Intelligent scheduling and tracking method and tracking system

Abstract

The invention discloses an intelligent scheduling and tracking method and tracking system, and particularly relates to the technical field of data management. By setting the comparison between ideal production state data and actual production data, monitoring the change of the production data in real time and calculating the deviation degree and coupling degree abnormal index, the failure risk of the intelligent scheduling system can be effectively identified, the system is divided into different adaptability levels according to the adaptability evaluation result, and for the high adaptability level, the system can be effectively identified. A resource allocation strategy is further optimized; for the low adaptability level, the failure decision is responded and repaired in time, and the impact on production is reduced; for the medium adaptability level, the adaptability of the system to data distribution drift is improved by predicting the abnormal degree and continuously optimizing the scheduling decision, so that the operation balance of the production line is ensured, the productivity is maximized, stagnation is avoided, the change of the industrial production environment can be dynamically adapted, and the accuracy of the intelligent scheduling system is improved; and the stability and reliability of production efficiency are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to an intelligent scheduling and tracking method and a tracking system. Background Art

[0002] Intelligent scheduling and tracking refers to the use of artificial intelligence (AI), big data, Internet of Things (IoT) and other technologies to optimize resource allocation and location tracking. Through algorithms and real-time data analysis, it improves system operation efficiency, reduces resource waste, and achieves accurate task allocation and dynamic adjustment. Intelligent scheduling is often used to solve resource allocation problems in complex systems, such as the prioritization of personnel, vehicles, equipment or tasks, while tracking methods monitor the location and status of these resources through sensors and positioning technology to achieve visualization and real-time management.

[0003] In industrial production, the intelligent scheduling system uses artificial intelligence technology to monitor and analyze the operating status of equipment on the production line in real time, optimize resource allocation and worker scheduling strategies, and maximize production efficiency. For example, when a certain device is overloaded or abnormal, the system can automatically adjust other devices to take over the task to avoid production interruptions. At the same time, with the help of sensors and Internet of Things technology, key equipment can be accurately tracked, and real-time feedback on operating status and maintenance needs can be provided, helping companies to promptly detect potential failures and take preventive measures, effectively reducing downtime and maintenance costs.

[0004] The prior art has the following deficiencies: The algorithms of intelligent scheduling systems usually rely on historical data and training models. However, the industrial production environment may change over time, such as equipment aging, fluctuations in production demand, and the introduction of new processes, causing data distribution to drift. If the model fails to dynamically adapt to these changes, the system scheduling decisions will quickly lose their effectiveness, which may lead to reduced production efficiency or even system chaos. And if the decision-making of the scheduling system fails, it will lead to unreasonable resource allocation, such as some equipment running overload while other equipment is idle, and unbalanced production line operation. Critical tasks may not be completed on time, overall production capacity will drop significantly, or even production will stagnate. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent scheduling and tracking method and tracking system to solve the shortcomings of the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: an intelligent scheduling and tracking method, comprising the following steps: S1: Set the ideal production state data in the production process as the target production data, and collect real-time production data in several time periods in the actual production process, compare the real-time production data with the target production data, and divide the real-time production data into production data that deviates from the target and production data that does not deviate from the target; S2: Analyze the distribution changes of the production data that deviates from the target in each time period, select the production data distribution in the initial time period of the intelligent scheduling system as the benchmark distribution, and determine the degree of deviation between the production data distribution in the current time period and the benchmark distribution; S3: If the degree of deviation is high, collect historical data of the scheduling prediction value of the intelligent scheduling system model and the actual equipment utilization rate, calculate the coupling degree after regression analysis, and analyze the abnormal changes of the coupling degree under different drift states to evaluate the impact of the intelligent scheduling system model failure on the production target; S4: Evaluate the adaptability of the intelligent scheduling system model to data distribution drift based on the degree of deviation between the production data distribution and the benchmark distribution in the current time period and the impact on the production target when the intelligent scheduling system model fails; S5: Based on the evaluation results, the adaptability of the intelligent scheduling system model to data distribution drift is divided into high adaptability level, medium adaptability level and low adaptability level. For the high adaptability level, the resource allocation strategy is further refined. For the low adaptability level, the failed decision is quickly responded and repaired to reduce the impact on production. S6: For the medium adaptability level, the abnormal degree of the intelligent scheduling system model's adaptability to data distribution drift within a fixed time period is predicted. If the abnormal degree is high, the intelligent scheduling system model is continuously optimized to improve the accuracy of scheduling decisions.

[0007] Preferably, in S1, the real-time data and the target data are compared in the same time window, and the deviation between the actual production data and the target production data is calculated, and the expression is: ; Compare the deviation between the actual production data and the target production data with the deviation reference threshold under normal production conditions set according to historical data. If the deviation between the actual production data and the target production data is greater than the deviation reference threshold, it is classified as deviating from the target production data; if the deviation between the actual production data and the target production data is less than or equal to the deviation reference threshold, it is classified as not deviating from the target production data.

[0008] Preferably, in S2, the deviation degree between the production data distribution and the reference distribution in the current time period is analyzed to generate a reference distribution deviation index, and the reference distribution deviation index is obtained by: Set the benchmark distribution and current distribution. The benchmark distribution P is the ideal production status data distribution, and the current distribution Q is the production data distribution collected in real time during the current time period. Calculate the KL divergence between the benchmark distribution and the current time period distribution. The calculation formula is: ;in: is the KL divergence between the benchmark distribution and the current time period distribution; P(i) is the probability mass of the i-th class in the benchmark distribution P; Q(i) is the probability mass of the i-th class in the current distribution Q; the calculated KL divergence between the benchmark distribution and the current time period distribution is used as the benchmark distribution deviation index.

