Production task dynamic adjustment method and system based on industrial vertical class large model

Abstract

The invention relates to the field of data processing, in particular to a production task dynamic adjustment method and system based on an industrial vertical large model, and the method comprises the steps: taking one-time production task scheduling as a time node, collecting workpiece process parameters from the scheduling completion to the processing completion at the current moment in real time, working procedure parameters of historical workpieces in all working procedures are obtained, the collected data are preprocessed, and a historical parameter sequence and a current parameter sequence are obtained respectively; calculating influence coefficients among the real-time production processes based on the current parameter sequence; and calculating the accumulated value of the influence coefficients corresponding to the processing of all workpieces from the scheduling completion to the current moment, and when the accumulated value of the influence coefficients is greater than a preset scheduling threshold value, triggering a rescheduling instruction to adjust a preset production task. According to the invention, through fusion of real-time data analysis and historical experience, adaptive optimization of the production process is realized.

Description

Technical Field

[0001] The present invention relates to the field of data processing. More specifically, the present invention relates to a method and system for dynamically adjusting production tasks based on an industrial vertical model. Background Art

[0002] Job shops, a common production model in modern manufacturing, cover multiple processing stages. In real-world production, the shop floor environment is constantly changing, with emergencies such as machine failures and urgent orders. To maintain production efficiency, these events must be responded to quickly, with production plans adjusted in real time to ensure timely completion of workpieces.

[0003] Currently, emergency response technologies are relatively mature. However, when responding to these emergencies, it's often easy to overlook low-priority disturbances, such as minor equipment fluctuations or material delays. While the impact of each individual disturbance is minimal, these disturbances can trigger a chain reaction through interactions between processes, potentially impacting the entire production process. Therefore, while handling emergencies, it's also necessary to monitor the interactions between processes and adjust production tasks in real time to maintain production stability and ensure timely completion of workpieces. Summary of the Invention

[0004] In order to solve the technical problem that the above-mentioned existing production scheduling technology ignores the chain reaction caused by low-priority disturbances through process coupling when responding to emergency dynamic events, thereby affecting the stability of the entire production process and the timely completion of workpieces, the present invention provides solutions in the following aspects.

[0005] In the first aspect, a method for dynamically adjusting production tasks based on an industrial vertical large model includes: Taking a production task scheduling as the time node, the process parameters of the workpiece from the completion of scheduling to the current moment of processing are collected in real time, and the process parameters of the historical workpiece in each process are obtained. The collected data are pre-processed to obtain the historical parameter sequence and the current parameter sequence respectively; Calculate the influence coefficients between various historical production processes based on historical parameter sequences; calculate the influence coefficients between various real-time production processes based on current parameter sequences; Calculate the cumulative value of the impact coefficient corresponding to all workpiece processing from the completion of scheduling to the current moment. When the cumulative value of the impact coefficient is greater than the preset scheduling threshold, trigger the rescheduling instruction and adjust the pre-set production task.

[0006] Preferably, the process parameters include workpiece processing time, processing equipment temperature and processing equipment pressure.

[0007] Preferably, the calculation of the influence coefficients between the various historical production processes based on the historical parameter sequence includes: Define the standard values ​​of the process parameters of the workpiece in any process and build the standard parameter sequence of the workpiece in each process; take the absolute value of the difference between each parameter in the historical parameter sequence of any workpiece in each process and the corresponding standard parameter to form a deviation difference sequence; Calculate the mutual information between the deviation difference sequences of all workpieces in the previous and next processes, calculate the standard deviation of the deviation difference sequence of any workpiece in all processes, add the product of the mutual information and standard deviation of all historical workpieces, divide it by the total number of historical workpieces and perform normalization to obtain the influence coefficient between adjacent processes.

[0008] Preferably, the calculation of the influence coefficients between the various historical production processes based on the historical parameter sequence includes: Define the standard values ​​of the process parameters of the workpiece in any process and build the standard parameter sequence of the workpiece in each process; take the absolute value of the difference between each parameter in the historical parameter sequence of any workpiece in each process and the corresponding standard parameter to form a deviation difference sequence; Calculate the Pearson correlation coefficient between the deviation difference sequence of all workpieces in the previous and next processes, calculate the standard deviation of the deviation difference sequence of any workpiece in all processes, then add the product of the Pearson correlation coefficient and the standard deviation of all historical workpieces, divide it by the total number of historical workpieces and perform normalization to obtain the influence coefficient between adjacent processes.

