Intelligent production scheduling and dispatching system and method based on digital twinning

Abstract

The invention relates to the technical field of intelligent production scheduling and scheduling, and particularly discloses an intelligent production scheduling and scheduling system and method based on digital twinning, and the method comprises the steps: arranging a to-be-scheduled order set into two to-be-scheduled order sequences through employing different sorting strategies; the resource-time matrix is used for carrying out production scheduling simulation on the two order sequences to be scheduled, corresponding simulation logs are generated by simulating production processes in different production scheduling modes, and then an optimized production scheduling mode is determined based on comparison between the simulation logs so as to carry out corresponding scheduling and management. Therefore, potential problems can be found in advance through virtual simulation in the digital twin technology, the production scheduling mode is optimized in time, the production plan is adjusted in time, and losses in actual production are avoided.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent production scheduling and dispatching, and more specifically, to an intelligent production scheduling and dispatching system and method based on digital twins. Background Art

[0002] In modern manufacturing, the manufacturing process of a workshop mainly consists of machining, fire processing and inspection. These machining processes include multiple processes, and each process includes multiple production lines. Therefore, production scheduling and dispatching are one of the core links of production management. The production scheduling goal is to sort the order tasks according to the order demand within a period of time to meet the production needs. Effective production scheduling and dispatching can not only improve production efficiency and reduce resource waste, but also ensure that products are delivered on time and improve customer satisfaction. With the intensification of market competition, enterprises are facing higher and higher production efficiency requirements and shorter product delivery cycles. Therefore, how to arrange production plans scientifically and reasonably has become an important manifestation of the competitiveness of enterprises.

[0003] However, traditional production scheduling and dispatching methods mostly rely on the experience and intuition of production managers. This method may be more effective when facing simple and repetitive production tasks, but it is prone to decision-making errors when dealing with complex and changing production environments, resulting in low production efficiency. Not only that, traditional production scheduling methods usually use some fixed rules or algorithms, which are difficult to adapt to market changes and rapid response to customer needs. Especially in the multi-variety and small-batch production mode, fixed rules are difficult to meet diverse needs, which can easily cause resource waste and production delays. In addition, traditional production scheduling methods often cannot make full use of existing resources. Whether it is manual experience or fixed rule algorithms, the level of intelligence of the production management and dispatching system is low, resulting in longer equipment idle time and changeover time, resulting in low overall production efficiency.

[0004] Therefore, an optimized production scheduling and dispatching system is desired. Summary of the invention

[0005] The present application provides an intelligent production scheduling and dispatching system and method based on digital twins, which can discover potential problems in advance through virtual simulation in digital twin technology, optimize production scheduling methods in a timely manner, and adjust production plans in a timely manner to avoid losses in actual production.

[0006] In a first aspect, an intelligent production scheduling and dispatching system based on digital twin is provided, including: a to-be-scheduled order set acquisition module, used to acquire a to-be-scheduled order set; a to-be-scheduled order set arrangement module, used to arrange the to-be-scheduled order set in a first manner to obtain a first to-be-scheduled order sequence and to arrange the to-be-scheduled order set in a second manner to obtain a second to-be-scheduled order sequence; a to-be-scheduled order sequence scheduling module, used to set the scheduling time and schedule the first to-be-scheduled order sequence and the second to-be-scheduled order sequence based on a resource-time matrix to obtain a first emission mode simulation log and a second emission mode simulation log; an emission mode simulation log display module, used to display the first emission mode simulation log and the second emission mode simulation log; an emission mode simulation log comparison decision module, used to determine whether to arrange the to-be-scheduled order set in the first manner or the second manner based on a comparison between the first emission mode simulation log and the second emission mode simulation log.

[0007] In the second aspect, an intelligent production scheduling and dispatching method based on digital twins is provided, including: obtaining a set of orders to be scheduled; arranging the set of orders to be scheduled in a first manner to obtain a first sequence of orders to be scheduled and arranging the set of orders to be scheduled in a second manner to obtain a second sequence of orders to be scheduled; setting a scheduling time and scheduling the first sequence of orders to be scheduled and the second sequence of orders to be scheduled based on a resource-time matrix to obtain a first emission mode simulation log and a second emission mode simulation log; displaying the first emission mode simulation log and the second emission mode simulation log; and determining whether to arrange the set of orders to be scheduled in the first manner or the second manner based on a comparison between the first emission mode simulation log and the second emission mode simulation log.

[0008] The application provides an intelligent production scheduling and dispatching system and method based on digital twins. After arranging the set of pending orders into two pending order sequences by adopting different sorting strategies, the two pending order sequences are respectively simulated for production scheduling using the resource-time matrix. By simulating the production process under different production scheduling methods, corresponding simulation logs are generated, and then the optimized production scheduling method is determined based on the comparison between the simulation logs for corresponding scheduling and management. In this way, potential problems can be discovered in advance through virtual simulation in digital twin technology, the production scheduling method can be optimized in time, and the production plan can be adjusted in time to avoid losses in actual production. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application are briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, and are not intended to limit the present application.

[0010] Figure 1 This is a schematic block diagram of an intelligent production scheduling and dispatching system based on digital twins according to an embodiment of the present application.

[0011] Figure 2 This is a schematic block diagram of a production scheduling module for the order sequence to be scheduled in the intelligent production scheduling and dispatching system based on digital twins in an embodiment of the present application.

[0012] Figure 3 This is a schematic block diagram of the emission mode simulation log comparison decision module in the digital twin-based intelligent production scheduling and dispatching system of an embodiment of the present application.

[0013] Figure 4 This is a schematic diagram of the data flow of the emission mode simulation log comparison decision module in the intelligent production scheduling and dispatching system based on digital twins in an embodiment of the present application.

[0014] Figure 5 This is a schematic flowchart of the intelligent production scheduling and dispatching method based on digital twins according to an embodiment of the present application. DETAILED DESCRIPTION

[0015] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.

[0016] Digital twin technology is an advanced technology that has emerged in recent years. It achieves seamless connection between the physical world and the digital world by building a virtual model of a physical entity. In the manufacturing industry, digital twins can be used to simulate the working status of production lines, predict equipment failures, and optimize production processes. Applying digital twin technology to the production scheduling and dispatch management process in industrial production can reflect the situation on the production site in real time, discover potential problems in advance through virtual simulation, and automatically optimize the scheduling of production scheduling, thereby making full use of equipment resources and reducing waste and losses in the actual production process.

