Robot polishing path optimization method based on linkage of industrial internet of things and MES

Abstract

A robot polishing path optimization method based on industrial internet of things and MES linkage comprises: acquiring real-time operation data of production line equipment through industrial internet of things deployment of multi-sensor network, and pre-processing the real-time operation data by using edge computing technology to construct structured data stream. Based on the structured data stream from the industrial internet of things, the best task allocation scheme of the polishing process and the upstream and downstream processes is calculated by using reinforcement learning or heuristic algorithm in combination with order demand, process requirement and historical operation data. The adaptive path fine-tuning algorithm is called to fine-tune the offline programming path of the polishing robot in the process of executing the best task allocation scheme by the polishing robot, so as to generate the optimal path. The optimal path executed by the polishing robot is monitored in real time, and the real-time monitoring data is fed back to the MES system and the industrial internet of things platform. The historical operation data is analyzed by machine learning to adaptively and iteratively optimize the optimal path.

Description

Technical Field

[0001] This invention relates to the fields of intelligent industry and workpiece grinding technology, specifically to a method for optimizing robot grinding paths based on the linkage between the Industrial Internet of Things and MES. Background Technology

[0002] With the continuous advancement of industrial robot technology and the widespread application of industrial robots in industries such as welding, cutting, carving, grinding, and deburring, more and more manual grinding operations are being replaced by automated and unmanned grinding workstations, solving the occupational health and safety issues of operators, and greatly improving grinding quality and efficiency.

[0003] To achieve high polishing quality and efficiency, strict requirements are placed on the robot's position, posture, and polishing path during the polishing process. Currently, most polishing workstations are programmed using online teaching, which is inefficient, with teaching times for a single part reaching tens of hours, and makes it difficult to accurately control the robot's position, posture, and polishing path. Offline programming, as a key technology in robot applications, has significantly improved the efficiency of robot operations and reduced the workload for robot teaching personnel. However, current offline programming technology for polishing workstations still has the following problems:

[0004] When offline programming software plans the polishing path, it usually only considers the process requirements of a single robot or a single workpiece, while ignoring the overall scheduling, cycle time synchronization, and information interaction between other processes (such as stamping and inspection) at the production line level. This can easily lead to production line bottlenecks or resource conflicts, making it difficult to realize the overall efficiency of a "smart factory". Summary of the Invention

[0005] To address the shortcomings of existing technologies, the present invention aims to solve the aforementioned defects and propose a robot grinding path optimization method based on the linkage of Industrial Internet of Things and MES.

[0006] The present invention adopts the following technical solution.

[0007] The first aspect of this invention discloses a method for optimizing robot grinding paths based on the linkage between Industrial Internet of Things (IIoT) and MES (Manufacturing Execution System), the method comprising:

[0008] By deploying a multi-sensor network through the Industrial Internet of Things to acquire real-time operating data of production line equipment, and using edge computing technology to preprocess the real-time operating data to construct a structured data stream;

[0009] The optimal task allocation scheme for the grinding process and its upstream and downstream processes is calculated by using reinforcement learning or heuristic algorithms based on the structured data stream from the Industrial Internet of Things, combined with order requirements, process requirements and historical operating data.

[0010] The adaptive path fine-tuning algorithm is invoked to fine-tune the offline programming path of the grinding robot during the execution of the optimal task allocation scheme, so as to generate the optimal path.

[0011] The optimal path executed by the grinding robot is monitored in real time, and the real-time monitoring data is transmitted back to the MES system and the industrial IoT platform. Historical operating data is analyzed through machine learning to adaptively and iteratively optimize the optimal path.

[0012] The production line equipment includes a grinding robot, a stamping machine, and testing equipment. The heuristic algorithm includes a genetic algorithm and a particle swarm optimization algorithm. The real-time monitoring data includes the position data, motion status data, and workpiece processing quality data of the grinding robot.

[0013] Furthermore, the step of acquiring real-time operating data of production line equipment through the deployment of a multi-sensor network via the Industrial Internet of Things (IIoT), and preprocessing the real-time operating data using edge computing technology to construct a structured data stream, includes:

[0014] Raw operating data is collected from the production line equipment and sent to the preprocessing unit using an edge computing gateway. The raw operating data is then preprocessed using a filtering function to obtain digital preprocessed data.

[0015] The digital preprocessed data from different devices are fused together, and a unified timestamp is added according to the data acquisition time to form a time-series fused data vector, and the structured data stream is constructed based on the fused data vector;

[0016] The raw operating data includes the motor temperature, grinding force, and end position of the grinding robot, as well as the stamping pressure and mold temperature of the stamping press and the optical and dimensional sensor data of the detection equipment.

[0017] Furthermore, the method of employing reinforcement learning or heuristic algorithms based on the structured data stream from the Industrial Internet of Things, combined with order requirements, process requirements, and historical operating data, to calculate the optimal task allocation scheme for the grinding process and its upstream and downstream processes includes:

[0018] The operating status, processing progress, and cycle time information of each device are parsed from the structured data stream. The MES system then uses the operating status, processing progress, and cycle time information of each device to parse the current task queue and the initial process requirements of each process to generate a task requirement vector.

[0019] The production scheduling objective is defined as minimizing the overall processing time and waiting time. At the same time, equipment load balancing constraints are introduced to construct a production scheduling optimization model. The task demand vector is used as the input of the production scheduling optimization model, and the output is the production scheduling objective function and the task quantity constraints of each equipment.

[0020] The operating status includes the operating status of the grinding robot, the operating status of the stamping machine, and the operating status of the testing equipment. The operating status of the grinding robot includes temperature, grinding force, and displacement. The operating status of the stamping machine includes stamping pressure and mold temperature. The operating status of the testing equipment includes dimensional deviation. The processing progress is the percentage of the current workpiece's processing progress. The cycle time information is the processing time of a single piece by the grinding robot. The task requirement vector is composed of the current processing progress percentage of each process, the process standards to be completed for each process, and the real-time operating data obtained by each device.

[0021] Furthermore, the method of using reinforcement learning or heuristic algorithms based on the structured data stream from the Industrial Internet of Things, combined with order requirements, process requirements, and historical operating data, to calculate the optimal task allocation scheme for the grinding process and upstream and downstream processes also includes:

[0022] The heuristic algorithm is used to construct a scheduling vector, and simultaneously generate an equipment allocation vector and a processing time allocation vector, in order to solve the production scheduling objective function and obtain a local or global optimal solution to the production scheduling objective function;

[0023] The final optimized process scheduling vector is obtained based on the local or global optimal solution of the production scheduling objective function.

[0024] The scheduling vector consists of the processing sequence number of each workpiece, the equipment allocation vector consists of the corresponding equipment allocated to each workpiece, the processing time allocation vector consists of the expected processing time of each workpiece, and the process scheduling vector is jointly composed of the scheduling vector, the equipment allocation vector, and the processing time allocation vector.

