Manufacturing unit innovation platform building method based on digital twin industrial robot

Abstract

The invention discloses a manufacturing unit innovation platform building method based on a digital twin industrial robot, and relates to the field of digital twin industrial robots, and the manufacturing unit innovation platform building method based on the digital twin industrial robot comprises the following steps: collecting a building parameter set, generating a construction plan according to the construction parameter set, inputting manual intervention, and combining the manual intervention with the construction plan to generate a construction scheme; and receiving building construction parameters, and comparing the building construction parameters with the building scheme to obtain a deviation correction data set. The building scheme is generated by collecting the building parameters and combining with manual intervention, then the building construction parameters and the building scheme are compared in real time to obtain deviation correction data, and the building accuracy of the manufacturing unit is ensured. The process not only improves the building efficiency, but also effectively reduces the production risk caused by the building deviation, and improves the overall performance of the manufacturing unit.

Description

Technical Field

[0001] The present invention relates to the field of digital twin industrial robots, and specifically to a method for building an innovative platform for a manufacturing unit based on digital twin industrial robots. Background Art

[0002] With the advent of the era of intelligent manufacturing, digital twin technology has become a key force in promoting industrial transformation and upgrading. Digital twin industrial robots, as one of the core applications of this technology, achieve accurate monitoring and efficient management of the robot's operating status by building a real-time mapping relationship between virtual models and physical robots. This technology not only improves production efficiency and product quality, but also significantly reduces operating costs and safety risks, providing strong support for the intelligent and automated development of the manufacturing industry.

[0003] In the existing technology, the construction of manufacturing units usually relies on traditional engineering design and manual debugging methods. This makes errors prone to occur during the construction process and difficult to detect and correct in time. At the same time, in terms of robot failure prediction, the existing technology mainly relies on regular maintenance and sensor detection.

[0004] In view of the shortcomings of existing technologies in manufacturing unit construction and robot fault prediction, we can find the following main problems: First, the manual control of manufacturing unit construction has poor error effect and lacks accurate data support and real-time feedback mechanism, which makes it difficult to ensure construction accuracy; second, fault prediction is insufficient and cannot be automatically adjusted. Existing technologies mainly rely on regular maintenance and sensor detection, and can only provide fault warning based on real-time data, and do not have automatic adjustment capabilities. Summary of the invention

[0005] The present application provides a method for building an innovative platform for a manufacturing unit based on a digital twin industrial robot, which is used to solve the technical problems of poor error effect, insufficient fault prediction and inability to automatically adjust in the existing manually controlled manufacturing unit construction.

[0006] In view of the above problems, the present application provides a method for building an innovation platform for a manufacturing unit based on a digital twin industrial robot, comprising the following steps: collecting a set of building parameters, generating a building plan according to the set of building parameters, entering manual intervention, and combining the manual intervention with the building plan to generate a building solution; receiving building construction parameters, comparing the building construction parameters with the building solution, and obtaining a correction data set; collecting a set of sensor data during the operation of the robot, analyzing the sensor data set to obtain robot operation status prediction data; collecting product quality inspection data, analyzing and establishing a relationship model between the quality inspection data and the robot operation status prediction data, and inputting the operation status prediction data according to the model to obtain failure rate prediction data; when the predicted failure rate reaches a set value, using a random environment to generate an adjustment plan, simulating and predicting the adjustment plan, and obtaining the optimal solution.

[0007] In summary, the present invention mainly has the following beneficial effects:

[0008] 1. The present invention collects construction parameters and generates a construction plan in combination with manual intervention, and then compares the construction parameters and the construction plan in real time to obtain correction data, thereby ensuring the accuracy of the construction of the manufacturing unit. This process not only improves the construction efficiency, but also effectively reduces the production risks caused by construction deviations and improves the overall performance of the manufacturing unit.

