Intelligent reverse scheduling optimization system and method for traditional manufacturing industry

Abstract

The invention discloses an intelligent reverse scheduling optimization system and method for the traditional manufacturing industry. The system comprises a data collection module, a work order generation module, a resource verification module, a scheduling optimization module and a monitoring adjustment module. The data collection module is used for collecting order information and processing the order information to obtain a to-be-produced work order list; the work order generation module optimizes the equipment task based on the to-be-produced work order list to generate a work order; the resource verification module is used for checking whether the equipment and the raw materials meet the requirements of the work order and generating constraint conditions; the scheduling optimization module performs priority ranking on the work orders based on constraint conditions by using a reverse production scheduling algorithm to generate an optimized production plan; the monitoring and adjusting module is used for monitoring the production process and dynamically adjusting the production plan according to the actual situation. By optimizing the production process, the efficiency can be improved and the cost can be reduced in the traditional manufacturing industry, so that the overall competitiveness is enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of production management, and in particular relates to an intelligent reverse scheduling optimization system and method for traditional manufacturing industry. Background Art

[0002] In traditional manufacturing, enterprises face many challenges, especially in the case of low information technology, production management often relies on experience and intuitive judgment. Although this approach may work well in the short term, it often appears to be stretched when dealing with complex orders and changing market environments.

[0003] Nowadays, many traditional manufacturing companies have not yet fully realized digitalization, and production processes and resource allocation rely on manual records and verbal communication. This leads to insufficient timeliness and accuracy of information, affecting the scientific nature of production decisions. In some traditional industries, customers have very clear requirements for delivery dates, which are often based on the delivery time in the contract. This single delivery date requirement makes production scheduling more challenging, especially when resources are limited. Traditional scheduling methods are usually linear and fail to take into account uncertainties and changes in the production process, such as equipment failures and material shortages. This inflexible scheduling method often leads to production delays and rising costs, which in turn affects the company's market competitiveness. Due to the lack of systematic information recording and management, problems that arise in the production process are often difficult to trace, affecting the company's monitoring and improvement of product quality. The ability to detect and solve problems in a timely manner has significantly decreased. Summary of the invention

[0004] The present invention aims to solve the deficiencies of the prior art and provides the following solutions:

[0005] An intelligent reverse scheduling optimization system for traditional manufacturing industry, comprising: a data collection module, a work order generation module, a resource verification module, a scheduling optimization module and a monitoring adjustment module;

[0006] The data collection module is used to collect order information and process the order information to obtain a list of work orders to be produced;

[0007] The work order generation module optimizes the equipment tasks based on the list of work orders to be produced and generates a work order;

[0008] The resource verification module is used to check whether the equipment, personnel and raw materials meet the requirements of the work order and generate constraint conditions;

[0009] The scheduling optimization module uses a reverse scheduling algorithm to prioritize the work orders based on the constraints to generate an optimized production plan;

[0010] The monitoring and adjustment module is used to monitor the production process and dynamically adjust the production plan according to actual conditions.

[0011] Preferably, the data collection module comprises: a data acquisition unit and a data processing unit;

[0012] The data collection unit is used to collect the order information from different data sources;

[0013] The data processing unit is used to perform data cleaning and key field screening on the order information to obtain the list of work orders to be produced.

[0014] Preferably, the work order generation module includes: an allocation function construction unit and a work order construction unit;

[0015] The allocation function construction unit adopts a heuristic algorithm to construct the objective function of task allocation:

[0016]

[0017] Where n represents the number of work orders, m represents the number of devices, and c ij represents the processing cost of work order i on equipment j, x ij represents the decision variable;

[0018] The work order construction unit optimizes the allocation of equipment tasks by minimizing the objective function to obtain the work order.

[0019] Preferably, the resource verification module includes: a verification unit and a constraint generation unit;

[0020] In the verification unit: for equipment, based on the performance parameters and maintenance records of the equipment, determine whether it can meet the production requirements of the work order; for personnel, check whether there are enough operators with the skills and qualifications to complete the production tasks required by the work order; for raw materials, check whether the inventory quantity meets the production requirements of the work order;

[0021] The constraint generation unit is used to construct task constraint conditions, including task sequence constraints and equipment requirement constraints.