[0017] Based on this, in the technical solution of this application, an intelligent production scheduling and dispatching system based on digital twin is proposed, which can use digital twin technology and artificial intelligence technology to solve the problems existing in the traditional production scheduling method. Specifically, in the technical solution of this application, Figure 1 Schematic block diagram of the intelligent production scheduling and dispatching system based on digital twins according to an embodiment of the present application. Figure 1As shown, the intelligent production scheduling and dispatching system 100 based on digital twins includes: a to-be-scheduled order set acquisition module 110, used to acquire a set of to-be-scheduled orders; a to-be-scheduled order set arrangement module 120, used to arrange the to-be-scheduled order set in a first manner to obtain a first sequence of to-be-scheduled orders and to arrange the to-be-scheduled order set in a second manner to obtain a second sequence of to-be-scheduled orders; a to-be-scheduled order sequence scheduling module 130, used to set the scheduling time and schedule the first sequence of to-be-scheduled orders and the second sequence of to-be-scheduled orders based on a resource-time matrix to obtain a first emission mode simulation log and a second emission mode simulation log; an emission mode simulation log display module 140, used to display the first emission mode simulation log and the second emission mode simulation log; an emission mode simulation log comparison decision module 150, used to determine whether to arrange the to-be-scheduled order set in the first manner or the second manner based on a comparison between the first emission mode simulation log and the second emission mode simulation log.

[0018] Correspondingly, the intelligent production scheduling and dispatching system arranges the set of pending orders into two pending order sequences by adopting different sorting strategies, and then uses the resource-time matrix to perform scheduling simulation on the two pending order sequences respectively, and generates corresponding simulation logs by simulating the production process under different scheduling methods, and then determines the optimized scheduling method based on the comparison between the simulation logs for corresponding scheduling and management. In this way, potential problems can be discovered in advance through virtual simulation in digital twin technology, the scheduling method can be optimized in time, and the production plan can be adjusted in time to avoid losses in actual production.

[0019] In the above-mentioned intelligent production scheduling and dispatching system based on digital twins, the module 110 for acquiring the set of pending orders is used to acquire the set of pending orders. It should be understood that acquiring the set of pending orders is the basis of the entire production scheduling and dispatching process. Only by clarifying the set of pending orders can we know which products need to be produced within a specific time period, and then arrange production resources reasonably. By acquiring the order set, we can understand the specific requirements of each order (such as bill of materials, process, equipment, etc.), so as to reasonably allocate production resources and avoid waste of resources. Based on the order set, a detailed production plan can be formulated, including the start time, end time, required equipment, etc. of each order, to ensure the smooth progress of the production process. By acquiring the set of pending orders, potential problems such as insufficient equipment and material shortages can be discovered before scheduling, and the production plan can be adjusted in time to avoid losses in actual production.

[0020] Optionally, in one embodiment of the present application, obtaining a collection of pending orders includes: collecting information of all pending orders from a sales department or a customer management system. The pending order information includes order number, product model, quantity, and delivery date. The collected order information is organized into a unified format to facilitate subsequent processing. Here, a spreadsheet, a database, or other data management tools can be used to store and manage the order information. The collected order information is verified to ensure the accuracy and completeness of the data. For example, check whether there are duplicate orders, whether the order information is complete, whether the delivery date is reasonable, etc.

[0021] Further, in another embodiment of the present application, obtaining a set of pending orders includes: obtaining the production process, processing time of each process, and delivery time of the pending orders. Here, the manufacturing process of the workshop is mainly composed of three major parts: machining-fire processing-inspection, that is, the production process includes: machining, fire processing, inspection, wherein machining and inspection each include multiple production lines, and fire processing includes multiple processes such as A, B, C, D, and E. Each process includes multiple production lines, and different products have different processes in the fire processing part. The production scheduling goal is to sort the order tasks according to the order demand within a period of time to meet the production needs.

[0022] In the above-mentioned intelligent production scheduling and dispatching system based on digital twins, the to-be-scheduled order set arrangement module 120 is used to arrange the set of to-be-scheduled orders in a first manner to obtain a first sequence of to-be-scheduled orders and to arrange the set of to-be-scheduled orders in a second manner to obtain a second sequence of to-be-scheduled orders. It should be understood that through different arrangement methods, the pros and cons of the production scheduling scheme can be evaluated from multiple angles to ensure that the final selected scheme is the best. At the same time, a single arrangement method may ignore certain potential problems. Through multiple arrangement methods, these problems can be discovered and avoided in advance. Different arrangement methods can cope with different production environments and market demands, and improve the flexibility and adaptability of production scheduling. By comparing the simulation results of different arrangement methods, more scientific decisions can be made, the best production scheduling method can be selected, and production efficiency and resource utilization can be improved.

[0023] Optionally, in one embodiment of the present application, the set of to-be-arranged orders is arranged by adopting a forward arrangement strategy for all processes of the machining and fire processing parts and semi-finished products to obtain a sequence of the first to-be-arranged orders, that is, starting from the production start time, the processing time of each order is gradually arranged according to the processing order of the order. At the same time, the set of to-be-arranged orders is arranged by adopting a reverse arrangement strategy for the last inspection process in the order to obtain a sequence of the second to-be-arranged orders. That is, starting from the delivery date of the order, the processing time of each order is reversely arranged to ensure that the order can be delivered on time. By means of a reverse arrangement strategy, it is possible to ensure that the order is delivered on time and minimize the delivery delay time. It should be noted that other arrangements can also be adopted, for example, by urgency of the order (such as the priority required by the customer). Arrange by the production difficulty of the order (such as the complexity of the required equipment and the complexity of the process). It is only in the technical solution of the present application that the above two production scheduling methods are used for explanation, but those skilled in the art should know that the technical solution of the present application is not limited to this, but covers all possible production scheduling solutions.

[0024] In the above-mentioned intelligent production scheduling and dispatching system based on digital twins, the to-be-scheduled order sequence scheduling module 130 is used to set the production scheduling time and schedule the first to-be-scheduled order sequence and the second to-be-scheduled order sequence based on the resource-time matrix to obtain the first emission mode simulation log and the second emission mode simulation log. It should be understood that by setting the production scheduling time and simulating different production scheduling methods based on the resource-time matrix, the effects of different production scheduling methods can be evaluated and the optimal production scheduling plan can be selected. More specifically, before scheduling, it is necessary to set a clear production scheduling time period, which is usually from the current time to a period of time in the future (such as a week, a month, etc.). By setting the production scheduling time, it can be ensured that the production scheduling plan is valid within a specific time range. At the same time, ensure that all resources (such as equipment, manpower, materials, etc.) are available within this time period.

