Intelligent production scheduling control method and system for hardware manufacturing workshop
By constructing a hardware manufacturing resource map and an order-dependent resource map, conducting multi-dimensional sufficiency evaluation and identifying abnormal factors, and combining risk prediction models to optimize resource scheduling, the problems of complex resource dependence and imbalance between supply and demand in hardware manufacturing workshops are solved, and accurate perception of resource status and dynamic optimization of scheduling strategies are achieved.
Patent Information
- Application Number
- CN202511045246.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-29
- Publication Date
- 2025-10-21
AI Technical Summary
The resource scheduling process in hardware manufacturing workshops is characterized by complex resource dependence, imbalance between supply and demand, and insufficient scheduling optimization, which leads to frequent adjustments to production plans, low resource utilization, and difficulty in responding to order changes and emergencies in a timely manner.
By constructing a hardware manufacturing resource map and an order-dependent resource map, multi-dimensional sufficiency evaluation and abnormal factor identification are carried out, and resource adjustment and optimization are carried out in combination with a risk prediction model, achieving accurate perception of resource status and dynamic optimization of scheduling strategies.
It achieves accurate perception of resource status and dynamic optimization of scheduling strategies, reduces production risks, and improves resource utilization and production efficiency.
Smart Images

Figure CN120822783A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of production control, and in particular to an intelligent production scheduling control method and system for a hardware manufacturing workshop. Background Art
[0002] The actual production process in hardware manufacturing workshops involves the coordinated use of multiple resources, including equipment, raw materials, manpower, and energy. Production orders have multi-dimensional and multi-level dependencies on these resources, and changes in resource status directly impact production cadence and delivery efficiency. Due to the dispersed distribution of resources and the dynamic dynamics of supply and demand, conventional scheduling methods struggle to fully assess resource availability and adaptability. This leads to frequent adjustments to production plans, low resource utilization, and difficulty in responding to order changes and emergencies, impacting overall production efficiency and management accuracy. Summary of the Invention
[0003] The present application provides an intelligent production scheduling control method and system for hardware manufacturing workshops, which is used to solve the technical problems of complex resource dependence, supply and demand imbalance and insufficient scheduling optimization in the resource scheduling process of hardware manufacturing workshops in the prior art.
[0004] In view of the above problems, the present application provides an intelligent production scheduling control method and system for hardware manufacturing workshops.
[0005] The first aspect of the present application provides an intelligent production scheduling control method for a hardware manufacturing workshop, the method comprising: Based on resource perception of the hardware manufacturing workshop, a hardware manufacturing resource map is established, and resource dependency analysis is performed on the hardware order set of the hardware manufacturing workshop to generate an order dependency resource map; based on the order dependency resource map, a multi-dimensional abundance evaluation is performed on the hardware manufacturing resource map to establish a resource abundance evaluation sequence; based on the abundance evaluation multi-dimensional constraints, an abnormality analysis is performed on the resource abundance evaluation sequence to determine the abundance abnormality factor; based on the abundance abnormality factor, the hardware manufacturing resource map is compensated and adjusted to establish a first production resource adjustment space, and the first production resource adjustment space is traversed and optimized based on the abundance evaluation multi-dimensional constraints to construct a second production resource adjustment space; a hardware production risk prediction model is introduced to perform global optimization on the second production resource adjustment space to determine a hardware production resource optimization strategy, and based on the hardware production resource optimization strategy, resources of the hardware manufacturing workshop are optimized.
[0006] The second aspect of the present application provides an intelligent production scheduling and control system for a hardware manufacturing workshop, the system comprising: A resource perception module is used to perceive resources according to the hardware manufacturing workshop, establish a hardware manufacturing resource map, and perform resource dependency analysis on the hardware order set of the hardware manufacturing workshop to generate an order dependency resource map; an abundance evaluation module is used to perform multi-dimensional abundance evaluation on the hardware manufacturing resource map according to the order dependency resource map and establish a resource abundance evaluation sequence; an anomaly analysis module is used to perform an anomaly analysis on the resource abundance evaluation sequence according to the abundance evaluation multi-dimensional constraints and determine the abundance anomaly factor; an adjustment space construction module is used to compensate and adjust the hardware manufacturing resource map according to the abundance anomaly factor, establish a first production resource adjustment space, and traverse and optimize the first production resource adjustment space according to the abundance evaluation multi-dimensional constraints to construct a second production resource adjustment space; a resource optimization module is used to introduce a hardware production risk prediction model to perform global optimization on the second production resource adjustment space, determine a hardware production resource optimization strategy, and optimize resources for the hardware manufacturing workshop according to the hardware production resource optimization strategy.
[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The present application performs resource perception based on a hardware manufacturing workshop, establishes a hardware manufacturing resource map, and performs resource dependency analysis on the hardware order set of the hardware manufacturing workshop to generate an order dependency resource map; performs multi-dimensional sufficiency evaluation on the hardware manufacturing resource map based on the order dependency resource map, and establishes a resource sufficiency evaluation sequence; performs abnormality analysis on the resource sufficiency evaluation sequence based on the sufficiency evaluation multi-dimensional constraints, and determines the sufficiency abnormality factor; compensates and adjusts the hardware manufacturing resource map based on the sufficiency abnormality factor, establishes a first production resource adjustment space, and traverses and optimizes the first production resource adjustment space based on the sufficiency evaluation multi-dimensional constraints to construct a second production resource adjustment space; introduces a hardware production risk prediction model to perform global optimization on the second production resource adjustment space, determines a hardware production resource optimization strategy, and optimizes resources for the hardware manufacturing workshop based on the hardware production resource optimization strategy. The present invention solves the technical problems of complex resource dependence, imbalance between supply and demand, and insufficient scheduling optimization in the resource scheduling process of hardware manufacturing workshops in the prior art. By constructing a hardware manufacturing resource map and an order-dependent resource map, conducting multi-dimensional abundance evaluation and abnormal factor identification, and combining a risk prediction model to perform resource adjustment and optimization, the present invention achieves the technical effects of accurate perception of resource status, dynamic optimization of scheduling strategies, and minimization of production risks. BRIEF DESCRIPTION OF THE DRAWINGS
[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of 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 creative work.
[0009] Figure 1 A flowchart of an intelligent production scheduling control method for a hardware manufacturing workshop provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of an intelligent production scheduling control system for a hardware manufacturing workshop provided in an embodiment of the present application.
