose of this step is to analyze and predict the tool remaining life and equipment failure risk based on time series data.

[0048] The machine learning model refers to a nonlinear mapping model trained by historical data; the tool wear refers to the width or volume loss of the tool relief surface wear; and the equipment failure probability value refers to the possibility of functional failure of the equipment within a predetermined period in the future.

[0049] It can be understood that the system extracts vibration spectrum entropy, temperature gradient, and speed fluctuation from the synchronous state data, constructs a feature vector sequence, inputs the feature vector sequence into the machine learning model, and the model learns the time series dependency relationship through the encoder-decoder structure to map the tool wear and failure probability value.

[0050] Step S30, obtain quality deviation data, input the quality deviation data and tool wear into the virtual equipment model for simulation iteration to obtain optimized process parameters; It should be noted that the purpose of this step is to quantify the quality deviation and tool state into a unified loss metric and solve the optimal process compensation.

[0051] The quality deviation data refers to the deviation of the actual measured size, geometric tolerance, surface roughness and target value after product processing; the multi-objective quality loss function refers to a weighted loss function that comprehensively considers size deviation, surface quality and tool wear; and the compensated process parameters refer to the adjustment amount of cutting speed, feed rate, cutting depth and the like.

[0052] It can be understood that the system reads the three-coordinate measurement data and roughness data from the product detection device, standardizes and fuses the quality deviation data and tool wear, constructs a loss function, and inputs the loss function into the simulation controller of the virtual equipment model, triggers the adaptive control algorithm to iteratively search for process parameters that minimize the loss function in the virtual environment.

[0053] In a feasible implementation, step S30 includes steps A21-A23: Step A21: based on the quality deviation data and the tool wear, a multi-objective quality loss function is constructed; It should be noted that the purpose of this step is to unify the influence of quantitative quality and equipment state on the process.

[0054] The quality deviation data refers to measurement results including size deviation values and surface roughness values; the multi-objective quality loss function refers to a mathematical expression that maps multi-dimensional deviations into a scalar optimization target.

[0055] It can be understood that the system performs z-score standardization on size deviations and surface roughness, normalizes tool wear, and weightedly sums to obtain a comprehensive loss function value, providing an objective function for subsequent iterative optimization.

[0056] Step A22: Input the multi-objective quality loss function into the virtual equipment model to trigger the adaptive control algorithm and iteratively calculate the compensated process parameters. It should be noted that the purpose of this step is to quickly simulate the quality response under different process parameters in a virtual environment.

[0057] The adaptive control algorithm refers to a closed-loop algorithm that dynamically adjusts control parameters according to the loss function gradient; the compensated process parameters refer to the increase or decrease of the original process parameters.

[0058] It can be understood that the system inputs the loss function into the simulation controller, and the controller uses gradient descent or model predictive control strategy to simulate the machining effect under different parameter combinations in the virtual equipment model, and iteratively calculates the compensation amount that makes the loss function continuously decrease.

[0059] Step A23: When the multi-objective quality loss function value meets the preset convergence condition, output the compensated process parameters as the optimized process parameters.

[0060] It should be noted that the purpose of this step is to judge the iteration termination condition and solidify the optimization result.

[0061] The preset convergence condition refers to that the gradient of the loss function value is less than a threshold or the number of iterations reaches an upper limit; the compensated process parameters as the optimized process parameters refer to the final adopted and executed process adjustment value.

[0062] It can be understood that the system monitors the loss function decrease amplitude after each iteration, and if the decrease amount is less than a preset proportion threshold for three consecutive iterations, it is considered to be converged, the calculation is terminated, and the current compensated process parameters are output as the optimization result.

[0063] Step S40: Input the optimized process parameters into the programmable logic controller to make the programmable logic controller control the physical equipment to perform machining operations according to the optimized process parameters, completing the collaborative optimization of equipment state and process quality.

[0064] It should be noted that the purpose of the step is to reliably map the virtual space optimization result to the physical device and trigger the associated management process.

[0065] The control instruction frame refers to a data message in the format of an industrial control protocol; the response message refers to a confirmation message returned by the programmable logic controller after receiving the instruction; and the maintenance work order refers to a maintenance task document automatically generated based on the fault probability value.