[0025] Optionally, in one embodiment of the present application, Figure 2 Schematic block diagram of the production scheduling module of the order sequence to be scheduled in the intelligent production scheduling and dispatching system based on digital twins in the embodiment of the present application. Figure 2As shown, the production scheduling module 130 for the sequence of pending orders includes: a resource-time matrix initialization unit 131, which is used to initialize the resource-time matrix, wherein the horizontal axis of the resource-time matrix represents the resources required for production, and the vertical axis of the resource-time matrix represents the time axis; an order information extraction unit 132, which is used to extract the order information of the current order from the sequence of the first pending orders; an order details parsing unit 133, which is used to extract the bill of materials, processes, equipment and processing time of each process required for the current order from the order information of the current order; an order process scheduling unit 134, which is used to find the earliest start time of the earliest process that satisfies the current order in the resource-time matrix based on the processing sequence of the processes of the current order, record the processing time of the earliest process, and occupy the time period in the resource-time matrix.

[0026] More specifically, the production scheduling module for the sequence of pending orders includes: all information initialized before scheduling, including equipment, product BOM, each product process, etc. Set the production scheduling time period, and then initialize a resource-time matrix, where the horizontal axis represents the resources required for production (machinery, equipment, manpower, materials, etc.), and the vertical axis represents the timeline, with minutes as the minimum unit in this scenario. For the first sequence of pending orders, according to the index in the sequence, the current order information is captured in turn, and the BOM, process, equipment, and processing time of each process required for the current order are calculated. Then, according to the processing order of the process, find the earliest start time that satisfies the current process in the resource-time matrix, record the processing time of the process, and record (occupy) this period of time in the resource-time matrix.

[0027] Furthermore, when scheduling the first sequence of orders to be scheduled, the following rules are also set for constraints, and the rules include: 1. The transfer rule is set to order as a unit, and transfer is performed after each order is completed. For example, in an example of the present application, the machining-fire processing dle (Detailed Line Execution) is 15 minutes, the internal transfer of the fire processing dle is 20 minutes, and the fire processing dle-inspection is 1 hour. 2. If the types of processed products before and after the selected processing equipment time period are different, it is necessary to reserve the changeover time of the production line. 3. If the process after machining is A, it is necessary to make an overall consideration during the calculation. After calculating the start-end time of process A, it is necessary to verify whether the total time of machining-A is less than 48 hours. If it is less than, no modification is required. If it is greater than 48 hours, the previous machining process needs to be modified, and the start time of the machining process needs to be postponed until the 48h constraint is met. 4. If multiple equipment can be selected in production, select the equipment that can start production the earliest. 5. The start time of each process needs to be after the end time of the previous process plus the transfer time.

[0028] More specifically, the order sequence scheduling module also includes: extracting the order information of the current order from the set of orders to be scheduled, including the order number, product model, quantity, delivery date, required bill of materials, process, equipment and processing time of each process, etc. According to the order information, the bill of materials, process, equipment and processing time of each process required for the current order are calculated. Starting from the delivery date, the latest end time of each inspection process is reversely found, the processing time of the process is recorded, and the time period in the resource-time matrix is ​​occupied.

[0029] Furthermore, when scheduling the second sequence of orders to be scheduled, the following rules are set for constraints, including: 1. Delivery time constraint. Under the condition of ensuring on-time delivery, the end time should be as close to the delivery date as possible. 2. Earliest completion time. If on-time delivery cannot be guaranteed, select the earliest completion time. 3. Transfer rule: The order is the unit, and each completed order is transferred. Machining-fire processing takes 15 minutes, internal transfer of fire processing takes 20 minutes, and fire processing-inspection takes 1 hour. 4. Changeover time: If the types of processed products before and after the selected processing equipment time period are different, it is necessary to reserve changeover time for the production line.

[0030] Finally, after completing the production scheduling, the model will output different resource-time matrices for the first sequence of orders to be scheduled and the second sequence of orders to be scheduled, as well as the start time, end time, occupied machines and other information of each process of each order. The utilization rate and number of changeovers of each equipment can be calculated based on the resource-time matrix; the delay time of each order can be calculated based on the end time, and a Gantt chart can be drawn.

[0031] In the above-mentioned intelligent production scheduling and dispatching system based on digital twins, the emission mode simulation log display module 140 is used to display the first emission mode simulation log and the second emission mode simulation log. It should be understood that by displaying the simulation log, the effects of different production scheduling methods can be intuitively evaluated and the optimal production scheduling plan can be selected. At the same time, by displaying the simulation log, potential problems such as insufficient resources, equipment conflicts, production bottlenecks, etc. can be discovered before actual production, and production plans can be adjusted in time to avoid losses in actual production. By displaying the simulation log, resource allocation can be better optimized to ensure the smooth progress of the production process. The resource-time matrix can intuitively display the use of resources, help managers reasonably arrange production resources, and reduce equipment idle time.

[0032] Optionally, in one embodiment of the present application, a Gantt chart is used to display the start time, end time and occupied machines of each process of each order. The Gantt chart can intuitively display the production progress and resource usage of the order. A bar chart or a line chart is used to display the utilization rate of each device. A bar chart or a line chart is used to display the number of changeovers of the hot processing part. A bar chart or a line chart is used to display the total delayed delivery time of all orders.

[0033] In the above-mentioned intelligent production scheduling and dispatching system based on digital twins, the emission mode simulation log comparison decision module 150 is used to determine whether to use the first method or the second method to arrange the set of orders to be arranged based on the comparison between the first emission mode simulation log and the second emission mode simulation log. It should be understood that in the above-mentioned intelligent production scheduling and dispatching system based on digital twins, it is crucial to compare the first emission mode simulation log and the second emission mode simulation log to determine which production scheduling method to use, because by comparing the simulation logs of the two production scheduling methods, the utilization rate of each equipment under different production scheduling methods can be evaluated. Selecting a production scheduling method with higher utilization can maximize the use of existing resources and improve production efficiency.

[0034] Specifically, when comparing the first emission mode simulation log and the second emission mode simulation log, the technical concept of the present application is to extract the sequence distribution of equipment utilization from different emission mode simulation logs, and use data processing and analysis algorithms based on artificial intelligence and deep learning in the back end to analyze the sequence distribution data of equipment utilization of these different emission modes, so as to capture the collaborative interaction and fusion characterization information between different equipment utilizations, thereby optimizing the production scheduling method to determine which production scheduling method to use for production and processing. In this way, the production scheduling and dispatching of the processing process can be realized in a more intelligent way, thereby ensuring the reliability of the production process and the scientific nature of the decision, and making full use of the existing equipment resources for product manufacturing.