[0009] 2. The present invention collects and analyzes sensor data during the operation of the robot, establishes a relationship model between quality inspection data and the robot's operating status, and thus predicts the failure rate. When the predicted failure rate reaches a set threshold, an adjustment plan is automatically generated and evaluated to determine the optimal solution. This method effectively prevents robot failures, ensures the stable operation of the production line, and improves production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 This is a logic diagram of a method for building an innovative platform for a manufacturing unit based on a digital twin industrial robot according to the present invention. DETAILED DESCRIPTION

[0011] The present application provides a method for building an innovative platform for a manufacturing unit based on a digital twin industrial robot, which is used to solve the technical problems of poor error effect, insufficient fault prediction and inability to automatically adjust in the existing manually controlled manufacturing unit construction.

[0012] After introducing the basic principles of the present application, the technical solutions in the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described here. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0013] Embodiment 1

[0014] A method for building a manufacturing unit innovation platform based on a digital twin industrial robot comprises the following steps:

[0015] S100: Collecting a set of building parameters, generating a building plan according to the set of building parameters, inputting manual intervention, and combining the manual intervention with the building plan to generate a building solution;

[0016] This includes the size, shape, ground material, load-bearing capacity, etc. of the site, which will directly affect the layout and movement path of the industrial robot. For example, if the site is small and the load-bearing capacity is limited, it is necessary to select a smaller and lighter industrial robot and plan its movement path reasonably.

[0017] Among them, S100 also includes:

[0018] S111: Collecting site environment model parameters as first building parameters;

[0019] S112: Collect device model parameters as second building parameters;

[0020] S113: Collect the equipment running radius as the third setting parameter;

[0021] S114: Collecting other component model parameters as fourth building parameters;

[0022] S115: taking the first construction parameter, the second construction parameter, the third construction parameter and the fourth construction parameter as the construction parameter set.

[0023] These parameters include but are not limited to the model, size, weight, and functional characteristics of the industrial robot. Whether the industrial robot has multiple functions such as grasping, handling, and processing, as well as the implementation methods and efficiency of these functions. The operating radius of the acquisition equipment refers to the maximum range that the industrial robot can cover under normal working conditions. This parameter is crucial to determining the number and layout of industrial robots. If the equipment operating radius is small, we need to increase the number of industrial robots to ensure the efficient operation of the entire manufacturing unit.

[0024] Other component model parameters include parameters of various sensors, controllers, actuators and other components used with industrial robots. It is necessary to understand the sensitivity, accuracy and response time of the sensor to ensure that it can accurately reflect the operating status of the industrial robot.

[0025] Among them, S100 also includes:

[0026] S121: parsing the set of building parameters;

[0027] S122: inputting manual intervention, analyzing the required part of the manual intervention, randomly generating multiple groups of random plans, simulating and running the random plans, and outputting the random plans that have passed the running as optional plans;

[0028] S123: re-enter the manual intervention, analyze the manual intervention and adjust the optional plan, output it after adjustment, and repeat this step until the manual intervention confirms any plan, and output the plan as the construction plan.

[0029] The collected set of building parameters is parsed and processed to extract key information. Exemplarily, based on the parsed set of building parameters, multiple sets of building plans are randomly generated using computer algorithms. These plans will cover different industrial robot layouts, movement paths, and component configurations. These plans are simulated and run, and plans that can successfully pass the simulation test are screened out as optional plans. After obtaining the optional plan, manual intervention will be entered again to adjust and optimize the plan. This includes adjusting the number and layout of industrial robots, optimizing movement paths, replacing or upgrading components, etc. according to actual needs. After adjustment, a new plan will be output, and this step will be repeated until manual intervention confirms that any plan is the final building plan.

[0030] S200: receiving construction parameters, comparing the construction parameters with the construction plan, and obtaining a correction data set;

[0031] In the digital twin industrial robot, the actual construction must be consistent with the preset construction plan, so that the digital twin system can be used for simulation in the future. First, the real-time parameters of the construction process are received, and then these parameters are carefully compared with the previous construction plan to find and correct any deviations that need to be corrected.