[0066] It can be understood that the system encapsulates the optimized process parameters into an OPC UA write request message, sends it to the controller and starts a timeout timer. If an acknowledgement response is received within the threshold time and the parameter verification is consistent, it is marked as successful, triggering the controller to perform actions according to the new parameters. If no response is received or the verification fails, it is retransmitted. After verification, the device fault probability value is pushed to the maintenance management system, and a maintenance work order is automatically generated based on the preset fault level threshold.

[0067] In a possible implementation, step S40 includes steps A31-A35. Step A31: encapsulate the optimized process parameters into a control instruction frame. It should be noted that the purpose of the step is to convert the optimization result into a protocol data unit that can be parsed by the controller.

[0068] The optimized process parameters refer to values such as speed, feed rate, and depth determined through simulation iteration; and the control instruction frame refers to a frame structure containing parameter identification, values, timestamps, and check codes.

[0069] It can be understood that the system binary encodes the process parameters according to the controller communication protocol format, adds CRC check codes and timestamp fields, and assembles them into a complete instruction frame.

[0070] Step A32: send the control instruction frame to the programmable logic controller. It should be noted that the purpose of the step is to transmit the instruction frame through an industrial communication protocol.

[0071] The open platform communication unified architecture protocol refers to an industrial Ethernet protocol that supports reliable transmission and security authentication.

[0072] It can be understood that the system sends the instruction frame to the controller specified variable node as an asynchronous write request through the established OPC UA session channel.

[0073] Step A33: verify the response message returned by the programmable logic controller to obtain a verification result. It should be noted that the purpose of the step is to confirm that the controller successfully receives and parses the instruction.

[0074] The response message refers to a status code and read-back data returned by the controller after performing the write operation; and the verification result refers to a judgment conclusion on the validity (timeliness, integrity, consistency) of the response.

[0075] It can be understood that the system compares whether the read-back parameter value in the response message is consistent with the sent value, and checks whether the response timestamp is within the timeout window.

[0076] Step A34: When the verification result is a verification failure or no response message is received, resend the control instruction frame; It should be noted that the purpose of this step is to ensure the reliability of instruction transmission.

[0077] Verification failure refers to inconsistent response verification or no response received within the timeout; retransmission refers to re-executing the sending process.

[0078] It can be understood that the system automatically falls back to step A31 to repackage and send the instruction frame when the verification fails, with a maximum of pre-set retries.

[0079] Step A35: When the verification result is a verification success, complete the issuance of the optimized process parameters, so that the programmable logic controller controls the physical device to perform the processing operation according to the optimized process parameters, and uses the device failure probability value to generate a maintenance work order, and completes the collaborative optimization of the device state and process quality.

[0080] It should be noted that the purpose of this step is to complete the parameter taking effect and trigger the associated management action.

[0081] Verification success refers to receiving a valid confirmation response; and the maintenance work order refers to a task document containing the failure device number, probability level, and recommended maintenance time.

[0082] It can be understood that the system marks the parameters as having taken effect after the verification is successful and records the log, while triggering the controller to execute according to the new parameters, and sends the device failure probability value to the maintenance management system to generate a work order.

[0083] Further, the method further comprises: Obtaining production plan data and device available state data; Inputting the production plan data, device available state data, and synchronization state data into a multi-objective optimization model, and taking production efficiency, product quality, and device energy consumption as optimization objectives; Allocating a dynamic weight coefficient to the multi-objective optimization model; Running a multi-objective intelligent optimization algorithm to solve the multi-objective optimization model, and generating a candidate production scheduling scheme; Inputting the candidate production scheduling scheme into a virtual device model for simulation verification; The candidate production scheduling scheme verified by simulation is used as the final production rhythm and resource scheduling instruction to guide actual production.

[0084] It should be noted that the present aspect aims to extend local process optimization to global production scheduling decision.

[0085] Production plan data refers to work order and delivery date information issued by enterprise resource planning system; device available state data refers to device health, load, and maintenance state; multi-objective intelligent optimization algorithm refers to meta-heuristic algorithm for solving multi-objective problem; candidate production scheduling scheme refers to scheduling solution containing process sequence, device allocation, and time period division; resource scheduling instruction refers to device start-stop and material distribution instruction issued to execution layer.