[0009] Preferably, in S3, after analyzing the abnormal changes of the coupling degree under different drift states, a coupling degree abnormality index is generated, and the method for obtaining the coupling degree abnormality index is: Construct historical coupling degree series respectively , and construct the coupling degree sequence ; First, construct an n×m distance matrix, where n and m are the lengths of the historical coupling sequence and the current coupling sequence respectively; at each element position (i, j), calculate the current time point and The distance between them, using the Euclidean distance , the expression is: ; The cumulative distance matrix is ​​calculated through dynamic programming. Each element D(i,j) of the cumulative distance matrix represents the minimum cumulative distance from the starting point to the position (i,j). The calculation formula is: ; In the formula, Represent paths in three directions: vertical, horizontal, and diagonal. By selecting the shortest path to accumulate the minimum distance, the shortest path DTW distance is calculated. The DTW distance is the element D(n,m) in the lower right corner of the matrix, that is, the minimum cumulative distance from the historical data sequence to the current data sequence. Normalize the DTW distance to get a standardized DTW distance value , the expression is: ; The normal mode DTW distance range is the mean and standard deviation of the DTW distances of multiple normal time periods calculated through historical data. The mean DTW distance of the historical normal mode is set to , the standard deviation is ; According to the difference between the current DTW distance and the historical mean, the coupling abnormality index is calculated. The formula is: ; Where Gt is the coupling anomaly index.

[0010] Preferably, in S4, the adaptability of the intelligent scheduling system model to data distribution drift is evaluated according to the degree of deviation between the production data distribution and the benchmark distribution in the current time period and the impact on the production target when the intelligent scheduling system model fails, specifically: The benchmark distribution deviation index and coupling degree anomaly index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the adaptability value label of the intelligent scheduling system model to the data distribution drift as the prediction target, and takes minimizing the sum of the prediction errors of the adaptability value labels of all intelligent scheduling system models to the data distribution drift 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 adaptability value of the intelligent scheduling system model to the data distribution drift is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0011] Preferably, in S5, the adaptability of the intelligent scheduling system model to data distribution drift is divided into a high adaptability level, a medium adaptability level and a low adaptability level, specifically: Compare the obtained adaptability value of the intelligent scheduling system model to the data distribution drift with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and compare the adaptability value of the intelligent scheduling system model to the data distribution drift with the first standard threshold and the second standard threshold respectively; If the adaptability value of the intelligent scheduling system model to data distribution drift is greater than the second standard threshold, it means that the intelligent scheduling system model has good adaptability to data distribution drift. At this time, a high adaptability signal is generated, and the adaptability of the intelligent scheduling system model to data distribution drift is classified as a high adaptability level; If the adaptability value of the intelligent scheduling system model to data distribution drift is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the adaptability of the intelligent scheduling system model to data distribution drift is average, and a medium adaptability signal is generated at this time, and the adaptability of the intelligent scheduling system model to data distribution drift is classified as a medium adaptability level; If the adaptability value of the intelligent scheduling system model to data distribution drift is less than the first standard threshold, it means that the intelligent scheduling system model has poor adaptability to data distribution drift. At this time, a low adaptability signal is generated, and the adaptability of the intelligent scheduling system model to data distribution drift is classified as a low adaptability level.

[0012] Preferably, in S6, for the medium adaptability level, the abnormal degree of adaptability of the intelligent scheduling system model to data distribution drift within a fixed time period is predicted, specifically: For the medium adaptability level, that is, the adaptability value of the intelligent scheduling system model generated within a fixed time period to the data distribution drift is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the adaptability values ​​generated within the subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected, and the corresponding data set is established, and the standard deviation of the data set is calculated as the adaptability abnormality degree value; The obtained adaptive abnormality degree value is compared with the abnormality degree value reference threshold value pre-set according to historical data. If the adaptive abnormality degree value is greater than or equal to the pre-set abnormality degree value reference threshold value, it means that the abnormality degree of adaptability of the intelligent scheduling system model to the data distribution drift within a fixed time period is high. At this time, an early warning signal is generated and the intelligent scheduling system is optimized; if the adaptive abnormality degree value is less than the pre-set abnormality degree value reference threshold value, it means that the abnormality degree of adaptability of the intelligent scheduling system model to the data distribution drift within a fixed time period is low. At this time, no early warning signal is generated and no additional processing is required.

[0013] Preferably, if the abnormality level is high, the intelligent dispatching system model is continuously optimized to improve the accuracy of dispatching decisions, specifically: Set the scheduling decision of the current model through a function To express, the intelligent scheduling system optimizes the decision by adjusting the model parameters θ: ;in: is a scheduling decision based on the current model prediction, is the actual production output result, is the regularization parameter, AE is the abnormality value, and s is the total number of samples; According to the optimized objective function, the model parameters θ are adjusted, and the new parameters are used to predict the scheduling decision. The optimization process is updated based on the gradient descent method: ; where η is the learning rate, ∇θ is the gradient of the objective function with respect to the model parameters, is the model parameter used by the intelligent scheduling system for the tth iteration, For the In the iteration, the new model parameters are optimized.

[0014] The present invention also provides an intelligent scheduling and tracking system, including a data comparison module, a distribution detection module, a coupling degree analysis module, an adaptability evaluation module, an adaptability level division module and an optimization module: Data comparison module: Set the ideal production status data in the production process as the target production data, and collect real-time production data in several time periods in the actual production process, compare the real-time production data with the target production data, and divide the real-time production data into production data that deviates from the target and production data that does not deviate from the target; Distribution detection module: Analyzes the distribution changes of production data that deviates from the target in each time period, selects the production data distribution in the initial time period of the intelligent scheduling system as the benchmark distribution, and determines the degree of deviation between the production data distribution in the current time period and the benchmark distribution; Coupling degree analysis module: If the degree of deviation is high, the historical data of the scheduling prediction value and the actual equipment utilization rate of the intelligent scheduling system model are collected, and the coupling degree is calculated after regression analysis. The abnormal changes of the coupling degree under different drift states are analyzed to evaluate the impact of the failure of the intelligent scheduling system model on the production target; Adaptability evaluation module: evaluates the adaptability of the intelligent scheduling system model to data distribution drift based on the degree of deviation between the production data distribution and the benchmark distribution in the current time period and the impact on the production target when the intelligent scheduling system model fails; Adaptability level division module: Based on the evaluation results, the adaptability of the intelligent scheduling system model to data distribution drift is divided into high adaptability level, medium adaptability level and low adaptability level. For the high adaptability level, the resource allocation strategy is further refined. For the low adaptability level, the failed decision is quickly responded and repaired to reduce the impact on production. Optimization module: For the medium adaptability level, the abnormal degree of the intelligent scheduling system model's adaptability to data distribution drift within a fixed time period is predicted. If the abnormal degree is high, the intelligent scheduling system model is continuously optimized to improve the accuracy of scheduling decisions.