[0010] Explanation of the accompanying symbols: resource perception module 11, sufficiency evaluation module 12, anomaly analysis module 13, adjustment space construction module 14, resource optimization module 15. DETAILED DESCRIPTION
[0011] This application provides an intelligent production scheduling and control method and system for hardware manufacturing workshops, aiming to solve the technical problems of complex resource dependence, supply and demand imbalance and insufficient scheduling optimization in the resource scheduling process of hardware manufacturing workshops in the prior art. By constructing a hardware manufacturing resource map and an order-dependent resource map, conducting multi-dimensional abundance evaluation and abnormal factor identification, and combining risk prediction models to adjust and optimize resources, the application achieves the technical effects of accurate perception of resource status, dynamic optimization of scheduling strategies and minimization of production risks.
[0012] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.
[0013] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.
[0014] Example 1, as Figure 1 As shown, the present application provides an intelligent production scheduling control method for a hardware manufacturing workshop, the method comprising: Step S100: performing resource perception based on the hardware manufacturing workshop, establishing a hardware manufacturing resource map, and performing resource dependency analysis on the hardware order set of the hardware manufacturing workshop to generate an order dependency resource map.
[0015] In an embodiment of the present application, when performing resource perception based on a hardware manufacturing workshop, the equipment resources, raw material resources, human resources and energy resources of the hardware manufacturing workshop are first perceived separately to construct a perceived equipment resource map, a perceived raw material resource map, a perceived human resource map and a perceived energy resource map, and the above four types of maps are integrated to form a hardware manufacturing resource map.
[0016] When performing resource dependency analysis on the hardware order set of a hardware manufacturing workshop, we first perform order scheduling analysis to determine the order scheduling plan, and then conduct multi-dimensional resource demand mining on the orders to form a multi-dimensional resource library of order demand; by confidently fusing the resource characteristics of each resource in the resource library, we generate a resource dependency set for each type of resource, and finally construct an order dependency resource map, which includes a map of dependent equipment resources, a map of dependent raw material resources, a map of dependent human resources, and a map of dependent energy resources.
[0017] Furthermore, in the method provided in the embodiment of the application, resource perception is performed based on the hardware manufacturing workshop to establish a hardware manufacturing resource map, which also includes: Based on the equipment resource perception of the hardware manufacturing workshop, a perception equipment resource map is generated; based on the raw material resource perception of the hardware manufacturing workshop, a perception raw material resource map is generated; based on the human resource perception of the hardware manufacturing workshop, a perception human resource map is generated; based on the energy resource perception of the hardware manufacturing workshop, a perception energy resource map is generated; the perception equipment resource map, the perception raw material resource map, the perception human resource map and the perception energy resource map are integrated to generate the hardware manufacturing resource map.
[0018] In this embodiment, device resource sensing is first performed in a hardware manufacturing workshop. During this process, status information is collected from the equipment within the workshop, including data such as the operating status, usage frequency, and maintenance records of each device, forming a device resource dataset. This dataset is then formatted and anomalies are removed to generate a device resource stream. This device resource stream is then correlated and integrated according to device category, usage period, and geographic distribution, completing a graph-based process to ultimately generate a device resource map.
[0019] The raw material resource perception process is similar to that of equipment resources. It also obtains data such as the inventory quantity, storage location, batch attributes, etc. of raw materials through information collection to form a raw material resource data set. After data cleaning and classification and labeling, it is organized into a raw material resource flow, and then related sorting is performed to construct a raw material resource map that reflects the raw material inventory, type and scheduling capacity.
[0020] In terms of human resource perception, by retrieving the workshop personnel's scheduling records, skill levels, working hour utilization and other information, a human resource data set is constructed, cleaned and standardized, and the human resource flow is obtained. It is then matched and integrated according to time periods and job types to form a human resource map that reflects personnel scheduling capabilities and workloads.
[0021] Energy resource perception reads various energy usage records in the energy consumption system, collects energy consumption data in different time periods, generates energy data sets, and obtains energy resource flows after data cleaning. It then performs structured sorting based on the load distribution of each energy source to generate an energy resource map.
[0022] Finally, the perception equipment resource map, perception raw material resource map, perception human resource map and perception energy resource map are integrated, and a unified hardware manufacturing resource map is generated through structural alignment and data fusion methods.
[0023] Furthermore, in the method provided in the embodiment of the application, the device resource perception of the hardware manufacturing workshop is performed to generate a perception device resource map, and the method further includes: Equipment resource information is collected from the hardware manufacturing workshop to generate an equipment resource data set; data cleaning is performed on the equipment resource data set to obtain an equipment resource flow; and the equipment resource flow is graphically combed to obtain the perceived equipment resource map.
[0024] In this embodiment, when collecting equipment resource information in a hardware manufacturing workshop, a fixed-point scanning method is first used to collect equipment status information. A timed collection program is set up on the equipment control terminal to regularly record basic parameters such as equipment number, operating status, current operation information, fault alarm code, and maintenance time. This data is collected at a set interval (e.g., every 10 seconds), ultimately generating an equipment resource dataset.
[0025] The equipment resource dataset was then cleaned using rule-based filtering. Specific operations included using thresholds to eliminate anomalies (such as operating temperatures exceeding 150°C or negative operating hours), filling default fields with null values (such as replacing missing maintenance plans with "No Plan"), and standardizing data formats (for example, dates are standardized to YYYY-MM-DD HH:MM:SS). This eliminates redundant and abnormal items, outputs a continuous, standardized data structure, and produces the cleaned equipment resource stream.
[0026] Finally, a field classification method was used to map the device resource flow. Using the device number as the node identifier, the device status field (e.g., running / standby / fault), location field (e.g., distributed in workshop area A / B), and maintenance field (e.g., remaining maintenance period) were used as node attributes. Similar substitutable relationships between devices (e.g., same model, same function) were connected as edges to represent connectivity, thus constructing a perceptual device resource map.
[0027] Furthermore, in the method provided in the embodiment of the application, resource dependency analysis is performed on the hardware order set of the hardware manufacturing workshop to generate an order dependency resource map, which also includes: Scheduling analysis is performed on the hardware order set to determine an order scheduling plan; multi-dimensional resource demand mining is performed on the hardware order set according to the order scheduling plan to obtain a multi-dimensional resource library of order demand; confidence fusion of each resource feature is performed on the multi-dimensional resource library of order demand to generate each resource dependency set; based on each resource dependency set, the order dependency resource map is constructed, and the order dependency resource map includes a dependent equipment resource map, a dependent raw material resource map, a dependent human resource map, and a dependent energy resource map.