[0086] It can be understood that the system reads production order from enterprise resource planning system, reads available state from device management account book, constructs multi-objective optimization model combined with synchronous state data, dynamically weights three targets of efficiency, quality, and energy consumption, runs genetic algorithm or particle swarm algorithm to solve Pareto frontier, selects the scheme with the highest satisfaction degree after virtual simulation verification, and issues the production rhythm and scheduling instruction to production execution system (MES / SCADA) to guide actual production.

[0087] Further, the method further comprises: Obtaining tool identification data and historical tool life record; Generating tool life record from tool identification data and tool wear amount; Uploading the tool life record to the blockchain network, so that the blockchain network performs verification, and stores the tool life record that passes the verification on the chain.

[0088] It should be noted that the present aspect aims to construct tool full life cycle credible record and realize intelligent spare part management.

[0089] Tool identification data refers to tool number, model, and installation time in radio frequency identification tag; tool life record refers to comprehensive record containing wear amount, use time, and number of processed parts; blockchain network refers to alliance chain composed of manufacturing, quality inspection, and maintenance nodes; verification refers to record signature and hash validity check by node through practical Byzantine fault tolerance mechanism; on-chain storage refers to writing record block header and Merkle root into account book; historical tool life record refers to accumulated wear curve of the same type of tool before scrapping on the chain; spare part procurement early warning information refers to next replacement time and recommended purchase quantity predicted based on historical data.

[0090] It can be understood that the system reads the tool radio frequency identification tag to obtain the identification, binds the wear amount to generate a life record, uploads to the blockchain network for consensus verification, and then is chained and stored, historical data is extracted from the chain to fit a tool life attenuation model, a replacement cycle is predicted and a procurement warning is generated, and the procurement management system is pushed to trigger the procurement process in advance.

[0091] The embodiment provides a device management and process quality collaborative optimization method based on a digital twin base, realizes real-time dynamic optimization of device states and process parameters through closed-loop collaboration of virtual-real synchronization, machine learning prediction and quality deviation optimization, and combines global optimization of production scheduling and blockchain tool traceability to break through the whole chain of device monitoring, process decision and spare parts management, improve the comprehensive efficiency of the device, reduce the downtime risk and quality cost.

[0092] Based on the first embodiment of the application, the same or similar contents as the above-mentioned embodiment one can refer to the above introduction, and the subsequent will not be described in detail. On this basis, please refer to Figure 4 , step S20, comprising steps S201-S204: Step S201, extracting multi-source sensor time sequence features from the synchronized state data, wherein the multi-source sensor time sequence features include vibration features, temperature features and rotation speed features; It should be noted that the purpose of this step is to extract key features from the synchronized state data that can represent the running state of the device, providing input for the subsequent prediction model.

[0093] Synchronized state data refers to data generated when a virtual device model generated by a physics engine is synchronized with a physical device, containing geometric, physical and behavioral state information of the device. Multi-source sensor time sequence features refer to feature sequences of data collected from different sensors (such as vibration sensors, temperature sensors, rotation speed sensors) over time. Among them, the vibration features include vibration amplitude, frequency, frequency spectrum entropy, etc.; the temperature features include temperature value, temperature change rate, temperature gradient, etc.; the rotation speed features include rotation speed value, rotation speed fluctuation, rotation speed stability, etc.

[0094] It can be understood that by extracting these features from the synchronized state data, the dynamic behavior and health status of the device during operation can be fully reflected.

[0095] Step S202, inputting the multi-source sensor time sequence features into a machine learning model for encoding to obtain a time sequence feature vector; It should be noted that the purpose of this step is to convert the multi-source sensor time sequence features into a format suitable for processing by the machine learning model.

[0096] The machine learning model usually requires that the input data have a unified structure and dimension, so the extracted features need to be encoded. The time series feature vector refers to arranging the multi-source sensor time series features in time sequence and converting them into vector form, which facilitates model learning and calculation.

[0097] It can be understood that by inputting the multi-source sensor time series features into the machine learning model for encoding, complex time series data can be converted into feature vectors that the model can understand and process, providing a basis for subsequent prediction tasks.

[0098] In step S203, the time series feature vector is subjected to tool wear regression calculation to obtain the tool wear amount. It should be noted that the purpose of this step is to perform regression analysis on the time series feature vector by the machine learning model to predict the tool wear amount.