[0009] Preferably, the calculation method of the influence coefficient between each process in real-time production is the same as the calculation method of the influence coefficient between each process in historical production.

[0010] Preferably, the setting of the scheduling threshold includes: For all historical production, calculate the mean of the cumulative sum of the differences between the actual value and the standard value of the processing parameter of any process as the deviation from the mean of the process, and then calculate the standard deviation of the deviation from the mean of the process; The deviation from the mean and standard deviation values ​​are weighted and summed to obtain the deviation from the baseline threshold of the process; the deviation from the baseline threshold of a single process is combined with the influence coefficient between the process and the next process to obtain the scheduling threshold.

[0011] Preferably, the setting of the scheduling threshold further includes adjusting the scheduling threshold to obtain a final scheduling threshold, and the adjustment process includes: Calculate the difference between the deviation mean of each process in the current production process and the deviation mean of the corresponding process in history, and sum up all processes to obtain the adjustment factor; multiply the adjustment factor by the scheduling threshold to obtain the final scheduling threshold.

[0012] In the second aspect, a dynamic adjustment system for production tasks based on industrial vertical big models includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, any one of the dynamic adjustment methods for production tasks based on industrial vertical big models is implemented.

[0013] The beneficial effects of the present invention are: The present invention collects data in real time and calculates the cumulative value of the influence coefficient. When the scheduling threshold is exceeded, a rescheduling instruction is triggered. The production tasks can be dynamically adjusted according to the actual situation in the production process, avoiding the inability to respond to emergencies or production deviations due to fixed plans, thereby improving the accuracy and adaptability of the production plan and ensuring the smooth completion of production tasks.

[0014] The calculation of the influence coefficients between various processes leverages historical and real-time data. By defining a standard parameter sequence and constructing a deviation difference sequence, both mutual information-based and Pearson correlation-based calculations accurately reveal the inter-process influence and correlation from different dimensions and perspectives. Furthermore, scheduling thresholds are dynamically adjusted (via adjustment factors) based not only on historical deviations from the mean and standard deviation but also on actual deviations in current production, ensuring more precise threshold settings and preventing over- or under-scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a method flow chart of steps S1 to S3 in the method for dynamically adjusting production tasks based on an industrial vertical large model in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The technical solutions 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 only part of the embodiments of the present invention, but not all of the embodiments.

[0017] Reference Figure 1 The method for dynamically adjusting production tasks based on the industrial vertical model includes steps S1 to S3, which are as follows: S1: Taking a production task scheduling as the time node, the process parameters of the workpiece from the completion of scheduling to the current moment of processing are collected in real time, and the process parameters of the historical workpiece in each process are obtained. The collected data are preprocessed to obtain the historical parameter sequence and the current parameter sequence respectively.

[0018] In one embodiment, parameter data for at least 100 historically processed workpieces in various processes (including turning, milling, grinding, etc.) is collected, including parameters such as workpiece processing time, equipment temperature, and equipment pressure. The parameter data for each workpiece in any process is organized into a corresponding historical parameter sequence.

[0019] Using a production task schedule as a time node, we collect the process parameters of at least 100 completed workpieces from the time the schedule was completed to the current moment in real time. These process parameters are the same as the parameter data obtained above. Similarly, the parameter data of each workpiece in any process is combined into a corresponding current parameter sequence.

[0020] The historical parameters and current parameters collected above are further preprocessed, such as using Gaussian filtering to remove noise, and each parameter is standardized to ensure that the data are comparable on the same scale.

[0021] S2: Calculate the influence coefficients between various historical production processes based on the historical parameter sequence; calculate the influence coefficients between various real-time production processes based on the current parameter sequence.

[0022] In modern manufacturing, workshops often encounter urgent dynamic events such as machine failures and urgent workpiece insertions. These events require prompt response and handling, otherwise they can disrupt the smooth progress of the entire production plan. In addition to urgent events, the production process also experiences low-priority disturbances, such as minor equipment fluctuations and minor material delays. While these disturbances may have a small impact individually, they can trigger a chain reaction through process coupling, gradually accumulating and significantly impacting the production process. Therefore, while responding promptly to urgent dynamic events, it is necessary to simultaneously address the cumulative impact of low-priority disturbances.

