Workshop equipment resource optimization method based on digital twinning

Abstract

The invention relates to the field of intelligent manufacturing, in particular to a digital twinning-based workshop equipment resource optimization method, which comprises the following steps of S1, constructing a digital twinning model of a weaving workshop; s2, constructing a mathematical model of a weaving workshop; s3, designing a two-stage optimization method based on the digital twinborn model, the optimization method including beam merging and resource optimization based on the merged beams, and solving the workshop mathematical model to obtain an optimal production scheduling scheme; s4, a visual platform is built in combination with the digital twin model, the visual platform is used for displaying the operation state, the production parameters and the environment data of the machines in the weaving workshop, and the data and the digital twin model are synchronized; according to the invention, real-time modeling is carried out on equipment, a production process and energy consumption in a workshop through a digital twinning technology, a virtual workshop model is constructed, and various production data in the workshop are comprehensively reflected.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing, and in particular to a workshop equipment resource optimization method based on digital twins. Background Art

[0002] Under the current background of intelligent manufacturing, the textile industry is undergoing a digital and intelligent transformation. With the increasingly fierce market competition, the production model of textile enterprises has also shifted from the traditional single-variety mass production to a multi-variety small-batch, customized production method. Although this change has improved flexibility and market responsiveness, it has also brought about a higher complexity of production scheduling. At the same time, the concept of green manufacturing has become a hot topic in recent years. As a major energy consumer, the textile industry faces the challenge of how to reduce energy consumption and environmental pollution while ensuring production efficiency and quality in the weaving, dyeing and finishing, and textile machinery and equipment operation.

[0003] Traditional textile production processes usually involve multiple links, and these links are interdependent, forming a complex production process. In the actual production of the weaving link, the weaving shaft needs to be reasonably allocated according to the production plan and the characteristics of the machine. The type, performance, load conditions, and different requirements of the production tasks of the machine all need to be comprehensively considered in the scheduling process in order to maximize production efficiency and equipment utilization. However, traditional production scheduling methods often rely on manual experience and rules, and it is difficult to effectively cope with the changing production environment, resulting in low production efficiency, unreasonable allocation of equipment resources, and high energy consumption.

[0004] Under this traditional production model, the production management process of the weaving workshop lacks real-time data and dynamic feedback, the equipment and production links lack sufficient coordination and data support, the equipment resource allocation is unreasonable, and the production scheduling is difficult to flexibly respond to market changes. More importantly, the energy consumption of the equipment is difficult to be effectively monitored and optimized, and unnecessary shutdowns and no-load operations often occur during the production process, resulting in energy waste and low efficiency. Summary of the invention

[0005] The purpose of the present invention is to provide a workshop equipment resource optimization method based on digital twins to improve production efficiency.

[0006] In order to achieve the above object, the present invention adopts such technical solution: A workshop equipment resource optimization method based on digital twins includes the following steps: S1: Build a digital twin model of the weaving workshop, which obtains order information, weaving shaft information of each weaving shaft, and production information of each machine in real time; The weaving beam information includes the total length of production, the type of weaving beam, the winding volume of the weaving beam, the winding density of the weaving beam, the total number of warp yarns, the warp yarn density, the warp yarn sizing rate, the initial length in the unprocessed state, the total length of the order production, the addition rate, the release rate, the fabric shrinkage rate, the length of the additional yarn, the weaving beam sequence and the delivery time; The production information includes processing time, preparation time, processing energy consumption coefficient, no-load energy consumption coefficient and start-stop energy consumption; S2: Constructing a workshop mathematical model based on the acquired order information and production information, wherein the workshop mathematical model minimizes energy consumption. and minimize the number of axis changes on the same machine As the optimization target, the workshop mathematical model is expressed by the following formula: ; ; in, is the processing energy consumption, is the no-load energy consumption, For start-stop energy consumption, Indicates the machine No. root beam type, m is the number of machines, n is the number of beams; Set the constraints as: (1); (2); (3); , , (4); , , (5); Among them, formula (1) means that for each machine except the first machine, if the current machine start-stop energy consumption is less than the no-load energy consumption during the current weaving beam preparation, the machine on / off strategy is selected, otherwise the machine no-load standby preparation is selected; Formula (2) indicates that the preparation time plus the processing time of the machine must be less than or equal to the end time of the weaving beam; Formula (3) indicates that for weaving beams i and i+1 to be processed on the same machine, the preparation time of weaving beam i+1 cannot be earlier than the completion time of weaving beam i; Formula (4) indicates that the processing time, processing energy consumption, and preparation time of efficient weaving beams and machines are all less than those of inefficient and averagely efficient ones; Formula (5) indicates that the processing time, processing energy consumption, and preparation time of the inefficient weaving beam and machine are greater than those of the average and high efficiency ones; S3: Based on the digital twin model and according to the production characteristics of the weaving workshop, a two-stage optimization method is designed, wherein the optimization method includes merging weaving shafts and optimizing resources based on the merged weaving shafts, using an improved PSO algorithm for resource optimization, solving the mathematical model of the workshop, and obtaining the optimal production scheduling solution; The weaving shaft merging is to merge weaving shafts with the same warp yarn type and process under the premise of ensuring the quality of the fabric, and the maximum winding length of the weaving shaft is calculated by the following formula , the actual winding length of the weaving shaft And the number of weaving beams : ; ; ; in, is the winding volume of the loom beam, Y is the winding density of the weaving beam, Z is the total number of warp yarns, W is the warp yarn density, β is the warp yarn sizing rate, is the initial length in the unprocessed state, λ are the addition and release rates, α is the fabric shrinkage rate, is the length of the extra yarn, L The total length of production for the order; S4: Build a visualization platform in combination with the digital twin model. The visualization platform is used to display the operating status, production parameters and environmental data of the machines in the weaving workshop, and synchronize these data with the digital twin model.