[0099] Tool wear amount refers to the degree of wear of the tool due to friction and cutting force during machining, usually represented by tool flank wear land width or volume loss.

[0100] It can be understood that by inputting the time series feature vector into the machine learning model for regression calculation, the tool wear condition can be dynamically predicted according to the changes in the equipment operating state, providing a basis for timely replacement of the tool, thereby reducing the machining quality problems caused by tool wear.

[0101] In step S204, the time series feature vector is subjected to equipment fault classification judgment to obtain an equipment failure probability value.

[0102] It should be noted that the purpose of this step is to perform classification analysis on the time series feature vector by the machine learning model to determine whether the equipment is likely to fail.

[0103] The equipment failure probability value refers to the likelihood of functional failure of the equipment within a predetermined future period, usually represented by a probability value.

[0104] It can be understood that by inputting the time series feature vector into the machine learning model for classification judgment, the possible failure of the equipment can be warned in advance, providing support for preventive maintenance and reducing equipment downtime and maintenance costs.

[0105] The embodiment provides a device management and process quality collaborative optimization method based on a digital twin base, which extracts multi-source sensor time series features from synchronous state data and encodes and predicts them by using a machine learning model, thereby achieving dynamic monitoring and early warning of tool wear amount and equipment failure probability. This predictive maintenance mechanism can detect potential problems in advance, reduce production interruptions and quality problems caused by equipment failure and tool wear, and significantly improve the reliability and production efficiency of the equipment.

[0106] It should be noted that the above examples are only for understanding the present application and do not constitute a limitation on the method for collaborative optimization of equipment management and process quality based on a digital twin base of the present application. Further simple transformations in more forms based on this technical concept are within the scope of protection of the present application.

[0107] The present application also provides a device for collaborative optimization of equipment management and process quality based on a digital twin base, which is described in detail in Figure 5 The device for collaborative optimization of equipment management and process quality based on a digital twin base comprises: a virtual-physical synchronization module 10 configured to input equipment running data obtained from a programmable logic controller into a physical engine, drive a virtual equipment model in the physical engine to run synchronously with a physical equipment, and obtain synchronous state data; a prediction analysis module 20 configured to input the synchronous state data into a machine learning model for prediction, and obtain a tool wear amount and a device failure probability value; a simulation module 30 configured to obtain quality deviation data, input the quality deviation data and the tool wear amount into the virtual equipment model for simulation iteration, and obtain optimized process parameters; an optimization module 40 configured to input the optimized process parameters into the programmable logic controller, so that the programmable logic controller controls the physical equipment to perform a machining operation according to the optimized process parameters, and completes collaborative optimization of the equipment state and the process quality.

[0108] The device for collaborative optimization of equipment management and process quality based on a digital twin base provided by the present application adopts the method for collaborative optimization of equipment management and process quality based on a digital twin base in the above embodiments, and can solve the technical problem that the equipment state monitoring and the process quality control are mutually disjointed and cannot be optimized in real time. Compared with the prior art, the device for collaborative optimization of equipment management and process quality based on a digital twin base provided by the present application has the same beneficial effects as the method for collaborative optimization of equipment management and process quality based on a digital twin base provided by the above embodiments, and other technical features in the device for collaborative optimization of equipment management and process quality based on a digital twin base are the same as the features disclosed in the above method, which will not be described here.

[0109] In an embodiment, the virtual-physical synchronization module 10 is further configured to read the equipment running data from the programmable logic controller; perform time stamp alignment and filtering preprocessing on the equipment running data to obtain preprocessed data; transmit the preprocessed data to the physical engine through an open platform communication unified architecture protocol; update the spatial pose and motion logic of the virtual equipment model based on the preprocessed data to trigger the physical engine to perform physical simulation calculation, and obtain the synchronous state data.

[0110] In an embodiment, the prediction analysis module 20 is further configured to extract multi-source sensor time series features from the synchronization state data, wherein the multi-source sensor time series features include vibration features, temperature features, and rotation speed features; The multi-source sensor time series features are input into a machine learning model for encoding to obtain time series feature vectors; The time series feature vectors are subjected to tool wear regression calculation to obtain tool wear amounts; The time series feature vectors are subjected to equipment failure classification judgment to obtain equipment failure probability values.