[0025] Furthermore, the adaptive path fine-tuning algorithm is invoked to fine-tune the offline programming path of the grinding robot during the execution of the optimal task allocation scheme, in order to generate the optimal path, including:

[0026] Based on the position of the workpiece in the processing sequence and the equipment allocation information in the process scheduling vector, the initial grinding path corresponding to each workpiece is extracted from the offline programming database to obtain the defined offline path vector.

[0027] During the grinding process, real-time feedback data is collected by multiple sensors to form a real-time feedback vector. Based on the actual grinding quality data of the workpiece and the actual working status data of the equipment, and combined with the offline programming path, correction is performed to establish an error function.

[0028] The offline path vector is composed of the spatial coordinates of each sampling point in the initial polishing path, and the expression for the error function is:

[0029]

[0030] In the formula, E represents the average spatial error, which reflects the degree of deviation between the polishing path and the actual state; M is the total number of path sampling points; and Δx i Δy i Δz i These represent the real-time deviations of the i-th sampling point in the path along the X, Y, and Z axes, respectively.

[0031] Furthermore, the step of invoking the adaptive path fine-tuning algorithm to fine-tune the offline programming path of the grinding robot during the execution of the optimal task allocation scheme by the grinding robot to generate the optimal path also includes:

[0032] Based on the real-time feedback vector and the average spatial error, a path compensation vector consisting of the deviation vector of each sampling point in the initial polishing path is obtained, and the corrected path is calculated by calling the dynamic adjustment formula. The corrected path is then smoothed using an interpolation smoothing algorithm to obtain the adjusted optimal path vector.

[0033] The optimal path vector is compared and verified with the actual equipment status through a virtual simulation platform or digital twin system, and the optimal path executed by the grinding robot is generated in combination with the defined verification indicators.

[0034] The dynamic adjustment formula is as follows:

[0035] P * =P0+k×ΔP

[0036] In the formula, P * P0 is the corrected path, k is the compensation factor, and ΔP is the path compensation vector.

[0037] Furthermore, the optimal path executed by the grinding robot is monitored in real time, and the real-time monitoring data is transmitted back to the MES system and the industrial IoT platform. Historical operating data is analyzed through machine learning to adaptively and iteratively optimize the optimal path, including:

[0038] By real-time monitoring of the optimal path executed by the grinding robot, the position data, motion state data, and workpiece processing quality data of the grinding robot when executing the optimal path are obtained, so as to output a defined feedback data vector consisting of average path deviation, average grinding force standard deviation, and workpiece surface processing quality index.

[0039] By defining a position error vector with the optimal path executed by the polishing robot as the ideal path, the path deviation between the actual execution path and the ideal path is calculated to evaluate the error of the feedback data vector.

[0040] Furthermore, the step of real-time monitoring of the optimal path executed by the grinding robot and transmitting the real-time monitoring data back to the MES system and the industrial IoT platform, and using machine learning to analyze historical operating data to adaptively and iteratively optimize the optimal path, also includes:

[0041] The compensation factor in the dynamic adjustment formula is adjusted according to the path deviation between the actual execution path and the ideal path, and the recalibration trigger condition is obtained according to the system response. An optimization suggestion vector is output, and the feedback data vector and the optimization suggestion vector are sent back to the MES system and the industrial IoT platform.

[0042] The optimization suggestion vector is composed of the suggested adjustment of the compensation factor, the suggested modification of the feed rate adjustment, and the suggested recalibration time or triggering condition.

[0043] A second aspect of the present invention discloses a terminal, including a processor and a storage medium; characterized in that:

[0044] The storage medium is used to store instructions;

[0045] The processor is configured to operate according to the instructions to perform the steps of the method described in the first aspect.

[0046] A third aspect of the present invention discloses a computer-readable storage medium having a computer program stored thereon, characterized in that the program, when executed by a processor, implements the steps of the method described in the first aspect.

[0047] The beneficial effects of the present invention are as follows: Compared with the prior art, the present invention has the following advantages:

[0048] (1) By deploying a multi-sensor network through the Industrial Internet of Things (IIoT), real-time status data of the robot grinding unit and various workstations (such as stamping, inspection, and assembly) on the production line can be collected. Data preprocessing can be performed using edge computing technology, which can effectively reduce network load and make some intelligent decisions locally.

[0049] (2) Using reinforcement learning or heuristic algorithms (such as genetic algorithms and particle swarm optimization) to calculate the optimal task allocation scheme can ensure that the grinding process and the upstream and downstream processes (stamping, assembly and inspection) operate in coordination, thereby reducing production bottlenecks.

[0050] (3) Based on the scheduling results of the MES system, the offline programming path of the grinding robot is optimized in a secondary manner to ensure that the path selection takes into account the production cycle, production line layout and equipment status. That is, an adaptive path adjustment algorithm is adopted to make fine adjustments based on real-time data during the robot's execution, such as avoiding bottlenecks in other processes and adjusting the feed speed.

[0051] (4) After the grinding robot performs its task, it transmits key process parameters (such as grinding force, time, quality inspection results, etc.) back to the MES and IIoT platform, forming a closed-loop feedback of the production process. By analyzing historical data through machine learning, the grinding strategy is further optimized, and adaptive iterative optimization is achieved. Attached Figure Description

[0052] Figure 1 This is a flowchart of a robot grinding path optimization method based on the linkage between Industrial Internet of Things and MES. Detailed Implementation

[0053] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] like Figure 1 As shown in one embodiment, a robot grinding path optimization method based on the linkage of Industrial Internet of Things and MES includes the following steps:

[0055] Step S110: Deploy a multi-sensor network through the Industrial Internet of Things to acquire real-time operating data of production line equipment, and use edge computing technology to preprocess the real-time operating data to construct a structured data stream.

[0056] The production line equipment includes grinding robots, stamping machines, and testing equipment.

[0057] In some embodiments, the robot grinding path optimization method based on the linkage of Industrial Internet of Things and MES provided by the present invention includes the following steps in step S110:

[0058] Step S111: Collect raw operating data from production line equipment and send the raw operating data to the preprocessing unit using an edge computing gateway to preprocess the raw operating data through a filtering function to obtain digital preprocessed data.

[0059] Step S112: The digital preprocessed data from different devices are fused together, and a unified timestamp is added according to the data acquisition time to form a time-series fused data vector, and a structured data stream is constructed based on the fused data vector.

[0060] The raw operating data includes the motor temperature, grinding force, and end position of the grinding robot, as well as the stamping pressure and mold temperature of the stamping press and the optical and dimensional sensor data of the detection equipment.

[0061] Step S120: Using reinforcement learning or heuristic algorithms, based on structured data streams from the Industrial Internet of Things, and combined with order requirements, process requirements, and historical operating data, calculate the optimal task allocation scheme for the grinding process and upstream and downstream processes.