[0022] Preferably, the scheduling optimization module includes: an evaluation function construction unit and a production plan generation unit;

[0023] The evaluation function construction unit is used to construct an evaluation function of the work order priority:

[0024] P = f(t, d, r)

[0025] Among them, t represents the remaining events of the work order, d represents the delivery date of the work order, and r represents the importance weight of the work order;

[0026] The production plan generating unit uses a reverse scheduling algorithm to prioritize the work orders based on the evaluation function to obtain the optimized production plan.

[0027] Preferably, the monitoring and adjustment module includes: a production monitoring unit and a plan adjustment unit;

[0028] The production monitoring unit is used to monitor real-time production process data, and the real-time production process data includes: equipment operation data, production progress data and quality data;

[0029] The plan adjustment unit uses an adaptive algorithm to dynamically adjust the optimized production plan according to the real-time production process data.

[0030] The present invention also provides an intelligent reverse scheduling optimization method for traditional manufacturing industry, the optimization method is applied to any of the above-mentioned optimization systems, and comprises the following steps:

[0031] Collect order information, process the order information, and obtain a list of work orders to be produced;

[0032] Optimizing equipment tasks based on the list of work orders to be produced and generating work orders;

[0033] To check whether the equipment and raw materials meet the requirements of the work order and generate constraints;

[0034] Prioritize the work orders based on the constraints using a reverse scheduling algorithm to generate an optimized production plan;

[0035] Monitor the production process and dynamically adjust the production plan based on actual conditions.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention starts from the final completion time of the order and gradually calculates the time arrangement of each production link, which can not only ensure on-time delivery, but also improve the traceability of the production process. The present invention not only conforms to the characteristics of the traditional manufacturing industry, but also provides an effective production management path for enterprises in an environment with a weak information foundation. By optimizing the production process, the traditional manufacturing industry can achieve efficiency improvement and cost reduction, thereby enhancing overall competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0039] Figure 1 Schematic diagram of the system structure of an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0042] Embodiment 1

[0043] In this embodiment, if Figure 1 As shown, an intelligent reverse scheduling optimization system for traditional manufacturing industry includes: a data collection module, a work order generation module, a resource verification module, a scheduling optimization module and a monitoring and adjustment module.

[0044] The data collection module is used to collect order information and process the order information to obtain a list of work orders to be produced.

[0045] The data collection module includes: a data collection unit and a data processing unit. The data collection unit is used to collect order information from different data sources; the data processing unit is used to clean the order information and filter key fields to obtain a list of work orders to be produced.

[0046] In this embodiment, the data acquisition unit collects order information from multiple data sources (such as order tables, equipment capacity tables, etc.), and synchronizes data through the ERP system (or similar systems) to ensure the real-time nature of production scheduling. The data processing unit preprocesses the collected data to remove invalid or duplicate data to ensure the effectiveness of subsequent analysis. The preprocessing uses a data cleaning algorithm to filter the data by setting data validity rules. For example, the key fields in the order information (such as order number, product model, quantity, delivery date, etc.) must be complete and meet specific format requirements. Those that do not meet the requirements are considered invalid data and removed. Extract valid order information from the daily order table, and filter the orders according to the equipment capacity summary to form a list of work orders to be produced.

[0047] The work order generation module optimizes equipment tasks based on the list of work orders to be produced and generates work orders.

[0048] The work order generation module includes: an allocation function construction unit and a work order construction unit. In this embodiment, orders of similar products are merged to generate work order information to form a T+N production plan (N can be dynamically adjusted according to actual needs). The allocation function construction unit uses a heuristic algorithm to construct the objective function of task allocation:

[0049]

[0050] Where n represents the number of work orders, m represents the number of devices, and c ij represents the processing cost of work order i on equipment j, x ij represents the decision variable, when work order i is assigned to equipment j, x ij =1, otherwise x ij =0. The work order construction unit optimizes the allocation of equipment tasks by minimizing the objective function, checks the equipment's in-process tasks, determines whether the equipment has remaining tasks, and makes adjustments. According to the equipment's current task queue and remaining capacity, the available time window of the equipment is calculated to ensure that the work order is allocated within the equipment's available time, generate a T+N pre-schedule for the next N days, and adjust it to T+(N-1), T+(N-2), etc. in turn, to achieve detailed production task scheduling and obtain work orders.