[0007] Preferably, in step S1, simulation software is used to construct a digital twin model of a weaving workshop, wherein the physical entities include machines and their production status, and the virtual model digitally maps the equipment operating status, order information, equipment energy consumption and production process through simulation software. The data acquisition and processing module analyzes and organizes the data acquired in real time to provide real-time support for the digital twin model.

[0008] Preferably, in step S3, the steps of using the improved PSO algorithm to optimize resources are as follows: S301: Encoding and decoding: The initial population size is p , the total length of chromosomes is set as the total number of spindles N , each gene position corresponds to a loom axis, and the loom axis varieties are expressed as J 1.J 2. J 3 ， Machine number m is an integer starting from 0. Create a position vector with a random value of 0 to 1 from the weaving axis sequence and sort it in descending order. Then, perform machine allocation operation on the sorted weaving axes, generate an initial solution set and calculate the fitness of each particle. S302: Non-dominated sorting and crowding calculation: By comparing the dominance relations between solutions, they are divided into multiple non-dominated layers, and then the crowding distance of each particle in each non-dominated layer is calculated; S303: Update the particle historical optimum and global optimum as well as the particle speed and position according to the fitness; S304: Design a local search method specifically for energy consumption, the specific steps are as follows: Get the machine with the largest total particle energy consumption after update and the corresponding weaving beam and variety; Obtain the processing time of all weaving beams on the machine with the largest total energy consumption, compare and sort them, and find the weaving beam with the shortest processing time; Delete three consecutive middle weaving shafts of different varieties from the original machine and insert them into the machine with the shortest processing time. If there are the same varieties, insert them before the weaving shafts of the same variety. If not, insert them randomly. Calculate the fitness of the new solution. S305: Elite selection: Mix the updated optimal solution with the parent solution, perform non-dominated sorting and crowding calculation, and select the next generation; S306: Determine whether the preset maximum number of iterations has been reached, if so, output the optimal solution, otherwise repeat steps S302-S306; S307: Generate an optimal production scheduling plan according to the output optimal solution, and generate a resource optimization Gantt chart according to the optimal production scheduling plan.

[0009] Preferably, in step S4, the operating status, production parameters and environmental data of the machines in the workshop are synchronized with the digital twin model in real time through sensors and Internet of Things devices.

[0010] A workshop equipment resource optimization system includes a memory and a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement any of the methods described above.

[0011] A computer-readable storage medium stores a computer program, which implements any of the above methods when executed.

[0012] A computer product comprises a computer program, which implements any of the above methods when executed by a processor.