[0062] Among them, heuristic algorithms include genetic algorithms and particle swarm optimization algorithms.

[0063] In some embodiments, the robot grinding path optimization method based on the linkage of Industrial Internet of Things and MES provided by the present invention includes the following steps in step S120:

[0064] Step S121: Parse the operating status, processing progress, and cycle time information of each device from the structured data stream, and use the MES system to parse the current task queue and the initial process requirements of each process based on the operating status, processing progress, and cycle time information of each device, so as to generate a task requirement vector.

[0065] Step S122: Define the production scheduling objective as minimizing the overall processing time and waiting time. At the same time, introduce equipment load balancing constraints, construct a production scheduling optimization model, and use the task demand vector as the input of the production scheduling optimization model. Output the production scheduling objective function and the task quantity constraints of each equipment.

[0066] The operating status includes the operating status of the grinding robot, the stamping machine, and the inspection equipment. The operating status of the grinding robot includes temperature, grinding force, and displacement. The operating status of the stamping machine includes stamping pressure and mold temperature. The operating status of the inspection equipment includes dimensional deviation. The processing progress is the percentage of the current workpiece's processing progress. The cycle time information is the processing time of a single piece by the grinding robot. The task requirement vector is composed of the current processing progress percentage of each process, the process standards to be completed for each process, and the real-time operating data obtained by each device.

[0067] In some embodiments, the robot grinding path optimization method based on the linkage of Industrial Internet of Things and MES provided by the present invention further includes the following steps in step S120:

[0068] Step S123: A heuristic algorithm is used to construct a scheduling vector, and at the same time, an equipment allocation vector and a processing time allocation vector are generated to solve the production scheduling objective function and obtain the local or global optimal solution of the production scheduling objective function.

[0069] Step S124: Obtain the final optimized process scheduling vector based on the local or global optimal solution of the production scheduling objective function.

[0070] The scheduling vector consists of the processing sequence number of each workpiece, the equipment allocation vector consists of the corresponding equipment allocated to each workpiece, the processing time allocation vector consists of the expected processing time of each workpiece, and the process scheduling vector consists of the scheduling vector, the equipment allocation vector, and the processing time allocation vector.

[0071] Step S130: The adaptive path fine-tuning algorithm is invoked to fine-tune the offline programming path of the grinding robot during the execution of the best task allocation scheme, so as to generate the optimal path.

[0072] In some embodiments, the robot grinding path optimization method based on the linkage of Industrial Internet of Things and MES provided by the present invention includes the following steps in step S130:

[0073] Step S131: Based on the position of the workpiece in the processing sequence and the equipment allocation information in the process scheduling vector, extract the initial grinding path corresponding to each workpiece from the offline programming database to obtain the defined offline path vector.

[0074] Step S132: During the grinding process, real-time feedback data is collected through multiple sensors to form a real-time feedback vector. Based on the actual grinding quality data of the workpiece and the actual working status data of the equipment, and combined with the offline programming path, correction is performed to establish an error function.

[0075] The offline path vector is composed of the spatial coordinates of each sampling point in the initial polishing path, and the expression for the error function is:

[0076]

[0077] In the formula, E represents the average spatial error, which reflects the degree of deviation between the polishing path and the actual state; M is the total number of path sampling points; and Δx i Δy i Δz i These represent the real-time deviations of the i-th sampling point in the path along the X, Y, and Z axes, respectively.

[0078] In some embodiments, the robot grinding path optimization method based on the linkage of Industrial Internet of Things and MES provided by the present invention further includes the following steps in step S130:

[0079] Step S133: Based on the real-time feedback vector and the average spatial error, obtain the path compensation vector, which is composed of the deviation vector of each sampling point in the initial polishing path. Then, call the dynamic adjustment formula to calculate the corrected path and use the interpolation smoothing algorithm to smooth the corrected path to obtain the adjusted optimal path vector.

[0080] Step S134: The optimal path vector is compared and verified with the actual equipment status through a virtual simulation platform or digital twin system, and the optimal path to be executed by the grinding robot is generated in combination with the defined verification indicators.

[0081] The dynamic adjustment formula is as follows:

[0082] P * =P0+k×ΔP

[0083] In the formula, P * P0 is the corrected path, k is the compensation factor, and ΔP is the path compensation vector.

[0084] Step S140: Monitor the optimal path executed by the grinding robot in real time, and send the real-time monitoring data back to the MES system and the industrial IoT platform. Analyze historical operating data through machine learning to adaptively iteratively optimize the optimal path.

[0085] The real-time monitoring data includes the position data, motion status data, and workpiece processing quality data of the grinding robot.

[0086] In some embodiments, the robot grinding path optimization method based on the linkage of Industrial Internet of Things and MES provided by the present invention includes the following steps in step S140:

[0087] Step S141: By real-time monitoring of the optimal path executed by the grinding robot, the position data, motion state data and workpiece processing quality data of the grinding robot when executing the optimal path are obtained, so as to output a defined feedback data vector consisting of average path deviation, average grinding force standard deviation and workpiece surface processing quality index.

[0088] Step S142: Define a position error vector by taking the optimal path executed by the grinding robot as the ideal path, calculate the path deviation between the actual execution path and the ideal path, and evaluate the error of the feedback data vector.

[0089] In some embodiments, the robot grinding path optimization method based on the linkage between Industrial Internet of Things and MES provided by the present invention further includes the following steps in step S140:

[0090] Step S143: Adjust the compensation factor in the dynamic adjustment formula according to the path deviation between the actual execution path and the ideal path, and obtain the suggested recalibration trigger conditions based on the system response. Output the optimization suggestion vector, and simultaneously send the feedback data vector and the optimization suggestion vector back to the MES system and the industrial IoT platform.

[0091] The optimization suggestion vector consists of the suggested adjustment of the compensation factor, the suggested modification of the feed rate, and the suggested recalibration time or triggering condition.

[0092] It should be noted that MES (Manufacturing Execution System) is a manufacturing execution system whose main functions include production scheduling, work order management, quality tracking, and real-time data acquisition.

[0093] In a specific embodiment, the robot polishing path optimization method based on the linkage of Industrial Internet of Things and MES provided by the present invention includes steps 1 to 4:

[0094] Step 1: Industrial IoT data acquisition and real-time operating condition monitoring.

[0095] By deploying a multi-sensor network through the Industrial Internet of Things (IIoT), real-time status data of the robot grinding unit and various workstations on the production line (such as stamping, inspection, and assembly) can be collected. Edge computing technology is used for data preprocessing to reduce network load and to make some intelligent decisions locally.

[0096] Specifically, this includes steps 1.1 to 1.4:

[0097] Step 1.1, Equipment data acquisition and deployment.