[0028] In this embodiment, a pre-prepared hardware order set is first read. A hardware order set refers to a collection of hardware product processing tasks received by a workshop during its production cycle. Each order contains information such as product number, process route, delivery cycle, and quantity requirements. Scheduling is then performed based on the hardware order set. Using a process parsing method, the product model and processing code corresponding to the hardware order set are searched for matching items in the process standards database. The order's required processing sequence, the execution time of each process, and the timing of resource allocation are determined, thereby generating an order scheduling plan.
[0029] Subsequently, based on the order scheduling plan, the hardware order set is mined for multidimensional resource requirements. During this process, for each process listed in the order scheduling plan, corresponding fields are extracted from the preset equipment archive table, raw material list, job human resource library, and energy standard consumption table to identify the equipment model, material specifications, personnel skill level, and standard energy consumption data required for each process. Through field-level matching and standardized organization, a resource requirement form under the order dimension is generated and archived into a uniformly structured data set, namely the order requirement multidimensional resource library. This multidimensional resource library covers static resource call lists in four dimensions: equipment resources, raw material resources, human resources, and energy resources.
[0030] Subsequently, the confidence level of each resource's characteristics is fused based on the multidimensional resource library of order requirements. A weighted scoring-based indicator integration mechanism is employed. For each resource type, its actual performance indicators from historical order execution (such as equipment fulfillment rate, raw material arrival on-time rate, personnel attendance reliability, and energy supply stability) are calculated. After normalization, weight factors are assigned (e.g., a weight of 0.5 for equipment resource fulfillment rate, 0.3 for stability, and 0.2 for replacement success rate) to calculate the resource's confidence level in the current order task. For example, a C25 punch press with a fulfillment rate of 90%, a stability of 95%, and a replacement success rate of 80% has a confidence score of 0.5 × 0.90 + 0.3 × 0.95 + 0.2 × 0.80 = 0.88. This approach integrates scores for equipment resources, raw material resources, human resources, and energy resources, forming a structured data set containing resource identifiers and confidence levels, thus generating each resource dependency set.
[0031] Finally, an order dependency resource graph is constructed based on each resource dependency set. That is, the order number is used as the source node in the graph, the resource items in each resource dependency set are used as the target nodes, and the confidence score is used as the weight of the edge. Four types of resource dependency subgraphs are constructed, including equipment dependency resource graph, raw material dependency resource graph, human resource dependency graph, and energy dependency resource graph.
[0032] Step S200: performing a multi-dimensional sufficiency evaluation on the hardware manufacturing resource map according to the order-dependent resource map, and establishing a resource sufficiency evaluation sequence.
[0033] In an embodiment of the present application, when performing a multi-dimensional sufficiency evaluation of the hardware manufacturing resource map based on the order-dependent resource map, multiple resource abundance assessment factors are first activated, namely, reserve sufficiency, available time matching, alternative resource sufficiency, and resource performance accuracy. Then, based on these assessment factors, resource-level sufficiency analysis is performed on the dependent equipment resource map and the perceived equipment resource map, the dependent raw material resource map and the perceived raw material resource map, the dependent human resource map and the perceived human resource map, and the dependent energy resource map and the perceived energy resource map, respectively. Equipment resource sufficiency, raw material resource sufficiency, human resource sufficiency, and energy resource sufficiency are sequentially generated. Finally, various resource sufficiency indicators are integrated to construct a resource sufficiency evaluation sequence.
[0034] Furthermore, in the method provided in the embodiment of the application, a multi-dimensional sufficiency evaluation is performed on the hardware manufacturing resource map according to the order-dependent resource map to establish a resource sufficiency evaluation sequence, which further includes: Activate resource abundance assessment factors, which include reserve adequacy, available time matching, alternative resource adequacy, and resource performance accuracy; based on the resource abundance assessment factors, perform an abundance analysis on the perceived equipment resource map according to the dependent equipment resource map to generate equipment resource abundance; based on the resource abundance assessment factors, perform an abundance analysis on the perceived raw material resource map according to the dependent raw material resource map to generate raw material resource abundance; based on the resource abundance assessment factors, perform an abundance analysis on the perceived human resource map according to the dependent human resource map to generate human resource abundance; based on the resource abundance assessment factors, perform an abundance analysis on the perceived energy resource map according to the dependent energy resource map to generate energy resource abundance, and combine the equipment resource abundance, the raw material resource abundance, and the human resource abundance to generate the resource abundance evaluation sequence.
[0035] In an embodiment of the present application, the resource abundance assessment factor used for sufficiency assessment is first activated, which includes reserve sufficiency (whether the resource quantity meets the order requirements), available time matching (the degree of overlap between the resource idle period and the order execution period), alternative resource sufficiency (whether there are functionally equivalent alternative resources), and resource performance accuracy (the degree to which the resource meets the order process requirements in terms of parameter indicators).
[0036] The process of analyzing equipment resource abundance begins by loading multiple resource abundance assessment record sets based on resource abundance assessment factors. These record sets include equipment operation logs, work order matching records, performance usage data, fault repair data, and alternative usage. This data is then subjected to knowledge distillation to extract representative assessment features and construct a resource abundance assessment model. The model then inputs device call demand information extracted from the dependent device resource map and actual resource status data from the perceived device resource map into the resource abundance assessment model to obtain a quantified equipment resource abundance assessment result. Based on the importance of each resource abundance assessment factor, corresponding weights are assigned to construct a resource abundance analysis model. The assessment results from each dimension are then integrated and calculated to ultimately output the equipment resource abundance.
[0037] For the abundance analysis of raw material resources, also based on the resource abundance assessment factors, first load the resource abundance assessment record set related to the raw materials, including inventory arrival cycle, batch validity period, actual receipt history and use of alternative materials, etc.; extract key supply indicators through knowledge distillation, build a raw material resource abundance assessment model, and input the demand information and inventory information in the dependent raw material resource map and the perceived raw material resource map into the model, and output the abundance score result of each raw material under the current order conditions; then build an analytical model based on the weight of each factor to output the raw material resource abundance.