[0015] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. The present invention can timely identify the adaptability problems of the intelligent scheduling system in the production environment by real-time monitoring and analyzing the deviation of production data and data distribution drift. Adaptability prediction is performed based on the KL divergence calculation between the baseline distribution and the current data distribution, coupling degree anomaly analysis, and comprehensive feature vector input machine learning model, so that the scheduling system can dynamically adapt to data drift caused by factors such as equipment aging, production demand fluctuations, and process changes. By dividing adaptability into high, medium, and low levels and taking corresponding resource optimization and decision-making repair measures, the present invention can effectively improve the robustness of the scheduling system and ensure the smooth operation of the production line.

[0016] 2. The present invention aims at the medium adaptability level, predicts the degree of adaptability abnormality and optimizes it to continuously improve the accuracy of scheduling decisions. Through the monitoring and early warning mechanism of the adaptability abnormality value, it can send out optimization signals in time when the system adaptability decreases, and optimize by adjusting the model parameters, further improve production efficiency, avoid equipment overload, production line imbalance and other problems, thereby reducing the risk of production stagnation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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.

[0018] Figure 1 The present invention is a flow chart of the method.

[0019] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0020] 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.

[0021] Example 1, please refer to Figure 1 and Figure 2 As shown, the intelligent scheduling and tracking method described in this embodiment includes the following steps: S1: Set the ideal production state data in the production process as the target production data, and collect real-time production data in several time periods in the actual production process, compare the real-time production data with the target production data, and divide the real-time production data into production data that deviates from the target and production data that does not deviate from the target; S2: Analyze the distribution changes of the production data that deviates from the target in each time period, select the production data distribution in the initial time period of the intelligent scheduling system as the benchmark distribution, and determine the degree of deviation between the production data distribution in the current time period and the benchmark distribution; S3: If the degree of deviation is high, collect historical data of the scheduling prediction value of the intelligent scheduling system model and the actual equipment utilization rate, calculate the coupling degree after regression analysis, and analyze the abnormal changes of the coupling degree under different drift states to evaluate the impact of the intelligent scheduling system model failure on the production target; S4: Evaluate the adaptability of the intelligent scheduling system model to data distribution drift based on the degree of deviation between the production data distribution and the benchmark distribution in the current time period and the impact on the production target when the intelligent scheduling system model fails; S5: Based on the evaluation results, the adaptability of the intelligent scheduling system model to data distribution drift is divided into high adaptability level, medium adaptability level and low adaptability level. For the high adaptability level, the resource allocation strategy is further refined. For the low adaptability level, the failed decision is quickly responded and repaired to reduce the impact on production. S6: For the medium adaptability level, the abnormal degree of the intelligent scheduling system model's adaptability to data distribution drift within a fixed time period is predicted. If the abnormal degree is high, the intelligent scheduling system model is continuously optimized to improve the accuracy of scheduling decisions.

[0022] In S1, the ideal production state data in the production process is set as the target production data, and the real-time production data in several time periods are collected in real time during the actual production process. The real-time production data is compared with the target production data, and the real-time production data is divided into the production data that deviates from the target and the production data that does not deviate from the target, specifically: Target production data is standard data defined based on ideal or optimal production status, including: Production rate (production line capacity): output per unit time in an ideal production process. Equipment status (utilization rate, failure rate, etc.): normal operating time, maintenance cycle, etc. of equipment when it is in an ideal working state. Worker efficiency (worker scheduling and production efficiency): work arrangements of workers under ideal conditions according to production needs. Resource utilization: reasonable allocation and use of resources such as raw materials, equipment, and energy. This part of data can be obtained through long-term production experience, historical data, or production simulation, reflecting the standardization requirements and expected efficient operation mode in the production process.

[0023] Actual production data is collected in real time through sensors, MES (manufacturing execution system) and other intelligent devices, mainly including: Equipment operation status: real-time load, operation time, fault alarm information, etc. Production data: actual production output, production rate, production quality, etc. Worker and operation status: worker operation efficiency, shift arrangement, working hours, etc. Resource usage data: consumption of various resources (such as raw materials, energy), inventory level, etc. These data are collected through the Industrial Internet of Things (IoT) system, real-time monitoring system or sensor network to form a full-process monitoring of the production process.

[0024] Once the actual production data is collected, it needs to be compared with the target production data. The main steps of the comparison include: Compare real-time data and target data within the same time window to ensure data synchronization. Usually, the production process can be divided into hours, shifts or other reasonable time periods. Remove noisy data or missing data and standardize the data to ensure that data from different sources are comparable.

[0025] The difference indicators (such as mean square error, percentage error, etc.) are used to calculate the deviation between the actual production data and the target production data. The expression is: ; Compare the deviations between different production indicators (such as output, equipment load, etc.) and evaluate the execution effect of various production activities.

[0026] If the deviation between the actual production data and the target production data exceeds the set allowable range (for example, the deviation is greater than a certain threshold), it is classified as deviating from the target production data. Otherwise, it is classified as not deviating from the target production data, indicating that the actual production status is relatively close to the target production status.

[0027] According to historical data, production experience and the fluctuation range of the production line, a reasonable tolerance range is set (for example, a deviation rate of more than 5% or 10% is considered to be a deviation from the target). This threshold can be dynamically adjusted according to the characteristics of different factories, different production lines and different production links.

[0028] The deviation between the actual production data and the target production data is compared with the deviation reference threshold under normal production conditions set according to historical data. If the deviation between the actual production data and the target production data is greater than the deviation reference threshold, it is classified as deviating from the target production data; if the deviation between the actual production data and the target production data is less than or equal to the deviation reference threshold, it is classified as not deviating from the target production data.

[0029] S2: Analyze the distribution changes of the production data that deviates from the target in each time period, select the production data distribution in the initial time period of the intelligent scheduling system as the benchmark distribution, and determine the degree of deviation between the production data distribution in the current time period and the benchmark distribution.

[0030] The benchmark distribution refers to the distribution of production data in the early stage of the intelligent scheduling system (usually the stage of stable operation of the system). The reason for choosing the data in the initial stage as the benchmark is that the production status at this time is often relatively stable and ideal, and the production process can maintain the best working state without external interference.