[0098] Raw operational data is collected from production line equipment (grinding robots, stamping machines, testing equipment), including:

[0099] Grinding robot: Equipped with sensors to collect data such as motor temperature, grinding force, and end effector displacement. For example, a temperature sensor collects data in real time (75℃), a force sensor measures the grinding force (12N), and a position encoder outputs the displacement (0.2m).

[0100] Stamping machine: Equipped with a pressure sensor and a die temperature sensor. For example, the pressure sensor collects the stamping pressure (1200kN), and the temperature sensor displays the die temperature (80℃).

[0101] Measurement equipment: This includes optical and dimensional sensors. For example, the measurement equipment outputs a dimensional deviation (0.05 mm).

[0102] Step 1.2, edge computing data preprocessing.

[0103] The raw sensor data collected is filtered and corrected to form digital preprocessed data.

[0104] First, using an edge computing gateway, the raw sensor data is input into the preprocessing module, and a filtering function is applied to obtain the preprocessed vector X. filt Its expression is:

[0105] X filt = [f1(x1), f2(x2), f3(x3)]

[0106] In the formula, x1 is the original temperature data in °C, x2 is the original grinding force or stamping pressure in N or kN, x3 is the original displacement or dimensional deviation in m or mm, and f1, f2, and f3 are the filtering functions for temperature, force, and displacement data, respectively. The filtering algorithm includes moving average or Kalman filtering, and its parameters are determined by the actual sensor characteristics.

[0107] Step 1.3, data fusion and time synchronization.

[0108] Preprocessed data from different devices are merged and timestamps are added to achieve data synchronization across multiple devices.

[0109] First, the digital preprocessed data X from each device filt A unified timestamp t is added based on the collection time to form a time-series fused data vector Y, the expression of which is:

[0110] Y = [t, S, M]

[0111] In the formula, t is the timestamp, in the format YYYY-MM-DDThh:mm:ss, for example, "2025-03-08T10:00:00". S is a structured data flow vector, a vector used to characterize the equipment status, containing key status data for each piece of equipment, namely the grinding robot (temperature, grinding force, displacement), the stamping machine (stamping pressure, die temperature), and the inspection equipment (dimensional deviation). M is the processing progress information, representing the percentage of the current workpiece that has been processed.

[0112] Step 1.4: Generate a structured data stream.

[0113] A structured data stream is constructed based on the fused data vector Y for use in subsequent process scheduling.

[0114] First, define a structured data flow vector S, whose expression is:

[0115] S = [D, P, B]

[0116] In the formula, D represents the equipment status data, including the status of the grinding robot, the stamping machine, and the testing equipment; P represents the processing progress information, taken from M; and B represents the cycle time information, indicating the processing time of a single piece of equipment, such as the grinding robot requiring 45 seconds to process each workpiece.

[0117] Step 2: Production scheduling optimization of the MES system.

[0118] The MES system receives data streams from the IIoT and, combined with order requirements, process specifications, and historical data, optimizes production scheduling at the production line level. It employs reinforcement learning or heuristic algorithms (such as genetic algorithms and particle swarm optimization) to calculate the optimal task allocation scheme, ensuring coordinated operation of the polishing process with upstream and downstream processes (stamping, assembly, and inspection), thereby reducing production bottlenecks.

[0119] Specifically, this includes steps 2.1 to 2.4:

[0120] Step 2.1: Structured data parsing and task requirement extraction.

[0121] The status, processing progress, and cycle time information of each device are parsed from the structured data flow vector S generated in step 1, providing initial parameters for production scheduling.

[0122] First, the structured data flow vector S = [D, P, B] is input. Based on the data in S, the MES system will parse the current task queue and the initial process requirements of each process, generating a task requirement vector T. rep :

[0123] T rep = [p, c, s]

[0124] In the formula, p is the current processing progress percentage of each workpiece, c is the process standard to be completed for each process, such as surface finish requirements and dimensional tolerances, and s is the real-time status information of each piece of equipment.

[0125] Step 2.2: Establish the production scheduling objective function.

[0126] Construct a production scheduling optimization model that considers processing time, waiting time, and equipment load balancing.

[0127] First, the production scheduling objective is defined as minimizing the overall processing and waiting time, and its expression is:

[0128]

[0129] In the formula, F is the objective function for production scheduling optimization, N is the total number of workpieces to be processed, and t is the total number of workpieces to be processed. p，it represents the actual processing time for the i-th workpiece, in seconds. This time is determined by the process requirements of each workpiece and the actual capabilities of the equipment; an initial step value of 45–60 seconds is acceptable. w，i The waiting time for the i-th workpiece (such as equipment idle waiting time or tool change time) is in seconds. It is calculated based on the equipment load. For example, when the current equipment load exceeds 80%, the extra waiting time can be set to 5-10 seconds.

[0130] Simultaneously, a load balancing constraint is introduced, assigning a task quantity n to each piece of equipment j (such as a grinding robot, a stamping machine, or an inspection device). j It should meet the following requirements:

[0131] max(n j )-min(n j )≤Δn

[0132] In the formula, Δn represents the allowable difference in the number of tasks, such as: n j -n i , representing the different number of tasks n j With n i The difference between them is used to ensure balanced scheduling.

[0133] Step 2.3: Generation of scheduling optimization algorithms and scheduling schemes.

[0134] Using optimization algorithms, a preliminary process schedule is generated based on the production scheduling objective function F and task requirements.

[0135] First, a heuristic algorithm (such as a genetic algorithm or particle swarm optimization algorithm) is used to solve the production scheduling objective function F, and a scheduling vector Q = [q1, q2, ..., q] is constructed. i , ..., q N ], where q i The processing order number for the i-th workpiece is assigned, such as q1 = 3 indicating that the third workpiece is processed first. Simultaneously, a device allocation vector R = (r1, r2, ..., r...) is generated. i ,...,r N ), where r i This indicates that the i-th workpiece is assigned to a certain device (e.g., "1" represents grinding robot A, "2" represents grinding robot B). Subsequently, a processing time allocation vector L = [l1, l2, ..., l...] ​​is generated. i , ..., l N ], where l i Let N represent the expected processing time for the i-th workpiece, and N represent the total number of sampling points.

[0136] Formula objective:

[0137]

[0138] The scheduling algorithm continuously adjusts Q, R, and L during the iteration process until the objective function F reaches a local or global optimum.

[0139] Step 2.4: Generate the optimized process schedule.

[0140] By integrating the aforementioned scheduling vectors, the final optimized process schedule is formed.

[0141] First, define the final optimized process scheduling vector S. opt for:

[0142] S opt =[Q,R,L]

[0143] For example, assuming that 5 workpieces need to be polished, the optimized scheduling scheme can be:

[0144] The processing sequence Q = [2, 5, 1, 3, 4] means that the second workpiece is processed first, followed by the fifth workpiece, and so on.