[0035] Optionally, in one embodiment of the present application, Figure 3 This is a schematic block diagram of the emission mode simulation log comparison decision module in the digital twin-based intelligent production scheduling and dispatching system of an embodiment of the present application. Figure 4 Schematic diagram of data flow of the emission mode simulation log comparison decision module in the intelligent production scheduling and dispatching system based on digital twins in the embodiment of the present application. Figure 3 and Figure 4 As shown, the emission mode simulation log comparison decision module 150 includes: a first equipment utilization determination unit 151, which is used to determine the utilization of each mechanical equipment based on the first emission mode simulation log to obtain the sequence distribution of the first equipment utilization; a second equipment utilization determination unit 152, which is used to determine the utilization of each mechanical equipment based on the second emission mode simulation log to obtain the sequence distribution of the second equipment utilization; an equipment utilization sequence encoding unit 153, which is used to sequence encode the sequence distribution of the first equipment utilization and the sequence distribution of the second equipment utilization respectively to obtain the implicit correlation feature vector between the first equipment utilization and the implicit correlation feature vector between the second equipment utilization; an equipment utilization collaborative interaction compensation fusion unit 154, which is used to perform feature interaction fusion based on common features on the implicit correlation feature vector between the first equipment utilization and the implicit correlation feature vector between the second equipment utilization to obtain the equipment utilization collaborative interaction compensation fusion representation; a production scheduling optimization unit 155, which is used to optimize the production scheduling based on the equipment utilization collaborative interaction compensation fusion representation to determine the optimization result, and the optimization result is used to indicate whether to adopt the first method or the second method.

[0036] In the above-mentioned intelligent production scheduling and dispatching system based on digital twin, the first equipment utilization determination unit 151 and the second equipment utilization determination unit 152 are used to determine the utilization of each mechanical equipment based on the first emission mode simulation log to obtain the sequence distribution of the first equipment utilization, and to determine the utilization of each mechanical equipment based on the second emission mode simulation log to obtain the sequence distribution of the second equipment utilization. It should be understood that equipment utilization is an important indicator for measuring production efficiency and resource utilization. By determining the utilization of each mechanical equipment, the effects of different production scheduling methods can be evaluated and the optimal production scheduling plan can be selected.

[0037] Optionally, in one embodiment of the present application, the utilization rate of each machining equipment is calculated as follows: utilization rate of a single machining equipment = actual production time of the machining equipment / (last production time of the machining equipment-production scheduling start time).

[0038] In the above-mentioned intelligent production scheduling and dispatching system based on digital twin, the equipment utilization sequence encoding unit 153 is used to perform sequence encoding on the sequence distribution of the first equipment utilization and the sequence distribution of the second equipment utilization respectively to obtain the implicit correlation feature vector between the first equipment utilization and the implicit correlation feature vector between the second equipment utilization. It should be understood that, considering that in the production scheduling and dispatching of the processing generation task, in different emission modes, the utilization rates of various mechanical equipment have mutual correlation relationships and complex correlation patterns, based on this, in the technical solution of the present application, the sequence distribution of the first equipment utilization and the sequence distribution of the second equipment utilization are further input into the sequence encoder based on the bidirectional LSTM model for feature mining, so as to extract the implicit correlation feature information between the equipment utilization in different modes of the two, so as to obtain the implicit correlation feature vector between the first equipment utilization and the implicit correlation feature vector between the second equipment utilization.

[0039] Optionally, in one embodiment of the present application, the equipment utilization sequence encoding unit is used to: input the sequence distribution of the first equipment utilization and the sequence distribution of the second equipment utilization into a sequence encoder based on a bidirectional LSTM model to obtain an implicit correlation feature vector between the first equipment utilizations and an implicit correlation feature vector between the second equipment utilizations.

[0040] In the above-mentioned intelligent production scheduling and dispatching system based on digital twin, the equipment utilization collaborative interaction compensation fusion unit 154 is used to perform feature interactive fusion based on common features on the implicit correlation feature vector between the first equipment utilization and the implicit correlation feature vector between the second equipment utilization to obtain the equipment utilization collaborative interaction compensation fusion representation. It should be understood that, considering that the implicit correlation feature vector between the first equipment utilization and the implicit correlation feature vector between the second equipment utilization respectively contain the implicit correlation feature information of the equipment utilization of different scheduling methods, when the features of the two are interactively fused and compared, each data source often carries unique information, and there is also certain redundant or overlapping information. Traditional feature fusion methods may ignore these unique key implicit correlation feature information of equipment utilization, resulting in incomplete feature representation. In addition, there may be misalignment of equipment utilization features between different feature sources, which will further affect the effect of feature fusion. In addition, it is also considered that although there are differences in equipment utilization under different scheduling methods, there are also some common features. These common features reflect some basic laws and patterns of equipment utilization under different scheduling methods. Therefore, if you want to improve the accuracy of the subsequent production scheduling optimization results, you can use the common characteristics of equipment utilization under these different production scheduling methods as a basis to compensate and optimize the expression of the first implicit correlation feature vector between equipment utilization and the second implicit correlation feature vector between equipment utilization. Based on this, in the technical solution of the present application, the first implicit correlation feature vector between equipment utilization and the second implicit correlation feature vector between equipment utilization are further subjected to feature interaction fusion based on common characteristics to obtain the equipment utilization collaborative interaction compensation fusion representation. In particular, the feature interaction fusion method based on common characteristics can compensate and fuse features in multimodal or multi-perspective feature representation, which extracts the common characteristics between the first implicit correlation feature vector between equipment utilization and the second implicit correlation feature vector between equipment utilization, and based on this, compensates for the unique information existing in the implicit correlation characteristics between equipment utilization under each production scheduling method, thereby achieving a richer and more comprehensive feature representation. In this way, not only can the common information of equipment utilization under the two production scheduling methods be retained, but also the unique information in each feature source can be effectively supplemented, thereby improving the effect of feature fusion, enhancing the performance of the machine learning model, and providing a basis for subsequent production scheduling optimization and scheduling.

