Production collaborative management method and system of digital factory

Abstract

The invention provides a production collaborative management method and system for a digital factory, and the method comprises the steps: calculating an affinity matrix between devices based on the physical positions, communication delays, device types and historical collaborative relationships of the devices, determining the collaborative weights of heterogeneous devices, and obtaining a device collaborative networking scheme; calculating a time sequence score according to the task completion quality, the energy consumption efficiency, the equipment stability and the collaborative adaptability of each equipment group, and performing dynamic weight adjustment in combination with environment monitoring data to obtain an equipment credit score; performing initial task allocation based on the equipment credit score, and performing continuous bias analysis and resource balancing by analyzing data in a task execution process to obtain a dynamic task allocation strategy; and finally, evaluating the collaborative effect of the equipment group according to the task allocation strategy, and dynamically optimizing the equipment group to obtain a collaborative evolution scheme. According to the method, the problem of unreasonable equipment resource allocation is effectively solved through a dynamic evaluation and balance mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a production collaborative management method and system for a digital factory. Background Art

[0002] In digital factories, production collaborative management is a key link to ensure production efficiency, and its core lies in how to reasonably allocate and schedule equipment resources. Existing digital factory production collaborative management methods mainly adopt task allocation strategies based on historical data, that is, the system will prioritize tasks to equipment with better historical performance based on the historical performance of the equipment. This method has shown certain advantages in the early stages of factory digital transformation and can ensure the basic requirements of production efficiency in the short term.

[0003] However, as the digital factory runs longer, this task allocation method based on historical data gradually reveals serious problems. As the equipment with better performance continues to obtain more task opportunities, its performance data will continue to accumulate and optimize, while the equipment with average performance lacks opportunities for practice and improvement due to fewer task allocations. This situation leads to the typical "Matthew effect" in the allocation of equipment resources, that is, the strong get stronger and the weak get weaker. What's more serious is that this imbalance in resource allocation will continue to intensify over time, eventually causing some equipment to be in an "optimization blind spot" and unable to participate in efficient production collaboration, affecting the production efficiency of the entire digital factory. This problem is particularly prominent in complex digital factory environments with multiple regions and multiple types of equipment. Summary of the invention

[0004] The main purpose of the present invention is to solve the technical problem that in the existing digital factory production collaborative management method, task allocation based on historical performance data easily leads to unreasonable resource allocation; A first aspect of the present invention provides a production collaborative management method for a digital factory, the production collaborative management method for a digital factory comprising: The affinity matrix between devices is calculated according to the physical location, communication delay, device type and historical collaboration relationship of the devices in each area of ​​the digital factory, and the collaboration weights of heterogeneous devices are determined based on the affinity matrix to obtain a device collaboration networking solution; Calculate the timing score of the device according to the task completion quality, energy consumption efficiency, device stability and collaborative adaptability of each device group in the device collaborative networking solution, and dynamically adjust the weight of the timing score based on the environmental monitoring data to obtain the device credit score; Initially assign tasks to devices according to the device credit score, and continuously analyze the bias of devices based on the task assignment data collected during task execution, balance device resources according to the analysis results, and obtain a dynamic task assignment strategy; According to the task allocation strategy, the synergistic effect of the equipment group's production efficiency, energy utilization and task completion quality is evaluated, and based on the evaluation results, the member composition and capability complementarity of the equipment group are dynamically optimized to obtain a collaborative evolution plan for the equipment group.

[0005] Optionally, in a first implementation of the first aspect of the present invention, the affinity matrix between devices is calculated according to the physical location, communication delay, device type and historical collaboration relationship of devices in each area of ​​the digital factory, and the collaboration weights of heterogeneous devices are determined based on the affinity matrix to obtain the device collaborative networking solution, including: Perform Euclidean distance calculation on the physical location data of the device to obtain the location distance matrix, and perform sampling calculation on the round-trip delay of the communication data packets between devices to obtain the communication delay matrix; The compatibility of communication protocols of different types of devices is calculated to obtain the device type affinity matrix, and the historical collaboration data of devices is processed by time decay function to obtain the collaboration intensity matrix; Perform multi-dimensional weighted fusion calculation according to the location distance matrix, communication delay matrix, device type affinity matrix and collaboration strength matrix to obtain an affinity matrix between devices; The communication efficiency between the heterogeneous device pairs in the affinity matrix is ​​evaluated to obtain an initial coordination weight, and the initial coordination weight is dynamically adjusted according to the coordination success rate of the heterogeneous device pairs under different working conditions to obtain the coordination weight between the heterogeneous devices; The devices are grouped and divided based on the collaboration weights to obtain a device collaborative networking solution.

[0006] Optionally, in a second implementation of the first aspect of the present invention, the timing score of the device is calculated according to the task completion quality, energy consumption efficiency, device stability and collaborative adaptability of each device group in the device collaborative networking solution, and the timing score is dynamically weighted based on the environmental monitoring data to obtain the device credit score, which includes: Performing least square fitting calculation on the task position accuracy deviation, task completion time deviation and task execution parameter deviation of each device group in the device collaborative networking solution to obtain a quality assessment matrix, performing piecewise linear regression calculation on the quality assessment matrix to obtain task quality time series data; Perform wavelet decomposition calculation on the equipment current fluctuation data, voltage fluctuation data and power factor data of each equipment group in the equipment collaborative networking solution to obtain an energy consumption characteristic sequence, perform cross-correlation calculation on the energy consumption characteristic sequence and the standard energy consumption model to obtain energy efficiency time series data; Performing empirical mode decomposition calculation on the equipment vibration spectrum data, temperature change data and motor speed fluctuation data of each equipment group in the equipment collaborative networking solution to obtain a state eigenvector, performing principal component analysis calculation on the state eigenvector to obtain stability time series data; Performing Markov chain transfer probability calculation on the task quality time series data, energy efficiency time series data, and stability time series data to obtain a time series score; The principal component analysis is performed on the regional temperature field gradient data, humidity distribution data and electromagnetic interference intensity distribution data in the environmental monitoring data to obtain the environmental feature vector, and the neural network weight calculation is performed on the environmental feature vector and the time series score to obtain the equipment credit score.

[0007] Optionally, in a third implementation of the first aspect of the present invention, performing Markov chain transition probability calculation on the task quality time series data, the energy efficiency time series data, and the stability time series data to obtain a time series score includes: Perform time series segmentation calculation on the task quality time series data to obtain a quality state sequence, perform frequency statistics on adjacent states in the quality state sequence to obtain a first-order transfer frequency matrix; Normalizing the energy efficiency time series data and the stability time series data to obtain a standardized data sequence, and performing state quantization calculation on the standardized data sequence to obtain an energy efficiency state sequence and a stability state sequence; Performing transfer probability calculation on the quality state sequence, energy efficiency state sequence and stability state sequence to obtain a Markov transfer probability matrix, and performing stationary distribution calculation on the Markov transfer probability matrix to obtain a state probability vector; n-step transition probability calculation is performed according to the state probability vector and the Markov transition probability matrix to obtain a time series score.