[0032] Among them, S200 also includes:

[0033] S210: Collecting construction parameters and generating twin construction progress parameters;

[0034] S220: Compare the twin construction progress parameter with the construction plan to obtain a total deviation value, and compare the total deviation value with a manually set allowable deviation value;

[0035] S230: If the total deviation value is less than or equal to the allowable deviation value, overwrite the twin construction progress parameter to the construction plan, and build a twin model according to the overwritten construction plan; if the total deviation value is greater than the allowable deviation value, output each deviation value as a correction data set;

[0036] The total deviation value is obtained by the following formula:

[0037]

[0038] Among them, S represents the total deviation value, W i It represents the weight value of the ith deviation item, which is set manually according to the deviation accuracy requirement. Psi represents the actual coordinate value of the ith deviation item, Pyi represents the coordinate value of the construction plan of the ith deviation item, and Pi represents the permitted deviation vector of the ith deviation item.

[0039] The system will first collect various parameters in the current construction, including but not limited to the location, installation angle, connection status, etc. of the equipment, which together constitute the twin construction progress parameters. Subsequently, the system will compare the collected twin construction progress parameters with the preset construction plan. This comparison process involves the precise matching of each parameter to find the difference between the two. For each difference, the system will calculate a total deviation value. This total deviation value reflects the overall degree of difference between the current construction and the construction plan. And judge whether the total deviation value exceeds the manually set allowable deviation value. If not, it means that the current construction is still within the acceptable range. The system will overwrite the twin construction progress parameters to the construction plan and continue to build the twin model according to the updated plan. If the allowable deviation value is exceeded, the system will output various deviation values ​​as a correction data set for subsequent adjustment. For example: Suppose that when building a production line based on a digital twin industrial robot, the system collects that the installation position of a certain industrial robot is different from the position in the actual construction plan. This deviation value is 5 cm, while the manually set allowable deviation value is only 2 cm. At this point, the system will consider this deviation to be unacceptable and calculate the corresponding total deviation value. Subsequently, the system will output this deviation value as part of the correction data set, prompting the operator to adjust the position of the industrial robot to ensure the construction accuracy and stability of the entire production line. Through this process, the system can monitor the progress and quality of the construction in real time to ensure that the final manufacturing unit can meet the expected requirements.

[0040] S300: Collecting a sensor data set during the operation of the robot, and analyzing the sensor data set to obtain robot operation state prediction data;

[0041] Among them, S300 also includes:

[0042] S310: Collecting operation time data of the transfer mechanism as first sensor data;

[0043] S320: Collecting the running time data of the working end as the second sensor data;

[0044] S330: Collecting loss rate data of each component as third sensor data;

[0045] S340: Collect idle time data as fourth sensor data;

[0046] S350: Collect average load data as fifth sensor data;

[0047] S360: Collecting operating temperature data as sixth sensor data;

[0048] S370: taking the first sensor data, the second sensor data, the third sensor data, the fourth sensor data, the fifth sensor data and the sixth sensor data as a sensor data set;

[0049] S380: Analyze the sensor data set to obtain robot operation status prediction data.

[0050] The transfer mechanism's operating time data reflects the activity of the industrial robot during material transfer or workpiece handling. By continuously monitoring this data, you can understand the robot's work intensity and possible wear and tear. For example: in an automobile manufacturing plant, industrial robots frequently move parts between different production lines. By collecting and analyzing the transfer mechanism's operating time data, it is possible to predict which robots may be at risk of wear and tear due to long working hours, so that maintenance can be carried out in advance.

[0051] The working end is the part of the industrial robot that performs specific work tasks. Its running time data evaluates the robot's work efficiency and lifespan. For example, in the assembly line of precision electronic products, the working end of the industrial robot needs to perform precision operations for a long time. By collecting the running time data of the working end, the wear degree of the end can be calculated, and a replacement or maintenance plan can be formulated accordingly.