[0031] The benchmark distribution should include: Production volume in a time period: production volume in each time period (such as per hour, per shift), equipment utilization rate, etc. Equipment utilization rate: data such as equipment load, idle time, and fault conditions. Production process data: including process parameters related to production such as temperature, humidity, and machine speed. Worker operation status: worker efficiency, shift scheduling, task execution, etc.

[0032] In each time period, the intelligent scheduling system collects production data in real time and compares it with the benchmark distribution. At this time, the following analysis needs to be performed on the real-time production data: Histogram comparison: By generating a histogram of the actual production data and the benchmark production data, check whether the shape of the data distribution has changed. Mainly check whether there is a significant deviation in the central tendency, distribution width, kurtosis, etc. of the data.

[0033] Distribution fitting (such as Gaussian distribution, Poisson distribution, etc.): Perform statistical fitting on the data to determine whether the actual data distribution still conforms to the distribution model in the initial stage. Model fitting is performed through maximum likelihood estimation (MLE) or least squares method.

[0034] Distance metrics (such as KL divergence or JS divergence): By calculating the difference between the actual data distribution and the benchmark distribution, KL divergence (Kullback-Leibler Divergence) or JS divergence (Jensen-Shannon Divergence) is used to measure the similarity or difference of the distribution.

[0035] Sliding window method: Select a time window of a certain length (for example, 1 hour, 1 shift) as the analysis range of real-time data. As time goes by, the window will slide, gradually updating the distribution of real-time data for comparison with the benchmark distribution.

[0036] Fixed time period comparison: For certain specific time periods in the production process (such as peak production periods or equipment maintenance periods), compare the deviation of the data with the benchmark distribution.

[0037] The benchmark distribution deviation index is generated by analyzing the deviation degree between the production data distribution and the benchmark distribution in the current time period to determine the deviation degree between the production data distribution and the benchmark distribution in the current time period. The method for obtaining the benchmark distribution deviation index is as follows: Set the baseline distribution and current distribution: The baseline distribution P is the ideal production status data distribution, which is usually constructed based on historical data, previous production standards, target production status, etc. The current distribution Q is the production data distribution collected in real time during the current time period.

[0038] If the production data is continuous data, it needs to be discretized, usually by binning or selecting a suitable probability density function (PDF). Common discretization methods include: discretization into a probability distribution of a fixed interval (such as a histogram). Use probability density estimation methods (such as kernel density estimation KDE).

[0039] Calculate the KL divergence between the baseline distribution and the current time period distribution. The calculation formula is: ;in: is the KL divergence between the benchmark distribution and the current time period distribution; P(i) is the probability mass (or probability density) of the i-th class in the benchmark distribution P. Q(i) is the probability mass (or probability density) of the i-th class in the current distribution Q. The calculated KL divergence between the benchmark distribution and the current time period distribution is used as the benchmark distribution deviation index.

[0040] KL divergence is very sensitive to zero probability values. If there are zero values ​​in P(i) or Q(i), the result may tend to infinity. To avoid this, add a smoothing constant v to the distribution, that is: ; is the probability mass of the i-th class in the smoothed benchmark distribution P, is the probability mass of the i-th class in the current distribution Q after smoothing.

[0041] The larger the deviation index of the benchmark distribution, the greater the deviation between the production data distribution and the benchmark distribution in the current time period. This means that there is a significant difference between the data in the actual production process and the ideal production state, which may be due to factors such as changes in the production environment, changes in equipment status, or fluctuations in production demand. When the deviation is large, the intelligent scheduling system may fail to adapt to these changes, resulting in unreasonable resource allocation, reduced production efficiency, or increased risk of potential equipment failure. Therefore, the system needs to be adjusted and the scheduling strategy needs to be re-optimized to cope with changes in the current production environment.

[0042] On the contrary, the smaller the benchmark distribution deviation index is, the smaller the deviation between the production data distribution and the benchmark distribution in the current time period is. This shows that the actual production data is closer to the ideal target production state, and the intelligent scheduling system can better track and adapt to the current production environment, ensuring the rational allocation of resources and the smooth operation of production. Smaller deviations mean that the scheduling system maintains good adaptability in the face of changes in the production environment, and system decisions can effectively meet production needs, thereby improving production efficiency and reducing the risk of resource waste or equipment overload.

[0043] S3: If the degree of deviation is high, collect historical data of the intelligent scheduling system model scheduling prediction value and the actual equipment utilization rate, calculate the coupling degree after using regression analysis, and analyze the abnormal changes in the coupling degree under different drift states to evaluate the impact of the intelligent scheduling system model failure on the production target.

[0044] When the degree of deviation is high, there may be a large difference between the scheduling prediction of the intelligent scheduling system and the actual equipment utilization, indicating that the model has poor adaptability, leading to problems in resource allocation and production scheduling. Therefore, in order to deeply analyze and evaluate the impact of this deviation, the historical data of the scheduling prediction value and the actual equipment utilization of the intelligent scheduling system can be collected, and the regression analysis method can be used to quantify the relationship between them, and further evaluate the impact of system failure on production goals.

[0045] Scheduling prediction value: This is the equipment utilization and production schedule predicted by the intelligent scheduling system based on historical data and current production conditions. Actual equipment utilization: This is the equipment operating status data actually collected from the production line, including equipment working hours, load levels, etc. Through the accumulation of historical data, the predicted values ​​and actual values ​​in different time periods are collected.

[0046] Regression analysis models (such as linear regression, ridge regression, etc.) are used to establish the relationship between the scheduling prediction value and the actual equipment utilization. The goal is to estimate the deviation between the actual utilization and the predicted utilization through the regression model.

[0047] The basic form of a linear regression model is: ; Where: Y is the actual equipment utilization rate, X is the scheduling prediction value of the intelligent scheduling system, β0 is the intercept term, β1 is the regression coefficient, which indicates the strength of the relationship between the predicted value and the actual value, and ϵ is the error term, which indicates the deviation of the model.

[0048] Through regression analysis, the regression coefficient β1 and the model's fit can be calculated to quantify the degree of match between the predicted value and the actual equipment utilization.