[0145] The equipment allocation R = (1, 2, 1, 2, 1) indicates that workpieces 2, 1, and 4 are processed by grinding robot A (number 1), and workpieces 5 and 3 are processed by grinding robot B (number 2).

[0146] The processing time L = [45, 50, 47, 52, 46] seconds, which are adjusted according to the actual processing requirements of the workpiece and the equipment capacity.

[0147] Final scheduling scheme S opt =[Q,R,L] simultaneously satisfies the requirements of production cycle time, equipment load balancing, and priority.

[0148] Step 3: Robot path optimization and dynamic adjustment.

[0149] Based on the MES scheduling results, the offline programming path of the grinding robot is further optimized to ensure that the path selection takes into account production cycle time, production line layout, and equipment status. An adaptive path adjustment algorithm (such as D* dynamic path planning) is adopted to make fine adjustments based on real-time data during robot execution, such as avoiding bottlenecks in other processes and adjusting the feed speed.

[0150] Specifically, this includes steps 3.1 to 3.4:

[0151] Step 3.1: Extraction of offline programming paths and construction of initial path schemes.

[0152] Based on the optimized process schedule S generated in step 2 opt Extract the offline programming path and construct an initial path scheme.

[0153] First, obtain the optimized process schedule S from step 2. opt =[Q,R,L], based on the workpiece's position in the processing sequence and equipment allocation information, the initial grinding path corresponding to each workpiece is extracted from the offline programming database. The defined offline path vector is: P0 = [p1, p2, ..., p...]. i , ..., p M ], P0 represents the initial offline path, p i Let p be the spatial coordinates of the i-th sampling point in the path. i =[x i y i , z i ], x i y i , z i These represent the positions of the sampling points along the X, Y, and Z coordinate axes, typically in mm. M is the total number of sampling points along the path, determined based on the complexity of the workpiece and the offline programming settings.

[0154] Step 3.2, Real-time data acquisition and path deviation calculation.

[0155] By using real-time sensor data, deviations of the workpiece or grinding robot during the actual grinding process are detected, and the path correction amount is calculated.

[0156] During the polishing process, real-time data is collected using sensors such as vision, force / torque, and displacement to form a real-time feedback vector: R f =[δ1, δ2, ..., δ i ,...,δ M In the formula, δ i Let δ represent the deviation vector from the i-th sampling point corresponding to the initial path. i =[Δx i Δy i Δz i ], Δx i Δy i Δz i These represent the real-time deviations of the point in the X, Y, and Z coordinate axes, respectively, in mm. The deviation values ​​are obtained by comparing the sensor-collected data with the preset path coordinates, and the algorithm parameters are set according to the sensor accuracy.

[0157] Simultaneously, actual workpiece grinding quality data (such as surface roughness) and equipment operating status data are collected, and corrections are performed using the offline programming path to establish an error function E:

[0158]

[0159] In the formula, E represents the average spatial error, which reflects the degree of deviation between the grinding path and the actual state.

[0160] Step 3.3, Dynamic path adjustment algorithm and compensation calculation.

[0161] Based on real-time feedback vector R f Based on the error function E, the initial path P0 is optimized twice using a dynamic path adjustment algorithm to generate a compensated path.

[0162] First, define the path compensation vector ΔP as: ΔP = [δ1, δ2, ... δ M The corrected path P is calculated using a dynamic adjustment formula. * Its expression is:

[0163] P * =P0+k×ΔP

[0164] In the formula, P * P0 is the corrected path, P0 is the initial path before correction, k is the compensation factor, which generally ranges from 0.8 to 1.2 and is dynamically adjusted according to the real-time error E. When E is large, k can be appropriately increased (e.g., increased to 1.1 to 1.2), and when E is small, k can be appropriately decreased (e.g., decreased to 0.8 to 1.0). ΔP is the path compensation vector.

[0165] To ensure path smoothness, interpolation smoothing algorithms (such as B-splines or Bézier curves) are applied to P. * After smoothing, the final path P is obtained. opt Its expression is:

[0166] P opt =Smooth(P * )

[0167] In the formula, Smooth is a smoothing algorithm used to ensure path continuity and the smoothness of the grinding robot's movement.

[0168] Step 3.4, Optimal path verification and real-time update.

[0169] The optimal path P generated by dynamic adjustment opt Perform real-time verification and ensure continuous updates during the polishing robot's operation.

[0170] First, using a virtual simulation platform or digital twin system, P opt The path is compared and verified with the real-time device status to ensure that it does not lead to robot collisions or excessive cutting. Secondly, a verification metric V is defined, with the expression:

[0171]

[0172] In the formula, For the index function, if If the preset safe distance is met, then Otherwise, the value is 0. The range of V is between 0 and 1. If V ≥ 0.95, the path is considered safe and reliable. If the verification index V does not meet the requirements, the compensation factor k is adjusted or ΔP is recalculated until V meets the standard. At the same time, the system continuously collects new sensor data in real time and repeats steps 3.2 and 3.3 based on the new deviation information to achieve closed-loop feedback updates.

[0173] In this embodiment, the optimal path expression executed by the grinding robot is:

[0174] P exec =P opt

[0175] Among them, P exec =[P exec，1 P exec，2 , ..., P exec，i , ..., P exec，M ], P exec，i This indicates the coordinates of the sampling point after real-time verification, used to ensure that the grinding robot moves along this path during actual operation.

[0176] Step 4: Closed-loop feedback and continuous optimization.

[0177] After the grinding robot performs its task, it transmits key process parameters (such as grinding force, time, and quality inspection results) back to the MES and IIoT platform, forming a closed-loop feedback in the production process. By analyzing historical data through machine learning, the grinding strategy is further optimized to achieve adaptive iterative optimization.

[0178] Specifically, this includes steps 4.1 to 4.4:

[0179] Step 4.1, Real-time data monitoring and feedback collection.

[0180] The optimal path executed by the robot is monitored in real time, and its motion status and processing quality data are collected.

[0181] First, based on the optimal path P executed by the robot in step 3. exec Real-time data acquisition includes position data (such as the deviation between the actual path point and the preset path point), motion state data (such as acceleration and the force value of the end effector), and processing quality data (such as the surface roughness of the workpiece). A feedback data vector is defined as: F = [f1, f2, f3], where f1 is the average path deviation, f2 is the average grinding force fluctuation (standard deviation), and f3 is the workpiece surface processing quality index.

[0182] Step 4.2, Error assessment and feedback data processing.

[0183] Error assessment is performed on the collected feedback data to calculate the deviation between the actual execution path and the ideal path, and other key indicators are quantified.

[0184] First, let the ideal path be the optimal path adjusted in step 3, and define the position error vector E. p E p = [e1, e2, ..., e i , ..., e M In the formula,

[0185]

[0186] Among them, e i The spatial error of the i-th sampling point is expressed in mm, x. opt，i y opt，i z opt，i These are the preset target coordinates, x and x. exec，i y exec，i z exec，i These are the coordinate values ​​executed by the grinding robot.