[0038] To analyze human resource sufficiency, we first load assessment records, including personnel scheduling records, skill matching logs, and historical attendance data, to extract key factors influencing personnel availability and construct a human resource sufficiency assessment model. This model compares the job skill levels and work period requirements recorded in the dependent human resource graph with the shift schedule, skill level, remaining work hours, and other data in the perceived human resource graph. This input is then fed into the model to obtain a human resource sufficiency score. This score is then weighted and integrated based on the resource sufficiency assessment factors to generate the corresponding human resource sufficiency score.
[0039] To analyze energy resource sufficiency, we load assessment datasets such as energy consumption logs, load conditions during power supply periods, and backup energy usage records to establish an energy supply and demand analysis model. The model matches the energy type, usage time period, and consumption intensity from the dependent energy resource map with the load level, electricity price fluctuations, and energy supply capacity from the perceived energy resource map. This input generates an energy sufficiency score, which is then weighted and analyzed to determine the energy resource sufficiency for the order.
[0040] Finally, the obtained equipment resource abundance, raw material resource abundance, human resource abundance and energy resource abundance are integrated and structured in units of orders to generate a resource abundance evaluation sequence.
[0041] Furthermore, in the method provided in the embodiment of the application, based on the resource abundance assessment factor, performing sufficiency analysis on the sensing device resource map according to the dependent device resource map to generate device resource sufficiency, the method further includes: Based on the resource abundance assessment factor, multiple resource abundance assessment record sets are loaded; knowledge distillation is performed based on the multiple resource abundance assessment record sets to construct a resource abundance assessment model; the dependent device resource map and the perception device resource map are input into the resource abundance assessment model to obtain a device resource abundance assessment result; weights are assigned based on the resource abundance assessment factor to construct a resource abundance analysis model; abundance calculation is performed on the device resource abundance assessment result based on the resource abundance analysis model to obtain the device resource abundance.
[0042] In the embodiment of the present application, first, based on the resource abundance assessment factors, namely, reserve adequacy, available time matching, alternative resource adequacy and resource performance accuracy, multiple resource abundance assessment record sets are loaded. The resource abundance assessment record set is a structured collection of historical production data, specifically including the historical dependent equipment resource map and historical perception equipment resource map of completed orders in the historical period, as well as the corresponding assessment results obtained by manual annotation, namely, the reserve adequacy coefficient, available time matching coefficient, alternative resource adequacy coefficient and resource performance accuracy coefficient of each group of dependent perception maps under the actual resource status at that time. These four coefficients are expressed as decimals between 0 and 1.
[0043] Subsequently, knowledge distillation is performed based on multiple resource abundance assessment record sets to construct a resource abundance assessment model. This process first extracts fields from the structural correspondence between the historical dependent device resource graph and the historical perception device resource graph, quantizing key features such as device model, device status, scheduling time, and device attribute parameters. Regression modeling is then performed on the target outputs (reserve adequacy coefficient, available time matching coefficient, alternative resource adequacy coefficient, and resource performance accuracy coefficient). The nonlinear mapping relationship between input and output is trained using a random forest algorithm or a BP neural network model, thereby constructing a resource abundance assessment model with predictive capabilities.
[0044] Subsequently, the dependent equipment resource map and the perceived equipment resource map are input into the resource abundance assessment model for analysis to obtain the equipment resource abundance assessment results. The equipment resource abundance assessment results are composed of the reserve adequacy coefficient, the available time matching coefficient, the alternative resource adequacy coefficient and the resource performance accuracy coefficient. These four coefficients are expressed as decimals between 0 and 1.
[0045] Next, weights are assigned based on the resource abundance assessment factors to construct a resource sufficiency analysis model. This process uses a fixed weighting method for the four resource abundance assessment factors based on the preset resource allocation strategy or task priority. For example, a weight of 0.4 is assigned to reserve sufficiency, 0.2 to available time matching, 0.2 to alternative resource sufficiency, and 0.2 to resource performance accuracy. This is how the resource sufficiency analysis model is constructed.
[0046] Finally, the resource sufficiency analysis model is used to calculate the sufficiency of the equipment resource abundance assessment results. This calculation process inputs the equipment resource sufficiency assessment results into the resource sufficiency analysis model for calculation. For example, when the reserve sufficiency coefficient is 1.0, the available time matching coefficient is 0.9, the alternative resource sufficiency coefficient is 0.8, and the resource performance accuracy coefficient is 0.95, the calculation formula is: Equipment Resource Sufficiency = 0.4 × 1.0 + 0.2 × 0.9 + 0.2 × 0.8 + 0.2 × 0.95 = 0.93. This calculation process yields the equipment resource sufficiency.
[0047] Step S300: performing abnormal analysis on the resource abundance evaluation sequence according to the abundance evaluation multi-dimensional constraints to determine an abundance abnormality factor.
[0048] In this embodiment, we first obtain pre-set multi-dimensional sufficiency evaluation constraints, including equipment resource constraints, raw material resource constraints, human resource constraints, and energy resource constraints. Each of these constraints corresponds to a pre-set threshold. For example, the equipment resource constraint is 0.85, the raw material resource constraint is 0.80, the human resource constraint is 0.75, and the energy resource constraint is 0.70.
[0049] Each resource sufficiency in the resource sufficiency evaluation sequence is then traversed and compared with the corresponding multi-dimensional sufficiency evaluation constraints. If the sufficiency of a resource dimension is less than the corresponding sufficiency constraint threshold, the resource dimension is deemed to not meet the usage conditions and is considered abnormal. The dimension is directly marked and recorded as a sufficiency anomaly factor.
[0050] Step S400: The hardware manufacturing resource map is adjusted according to the abundance abnormality factor compensation, a first production resource adjustment space is established, and the first production resource adjustment space is optimized through traversal according to the abundance evaluation multidimensional constraint to construct a second production resource adjustment space.
[0051] In an embodiment of the present application, when adjusting the hardware manufacturing resource map based on the compensation of the abundance anomaly factor, a simple substitution, expansion or adjustment method is used to correct the resource dimension corresponding to each abundance anomaly factor. For example, for equipment resource anomalies, compensation is performed by adding spare equipment, adjusting the equipment production sequence or activating idle equipment; for raw material resource anomalies, adjustment is performed by calling other warehouse inventories, adjusting material arrival times or selecting alternative raw materials; for human resource anomalies, personnel with corresponding skill levels are deployed, or the shift plan is adjusted so that manpower covers task requirements during critical periods; for energy resource anomalies, tasks are adjusted to low-load time periods, or spare energy channels are activated for load dispersion. After combining the above-mentioned resource compensation strategies, several groups of resource allocation schemes are formed for scheduling selection, and these schemes constitute the first space for production resource adjustment.