[0052] Component wear rate data is an important basis for evaluating the overall health of the robot. By regularly testing the wear of each component, potential faults can be discovered in time and measures can be taken. For example: In the field of heavy machinery manufacturing, the various components of industrial robots often face the challenges of high-load operation and harsh environments. By collecting the wear rate data of each component, the overall performance of the robot can be evaluated, and components can be replaced or upgraded when necessary.

[0053] Idle time data helps understand the non-working status of robots, thereby optimizing production scheduling and improving equipment utilization.

[0054] The average load data reflects the average pressure that an industrial robot bears when performing a task and is an important indicator for evaluating its performance.

[0055] Industrial robots working in high temperature environments are prone to damage due to overheating of their electrical components. By collecting operating temperature data, overheating problems can be detected and handled in a timely manner, thus avoiding potential failures and safety accidents.

[0056] S400: Collect product quality inspection data, analyze and establish a relationship model between the quality inspection data and robot operation status prediction data, and input the operation status prediction data according to the model to obtain failure rate prediction data;

[0057] Collect product quality inspection data and analyze the relationship between this data and the robot's operating status prediction data to predict future failure rates, provide a basis for preventive maintenance, and provide support for production optimization and maintenance decisions.

[0058] Among them, S400 also includes:

[0059] S411: Obtain product quality inspection data;

[0060] S412: Matching the product quality inspection data with the robot operation state prediction data to obtain a matching data set;

[0061] S413: analyzing the influence probability between each parameter in the robot operation state prediction data and the product quality inspection data according to the matching data set, and using the influence probability as the influence weight of each item;

[0062] S414: Construct a relationship model according to the influence weights.

[0063] Product quality inspection data includes but is not limited to product size, weight, appearance defects, performance parameters and other aspects, which reflect the overall quality level of the product. The product quality inspection data is matched with the robot operation status prediction data to form a matching data set.

[0064] According to the matching data set, the impact probability of each parameter in the robot running state prediction data on the product quality inspection data is analyzed, and these impact probabilities are used as the impact weights of each parameter. For example: by analyzing the data, the factory found that the size deviation of the parts produced by the robot was large under high load and long-term operation. Therefore, the factory regards the robot's load and running time as important parameters affecting product quality and assigns them higher impact weights.

[0065] Based on the above analysis, a relationship model between quality inspection data and robot operation status prediction data is constructed. This model can reflect the direct impact of the robot operation status on product quality.

[0066] Among them, S400 also includes:

[0067] S421: Bringing the operation status prediction data into the relationship model to obtain target fault prediction parameters;

[0068] S422: traverse all devices to obtain multiple target fault prediction parameters;

[0069] S423: taking all the target fault prediction parameters as failure rate prediction data;

[0070] Among them, the failure rate formula used in the relational model is as follows:

[0071] Fr=k*Tta*Twb*Wec*Tid*Loe*Tef

[0072] In this formula, Fr is the failure rate, which indicates the probability or frequency of failure of the industrial robot per unit time, k is a constant term used to adjust the overall scale of the formula, Tt is the operating time of the transfer mechanism, which indicates the cumulative operating time of the mechanism responsible for material transfer or workpiece handling in the industrial robot, Tw is the operating time of the working end, which indicates the cumulative operating time of the end that performs specific work tasks in the industrial robot, We is the loss rate of each component, which is calculated through data detected by multiple sensors and is used to indicate the degree of loss of each key component of the industrial robot, Ti is the idle time, which indicates the cumulative time that the industrial robot is in a non-working state, Lo is the average load, which indicates the average load size that the industrial robot bears when performing tasks, Te is the operating temperature, which indicates the ambient temperature when the industrial robot is working, and the indexes a, b, c, d, e, and f respectively indicate the influence weights of these factors.