[0041] Optionally, in one embodiment of the present application, the equipment utilization collaborative interaction compensation fusion unit includes: a common feature extraction secondary subunit, which is used to input the implicit correlation feature vector between the first equipment utilizations and the implicit correlation feature vector between the second equipment utilizations into a common feature extraction network to obtain a common feature representation vector between equipment utilization features; an equipment utilization feature probabilistic processing secondary subunit, which is used to input the implicit correlation feature vector between the first equipment utilizations, the implicit correlation feature vector between the second equipment utilizations and the common feature representation vector between the equipment utilization features into a vector probabilization unit based on the Sigmoid function to obtain a probabilistic first equipment utilization implicit correlation feature vector, a probabilistic second equipment utilization implicit correlation feature vector and a probabilistic equipment utilization feature common feature representation vector; a first information fine-grained compensation calculation secondary subunit, which is used to calculate the first equipment utilization information fine-grained compensation vector of the probabilistic first equipment utilization implicit correlation feature vector relative to the probabilistic equipment utilization feature common feature representation vector ; A second information fine-grained compensation calculation secondary subunit, used to calculate the second device utilization information fine-grained compensation vector of the implicit correlation feature vector between the probabilistic second device utilizations relative to the common feature representation vector between the probabilistic device utilization features; a first fine-grained compensation secondary subunit, used to input the first device utilization information fine-grained compensation vector and the first device utilization implicit correlation feature vector into the fine-grained compensation module to obtain the first device utilization fine-grained feature compensation vector; a second fine-grained compensation secondary subunit, used to input the second device utilization information fine-grained compensation vector and the second device utilization implicit correlation feature vector into the fine-grained compensation module to obtain the second device utilization fine-grained feature compensation vector; a vector cascade secondary subunit, used to cascade the first device utilization fine-grained feature compensation vector, the second device utilization fine-grained feature compensation vector and the common feature representation vector between the device utilization features to obtain the device utilization collaborative interaction compensation fusion representation vector as the device utilization collaborative interaction compensation fusion representation.

[0042] Optionally, in one embodiment of the present application, the common feature extraction secondary sub-unit is used to: calculate the positional sum of the implicit correlation feature vector between the first device utilizations and the implicit correlation feature vector between the second device utilizations to obtain a device utilization correlation fusion feature vector; multiply the device utilization correlation fusion feature vector with the modulation weight matrix and then add it positionally with the modulation bias vector, and input the obtained modulated device utilization correlation fusion feature vector into a tanh function for activation processing to obtain a common feature representation vector between the device utilization features.

[0043] Optionally, in one embodiment of the present application, the first information fine-grained compensation calculation secondary sub-unit is used to: calculate the positional division between the probabilistic first device utilization implicit correlation feature vector and the probabilistic device utilization feature common feature representation vector to obtain the first device utilization common feature interaction feature vector; calculate the logarithmic function value with base 2 of the absolute value of the feature value at each position in the first device utilization common feature interaction feature vector, and then multiply the obtained first device utilization common feature interaction logarithmic representation vector by position with the probabilistic first device utilization implicit correlation feature vector to obtain the first device utilization information optimization representation vector; calculate the natural exponential function value with the natural constant e as the base and the feature value at each position in the first device utilization information optimization representation vector as the exponential power, and then input the obtained feature vector into the softmax function for processing to obtain the first device utilization information fine-grained compensation vector.

[0044] Optionally, in one embodiment of the present application, the first fine-grained compensation secondary subunit is used to: calculate the point-by-point multiplication between the first device utilization information fine-grained compensation vector and the first device utilization implicit association feature vector to obtain the first device utilization fine-grained feature compensation vector.

[0045] In summary, in the embodiment of the present application, the implicit correlation feature vector between the first device utilizations and the implicit correlation feature vector between the second device utilizations are subjected to feature interaction fusion based on common features to obtain the collaborative interaction compensation fusion representation of the device utilizations; wherein the feature interaction fusion formula is: ;in, and are respectively an implicit correlation feature vector between the first device utilizations and an implicit correlation feature vector between the second device utilizations, and are the modulation weight matrix and the modulation bias vector respectively, for function, is the common feature representation vector between equipment utilization features, for function, , and are respectively the common feature representation vector between probabilistic equipment utilization features, the implicit correlation feature vector between the probabilistic first equipment utilizations, and the implicit correlation feature vector between the probabilistic second equipment utilizations. , and are the common feature representation vector between probabilistic equipment utilization features, the implicit association feature vector between probabilistic first equipment utilizations, and the implicit association feature vector between probabilistic second equipment utilizations, respectively. is the value of the natural exponential function with the natural constant e as the base, for function, is each position feature value in the fine-grained compensation vector of the first device utilization information, is each position feature value in the fine-grained compensation vector of the second device utilization information, and are respectively the first device utilization information fine-grained compensation vector and the second device utilization information fine-grained compensation vector, For point-by-position multiplication, Indicates adding by position point. and are respectively a first device utilization fine-grained feature compensation vector and a second device utilization fine-grained feature compensation vector, For cascade operation, Fusing representation vectors for collaborative interaction compensation of equipment utilization.

[0046] Specifically, the feature interaction fusion process based on common features includes the following steps: First, a common feature extraction network is used to use a neural network architecture, such as a fully connected layer, to learn the common features and intrinsic connections between the implicit correlation feature vectors between the first equipment utilizations and the implicit correlation feature vectors between the second equipment utilizations. These common features reflect some basic laws and patterns of equipment utilization under different production scheduling methods. Retaining common information helps ensure the consistency of the final feature representation, avoids decision-making bias caused by missing features, and provides a basis for subsequent feature compensation and production scheduling optimization tasks.

[0047] Next, the implicit correlation feature vector between the first equipment utilization, the implicit correlation feature vector between the second equipment utilization, and the common feature representation vector between the equipment utilization features are input into a vector probabilization unit based on the Sigmoid function. The Sigmoid function is an activation function that can map real values ​​to the interval (0,1). In this step, the role of the Sigmoid function is to normalize each feature vector so that the feature values ​​at each position in each feature vector are converted into a probability form, thereby better measuring the importance of the feature. That is, the Sigmoid function is used to probabilize the feature vector, and the probabilized feature vector can more intuitively reflect which equipment utilization correlation features are significant and which are secondary, which helps to more comprehensively describe the correlation pattern of utilization between various mechanical equipment.

[0048] Then, considering that the change pattern of equipment utilization may be different under different production scheduling methods, each method has its own unique information. Therefore, the first equipment utilization information fine-grained compensation vector is further calculated by calculating the implicit correlation feature vector between the probabilistic first equipment utilization relative to the common feature representation vector between the probabilistic equipment utilization features. This process finds out the unique information about the first equipment utilization implicit correlation feature vector in addition to the common features by calculating the difference between the probabilistic feature vectors of the two. This information can help with subsequent production scheduling and dispatching tasks. At the same time, the second equipment utilization information fine-grained compensation vector is calculated for the implicit correlation feature vector between the probabilistic second equipment utilization relative to the common feature representation vector between the probabilistic equipment utilization features. Similar to the former, the goal is to identify the information in the second equipment utilization implicit correlation feature vector that is not fully covered in the common features. In this way, it can be ensured that as much implicit correlation feature information and unique information about equipment utilization of different production scheduling tasks as possible are retained in the final feature fusion process.