[0008] Optionally, in a fourth implementation of the first aspect of the present invention, performing initial task allocation to the device according to the device credit score, performing continuous bias analysis on the device based on the task allocation data collected during task execution, and balancing device resources according to the analysis results to obtain a dynamic task allocation strategy includes: Calculating the sample standard deviation of the equipment credit score to obtain score dispersion data, calculating the probability density distribution of the score dispersion data to obtain an initial task allocation probability matrix, and performing initial task allocation according to the initial task allocation probability matrix; Performing time series acquisition and sliding time window calculation on the task allocation data after the initial task allocation to obtain a task allocation time series matrix; Performing K-means clustering calculation on the task allocation timing matrix to obtain a device task density distribution map, calculating the skewness coefficient on the device task density distribution map, grouping and marking devices whose skewness coefficient exceeds a threshold, and obtaining an optimized blind spot device group; Performing principal component analysis calculation on the task execution data of the blind spot optimization equipment group to obtain a task feature matrix, and performing hierarchical clustering calculation on the task feature matrix to obtain task difficulty level data; The initial task allocation probability matrix is ​​subjected to Bayesian update calculation according to the task difficulty level data to obtain a dynamic task allocation strategy.

[0009] Optionally, in a fifth implementation of the first aspect of the present invention, performing K-means clustering calculation on the task allocation timing matrix to obtain a device task density distribution map, performing skewness coefficient calculation on the device task density distribution map, grouping and marking devices whose skewness coefficient exceeds a threshold, and obtaining an optimized blind spot device group includes: Performing Gaussian kernel density estimation calculation on each sampling point of the task allocation timing matrix to obtain a device task distribution probability map, and performing gradient descent clustering calculation on the device task distribution probability map to obtain a task density clustering center; Performing Euclidean distance calculation on the task density cluster centers to obtain a cluster distance matrix, and performing K-means iterative calculation based on the cluster distance matrix to obtain a device task density distribution map; Performing probability moment estimation calculation on the equipment task density distribution diagram to obtain a distribution matrix, and performing third-order moment calculation on the distribution matrix to obtain a skewness coefficient; A dynamic threshold value is calculated for the device according to the skewness coefficient to obtain a grouping threshold value, the grouping threshold value is compared with the skewness coefficient, and the devices whose skewness coefficient exceeds the grouping threshold value are grouped and marked to obtain an optimized blind spot device group.

[0010] Optionally, in a sixth implementation of the first aspect of the present invention, the collaborative effect evaluation of the production efficiency, energy utilization rate and task completion quality of the equipment group is performed according to the task allocation strategy, and the member composition and capability complementarity of the equipment group are dynamically optimized based on the evaluation result to obtain the collaborative evolution plan of the equipment group, including: Performing time series collection on the equipment group task throughput data, equipment group task response time data and equipment group task accuracy data during the execution of the task allocation strategy to obtain equipment group production efficiency evaluation data; Performing weighted calculation on the equipment group energy consumption data, equipment group standby time data and equipment group peak power data during the execution of the task allocation strategy to obtain equipment group energy utilization rate evaluation data; Performing hierarchical analysis calculation on the equipment group according to the production efficiency evaluation data and the energy utilization rate evaluation data to obtain an equipment group performance evaluation matrix, and performing eigenvalue decomposition calculation on the equipment group performance evaluation matrix to obtain an equipment group capability eigenvector; An optimal matching calculation is performed on the device group members according to the device group capability feature vector to obtain a device group member reorganization plan, and a prediction calculation is performed on the device group coordination efficiency in the device group member reorganization plan to obtain a coordinated evolution plan of the device group.

[0011] A second aspect of the present invention provides a production collaborative management system for a digital factory, the production collaborative management system for a digital factory comprising: The networking module is used to calculate the affinity matrix between devices according to the physical location, communication delay, device type and historical collaboration relationship of the devices in each area of ​​the digital factory, and determine the collaboration weights of heterogeneous devices based on the affinity matrix to obtain a device collaboration networking solution; A scoring module, used to calculate the timing score of the device according to the task completion quality, energy consumption efficiency, device stability and collaborative adaptability of each device group in the device collaborative networking solution, and dynamically adjust the weight of the timing score based on the environmental monitoring data to obtain the device credit score; A scheduling module, used to perform initial task allocation to the device according to the device credit score, and perform continuous bias analysis on the device based on the task allocation data collected during the task execution process, balance the device resources according to the analysis results, and obtain a dynamic task allocation strategy; The optimization module is used to evaluate the synergistic effect of the production efficiency, energy utilization and task completion quality of the equipment group according to the task allocation strategy, and dynamically optimize the member composition and capability complementarity of the equipment group based on the evaluation results to obtain a collaborative evolution plan for the equipment group.

[0012] The above-mentioned production collaborative management method and system of the digital factory calculates the affinity matrix between devices based on the physical location, communication delay, device type and historical collaborative relationship of the devices, and determines the collaborative weight of heterogeneous devices to obtain a collaborative networking solution for the devices; then, the timing score is calculated according to the task completion quality, energy consumption efficiency, device stability and collaborative adaptability of each device group, and the weight is dynamically adjusted in combination with environmental monitoring data to obtain the device credit score; then, the initial task allocation is performed based on the device credit score, and continuous bias analysis and resource balancing are performed by analyzing the data during the task execution process to obtain a dynamic task allocation strategy; finally, the collaborative effect of the device group is evaluated according to the task allocation strategy, and the device group is dynamically optimized to obtain a collaborative evolution solution. The present invention effectively solves the problem of unreasonable equipment resource allocation through dynamic evaluation and balancing mechanisms.

[0013] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0014] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a schematic diagram of a first embodiment of a production collaborative management method for a digital factory according to an embodiment of the present invention; Figure 2 It is a schematic diagram of an embodiment of a production collaborative management system of a digital factory in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. 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.

[0017] The terms "including" and "having" and any variations thereof mentioned in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device end including a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or device ends.

[0018] To facilitate understanding of this embodiment, a production collaborative management method for a digital factory disclosed in an embodiment of the present invention is first described in detail. Figure 1 As shown, the method comprises the following steps: 101. Calculate the affinity matrix between devices according to the physical location, communication delay, device type and historical collaboration relationship of the devices in each area of ​​the digital factory, and determine the collaboration weights of heterogeneous devices based on the affinity matrix to obtain a collaborative networking solution for the devices; In one embodiment of the present invention, the affinity matrix between devices is calculated according to the physical location, communication delay, device type and historical collaboration relationship of the devices in each area of ​​the digital factory, and the collaboration weights of heterogeneous devices are determined based on the affinity matrix to obtain a collaborative networking solution for the devices, including: performing Euclidean distance calculation on the physical location data of the devices to obtain a location distance matrix, and performing sampling calculation on the round-trip delay of communication data packets between devices to obtain a communication delay matrix; performing matching degree calculation on the communication protocol compatibility of different types of devices to obtain a device type affinity matrix, and performing time decay function processing on the historical collaboration data of the devices to obtain a collaboration intensity matrix; performing multi-dimensional weighted fusion calculation based on the location distance matrix, communication delay matrix, device type affinity matrix and collaboration intensity matrix to obtain an affinity matrix between devices; evaluating the communication efficiency between heterogeneous device pairs in the affinity matrix to obtain an initial collaboration weight, and dynamically adjusting the initial collaboration weight based on the collaboration success rate of heterogeneous device pairs under different working conditions to obtain a collaboration weight between heterogeneous devices; and grouping and dividing the devices based on the collaboration weight to obtain a collaborative networking solution for the devices.