[0013] By adopting the aforementioned design scheme, the beneficial effects of the present invention are as follows: the present application uses digital twin technology to perform real-time modeling of the equipment, production process and energy consumption in the workshop, constructs a virtual workshop model, and comprehensively reflects various production data in the workshop; establishes two optimization goals: energy consumption and the number of shaft changes for different varieties; through a two-stage optimization method, the first stage is to merge the weaving shafts, and the second stage uses an improved PSO algorithm to achieve precise control and optimization of the production process, while minimizing the waste of equipment resources and reducing energy consumption while ensuring production quality and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A flow chart of the workshop equipment resource optimization method of the present invention; Figure 2 This is a system architecture diagram of the digital twin model of the present invention; Figure 3 A flow chart of resource optimization using the improved PSO algorithm of the present invention; Figure 4 A search schematic diagram of a local search of the present invention; Figure 5 A scheduling Gantt chart of scheme 1 of a specific embodiment of the present invention; Figure 6 This is a scheduling Gantt chart of Solution 2 of a specific embodiment of the present invention. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only partial embodiments of the present invention, rather than all 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.

[0016] A workshop equipment resource optimization method based on digital twins, such as Figure 1 As shown, the following steps are included: S1: Build a digital twin model of the weaving workshop. The digital twin model obtains order information, weaving shaft information of each weaving shaft, and production information of each machine in real time; Weaving beam information includes total production length, weaving beam type, weaving beam winding volume, weaving beam winding density, total number of warp yarns, warp yarn density, warp yarn sizing rate, initial length in unprocessed state, total order production length, addition rate, release rate, fabric shrinkage rate, length of additional yarn, weaving beam sequence and delivery time; Production information includes processing time, preparation time, processing energy consumption coefficient, no-load energy consumption coefficient, and start-stop energy consumption; The digital twin model of a textile workshop uses advanced technologies such as sensors, the Internet of Things, big data, and artificial intelligence to build a real-time digital model of the physical entity, simulate the behavior and state of the physical workshop in the virtual space, and achieve real-time data interaction and synchronization. The system is mainly composed of five core modules, including the physical workshop, virtual model, twin data, service system, and the interconnection architecture of data and information. The following describes the functions and characteristics of each module of the digital twin system of a textile workshop. The architecture of the digital twin model of a textile workshop is as follows: Figure 2 As shown in the figure, the specific contents of each module of the weaving workshop are as follows: Physical entity of weaving workshop: Physical entity refers to various types of actual production equipment and facilities in the weaving workshop, such as double-jet flat machines, single-jet multi-arm machines, cam machines and other weaving equipment. In addition, it also includes a variety of sensors arranged in the equipment to collect key production information such as equipment operating status, processing signals, energy consumption data, etc. Through the sensor network and information transmission module, the weaving workshop can monitor the equipment status in real time, realize information feedback and command execution, and provide data support and real-time update capabilities for the virtual model.

[0017] Weaving workshop virtual model: The virtual model is a digital representation based on the production data and dynamic information of the weaving workshop. The virtual model can not only accurately reflect the operating status of the physical weaving workshop, but also form a comprehensive digital representation of production by integrating multiple modeling technologies. Specifically, the virtual model includes the following four sub-models: Three-dimensional visualization model: Based on the equipment and layout of the physical weaving workshop, a highly simulated three-dimensional model is constructed through simulation software to achieve visual management of the weaving workshop.

[0018] Behavioral model: describes the operational logic and behavioral characteristics of the weaving production process, and depicts the operating mechanism of the weaving production link.

[0019] Physical model: defines the physical properties of the machine and process, reflecting the machine performance and production capacity.

[0020] Rule model: A set of rules extracted based on production constraints and operating rules, used to guide weaving workshop scheduling and production optimization.

[0021] Through the fusion of multiple models, the virtual model can dynamically map the actual production status of the physical weaving workshop and provide decision support for the management and optimization of the weaving workshop.

[0022] Twin data: Twin data is the core link between the physical weaving workshop, virtual model and service system, including real-time sensor data from weaving workshop equipment, data generated by virtual model simulation and service data derived from the service system. Twin data uses multi-fusion technology to unify the timeliness and diversity of data on one platform, providing a reliable data foundation for monitoring the operating status of the weaving workshop, diagnosing equipment failures and optimizing production scheduling.