[0051] The resource verification module is used to check whether the equipment, personnel and raw materials meet the requirements of the work order and generate constraints.

[0052] The resource verification module includes: a verification unit and a constraint generation unit. In the verification unit: for equipment, based on the performance parameters and maintenance records of the equipment, determine whether it can meet the production requirements of the work order; for personnel, check whether there are enough operators with skills and qualifications to complete the production tasks required by the work order; for raw materials, check whether the inventory quantity meets the production demand of the work order; the constraint generation unit is used to construct the constraints of the task, including: task sequence constraints and equipment requirement constraints.

[0053] In this embodiment, the verification unit will check whether the equipment and raw materials meet the requirements of the work order to ensure the availability of resources. For equipment, determine whether it can meet the production requirements of the work order based on the performance parameters and maintenance records of the equipment. For personnel, check whether there are enough operators with the corresponding skills and qualifications to complete the production tasks required by the work order. For raw materials, check whether the inventory quantity meets the needs of work order production, and consider the procurement cycle and supply stability of raw materials. The constraint generation unit uses a constraint satisfaction algorithm to optimize the production sequence, reduce the number of changeovers, reasonably arrange production resources, and avoid resource waste. Suppose the production task set is T = {t1, t2,…, t n}, each t i The task has a set of constraints C i ={ci1 ,c i2 ,…,c im}, such as task sequence constraints, equipment requirement constraints, etc.

[0054] The scheduling optimization module uses the reverse scheduling algorithm to prioritize work orders based on constraints and generate an optimized production plan.

[0055] The scheduling optimization module includes: an evaluation function construction unit and a production plan generation unit. In this embodiment, when resources are insufficient or scheduling conflicts occur, an early warning signal is issued to prompt order adjustment and resource reallocation. By real-time monitoring of resource usage and task execution progress, and comparing the preset resource threshold and task plan, when resource usage exceeds the threshold or task execution deviates from the plan, an early warning is triggered; then, the production schedule is readjusted according to the priority by inserting and changing the work order. Specifically, the evaluation function construction unit is used to construct an evaluation function for the work order priority:

[0056] P = f(t, d, r)

[0057] Among them, t represents the remaining events of the work order, d represents the delivery date of the work order, and r represents the importance weight of the work order (determined according to factors such as order type and customer importance); the production plan generation unit uses the reverse scheduling algorithm to prioritize the work orders based on the evaluation function to obtain an optimized production plan. Specifically:

[0058] First, the algorithm takes the delivery date d of the work order as the starting point, which is the key basis for the entire reverse scheduling. For each work order, the deadline by which it must be completed is clearly defined to ensure that the production plan can meet the customer's strict requirements for delivery time. For example, the delivery date of work order A is 2024-10-10. The algorithm uses this date as the final time node of the work order production process, and all production activities must be completed before this date.

[0059] Secondly, combined with the remaining events t of the work order, the algorithm calculates the remaining processing time for each work order in each production link. This requires comprehensive consideration of factors such as the performance parameters of the equipment, maintenance records, and the current task queue to determine the actual time window in which the equipment can be used to process the work order. Assuming that the remaining events of work order A are 5 days (assuming it is calculated in working days), after equipment E1 completes the current task, based on its performance and maintenance plan, the effective time available for processing work order A every day is 6 hours. Then, the algorithm will calculate the actual processing time schedule of work order A on equipment E1 based on this information, while also considering the supply of raw materials. If the inventory of raw materials is limited and the procurement cycle is long, the algorithm will reserve enough lead time in the time schedule to ensure that the raw materials can be supplied in time without affecting the production progress.

[0060] Afterwards, the algorithm prioritizes the work orders according to their importance weights. Work orders with higher importance weights are given priority in the production scheduling process. For example, the importance weight of work order A is 0.8, and the importance weight of work order B is 0.6. During production scheduling, even if the delivery date of work order B is slightly earlier than that of work order A, due to the higher importance weight of work order A, the algorithm will prioritize the production of work order A under certain conditions to ensure that key orders can be completed on time and with high quality.