[0111] In an embodiment, the simulation module 30 is further configured to construct a multi-objective quality loss function based on the quality deviation data and the tool wear amounts; The multi-objective quality loss function is input into a virtual equipment model to trigger an adaptive control algorithm for iterative calculation of compensated process parameters; When the multi-objective quality loss function value meets a preset convergence condition, the compensated process parameters are output as optimized process parameters.

[0112] In an embodiment, the optimization module 40 is further configured to encapsulate the optimized process parameters into control instruction frames; The control instruction frames are sent to a programmable logic controller; A response message returned by the programmable logic controller is verified to obtain a verification result; When the verification result is a verification failure or no response message is received, the control instruction frames are resent; When the verification result is a verification success, the optimized process parameters are issued to enable the programmable logic controller to control the physical equipment to perform a machining operation according to the optimized process parameters, and the equipment failure probability values are used to generate a maintenance work order to complete the collaborative optimization of the equipment state and the process quality.

[0113] In an embodiment, the optimization module 40 is further configured to obtain production plan data and equipment available state data; The production plan data, the equipment available state data, and the synchronization state data are input into a multi-objective optimization model, and the multi-objective optimization model takes production efficiency, product quality, and equipment energy consumption as optimization objectives; Dynamic weight coefficients are assigned to the multi-objective optimization model; A multi-objective intelligent optimization algorithm is run to solve the multi-objective optimization model to generate a candidate production scheduling scheme; The candidate production scheduling scheme is input into a virtual equipment model for simulation verification; The candidate production scheduling scheme that passes the simulation verification is taken as final production tempo and resource scheduling instructions to guide actual production.

[0114] In an embodiment, the optimization module 40 is further configured to acquire tool identification data and historical tool life records; The tool identification data and the tool wear amount are used to generate a tool life record; The tool life record is uploaded to a blockchain network, so that the blockchain network performs verification, and the tool life record that passes the verification is stored on the chain.

[0115] The application provides a device management and process quality collaborative optimization device based on a digital twin base. The device management and process quality collaborative optimization device based on the digital twin base comprises at least one processor and a memory in communication connection with the at least one processor. The memory stores instructions executable by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the device management and process quality collaborative optimization method based on the digital twin base in Embodiment I.

[0116] Reference will be made to the following description Figure 6 which shows a structural schematic diagram of the device management and process quality collaborative optimization device based on the digital twin base suitable for being used to implement the embodiments of the application. The device management and process quality collaborative optimization device based on the digital twin base in the embodiments of the application can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast acquirers, PDAs (Personal Digital Assistant), PADs (Portable Application Description), PMPs (Portable Media Player), vehicle-mounted terminals (for example, vehicle-mounted navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 6 The device management and process quality collaborative optimization device based on the digital twin base shown is only an example, and should not bring any limitation to the functions and use range of the embodiments of the application.

[0117] As Figure 6As shown, the digital-twin-infrastructure-based equipment management and process quality collaborative optimization device can include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to programs stored in a ROM (Read Only Memory) 1002 or programs loaded from a storage device 1003 into a RAM (Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the digital-twin-infrastructure-based equipment management and process quality collaborative optimization device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the digital-twin-infrastructure-based equipment management and process quality collaborative optimization device to communicate wirelessly or wired with other devices to exchange data. Although the digital-twin-infrastructure-based equipment management and process quality collaborative optimization device with various systems is shown in the figure, it should be understood that all the systems shown are not required to be implemented or possessed. More or fewer systems can be alternatively implemented or possessed.

[0118] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.

[0119] The device management and process quality collaborative optimization device based on the digital twin base provided in the application adopts the device management and process quality collaborative optimization method based on the digital twin base in the above embodiment, and can solve the technical problem that device state monitoring and process quality control are mutually isolated and cannot be optimized in real time. Compared with the prior art, the device management and process quality collaborative optimization device based on the digital twin base provided in the application has the same beneficial effects as the device management and process quality collaborative optimization method based on the digital twin base provided in the above embodiment, and other technical features in the device management and process quality collaborative optimization device based on the digital twin base are the same as the features disclosed in the above embodiment method, and will not be repeated here.