[0052] The first production resource adjustment space is then traversed and optimized based on the multidimensional sufficiency evaluation constraints. This process first performs a multidimensional sufficiency evaluation on each resource allocation scheme in the first production resource adjustment space, based on the order-dependent resource map, to generate a corresponding sufficiency evaluation sequence. Each set of sufficiency evaluation sequences is then compared and anomaly detected based on the pre-set multidimensional sufficiency evaluation constraints. The system then determines whether any resource dimensions do not meet the threshold and outputs the anomaly detection results. Finally, based on the anomaly detection results for each scheme, resource combination schemes are selected whose resource dimensions meet the multidimensional sufficiency evaluation constraints in all dimensions to form the second production resource adjustment space.
[0053] Furthermore, in the method provided in the embodiment of the application, the first production resource adjustment space is optimized according to the sufficiency evaluation multi-dimensional constraint traversal to construct the second production resource adjustment space, and further includes: Based on the order-dependent resource map, the first space for production resource adjustment is traversed to perform multidimensional sufficiency evaluation to obtain a sufficiency evaluation sequence for each plan; anomaly detection is performed on the sufficiency evaluation sequence for each plan according to the multidimensional constraints of the sufficiency evaluation to obtain anomaly detection results for each plan; and the first space for production resource adjustment is selected based on the anomaly detection results for each plan to obtain the second space for production resource adjustment.
[0054] In this embodiment, based on the order-dependent resource map, each set of resource compensation solutions generated in the first production resource adjustment space is first traversed and a multi-dimensional sufficiency evaluation is performed. Specifically, each set of compensation resource configurations is compared against the order-dependent resource map, and the equipment resource sufficiency, raw material resource sufficiency, human resource sufficiency, and energy resource sufficiency are recalculated to generate a sufficiency evaluation sequence corresponding to the solution.
[0055] After the sufficiency evaluation is complete, the sufficiency evaluation sequence for each solution is verified item by item according to the preset multi-dimensional sufficiency evaluation constraints, and anomaly detection is performed. During this process, the sufficiency value of each resource dimension is compared with its corresponding threshold. If the sufficiency of a dimension is lower than its constraint value, the dimension is judged to be abnormal, marked as unsatisfied, and the anomaly detection result for the solution is output, which contains the status mark information of each resource dimension under the solution.
[0056] Finally, based on the anomaly detection results of each plan, the constraint screening method is used to screen all the plans in the first space of production resource adjustment, eliminate the configuration plans with abnormal resource dimensions, and only retain the adjustment plans whose all resource dimensions meet the multi-dimensional constraints of abundance evaluation, and finally form the second space of production resource adjustment.
[0057] Step S500: introducing a hardware production risk prediction model to perform global optimization on the second space of production resource adjustment, determining a hardware production resource optimization strategy, and optimizing resources of the hardware manufacturing workshop according to the hardware production resource optimization strategy.
[0058] In an embodiment of the present application, a hardware production risk prediction model is introduced to perform global optimization on the second space of production resource adjustment. First, risk analysis and screening are performed on each resource adjustment scheme in the second space of production resource adjustment according to the hardware production risk prediction model, and a third space of production resource adjustment containing low-risk schemes is established. Subsequently, weights are assigned based on preset multi-dimensional risk prediction indicators, including equipment resource risk, raw material resource risk, human resource risk, and energy resource risk, to construct a production global risk analysis model that comprehensively evaluates the impact of various risks. Finally, based on the production global risk analysis model, the schemes in the third space of production resource adjustment are evaluated and ranked, and the production global risk minimization optimization is performed to screen out the optimal resource allocation scheme and generate a hardware production resource optimization strategy.
[0059] Furthermore, in the method provided in the embodiment of the application, a hardware production risk prediction model is introduced to perform global optimization on the second space of production resource adjustment to determine the hardware production resource optimization strategy, and further includes: According to the hardware production risk prediction model, the second space of production resource adjustment is optimized for risk, and the third space of production resource adjustment is established; according to the risk prediction multidimensional indicators of the hardware production risk prediction model, weights are allocated to obtain a production global risk analysis model, and the risk prediction multidimensional indicators include equipment resource risk, raw material resource risk, human resource risk and energy resource risk; according to the production global risk analysis model, the third space of production resource adjustment is optimized for production global risk minimization to generate the hardware production resource optimization strategy.
[0060] In this embodiment, risk optimization is first performed on the second production resource adjustment space based on the hardware production risk prediction model. Specifically, each nth production resource adjustment plan (n is a positive integer) in the second production resource adjustment space is traversed and extracted. Based on the process structure and resource status information of the current hardware manufacturing workshop, a corresponding hardware production virtual workshop is constructed. This nth plan is then implemented in the virtual workshop to perform scheduling simulation operations, generating corresponding nth resource virtual scheduling data. This nth resource virtual scheduling data is then input into the hardware production risk prediction model to obtain the corresponding nth production risk prediction result. This prediction result comprises risk coefficients in four dimensions: equipment resource risk coefficient, raw material resource risk coefficient, human resource risk coefficient, and energy resource risk coefficient. All coefficients are real numbers between 0 and 1. The nth production risk prediction result is compared with preset hardware production risk constraints. If all four risk coefficients are below corresponding thresholds (e.g., no more than 0.3), the nth production resource adjustment plan is added to the third production resource adjustment space.
[0061] Subsequently, weights are assigned based on the multi-dimensional risk prediction indicators of the hardware production risk prediction model. During this process, technical experts set fixed weights for equipment resource risk, raw material resource risk, human resource risk, and energy resource risk. For example, the equipment resource risk weight is set to 0.4, the raw material resource risk weight is set to 0.2, the human resource risk weight is set to 0.2, and the energy resource risk weight is set to 0.2. These fixed weights are used to weight the four risk factors of each adjustment plan, generating a global risk score representing the overall risk level of the plan, which forms the global production risk analysis model used for subsequent screening.