[0023] Service system: The service system builds a multifunctional support module through in-depth analysis and mining of the twin data of the weaving workshop. This module can synchronize the operating status of the physical workshop in real time, and provide functions such as equipment health and energy consumption monitoring, fault prediction and diagnosis, and production scheduling optimization. In addition, based on intelligent algorithms and dynamic data analysis technology, the service system effectively improves the resource utilization efficiency, operation stability, and production flexibility of the workshop, providing a key guarantee for achieving efficient production.

[0024] Data and information interconnection architecture: The efficient connection of data and information is the technical basis for the operation of the digital twin system of the weaving workshop. The physical weaving workshop collects real-time operation data of production equipment through sensors and industrial networks, and transmits it to the central data center for processing using standard communication protocols. The virtual model is data-driven through interface technology, so that the digital twin can dynamically respond to changes in the state of the physical workshop and ensure synchronous operation of the virtual and real. By building a unified interconnection architecture, the digital twin system can realize real-time data flow and functional coordination, laying the foundation for the intelligent operation of the weaving workshop.

[0025] In this embodiment, simulation software is used to construct a digital twin model of a weaving workshop, in which the physical entities include machines and their production status, and the virtual model digitally maps the equipment operating status, order information, equipment energy consumption and production process through simulation software. The data acquisition and processing module analyzes and organizes the data acquired in real time to provide real-time support for the digital twin model.

[0026] The analysis performed by the processing module based on the collected data includes: Equipment operation status analysis: Analyze equipment status, including startup, standby, and shutdown, and monitor whether the equipment is in a normal state and whether there are any faults.

[0027] Equipment energy consumption analysis: Analyze the energy consumption of equipment when producing different weaving beams and identify equipment with higher energy consumption.

[0028] The collected data is denoised and outliers and invalid data are removed to ensure data quality.

[0029] Weaving shaft information analysis: Analyze the production progress, delivery date, process parameters of different weaving shafts, and the production order number of each weaving shaft.

[0030] In weaving production, order processing and execution is a complex and critical link. Before production, the order information is first analyzed and designed to determine the total number of warp yarns and other production requirements required for each order. According to the specifications of the order, the yarn is wound onto the warp beam through the warping process. After warping, the warp yarn on the warp beam is sized to enhance the strength of the yarn and reduce the breakage rate to ensure the smooth progress of the subsequent weaving process. The sized warp yarn is then wound onto the weaving beam to make a weaving beam for weaving.

[0031] Generate an array based on the total length of the production obtained R={r 1 ,r 2 ,...,r n } ; Produce arrays according to the obtained weaving beam varieties V={v 1 ,v 2 ,...,v n } ; Produce an array based on the obtained delivery time D={d 1 ,d 2 ,...d n } ; Generate an array based on the total number of warp yarns obtained T={t 1 ,t 2 ,...,t n } ; Wherein, n represents the number of weaving beams; Generate a matrix based on the processing time obtained by the machine ; Generate a matrix based on the preparation time obtained by the machine ; Generate a matrix based on the obtained processing energy consumption coefficient ; Processing energy consumption ; Generate an array based on the obtained no-load energy consumption coefficient ; No-load energy consumption ; Generate an array based on the acquired start-stop energy consumption ,in, m Indicates the number of machines; In order to cope with the small batch production of multiple varieties of market orders, improve production efficiency and reduce the frequency of equipment switching, weaving shafts with the same process varieties are merged. After entering the weaving stage, the characteristics of the weaving shafts and the choice of machines have a significant impact on production efficiency. The combination of different varieties of weaving shafts and different types of machines determines the level of production efficiency, as shown in Table 1 below: Table 1 Efficiency of different types of machines and different types of weaving beam combinations

[0032] S2: Due to the complicated production process and variety of weaving workshops, the production tasks are heavy and the production process is intensive and complex. In this process, due to the imperfect production process and the imprecise management, various resources cannot be reasonably optimized, which leads to frequent waste of resources. At the same time, the long-term operation and high-load operation of many production equipment and some unreasonable production arrangements inevitably bring about energy consumption problems. In order to achieve a balance between various needs, a workshop mathematical model is constructed based on the acquired order information and production information. The workshop mathematical model is based on minimizing energy consumption. and minimize the number of axis changes on the same machine As the optimization target, the workshop mathematical model is expressed by the following formula: ; ; in, is the processing energy consumption, is the no-load energy consumption, For start-stop energy consumption, Indicates the machine No. The root weaving beam type, m is the number of machines, and n is the number of weaving beams.