[0061] In addition, during the reverse scheduling process, the algorithm monitors the use of resources in real time, including equipment load, raw material inventory, etc. When insufficient resources or scheduling conflicts are found, such as the load of the equipment in a certain time period exceeds its rated load, or the raw material inventory cannot meet the production needs of the work order, the algorithm immediately issues an early warning signal. For example, equipment E1 has been occupied by other work orders at a certain time, and work order A also needs to use equipment E1 within this time period according to the reverse scheduling algorithm. At this time, the algorithm will issue an early warning to prompt order adjustment and resource reallocation. At the same time, the algorithm will try to adjust the production order of the work order or find alternative equipment based on priority and resource conditions to resolve resource conflicts.

[0062] Finally, after the above complex calculation and adjustment process, the reverse scheduling algorithm finally generates an optimized production plan, determines the precise processing order, start time, end time and other detailed information of each work order on each device, outputs the optimized scheduling results to the database, and provides an API interface for other systems or users to query and call. The scheduling results include the processing status, time schedule, and corresponding equipment and work order information of each batch. By defining a unified data format and interface specifications, the accuracy and consistency of the data are ensured. For example, the scheduling results are encapsulated in JSON format, and key-value pairs are defined to describe the detailed information of each batch, such as:

[0063] {"batch_id":"001","product_name":"Product A","processing_status":"Started","start_time":"2024-10-01 08:00:00","end_time":"2024-10-02 12:00:00","equipment_id":"E001","work_order_id":"W001"}.

[0064] The monitoring and adjustment module is used to monitor the production process and dynamically adjust the production plan according to actual conditions.

[0065] The monitoring and adjustment module includes: production monitoring unit and plan adjustment unit. The production monitoring unit is used to monitor real-time production process data, which includes: equipment operation data, production progress data and quality data; the plan adjustment unit uses an adaptive algorithm to dynamically adjust the optimized production plan according to real-time production process data.

[0066] In this embodiment, production tasks are released, and corresponding production operations and quality inspection operations are arranged. According to the optimized production plan, the work order information and production requirements are sent to the corresponding production equipment and operator terminals. By real-time monitoring of production progress, feedback of abnormal status, statistics of missing deliveries, and timely adjustments. Internet of Things technology and sensor equipment are used to collect real-time operating data of production equipment and quality data in the production process. For example, for production equipment, the operating time, temperature, pressure and other parameters of the equipment are collected, and data analysis is used to determine whether the equipment is operating normally; for product quality, the size, weight, performance and other indicators of the product are collected and compared with the quality standards. If abnormalities are found, relevant personnel are notified in time for processing.

[0067] Specifically, the production process is monitored, and the scheduling plan is adjusted dynamically according to the actual situation to improve the flexibility and adaptability of the production line. The production monitoring unit continuously collects various data in the production process, including equipment operation data, production progress data, quality data, etc.; the planning adjustment unit uses an adaptive algorithm to adjust the scheduling plan according to real-time data. First, the state space is defined as various state combinations in the production process S = {s1, s2, s3}, where s1 represents the equipment state (such as whether the equipment is operating normally, the load condition of the equipment, etc.), s2 represents the progress of the work order (such as the proportion of completed work orders, the number of remaining work orders, etc.), and s3 represents the inventory level (such as the number of raw material inventory, the number of finished product inventory, etc.); the action space is the scheduling adjustment actions that can be taken, A = {a1, a2, a3}, where a1 represents adjusting the order of work orders, a2 represents replacing equipment, and a3 represents postponing tasks; then, the reward function is determined based on factors such as production efficiency, delivery timeliness, and resource utilization:

[0068] R(s,a)=w1×E(s,a)+w2×D(sa)+w3×U(s,a)

[0069] Among them, w1, w2, and w3 are weight coefficients, which respectively represent the importance of production efficiency, delivery timeliness, and resource utilization in the reward function. E(s,a) represents the change in production efficiency after taking action in the state (which can be measured by calculating the change in the number of work orders completed per unit time), D(s,a) represents the change in delivery timeliness after taking action in the state (for example, by calculating the change in the degree of proximity to the delivery date), and U(s,a) represents the change in resource utilization after taking action in the state (such as changes in equipment utilization, raw material utilization, etc.). By continuously learning the relationship between state-action-reward, the optimal scheduling adjustment strategy can be automatically selected according to the actual production situation.

