High-efficiency synchronous device parameter adjustment method and system

Abstract

The present invention discloses an efficient synchronous device parameter adjustment method and system, and specifically relates to the technical field of device parameter adjustment. Parameters are selected through a parameter adjustment interface, and adjustment tasks are decomposed into multiple parallel threads, each thread is responsible for adjusting parameters of different devices, thereby realizing synchronous parameter adjustment. By real-time monitoring of the execution status and parameter adjustment results of each thread, it is possible to promptly discover whether there is an abnormality in the overall parameter adjustment time, conduct a comprehensive analysis of the stability of the overall parameter adjustment efficiency between different devices and the accuracy of parameter adjustment of different devices, evaluate the consistency of parameter adjustment between different devices, and when adjustment inconsistencies occur between different devices, manage the execution of parameter adjustment tasks through a thread pool mechanism, dynamically adjust task priorities, and realize intelligent scheduling of tasks, thereby reducing the overall parameter adjustment time, improving the stability and efficiency of the system, and reducing the inconsistencies that occur during the device parameter adjustment process, thereby improving the stability of production and the quality of products.

Description

Technical Field

[0001] The present invention relates to the technical field of device parameter adjustment, and in particular to a method and system for adjusting parameters of an efficient synchronous device. Background Art

[0002] In industrial production scenarios, as the demand for multi-camera applications becomes increasingly prominent, it becomes necessary to frequently adjust camera parameters and status during on-site machine adjustment and debugging. Traditionally, if you want to adjust specific parameters of multiple devices, you need to manually switch to the parameter page of each device and adjust them one by one, which is time-consuming and inefficient. Efficient synchronous device parameter adjustment is a technical method that aims to ensure the consistency and coordination of parameter adjustment and operation of multiple devices. Through advanced network protocols, distributed control systems, and feedback control mechanisms, high-speed data transmission and time synchronization between devices are achieved to ensure that the same operations are performed at the same time, avoiding system failures or data errors caused by asynchrony. Automated and intelligent control systems monitor and analyze device status in real time, respond quickly and adjust parameters to ensure that the system operates in an efficient and stable state.

[0003] The prior art has the following disadvantages:

[0004] In the traditional manual parameter adjustment method, users need to enter the parameter adjustment interface of each device one by one and set the parameters for each device. Since this is a serial operation and needs to be completed one by one, the time cost of overall parameter adjustment will increase linearly with the increase in the number of devices. And as the time of overall parameter adjustment increases, there may be inconsistencies in the adjustment of different devices, resulting in parameter differences between devices, which in turn affects the stability of production and the quality of products. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for adjusting parameters of an efficient synchronization device to solve the deficiencies in the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a method for adjusting parameters of an efficient synchronization device, comprising the following steps:

[0007] S1: Select the parameter to be adjusted through the parameter adjustment interface, decompose the parameter adjustment action into multiple parallel thread tasks, adjust the parameters of different devices through each task, wait for the adjustment action of each thread to be completed, and determine whether the overall parameter adjustment time between different devices is abnormal;

[0008] S2: When the overall parameter adjustment time between different devices is abnormal, analyze the overall parameter adjustment efficiency between different devices, determine the abnormal degree of the parameter adjustment efficiency during the device parameter adjustment process, and evaluate the stability of the overall parameter adjustment efficiency between different devices;

[0009] S3: Use each thread to synchronously adjust the same parameter of different devices. After the parameter adjustment of all devices has taken effect, compare and analyze the adjusted parameters to evaluate the accuracy of parameter adjustment of different devices.

[0010] S4: Comprehensively analyze the stability of the overall parameter adjustment efficiency between different devices and the accuracy of parameter adjustment of different devices to evaluate the consistency of parameter adjustment between different devices;

[0011] S5: According to the evaluation results, the consistency of parameter adjustment between different devices is divided into two categories: consistent adjustment and inconsistent adjustment;

[0012] S6: When there is inconsistency in parameter adjustment between different devices, the execution of parameter adjustment tasks is managed through the thread pool mechanism, and the execution status of each parameter adjustment task is monitored in real time. According to the parameter adjustment situation of different devices, the priority of the task is dynamically adjusted to reduce the overall parameter adjustment time.

[0013] In a preferred embodiment, in S1, devices with abnormal adjustment time are identified from system records, and their adjustment time data are collected, including the start adjustment time and the completion adjustment time of the abnormal devices; the adjustment time data of normal devices are collected, including the start adjustment time and the completion adjustment time of the normal devices; the parameter adjustment time of the abnormal devices is calculated based on the start adjustment time and the completion adjustment time of the abnormal devices, and the parameter adjustment time is equal to the completion adjustment time minus the start adjustment time; for normal devices, the parameter adjustment time of the normal devices is also calculated based on the start adjustment time and the completion adjustment time;

[0014] For the parameter adjustment time of abnormal devices, the degree of outlier is measured by the outlier index; this includes calculating the mean and standard deviation of the parameter adjustment time of abnormal devices, and then calculating the Z-score value of the parameter adjustment time of each abnormal device. For each abnormal device, the calculated Z-score value is checked, and the calculated Z-score value is compared with the preset abnormal parameter adjustment time threshold. If the Z-score value of the abnormal device is greater than or equal to the abnormal parameter adjustment time threshold, then the overall parameter adjustment time between different devices is abnormal; if the Z-score value of the abnormal device is less than the abnormal parameter adjustment time threshold, then the overall parameter adjustment time between different devices is not abnormal.