[0033] Set the constraints as: (1); (2); (3); , , (4); , , (5); Among them, formula (1) means that for each machine except the first machine, if the current machine start-stop energy consumption is less than the no-load energy consumption during the current weaving beam preparation, the machine on / off strategy is selected, otherwise the machine no-load standby preparation is selected; Formula (2) indicates that the preparation time plus the processing time of the machine must be less than or equal to the end time of the weaving beam; Formula (3) indicates that for weaving beams i and i+1 to be processed on the same machine, the preparation time of weaving beam i+1 cannot be earlier than the completion time of weaving beam i; Formula (4) indicates that the processing time, processing energy consumption, and preparation time of efficient weaving beams and machines are all less than those of inefficient and averagely efficient ones; Formula (5) indicates that the processing time, processing energy consumption, and preparation time of the inefficient weaving beam and machine are greater than those of the average and high efficiency ones; S3: Based on the digital twin model and according to the production characteristics of the textile workshop, a two-stage optimization method is designed. The optimization method includes weaving shaft merging and resource optimization based on the merged weaving shafts, such as Figure 3 As shown, the improved PSO algorithm is used to optimize resources, solve the mathematical model of the workshop, and obtain the optimal production scheduling plan; In this embodiment, the optimal generation scheduling plan includes the production and processing conditions and processing sequence of each weaving shaft and each machine.

[0034] Weaving beam merging is to merge weaving beams with the same warp yarn variety and process under the premise of ensuring fabric quality, that is, to merge the warp yarns on multiple warp beams of different orders in the weaving workshop into a smaller number of weaving beams. The warp yarns on multiple warp beams of different orders in the textile workshop are merged into the same weaving beam, and the maximum winding length of the weaving beam is calculated using the following formula , the actual winding length of the weaving shaft And the number of weaving beams : ; ; ; in, is the winding volume of the loom beam, Y is the winding density of the weaving beam, Z is the total number of warp yarns, W is the warp yarn density, β is the warp yarn sizing rate, is the initial length in the unprocessed state, λ are the addition and release rates, α is the fabric shrinkage rate, is the length of the extra yarn, L The total length of production for the order; The steps of using the improved PSO algorithm for resource optimization are as follows: S301: Encoding and decoding: The initial population size is p , the total length of chromosomes is set as the total number of spindles N , each gene position corresponds to a loom axis, and the loom axis varieties are expressed as J 1. J 2. J 3 ， Machine number mis an integer starting from 0. Create a position vector with a random value of 0 to 1 from the weaving axis sequence and sort it in descending order. Then, perform machine allocation operation on the sorted weaving axes, generate an initial solution set and calculate the fitness of each particle. S302: Non-dominated sorting and crowding calculation: By comparing the dominance relations between solutions, they are divided into multiple non-dominated layers, and then the crowding distance of each particle in each non-dominated layer is calculated; S303: Update operation: update the particle historical optimum and global optimum as well as the particle speed and position according to the fitness; S304: Design a local search method specifically for energy consumption, such as Figure 4 As shown, the specific steps are as follows: Get the machine with the largest total particle energy consumption after update and the corresponding weaving beam and variety; Get the processing time of all weaving beams on the machine with the largest total energy consumption, sort them by comparison and find the order with the shortest processing time; Delete three consecutive middle weaving shafts of different varieties from the original machine and insert them into the machine with the shortest processing time. If there are orders of the same variety, insert them before them. If not, insert them randomly. Calculate the fitness of the new solution. S305: Elite selection: Mix the updated optimal solution with the parent solution, perform non-dominated sorting and crowding calculation, and select the next generation; S306: Determine whether the preset maximum number of iterations has been reached, if so, output the optimal solution, otherwise repeat steps S302-S306; S307: Generate an optimal production scheduling plan based on the output optimal solution, and generate a resource optimization Gantt chart based on the optimal production scheduling plan. The purpose of generating the resource optimization Gantt chart is to better display the production status of each machine, such as Figure 5 and Figure 6 shown.

[0035] This embodiment provides the following example to further illustrate the steps of using the improved PSO algorithm to perform resource optimization.

[0036] In this example, there are 10 orders in total, and the order information is shown in Table 2.