[0062] Finally, the global production risk analysis model is used to optimize the third space for production resource adjustment by minimizing global production risk. In this step, all adjustment options within the third space are traversed, their corresponding risk coefficients are input into the global risk analysis model to calculate a global risk score, and all scores are ranked and analyzed. Ultimately, the adjustment option with the lowest global risk score is selected as the optimal hardware production resource optimization strategy under the current environment.
[0063] Furthermore, in the method provided in the embodiment of the application, risk optimization is performed on the second production resource adjustment space according to the hardware production risk prediction model to establish a third production resource adjustment space, and the method further includes: According to the second space of production resource adjustment, the nth production resource adjustment plan is extracted, where n is a positive integer; according to the hardware manufacturing workshop, a hardware production virtual workshop is constructed, and virtual scheduling is performed in combination with the nth production resource adjustment plan to obtain nth resource virtual scheduling data; the nth resource virtual scheduling data is input into the hardware production risk prediction model to obtain the nth production risk prediction result; if the nth production risk prediction result meets the hardware production risk constraint, the nth production resource adjustment plan is added to the third space of production resource adjustment.
[0064] In this embodiment, the nth production resource adjustment plan is first extracted from the second production resource adjustment space. This plan includes a list of equipment resource allocations, a raw material allocation plan, human resource scheduling data, and an energy usage plan. This extraction method uses a sequential traversal, which sequentially reads each plan from the generated set of second production resource adjustment space plans.
[0065] Next, based on the basic information of the hardware manufacturing workshop, including the layout of production line stations, equipment types, work rhythm, material flow paths, and energy interface locations, a virtual workshop that reflects actual production characteristics is constructed. This virtual workshop is modeled using discrete event simulation methods. By setting resource objects and scheduling rules, it simulates the task execution process and resource call status, and has basic scheduling, waiting, occupation, and release behaviors. Then, the extracted nth solution is applied to the constructed virtual workshop to perform virtual scheduling simulation. The simulation process is driven by an event, simulating the resource operation process driven by the task schedule, and recording the usage of various resources throughout the production cycle, including the number of equipment starts and stops, the rhythm of raw material consumption, the length of human work hours, and energy consumption fluctuations. Finally, the virtual scheduling data of the nth resource is output.
[0066] This n-th resource virtual scheduling data is then input into a hardware production risk prediction model to perform a risk assessment. This hardware production risk prediction model is trained using a gradient boosting decision tree. The training data is derived from historical scheduling data, specifically historical resource scheduling records that have the same structure as the n-th resource virtual scheduling data. This historical data serves as input, and the output data is a risk coefficient assigned by technical experts based on this historical scheduling data. These coefficients include equipment resource risk coefficients, raw material resource risk coefficients, human resource risk coefficients, and energy resource risk coefficients, all of which are numerical values between 0 and 1.
[0067] Finally, the nth production risk prediction result is compared with the preset hardware production risk constraints. If all risk coefficients are less than or equal to their corresponding thresholds (for example, no higher than 0.3), the plan has low resource risk and is acceptable. At this point, the nth plan is added to the production resource adjustment third space. The preset hardware production risk constraints include equipment resource risk constraints, raw material resource risk constraints, human resource risk constraints, and energy resource risk constraints.
[0068] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects: The present application performs resource perception based on a hardware manufacturing workshop, establishes a hardware manufacturing resource map, and performs resource dependency analysis on the hardware order set of the hardware manufacturing workshop to generate an order dependency resource map; performs multi-dimensional sufficiency evaluation on the hardware manufacturing resource map based on the order dependency resource map, and establishes a resource sufficiency evaluation sequence; performs abnormality analysis on the resource sufficiency evaluation sequence based on the sufficiency evaluation multi-dimensional constraints, and determines the sufficiency abnormality factor; compensates and adjusts the hardware manufacturing resource map based on the sufficiency abnormality factor, establishes a first production resource adjustment space, and traverses and optimizes the first production resource adjustment space based on the sufficiency evaluation multi-dimensional constraints to construct a second production resource adjustment space; introduces a hardware production risk prediction model to perform global optimization on the second production resource adjustment space, determines a hardware production resource optimization strategy, and optimizes resources for the hardware manufacturing workshop based on the hardware production resource optimization strategy. The present invention solves the technical problems of complex resource dependence, imbalance between supply and demand, and insufficient scheduling optimization in the resource scheduling process of hardware manufacturing workshops in the prior art. By constructing a hardware manufacturing resource map and an order-dependent resource map, conducting multi-dimensional abundance evaluation and abnormal factor identification, and combining a risk prediction model to perform resource adjustment and optimization, the present invention achieves the technical effects of accurate perception of resource status, dynamic optimization of scheduling strategies, and minimization of production risks.
[0069] Example 2 is based on the same inventive concept as the intelligent production scheduling control method for a hardware manufacturing workshop in the above embodiment. Figure 2 As shown, the present application provides an intelligent production scheduling control system for hardware manufacturing workshops. The system and method embodiments in the present application are based on the same inventive concept. The system includes:
[0070] The resource perception module 11 is used to perceive resources according to the hardware manufacturing workshop, establish a hardware manufacturing resource map, and perform resource dependency analysis on the hardware order set of the hardware manufacturing workshop to generate an order dependency resource map; the abundance evaluation module 12 is used to perform multi-dimensional abundance evaluation on the hardware manufacturing resource map according to the order dependency resource map and establish a resource abundance evaluation sequence; the anomaly analysis module 13 is used to perform anomaly analysis on the resource abundance evaluation sequence according to the abundance evaluation multi-dimensional constraints and determine the abundance anomaly factor; the adjustment space construction module 14 is used to compensate and adjust the hardware manufacturing resource map according to the abundance anomaly factor, establish a first production resource adjustment space, and traverse and optimize the first production resource adjustment space according to the abundance evaluation multi-dimensional constraints to construct a second production resource adjustment space; the resource optimization module 15 is used to introduce a hardware production risk prediction model to perform global optimization on the second production resource adjustment space, determine a hardware production resource optimization strategy, and optimize the resources of the hardware manufacturing workshop according to the hardware production resource optimization strategy.