[0187] Next, calculate the average path deviation:

[0188]

[0189] Simultaneously, the fluctuation of grinding force data is collected, its standard deviation f2 is calculated, and the average value f3 of surface roughness data is obtained.

[0190] Step 4.3, optimize the suggestion generation algorithm.

[0191] Based on the feedback data F, targeted optimization suggestions are generated to adjust the offline path compensation factor and feed parameters of the grinding robot.

[0192] First, define the optimization suggestion vector: G = [g1, g2, g3], where g1 represents the suggested change in the compensation factor, g2 represents the suggested change in the feed rate, and g3 represents the suggested recalibration time or trigger condition.

[0193] Adjust the compensation factor k based on the magnitude of the feedback data f1. For example, let the current compensation factor be k. old (It serves the same purpose as the adjustment factor k, the difference being k) old The adjustment compensation factor at the current moment is used to adjust the current adjustment compensation factor k. old (Compensation and correction of the current offline path) can be performed according to the formula:

[0194]

[0195] Wherein, Δk is the suggested change in the compensation factor, which typically ranges from 0.05 to 0.1.

[0196] Regarding feed rate, if the feedback data shows a grinding quality deviation f3 (e.g., exceeding the target by 1.0 μm) or excessive force fluctuation f2 (e.g., exceeding 3.0 N), it is recommended to reduce the feed rate v. The formula is as follows:

[0197]

[0198] The suggested value for Δv is 0.01 to 0.05 m / s.

[0199] Based on the system response, it is recommended to set the recalibration trigger condition g3, such as:

[0200]

[0201] Step 4.4: Output and callback of feedback data and optimization suggestions.

[0202] The generated feedback data and optimization suggestions are transmitted to the control system to achieve closed-loop feedback and guide the dynamic adjustment of subsequent paths.

[0203] The specific application scenarios of this invention are as follows:

[0204] Case 1: Path optimization for high-cycle production of small Class A workpieces

[0205] 1. Specific parameters of the MES scheduling result:

[0206] Production cycle time: 45 seconds per workpiece (each workpiece is required to be polished within 45 seconds).

[0207] Workpiece priority: Category A workpieces take precedence over Category B workpieces. The current order primarily consists of Category A workpieces and should be completed first.

[0208] Equipment load status: Grinding robot A is performing grinding tasks on the production line. The current load rate is about 85%, which is close to its full load.

[0209] Other parameters: Category A workpieces are small aluminum alloy parts with a medium surface finish required; Category B workpieces currently have fewer orders and have little impact on production capacity.

[0210] 2. The original offline programming path:

[0211] Grinding sequence: Robot A grinds each surface and edge of the workpiece in a fixed order. For example, it grinds the outer surface first and then processes all the edges.

[0212] Feed rate: The initial programming set the feed rate to 0.2 m / s to ensure surface quality, but the 45-second cycle time requirement was not fully considered.

[0213] Tool change timing: The robot uses two grinding tools (rough grinding wheel and polishing wheel). The original path was to change tools once after rough grinding of all surfaces, and then perform polishing; that is, fine polishing would only begin after rough grinding of each workpiece was completed.

[0214] Path characteristics: The initial path is not optimized for a 45-second cycle time. The actual polishing time for a single piece is about 50 seconds, with excess idle strokes and waiting time.

[0215] 3. Secondary optimization path based on MES scheduling:

[0216] Optimize the path sequence: Based on the cycle time requirements provided by MES, replan the grinding sequence to reduce the time the robot spends moving back and forth between different surfaces. For example, adjust the process to grind adjacent surfaces continuously before moving to the next area, avoiding frequent jumping movements and thus reducing idle time.

[0217] Shorten tool change time: To meet the requirement of completing grinding within 45 seconds, the tool change strategy has been optimized. Just before the rough grinding is finished, the robot moves closer to the tool changer to complete the tool change as quickly as possible, reducing the time required for tool changes. If necessary, segmented processing can also be used: the workpiece is divided into sections, and after rough grinding of one section, polishing is immediately performed on that area. This segmented cycle avoids prolonged pauses during concentrated tool changes.

[0218] Adjust the feed rate: While ensuring quality, increase the feed rate to 0.25 m / s to speed up the grinding process. For areas with lower surface finish requirements, further increase the speed to save time, while maintaining an appropriate speed for areas with high requirements to balance quality and efficiency.

[0219] Optimization Results: Through the above optimizations, the grinding time for a single piece by robot A is reduced to approximately 45 seconds, synchronizing with the production cycle. Workpieces of type A are still processed according to their priority order, while workpieces of type B are inserted when there is free time, without affecting the timely completion of workpieces of type A.

[0220] Case 2: Multi-process grinding optimization for Class A precision parts and Class B structural parts

[0221] 1. Specific parameters of the MES scheduling result:

[0222] Production cycle time: 90 seconds / workpiece (the planned time for each workpiece to be polished is approximately 90 seconds, including two processes: rough grinding and fine grinding).

[0223] Workpiece priority: Category A workpieces (such as exterior parts, requiring high surface finish) take precedence over Category B workpieces (such as internal structural parts, with lower surface finish requirements). The MES system issues instructions requiring the delivery deadlines of Category A workpieces to be met first.

[0224] Equipment load status: Grinding robot A is responsible for processing all workpieces at this station. The current load rate is about 75%, and it needs to handle both A-class and B-class workpieces.

[0225] Other parameters: Type A workpieces require two steps, rough grinding and fine grinding, to meet the surface requirements; Type B workpieces only need rough grinding to remove burrs (fine grinding is not necessary), which affects the grinding path and tool change requirements.

[0226] 2. The original offline programming path:

[0227] Grinding sequence: To improve equipment utilization, the original path adopted a process merging strategy. For example, multiple workpieces arriving consecutively are first rough-ground, and then the tool is changed for fine grinding. Specifically, robot A first rough-grounds a batch of workpieces (including types A and B) one by one, and then changes to a fine grinding tool to complete the fine grinding one by one.

[0228] Feed rate: The feed rate is set to 0.3 m / s during the rough grinding stage and 0.15 m / s during the fine grinding stage to ensure high surface quality for Class A workpieces. This speed setting is consistent for all workpieces and is not differentiated based on workpiece priority.

[0229] Tool change timing: The original programming performs a single tool change for finish grinding after all rough grinding tasks are completed, meaning only one tool change occurs per batch of workpieces. However, this means that after rough grinding of a certain type A workpiece is completed, finish grinding can only begin after all workpieces in that batch have finished rough grinding and had their tools changed, thus extending the overall machining time for type A workpieces.

[0230] Problem: Although batch processing reduces the frequency of tool changes, the fine grinding of Class A workpieces is delayed and cannot be completed as early as possible, which violates the priority delivery requirement.