[0019] Specifically, in the actual operation environment of the digital factory, it is first necessary to obtain the physical coordinate data of each device from the device management system. These data usually exist in the form of X, Y, and Z three-dimensional coordinates, which accurately reflect the specific location of the device in the three-dimensional space of the factory. For these location data, the system uses the spatial rectangular coordinate system calculation method to calculate the actual distance between each pair of devices, thereby constructing a position distance matrix that reflects the spatial relationship between devices. At the same time, the system also needs to evaluate the communication performance between devices. This process is completed by cyclically sending detection data packets between devices. Specifically, the system will collect the round-trip transmission time of data packets in different time periods, such as production peak period and production stable period. The number of samples in each time period is not less than 1000 times, and the sampling interval is 100 milliseconds. For the collected delay data, the system will remove outliers and calculate the average value, and finally obtain the communication delay matrix that characterizes the communication performance between devices. For example, between two brands of AGV devices deployed in a digital factory, the system will record their delays when transmitting different types of data packets such as task instructions, status information, and sensor data. These data fully record the communication performance characteristics between devices. By establishing the location distance matrix and the communication delay matrix, the system obtains the basic data of the physical distribution and communication performance between devices.

[0020] Specifically, in the digital factory environment, different types of equipment often use different communication protocols, such as OPC UA, Modbus, Profinet, etc. The system needs to conduct in-depth analysis of these protocols, including the data encapsulation format, transmission mechanism, security policy, error handling mechanism and other aspects of the protocol. By establishing the protocol feature vector, the system can calculate the degree of matching between different protocols. For example, when two devices both support the OPC UA protocol, their protocol matching will be assigned a higher value, while when one device uses OPC UA and the other uses Modbus, the system will give a relatively low matching value according to the complexity of the protocol conversion. These matching values ​​ultimately constitute the device type affinity matrix. At the same time, the system will extract the collaboration records of the equipment from the production history database, which contain information such as collaboration time, collaboration type, and collaboration results. By designing a time decay function, the system processes these historical collaboration data, and the newer collaboration records obtain a larger weight value, while the older collaboration records obtain a smaller weight value. This processing method reflects the timeliness of the collaboration relationship between devices, and the resulting collaboration intensity matrix can accurately characterize the actual collaboration capabilities between devices. In practical applications, the time decay function adopts an exponential decay form, which ensures that the impact intensity of historical data gradually decreases over time.

[0021] Specifically, after obtaining the four basic matrices that reflect the different characteristics of the equipment, the system needs to fuse these matrices in multiple dimensions to obtain a comprehensive affinity matrix. This fusion process first requires standardization of each matrix to make the data of different dimensions comparable. The standardized matrix is ​​multiplied by its corresponding weight coefficient, which reflects the importance of each dimension in the equipment collaboration process. For example, in some scenarios, communication performance may be more important than physical distance, so the weight coefficient of the communication delay matrix will be increased accordingly. The weighted results of multiple matrices are linearly combined to obtain the final affinity matrix, in which each element quantitatively represents the comprehensive affinity between the corresponding equipment pairs. In order to ensure the reliability of the calculation results, the system will perform outlier detection and data cleaning on the raw data of each dimension, and consider the confidence of the data during the fusion process. At the same time, in order to cope with the dynamic changes in the factory environment, these weight coefficients are not fixed, but will be dynamically adjusted according to the actual production situation, so as to ensure that the affinity matrix can truly reflect the current equipment collaboration status. This process adopts a multi-dimensional weighted fusion algorithm, which comprehensively considers the influence of multiple factors such as location distance, communication delay, protocol compatibility and historical collaboration.

[0022] Specifically, in digital factories, heterogeneous devices mainly refer to AGV devices of different brands and models. Although these devices have the basic functions of automatic navigation and task execution, they have significant differences in control systems, communication protocols, and performance characteristics due to different manufacturers. The communication efficiency of these heterogeneous devices is specially evaluated because data exchange between devices of different brands often requires protocol conversion or data format conversion, which will bring additional communication overhead and potential compatibility issues. The system collects data on data transmission rate, data packet integrity, protocol conversion time, and other indicators between heterogeneous devices to build a quantitative communication efficiency evaluation system, thereby calculating the initial collaborative weight. In the actual production process, heterogeneous devices will face a variety of working conditions, such as regular task delivery under normal working conditions, intensive scheduling under high-load working conditions, and emergency avoidance under interference working conditions. The system will continuously collect and statistically analyze the collaboration of heterogeneous devices under these different working conditions, including data such as task completion rate, collaborative response time, and error handling capability. These statistical data are used to calculate the collaboration success rate of heterogeneous devices under various working conditions, and the initial collaborative weight is corrected accordingly. Through this dynamic adjustment mechanism, the final collaborative weight can accurately reflect the collaborative capabilities of heterogeneous devices in actual production environments.

[0023] Specifically, after obtaining the collaborative weights between heterogeneous devices, the system starts to execute the device grouping process. First, a device relationship graph is constructed based on the collaborative weights, in which the nodes represent the devices and the weights of the edges represent the strength of the collaborative relationship between the devices. Through the community discovery algorithm of the graph, the system can identify closely collaborative groups between devices. In the grouping process, the system will prioritize the devices with higher collaborative weights to the same group, while considering the balance of the number of devices in the group. In addition, the system also needs to evaluate the impact of the grouping scheme on the overall communication load and minimize the communication requirements between groups. The final device collaborative networking scheme not only clarifies the member composition of each device group, but also defines the collaborative relationship between groups. The scheme includes the communication routing strategy, load balancing strategy and failover mechanism of each device group, which are comprehensively formulated based on various types of data obtained in the early stage. In actual applications, the system uses a graph partitioning algorithm to achieve device grouping. The algorithm can maintain the scale balance of each device group while ensuring high collaboration, forming the final device collaborative networking scheme.

[0024] 102. Calculate the timing score of the equipment according to the task completion quality, energy consumption efficiency, equipment stability and collaborative adaptability of each equipment group in the equipment collaborative networking solution, and dynamically adjust the timing score based on the environmental monitoring data to obtain the equipment credit score; In one embodiment of the present invention, the device timing score is calculated according to the task completion quality, energy consumption efficiency, device stability and collaborative adaptability of each device group in the device collaborative networking scheme, and the timing score is dynamically weighted adjusted based on environmental monitoring data to obtain the device credit score, including: performing least squares fitting calculation on the task position accuracy deviation, task completion time deviation and task execution parameter deviation of each device group in the device collaborative networking scheme to obtain a quality evaluation matrix, performing piecewise linear regression calculation on the quality evaluation matrix to obtain task quality timing data; performing wavelet decomposition calculation on the device current fluctuation data, voltage fluctuation data and power factor data of each device group in the device collaborative networking scheme to obtain an energy consumption characteristic sequence, and performing a least squares fitting calculation on the quality evaluation matrix to obtain a quality evaluation matrix, and performing a piecewise linear regression calculation on the quality evaluation matrix to obtain task quality timing data. The energy consumption characteristic sequence is cross-correlated with the standard energy consumption model to obtain energy efficiency time series data; the equipment vibration spectrum data, temperature change data and motor speed fluctuation data of each equipment group in the equipment collaborative networking solution are subjected to empirical mode decomposition calculation to obtain state characteristic vectors, and the state characteristic vectors are subjected to principal component analysis calculation to obtain stability time series data; the task quality time series data, energy efficiency time series data and stability time series data are subjected to Markov chain transfer probability calculation to obtain a time series score; the regional temperature field gradient data, humidity distribution data and electromagnetic interference intensity distribution data in the environmental monitoring data are subjected to principal component analysis calculation to obtain an environmental characteristic vector, and the environmental characteristic vector and the time series score are subjected to neural network weight calculation to obtain an equipment credit score.