[0049] The coupling degree reflects the strength of the relationship between the predicted value and the actual equipment utilization rate. In regression analysis, this coupling degree can be measured by calculating the correlation coefficient r, which is: ; In the formula, and are the predicted value and actual value at the i-th moment, respectively. and is the average of the predicted value and the actual value. The coupling degree r ranges from [−1,1]: It indicates that the predicted value is highly correlated with the actual value, and the system's scheduling model has good adaptability and small error. It means that there is no obvious relationship between the predicted value and the actual value, and the model is invalid or has poor adaptability. Indicates a high negative correlation between the predicted value and the actual value.

[0050] In actual applications, data distribution and production environment may change, resulting in changes in the relationship between the predicted value of the intelligent scheduling system and the actual equipment utilization rate. If the coupling degree fluctuates abnormally, it means that the adaptability and prediction accuracy of the system are affected, which may cause the production scheduling to fail. For example: Normal state: When the production environment does not change much, the coupling degree between the predicted value and the actual value is usually stable, reflecting the effectiveness of the scheduling system over the past period of time. Drift state: When the production environment changes (such as equipment aging, fluctuations in production demand, etc.), the coupling degree may decrease. If the coupling degree is significantly lower than the normal state, it means that the risk of model failure is increased and the system needs to be adjusted.

[0051] After analyzing the abnormal changes in coupling degree under different drift states, the coupling degree abnormality index is generated to evaluate the impact of the intelligent scheduling system model failure on the production target. The method for obtaining the coupling degree abnormality index is as follows: Historical coupling data (normal mode): represents the coupling data of the system when there is no abnormality and the system is running stably. This is usually a standard built based on past production data (such as equipment utilization, production efficiency, etc.). Current coupling data: is the coupling data collected in real time from the intelligent scheduling system during the current time period.

[0052] Construct historical coupling degree series respectively , and construct the coupling degree sequence ; First, construct an n×m distance matrix, where n and m are the lengths of the historical coupling sequence and the current coupling sequence respectively; at each element position (i, j), calculate the current time point and The distance between them is usually calculated using the Euclidean distance , the expression is: ; The cumulative distance matrix is ​​calculated through dynamic programming. Each element D(i,j) of the cumulative distance matrix represents the minimum cumulative distance from the starting point to the position (i,j). The calculation formula is: ; In the formula, Represents paths in three directions: vertical, horizontal, and diagonal. The minimum distance is accumulated by selecting the shortest path. The shortest path DTW distance is calculated. The DTW distance is the element D(n,m) in the lower right corner of the matrix, that is, the minimum cumulative distance from the historical data sequence to the current data sequence.

[0053] In order to make the DTW distance comparable between time series of different lengths, it is usually necessary to normalize the DTW distance. This can be done by dividing the minimum distance by the total length of the two sequences. To normalize, get a standardized DTW distance value , the expression is: ; The degree of abnormality is assessed by comparing the current DTW distance with the historical normal mode.

[0054] The normal mode DTW distance range is to calculate the mean and standard deviation of the DTW distances of multiple normal time periods through historical data, and set the mean DTW distance of the historical normal mode to , the standard deviation is ; According to the difference between the current DTW distance and the historical mean, the coupling abnormality index is calculated. The formula is: ; Where Gt is the coupling anomaly index.

[0055] The larger the coupling abnormality index is, the more significant the difference between the coupling degree of the current intelligent scheduling system and the historical normal mode is. This indicates that the system has a large abnormality in the current operating state, which may be due to scheduling decision failure, equipment overload or unreasonable resource allocation, resulting in a strong impact on the production target. In this case, production efficiency is significantly reduced, key tasks cannot be completed on time, and even production lines may stagnate, affecting overall production capacity and production progress.

[0056] The smaller the coupling abnormality index is or the closer it is to zero, the more similar the coupling degree of the current intelligent scheduling system is to the historical normal mode, and the system runs relatively smoothly. At this time, the scheduling system can effectively adapt to changes in the production environment, adjust decisions in a timely manner, and ensure smooth production. Therefore, the production target is less affected, the production line runs stably, resources are allocated reasonably, production capacity is not significantly affected, and overall production efficiency is high.

[0057] S4: Evaluate the adaptability of the intelligent scheduling system model to data distribution drift based on the degree of deviation between the production data distribution and the benchmark distribution in the current time period and the impact on the production target when the intelligent scheduling system model fails.

[0058] The benchmark distribution deviation index and coupling degree anomaly index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the adaptability value label of the intelligent scheduling system model to the data distribution drift as the prediction target, and takes minimizing the sum of the prediction errors of the adaptability value labels of all intelligent scheduling system models to the data distribution drift 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 adaptability value of the intelligent scheduling system model to the data distribution drift is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0059] The method for obtaining the adaptability value of the intelligent scheduling system model to data distribution drift is to obtain the corresponding function expression from the comprehensive feature vector training data of the trained machine learning model: ; In the formula, is the output function of the model, Hr is the benchmark distribution deviation index, Gt is the coupling anomaly index, It is the adaptability value of the intelligent scheduling system model to data distribution drift.

[0060] S5: Based on the evaluation results, the adaptability of the intelligent scheduling system model to data distribution drift is divided into high adaptability level, medium adaptability level and low adaptability level. For the high adaptability level, the resource allocation strategy is further refined. For the low adaptability level, the failed decision is quickly responded and repaired to reduce the impact on production. Compare the obtained adaptability value of the intelligent scheduling system model to the data distribution drift with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and compare the adaptability value of the intelligent scheduling system model to the data distribution drift with the first standard threshold and the second standard threshold respectively; If the adaptability value of the intelligent scheduling system model to data distribution drift is greater than the second standard threshold, it means that the intelligent scheduling system model has good adaptability to data distribution drift. At this time, a high adaptability signal is generated, and the adaptability of the intelligent scheduling system model to data distribution drift is classified as a high adaptability level; If the adaptability value of the intelligent scheduling system model to data distribution drift is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the adaptability of the intelligent scheduling system model to data distribution drift is average, and a medium adaptability signal is generated at this time, and the adaptability of the intelligent scheduling system model to data distribution drift is classified as a medium adaptability level; If the adaptability value of the intelligent scheduling system model to data distribution drift is less than the first standard threshold, it means that the intelligent scheduling system model has poor adaptability to data distribution drift. At this time, a low adaptability signal is generated, and the adaptability of the intelligent scheduling system model to data distribution drift is classified as a low adaptability level.