[0037] Table 2 Order information

[0038] The weaving shafts are now merged and optimized, and the varieties with consistent processes are merged. The information of the merged weaving shafts is shown in Table 3, where PE=[1,1,1,1,1], SSE=[5,5,5,5,5].

[0039] Table 3 Weaving beam information

[0040] Processing time , preparation time , processing energy consumption coefficient .

[0041] The improved PSO algorithm (Scheme 1) and the unimproved PSO algorithm (Scheme 2) are used to optimize equipment resources. The objective function values ​​of the two equipment resource optimization schemes are compared as shown in Table 4. Finally, the two scheduling Gantt charts are generated as shown in Figure 5 and Figure 6 As shown, green represents the weaving beam, blue represents the preparation time, the minimum completion time of Scheme 1 is 45, and the minimum completion time of Scheme 2 is 57.

[0042] Table 4 Objective functions of the comparison schemes

[0043] S4: Build a visualization platform in combination with the digital twin model. The visualization platform is used to display the operating status, production parameters and environmental data of the machines in the weaving workshop, and synchronize these data with the digital twin model.

[0044] Through sensors and IoT devices, the visualization platform can collect the operating status, production parameters and environmental data of the equipment in the workshop in real time, and synchronize these data with the digital twin model. Combining big data analysis and artificial intelligence technology, the visualization platform can identify potential equipment failures and issue early warnings, dynamically adjust process parameters to optimize production efficiency, and monitor production scheduling to propose energy-saving solutions in real time based on energy consumption. The visualization platform can also convert the analysis results into specific control instructions, and realize closed-loop feedback adjustment of actual equipment through industrial control systems. This mechanism not only improves the production efficiency and equipment stability of the workshop, but also ensures the efficient, green and intelligent operation of the production process.

[0045] The visualization platform provides comprehensive data support and visualization platform for factory management, which can better monitor production conditions, improve production efficiency, and reduce production risks. Through digital means, it helps enterprises achieve intelligent production.

[0046] This embodiment also provides a system for implementing the above method.

[0047] A workshop equipment resource optimization system includes a memory and a processor, and a computer program stored in the memory, and the processor executes the computer program to implement any of the methods described above.

[0048] This embodiment also provides a storage medium storing a computer program capable of implementing the above method.

[0049] A computer-readable storage medium stores a computer program, which implements any of the above methods when executed.

[0050] This embodiment also provides a computer product capable of implementing the above method.

[0051] A computer product comprises a computer program, which implements any of the above methods when executed by a processor.

[0052] To sum up, this application combines digital twin technology with equipment resource optimization, which not only solves the problems of energy waste and unreasonable resource allocation under traditional methods, but also provides accurate decision-making support for production scheduling, so that each link in the production process can be optimized and adjusted according to real-time data, and ultimately realize the green, intelligent and efficient production process.

[0053] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A workshop equipment resource optimization method based on digital twins, characterized by: The steps include: S1: Build a digital twin model of the weaving workshop, which obtains order information, weaving shaft information of each weaving shaft, and production information of each machine in real time; The weaving beam information includes the total length of production, the type of weaving beam, the total number of warp yarns, the winding volume of the weaving beam, the winding density of the weaving beam, the warp yarn density, the warp yarn sizing rate, the initial length in the unprocessed state, the total length of the order production, the addition rate, the release rate, the fabric shrinkage rate, the length of the additional yarn, the weaving beam sequence and the delivery time; The production information includes processing time, preparation time, processing energy consumption coefficient, no-load energy consumption coefficient and start-stop energy consumption; S2: Constructing a workshop mathematical model based on the acquired order information and production information, wherein the workshop mathematical model minimizes energy consumption. and minimize the number of axis changes on the same machine As the optimization target, the workshop mathematical model is expressed by the following formula: ； ； in, is the processing energy consumption, is the no-load energy consumption, is the start-stop energy consumption, Indicates the machine No. root beam type, m is the number of machines, n is the number of beams; Set the constraints as: (1)； (2)； (3)； ， , (4)； ， , (5)； Among them, formula (1) means that for each machine except the first machine, if the current machine start-stop energy consumption is less than the no-load energy consumption during the current weaving beam preparation, the machine on / off strategy is selected, otherwise the machine no-load standby preparation is selected; Formula (2) indicates that the preparation time plus the processing time of the machine must be less than or equal to the end time of the weaving beam; Formula (3) indicates that for weaving beams i and i+1 to be processed on the same machine, the preparation time of weaving beam i+1 cannot be earlier than the completion time of weaving beam i; Formula (4) indicates that the processing time, processing energy consumption, and preparation time of efficient weaving beams and machines are all less than those of inefficient and averagely efficient ones; Formula (5) indicates that the processing time, processing energy consumption, and preparation time of the inefficient weaving beam and machine are greater than those of the average and high efficiency ones; S3: Based on the digital twin model and according to the production characteristics of the weaving workshop, a two-stage optimization method is designed, wherein the optimization method includes merging weaving shafts and optimizing resources based on the merged weaving shafts, using an improved PSO algorithm for resource optimization, solving the mathematical model of the workshop, and obtaining the optimal production scheduling solution; The weaving shaft merging is to merge weaving shafts with the same warp yarn type and process under the premise of ensuring the quality of the fabric, and the maximum winding length of the weaving shaft is calculated by the following formula , the actual winding length of the weaving shaft And the number of weaving beams : ； ； ； in, is the winding volume of the loom beam, Y is the winding density of the weaving beam, Z is the total number of warp yarns, W is the warp yarn density, β is the warp yarn sizing rate, is the initial length in the unprocessed state, λ are the addition and release rates, α is the fabric shrinkage rate, is the length of the extra yarn, L The total length of production for the order; S4: Build a visualization platform in combination with the digital twin model. The visualization platform is used to display the operating status, production parameters and environmental data of the machines in the weaving workshop, and synchronize these data with the digital twin model.