[0070] Embodiment 2

[0071] In this embodiment, the specific working process of the system will be described in detail.

[0072] (1) The data acquisition unit system obtains relevant data by establishing connections with multiple data sources, such as the order management system, equipment monitoring system, and inventory management system. These data sources provide order information (including order number, product model, quantity, delivery date, etc.), equipment capacity information (including equipment model, maximum capacity, current task, etc.), and raw material inventory information (including raw material name, inventory quantity, procurement cycle, etc.).

[0073] (2) The data processing unit preprocesses the collected data using a data cleaning algorithm. First, the integrity and validity of the data are checked according to predefined rules. For example, the delivery date in the order information must be in a legal date format, and the maximum capacity in the equipment capacity information must be a value greater than zero. Data that does not meet the rules is marked or deleted directly. Then, the data is deduplicated to remove duplicate order records and equipment information to ensure the uniqueness of the data. Finally, the data is formatted and the data formats of different data sources are uniformly converted into a format that can be processed within the system, such as unifying the date format into "YYYY-MM-DD" and unifying the values ​​into specific data types (such as integers or floating point numbers).

[0074] (3) The data processing unit extracts valid order information from the daily order table, summarizes and screens orders according to equipment capacity, and forms a list of work orders to be produced. During the screening process, the remaining capacity of the equipment and the delivery date of the order are considered, and orders that are within the remaining capacity of the equipment and have a closer delivery date are given priority. For example, for a piece of equipment, its remaining capacity is to produce 100 products per day, and order A requires the production of 50 products with a delivery date of tomorrow, and order B requires the production of 80 products with a delivery date of the day after tomorrow, then order A is given priority to enter the list of work orders to be produced. Orders of similar products are merged to generate work order information. The system analyzes the product model and production requirements in the order and merges orders with the same product model and similar production requirements into one work order. For example, if there are three orders that require the production of product model A, and the production processes and requirements are basically the same, then these three orders will be merged into one work order, and the work order information records the product model A, the quantity is the sum of the quantities of the three orders, and the production requirements are the common production processes and requirements.

[0075] (4) The work order generation module uses a heuristic algorithm to optimize the allocation of equipment tasks and form a T+N production plan. During the allocation process, the processing cost (including time cost, material consumption cost, etc.) of each equipment for different work orders is first calculated. For example, the time cost of equipment 1 to process work order 1 is 2 hours, and the material consumption cost is 10 yuan; the time cost of equipment 2 to process work order 1 is 3 hours, and the material consumption cost is 8 yuan. Then, according to the remaining capacity of the equipment and the production requirements of the work order, the equipment with the lowest processing cost is selected to allocate the work order. For the T+N production plan, N can be dynamically adjusted according to actual needs. For example, if there are many orders at present and the delivery date is tight, the value of N can be appropriately increased to arrange more production tasks in advance; if there are few orders and the delivery date is loose, the value of N can be appropriately reduced to avoid equipment idleness.

[0076] (5) The resource verification module checks the equipment's in-process tasks, determines whether the equipment has any remaining tasks, and makes adjustments. By obtaining the equipment's current task queue and remaining capacity information, it determines whether the equipment is capable of taking on new work orders. If the equipment has remaining tasks, the priority of the remaining tasks is compared with the priority of the new work order, and the tasks with higher priority are prioritized. If the equipment has no remaining tasks, the new work order is directly assigned to the equipment. At the same time, in the process of generating the T+N pre-schedule plan for the next N days, it is adjusted to T+(N-1), T+(N-2), etc. in sequence to ensure that the production tasks are arranged more carefully and reasonably.