[0061] For the intelligent scheduling system model that is rated as high adaptability, it means that the system can effectively adapt to data distribution drift, has high prediction accuracy, and has strong adaptability to production environment and scheduling decisions. Therefore, the main goal of the system at this level is to further optimize and refine resource allocation to improve overall production efficiency. Specific strategies include: Based on real-time data, the scheduling sequence of production tasks can be further optimized. For example, the actual completion time of each task can be predicted through machine learning algorithms, and the task arrangement can be adjusted reasonably to reduce equipment idle time and waiting time. According to the load of the production line, the workload of the equipment can be dynamically adjusted to ensure that each equipment operates in the optimal state and avoid waste of resources.

[0062] Optimize the workers' shift schedule and assign work according to their skills and production task requirements to ensure that workers are in the most suitable positions. Through data analysis, predict changes in personnel demand, avoid personnel redundancy or shortage, and ensure smooth production.

[0063] Using data analysis and predictive maintenance technology, we can adjust the maintenance cycle according to the equipment usage and health status to avoid over-maintenance or under-maintenance and ensure that the equipment operates in the best condition. We can dynamically adjust the equipment maintenance time and production scheduling plan to reduce downtime and improve equipment utilization.

[0064] Accurately predict energy demand during the production process, optimize energy scheduling through smart grids and energy management systems, reduce unnecessary energy consumption, and improve energy efficiency.

[0065] For intelligent scheduling system models that are rated as low adaptability, it means that the system fails to adapt to changes in the production environment or data distribution drift in a timely manner, resulting in prediction failure and a large impact on production targets. Therefore, the main goal of the system at this level is to respond quickly and repair failed decisions to reduce the negative impact on production. Specific strategies include: The system must quickly identify the reasons for the current scheduling failure and adjust the scheduling plan based on real-time feedback. For example, if the system predicts that uneven equipment load causes some equipment to be overloaded while other equipment is idle, the equipment's operating schedule needs to be adjusted immediately to distribute the workload appropriately. For the scheduling of critical tasks, an emergency scheduling strategy is adopted to ensure that critical tasks can be completed first and avoid delays or stagnation.

[0066] Since low adaptability levels may be related to equipment aging or frequent failures, it is necessary to strengthen equipment health monitoring. By real-time monitoring of equipment operating data, such as vibration, temperature, pressure, etc., equipment abnormalities can be discovered and intervened in a timely manner. If equipment is found to be operating abnormally or about to fail, the equipment should be immediately arranged for maintenance to avoid more serious production line stoppages caused by the failure.

[0067] In the case of low adaptability, the system can be enhanced with automated fault detection and repair mechanisms. For example, use an automated system to remotely monitor equipment, and automatically switch to backup equipment or reschedule tasks if a fault or abnormal operation is detected. Enhance emergency response capabilities. When the system identifies a risk, it immediately adjusts the production process to avoid a single link failure causing the entire production line to stagnate.

[0068] When the adaptability of the system model is low, a simplified production strategy is temporarily adopted, such as reducing complex production scheduling decisions, reducing the flexibility requirements of the production process, and reducing the risks of the production line. Through manual intervention, the production manager can manually adjust the scheduling strategy when the model fails to ensure that production will not stagnate and key production tasks can be completed on time.

[0069] S6: For the medium adaptability level, the abnormal degree of the intelligent scheduling system model's adaptability to data distribution drift within a fixed time period is predicted. If the abnormal degree is high, the intelligent scheduling system model is continuously optimized to improve the accuracy of scheduling decisions.

[0070] For the medium adaptability level, that is, the adaptability value of the intelligent scheduling system model generated within a fixed time period to the data distribution drift is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the adaptability values ​​generated in the subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected, and the corresponding data set is established, and the standard deviation of the data set is calculated as the adaptability abnormality degree value.

[0071] The obtained adaptability abnormality degree value is compared with the abnormality degree value reference threshold value pre-set according to historical data. If the adaptability abnormality degree value is greater than or equal to the pre-set abnormality degree value reference threshold value, it means that the abnormality degree of adaptability of the intelligent scheduling system model to the data distribution drift within a fixed time period is high. At this time, a warning signal is generated, indicating that the adaptability of the scheduling system is poor and the decision-making accuracy is low. The intelligent scheduling system is optimized; if the adaptability abnormality degree value is less than the pre-set abnormality degree value reference threshold value, it means that the abnormality degree of adaptability of the intelligent scheduling system model to the data distribution drift within a fixed time period is low. At this time, no warning signal is generated and no additional processing is required.

[0072] The optimization goal is to reduce the abnormality value AE, thereby improving the adaptability of the system, collecting historical production data, equipment utilization data, and the results of scheduling decisions. Use machine learning algorithms such as regression models, support vector machines (SVM), and neural networks to train models to predict and adjust scheduling decisions. The goal of the optimization model is to minimize the prediction error and the degree of abnormality.

[0073] Set the scheduling decision of the current model through a function To express, the intelligent scheduling system optimizes the decision by adjusting the model parameters θ: ;in: is a scheduling decision based on the current model prediction, is the actual production output result, is the regularization parameter, balancing the weight between prediction error and anomaly degree, AE is the anomaly degree value, and s is the total number of samples, which refers to the number of samples in all training data.

[0074] According to the optimized objective function, the model parameters θ are adjusted, and the new parameters are used to predict the scheduling decision. The optimization process is updated based on the gradient descent method: ; where η is the learning rate, ∇θ is the gradient of the objective function with respect to the model parameters, is the model parameter used by the intelligent scheduling system in the tth iteration. It represents the set of all parameters used by the model to generate scheduling decisions in the current iteration. For the In the iteration, the new model parameters are optimized.

[0075] The optimization process is a continuous iterative process. After each update, the system will recalculate the abnormality AE and determine whether further optimization is needed. If the abnormality continues to be high, the system will further adjust the scheduling strategy and repeatedly optimize until the AE is reduced to an acceptable range.

[0076] When the optimization process is completed, the system will update the scheduling decision model and apply it to actual production. The optimized intelligent scheduling system can better adapt to the drift of data distribution and improve decision accuracy and production efficiency.