[0073] The robot's operating status prediction data is input into the constructed relational model to obtain the target fault prediction parameters. These parameters can reflect the type and probability of future failures that may occur in the robot. In order to comprehensively evaluate the failure risk of the entire production line, it is necessary to traverse all industrial robots and obtain their respective target fault prediction parameters. All target fault prediction parameters are integrated to form failure rate prediction data. These data provide the factory with a comprehensive failure risk assessment and help formulate targeted maintenance plans.

[0074] S500: When the predicted failure rate reaches a set value, an adjustment plan is generated using a random environment, and simulation prediction is performed on the adjustment plan to obtain an optimal solution.

[0075] The system will initiate a series of plan generation and evaluation processes to find the best solution. When the system predicts that the failure rate of a certain industrial robot or robots will reach or exceed the preset threshold, it will automatically start the plan generation and evaluation process to find the best adjustment plan through simulation prediction to reduce the risk of failure and ensure the stable operation of the production line.

[0076] S510: Manually set the fault rate adjustment threshold;

[0077] S520: When the failure rate prediction data is greater than or equal to the failure rate adjustment threshold, start the adjustment procedure;

[0078] S530: excluding devices whose failure rate prediction data is greater than or equal to the failure rate adjustment threshold, and adding the remaining devices to the reorganization sequence;

[0079] S540: generating a plurality of groups of adjustment plans according to the recombinant sequence;

[0080] S550: Verify the adjustment plan, calculate the corresponding overall failure rate, and obtain overall failure rate data of multiple groups of plans;

[0081] S560: Arrange the overall failure rate data of the solutions, and take the lowest value as the optional optimal solution;

[0082] S570: Add maintenance tags to all devices whose failure rate prediction data is greater than or equal to the failure rate adjustment threshold, and generate a maintenance list;

[0083] S580: Output the optional optimal solution and the maintenance list as the optimal solution.

[0084] This is the basis of the entire process, and it is necessary to manually set a reasonable failure rate threshold based on the actual situation of the production line and the performance characteristics of the robot. When the predicted failure rate reaches or exceeds this threshold, the system will trigger the adjustment procedure. For example: In an automobile manufacturing plant, engineers set the failure rate threshold to 0.05% based on the allowable value of the defect rate during product production or other possible business needs. This means that when the predicted failure rate of a robot reaches or exceeds 0.05%, the system will automatically start the plan generation and evaluation process.

[0085] When the system detects that the predicted failure rate data of a certain robot or certain robots reaches or exceeds the set threshold, the adjustment program will be automatically started and the plan generation stage will be entered. After starting the adjustment program, the system will first exclude the equipment whose predicted failure rate data reaches or exceeds the threshold from the current production line, and then recombines the remaining equipment into a new sequence for subsequent generation of adjustment plans. For example: In an automobile manufacturing plant, when the system detects that the predicted failure rate of a certain robot exceeds 0.05%, the robot will be temporarily removed from the production line. Subsequently, the system will recombine the remaining equipment to form a new production line sequence with a lower risk of failure.

[0086] Based on the reorganized equipment sequence, the system will automatically generate multiple possible adjustment plans. These plans may include adjusting the robot's workload, optimizing the production process, replacing faulty parts, and other measures. For example, in an automobile manufacturing plant, the system may generate the following adjustment plans: reduce the workload of robots with high risk of failure and assign them to other production lines; optimize the production process to reduce unnecessary operations of robots; replace parts with high failure rates, such as motors or sensors.

[0087] For each set of plans generated, the system will conduct simulation predictions to evaluate their effectiveness in actual operation. By calculating the overall failure rate after the implementation of the plan, the system can compare the pros and cons of different plans. After comparing the failure rate data of all plans, the system will select the plan with the lowest failure rate as the best plan. This plan will serve as the basis for subsequent implementation adjustments.

[0088] For all devices whose failure rate prediction data reaches or exceeds the threshold, the system will add a maintenance tag to them and generate a maintenance list. This list will serve as a reference for subsequent maintenance work. For example: In an automobile manufacturing plant, all robots with a failure rate exceeding 0.05% are added with maintenance tags and included in a detailed maintenance list. This list includes the failure type, maintenance recommendations, and estimated maintenance time information for each robot.