[0231] 3. Secondary optimization path based on MES scheduling:

[0232] Optimize the path sequence: Based on the priority requirements provided by the MES, adjust the grinding sequence to complete all processes for Class A workpieces first. Specifically, for Class A workpieces, instead of waiting for all workpieces to finish rough grinding, immediately change tools for fine grinding after rough grinding to ensure that Class A workpieces are completed as early as possible. Fine grinding of Class B workpieces can be postponed and processed uniformly, or only rough grinding can be performed and the workpiece can be temporarily stored, waiting for an idle time for fine grinding.

[0233] Reduce tool change time: To address the increased tool change time for Class A workpieces, optimize the program to reduce tool change time. For example, at the end of the rough grinding phase of a Class A workpiece, the robot decelerates early and approaches the tool change position to switch to the fine grinding tool as quickly as possible. For multiple consecutive Class A workpieces, rough grinding is completed sequentially as much as possible, followed by immediate fine grinding of each workpiece, with rapid tool changes between each workpiece, utilizing the overlap time of robot movements to shorten downtime.

[0234] Adjust feed rate: Use differentiated feed rates for workpieces with different priorities. For Class A workpieces, appropriately increase the speed during rough grinding and fine grinding (e.g., increase rough grinding to 0.35 m / s) to speed up processing and shorten the total time while ensuring quality; while for Class B workpieces, due to their lower priority, the rough grinding speed can be slightly reduced to 0.25 m / s, thereby extending their processing time and allowing time to prioritize the completion of Class A workpieces.

[0235] Optimization Results: Through the above adjustments, Class A workpieces can be completed independently and quickly without waiting for batch processing, reducing the total processing time per piece from approximately 100 seconds to nearly 90 seconds, thus meeting the priority delivery requirements. Meanwhile, although the finishing time for Class B workpieces is slightly delayed or processed at a slower speed, it remains within the allowable cycle time and does not affect the overall production rhythm.

[0236] Case 3: Load Balancing Optimization in Dual-Robot Collaborative Grinding

[0237] 1. Specific parameters of the MES scheduling result:

[0238] Production cycle time: 60 seconds / workpiece (the production line cycle time is 60 seconds, and one workpiece needs to be polished every minute).

[0239] Workpiece priority: Category A workpieces take precedence over Category B workpieces. Currently, Category A workpieces account for approximately 70% of the order quantity, while Category B workpieces account for approximately 30%. Category A orders are urgent and require expedited processing.

[0240] Equipment load status: Grinding robot A is currently at 85% load, while robot B is at 60% load. Robot A is overloaded and has become a bottleneck, while robot B still has spare capacity.

[0241] Other parameters: The two robots are located in parallel workstations and originally each processed a fixed type of workpiece (Robot A processes type A workpieces, and Robot B processes type B workpieces). The process flow and grinding tools are slightly different but similar in general.

[0242] 2. The original offline programming path:

[0243] Grinding sequence: Robots A and B grind independently according to a fixed order for their respective workpiece types. Robot A continuously processes the queue of workpieces of type A, while robot B processes the queue of workpieces of type B. As a result, robot A often operates continuously without idle time, while robot B waits for the next batch after completing its current batch of workpieces of type B, thus having idle time.

[0244] Feed rate: Both robots operate according to standard parameters, with A and B using the same default feed rate (e.g., 0.3 m / s) without adjustment based on their respective load conditions. Robot A, due to prolonged high-load operation, has approached its cycle time limit.

[0245] Tool Change Timing: Each robot changes tools according to its own process requirements. Assume that workpiece A requires one tool change (rough grinding → fine grinding), while workpiece B uses a single grinding wheel and does not require frequent tool changes. The original programming did not consider task coordination and tool change coordination between the two robots.

[0246] Problem: Under this setup, robot A is busy processing a large number of A-type workpieces, while robot B is often idle. Although the overall production line can barely meet the 60-second cycle time, there is a backlog of A-type workpieces, which poses a risk of delays and results in uneven equipment utilization.

[0247] 3. Secondary optimization path based on MES scheduling:

[0248] Optimize task allocation: Based on the MES scheduling results, some Class A workpieces are reassigned to robot B for processing to achieve load balancing. Adjust the offline programming to enable robot B to execute the grinding path for Class A workpieces. For example, modify robot B's program to add the grinding sequence and actions for Class A workpieces, allowing it to take over processing Class A workpieces when there are no Class B tasks available. In this way, the two robots can process Class A workpieces in parallel (grinding different workpieces separately), completing more Class A workpieces per unit time.

[0249] Reduce tool change and waiting time: As robot B begins handling type A workpieces, it also needs to change tools for rough and fine grinding. Optimize the program so that robot B can prepare for tool changes in advance during idle periods, ensuring no additional tool change time is incurred when taking over type A workpieces. For robot A, if certain minor surfaces or steps of type A workpieces can be handled by robot B, robot A can skip the corresponding operations and tool changes and directly move on to the next workpiece, reducing waiting time.

[0250] Adjusting the feed rate: After load balancing, the pressure on robot A is reduced, and it can grind at a steady speed to ensure quality; when robot B takes on more tasks, the feed rate can be slightly increased within the allowable range (e.g., from 0.3m / s to 0.35m / s) to shorten the time it takes to process each type A workpiece and help the whole system keep up with the cycle time requirements.

[0251] Optimization Results: After secondary optimization, the two robots work collaboratively: Robot A's load is reduced to approximately 70%, while Robot B's increases to approximately 75%, resulting in more balanced capacity utilization. The grinding path for each workpiece is re-programmed according to scheduling requirements, ensuring that the processing of type A workpieces is prioritized within a 60-second cycle time. Type B workpieces are processed by Robot B during gaps, without affecting the priority production of type A workpieces. Overall production efficiency is improved, and the on-time delivery rate of key workpieces is increased.

[0252] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. "A plurality of" means two or more, unless otherwise explicitly specified.