[0023] By analyzing historical data and quantifying the degree of deviation in workpiece parameters within each process, we can clearly identify the impact of each process on the others. This quantitative analysis helps us better understand the inherent relationships within the production process. Calculating the influence coefficients between adjacent processes can more accurately reflect the impact of the previous process on the subsequent one. This impact can manifest itself as, for example, a parameter deviation in the previous process leading to a change in the processing quality of the subsequent process.

[0024] First, define the standard values ​​of the process parameters of the workpiece in any process, such as the standard processing time is 10 minutes, and then build the standard parameter sequence of the workpiece in each process; Furthermore, for any workpiece in each process, the absolute value of the difference between each parameter in the historical parameter sequence and the corresponding standard parameter is taken to form a deviation difference sequence.

[0025] In one embodiment, a mutual information method is used to quantify the influence coefficient of a previous process on a subsequent process, so as to better understand the relationship between processes in the production process.

[0026] Calculate the mutual information between the deviation difference sequences of all workpieces in the previous and next processes. In short, calculating the mutual information indicates how much information is shared between the deviation difference sequences of the two processes, or how strong their correlation is. The larger the mutual information value, the more correlated the deviation between the two processes, that is, the higher the influence coefficient of the previous process on the next process.

[0027] At the same time, the standard deviation of the deviation of any workpiece from the difference sequence in all processes is also considered. The larger the standard deviation, the more discrete the parameter deviation of the workpiece is and the greater the possibility of abnormality.

[0028] Finally, the product of the mutual information and standard deviation of all historical artifacts is added, divided by the total number of historical artifacts and normalized to obtain the influence coefficient between adjacent processes.

[0029] For example, the above influence coefficient is expressed as follows: Where, For process and process The influence coefficient between For the history Workpieces in process The deviation difference sequence of For the history Workpieces in process The deviation difference sequence of represents mutual information, is the total number of historical artifacts, For the history The standard deviation of the difference sequence of the workpiece in all processes, Indicates normalization processing.

[0030] In another embodiment, the Pearson correlation coefficient method is used to quantify the influence coefficient of the previous process on the next process, so as to better understand the relationship between the processes in the production process.

[0031] First, the Pearson correlation coefficient between the deviation difference sequence of all workpieces in the previous and next processes is calculated, and the standard deviation of the deviation difference sequence of any workpiece in all processes is calculated. Then, the product of the Pearson correlation coefficient and the standard deviation of all historical workpieces is added, and then divided by the total number of historical workpieces and normalized to obtain the influence coefficient between adjacent processes.

[0032] Then the above influence coefficient satisfies the relationship: Where, For process and process The influence coefficient between For the history Workpieces in process The deviation difference sequence of For the history Workpieces in process The deviation difference sequence of represents the Pearson correlation coefficient, is the total number of historical artifacts, For the history The standard deviation of the difference sequence of the workpiece in all processes, Indicates normalization processing.

[0033] The above Pearson correlation coefficient value is close to 1, indicating that the two sequences are highly positively correlated in their changing trends, that is, when the parameter deviation of one process increases, the parameter deviation of the next process also tends to increase; if the Pearson correlation coefficient is close to -1, it indicates that the two sequences are highly negatively correlated, that is, when the parameter deviation of one process increases, the parameter deviation of the next process tends to decrease; if the Pearson correlation coefficient value is close to 0, it indicates that there is almost no linear correlation between the two sequences.

[0034] In general, if the PPMCC value is very high (close to 1 or -1), it means that the parameter changes in the previous process have a significant impact on the next process, which may mean that small fluctuations in the previous process will be transmitted to the next process through process coupling; if the PPMCC value is low (close to 0), it indicates that the linear correlation between the two processes is weak, which may mean that the fluctuations in the previous process have little impact on the next process.

[0035] The standard deviation is used as a weight factor. The larger the standard deviation, the more discrete the parameter deviation of the workpiece in the process, and the greater the possibility of abnormality. Therefore, when calculating the influence coefficient between adjacent processes, a higher weight is given; the smaller the standard deviation, the more concentrated the parameter deviation of the workpiece in the process, and the smaller the possibility of abnormality. Therefore, when calculating the influence coefficient between adjacent processes, a lower weight is given.

[0036] By calculating the deviation degree of historically processed workpieces and the influence coefficients between historical processes, a benchmark reference can be established for the entire production process. This allows us to understand the approximate range of deviation of workpiece parameters from the standard in each process under normal production conditions, as well as the mutual influence of parameter deviations between adjacent processes.

[0037] Since the production process is dynamic and may be affected by various factors, such as equipment wear and fluctuations in the quality of workpiece raw materials, it is necessary to turn attention to the workpiece parameter data in the current production process.