[0015] In a preferred embodiment, in S2, the abnormal degree of the parameter adjustment efficiency during the device parameter adjustment process is determined, including obtaining the parameter adjustment efficiency fluctuation value and evaluating the stability of the overall parameter adjustment efficiency between different devices. The method for obtaining the parameter adjustment efficiency fluctuation value is:

[0016] Collect the actual time data spent on parameter adjustment for each device, compare the parameter adjustment time of different devices, analyze the expected parameter adjustment time of each device by using the autoregressive sliding average model, set the size of the time window to W according to the expected parameter adjustment time at the tth time point, calculate the sliding average of each time point, and calculate the adjustment time residual of each device at the tth time point through the expected parameter adjustment time and the sliding average. Compare and analyze the sliding average of each time point with the adjustment time residual at the tth time point, and calculate the parameter adjustment efficiency fluctuation value.

[0017] In a preferred embodiment, the acquired parameter adjustment efficiency fluctuation value is compared with the adjustment efficiency fluctuation value reference threshold. If the adjustment efficiency fluctuation value is greater than or equal to the adjustment efficiency fluctuation value reference threshold, an overall adjustment efficiency abnormal signal is generated; if the adjustment efficiency fluctuation value is less than the adjustment efficiency fluctuation value reference threshold, an overall adjustment efficiency normal signal is generated.

[0018] In a preferred embodiment, in S3, the parameter values ​​after the equipment parameters are adjusted are compared with the parameter adjustment standard values, and the adjustment parameter deviation values ​​after the adjustment of different equipment parameters are obtained to evaluate the accuracy of the adjustment of different equipment parameters. The method for obtaining the adjustment parameter deviation values ​​is:

[0019] Acquire all parameter values ​​after parameter adjustment of each device, and establish a corresponding data set, and establish a corresponding data set with parameter adjustment standard values ​​corresponding to all parameter values ​​after parameter adjustment of the device;

[0020] For each device, calculate the difference between all parameter values ​​after parameter adjustment and their corresponding parameter adjustment standard values, standardize each difference to obtain a standardized difference, and establish a standardized difference data set. After calculating the average value of the standardized differences in the standardized difference data set, calculate the deviation ratio of device parameter adjustment. Based on the calculated deviation ratio of parameter adjustment for each device, determine the degree of deviation of parameter adjustment of abnormal devices whose parameter adjustment results obviously deviate from those of normal devices among all devices, that is, calculate the adjustment parameter deviation value.

[0021] In a preferred embodiment, the acquired adjustment parameter deviation value is compared with the historical reference threshold of the adjustment parameter deviation value in the historical data. If the adjustment parameter deviation value is greater than or equal to the historical reference threshold of the adjustment parameter deviation value in the historical data, a parameter adjustment abnormal signal is generated; if the adjustment parameter deviation value is less than the historical reference threshold of the adjustment parameter deviation value in the historical data, a parameter adjustment normal signal is generated.

[0022] In a preferred embodiment, in S4, the stability of the overall parameter adjustment efficiency between different devices and the accuracy of parameter adjustment of different devices are comprehensively analyzed, specifically:

[0023] The adjustment efficiency fluctuation value and the adjustment parameter deviation value are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses each group of first eigenvectors to predict the consistency value label of the parameter adjustment between different devices as the prediction target, and takes minimizing the sum of the prediction errors of the consistency value labels of the parameter adjustment between all different devices as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The consistency coefficient of the parameter adjustment between different devices is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0024] In a preferred embodiment, in S5, the consistency of parameter adjustment between different devices is divided into two categories: consistency adjustment and inconsistency adjustment, specifically:

[0025] The obtained consistency coefficient of parameter adjustment between different devices is compared with the consistency standard threshold. If the consistency coefficient of parameter adjustment between different devices is greater than or equal to the consistency standard threshold, the consistency degree of parameter adjustment between different devices is classified as consistent adjustment, and no additional adjustment is required; if the consistency coefficient of parameter adjustment between different devices is less than the consistency standard threshold, the consistency degree of parameter adjustment between different devices is classified as inconsistent adjustment, and the parameters of the device are readjusted.

[0026] In a preferred embodiment, in S6, the execution status of each parameter adjustment task is monitored in real time, and the priority of the task is dynamically adjusted according to the adjustment of different device parameters to reduce the overall parameter adjustment time, specifically:

[0027] Mark the task execution time of device h as , the expected execution time of the task of device h is marked as , and mark the deviation of the parameter adjustment result of device h as , the task priority of device h is marked as , the system resources allocated by device h are marked as , the task queue is marked as ;

[0028] Initialize the priority and task queue. The initial priority of each device is set to a constant value. The task queue Q initially contains all tasks. During the task execution process, monitor the execution time and parameter adjustment result deviation of each task. If the execution time of the task is longer than the expected execution time and the parameter adjustment result deviation is greater than the expected deviation value, increase the priority of the task.

[0029] Move high-priority tasks to the front of the task queue, execute them first, and allocate more system resources to them;

[0030] Continuously monitor the execution of high-priority tasks to determine whether their parameter adjustment results meet expectations.

[0031] In a preferred embodiment, the execution status of each parameter adjustment task is monitored in real time, and the priority of the task is dynamically adjusted according to the adjustment conditions of different device parameters to reduce the overall parameter adjustment time. When the task execution time and the deviation of the parameter adjustment result exceed expectations, the task execution status is continuously monitored to ensure that the parameter adjustment result meets the expected process, and the priority of the task is dynamically adjusted to reduce the overall parameter adjustment time.