[0025] Specifically, after the equipment collaborative networking scheme is formed, it is necessary to analyze the task execution of the equipment in each equipment group. First, the task position accuracy deviation data is collected, that is, the error between the actual docking position and the preset position of the AGV when performing the handling task. These error data include X-axis deviation, Y-axis deviation and angle deviation. At the same time, the task completion time deviation is recorded, including time parameters such as task start delay, path execution time difference and task end confirmation delay. In addition, it is necessary to collect task execution parameter deviations, such as motion parameters such as speed fluctuation, acceleration change and steering compensation of the AGV during task execution. For these multi-dimensional deviation data, the system uses the least squares fitting method to calculate, and by constructing a group of error equations and solving the optimal fitting curve, a quality evaluation matrix reflecting the task execution capability of the equipment is obtained. Then, the quality evaluation matrix is ​​divided into multiple intervals according to the time series, and linear regression analysis is performed in each interval to obtain segmented linear fitting results. This segmented processing method takes into account the nonlinear change characteristics of equipment performance over time, and the task quality time series data finally generated contains the performance change trend of the equipment in different time periods.

[0026] Specifically, the analysis of the energy consumption of the equipment starts with three key electrical parameters: the current fluctuation data reflects the energy consumption changes of the equipment under different load conditions, by collecting the real-time value of the current and recording its fluctuation range; the voltage fluctuation data characterizes the power supply quality and the stability of the equipment's power consumption, and it is necessary to monitor the instantaneous value and effective value of the voltage; the power factor data reflects the energy utilization efficiency of the equipment, which is obtained by measuring the ratio of active power to apparent power. These raw data often contain multiple frequency components. The system uses the wavelet decomposition method to perform multi-scale analysis on them and decompose the signal into sub-signals of different frequency bands. By selecting the appropriate wavelet basis function and the number of decomposition layers, the system can extract the most representative energy consumption characteristics. These feature sequences are cross-correlated with the pre-established standard energy consumption model, which is constructed based on the typical energy consumption data of the equipment under normal operation. By calculating the cross-correlation coefficient between the feature sequence and the standard model, the energy efficiency time series data reflecting the current energy efficiency of the equipment are obtained. These data clearly record the change process of the energy consumption level of the equipment over time.

[0027] Specifically, the stability assessment of the equipment requires the analysis of a variety of mechanical and thermal parameters. The system first collects the vibration spectrum data of the equipment. These data come from vibration sensors installed at key parts of the AGV, and contain the vibration amplitude and frequency information of the equipment during operation. At the same time, the temperature change data of the equipment is monitored, and the temperature changes of core components such as motors, batteries, and controllers are recorded through temperature sensors. In addition, the motor speed fluctuation data needs to be collected, which reflects the operating stability of the AGV drive system. For these multi-source heterogeneous monitoring data, the system uses the empirical mode decomposition method to process. This method can adaptively decompose complex nonlinear and non-stationary signals into a series of intrinsic mode functions, each of which represents a characteristic component in the original signal. By analyzing these mode functions, the characteristic vector reflecting the operating status of the equipment is obtained. Then, these high-dimensional characteristic vectors are subjected to principal component analysis to extract the most representative feature combination, and finally generate stability time series data reflecting the stability of the equipment operation.

[0028] Specifically, after the system collects three sets of time series data that characterize different aspects of the equipment's performance, it needs to establish a dynamic association between these data through Markov chain transition probability analysis. First, each set of time series data is divided into several state intervals according to its numerical range, and each interval represents a performance level. Then, the frequency of state transitions between adjacent moments is statistically analyzed to construct a state transition frequency matrix. By normalizing the transition frequencies, the transition probability matrix between states is obtained. This probability matrix describes the evolution law of the equipment's performance state, and each element in it represents the probability of the equipment changing from one performance state to another. Based on the transition probability matrix, the system predicts the future performance state of the equipment, and uses the degree of fit between the prediction results and the actual observed values ​​as the basis for calculating the time series score. This Markov chain-based scoring method takes into account the dynamic change characteristics of equipment performance.

[0029] Specifically, environmental factors have a significant impact on the operating status of the equipment, and comprehensive monitoring of the workshop environmental parameters is required. The environmental monitoring network deployed by the system collects regional temperature field gradient data, which reflects the temperature distribution in different areas of the workshop; at the same time, it monitors humidity distribution data and records the spatial distribution characteristics of air humidity; it also collects electromagnetic interference intensity distribution data, which comes from the electromagnetic field intensity measurement points in the workshop. These environmental monitoring data usually have a high dimension and need to be reduced in dimension through principal component analysis. The system extracts the main features of these data and constructs an environmental feature vector, which comprehensively reflects the overall condition of the workshop environment. The environmental feature vector and the previously obtained time series score are input into a pre-trained neural network model, which can learn the influence of environmental factors on equipment performance. The final equipment credit score is obtained through the calculation of the neural network. This score comprehensively considers the two factors of the equipment's own performance and environmental impact.

[0030] Furthermore, the Markov chain transfer probability calculation of the task quality time series data, energy efficiency time series data and stability time series data to obtain a time series score includes: performing time series segmentation calculation on the task quality time series data to obtain a quality state sequence, performing frequency statistics on adjacent states in the quality state sequence to obtain a first-order transfer frequency matrix; normalizing the energy efficiency time series data and the stability time series data to obtain a standardized data sequence, performing state quantization calculation on the standardized data sequence to obtain an energy efficiency state sequence and a stability state sequence; performing transfer probability calculation on the quality state sequence, energy efficiency state sequence and stability state sequence to obtain a Markov transfer probability matrix, performing stationary distribution calculation on the Markov transfer probability matrix to obtain a state probability vector; performing n-step transfer probability calculation based on the state probability vector and the Markov transfer probability matrix to obtain a time series score.

[0031] Specifically, when processing the task quality time series data, the data sequence is first divided into several time periods according to the time window, and the length of each time period is set to 30 minutes. In each time period, the system counts the mean and standard deviation of the task position accuracy deviation, completion time deviation, and execution parameter deviation, and uses these statistical values ​​as the state characteristics of the time period. According to the distribution of these characteristic values, the state space is divided into multiple discrete state intervals, for example, the task execution quality is divided into four levels: "excellent", "good", "general", and "poor". By mapping the characteristic values ​​of each time period to the corresponding state interval, a state sequence reflecting the change of task quality is obtained. For this state sequence, the system calculates the number of transitions between adjacent time states, records the frequency of transitions from one state to another, and finally constructs a first-order transition frequency matrix. The rows and columns of the matrix correspond to each state in the state space, and the matrix elements record the number of transitions between corresponding state pairs.

[0032] Specifically, the energy efficiency time series data and stability time series data contain indicators of different dimensions and numerical ranges, and data standardization is required to make them comparable. For energy efficiency time series data, the system uses the maximum and minimum value standardization method to map the data to the [0,1] interval; for stability time series data, the Z-score standardization method is used to make the data obey the standard normal distribution. The standardized data sequence maintains the change trend of the original data while eliminating the influence of dimensions and scales. Then, the system quantifies the state of the standardized data sequence and uses the K-means clustering method to divide the continuous values ​​into discrete states. During clustering, the energy efficiency data is divided into three states: "high efficiency", "normal", and "low efficiency", and the stability data is divided into three states: "stable", "fluctuation", and "abnormal". Through this quantification process, the system obtains energy efficiency state sequences and stability state sequences, which describe the operating conditions of the equipment at different times with discrete state values.