[0089] Finally, the system outputs the optimal solution and maintenance list as the output of the entire process. These results will serve as the basis for subsequent production adjustments and maintenance work.

[0090] Those skilled in the art will understand that the various digital numbers such as the first and second involved in this application are only for the convenience of description, and are not used to limit the scope of this application, nor do they indicate a sequence of precedence. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated with each other are in an "or" relationship. "At least one" refers to one or more. At least two refers to two or more. "At least one", "any one" or similar expressions refer to any combination of these items, including any combination of single items (individuals) or plural items (individuals). For example, at least one item (individual, kind) of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0091] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in this application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0092] The steps of the method or algorithm described in this application can be directly embedded in hardware, software units executed by a processor, or a combination of the two. The software unit can be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, register, hard disk, removable disk, CD-ROM or any other form of storage medium in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium can be arranged in an ASIC, and the ASIC can be arranged in a terminal. Optionally, the processor and the storage medium can also be arranged in different components in the terminal. These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are performed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.

[0093] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A method for building a manufacturing unit innovation platform based on a digital twin industrial robot, characterized in that: The following steps are involved: Collecting a set of building parameters, generating a building plan according to the set of building parameters, inputting manual intervention, and combining the manual intervention with the building plan to generate a building solution; Receiving construction parameters, comparing the construction parameters with the construction plan, and obtaining a correction data set; Collecting a set of sensor data during the operation of the robot, and analyzing the set of sensor data to obtain robot operation status prediction data; Collect product quality inspection data, analyze and establish a relationship model between the quality inspection data and robot operation status prediction data, and input the operation status prediction data according to the model to obtain failure rate prediction data; When the predicted failure rate reaches a set value, a random environment is used to generate an adjustment plan, and the adjustment plan is simulated and predicted to obtain the optimal solution.

2. The method for building a manufacturing unit innovation platform based on a digital twin industrial robot according to claim 1, characterized in that: The acquisition and construction parameter set further includes: Collect site environment model parameters as the first construction parameters; Collect device model parameters as the second building parameters; The operating radius of the acquisition equipment is used as the third construction parameter; Collect other component model parameters as the fourth building parameter; The first construction parameter, the second construction parameter, the third construction parameter and the fourth construction parameter are taken as the construction parameter set.

3. The method for building a manufacturing unit innovation platform based on a digital twin industrial robot according to claim 2 is characterized in that: The generating of a construction plan according to the construction parameter set, inputting manual intervention, and combining the manual intervention with the construction plan to generate a construction solution further includes: Parsing the set of building parameters; Entering manual intervention, analyzing the required parts of the manual intervention, randomly generating multiple groups of random plans, simulating and running the random plans, and outputting the random plans that have passed the running as optional plans; The manual intervention is input again, the manual intervention is analyzed and the optional plan is adjusted, and the adjusted plan is output, and this step is repeated until the manual intervention confirms any plan, and the plan is output as the construction plan.

4. The method for building a manufacturing unit innovation platform based on a digital twin industrial robot according to claim 1, characterized in that: The receiving of the erection construction parameters, comparing the erection construction parameters with the erection plan, and obtaining a correction data set further includes: Collect construction parameters and generate twin construction progress parameters; Comparing the twin construction progress parameter with the construction plan to obtain a total deviation value, and comparing the total deviation value with a manually set allowable deviation value; If the total deviation value is less than or equal to the allowable deviation value, the twin construction progress parameter is overwritten to the construction plan, and the twin model is constructed according to the overwritten construction plan; if the total deviation value is greater than the allowable deviation value, each deviation value is output as a correction data set; The total deviation value is obtained by the following formula: Among them, S represents the total deviation value, W i It represents the weight value of the ith deviation item, which is set manually according to the deviation accuracy requirement. Psi represents the actual coordinate value of the ith deviation item, Pyi represents the coordinate value of the construction plan of the ith deviation item, and Pi represents the permitted deviation vector of the ith deviation item.