[0120] It should be understood that parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0121] The above is merely specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0122] The present application provides a computer readable storage medium having computer readable program instructions (i.e. computer programs) stored thereon, the computer readable program instructions being used to execute the device management and process quality collaborative optimization method based on the digital twin base in the above embodiment.

[0123] The computer readable storage medium provided in the application may be, for example, a U disk, but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system or device, or any combination thereof. More specific examples of the computer readable storage medium may include, but are not limited to, an electrical connection with one or more conductive wires, a portable computer disk, a hard disk, a RAM (Random Access Memory), a ROM (Read Only Memory), an EPROM (Erasable Programmable Read Only Memory or flash memory), an optical fiber, a CD-ROM (CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the embodiment, the computer readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to an electrical wire, an optical cable, an RF (Radio Frequency), etc., or any suitable combination thereof.

[0124] The computer readable storage medium described above may be contained in the device management and process quality collaborative optimization device based on the digital twin base, or may exist separately without being assembled into the device management and process quality collaborative optimization device based on the digital twin base.

[0125] The computer readable storage medium described above carries one or more programs, when the one or more programs are executed by the device management and process quality collaborative optimization device based on the digital twin base, the device management and process quality collaborative optimization device based on the digital twin base: inputs the device running data obtained from the programmable logic controller into the physical engine, drives the virtual device model in the physical engine to run synchronously with the physical device, obtains synchronous state data; inputs the synchronous state data into the machine learning model for prediction, obtains the tool wear amount and the device failure probability value; obtains the quality deviation data, inputs the quality deviation data and the tool wear amount into the virtual device model for simulation iteration, obtains the optimized process parameters; inputs the optimized process parameters into the programmable logic controller, so that the programmable logic controller controls the physical device to perform the machining operation according to the optimized process parameters, and completes the collaborative optimization of the device state and the process quality.

[0126] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0127] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0128] The modules involved in the embodiments of the present application can be implemented in software or hardware. In some cases, the names of the modules do not constitute a limitation on the modules themselves.

[0129] The readable storage medium provided by the application is a computer readable storage medium, and the computer readable storage medium stores computer readable program instructions (i.e., a computer program) for executing the above-mentioned device management and process quality collaborative optimization method based on a digital twin base, which can solve the technical problem that device state monitoring and process quality control are mutually isolated and cannot be optimized in real time. Compared with the prior art, the computer readable storage medium provided by the application has the same beneficial effects as the device management and process quality collaborative optimization method based on a digital twin base provided by the above-mentioned embodiments, and will not be described here.

[0130] The application also provides a computer program product comprising a computer program, which, when executed by a processor, implements the steps of the device management and process quality collaborative optimization method based on a digital twin base as described above.

[0131] The computer program product provided by the application can solve the technical problem that device state monitoring and process quality control are mutually isolated and cannot be optimized in real time. Compared with the prior art, the computer program product provided by the application has the same beneficial effects as the device management and process quality collaborative optimization method based on a digital twin base provided by the above-mentioned embodiments, and will not be described here.

[0132] The above-mentioned is only part of the embodiments of the application, and does not limit the patent scope of the application, and any equivalent structural transformation made by using the content of the specification and drawings of the application, or direct / indirect application in other related technical fields is included in the patent protection scope of the application.

Claims

1. A method for collaborative optimization of equipment management and process quality based on digital twin base, characterized in that, The method comprises: inputting device running data obtained from a programmable logic controller into a physical engine to drive a virtual device model in the physical engine to run synchronously with a physical device to obtain synchronous state data; inputting the synchronous state data into a machine learning model for prediction to obtain a tool wear amount and a device failure probability value; obtaining quality deviation data, inputting the quality deviation data and the tool wear amount into the virtual device model for simulation iteration to obtain optimized process parameters; inputting the optimized process parameters into the programmable logic controller to enable the programmable logic controller to control the physical device to perform a machining operation according to the optimized process parameters, thereby completing collaborative optimization of device state and process quality.

2. The method of claim 1, wherein, The step of inputting device running data obtained from a programmable logic controller into a physical engine to drive a virtual device model in the physical engine to run synchronously with a physical device to obtain synchronous state data comprises: device running data read from a programmable logic controller; timestamp alignment and filtering preprocessing of the device running data to obtain preprocessed data; transmission of the preprocessed data to a physical engine through an open platform communication unified architecture protocol; updating the spatial pose and motion logic of the virtual device model based on the preprocessed data to trigger the physical engine to perform physical simulation calculation to obtain synchronous state data.