[0049] Subsequently, the first device utilization information fine-grained compensation vector and the first device utilization implicit correlation feature vector are input into the fine-grained compensation module to obtain the first device utilization fine-grained feature compensation vector. Furthermore, the second device utilization information fine-grained compensation vector and the second device utilization implicit correlation feature vector are input into the fine-grained compensation module to obtain the second device utilization fine-grained feature compensation vector. A fine-grained compensation module is generally a mechanism designed to enhance or supplement specific features, where the module receives the original device utilization implicit correlation feature vector and its corresponding compensation vector, and adds the compensation vector to the original feature vector in some way, such as multiplication, to generate a new feature vector containing more detailed information, thereby ensuring that the final feature representation retains both the common information between the two and contains unique information, thereby ensuring the consistency and integrity of the final feature fusion.

[0050] Finally, the first equipment utilization fine-grained feature compensation vector, the second equipment utilization fine-grained feature compensation vector, and the common feature representation vector between the equipment utilization features are cascaded to obtain the equipment utilization collaborative interaction compensation fusion representation vector as the equipment utilization collaborative interaction compensation fusion representation. This step creates a comprehensive feature representation by merging all compensated feature vectors. In particular, the cascade operation may be a simple vector concatenation, or a more complex fusion mechanism, such as an attention mechanism, to ensure that the final feature representation retains the common features and contains the unique information in the two input feature vectors. This comprehensive feature representation can more comprehensively reflect the changes in equipment utilization under different scheduling methods, improve the effect of feature fusion, and provide a basis for subsequent scheduling tasks.

[0051] In the above-mentioned intelligent production scheduling and dispatching system based on digital twin, the production scheduling mode optimization unit 155 is used to optimize the production scheduling mode based on the equipment utilization collaborative interaction compensation fusion representation to determine the optimization result, and the optimization result is used to indicate whether the first method or the second method is adopted. Optionally, in one embodiment of the present application, the production scheduling mode optimization unit is used to: input the equipment utilization collaborative interaction compensation fusion representation vector into the production scheduling mode optimization module based on the classifier to obtain the optimization result, and the optimization result is used to indicate whether the first method or the second method is adopted. That is to say, the collaborative interaction compensation fusion feature representation of the two equipment utilizations is used for classification processing to optimize the production scheduling mode. Further, in the technical solution of the present application, not only the two production scheduling modes listed above should be considered, but also other possible production scheduling modes (such as the difficulty of production according to the order, the value of the order, the resource requirements of the order, etc.) should be considered. By comparing all possible production scheduling modes in the above manner, it is determined which production scheduling mode is the best for production and processing. In this way, the production scheduling and dispatching of the processing process can be realized in a more intelligent way, thereby ensuring the reliability of the production process and the scientific nature of the decision, and making full use of the existing equipment resources for product manufacturing.

[0052] Optionally, in one embodiment of the present application, the equipment utilization collaborative interaction compensation fusion representation vector is input into a production scheduling optimization module based on a classifier to obtain an optimization result, including: using the fully connected layer of the classifier to fully connect the equipment utilization collaborative interaction compensation fusion representation vector to obtain a fully connected equipment utilization collaborative interaction compensation fusion representation vector; inputting the fully connected equipment utilization collaborative interaction compensation fusion representation vector into the Softmax classification function of the classifier to obtain the probability value of the equipment utilization collaborative interaction compensation fusion representation vector belonging to each classification label, the classification label including a first classification label for indicating that a first method is adopted and a second classification label for indicating that a second method is adopted; and determining the classification label corresponding to the largest of the probability values ​​as the optimization result.

[0053] In the case where the implicit correlation feature vector between the first device utilizations and the implicit correlation feature vector between the second device utilizations respectively represent the short-range-long-range bidirectional temporal correlation features of the first device utilizations and the second device utilizations, when performing compensatory interaction between features with common features as masks, the sparsity between the common mask features corresponding to the multi-dimensional correlation differences of the temporal features under the source temporal distribution will lead to the lack of local compensatory interaction between features, that is, it will cause the interactive distribution representation of the collaborative interactive compensatory fusion representation vector of the device utilizations to be simply repeated within the local interaction domain, affecting its semantic logical dependency and reducing the accuracy of the classification results.

[0054] Therefore, preferably, when the equipment utilization collaborative interaction compensation fusion representation vector is input into the classifier-based production scheduling optimization module to obtain the optimization result, the equipment utilization collaborative interaction compensation fusion representation vector is optimized, specifically including: determining the equipment utilization collaborative interaction compensation fusion association response matrix and the equipment utilization collaborative interaction compensation fusion distance response matrix based on the square root of the association value of the eigenvalue of the equipment utilization collaborative interaction compensation fusion representation vector and the L2 distance value, that is: ;in, and They represent the first The eigenvalues ​​and eigenvalues, represents the equipment utilization rate collaborative interaction compensation fusion representation vector, represents the set of real numbers, represents the length of the equipment utilization collaborative interaction compensation fusion representation vector, Represents the equipment utilization rate collaborative interaction compensation fusion correlation response matrix The eigenvalues ​​of the positions, Represents the equipment utilization rate in the collaborative interaction compensation fusion distance response matrix The eigenvalue of the location.

[0055] The equipment utilization collaborative interaction compensation fusion representation vector is matrix-multiplied with the equipment utilization collaborative interaction compensation fusion association response matrix to obtain an equipment utilization collaborative interaction compensation fusion association response vector.

[0056] The equipment utilization collaborative interaction compensation fusion distance response matrix is ​​matrix-multiplied with the transposed vector of the equipment utilization collaborative interaction compensation fusion representation vector to obtain the equipment utilization collaborative interaction compensation fusion distance response vector.

[0057] After point multiplication of the equipment utilization collaborative interaction compensation fusion association response matrix and the equipment utilization collaborative interaction compensation fusion distance response matrix, matrix multiplication is performed with the transposed vector of the equipment utilization collaborative interaction compensation fusion representation vector to obtain the equipment utilization collaborative interaction compensation fusion bias vector.

[0058] The equipment utilization collaborative interaction compensation fusion associated response vector, the equipment utilization collaborative interaction compensation fusion distance response vector and the equipment utilization collaborative interaction compensation fusion bias vector are added to obtain an optimized equipment utilization collaborative interaction compensation fusion representation vector.