[0033] Specifically, the system combines the quality state sequence, energy efficiency state sequence and stability state sequence into a multidimensional state space, and calculates the state transition probability on this basis. First, the transition frequency between each state combination in the multidimensional state space is counted, and then the transition frequency of each state is normalized to obtain the Markov transition probability matrix. This matrix describes the probability distribution of the system transitioning from the current state to the next state, where the sum of the elements in each row of the matrix is ​​1, indicating the sum of the probabilities of transitioning from a certain state to all possible states. This transition probability matrix is ​​subjected to eigenvalue decomposition and iterative calculation. When the state distribution tends to be stable, the resulting probability distribution is the stationary distribution of the Markov chain. This stationary distribution represents the frequency of occurrence of each state of the system in the long-term evolution process in the form of a probability vector, reflecting the long-term performance of the equipment performance state.

[0034] Specifically, after obtaining the state probability vector and the Markov transition probability matrix, the system needs to predict the performance state distribution of the device in the next n time steps. By performing n-time power operations on the Markov transition probability matrix, an n-step transition probability matrix is ​​obtained, which describes the probability of the system transferring from the current state to each target state after n time steps. Multiply the current state probability vector by the n-step transition probability matrix to obtain the state probability distribution after n steps. The system compares this probability distribution with the preset performance standards, calculates the weighted average according to the weight coefficients of each state, and finally obtains a time series score that reflects the expected level of device performance. This score comprehensively considers the historical performance and future trends of the equipment in the three dimensions of quality, energy efficiency and stability, and provides a quantitative basis for equipment performance evaluation.

[0035] 103. Perform initial task allocation to devices based on device credit scores, and perform continuous bias analysis on devices based on task allocation data collected during task execution. Balance device resources based on the analysis results to obtain a dynamic task allocation strategy. In one embodiment of the present invention, the initial task allocation to the device according to the device credit score, and the continuous bias analysis of the device based on the task allocation data collected during the task execution process, and the device resource balancing according to the analysis results to obtain a dynamic task allocation strategy include: calculating the sample standard deviation of the device credit score to obtain score dispersion data, performing probability density distribution calculation on the score dispersion data to obtain an initial task allocation probability matrix, and performing initial task allocation according to the initial task allocation probability matrix; performing time series collection and sliding time window calculation on the task allocation data after the initial task allocation to obtain a task allocation time series matrix; performing K-means clustering calculation on the task allocation time series matrix to obtain a device task density distribution map, performing skewness coefficient calculation on the device task density distribution map, grouping and marking the devices whose skewness coefficient exceeds the threshold to obtain an optimized dead-end device group; performing principal component analysis calculation on the task execution data of the optimized dead-end device group to obtain a task feature matrix, and performing hierarchical clustering calculation on the task feature matrix to obtain task difficulty level data; performing Bayesian update calculation on the initial task allocation probability matrix according to the task difficulty level data to obtain a dynamic task allocation strategy.

[0036] Specifically, when processing equipment credit scores, the system collects the score data of all equipment in the last 24 hours at a frequency of recording once every 10 minutes. The score at each time point includes the comprehensive performance of the equipment at that time, such as the task completion, energy efficiency and equipment status. Taking 10 AGV equipment in a factory as an example, the system will collect 144 score values ​​for each equipment within 24 hours. Then calculate the score standard deviation of each equipment. When calculating, first find the average of the 144 scores, then calculate the difference between each score and the average, square these differences and sum them, divide them by the number of samples and square them to get the standard deviation. In this way, 10 standard deviation values ​​are obtained, which constitute the score dispersion data. When calculating the probability density distribution of these dispersion data, the kernel density estimation method is used, and each data point is smoothed using the Gaussian kernel function. In the specific operation, a point is taken every 0.1 unit within the data range, and the sum of the contribution values ​​of all sample points at this point after the Gaussian kernel function is calculated to obtain the probability density of the point. The choice of bandwidth parameters is determined by calculating the standard deviation and interquartile range of the samples. A smaller bandwidth will obtain finer distribution details, while a larger bandwidth can reduce the impact of noise. Finally, the calculated probability density is combined with the historical completion of each device for different task types to establish the initial task assignment probability matrix. For example, if there are three types of handling tasks in the factory, the system will obtain a probability matrix with 10 rows and 3 columns. Each value in the matrix represents the probability of the corresponding device being assigned a specific type of task.

[0037] Specifically, after executing the initial task allocation, the system uses a distributed task monitoring network to collect task execution data in real time. Each AGV device is equipped with a task execution status recorder, which records the currently executed task information every 5 minutes, including task number, task type identification, task start timestamp, expected completion time, actual completion time, task execution quality indicators, etc. The collected data is transmitted to the central data processing server via industrial Ethernet. The server sets a 60-minute time window, which slides forward every 5 minutes to process the data in the window. In each time window, the system counts the distribution of task quantity, task type proportion, average execution time, task completion rate and other indicators for each device. These statistical data are arranged in order of device number and time to form a task allocation time series matrix. Taking 10 AGV devices as an example, when the system runs for 8 hours, a time series matrix with 10 rows and 96 columns will be formed. Each row represents a device, each column represents the statistical result of a time window, and the matrix elements contain the detailed data of the task execution of the device in the time window.

[0038] Specifically, when analyzing the task allocation time series matrix, the system first preprocesses the data and standardizes different types of indicator data to the same scale. Then the K-means clustering algorithm is executed. The number of clusters is set to 3 during clustering, representing the three states of high load, normal load and low load. During the clustering process, the system randomly selects three initial cluster centers, calculates the distance between the task allocation data of each device and these three centers, and allocates the device to the cluster with the closest distance. Then the center point of each cluster is recalculated, and this process is repeated until the cluster center no longer changes significantly. The clustering results are represented by a device task density distribution diagram, in which the horizontal axis is time and the vertical axis is task density. Curves of different colors represent devices with different load states. When calculating the skewness coefficient of this distribution diagram, the data points of each curve are first sorted by size, the median and quartiles are calculated, and the degree of skewness of the distribution is determined based on the central trend of the data. The system sets the skewness threshold to plus or minus 1.5. When the skewness coefficient of the device exceeds this range, it is marked as an optimization dead-end device, indicating that the device is either in a state of task overload or in a state of task underload for a long time.

[0039] Specifically, the system collects detailed task execution data from the optimized blind spot device group, including navigation positioning accuracy, path planning time, task completion time, battery consumption rate, task switching frequency, error handling times and other indicators. These raw data are first cleaned to remove outliers and missing values. Then the principal component analysis is performed. First, the correlation coefficient matrix between the indicators is calculated, and its eigenvalues ​​and eigenvectors are solved, and several eigenvectors with the largest eigenvalues ​​are selected as principal components. The task feature matrix is ​​constructed through these principal components. Each row of the matrix represents a task, and each column represents a principal component feature. Then, the hierarchical clustering algorithm is used. First, each task is regarded as a separate class, and the Euclidean distance between classes is calculated. The two classes with the closest distance are merged each time to form a task clustering tree. Select the appropriate segmentation level in the clustering tree to divide the tasks into different difficulty levels, usually divided into three levels: basic, advanced and expert.

[0040] Specifically, the system uses the Bayesian update method to dynamically adjust the task allocation strategy. First, a priori model is constructed through the historical working data of the equipment to record the success rate of each device on tasks of different difficulty levels. When new task execution data is generated, these probability values ​​are updated using the Bayesian formula. During the update process, a larger weight is given to the most recent execution data, and a smaller weight is given to the earlier data. The updated probability value is multiplied by the initial task allocation probability matrix to obtain a new task allocation strategy. For example, after an AGV device completes an expert-level task, the system will increase the probability of the device being assigned to high-difficulty tasks, while correspondingly reducing the probability of being assigned to tasks of other difficulty levels. This dynamic update mechanism ensures that the task allocation strategy can promptly reflect changes in the actual working capacity of the equipment. The final dynamic task allocation strategy is stored in the system in the form of a probability matrix to guide the subsequent task allocation process.