[0253] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0254] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0255] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0256] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0257] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0258] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0259] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0260] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0261] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A robot polishing path optimization method based on linkage of industrial Internet of Things and MES, characterized in that, The method comprises: obtaining real-time operation data of production line equipment through an industrial internet of things deployment multi-sensor network, and pre-processing the real-time operation data using edge computing technology to construct a structured data stream; calculating an optimal task allocation scheme for a polishing process and upstream and downstream processes based on the structured data stream from the industrial internet of things, in combination with order demand, process requirements, and historical operation data, using reinforcement learning or a heuristic algorithm; calling an adaptive path fine-tuning algorithm to fine-tune the offline programming path of the polishing robot during execution of the optimal task allocation scheme by the polishing robot, to generate an optimal path; real-time monitoring the optimal path executed by the polishing robot, and returning real-time monitoring data to an MES system and an industrial internet of things platform, and iteratively optimizing the optimal path adaptively through machine learning analysis of historical operation data; wherein the production line equipment comprises a polishing robot, a punching machine, and a detection device, the heuristic algorithm comprises a genetic algorithm and a particle swarm optimization algorithm, and the real-time monitoring data comprises position data, motion state data, and workpiece processing quality data of the polishing robot; the calling of the adaptive path fine-tuning algorithm to fine-tune the offline programming path of the polishing robot during execution of the optimal task allocation scheme by the polishing robot to generate an optimal path comprises: extracting an initial polishing path corresponding to each workpiece from an offline programming database according to the position of the workpiece in the machining sequence and the device allocation information in the process scheduling vector, to obtain a defined offline path vector; collecting real-time feedback data through multiple sensors during the polishing process to form a real-time feedback vector, and correcting in combination with the offline programming path according to workpiece actual polishing quality data and device actual working state data, to establish an error function; wherein the offline path vector is composed of the spatial coordinates of each sampling point in the initial polishing path, and the expression of the error function is: In the formula, E represents the average spatial error, used to reflect the deviation degree between the polishing path and the actual state, M is the total number of path sampling points, 、 、 are the real-time deviations of the i-th sampling point in the path in the X, Y, and Z axis directions, respectively. the calling of the adaptive path fine-tuning algorithm to fine-tune the offline programming path of the polishing robot during execution of the optimal task allocation scheme by the polishing robot to generate an optimal path further comprises: based on the real-time feedback vector and the average spatial error, obtaining a defined path compensation vector composed of a deviation vector of each sampling point in the initial polishing path, and calling a dynamic adjustment formula to calculate a corrected path, to smooth the corrected path using an interpolation smoothing algorithm to obtain an adjusted optimal path vector; comparing and verifying the optimal path vector with the actual device state through a virtual simulation platform or a digital twin system, and generating an optimal path executed by the polishing robot in combination with defined verification indicators; wherein the dynamic adjustment formula is: wherein, is the modified path, is the initial path before modification, is the compensation factor, is the path compensation vector.

2. The robot polishing path optimization method based on the linkage of the industrial Internet of Things and the MES according to claim 1, characterized in that, the obtaining of real-time operation data of production line equipment through an industrial internet of things deployment multi-sensor network, and the pre-processing of the real-time operation data using edge computing technology to construct a structured data stream comprises: Raw operation data is collected from the production line equipment and sent to a preprocessing unit using an edge computing gateway to preprocess the raw operation data through a filtering function to obtain digitized preprocessing data; The digitized preprocessing data of different equipment is fused, a uniform timestamp is added according to the data collection time to form a time-series fusion data vector, and the structured data stream is constructed based on the fusion data vector; The raw operation data includes motor temperature, polishing force, and end position of the polishing robot, and stamping pressure and mold temperature of the stamping machine, as well as optical and dimensional sensor data of the detection equipment.

3. The robot polishing path optimization method based on the linkage of the industrial Internet of Things and the MES according to claim 2, characterized in that, The structured data stream from the industrial Internet of Things is used to calculate the optimal task allocation scheme for the polishing process and upstream and downstream processes based on the structured data stream from the industrial Internet of Things, combined with order demand, process requirements, and historical operation data, including: The running state, processing progress, and beat information of each device are parsed from the structured data stream, and the current task queue and initial process requirements of each process are parsed from the running state, processing progress, and beat information of each device through the MES system to generate a task demand vector; The production scheduling optimization model is constructed by defining the production scheduling target as minimizing the overall processing time and waiting time, while introducing device load balancing constraints, and taking the task demand vector as the input of the production scheduling optimization model to output the production scheduling objective function and the task quantity constraint of each device. The running state includes the polishing robot running state, stamping machine running state, and detection equipment running state, the polishing robot running state includes temperature, polishing force, and displacement, the stamping machine running state includes stamping pressure and mold temperature, and the detection equipment running state includes dimensional deviation, the processing progress is the processing progress percentage of the current workpiece, the beat information is the single piece processing time of the polishing robot, and the task demand vector is composed of the processing progress percentage of each process, the process standard required by each process, and the real-time operation data obtained by each device.

4. The robot polishing path optimization method based on industrial Internet of Things and MES linkage according to claim 3, characterized in that, The structured data stream from the industrial Internet of Things is used to calculate the optimal task allocation scheme for the polishing process and upstream and downstream processes based on the structured data stream from the industrial Internet of Things, combined with order demand, process requirements, and historical operation data, including: The heuristic algorithm is used to construct a scheduling vector, generate a device allocation vector and a processing time allocation vector, and solve the production scheduling objective function to obtain a local or global optimal solution of the production scheduling objective function; Based on the local or global optimal solution of the production scheduling objective function, the final optimized process scheduling vector is obtained; The scheduling vector is composed of the processing order number of each workpiece, the device allocation vector is composed of the corresponding device allocated to each workpiece, the processing time allocation vector is composed of the expected processing time of each workpiece, and the process scheduling vector is composed of the scheduling vector, device allocation vector, and processing time allocation vector.

5. The robot polishing path optimization method based on industrial Internet of Things and MES linkage according to claim 4, characterized in that, The optimal path executed by the polishing robot is monitored in real time, and real-time monitoring data is fed back to the MES system and the industrial Internet of Things platform. Historical operation data is analyzed through machine learning to adaptively and iteratively optimize the optimal path, including: The position data, motion state data, and workpiece processing quality data when the polishing robot executes the optimal path are obtained by real-time monitoring of the optimal path executed by the polishing robot, to output a defined feedback data vector composed of average path deviation, average polishing force standard deviation, and workpiece surface processing quality index; A position error vector is defined based on the optimal path executed by the polishing robot as an ideal path, the path deviation between the actual execution path and the ideal path is calculated, and the feedback data vector is error-evaluated.

6. The robot polishing path optimization method based on industrial Internet of Things and MES linkage according to claim 5, characterized in that, The optimal path executed by the polishing robot is monitored in real time, and real-time monitoring data is fed back to the MES system and the industrial Internet of Things platform. Historical operation data is analyzed through machine learning to adaptively and iteratively optimize the optimal path, and further includes: According to the path deviation between the actual execution path and the ideal path, the compensation factor in the dynamic adjustment formula is adjusted, and the recommended setting of the recalibration trigger condition is obtained according to the system response, an optimization suggestion vector is output, and the feedback data vector and the optimization suggestion vector are fed back to the MES system and the industrial Internet of Things platform; The optimization suggestion vector is composed of the recommended adjustment of the compensation factor change, the recommended modification of the feed speed adjustment, and the recommended recalibration time or trigger condition.

7. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is used to operate according to the instructions to perform the steps of the method according to any one of claims 1-6.

8. A computer readable storage medium having stored thereon a computer program, characterized in that The program is executed by the processor to realize the steps of the method according to any one of claims 1-6.

Images