[0059] Here, the optimized device utilization synergistic interaction compensation fusion representation vector It is expressed as: ;in, ,and : ;in, represents the equipment utilization collaborative interaction compensation fusion correlation response matrix, represents the equipment utilization collaborative interaction compensation fusion distance response matrix, represents the equipment utilization rate collaborative interaction compensation fusion representation vector, represents the set of real numbers, represents the length of the equipment utilization collaborative interaction compensation fusion representation vector, represents matrix multiplication, It means point multiplication by position. Indicates adding by position point. represents the transpose of a vector, represents the equipment utilization collaborative interaction compensation fusion associated response vector, represents the equipment utilization rate collaborative interaction compensation fusion distance response vector, represents the equipment utilization cooperative interaction compensation fusion logic bias vector, The device utilization synergy interaction compensation fusion representation vector representing optimization.

[0060] That is, by using the equipment utilization collaborative interaction compensation fusion representation vector as its statistical reference-free distribution response framework based on the self-correlation matrix and the self-distance matrix, and constructing the retrieval-enhanced reverse response of the equipment utilization collaborative interaction compensation fusion representation vector to avoid simple repetition of feature distribution, and by ensuring the intrinsic mapping logic of the equipment utilization collaborative interaction compensation fusion representation vector based on the retrieval-response context to avoid its surface combination mapping, so as to achieve the semantic logic dependency mapping of the equipment utilization collaborative interaction compensation fusion representation vector while maintaining the intuitive response correlation, thereby improving the accuracy of the optimization result obtained by the equipment utilization collaborative interaction compensation fusion representation vector input into the classifier-based production scheduling optimization module. In this way, the production scheduling and dispatching of the processing process can be realized in a more intelligent way, thereby ensuring the reliability of the production process and the scientific nature of the decision.

[0061] Optionally, in another embodiment of the present application, the optimization solver black box optimization framework can also be used to optimize the production scheduling mode of the equipment utilization collaborative interaction compensation fusion representation vector to determine the optimization result, wherein the algorithm framework adopts Bayesian optimization based on Gaussian regression process, and can obtain an approximate solution to the complex objective function with fewer evaluation times. The software adopts advanced black box optimization technology, which can optimize various industrial production problems without data modeling, greatly promoting enterprises to reduce costs and increase efficiency.

[0062] The basic optimization process of the optimization solver includes: the proxy model is a machine learning model trained by data in the task database, which is used to approximate the simulation process; the acquisition function is used to provide the search direction; for sequence optimization, the local search mainly uses the neighborhood search algorithm. Since it takes a lot of time to simulate a target, a proxy model is used to approximate the simulation. After each simulation generates a target, the target and the corresponding solution are updated to the database, and then the proxy model is updated. The local search can solve a new solution with a better possibility and the largest row according to the updated proxy model. The new solution is simulated to obtain the real target. In this way, it is continuously iterated, and good optimization results can be obtained with fewer iterations.

[0063] In summary, the intelligent production scheduling and dispatching system based on digital twins according to the embodiment of the present application is explained, which arranges the set of pending orders into two pending order sequences by adopting different sorting strategies, and then uses the resource-time matrix to perform scheduling simulation on the two pending order sequences respectively, and generates corresponding simulation logs by simulating the production process under different scheduling methods, and then determines the optimized scheduling method based on the comparison between the simulation logs for corresponding scheduling and management. In this way, potential problems can be discovered in advance through virtual simulation in digital twin technology, the scheduling method can be optimized in time, and the production plan can be adjusted in time to avoid losses in actual production.

[0064] Figure 5 Schematic flow chart of the intelligent production scheduling and dispatching method based on digital twins in the embodiment of the present application. Figure 5 As shown, the intelligent production scheduling and dispatching method based on digital twins includes: S1, obtaining a set of orders to be scheduled; S2, arranging the set of orders to be scheduled in a first manner to obtain a first sequence of orders to be scheduled and arranging the set of orders to be scheduled in a second manner to obtain a second sequence of orders to be scheduled; S3, setting the scheduling time and scheduling the first sequence of orders to be scheduled and the second sequence of orders to be scheduled based on the resource-time matrix to obtain a first emission mode simulation log and a second emission mode simulation log; S4, displaying the first emission mode simulation log and the second emission mode simulation log; S5, determining whether to arrange the set of orders to be scheduled in the first manner or the second manner based on a comparison between the first emission mode simulation log and the second emission mode simulation log.

[0065] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned intelligent production scheduling and dispatching method based on digital twins have been referred to above. Figures 1 to 4It has been introduced in detail in the description of the digital twin-based intelligent production scheduling and dispatching system, and therefore, its repeated description will be omitted.

[0066] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0067] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the module division is only a logical function division, and there may be other division methods in actual implementation. The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0068] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0069] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference to a figure in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An intelligent production scheduling and dispatching system based on digital twins, characterized in that: include: A module for obtaining a set of orders to be scheduled, used to obtain a set of orders to be scheduled; A module for arranging a set of orders to be arranged, configured to arrange the set of orders to be arranged in a first manner to obtain a first sequence of orders to be arranged and to arrange the set of orders to be arranged in a second manner to obtain a second sequence of orders to be arranged; A production scheduling module for a sequence of pending orders, used for setting a production scheduling time and scheduling the sequence of the first pending orders and the sequence of the second pending orders based on a resource-time matrix to obtain a first emission mode simulation log and a second emission mode simulation log; An emission mode simulation log display module, used for displaying the first emission mode simulation log and the second emission mode simulation log; The emission mode simulation log comparison decision module is used to determine whether to arrange the set of to-be-arranged orders in the first mode or the second mode based on the comparison between the first emission mode simulation log and the second emission mode simulation log.

2. The intelligent production scheduling and dispatching system based on digital twin according to claim 1 is characterized in that: The production scheduling module for the sequence of pending orders includes: a resource-time matrix initialization unit, used to initialize the resource-time matrix, wherein the horizontal axis of the resource-time matrix represents the resources required for production, and the vertical axis of the resource-time matrix represents the time axis; an order information extraction unit, used to extract the order information of the current order from the sequence of the first pending orders; an order detailed information parsing unit, used to extract the bill of materials, processes, equipment and processing time of each process required for the current order from the order information of the current order; an order process scheduling unit, used to find the earliest start time of the earliest process that satisfies the current order in the resource-time matrix based on the processing sequence of the processes of the current order, record the processing time of the earliest process, and occupy this period of time in the resource-time matrix.