[0041] Furthermore, the K-means clustering calculation is performed on the task allocation timing matrix to obtain a device task density distribution map, the skewness coefficient is calculated on the device task density distribution map, and the devices whose skewness coefficient exceeds a threshold are grouped and marked to obtain an optimized dead-end device group, including: performing Gaussian kernel density estimation calculation on each sampling point of the task allocation timing matrix to obtain a device task distribution probability map, performing gradient descent clustering calculation on the device task distribution probability map to obtain a task density cluster center; performing Euclidean distance calculation on the task density cluster center to obtain a cluster distance matrix, performing K-means iterative calculation based on the cluster distance matrix to obtain a device task density distribution map; performing probability moment estimation calculation on the device task density distribution map to obtain a distribution matrix, performing third-order moment calculation on the distribution matrix to obtain a skewness coefficient; performing dynamic threshold calculation on the devices based on the skewness coefficient to obtain a grouping threshold, performing a comparison operation on the grouping threshold and the skewness coefficient, grouping and marking the devices whose skewness coefficient exceeds the grouping threshold, and obtaining an optimized dead-end device group.

[0042] Specifically, when processing the task allocation time series matrix, the system performs Gaussian kernel density estimation calculation on the data of each sampling point. In the specific operation, the task allocation data at each time point in the time series matrix is ​​first taken as a sample point, and the appropriate bandwidth parameter is selected, and the Gaussian kernel function is applied to each sample point for smoothing. In actual applications, the time series matrix contains sampling data once every 5 minutes, and each sampling point records the number of tasks, task type, execution time and other information of the device. The system performs kernel density estimation on these sampling points one by one and calculates the probability density of task distribution at each time point. By processing a large number of sampling points, the system generates a continuous probability distribution curve to form a probability map of device task distribution. Then, the gradient descent clustering calculation is performed on this probability map to find the local maximum points in an iterative manner. These points are the cluster centers of task density. In the clustering process, the system sets a convergence condition and stops the iteration when the gradient change is less than the preset threshold. The final cluster center reflects the main mode of task allocation.

[0043] Specifically, after obtaining the task density cluster centers, the system calculates the Euclidean distance between these center points. The calculation takes into account features of multiple dimensions, including the number of tasks, distribution of task types, execution time, etc. The distance values ​​between each pair of cluster centers are recorded in the cluster distance matrix, which is a symmetric matrix with zero diagonal elements. For 10 cluster centers, a 10×10 distance matrix is ​​formed. Based on this distance matrix, the system performs K-means iterative calculation, and the iterative process includes two steps: allocation and update. In the allocation step, each data point is assigned to the cluster center with the nearest distance; in the update step, the center point position of each class is recalculated. This process is repeated until the clustering result tends to be stable. The final generated device task density distribution diagram shows the distribution of different devices in task allocation. Each curve in the figure represents the trend of task load changes of a device.

[0044] Specifically, the system further analyzes the distribution diagram of the equipment task density, and first performs probability moment estimation calculations. During the estimation process, the mean, variance and other statistics are calculated for each task density curve, and these statistics constitute the distribution matrix. Each row in the distribution matrix corresponds to a device, and each column corresponds to a statistical feature. During the data processing process, the system centralizes the original data to facilitate subsequent moment calculations. The processed distribution matrix is ​​calculated for the third-order moment, which reflects the degree of asymmetry of the data distribution. During the calculation of the third-order moment, the system cubes the deviation of each data point from the mean, then calculates the average value, and finally divides it by the cube of the standard deviation to obtain the skewness coefficient. This coefficient reflects the degree of skewness of the task allocation. A positive value indicates that the distribution is right-skewed, and a negative value indicates that the distribution is left-skewed.

[0045] Specifically, after obtaining the skewness coefficient, the system needs to determine the appropriate grouping threshold. This process uses a dynamic threshold calculation method. First, the distribution of the skewness coefficients of all devices is counted, and the mean and standard deviation of the skewness coefficients are calculated. Based on historical operating experience, the system sets the threshold to the mean plus or minus two times the standard deviation. This setting can better identify devices with abnormal task allocation. When the skewness coefficient of a device exceeds this range, the system marks it as a device to be optimized. In the specific comparison process, the system considers both the positive and negative directions of the skewness. Excessively high positive skewness indicates that the device tasks are too concentrated, and too low negative skewness indicates that the device tasks are insufficiently allocated. The marked devices will eventually be classified into the optimization blind spot device group, and these devices will be optimized in the subsequent task allocation. In this way, the system can promptly detect and correct the imbalance in task allocation.

[0046] 104. According to the task allocation strategy, the synergistic effect of the equipment group's production efficiency, energy utilization and task completion quality is evaluated, and based on the evaluation results, the member composition and capability complementarity of the equipment group are dynamically optimized to obtain the collaborative evolution plan of the equipment group.

[0047] In one embodiment of the present invention, the synergistic effect evaluation of the production efficiency, energy utilization rate and task completion quality of the equipment group is performed according to the task allocation strategy, and the member composition and capability complementarity of the equipment group are dynamically optimized based on the evaluation results to obtain the collaborative evolution plan of the equipment group, including: time series acquisition of the equipment group task throughput data, the equipment group task response time data and the equipment group task accuracy data during the execution of the task allocation strategy to obtain the equipment group production efficiency evaluation data; weighted calculation of the equipment group energy consumption data, the equipment group standby time data and the equipment group peak power data during the execution of the task allocation strategy to obtain the equipment group energy utilization evaluation data; hierarchical analysis calculation of the equipment group according to the production efficiency evaluation data and the energy utilization evaluation data to obtain the equipment group performance evaluation matrix, eigenvalue decomposition calculation of the equipment group performance evaluation matrix to obtain the equipment group capability characteristic vector; optimal matching calculation of the equipment group members according to the equipment group capability characteristic vector to obtain the equipment group member reorganization plan, predictive calculation of the equipment group collaborative efficiency in the equipment group member reorganization plan to obtain the equipment group collaborative evolution plan.

[0048] Specifically, during the execution of the task allocation strategy, the system monitors the operating status of the equipment group in real time through a distributed data acquisition network. Each equipment group is equipped with a dedicated data acquisition module to collect task throughput data at intervals of 10 seconds and record the number of tasks completed per unit time. For example, a device group consisting of 5 AGVs will generate 2880 throughput sampling points in an 8-hour working cycle. At the same time, the system also collects task response time data, including the waiting time from receiving the task instruction to starting execution, the actual time of task execution, and other information. For task accuracy data, the system records indicators such as position accuracy and posture accuracy of task completion. After preprocessing, these raw data are arranged in chronological order to form a multidimensional time series. The system performs sliding window processing on these time series data, with the window size set to 30 minutes and each sliding for 10 minutes. Statistics such as the mean and standard deviation are calculated in each window, and finally the evaluation data reflecting the overall production efficiency of the equipment group is obtained.