3. The method of claim 1, wherein, The step of inputting the synchronous state data into a machine learning model for prediction to obtain a tool wear amount and a device failure probability value comprises: extracting multi-source sensor time sequence features from the synchronous state data, wherein the multi-source sensor time sequence features include vibration features, temperature features, and rotation speed features; inputting the multi-source sensor time sequence features into a machine learning model for encoding to obtain a time sequence feature vector; performing tool wear regression calculation on the time sequence feature vector to obtain a tool wear amount; performing device failure classification judgment on the time sequence feature vector to obtain a device failure probability value.

4. The method of claim 1, wherein, The step of inputting the quality deviation data and the tool wear amount into the virtual device model for simulation iteration to obtain optimized process parameters comprises: constructing a multi-objective quality loss function based on the quality deviation data and the tool wear amount; inputting the multi-objective quality loss function into the virtual device model to trigger an adaptive control algorithm to iteratively calculate compensated process parameters; when the multi-objective quality loss function value meets a preset convergence condition, outputting the compensated process parameters as optimized process parameters.

5. The method of claim 1, wherein, The step of inputting the optimized process parameters into the programmable logic controller to enable the programmable logic controller to control the physical device to perform a machining operation according to the optimized process parameters, thereby completing collaborative optimization of device state and process quality, comprises: packaging the optimized process parameters into a control instruction frame; sending the control instruction frame to the programmable logic controller; verifying a response message returned by the programmable logic controller to obtain a verification result; when the verification result is a verification failure or no response message is received, resending the control instruction frame; When the verification result is a verification success, the optimized process parameters are issued to make the programmable logic controller control the physical device to perform a machining operation according to the optimized process parameters, and the device failure probability value is used to generate a maintenance work order, thereby completing the collaborative optimization of the device state and the process quality.

6. The method of claim 1, wherein, The method further comprises: acquiring production plan data and device available state data; inputting the production plan data, the device available state data, and the synchronization state data into a multi-objective optimization model, the multi-objective optimization model taking production efficiency, product quality, and device energy consumption as optimization objectives; allocating dynamic weight coefficients to the multi-objective optimization model; running a multi-objective intelligent optimization algorithm to solve the multi-objective optimization model and generate a candidate production scheduling scheme; inputting the candidate production scheduling scheme into the virtual device model for simulation verification; using the candidate production scheduling scheme that passes the simulation verification as final production tempo and resource scheduling instructions to guide actual production.

7. The method of claim 1, wherein, The method further comprises: acquiring tool identification data and historical tool life records; generating tool life records from the tool identification data and tool wear; uploading the tool life records to a blockchain network to make the blockchain network perform verification and store the tool life records that pass the verification on the chain.

8. A device management and process quality collaborative optimization apparatus based on a digital twin base, characterized in that, The device comprises: a virtual-real synchronization module configured to input device running data obtained from a programmable logic controller into a physical engine to drive the virtual device model in the physical engine to run synchronously with the physical device and obtain synchronization state data; a prediction analysis module configured to input the synchronization state data into a machine learning model for prediction to obtain tool wear and device failure probability values; a simulation module configured to acquire quality deviation data, input the quality deviation data and the tool wear into the virtual device model for simulation iteration to obtain optimized process parameters; an optimization module configured to input the optimized process parameters into the programmable logic controller to make the programmable logic controller control the physical device to perform a machining operation according to the optimized process parameters, thereby completing the collaborative optimization of the device state and the process quality.

9. A device management and process quality collaborative optimization device based on a digital twin base, characterized in that, The device comprises a memory, a processor, and a digital-twin-based device management and process quality collaborative optimization program stored on the memory and executable on the processor, the digital-twin-based device management and process quality collaborative optimization program being configured to implement the steps of the digital-twin-based device management and process quality collaborative optimization method according to any one of claims 1 to 7.

10. A storage medium, characterized by The storage medium stores a digital-twin-based device management and process quality collaborative optimization program, the digital-twin-based device management and process quality collaborative optimization program being executable by the processor to implement the steps of the digital-twin-based device management and process quality collaborative optimization method according to any one of claims 1 to 7.

Images