[0071] Furthermore, the system is also used to implement the following functions: Scheduling analysis is performed on the hardware order set to determine an order scheduling plan; multi-dimensional resource demand mining is performed on the hardware order set according to the order scheduling plan to obtain a multi-dimensional resource library of order demand; confidence fusion of each resource feature is performed on the multi-dimensional resource library of order demand to generate each resource dependency set; based on each resource dependency set, the order dependency resource map is constructed, and the order dependency resource map includes a dependent equipment resource map, a dependent raw material resource map, a dependent human resource map, and a dependent energy resource map.
[0072] Furthermore, the system is also used to implement the following functions: Activate resource abundance assessment factors, which include reserve adequacy, available time matching, alternative resource adequacy, and resource performance accuracy; based on the resource abundance assessment factors, perform an abundance analysis on the perceived equipment resource map according to the dependent equipment resource map to generate equipment resource abundance; based on the resource abundance assessment factors, perform an abundance analysis on the perceived raw material resource map according to the dependent raw material resource map to generate raw material resource abundance; based on the resource abundance assessment factors, perform an abundance analysis on the perceived human resource map according to the dependent human resource map to generate human resource abundance; based on the resource abundance assessment factors, perform an abundance analysis on the perceived energy resource map according to the dependent energy resource map to generate energy resource abundance, and combine the equipment resource abundance, the raw material resource abundance, and the human resource abundance to generate the resource abundance evaluation sequence.
[0073] Furthermore, the system is also used to implement the following functions: Based on the resource abundance assessment factor, multiple resource abundance assessment record sets are loaded; knowledge distillation is performed based on the multiple resource abundance assessment record sets to construct a resource abundance assessment model; the dependent device resource map and the perception device resource map are input into the resource abundance assessment model to obtain a device resource abundance assessment result; weights are assigned based on the resource abundance assessment factor to construct a resource abundance analysis model; abundance calculation is performed on the device resource abundance assessment result based on the resource abundance analysis model to obtain the device resource abundance.
[0074] Furthermore, the system is also used to implement the following functions: Based on the order-dependent resource map, the first space for production resource adjustment is traversed to perform multidimensional sufficiency evaluation to obtain a sufficiency evaluation sequence for each plan; anomaly detection is performed on the sufficiency evaluation sequence for each plan according to the multidimensional constraints of the sufficiency evaluation to obtain anomaly detection results for each plan; and the first space for production resource adjustment is selected based on the anomaly detection results for each plan to obtain the second space for production resource adjustment.
[0075] Furthermore, the system is also used to implement the following functions: According to the hardware production risk prediction model, the second space of production resource adjustment is optimized for risk, and the third space of production resource adjustment is established; according to the risk prediction multidimensional indicators of the hardware production risk prediction model, weights are allocated to obtain a production global risk analysis model, and the risk prediction multidimensional indicators include equipment resource risk, raw material resource risk, human resource risk and energy resource risk; according to the production global risk analysis model, the third space of production resource adjustment is optimized for production global risk minimization to generate the hardware production resource optimization strategy.
[0076] Furthermore, the system is also used to implement the following functions: According to the second space of production resource adjustment, the nth production resource adjustment plan is extracted, where n is a positive integer; according to the hardware manufacturing workshop, a hardware production virtual workshop is constructed, and virtual scheduling is performed in combination with the nth production resource adjustment plan to obtain nth resource virtual scheduling data; the nth resource virtual scheduling data is input into the hardware production risk prediction model to obtain the nth production risk prediction result; if the nth production risk prediction result meets the hardware production risk constraint, the nth production resource adjustment plan is added to the third space of production resource adjustment.
[0077] Furthermore, the system is also used to implement the following functions: Based on the equipment resource perception of the hardware manufacturing workshop, a perception equipment resource map is generated; based on the raw material resource perception of the hardware manufacturing workshop, a perception raw material resource map is generated; based on the human resource perception of the hardware manufacturing workshop, a perception human resource map is generated; based on the energy resource perception of the hardware manufacturing workshop, a perception energy resource map is generated; the perception equipment resource map, the perception raw material resource map, the perception human resource map and the perception energy resource map are integrated to generate the hardware manufacturing resource map.
[0078] Furthermore, the system is also used to implement the following functions: Equipment resource information is collected from the hardware manufacturing workshop to generate an equipment resource data set; data cleaning is performed on the equipment resource data set to obtain an equipment resource flow; and the equipment resource flow is graphically combed to obtain the perceived equipment resource map.
[0079] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0080] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.
[0081] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.
Claims
1. An intelligent production scheduling control method for a hardware manufacturing workshop, characterized in that: The method comprises: Perform resource perception based on the hardware manufacturing workshop, establish a hardware manufacturing resource map, and perform resource dependency analysis on the hardware order set of the hardware manufacturing workshop to generate an order dependency resource map; Performing a multi-dimensional sufficiency evaluation on the hardware manufacturing resource map according to the order-dependent resource map, and establishing a resource sufficiency evaluation sequence; Performing anomaly analysis on the resource abundance evaluation sequence according to the abundance evaluation multi-dimensional constraints to determine an abundance anomaly factor; The hardware manufacturing resource map is compensated and adjusted according to the abundance abnormality factor to establish a first production resource adjustment space, and the first production resource adjustment space is optimized through traversal according to the abundance evaluation multidimensional constraint to construct a second production resource adjustment space; A hardware production risk prediction model is introduced to perform global optimization on the second space of production resource adjustment, determine the hardware production resource optimization strategy, and optimize the resources of the hardware manufacturing workshop according to the hardware production resource optimization strategy.
2. The intelligent production scheduling control method for a hardware manufacturing workshop according to claim 1, characterized in that: Perform resource dependency analysis on the hardware order set of the hardware manufacturing workshop to generate an order dependency resource map, including: Perform scheduling analysis based on the hardware order set to determine an order scheduling plan; Perform multi-dimensional resource demand mining on the hardware order set according to the order scheduling plan to obtain a multi-dimensional resource library of order demand; Perform confidence fusion of resource features according to the multi-dimensional resource library of order requirements to generate resource dependency sets; According to the resource dependency sets, the order dependency resource map is constructed, and the order dependency resource map includes an equipment dependency resource map, a raw material dependency resource map, a human resource dependency map, and an energy dependency resource map.