[0032] The present invention also provides an efficient synchronization device parameter adjustment system, including a parameter adjustment interface module, a parameter adjustment efficiency judgment module, a parameter adjustment accuracy judgment module, a comprehensive analysis module, an adjustment consistency division module and a scheduling optimization module:

[0033] Parameter adjustment interface module: select the parameters to be adjusted through the parameter adjustment interface, decompose the parameter adjustment action into multiple parallel thread tasks, adjust the parameters of different devices through each task, wait for the adjustment action of each thread to be completed, and determine whether the overall parameter adjustment time between different devices is abnormal;

[0034] Parameter adjustment efficiency judgment module: When the overall parameter adjustment time between different devices is abnormal, the overall parameter adjustment efficiency between different devices is analyzed to determine the abnormal degree of the parameter adjustment efficiency during the device parameter adjustment process and evaluate the stability of the overall parameter adjustment efficiency between different devices;

[0035] Parameter adjustment accuracy judgment module: Each thread adjusts the same parameter of different devices synchronously. After the parameter adjustment of all devices has taken effect, the adjusted parameters are compared and analyzed to evaluate the accuracy of parameter adjustment of different devices.

[0036] Comprehensive analysis module: conducts comprehensive analysis on the stability of the overall parameter adjustment efficiency between different devices and the accuracy of parameter adjustment of different devices, and evaluates the consistency of parameter adjustment between different devices;

[0037] Adjustment consistency classification module: Based on the evaluation results, the consistency of parameter adjustment between different devices is divided into two categories: consistent adjustment and inconsistent adjustment;

[0038] Scheduling optimization module: When there are inconsistencies in parameter adjustments between different devices, the execution of parameter adjustment tasks is managed through the thread pool mechanism, the execution status of each parameter adjustment task is monitored in real time, and the priority of the task is dynamically adjusted according to the parameter adjustment conditions of different devices to reduce the overall parameter adjustment time.

[0039] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0040] 1. The present invention improves the overall parameter adjustment efficiency and stability by parallelizing parameter adjustment tasks, real-time abnormality monitoring and analysis, accuracy assessment and consistency analysis. By parallelizing tasks, the overall parameter adjustment time cost is reduced, and real-time monitoring and analysis can detect abnormal situations in a timely manner to ensure production stability. Accuracy assessment and consistency analysis improve the accuracy and consistency of parameter adjustment, thereby further optimizing product quality and production efficiency. It can effectively reduce the time cost of equipment parameter adjustment and improve the stability and efficiency of the production process.

[0041] 2. The present invention improves the overall parameter adjustment efficiency and stability by real-time monitoring of task execution status and dynamic adjustment of task priority. By processing parameter adjustment tasks in parallel, the overall parameter adjustment time is reduced. At the same time, through priority adjustment and resource allocation, the rapid execution of high-priority tasks is ensured, thereby reducing the overall parameter adjustment time. This process not only improves production efficiency, but also ensures the accuracy and consistency of parameter adjustment results, bringing higher stability and reliability to the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0043] Figure 1 The figure is a flow chart of the method of the present invention.

[0044] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] Example 1

[0047] See also Figure 1 As shown, the efficient synchronization device parameter adjustment method described in this embodiment includes the following steps:

[0048] S1: Select the parameter to be adjusted through the parameter adjustment interface, decompose the parameter adjustment action into multiple parallel thread tasks, adjust the parameters of different devices through each task, wait for the adjustment action of each thread to be completed, and determine whether the overall parameter adjustment time between different devices is abnormal;

[0049] S2: When the overall parameter adjustment time between different devices is abnormal, analyze the overall parameter adjustment efficiency between different devices, determine the abnormal degree of the parameter adjustment efficiency during the device parameter adjustment process, and evaluate the stability of the overall parameter adjustment efficiency between different devices;

[0050] S3: Use each thread to synchronously adjust the same parameter of different devices. After the parameter adjustment of all devices has taken effect, compare and analyze the adjusted parameters to evaluate the accuracy of parameter adjustment of different devices.

[0051] S4: Comprehensively analyze the stability of the overall parameter adjustment efficiency between different devices and the accuracy of parameter adjustment of different devices to evaluate the consistency of parameter adjustment between different devices;

[0052] S5: According to the evaluation results, the consistency of parameter adjustment between different devices is divided into two categories: consistent adjustment and inconsistent adjustment;

[0053] S6: When there is inconsistency in parameter adjustment between different devices, the execution of parameter adjustment tasks is managed through the thread pool mechanism, and the execution status of each parameter adjustment task is monitored in real time. According to the parameter adjustment situation of different devices, the priority of the task is dynamically adjusted to reduce the overall parameter adjustment time.

[0054] Among them, in S1, the parameters to be adjusted are selected through the parameter adjustment interface, and the action of adjusting the parameters is decomposed into multiple parallel thread tasks. The parameters of different devices are adjusted through each task. After the adjustment action of each thread is completed, it is determined whether the overall parameter adjustment time between different devices is abnormal. Specifically:

[0055] The operator first selects the parameters to be adjusted in the parameter adjustment interface. The system splits the adjustment task into multiple independent tasks based on the selected parameters, and each task is responsible for adjusting the parameters of different devices. Each task is executed in parallel in its own thread, that is, the parameters of multiple devices are adjusted at the same time. This can avoid serial execution and improve the adjustment efficiency.

[0056] The system will wait for each thread's adjustment to complete before proceeding to the next step. This ensures that all device parameter adjustments are complete and avoids inconsistent adjustment times between different devices.

[0057] After all devices have been adjusted, the system will compare and analyze the overall adjustment time between different devices. If it is found that the adjustment time of some devices is significantly different from that of other devices, the system will determine that the adjustment time is abnormal and may require further analysis and processing.

[0058] The system will compare and analyze the overall parameter adjustment time between different devices. The system can add a timestamp record to each device's parameter adjustment action, recording the start and completion time of the adjustment. By comparing the timestamp records of each device, you can intuitively understand the adjustment time of each device, and then compare and analyze it, specifically:

[0059] First, the system needs to record the timestamp data of the start and completion time of each device parameter adjustment. These timestamp data should be associated with specific devices and parameter adjustment tasks and stored in the system database or log file.