[0077] (6) The verification unit checks whether the equipment, personnel, and raw materials meet the requirements of the work order to ensure the availability of resources. For equipment, determine whether it can meet the production requirements of the work order based on the equipment's performance parameters and maintenance records. For example, if a work order requires the use of processing equipment with a specific precision, and the equipment's precision meets the requirements, then the equipment is available. For personnel, check whether there are enough operators with the corresponding skills and qualifications to complete the production tasks required by the work order. For raw materials, check whether the inventory quantity meets the production requirements of the work order, and consider the procurement cycle and supply stability of the raw materials. For example, if a work order requires the production of 100 products, which requires 10 kg of a certain raw material, and there are 15 kg of this raw material in inventory, and the procurement cycle is short, then the raw material is available.

[0078] (7) The constraint generation unit uses the constraint satisfaction algorithm to optimize the production sequence, reduce the number of changeovers, and reasonably arrange production resources to avoid resource waste. Suppose the production task set is T = {t1, t2, …, t n}, each t i The task has a set of constraints C i ={c i1 ,c i2 ,…,c im}, such as task sequence constraints, equipment requirement constraints, etc. The production sequence can be optimized by finding the task arrangement sequence that satisfies all constraints. For example, there are three tasks t1, t2, and t3. t1 is required to be completed before t2, and t3 requires the use of specific equipment. Through the constraint satisfaction algorithm, it is determined that the optimal production sequence may be t1-t3-t2, which can avoid unnecessary equipment replacement and production interruption, and improve production efficiency.

[0079] (8) In the scheduling optimization module, when resources are insufficient or scheduling conflicts occur, the system issues an early warning signal to prompt order adjustments and resource reallocation. By real-time monitoring of resource usage and task execution progress, and comparing the preset resource thresholds with the task plan, an early warning is triggered when resource usage exceeds the threshold or task execution deviates from the plan. For example, when the load of a device exceeds 80% of its rated load, the system issues an early warning signal, indicating that it may be necessary to adjust order allocation or add equipment. When the raw material inventory is lower than the safety inventory, the system will also issue an early warning signal to prompt the need to purchase raw materials in a timely manner.

[0080] (9) The scheduling optimization module supports the insertion and modification of work orders. The evaluation function construction unit readjusts the production schedule according to the priority. The evaluation function for setting the work order priority:

[0081] P = f(t, d, r)

[0082] Among them, t represents the remaining time of the work order, d represents the delivery date of the work order, and r represents the importance weight of the work order (determined by factors such as order type and customer importance). The work orders are prioritized according to this evaluation function, and when adjusting the schedule, the work orders with high priority are given priority. For example, there are two work orders. The remaining time of work order A is 3 days, the delivery date is 5 days later, and the importance weight is 0.8; the remaining time of work order B is 2 days, the delivery date is 4 days later, and the importance weight is 0.6. According to the evaluation function, the priority of work order A is P(A)=0.8*(3 / 5)=0.48, and the priority of work order B is P(B)=0.6*(2 / 4)=0.3. Therefore, when adjusting the schedule, work order A is given priority.

[0083] (10) The production plan generation unit outputs the optimized scheduling results to the database and provides an API interface for other systems or users to query and call. The scheduling results include the processing status, time schedule, and corresponding equipment and work order information of each batch. The accuracy and consistency of the data are ensured by defining a unified data format and interface specifications. The system provides services through the API interface, and external systems or users can obtain scheduling result information by calling these interfaces. For example, users can query the production progress of an order through the interface, or obtain the task schedule of a specific device. The interface design follows the RESTful specification and uses the HTTP protocol for communication to ensure the universality and ease of use of the interface. Release production tasks and arrange corresponding production operations and quality inspection operations. According to the scheduling results, the work order information and production requirements are sent to the corresponding production equipment and operator terminals. For example, the product model, quantity, production process and other information in the work order information are sent to the control system of the production equipment, and the quality standard, inspection method and other information in the production requirements are sent to the terminal device of the quality inspector.

[0084] (11) The monitoring and adjustment module monitors the production progress in real time, feedbacks abnormal status, counts the number of missed deliveries, and makes timely adjustments. The IoT technology and sensor equipment are used to collect real-time operating data of production equipment and quality data during the production process. For example, for production equipment, the operating time, temperature, pressure and other parameters of the equipment are collected, and data analysis is used to determine whether the equipment is operating normally; for product quality, the dimensions, weight, performance and other indicators of the product are collected and compared with the quality standards. If any abnormality is found, relevant personnel are notified in a timely manner for processing.