[0077] In this embodiment, first, the system sets the ideal production status data as the target, collects production data in real time for comparison, and identifies data that deviates from the target. Then, by analyzing the distribution changes of the deviation data and calculating the degree of deviation from the benchmark distribution, the model failure risk of the intelligent scheduling system under different drift states is evaluated. Based on these evaluations, the system divides the adaptability into three levels: high, medium, and low, and takes corresponding countermeasures according to the adaptability level: for high adaptability levels, further refine the resource allocation strategy; for low adaptability levels, quickly respond to and repair failed decisions to reduce production shocks; for medium adaptability levels, the system is optimized to improve the accuracy of scheduling decisions and ensure efficient and smooth operation of the production line.

[0078] Embodiment 2, an intelligent scheduling and tracking system described in this embodiment includes a data comparison module, a distribution detection module, a coupling degree analysis module, an adaptability evaluation module, an adaptability level division module and an optimization module: Data comparison module: Set the ideal production status data in the production process as the target production data, and collect real-time production data in several time periods in the actual production process, compare the real-time production data with the target production data, and divide the real-time production data into production data that deviates from the target and production data that does not deviate from the target; Distribution detection module: Analyzes the distribution changes of production data that deviates from the target in each time period, selects the production data distribution in the initial time period of the intelligent scheduling system as the benchmark distribution, and determines the degree of deviation between the production data distribution in the current time period and the benchmark distribution; Coupling degree analysis module: If the degree of deviation is high, the historical data of the scheduling prediction value and the actual equipment utilization rate of the intelligent scheduling system model are collected, and the coupling degree is calculated after regression analysis. The abnormal changes of the coupling degree under different drift states are analyzed to evaluate the impact of the failure of the intelligent scheduling system model on the production target; Adaptability evaluation module: evaluates the adaptability of the intelligent scheduling system model to data distribution drift based on the degree of deviation between the production data distribution and the benchmark distribution in the current time period and the impact on the production target when the intelligent scheduling system model fails; Adaptability level division module: Based on the evaluation results, the adaptability of the intelligent scheduling system model to data distribution drift is divided into high adaptability level, medium adaptability level and low adaptability level. For the high adaptability level, the resource allocation strategy is further refined. For the low adaptability level, the failed decision is quickly responded and repaired to reduce the impact on production. Optimization module: For the medium adaptability level, the abnormal degree of the intelligent scheduling system model's adaptability to data distribution drift within a fixed time period is predicted. If the abnormal degree is high, the intelligent scheduling system model is continuously optimized to improve the accuracy of scheduling decisions.

[0079] 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.

[0080] 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.

[0081] 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.

[0082] 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 intelligent scheduling and tracking method, characterized in that: The following steps are involved: S1: Set the ideal production state data in the production process as the target production data, and collect real-time production data in several time periods in the actual production process, compare the real-time production data with the target production data, and divide the real-time production data into production data that deviates from the target and production data that does not deviate from the target; S2: Analyze the distribution changes of the production data that deviates from the target in each time period, select the production data distribution in the initial time period of the intelligent scheduling system as the benchmark distribution, and determine the degree of deviation between the production data distribution in the current time period and the benchmark distribution; S3: If the degree of deviation is high, collect historical data of the scheduling prediction value of the intelligent scheduling system model and the actual equipment utilization rate, calculate the coupling degree after regression analysis, and analyze the abnormal changes of the coupling degree under different drift states to evaluate the impact of the intelligent scheduling system model failure on the production target; S4: Evaluate the adaptability of the intelligent scheduling system model to data distribution drift based on the degree of deviation between the production data distribution and the benchmark distribution in the current time period and the impact on the production target when the intelligent scheduling system model fails; S5: Based on the evaluation results, the adaptability of the intelligent scheduling system model to data distribution drift is divided into high adaptability level, medium adaptability level and low adaptability level. For the high adaptability level, the resource allocation strategy is further refined. For the low adaptability level, the failed decision is quickly responded and repaired to reduce the impact on production. S6: For the medium adaptability level, the abnormal degree of the intelligent scheduling system model's adaptability to data distribution drift within a fixed time period is predicted. If the abnormal degree is high, the intelligent scheduling system model is continuously optimized to improve the accuracy of scheduling decisions.

2. The intelligent scheduling and tracking method according to claim 1, characterized in that: In S1, the real-time data and the target data are compared in the same time window, and the deviation between the actual production data and the target production data is calculated. The expression is: ; Compare the deviation between the actual production data and the target production data with the deviation reference threshold under normal production conditions set according to historical data. If the deviation between the actual production data and the target production data is greater than the deviation reference threshold, it is classified as deviating from the target production data; If the deviation between the actual production data and the target production data is less than or equal to the deviation reference threshold, it is classified as not deviating from the target production data.

3. The intelligent scheduling and tracking method according to claim 1, characterized in that: In S2, the deviation degree between the production data distribution and the benchmark distribution in the current time period is analyzed to generate a benchmark distribution deviation index. The benchmark distribution deviation index is obtained as follows: Set the benchmark distribution and current distribution. The benchmark distribution P is the ideal production status data distribution, and the current distribution Q is the production data distribution collected in real time during the current time period. Calculate the KL divergence between the benchmark distribution and the current time period distribution. The calculation formula is: ;in: is the KL divergence between the benchmark distribution and the current time period distribution; P(i) is the probability mass of the i-th class in the benchmark distribution P; Q(i) is the probability mass of the i-th class in the current distribution Q; the calculated KL divergence between the benchmark distribution and the current time period distribution is used as the benchmark distribution deviation index.

4. The intelligent scheduling and tracking method according to claim 3, characterized in that: In S3, the coupling degree abnormality index is generated after analyzing the abnormal changes of the coupling degree under different drift states. The coupling degree abnormality index is obtained by: Construct historical coupling degree series respectively , and construct the coupling degree sequence ; First, construct an n×m distance matrix, where n and m are the lengths of the historical coupling sequence and the current coupling sequence respectively; at each element position (i, j), calculate the current time point and The distance between them, using the Euclidean distance , the expression is: ; The cumulative distance matrix is ​​calculated by dynamic programming. Each element D(i,j) of the cumulative distance matrix represents the minimum cumulative distance from the starting point to the position (i,j). The calculation formula is: ; In the formula, Represent paths in three directions: vertical, horizontal, and diagonal. By selecting the shortest path to accumulate the minimum distance, the shortest path DTW distance is calculated. The DTW distance is the element D(n,m) in the lower right corner of the matrix, that is, the minimum cumulative distance from the historical data sequence to the current data sequence. Normalize the DTW distance to get a standardized DTW distance value , the expression is: ; The normal mode DTW distance range is the mean and standard deviation of the DTW distances of multiple normal time periods calculated from historical data. The mean DTW distance of the historical normal mode is set to , the standard deviation is ; According to the difference between the current DTW distance and the historical mean, the coupling abnormality index is calculated. The formula is: ; Where Gt is the coupling anomaly index.