[0060] For each device parameter adjustment, the system calculates the adjustment time based on the timestamp data. The adjustment time is obtained by subtracting the start adjustment time from the completion adjustment time. The obtained adjustment time should be relatively accurate and can reflect the time taken to adjust the device parameters.

[0061] The system sets a standard adjustment time range based on the actual situation of the production line and the characteristics of the equipment. This range can be determined based on historical data, equipment specifications, technical requirements, etc.

[0062] For each device's parameter adjustment time, the system compares it with the set standard adjustment time range. If the device's adjustment time exceeds the set standard adjustment time range, the device's adjustment time is abnormal.

[0063] The abnormal parameter adjustment time is compared with the parameter adjustment time of other devices, and the outlier index of the abnormal parameter adjustment time is calculated to determine whether there is an overall parameter adjustment time abnormality between different devices.

[0064] First, identify the devices with abnormal adjustment time from the system records and collect their adjustment time data, including the start adjustment time and the completion adjustment time of the abnormal devices.

[0065] At the same time, the adjustment time data of normal equipment is collected, which includes the start adjustment time and the completion adjustment time of normal equipment.

[0066] The parameter adjustment time of the abnormal device is calculated based on the start adjustment time and the completion adjustment time of the abnormal device. The parameter adjustment time is equal to the completion adjustment time minus the start adjustment time.

[0067] For normal equipment, the parameter adjustment time of the normal equipment is also calculated based on the start adjustment time and the completion adjustment time.

[0068] For the parameter adjustment time of abnormal devices, the outlier index is used to measure its degree of outlier. The mean and standard deviation of the parameter adjustment time of abnormal devices are calculated, and then the Z-score value of the parameter adjustment time of each abnormal device is calculated. This value represents the degree of deviation between the parameter adjustment time of the device and the mean value, which is used to measure its degree of outlier.

[0069] For each abnormal device, check its calculated Z-score value, and compare the calculated Z-score value with the preset abnormal parameter adjustment time threshold. If the Z-score value of the abnormal device is greater than or equal to the abnormal parameter adjustment time threshold, it means that the parameter adjustment time of the abnormal device has obviously deviated from the average level and there is a large degree of outlier, then the overall parameter adjustment time between different devices is abnormal; if the Z-score value of the abnormal device is less than the abnormal parameter adjustment time threshold, then the overall parameter adjustment time between different devices is not abnormal.

[0070] S2: When the overall parameter adjustment time between different devices is abnormal, analyze the overall parameter adjustment efficiency between different devices, determine the abnormal degree of the parameter adjustment efficiency during the device parameter adjustment process, and evaluate the stability of the overall parameter adjustment efficiency between different devices.

[0071] Collect the time data for parameter adjustment of each device. Compare the parameter adjustment time of different devices. Analyze this data to find out the devices with abnormally long or short adjustment time. For devices with abnormally long or short parameter adjustment time, determine the abnormal degree of their parameter adjustment efficiency.

[0072] Among them, judging the abnormal degree of parameter adjustment efficiency during the device parameter adjustment process includes obtaining the parameter adjustment efficiency fluctuation value and evaluating the stability of the overall parameter adjustment efficiency between different devices. The method for obtaining the parameter adjustment efficiency fluctuation value is:

[0073] Collect the actual time data spent on parameter adjustment for each device, and mark the actual time data spent on parameter adjustment for each device as: , , , ..., ;in, is a positive integer greater than 0. The parameter adjustment time of different devices is compared. The expected parameter adjustment time of each device is analyzed by using the autoregressive moving average model, where the autoregressive moving average model is expressed as:

[0074] ; In the formula, is the expected adjustment time of the parameter at the tth time point, , ,..., is the autoregressive coefficient, and , ,..., are all greater than 0, p is the order of the autoregressive model, is the error term, , ,..., is the sliding coefficient, and , ,..., are all greater than 0, q is the order of the moving average model, are independent and identically distributed random errors; where , ,..., and , ,..., The specific value is estimated from historical data. According to the expected parameter adjustment time at the t-th time point, the size of the time window is set to W, the sliding average value at each time point is calculated, and the adjustment time residual of each device at the t-th time point is calculated by the expected parameter adjustment time and the sliding average value. The specific calculation expression is:

[0075] ; In the formula, is the adjustment time residual at the tth time point, and the sliding average of each time point Compare and analyze the adjustment time residual at the t-th time point to calculate the adjustment efficiency fluctuation value of the parameter. The specific calculation expression is: ; In the formula, To adjust the efficiency fluctuation value.

[0076] The obtained parameter adjustment efficiency fluctuation value is compared with the adjustment efficiency fluctuation value reference threshold. If the adjustment efficiency fluctuation value is greater than or equal to the adjustment efficiency fluctuation value reference threshold, it means that the stability of the overall parameter adjustment efficiency between different devices is low, and an overall parameter adjustment efficiency abnormal signal is generated at this time; if the adjustment efficiency fluctuation value is less than the adjustment efficiency fluctuation value reference threshold, it means that the stability of the overall parameter adjustment efficiency between different devices is high, and an overall parameter adjustment efficiency normal signal is generated at this time.

[0077] The increase in the fluctuation value of the parameter adjustment efficiency may indicate that the adjustment efficiency between devices has changed significantly in different time periods or operating conditions. This instability will cause drastic fluctuations in the adjustment efficiency during the production process, making it difficult to maintain the overall efficiency of the production line stable.

[0078] The instability of equipment parameter adjustment efficiency will directly affect the stability of production efficiency. If there is a large fluctuation in the adjustment efficiency between different equipment, the overall efficiency of the production line will also fluctuate, thus affecting the execution of the production plan and the quality of the product.