[0038] In one embodiment, according to the above calculation formula for calculating the influence coefficient between each historical production process based on the historical parameter sequence, the influence coefficient between each real-time production process is similarly calculated based on the current parameter sequence.

[0039] S3: Calculate the cumulative value of the impact coefficient corresponding to all workpiece processing from the completion of scheduling to the current moment. When the cumulative value of the impact coefficient is greater than the preset scheduling threshold, trigger the rescheduling instruction to adjust the pre-set production task.

[0040] After determining the influence coefficients between each real-time production process, the average of the deviation difference series for any workpiece in any process from the time the schedule was completed to the current moment is calculated, multiplied by the influence coefficient between that process and the next process. This sum is then applied to all workpieces and all processes to obtain the cumulative influence coefficients corresponding to all workpieces processed from the time the schedule was completed to the current moment. This cumulative influence coefficient value is then used to further analyze the impact it has on production progress.

[0041] It's important to consider that in actual production, there's a certain tolerance for deviations in workpiece processing parameters from their standard values ​​in each process. By setting reasonable baseline deviation thresholds and cumulative impact coefficient thresholds, production strategies can be flexibly adjusted based on actual production conditions. This improves production flexibility and adaptability while ensuring quality, better meeting actual production needs.

[0042] In one embodiment, a deviation threshold value of each process step is calculated based on historical processing parameter data.

[0043] First, obtain all the processing parameter data for each process in each historical production run and determine the standard or ideal values ​​for each process parameter. For all historical production runs, calculate the mean of the cumulative sum of the differences between the actual and standard values ​​of the process parameters for that process. This is used as the deviation from the mean for that process, and then calculate the standard deviation of this deviation from the mean.

[0044] The deviation from the mean and standard deviation values ​​are weighted and summed to obtain the deviation from the baseline threshold of the process. This satisfies the following relationship: Where, For process The deviation threshold from the baseline, For historical production processes The deviation from the mean, For historical production processes The standard deviation of the deviation from the mean. is the safety factor, and the initial value is 3.

[0045] Taking into account the influence between adjacent processes, after obtaining the deviation threshold of each process from the baseline, the deviation threshold of a single process is combined with the influence coefficient between adjacent processes to obtain the scheduling threshold, which satisfies the relationship: Where, is the scheduling threshold, For process The deviation threshold from the baseline, For real-time production processes and process The influence coefficient between is the total number of processes.

[0046] The above scheduling threshold reflects the cumulative impact of the deviation of each process in the historical processing data on the overall production task.

[0047] When the disturbance in the production process is small, if the production task rescheduling is frequently triggered according to a fixed threshold, the scheduling cost will increase, including the workload of the scheduling personnel, the downtime adjustment time of the production equipment, etc. Therefore, it is necessary to further dynamically adjust the scheduling threshold.

[0048] In one embodiment, the difference between the deviation mean of each process in the current production process and the deviation mean of the corresponding process in history is calculated, and the sum of all processes is summed to obtain an adjustment factor.

[0049] Multiplying this adjustment factor by the aforementioned scheduling threshold yields the final scheduling threshold. Dynamically adjusting the scheduling threshold ensures that scheduling decisions are both adaptable to current production conditions and infrequent, avoiding resource waste.

[0050] In one embodiment, the cumulative value of the impact coefficients of all processed workpieces in the entire processing process from the completion of one scheduling to the current moment is compared with the final scheduling threshold. If the cumulative value of the impact coefficients is less than or equal to the final scheduling threshold, it means that the cumulative impact coefficients in the current production process have not exceeded the final scheduling threshold, and the production tasks are still within the controllable range, and the production tasks can continue to be scheduled according to the last scheduling results; on the contrary, if the cumulative value of the impact coefficients is greater than the final scheduling threshold, it means that the disturbances in the production process have accumulated to a certain extent and exceeded the final scheduling threshold. At this time, it is determined that the production process needs to be adjusted, and the production task rescheduling instruction is automatically triggered to make new scheduling arrangements for the production tasks.

[0051] When a rescheduling order is triggered, the rescheduling objectives and principles should be clearly defined, such as prioritizing key processes, minimizing the impact on the overall production schedule, and rationally utilizing existing resources. For example, after a rescheduling order is issued, the production scheduling department is required to develop a new production plan within two hours, ensuring that the process sequence and resource allocation of the current production task are adjusted without affecting other production deliveries.