5. The method for building a manufacturing unit innovation platform based on a digital twin industrial robot according to claim 1, characterized in that: The collecting of sensor data sets during the operation of the robot and analyzing the sensor data sets to obtain robot operation state prediction data further include: collecting operating time data of the transfer mechanism as first sensor data; Collecting the running time data of the working end as the second sensor data; Collecting the loss rate data of each component as the third sensor data; collecting idle time data as fourth sensor data; collecting average load data as fifth sensor data; collecting operating temperature data as sixth sensor data; taking the first sensor data, the second sensor data, the third sensor data, the fourth sensor data, the fifth sensor data and the sixth sensor data as a sensor data set; The sensor data set is analyzed to obtain robot operation status prediction data.

6. The method for building a manufacturing unit innovation platform based on a digital twin industrial robot according to claim 1, characterized in that: The collecting of product quality inspection data and analyzing and establishing a relationship model between the quality inspection data and the robot operation status prediction data further includes: Obtain product quality inspection data; Matching the product quality inspection data with the robot operation status prediction data to obtain a matching data set; Analyze the influence probability between each parameter in the robot operation state prediction data and the product quality inspection data according to the matching data set, and use the influence probability as the influence weight of each item; Build relationship models based on influence weights.

7. The method for building a manufacturing unit innovation platform based on a digital twin industrial robot according to claim 6 is characterized in that: The step of inputting the running state prediction data according to the model to obtain the failure rate prediction data further includes: Bringing the operation status prediction data into the relationship model to obtain target fault prediction parameters; Traverse all devices and obtain multiple target fault prediction parameters; taking all the target fault prediction parameters as failure rate prediction data; Among them, the failure rate formula used in the relational model is as follows: Fr=k*Tta*Twb*Wec*Tid*Loe*Tef In this formula, Fr is the failure rate, which indicates the probability or frequency of failure of the industrial robot per unit time, k is a constant term used to adjust the overall scale of the formula, Tt is the operating time of the transfer mechanism, which indicates the cumulative operating time of the mechanism responsible for material transfer or workpiece handling in the industrial robot, Tw is the operating time of the working end, which indicates the cumulative operating time of the end that performs specific work tasks in the industrial robot, We is the loss rate of each component, which is calculated through data detected by multiple sensors and is used to indicate the degree of loss of each key component of the industrial robot, Ti is the idle time, which indicates the cumulative time that the industrial robot is in a non-working state, Lo is the average load, which indicates the average load size that the industrial robot bears when performing tasks, Te is the operating temperature, which indicates the ambient temperature when the industrial robot is working, and the indexes a, b, c, d, e, and f respectively indicate the influence weights of these factors.

8. The method for building a manufacturing unit innovation platform based on a digital twin industrial robot according to claim 7, characterized in that: When the predicted failure rate reaches a set value, using a random environment to generate an adjustment plan, simulating and predicting the adjustment plan, and obtaining an optimal solution further includes: Manually set the fault rate adjustment threshold; When the failure rate prediction data is greater than or equal to the failure rate adjustment threshold, the adjustment procedure is started; Excluding devices whose failure rate prediction data is greater than or equal to the failure rate adjustment threshold, and adding the remaining devices to the reorganization sequence; Generating a plurality of groups of adjustment plans according to the recombinant sequence; Verify the adjustment plan, calculate the corresponding overall failure rate, and obtain overall failure rate data of multiple groups of plans; Arrange the overall failure rate data of the solutions and take the lowest value as the optional optimal solution; Add maintenance tags to all devices whose failure rate prediction data is greater than or equal to the failure rate adjustment threshold, and generate a maintenance list; The selectable optimal solution and the maintenance list are output as the optimal solution.

Images