[0079] The instability of parameter adjustment efficiency may lead to waste or inefficient use of resources. For example, some equipment requires more adjustment time during certain periods, while other equipment is idle, which will lead to uneven allocation of resources and affect the overall efficiency and resource utilization efficiency of the production line.

[0080] S3: Use each thread to synchronously adjust the same parameter of different devices. After the parameter adjustment of all devices has taken effect, compare and analyze the adjusted parameters to evaluate the accuracy of parameter adjustment of different devices.

[0081] Each thread is responsible for synchronously adjusting the value of a specific parameter on different devices. This ensures that each device uses the same parameter settings during the adjustment process, avoiding production line instability or product quality problems caused by inconsistent parameters. Once the parameter adjustment of all devices has been completed, the system will collect and compare the adjusted parameters of each device. Through comparative analysis, the system can evaluate the accuracy of device parameter adjustment. If the parameters of the device after adjustment are as expected, it means that the parameter adjustment is relatively accurate; otherwise, there may be inaccurate or abnormal device parameter adjustment, which requires further investigation and correction.

[0082] Compare the parameter values ​​after the equipment parameter adjustment is completed with the parameter adjustment standard values, obtain the adjustment parameter deviation values ​​after the adjustment of different equipment parameters is completed, and evaluate the accuracy of the adjustment of different equipment parameters. The method for obtaining the adjustment parameter deviation values ​​is:

[0083] Get all parameter values ​​after parameter adjustment for each device and mark them as , and establish the corresponding data set , is a positive integer greater than 0, and the parameter adjustment standard value corresponding to all parameter values ​​after the device parameter adjustment is completed is marked as , establish the corresponding data set ;

[0084] For each device, calculate the difference between all parameter values ​​after parameter adjustment and its corresponding parameter adjustment standard value, standardize each difference to obtain a standardized difference, and mark the standardized difference as , and establish a standardized difference data set, , c is a positive integer greater than 0. After calculating the average value of the standardized difference in the standardized difference data set, the deviation ratio of the equipment parameter adjustment is calculated. The specific calculation expression is:

[0085] ; In the formula, is the mean of the standardized differences, is the standard deviation of the standardized differences, Deviation ratio for equipment parameter adjustment;

[0086] According to the calculated deviation ratio of parameter adjustment of each device, the deviation degree of parameter adjustment of abnormal devices whose parameter adjustment results obviously deviate from those of normal devices is determined, that is, the deviation value of adjustment parameters is calculated. The specific calculation expression is:

[0087] ; In the formula, is the adjustment parameter deviation value, and W is the total number of abnormal devices whose parameter adjustment results deviate among all devices.

[0088] The obtained adjustment parameter deviation value is compared with the historical reference threshold of the adjustment parameter deviation value in the historical data. If the adjustment parameter deviation value is greater than or equal to the historical reference threshold of the adjustment parameter deviation value in the historical data, it means that the accuracy of adjustment of different device parameters is low, and a parameter adjustment abnormal signal is generated at this time; if the adjustment parameter deviation value is less than the historical reference threshold of the adjustment parameter deviation value in the historical data, it means that the accuracy of adjustment of different device parameters is high, and a parameter adjustment normal signal is generated at this time.

[0089] Large deviations in adjustment parameters will lead to inconsistent equipment parameters on the production line, affecting the stability and consistency of the production process and possibly causing product quality problems.

[0090] An inaccurately regulated machine may not coordinate well with other equipment, resulting in a decrease in the overall efficiency of the production line.

[0091] Equipment with large deviations may require frequent adjustments and corrections, increasing the complexity of operation and maintenance and increasing the risk of equipment failure.

[0092] S4: Comprehensively analyze the stability of the overall parameter adjustment efficiency between different devices and the accuracy of parameter adjustment of different devices to evaluate the consistency of parameter adjustment between different devices.

[0093] The adjustment efficiency fluctuation value and the adjustment parameter deviation value are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses each group of first eigenvectors to predict the consistency value label of the parameter adjustment between different devices as the prediction target, and takes minimizing the sum of the prediction errors of the consistency value labels of the parameter adjustment between all different devices as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The consistency coefficient of the parameter adjustment between different devices is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0094] The method for obtaining the consistency coefficient of parameter adjustment between different devices is: from the first feature vector training data of the trained machine learning model, obtain the corresponding function expression:

[0095] ; In the formula, is the output function of the model, To adjust the efficiency fluctuation value, To adjust the parameter deviation value, is the consistency coefficient.

[0096] S5: According to the evaluation results, the consistency of parameter adjustment between different devices is divided into two categories: consistent adjustment and inconsistent adjustment;

[0097] The obtained consistency coefficient of parameter adjustment between different devices is compared with the consistency standard threshold. If the consistency coefficient of parameter adjustment between different devices is greater than or equal to the consistency standard threshold, it means that the consistency of parameter adjustment between different devices is high, and the consistency degree of parameter adjustment between different devices is classified as consistent adjustment, and no additional adjustment is required; if the consistency coefficient of parameter adjustment between different devices is less than the consistency standard threshold, it means that the consistency of parameter adjustment between different devices is low, and the consistency degree of parameter adjustment between different devices is classified as inconsistent adjustment, and the parameters of the device need to be readjusted.