3. The intelligent production scheduling and dispatching system based on digital twin according to claim 2 is characterized in that: The emission mode simulation log comparison decision module includes: a first equipment utilization determination unit, which is used to determine the utilization of each mechanical equipment based on the first emission mode simulation log to obtain a sequence distribution of the first equipment utilization; a second equipment utilization determination unit, which is used to determine the utilization of each mechanical equipment based on the second emission mode simulation log to obtain a sequence distribution of the second equipment utilization; an equipment utilization sequence encoding unit, which is used to sequence encode the sequence distribution of the first equipment utilization and the sequence distribution of the second equipment utilization respectively to obtain an implicit correlation feature vector between the first equipment utilization and an implicit correlation feature vector between the second equipment utilization; an equipment utilization collaborative interaction compensation fusion unit, which is used to perform feature interaction fusion based on common features on the implicit correlation feature vector between the first equipment utilization and the implicit correlation feature vector between the second equipment utilization to obtain an equipment utilization collaborative interaction compensation fusion representation; a production scheduling optimization unit, which is used to optimize the production scheduling based on the equipment utilization collaborative interaction compensation fusion representation to determine an optimization result, and the optimization result is used to indicate whether to adopt the first mode or the second mode.

4. The intelligent production scheduling and dispatching system based on digital twin according to claim 3 is characterized in that: The equipment utilization sequence encoding unit is used to: input the sequence distribution of the first equipment utilization and the sequence distribution of the second equipment utilization into a sequence encoder based on a bidirectional LSTM model to obtain an implicit correlation feature vector between the first equipment utilizations and an implicit correlation feature vector between the second equipment utilizations.

5. The intelligent production scheduling and dispatching system based on digital twin according to claim 4 is characterized in that: The equipment utilization collaborative interaction compensation fusion unit includes: a common feature extraction secondary subunit, which is used to input the implicit correlation feature vector between the first equipment utilizations and the implicit correlation feature vector between the second equipment utilizations into a common feature extraction network to obtain a common feature representation vector between equipment utilization features; an equipment utilization feature probabilistic processing secondary subunit, which is used to input the implicit correlation feature vector between the first equipment utilizations, the implicit correlation feature vector between the second equipment utilizations and the common feature representation vector between the equipment utilization features into a vector probabilization unit based on a Sigmoid function to obtain a probabilistic first equipment utilization implicit correlation feature vector, a probabilistic second equipment utilization implicit correlation feature vector and a probabilistic common feature representation vector between equipment utilization features; a first information fine-grained compensation calculation secondary subunit, which is used to calculate the first equipment utilization information fine-grained compensation vector of the probabilistic first equipment utilization implicit correlation feature vector relative to the probabilistic common feature representation vector between equipment utilization features; and a second information fine-grained processing secondary subunit. A compensation calculation secondary subunit is used to calculate the second device utilization information fine-grained compensation vector of the implicit correlation feature vector between the probabilistic second device utilizations relative to the common feature representation vector between the probabilistic device utilization features; a first fine-grained compensation secondary subunit is used to input the first device utilization information fine-grained compensation vector and the first device utilization implicit correlation feature vector into the fine-grained compensation module to obtain the first device utilization fine-grained feature compensation vector; a second fine-grained compensation secondary subunit is used to input the second device utilization information fine-grained compensation vector and the second device utilization implicit correlation feature vector into the fine-grained compensation module to obtain the second device utilization fine-grained feature compensation vector; a vector cascade secondary subunit is used to cascade the first device utilization fine-grained feature compensation vector, the second device utilization fine-grained feature compensation vector and the common feature representation vector between the device utilization features to obtain the device utilization collaborative interaction compensation fusion representation vector as the device utilization collaborative interaction compensation fusion representation.

6. The intelligent production scheduling and dispatching system based on digital twin according to claim 5 is characterized in that: The common feature extraction secondary subunit is used to: calculate the positional sum between the implicit correlation feature vector between the first device utilizations and the implicit correlation feature vector between the second device utilizations to obtain a device utilization correlation fusion feature vector; multiply the device utilization correlation fusion feature vector with the modulation weight matrix and then add it with the modulation bias vector in position, and input the obtained modulated device utilization correlation fusion feature vector into a tanh function for activation processing to obtain a common feature representation vector between the device utilization features.

7. The intelligent production scheduling and dispatching system based on digital twin according to claim 6 is characterized in that: The first information fine-grained compensation calculation secondary subunit is used to: calculate the positional division between the implicit correlation feature vector between the probabilistic first device utilizations and the common feature representation vector between the probabilistic device utilization features to obtain the first device utilization common feature interaction feature vector; After calculating the logarithmic function value with base 2 of the absolute value of the feature value at each position in the common feature interaction feature vector of the first device utilization, the obtained first device utilization common feature interaction logarithmic representation vector and the probabilistic first device utilization implicit correlation feature vector are multiplied by position to obtain the first device utilization information optimization representation vector; after calculating the natural exponential function value with base e as the natural constant and the feature value at each position in the first device utilization information optimization representation vector as the exponential power, the obtained feature vector is input into the softmax function for processing to obtain the first device utilization information fine-grained compensation vector.

8. The intelligent production scheduling and dispatching system based on digital twin according to claim 7 is characterized in that: The first fine-grained compensation secondary subunit is used to calculate the first device utilization information fine-grained compensation vector and the first device utilization implicit association feature vector by point-by-point multiplication to obtain the first device utilization fine-grained feature compensation vector.

9. The intelligent production scheduling and dispatching system based on digital twin according to claim 8 is characterized in that: The production scheduling optimization unit is used to: input the equipment utilization collaborative interaction compensation fusion representation vector into the classifier-based production scheduling optimization module to obtain an optimization result, and the optimization result is used to indicate whether the first method or the second method is adopted.

10. An intelligent production scheduling and dispatching method based on digital twins, characterized in that: include: Get the collection of pending orders; Arranging the set of to-be-arranged orders in a first manner to obtain a first sequence of to-be-arranged orders and arranging the set of to-be-arranged orders in a second manner to obtain a second sequence of to-be-arranged orders; Set the scheduling time and schedule the first sequence of orders to be scheduled and the second sequence of orders to be scheduled based on the resource-time matrix to obtain a first emission mode simulation log and a second emission mode simulation log; display the first emission mode simulation log and the second emission mode simulation log; based on the comparison between the first emission mode simulation log and the second emission mode simulation log, determine whether to use the first method or the second method to arrange the set of orders to be scheduled.

Images