[0049] Specifically, the equipment group generates a large amount of energy-related data during operation. The system first collects real-time energy consumption data, including the instantaneous power and cumulative power consumption of each device. These data are recorded once a minute through an industrial-grade power collector. At the same time, the standby time data of the equipment is recorded, that is, the time period when the equipment is idle but still consumes energy. In addition, the peak power data of the equipment group is monitored to record the power peaks and their duration during the production process. These three types of data have different levels of importance. The system sets weight coefficients according to their impact on energy efficiency. Usually, the weight of energy consumption data is 0.5, the weight of standby time data is 0.3, and the weight of peak power data is 0.2. These weighted data are normalized and unified into the same numerical range, and then linearly combined to obtain evaluation data that comprehensively reflects the energy efficiency of the equipment group. This evaluation data can objectively reflect the overall performance of the equipment group in energy utilization.

[0050] Specifically, after obtaining the production efficiency evaluation data and energy utilization evaluation data, the system uses the hierarchical analysis method to conduct a comprehensive evaluation of the equipment group. First, an evaluation index system is established, including two categories: production efficiency index group and energy efficiency index group. The production efficiency index group includes three secondary indicators: task throughput, response time, and accuracy; the energy efficiency index group includes three secondary indicators: energy consumption level, standby time, and peak management. The weights of indicators at all levels are determined by expert scoring, and a judgment matrix is ​​constructed. The judgment matrix is ​​checked for consistency to ensure the reliability of the evaluation results. On this basis, the equipment group performance evaluation matrix is ​​obtained, which comprehensively reflects the performance of the equipment group on different indicators. Then, the performance evaluation matrix is ​​decomposed and calculated to obtain the eigenvector that can characterize the core capabilities of the equipment group. This eigenvector contains the main performance characteristics of the equipment group and provides a basis for subsequent optimization.

[0051] Specifically, based on the equipment group capability feature vector, the system begins to perform member optimization matching calculations. First, a device capability model is constructed, which includes the degree of expertise of each device in different task types. For example, in an equipment group that mixes multiple brands of AGVs, some devices are good at precision positioning tasks, while others perform better in long-distance transportation tasks. The system conducts a complementary analysis based on these specialties to find the optimal equipment combination. The optimization process uses a genetic algorithm to encode the combination of equipment into chromosomes and find the optimal solution through multiple generations of evolution. For each recombination scheme obtained, the system will build a prediction model based on historical data to calculate the expected collaborative efficiency of the scheme in the future. Finally, the scheme with the highest expected efficiency is selected as the collaborative evolution scheme of the equipment group, which specifies in detail the member composition, task division strategy and collaboration mechanism of the equipment group.

[0052] In this embodiment, the affinity matrix between devices is calculated based on the physical location, communication delay, device type and historical collaboration relationship of the device, and the collaboration weight of heterogeneous devices is determined to obtain a device collaboration networking solution; then the timing score is calculated according to the task completion quality, energy consumption efficiency, device stability and collaborative adaptability of each device group, and the dynamic weight adjustment is performed in combination with environmental monitoring data to obtain the device credit score; then the initial task allocation is performed based on the device credit score, and continuous bias analysis and resource balancing are performed by analyzing the data during the task execution process to obtain a dynamic task allocation strategy; finally, the collaborative effect of the device group is evaluated according to the task allocation strategy, and the device group is dynamically optimized to obtain a collaborative evolution solution. The present invention effectively solves the problem of unreasonable device resource allocation through dynamic evaluation and balancing mechanisms.

[0053] The above describes the production collaborative management method of the digital factory in the embodiment of the present invention. The following describes the production collaborative management system of the digital factory in the embodiment of the present invention. Figure 2 , an embodiment of the production collaborative management system of a digital factory in an embodiment of the present invention includes: The networking module 201 is used to calculate the affinity matrix between devices according to the physical location, communication delay, device type and historical collaboration relationship of the devices in each area of ​​the digital factory, and determine the collaboration weights of heterogeneous devices based on the affinity matrix to obtain a device collaboration networking solution; Scoring module 202, used to calculate the timing score of the device according to the task completion quality, energy consumption efficiency, device stability and collaborative adaptability of each device group in the device collaborative networking solution, and dynamically adjust the weight of the timing score based on the environmental monitoring data to obtain the device credit score; The scheduling module 203 is used to perform initial task allocation to the device according to the device credit score, and perform continuous bias analysis on the device based on the task allocation data collected during the task execution process, balance the device resources according to the analysis results, and obtain a dynamic task allocation strategy; The optimization module 204 is used to evaluate the synergistic effect of the production efficiency, energy utilization and task completion quality of the equipment group according to the task allocation strategy, and dynamically optimize the member composition and capability complementarity of the equipment group based on the evaluation results to obtain a collaborative evolution plan for the equipment group.

[0054] In an embodiment of the present invention, the production collaborative management system of the digital factory runs the production collaborative management method of the digital factory. The production collaborative management system of the digital factory calculates the affinity matrix between devices based on the physical location, communication delay, device type and historical collaborative relationship of the devices, and determines the collaborative weight of heterogeneous devices to obtain a collaborative networking solution for the devices; then, the timing score is calculated according to the task completion quality, energy consumption efficiency, device stability and collaborative adaptability of each device group, and the dynamic weight adjustment is performed in combination with environmental monitoring data to obtain the device credit score; then, the initial task allocation is performed based on the device credit score, and continuous bias analysis and resource balancing are performed by analyzing the data during the task execution process to obtain a dynamic task allocation strategy; finally, the collaborative effect of the device group is evaluated according to the task allocation strategy, and the device group is dynamically optimized to obtain a collaborative evolution solution. The present invention effectively solves the problem of unreasonable device resource allocation through dynamic evaluation and balancing mechanisms.

[0055] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device, or unit can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0056] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0057] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A production collaborative management method for a digital factory, characterized in that: The production collaborative management method of the digital factory includes: The affinity matrix between devices is calculated according to the physical location, communication delay, device type and historical collaboration relationship of the devices in each area of ​​the digital factory, and the collaboration weights of heterogeneous devices are determined based on the affinity matrix to obtain a device collaboration networking solution; Calculate the timing score of the device according to the task completion quality, energy consumption efficiency, device stability and collaborative adaptability of each device group in the device collaborative networking solution, and dynamically adjust the weight of the timing score based on the environmental monitoring data to obtain the device credit score; Initially assign tasks to devices according to the device credit score, and continuously analyze the bias of devices based on the task assignment data collected during task execution, balance device resources according to the analysis results, and obtain a dynamic task assignment strategy; According to the task allocation strategy, the synergistic effect of the equipment group's production efficiency, energy utilization and task completion quality is evaluated, and based on the evaluation results, the member composition and capability complementarity of the equipment group are dynamically optimized to obtain a collaborative evolution plan for the equipment group.

2. The production collaborative management method of a digital factory according to claim 1, characterized in that: The affinity matrix between devices is calculated according to the physical location, communication delay, device type and historical collaboration relationship of the devices in each area of ​​the digital factory, and the collaboration weights of heterogeneous devices are determined based on the affinity matrix to obtain the device collaboration networking solution, including: Perform Euclidean distance calculation on the physical location data of the device to obtain the location distance matrix, and perform sampling calculation on the round-trip delay of the communication data packets between devices to obtain the communication delay matrix; The compatibility of communication protocols of different types of devices is calculated to obtain the device type affinity matrix, and the historical collaboration data of devices is processed by time decay function to obtain the collaboration intensity matrix; Perform multi-dimensional weighted fusion calculation according to the location distance matrix, communication delay matrix, device type affinity matrix and collaboration strength matrix to obtain an affinity matrix between devices; The communication efficiency between the heterogeneous device pairs in the affinity matrix is ​​evaluated to obtain an initial coordination weight, and the initial coordination weight is dynamically adjusted according to the coordination success rate of the heterogeneous device pairs under different working conditions to obtain the coordination weight between the heterogeneous devices; The devices are grouped and divided based on the collaboration weights to obtain a device collaborative networking solution.