3. The intelligent production scheduling control method for a hardware manufacturing workshop according to claim 1, characterized in that: Performing a multi-dimensional sufficiency evaluation on the hardware manufacturing resource map according to the order-dependent resource map, and establishing a resource sufficiency evaluation sequence, including: Activating resource abundance assessment factors, including reserve adequacy, available time matching, alternative resource adequacy, and resource performance accuracy; Based on the resource abundance assessment factor, performing sufficiency analysis on the sensing device resource map according to the dependent device resource map to generate device resource sufficiency; Based on the resource abundance assessment factor, performing an abundance analysis on the perceived raw material resource map according to the dependent raw material resource map to generate the raw material resource abundance; Based on the resource abundance assessment factor, performing sufficiency analysis on the perceived human resource map according to the dependent human resource map to generate human resource sufficiency; Based on the resource abundance assessment factor, the perceived energy resource map is analyzed for abundance according to the dependent energy resource map to generate energy resource abundance, and the resource abundance evaluation sequence is generated by combining the equipment resource abundance, the raw material resource abundance and the human resource abundance.
4. The intelligent production scheduling control method for a hardware manufacturing workshop according to claim 3, characterized in that: Based on the resource abundance assessment factor, performing sufficiency analysis on the sensing device resource map according to the dependent device resource map to generate device resource sufficiency, including: Based on the resource abundance assessment factor, loading multiple resource abundance assessment record sets; Performing knowledge distillation based on the multiple resource abundance assessment record sets to construct a resource abundance assessment model; Inputting the dependent device resource map and the sensing device resource map into the resource abundance assessment model to obtain a device resource abundance assessment result; Allocate weights according to the resource abundance assessment factors and construct a resource abundance analytical model; The resource sufficiency analysis model is used to perform sufficiency calculation on the device resource sufficiency evaluation result to obtain the device resource sufficiency.
5. The intelligent production scheduling control method for a hardware manufacturing workshop according to claim 1, characterized in that: The first production resource adjustment space is optimized according to the sufficiency evaluation multi-dimensional constraint traversal to construct the second production resource adjustment space, including: Based on the order-dependent resource graph, traverse the first production resource adjustment space to perform multi-dimensional sufficiency evaluation to obtain a sufficiency evaluation sequence for each solution; Performing anomaly detection on the adequacy evaluation sequence of each scheme according to the adequacy evaluation multidimensional constraint to obtain anomaly detection results for each scheme; The first production resource adjustment space is optimally selected based on the abnormality detection results of each solution to obtain the second production resource adjustment space.
6. The intelligent production scheduling control method for a hardware manufacturing workshop according to claim 1, characterized in that: A hardware production risk prediction model is introduced to perform global optimization on the second space of production resource adjustment to determine the hardware production resource optimization strategy, including: Perform risk optimization on the second production resource adjustment space according to the hardware production risk prediction model to establish a third production resource adjustment space; The weight distribution is performed based on the risk prediction multidimensional indicators of the hardware production risk prediction model to obtain a production global risk analysis model, wherein the risk prediction multidimensional indicators include equipment resource risk, raw material resource risk, human resource risk and energy resource risk; The global production risk analysis model is used to optimize the third space for production resource adjustment by minimizing the global production risk, and the hardware production resource optimization strategy is generated.
7. The intelligent production scheduling control method for a hardware manufacturing workshop according to claim 6, characterized in that: Performing risk optimization on the second production resource adjustment space according to the hardware production risk prediction model to establish a third production resource adjustment space, including: Extracting the nth production resource adjustment plan according to the second production resource adjustment space, where n is a positive integer; According to the hardware manufacturing workshop, a hardware production virtual workshop is constructed, and virtual scheduling is performed in combination with the production resource adjustment n-th plan to obtain n-th resource virtual scheduling data; Inputting the nth resource virtual scheduling data into the hardware production risk prediction model to obtain the nth production risk prediction result; If the nth production risk prediction result meets the hardware production risk constraint, the nth production resource adjustment plan is added to the production resource adjustment third space.
8. The intelligent production scheduling control method for a hardware manufacturing workshop according to claim 1, characterized in that: Conduct resource awareness based on the hardware manufacturing workshop and establish a hardware manufacturing resource map, including: Perform equipment resource perception based on the hardware manufacturing workshop and generate a perception equipment resource map; Perform raw material resource perception based on the hardware manufacturing workshop and generate a perceived raw material resource map; Performing human resource perception based on the hardware manufacturing workshop to generate a perceived human resource map; Perform energy resource sensing based on the hardware manufacturing workshop and generate a sensed energy resource map; The hardware manufacturing resource map is generated by integrating the perception equipment resource map, the perception raw material resource map, the perception human resource map and the perception energy resource map.
9. The intelligent production scheduling control method for a hardware manufacturing workshop according to claim 8, characterized in that: Based on the hardware manufacturing workshop, equipment resource perception is performed to generate a perception equipment resource map, including: Collecting equipment resource information from the hardware manufacturing workshop to generate an equipment resource data set; Performing data cleaning on the device resource data set to obtain a device resource flow; The device resource flow is graphically sorted to obtain the perception device resource map.
10. An intelligent production scheduling control system for hardware manufacturing workshops, characterized in that: The system is used to execute the intelligent production scheduling control method for a hardware manufacturing workshop as described in any one of claims 1 to 9, and the system includes: The resource perception module is used to perform resource perception based on the hardware manufacturing workshop, establish a hardware manufacturing resource map, and perform resource dependency analysis on the hardware order set of the hardware manufacturing workshop to generate an order dependency resource map; A sufficiency evaluation module is used to perform a multi-dimensional sufficiency evaluation on the hardware manufacturing resource map according to the order-dependent resource map, and establish a resource sufficiency evaluation sequence; An anomaly analysis module, configured to perform an anomaly analysis on the resource abundance evaluation sequence according to the abundance evaluation multi-dimensional constraints, and determine an abundance anomaly factor; An adjustment space construction module is used to compensate and adjust the hardware manufacturing resource map according to the abundance abnormality factor, establish a first production resource adjustment space, and traverse and optimize the first production resource adjustment space according to the abundance evaluation multidimensional constraint to construct a second production resource adjustment space; The resource optimization module is used to introduce a hardware production risk prediction model to perform global optimization on the second space of production resource adjustment, determine the hardware production resource optimization strategy, and optimize the resources of the hardware manufacturing workshop according to the hardware production resource optimization strategy.
Citation Information
Cited By
Printing order commission distribution and resource allocation linkage method based on multi-channel data collaboration
CN121414087A