[0085] Embodiment 3

[0086] In this embodiment, an intelligent reverse scheduling optimization method for traditional manufacturing industry includes the following steps: collecting order information, processing the order information, and obtaining a list of work orders to be produced; optimizing equipment tasks based on the list of work orders to be produced to generate work orders; checking whether the equipment and raw materials meet the requirements of the work orders, and generating constraints; using a reverse scheduling algorithm to prioritize the work orders based on the constraints and generate an optimized production plan; monitoring the production process, and dynamically adjusting the production plan according to actual conditions.

[0087] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. An intelligent reverse scheduling optimization system for traditional manufacturing industry, characterized in that: include: Data collection module, work order generation module, resource verification module, scheduling optimization module and monitoring adjustment module; The data collection module is used to collect order information and process the order information to obtain a list of work orders to be produced; The work order generation module optimizes the equipment tasks based on the list of work orders to be produced and generates a work order; The resource verification module is used to check whether the equipment, personnel and raw materials meet the requirements of the work order and generate constraint conditions; The scheduling optimization module uses a reverse scheduling algorithm to prioritize the work orders based on the constraints to generate an optimized production plan; The monitoring and adjustment module is used to monitor the production process and dynamically adjust the production plan according to actual conditions.

2. According to claim 1, an intelligent reverse scheduling optimization system for traditional manufacturing industry is characterized in that: The data collection module includes: a data acquisition unit and a data processing unit; The data collection unit is used to collect the order information from different data sources; The data processing unit is used to perform data cleaning and key field screening on the order information to obtain the list of work orders to be produced.

3. According to claim 1, an intelligent reverse scheduling optimization system for traditional manufacturing industry is characterized in that: The work order generation module includes: an allocation function construction unit and a work order construction unit; The allocation function construction unit adopts a heuristic algorithm to construct the objective function of task allocation: Where n represents the number of work orders, m represents the number of devices, and c ij represents the processing cost of work order i on equipment j, xi j represents the decision variable; The work order construction unit optimizes the allocation of equipment tasks by minimizing the objective function to obtain the work order.

4. According to claim 1, an intelligent reverse scheduling optimization system for traditional manufacturing industry is characterized in that: The resource verification module includes: a verification unit and a constraint generation unit; In the verification unit: for equipment, judging whether the production requirements of the work order can be met based on the performance parameters and maintenance records of the equipment; for personnel, checking whether there are enough operators with the skills and qualifications to complete the production tasks required by the work order; for raw materials, checking whether the inventory quantity meets the production requirements of the work order; The constraint generation unit is used to construct task constraint conditions, including task sequence constraints and equipment requirement constraints.

5. According to claim 1, an intelligent reverse scheduling optimization system for traditional manufacturing industry is characterized in that: The scheduling optimization module includes: an evaluation function construction unit and a production plan generation unit; The evaluation function construction unit is used to construct an evaluation function of the work order priority: P=f(t,d,r) Among them, t represents the remaining events of the work order, d represents the delivery date of the work order, and r represents the importance weight of the work order; The production plan generating unit uses a reverse scheduling algorithm to prioritize the work orders based on the evaluation function to obtain the optimized production plan.

6. According to claim 1, an intelligent reverse scheduling optimization system for traditional manufacturing industry is characterized in that: The monitoring and adjustment module includes: a production monitoring unit and a plan adjustment unit; The production monitoring unit is used to monitor real-time production process data, and the real-time production process data includes: equipment operation data, production progress data and quality data; The plan adjustment unit uses an adaptive algorithm to dynamically adjust the optimized production plan according to the real-time production process data.

7. An intelligent reverse scheduling optimization method for traditional manufacturing industry, the optimization method is applied to the optimization system according to any one of claims 1 to 6, characterized in that: The following steps are involved: Collect order information, process the order information, and obtain a list of work orders to be produced; Optimizing equipment tasks based on the list of work orders to be produced and generating work orders; To check whether the equipment and raw materials meet the requirements of the work order and generate constraints; Prioritize the work orders based on the constraints using a reverse scheduling algorithm to generate an optimized production plan; Monitor the production process and dynamically adjust the production plan based on actual conditions.

Images