2. A workshop equipment resource optimization method based on digital twins as claimed in claim 1, characterized in that: In step S1, simulation software is used to build a digital twin model of the weaving workshop, in which the physical entities include machines and their production status, and the virtual model digitally maps the equipment operating status, order information, equipment energy consumption and production process through simulation software. The data acquisition and processing module analyzes and organizes the real-time acquired data to provide real-time support for the digital twin model.

3. A workshop equipment resource optimization method based on digital twins as claimed in claim 1, characterized in that: In step S3, the steps of using the improved PSO algorithm to optimize resources are as follows: S301: Encoding and decoding: The initial population size is p , the total length of chromosomes is set as the total number of spindles N , each gene position corresponds to a weaving axis, and the weaving axis varieties are expressed as J 1. J 2. J 3 ， Machine number m is an integer starting from 0. Create a position vector with a random value of 0 to 1 from the weaving axis sequence and sort it in descending order. Then, perform machine allocation operation on the sorted weaving axes, generate an initial solution set and calculate the fitness of each particle. S302: Non-dominated sorting and crowding calculation: By comparing the dominance relations between solutions, they are divided into multiple non-dominated layers, and then the crowding distance of each particle in each non-dominated layer is calculated; S303: Update the particle historical optimum and global optimum as well as the particle speed and position according to the fitness; S304: Design a local search method specifically for energy consumption, the specific steps are as follows: Get the machine with the largest total particle energy consumption after update and the corresponding weaving beam and variety; Obtain the processing time of all weaving beams on the machine with the largest total energy consumption, compare and sort them, and find the weaving beam with the shortest processing time; Delete three consecutive middle weaving shafts of different varieties from the original machine and insert them into the machine with the shortest processing time. If there are the same varieties, insert them before the weaving shafts of the same variety. If not, insert them randomly. Calculate the fitness of the new solution. S305: Elite selection: Mix the updated optimal solution with the parent solution, perform non-dominated sorting and crowding calculation, and select the next generation; S306: Determine whether the preset maximum number of iterations has been reached, if so, output the optimal solution, otherwise repeat steps S302-S306; S307: Generate an optimal production scheduling plan according to the output optimal solution, and generate a resource optimization Gantt chart according to the optimal production scheduling plan.

4. A workshop equipment resource optimization method based on digital twins as claimed in claim 1, characterized in that: In step S4, the operating status, production parameters and environmental data of the machines in the workshop are synchronized with the digital twin model in real time through sensors and IoT devices.

5. A workshop equipment resource optimization system, comprising a memory and a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the method according to any one of claims 1 to 4.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the method described in any one of claims 1 to 4 is implemented.

7. A computer product, comprising a computer program, characterized in that: When the computer program is executed by a processor, the method described in any one of claims 1 to 4 is implemented.

Images