[0098] In this embodiment, the parameter to be adjusted is selected through the parameter adjustment interface, the action of adjusting the parameter is decomposed into multiple parallel thread tasks, and the parameters of different devices are adjusted through each task. After the adjustment action of each thread is completed, it is determined whether the overall parameter adjustment time between different devices is abnormal; when the overall parameter adjustment time between different devices is abnormal, the overall parameter adjustment efficiency between different devices is analyzed, the abnormal degree of the parameter adjustment efficiency during the device parameter adjustment process is determined, and the stability of the overall parameter adjustment efficiency between different devices is evaluated; the same parameter of different devices is synchronously adjusted through each thread, and after the parameter adjustment of all devices has taken effect, the adjusted parameters are compared and analyzed to evaluate the accuracy of parameter adjustment of different devices; the stability of the overall parameter adjustment efficiency between different devices and the accuracy of parameter adjustment of different devices are comprehensively analyzed to evaluate the consistency of parameter adjustment between different devices; according to the evaluation results, the consistency of parameter adjustment between different devices is divided into two categories: consistency adjustment and inconsistency adjustment, and corresponding processing is performed respectively to improve the consistency and stability of device parameter adjustment, thereby optimizing the production process to improve the stability and efficiency of the production process.

[0099] Example 2

[0100] S6: When there is inconsistency in parameter adjustment between different devices, the execution of parameter adjustment tasks is managed through the thread pool mechanism, and the execution status of each parameter adjustment task is monitored in real time. According to the parameter adjustment situation of different devices, the priority of the task is dynamically adjusted to reduce the overall parameter adjustment time.

[0101] The thread pool is a mechanism that can create and reuse threads in advance. The thread pool can avoid frequent creation and destruction of threads, thereby reducing system overhead and improving parameter adjustment efficiency. During the parameter adjustment process, each parameter adjustment task (corresponding to the parameter adjustment of a device) will be assigned to a thread in the thread pool for processing. Create a thread pool of a fixed size (for example, containing 10 threads).

[0102] Add the parameter adjustment tasks of all devices to the task queue and set the initial priority. The threads in the thread pool start to execute the parameter adjustment tasks and monitor the execution status of the tasks in real time (for example, Task A, Task B, Task C...). The monitoring indicators include the execution time, progress, and parameter adjustment results of each task. If the execution time of a task (for example, Task A) exceeds expectations, or the parameter adjustment results deviate greatly from expectations, increase the priority of Task A. Re-adjust the task queue, move Task A to the front of the queue, and execute it first. Allocate more system resources (such as more threads or higher CPU time slices) to high-priority tasks (such as Task A). Monitor the execution of Task A to ensure that its parameter adjustment results meet expectations.

[0103] Among them, the task execution time of device h is marked as , the expected execution time of the task of device h is marked as , and mark the deviation of the parameter adjustment result of device h as , the task priority of device h is marked as , the system resources (such as the number of threads or CPU time slices) allocated to device h are marked as , the task queue is marked as ;

[0104] Initialize the priority and task queue, and set the initial priority of each device to a constant value: ; In the formula, is the constant value of the task priority after initialization, where the task queue Q initially contains all tasks: ,in, , It is a positive integer greater than 0 and is the total number of all execution times;

[0105] During task execution, monitor the execution time of each task Deviation from the tuning result , if the execution time of the task Longer than expected execution time , and the parameter adjustment results are biased Greater than expected deviation , then increase the priority of the task, the judgment conditions are: , The highest task priority;

[0106] High priority tasks Move to the front of the task queue Q and execute it first: ; For high priority tasks Allocate more system resources: ; In the formula, Allocate system resources for the highest;

[0107] Continuous monitoring of high priority tasks The execution of the test is used to determine whether the parameter adjustment results meet expectations. The judgment conditions are:

[0108] ;

[0109] Monitor the execution status of each parameter adjustment task in real time, and dynamically adjust the priority of the task according to the adjustment of different device parameters to reduce the overall parameter adjustment time. The specific judgment formula is:

[0110] ;

[0111] The formula is used to determine when the task execution time and the deviation of the parameter adjustment result exceed expectations. The whole process of ensuring that the parameter adjustment result meets expectations is ensured by adjusting the task priority, rearranging the task queue, allocating more system resources, and continuously monitoring the task execution status, thereby dynamically adjusting the task priority and reducing the overall parameter adjustment time.

[0112] In this embodiment, by creating a thread pool of fixed size, each parameter adjustment task will be assigned to a thread in the thread pool for processing. Initially, the tasks of all devices are added to the task queue and are assigned an initial priority. The threads in the thread pool start to execute the parameter adjustment tasks and monitor the execution status of the tasks in real time, including the execution time and the deviation of the parameter adjustment results. If the execution time of a task exceeds expectations and the deviation of the parameter adjustment results from expectations is large, the priority of the task is increased and it is moved to the front of the queue for priority execution. At the same time, more system resources are allocated to high-priority tasks to speed up their execution. The execution of high-priority tasks is continuously monitored until the parameter adjustment results meet expectations. Through this process, the priority of the task is dynamically adjusted to reduce the overall parameter adjustment time and ensure that the final parameter adjustment results meet expectations.

[0113] Example 3

[0114] See also Figure 2 As shown, the efficient synchronization device parameter adjustment system described in this embodiment includes a parameter adjustment interface module, a parameter adjustment efficiency judgment module, a parameter adjustment accuracy judgment module, a comprehensive analysis module, an adjustment consistency division module and a scheduling optimization module:

[0115] Parameter adjustment interface module: select the parameters to be adjusted through the parameter adjustment interface, decompose the parameter adjustment action into multiple parallel thread tasks, adjust the parameters of different devices through each task, wait for the adjustment action of each thread to be completed, and determine whether the overall parameter adjustment time between different devices is abnormal;

[0116] Parameter adjustment efficiency judgment module: When the overall parameter adjustment time between different devices is abnormal, the overall parameter adjustment efficiency between different devices is analyzed to determine the abnormal degree of the parameter adjustment efficiency during the device parameter adjustment process and evaluate the stability of the overall parameter adjustment efficiency between different devices;

[0117] Parameter adjustment accuracy judgment module: Each thread adjusts the same parameter of different devices synchronously. After the parameter adjustment of all devices has taken effect, the adjusted parameters are compared and analyzed to evaluate the accuracy of parameter adjustment of different devices.