3. The production collaborative management method of a digital factory according to claim 1, characterized in that: The device credit score is obtained by calculating the device timing score based on the task completion quality, energy consumption efficiency, device stability and collaborative adaptability of each device group in the device collaborative networking solution, and dynamically adjusting the timing score based on environmental monitoring data. The device credit score includes: Performing least square fitting calculation on the task position accuracy deviation, task completion time deviation and task execution parameter deviation of each device group in the device collaborative networking solution to obtain a quality assessment matrix, performing piecewise linear regression calculation on the quality assessment matrix to obtain task quality time series data; Perform wavelet decomposition calculation on the equipment current fluctuation data, voltage fluctuation data and power factor data of each equipment group in the equipment collaborative networking solution to obtain an energy consumption characteristic sequence, perform cross-correlation calculation on the energy consumption characteristic sequence and the standard energy consumption model to obtain energy efficiency time series data; Performing empirical mode decomposition calculation on the equipment vibration spectrum data, temperature change data and motor speed fluctuation data of each equipment group in the equipment collaborative networking solution to obtain a state eigenvector, performing principal component analysis calculation on the state eigenvector to obtain stability time series data; Performing Markov chain transfer probability calculation on the task quality time series data, energy efficiency time series data, and stability time series data to obtain a time series score; The principal component analysis is performed on the regional temperature field gradient data, humidity distribution data and electromagnetic interference intensity distribution data in the environmental monitoring data to obtain the environmental feature vector, and the neural network weight calculation is performed on the environmental feature vector and the time series score to obtain the equipment credit score.

4. The production collaborative management method of a digital factory according to claim 3 is characterized in that: The Markov chain transfer probability calculation is performed on the task quality time series data, energy efficiency time series data and stability time series data to obtain the time series score, which includes: Perform time series segmentation calculation on the task quality time series data to obtain a quality state sequence, perform frequency statistics on adjacent states in the quality state sequence to obtain a first-order transfer frequency matrix; Normalizing the energy efficiency time series data and the stability time series data to obtain a standardized data sequence, and performing state quantization calculation on the standardized data sequence to obtain an energy efficiency state sequence and a stability state sequence; Performing transfer probability calculation on the quality state sequence, energy efficiency state sequence and stability state sequence to obtain a Markov transfer probability matrix, and performing stationary distribution calculation on the Markov transfer probability matrix to obtain a state probability vector; n-step transition probability calculation is performed according to the state probability vector and the Markov transition probability matrix to obtain a time series score.

5. The production collaborative management method of a digital factory according to claim 1, characterized in that: The initial task allocation is performed on the device according to the device credit score, and the device is continuously biased based on the task allocation data collected during the task execution process. The device resources are balanced according to the analysis results to obtain a dynamic task allocation strategy, which includes: Calculating the sample standard deviation of the equipment credit score to obtain score dispersion data, calculating the probability density distribution of the score dispersion data to obtain an initial task allocation probability matrix, and performing initial task allocation according to the initial task allocation probability matrix; Performing time series acquisition and sliding time window calculation on the task allocation data after the initial task allocation to obtain a task allocation time series matrix; Performing K-means clustering calculation on the task allocation timing matrix to obtain a device task density distribution map, calculating the skewness coefficient on the device task density distribution map, grouping and marking devices whose skewness coefficient exceeds a threshold, and obtaining an optimized blind spot device group; Performing principal component analysis calculation on the task execution data of the optimized blind spot equipment group to obtain a task feature matrix, and performing hierarchical clustering calculation on the task feature matrix to obtain task difficulty level data; The initial task allocation probability matrix is ​​subjected to Bayesian update calculation according to the task difficulty level data to obtain a dynamic task allocation strategy.

6. The production collaborative management method of a digital factory according to claim 5, characterized in that: The K-means clustering calculation is performed on the task allocation timing matrix to obtain a device task density distribution map, the skewness coefficient is calculated on the device task density distribution map, and the devices whose skewness coefficient exceeds a threshold are grouped and marked to obtain an optimized blind spot device group, including: Performing Gaussian kernel density estimation calculation on each sampling point of the task allocation timing matrix to obtain a device task distribution probability map, and performing gradient descent clustering calculation on the device task distribution probability map to obtain a task density clustering center; Performing Euclidean distance calculation on the task density cluster centers to obtain a cluster distance matrix, and performing K-means iterative calculation based on the cluster distance matrix to obtain a device task density distribution map; Performing probability moment estimation calculation on the equipment task density distribution diagram to obtain a distribution matrix, and performing third-order moment calculation on the distribution matrix to obtain a skewness coefficient; A dynamic threshold value is calculated for the device according to the skewness coefficient to obtain a grouping threshold value, the grouping threshold value is compared with the skewness coefficient, and the devices whose skewness coefficient exceeds the grouping threshold value are grouped and marked to obtain an optimized blind spot device group.

7. The production collaborative management method of a digital factory according to claim 1, characterized in that: The collaborative effect evaluation of the production efficiency, energy utilization rate and task completion quality of the equipment group is performed according to the task allocation strategy, and the member composition and capability complementarity of the equipment group are dynamically optimized based on the evaluation results to obtain the collaborative evolution plan of the equipment group, including: Performing time series collection on the equipment group task throughput data, equipment group task response time data and equipment group task accuracy data during the execution of the task allocation strategy to obtain equipment group production efficiency evaluation data; Performing weighted calculation on the equipment group energy consumption data, equipment group standby time data and equipment group peak power data during the execution of the task allocation strategy to obtain equipment group energy utilization rate evaluation data; Performing hierarchical analysis calculation on the equipment group according to the production efficiency evaluation data and the energy utilization rate evaluation data to obtain an equipment group performance evaluation matrix, and performing eigenvalue decomposition calculation on the equipment group performance evaluation matrix to obtain an equipment group capability eigenvector; An optimal matching calculation is performed on the device group members according to the device group capability feature vector to obtain a device group member reorganization plan, and a prediction calculation is performed on the device group coordination efficiency in the device group member reorganization plan to obtain a coordinated evolution plan of the device group.

8. A production collaborative management system for a digital factory, characterized in that: The production collaborative management system of the digital factory includes: The networking module is used to calculate the affinity matrix between devices according to the physical location, communication delay, device type and historical collaboration relationship of the devices in each area of ​​the digital factory, and determine the collaboration weights of heterogeneous devices based on the affinity matrix to obtain a device collaboration networking solution; A scoring module, used to calculate the timing score of the device according to the task completion quality, energy consumption efficiency, device stability and collaborative adaptability of each device group in the device collaborative networking solution, and dynamically adjust the weight of the timing score based on the environmental monitoring data to obtain the device credit score; A scheduling module, used to perform initial task allocation to the device according to the device credit score, and perform continuous bias analysis on the device based on the task allocation data collected during the task execution process, balance the device resources according to the analysis results, and obtain a dynamic task allocation strategy; The optimization module is used to evaluate the synergistic effect of the production efficiency, energy utilization and task completion quality of the equipment group according to the task allocation strategy, and dynamically optimize the member composition and capability complementarity of the equipment group based on the evaluation results to obtain a collaborative evolution plan for the equipment group.

Images