5. The intelligent scheduling and tracking method according to claim 4, characterized in that: In S4, the adaptability of the intelligent scheduling system model to data distribution drift is evaluated based on the degree of deviation between the production data distribution and the benchmark distribution in the current time period and the impact on the production target when the intelligent scheduling system model fails. Specifically: The benchmark distribution deviation index and coupling degree anomaly index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the adaptability value label of the intelligent scheduling system model to the data distribution drift as the prediction target, and takes minimizing the sum of the prediction errors of the adaptability value labels of all intelligent scheduling system models to the data distribution drift 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 adaptability value of the intelligent scheduling system model to the data distribution drift is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

6. The intelligent scheduling and tracking method according to claim 5, characterized in that: In S5, the adaptability of the intelligent scheduling system model to data distribution drift is divided into high adaptability level, medium adaptability level and low adaptability level, specifically: Compare the obtained adaptability value of the intelligent scheduling system model to the data distribution drift with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and compare the adaptability value of the intelligent scheduling system model to the data distribution drift with the first standard threshold and the second standard threshold respectively; If the adaptability value of the intelligent scheduling system model to data distribution drift is greater than the second standard threshold, it means that the intelligent scheduling system model has good adaptability to data distribution drift. At this time, a high adaptability signal is generated, and the adaptability of the intelligent scheduling system model to data distribution drift is classified as a high adaptability level; If the adaptability value of the intelligent scheduling system model to data distribution drift is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the adaptability of the intelligent scheduling system model to data distribution drift is average, and a medium adaptability signal is generated at this time, and the adaptability of the intelligent scheduling system model to data distribution drift is classified as a medium adaptability level; If the adaptability value of the intelligent scheduling system model to data distribution drift is less than the first standard threshold, it means that the intelligent scheduling system model has poor adaptability to data distribution drift. At this time, a low adaptability signal is generated, and the adaptability of the intelligent scheduling system model to data distribution drift is classified as a low adaptability level.

7. The intelligent scheduling and tracking method according to claim 1, characterized in that: In S6, for the medium adaptability level, the abnormal degree of adaptability of the intelligent scheduling system model to data distribution drift within a fixed time period is predicted, specifically: For the medium adaptability level, that is, the adaptability value of the intelligent scheduling system model generated within a fixed time period to the data distribution drift is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the adaptability values ​​generated within the subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected, and the corresponding data set is established, and the standard deviation of the data set is calculated as the adaptability abnormality degree value; The obtained adaptive abnormality degree value is compared with the abnormality degree value reference threshold value pre-set according to historical data. If the adaptive abnormality degree value is greater than or equal to the pre-set abnormality degree value reference threshold value, it means that the abnormality degree of adaptability of the intelligent scheduling system model to the data distribution drift within a fixed time period is high. At this time, an early warning signal is generated and the intelligent scheduling system is optimized; if the adaptive abnormality degree value is less than the pre-set abnormality degree value reference threshold value, it means that the abnormality degree of adaptability of the intelligent scheduling system model to the data distribution drift within a fixed time period is low. At this time, no early warning signal is generated and no additional processing is required.

8. The intelligent scheduling and tracking method according to claim 7, characterized in that: If the abnormality is high, the intelligent dispatching system model is continuously optimized to improve the accuracy of dispatching decisions, specifically: Set the scheduling decision of the current model through a function To express, the intelligent scheduling system optimizes the decision by adjusting the model parameters θ: ;in: is a scheduling decision based on the current model prediction, is the actual production output result, is the regularization parameter, AE is the abnormality value, and s is the total number of samples; According to the optimized objective function, the model parameters θ are adjusted, and the new parameters are used to predict the scheduling decision. The optimization process is updated based on the gradient descent method: ; where η is the learning rate, ∇θ is the gradient of the objective function with respect to the model parameters, is the model parameter used by the intelligent scheduling system for the tth iteration, For the In the iteration, the new model parameters are optimized.

9. An intelligent scheduling and tracking system, used to implement an intelligent scheduling and tracking method according to any one of claims 1 to 8, characterized in that: It includes data comparison module, distribution detection module, coupling analysis module, adaptability evaluation module, adaptability level division module and optimization module: Data comparison module: Set the ideal production status data in the production process as the target production data, and collect real-time production data in several time periods in the actual production process, compare the real-time production data with the target production data, and divide the real-time production data into production data that deviates from the target and production data that does not deviate from the target; Distribution detection module: Analyzes the distribution changes of production data that deviates from the target in each time period, selects the production data distribution in the initial time period of the intelligent scheduling system as the benchmark distribution, and determines the degree of deviation between the production data distribution in the current time period and the benchmark distribution; Coupling degree analysis module: If the degree of deviation is high, the historical data of the scheduling prediction value and the actual equipment utilization rate of the intelligent scheduling system model are collected, and the coupling degree is calculated after regression analysis. The abnormal changes of the coupling degree under different drift states are analyzed to evaluate the impact of the failure of the intelligent scheduling system model on the production target; Adaptability evaluation module: evaluates the adaptability of the intelligent scheduling system model to data distribution drift based on the degree of deviation between the production data distribution and the benchmark distribution in the current time period and the impact on the production target when the intelligent scheduling system model fails; Adaptability level division module: Based on the evaluation results, the adaptability of the intelligent scheduling system model to data distribution drift is divided into high adaptability level, medium adaptability level and low adaptability level. For the high adaptability level, the resource allocation strategy is further refined. For the low adaptability level, the failed decision is quickly responded and repaired to reduce the impact on production. Optimization module: For the medium adaptability level, the abnormal degree of the intelligent scheduling system model's adaptability to data distribution drift within a fixed time period is predicted. If the abnormal degree is high, the intelligent scheduling system model is continuously optimized to improve the accuracy of scheduling decisions.

Images