[0118] Comprehensive analysis module: conducts comprehensive analysis on the stability of the overall parameter adjustment efficiency between different devices and the accuracy of parameter adjustment of different devices, and evaluates the consistency of parameter adjustment between different devices;

[0119] Adjustment consistency classification module: Based on the evaluation results, the consistency of parameter adjustment between different devices is divided into two categories: consistent adjustment and inconsistent adjustment;

[0120] Scheduling optimization module: When there are inconsistencies in parameter adjustments between different devices, the execution of parameter adjustment tasks is managed through the thread pool mechanism, the execution status of each parameter adjustment task is monitored in real time, and the priority of the task is dynamically adjusted according to the parameter adjustment conditions of different devices to reduce the overall parameter adjustment time.

[0121] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0122] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments 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 or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present 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 device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0123] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0124] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0125] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0126] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An efficient synchronous device parameter adjustment method, characterized in that: The steps include: S1: Select the parameter to be adjusted through the parameter adjustment interface, decompose the parameter adjustment action into multiple parallel thread tasks, adjust the parameters of different devices through each task, wait for the adjustment action of each thread to be completed, and determine whether the overall parameter adjustment time between different devices is abnormal; S2: When the overall parameter adjustment time between different devices is abnormal, analyze the overall parameter adjustment efficiency between different devices, determine the abnormal degree of the parameter adjustment efficiency during the device parameter adjustment process, and evaluate the stability of the overall parameter adjustment efficiency between different devices; Including obtaining the parameter adjustment efficiency fluctuation value, the parameter adjustment efficiency fluctuation value is obtained by: collecting the actual time data spent on parameter adjustment of each device, comparing the parameter adjustment time of different devices, analyzing the expected parameter adjustment time of each device by using an autoregressive sliding average model, setting the size of the time window to W according to the expected parameter adjustment time at the t-th time point, calculating the sliding average value of each time point, and calculating the adjustment time residual of each device at the t-th time point through the expected parameter adjustment time and the sliding average value, comparing and analyzing the sliding average value of each time point with the adjustment time residual at the t-th time point, and calculating the parameter adjustment efficiency fluctuation value; S3: Use each thread to synchronously adjust the same parameter of different devices. After the parameter adjustment of all devices has taken effect, compare and analyze the adjusted parameters to evaluate the accuracy of parameter adjustment of different devices. S4: Comprehensively analyze the stability of the overall parameter adjustment efficiency between different devices and the accuracy of parameter adjustment of different devices to evaluate the consistency of parameter adjustment between different devices; S5: According to the evaluation results, the consistency of parameter adjustment between different devices is divided into two categories: consistent adjustment and inconsistent adjustment; S6: When there is inconsistency in parameter adjustment between different devices, the execution of parameter adjustment tasks is managed through the thread pool mechanism, and the execution status of each parameter adjustment task is monitored in real time. According to the parameter adjustment situation of different devices, the priority of the task is dynamically adjusted to reduce the overall parameter adjustment time.

2. The method for adjusting parameters of a high-efficiency synchronous device according to claim 1, characterized in that: In S1, the device with abnormal adjustment time is identified from the system record, and its adjustment time data is collected, including the start adjustment time and the completion adjustment time of the abnormal device; Collect the adjustment time data of normal equipment, including the start adjustment time and the completion adjustment time of normal equipment; calculate the parameter adjustment time of abnormal equipment according to the start adjustment time and the completion adjustment time of abnormal equipment, and the parameter adjustment time is equal to the completion adjustment time minus the start adjustment time; For normal equipment, the parameter adjustment time of normal equipment is also calculated based on the start adjustment time and the completion adjustment time; For the parameter adjustment time of abnormal equipment, the degree of outlier is measured by outlier index; It includes calculating the mean and standard deviation of the parameter adjustment time of the abnormal devices, and then calculating the Z-score value of the parameter adjustment time of each abnormal device. For each abnormal device, check its calculated Z-score value, and compare the calculated Z-score value with the preset abnormal parameter adjustment time threshold. If the Z-score value of the abnormal device is greater than or equal to the abnormal parameter adjustment time threshold, then the overall parameter adjustment time between different devices is abnormal; if the Z-score value of the abnormal device is less than the abnormal parameter adjustment time threshold, then the overall parameter adjustment time between different devices is not abnormal.

3. The method for adjusting parameters of a high-efficiency synchronous device according to claim 1, characterized in that: The obtained parameter adjustment efficiency fluctuation value is compared with the adjustment efficiency fluctuation value reference threshold. If the adjustment efficiency fluctuation value is greater than or equal to the adjustment efficiency fluctuation value reference threshold, an overall parameter adjustment efficiency abnormal signal is generated; if the adjustment efficiency fluctuation value is less than the adjustment efficiency fluctuation value reference threshold, an overall parameter adjustment efficiency normal signal is generated.

4. The method for adjusting parameters of a high-efficiency synchronous device according to claim 1, characterized in that: In S3, the parameter values ​​after the equipment parameter adjustment are completed are compared with the parameter adjustment standard values, and the adjustment parameter deviation values ​​after the adjustment of different equipment parameters are completed are obtained to evaluate the accuracy of the adjustment of different equipment parameters. The method for obtaining the adjustment parameter deviation values ​​is: Acquire all parameter values ​​after parameter adjustment of each device, and establish a corresponding data set, and establish a corresponding data set with parameter adjustment standard values ​​corresponding to all parameter values ​​after parameter adjustment of the device; For each device, calculate the difference between all parameter values ​​after parameter adjustment and their corresponding parameter adjustment standard values, standardize each difference to obtain a standardized difference, and establish a standardized difference data set. After calculating the average value of the standardized differences in the standardized difference data set, calculate the deviation ratio of device parameter adjustment. Based on the calculated deviation ratio of parameter adjustment for each device, determine the degree of deviation of parameter adjustment of abnormal devices whose parameter adjustment results obviously deviate from those of normal devices among all devices, that is, calculate the adjustment parameter deviation value.