[0052] The system includes a processor and a memory, and the memory stores computer program instructions. When the computer program instructions are executed by the processor, the method for dynamically adjusting production tasks based on the industrial vertical model according to the first aspect of the present invention is implemented.

[0053] The system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and therefore will not be described in detail here.

[0054] It should be noted that those skilled in the art may make various modifications and improvements without departing from the scope of the present invention, and these modifications and improvements fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be based on the appended claims.

Claims

1. A method for dynamically adjusting production tasks based on an industrial vertical model, characterized in that: include: Taking a production task scheduling as the time node, the process parameters of the workpiece from the completion of scheduling to the current moment of processing are collected in real time, and the process parameters of the historical workpiece in each process are obtained. The collected data are pre-processed to obtain the historical parameter sequence and the current parameter sequence respectively; Calculate the influence coefficients between various historical production processes based on historical parameter sequences; calculate the influence coefficients between various real-time production processes based on current parameter sequences; Calculate the cumulative value of the impact coefficient corresponding to all workpiece processing from the completion of scheduling to the current moment. When the cumulative value of the impact coefficient is greater than the preset scheduling threshold, trigger the rescheduling instruction and adjust the pre-set production task.

2. The method for dynamically adjusting production tasks based on an industrial vertical model according to claim 1 is characterized in that: The process parameters include workpiece processing time, processing equipment temperature and processing equipment pressure.

3. The method for dynamically adjusting production tasks based on an industrial vertical model according to claim 1 is characterized in that: The calculation of the influence coefficients between the various historical production processes based on the historical parameter sequence includes: Define the standard values ​​of the process parameters of the workpiece in any process and build the standard parameter sequence of the workpiece in each process; take the absolute value of the difference between each parameter in the historical parameter sequence of any workpiece in each process and the corresponding standard parameter to form a deviation difference sequence; Calculate the mutual information between the deviation difference sequences of all workpieces in the previous and next processes, calculate the standard deviation of the deviation difference sequence of any workpiece in all processes, add the product of the mutual information and standard deviation of all historical workpieces, divide it by the total number of historical workpieces and perform normalization to obtain the influence coefficient between adjacent processes.

4. The method for dynamically adjusting production tasks based on an industrial vertical model according to claim 1 is characterized in that: The calculation of the influence coefficients between the various historical production processes based on the historical parameter sequence includes: Define the standard values ​​of the process parameters of the workpiece in any process and build the standard parameter sequence of the workpiece in each process; take the absolute value of the difference between each parameter in the historical parameter sequence of any workpiece in each process and the corresponding standard parameter to form a deviation difference sequence; Calculate the Pearson correlation coefficient between the deviation difference sequence of all workpieces in the previous and next processes, calculate the standard deviation of the deviation difference sequence of any workpiece in all processes, then add the product of the Pearson correlation coefficient and the standard deviation of all historical workpieces, divide it by the total number of historical workpieces and perform normalization to obtain the influence coefficient between adjacent processes.

5. The method for dynamically adjusting production tasks based on an industrial vertical model according to claim 1 is characterized in that: The calculation method of the influence coefficient between each process in real-time production is the same as the calculation method of the influence coefficient between each process in historical production.

6. The method for dynamically adjusting production tasks based on an industrial vertical model according to claim 1 is characterized in that: The setting of the scheduling threshold includes: For all historical production, calculate the mean of the cumulative sum of the differences between the actual value and the standard value of the processing parameter of any process as the deviation from the mean of the process, and then calculate the standard deviation of the deviation from the mean of the process; The deviation from the mean and standard deviation values ​​are weighted and summed to obtain the deviation from the baseline threshold of the process; the deviation from the baseline threshold of a single process is combined with the influence coefficient between the process and the next process to obtain the scheduling threshold.

7. The method for dynamically adjusting production tasks based on an industrial vertical model according to claim 6 is characterized in that: The setting of the scheduling threshold also includes adjusting the scheduling threshold to obtain a final scheduling threshold. The adjustment process includes: Calculate the difference between the deviation mean of each process in the current production process and the deviation mean of the corresponding process in history, and sum up all processes to obtain the adjustment factor; multiply the adjustment factor by the scheduling threshold to obtain the final scheduling threshold.

8. The production task dynamic adjustment system based on the industrial vertical model is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for dynamically adjusting production tasks based on an industrial vertical model according to any one of claims 1 to 7 is implemented.

Images