5. The method for adjusting parameters of a high-efficiency synchronous device according to claim 4, characterized in that: The obtained adjustment parameter deviation value is compared with the historical reference threshold of the adjustment parameter deviation value in the historical data. If the adjustment parameter deviation value is greater than or equal to the historical reference threshold of the adjustment parameter deviation value in the historical data, a parameter adjustment abnormal signal is generated; if the adjustment parameter deviation value is less than the historical reference threshold of the adjustment parameter deviation value in the historical data, a parameter adjustment normal signal is generated.

6. The method for adjusting parameters of a high-efficiency synchronous device according to claim 5, characterized in that: In S4, the stability of the overall parameter adjustment efficiency between different devices and the accuracy of parameter adjustment of different devices are comprehensively analyzed, specifically: The adjustment efficiency fluctuation value and the adjustment parameter deviation value are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses each group of first eigenvectors to predict the consistency value label of the parameter adjustment between different devices as the prediction target, and takes minimizing the sum of the prediction errors of the consistency value labels of the parameter adjustment between all different devices as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The consistency coefficient of the parameter adjustment between different devices is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

7. The method for adjusting parameters of a high-efficiency synchronous device according to claim 6, characterized in that: In S5, the consistency of parameter adjustment between different devices is divided into two categories: consistency adjustment and inconsistency adjustment, specifically: The obtained consistency coefficient of parameter adjustment between different devices is compared with the consistency standard threshold. If the consistency coefficient of parameter adjustment between different devices is greater than or equal to the consistency standard threshold, the consistency degree of parameter adjustment between different devices is classified as consistency adjustment, and no additional adjustment is required. If the consistency coefficient of parameter adjustment between different devices is less than the consistency standard threshold, the consistency degree of parameter adjustment between different devices is classified as inconsistent adjustment, and the parameters of the devices are readjusted.

8. The method for adjusting parameters of a high-efficiency synchronous device according to claim 7, characterized in that: In S6, the execution status of each parameter adjustment task is monitored in real time. According to the adjustment of different device parameters, the priority of the task is dynamically adjusted to reduce the overall parameter adjustment time. Specifically: The task execution time of device h is marked as T h , the expected execution time of the task of device h is marked as E h , mark the deviation of the parameter adjustment result of device h as D h , the task priority of device h is marked as P h , the system resources allocated by device h are marked as R h , the task queue is marked as Q; Initialize the priority and task queue. The initial priority of each device is set to a constant value. The task queue Q initially contains all tasks. During the task execution process, monitor the execution time and parameter adjustment result deviation of each task. If the execution time of the task is longer than the expected execution time and the parameter adjustment result deviation is greater than the expected deviation value, increase the priority of the task. Move high-priority tasks to the front of the task queue, execute them first, and allocate more system resources to them; Continuously monitor the execution of high-priority tasks to determine whether their parameter adjustment results meet expectations.

9. The method for adjusting parameters of a high-efficiency synchronous device according to claim 8, characterized in that: Monitor the execution status of each parameter adjustment task in real time, and dynamically adjust the task priority according to the adjustment of different device parameters to reduce the overall parameter adjustment time. When the task execution time and the deviation of the parameter adjustment result exceed expectations, continuously monitor the task execution status to ensure that the parameter adjustment result meets the expected process, dynamically adjust the task priority, and reduce the overall parameter adjustment time.

10. A high-efficiency synchronous device parameter adjustment system, used to implement the high-efficiency synchronous device parameter adjustment method according to any one of claims 1 to 9, characterized in that: It includes parameter adjustment interface module, parameter adjustment efficiency judgment module, parameter adjustment accuracy judgment module, comprehensive analysis module, adjustment consistency division module and scheduling optimization module: Parameter adjustment interface module: select the parameters to be adjusted through the parameter adjustment interface, decompose the parameter adjustment action into multiple parallel thread tasks, adjust the parameters of different devices through each task, wait for the adjustment action of each thread to be completed, and determine whether the overall parameter adjustment time between different devices is abnormal; Parameter adjustment efficiency judgment module: When the overall parameter adjustment time between different devices is abnormal, the overall parameter adjustment efficiency between different devices is analyzed to determine the abnormal degree of the parameter adjustment efficiency during the device parameter adjustment process and evaluate the stability of the overall parameter adjustment efficiency between different devices; Parameter adjustment accuracy judgment module: Each thread adjusts the same parameter of different devices synchronously. After the parameter adjustment of all devices has taken effect, the adjusted parameters are compared and analyzed to evaluate the accuracy of parameter adjustment of different devices. Comprehensive analysis module: comprehensively analyzes the stability of the overall parameter adjustment efficiency between different devices and the accuracy of parameter adjustment of different devices, and evaluates the consistency of parameter adjustment between different devices; Adjustment consistency classification module: Based on the evaluation results, the consistency of parameter adjustment between different devices is divided into two categories: consistent adjustment and inconsistent adjustment; Scheduling optimization module: When there are inconsistencies in parameter adjustments between different devices, the execution of parameter adjustment tasks is managed through the thread pool mechanism, the execution status of each parameter adjustment task is monitored in real time, and the priority of the task is dynamically adjusted according to the parameter adjustment conditions of different devices to reduce the overall parameter adjustment time.

Images