Multi-process energy consumption dynamic optimization control system of precious metal processing production line

Abstract

The invention discloses a multi-process energy consumption dynamic optimization control system for a precious metal processing production line, and relates to the technical field of precious metal processing, and the system comprises a data collection module which is used for collecting energy consumption data, process parameters and material flow data of equipment in real time; the optimization decision module comprises an energy consumption modeling unit and a dynamic optimization unit; the energy consumption modeling unit is used for establishing an energy consumption digital twin model for key equipment on a production line; the dynamic optimization unit is used for receiving and calculating a current optimal process parameter set value and an optimization instruction for adjusting the operation power and rhythm of equipment; and the driving execution module is used for realizing collaborative energy consumption optimization control of multiple processes. The method has the advantages that accurate energy consumption perception is achieved by constructing the energy consumption digital twinborn model, meanwhile, order merging is intelligently decided based on the material flow state and the order delivery time, and double optimization of overall energy efficiency improvement of the production line and comprehensive energy consumption cost is achieved.

Description

Technical Field

[0001] This invention relates to the field of precious metal processing technology, specifically to a multi-process energy consumption dynamic optimization control system for a precious metal processing production line. Background Technology

[0002] Precious metal processing is a high-energy-consuming process industry, with production lines typically involving multiple complex processes such as smelting, hot rolling, annealing, and cold rolling. Currently, energy consumption control in the industry is mostly limited to the level of individual equipment, such as achieving localized energy savings by improving furnace insulation materials or increasing motor efficiency. While some advanced energy management systems can monitor energy consumption across the entire line, their optimization strategies are often static and lagging, making it difficult to cope with dynamic factors such as order changes and equipment status fluctuations. More importantly, existing systems generally lack consideration for the coordination of "material flow" and "energy flow," with energy consumption optimization for each process being independent and even conflicting, making it impossible to achieve optimal control of total energy consumption at the system level and resulting in significant energy waste.

[0003] In the specific context of precious metal processing, the materials are of high value, the processes are demanding, and production is often conducted in small-batch, multi-variety order patterns. This presents unique optimization challenges: while simple order queuing can guarantee delivery, it cannot mitigate the energy consumption of high-energy-consuming equipment, such as the single-start energy consumption of annealing furnaces, by merging processes; on the other hand, blindly merging orders may disrupt downstream production rhythms due to differences in process paths between different orders, increasing work-in-process inventory and ultimately raising overall costs. Therefore, current technology lacks an intelligent control system capable of dynamically assessing the energy efficiency and production disruption risks of order merging and performing real-time, collaborative optimization accordingly. This has become a key bottleneck restricting precious metal processing enterprises from further achieving energy conservation and cost reduction. Summary of the Invention

[0004] To solve the above-mentioned technical problems, a multi-process energy consumption dynamic optimization control system for a precious metal processing production line is provided. This technical solution solves at least one of the technical problems mentioned in the background section.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A multi-process energy consumption dynamic optimization control system for a precious metal processing production line includes:

[0007] The data acquisition module includes smart meters, process sensors, and material identification devices installed on equipment in each process of the production line, for real-time acquisition of equipment energy consumption data, process parameters, and material flow data;

[0008] An optimization decision-making module is communicatively connected to the data acquisition module, and the optimization decision-making module includes an energy consumption modeling unit and a dynamic optimization unit.

[0009] The energy consumption modeling unit is used to establish a digital twin model of energy consumption for key equipment on the production line based on historical and real-time data.

[0010] The dynamic optimization unit is used to receive real-time production plans and energy price signals, and to perform the following operations independently for each high-energy-consuming process: based on its corresponding energy consumption model, with the goal of minimizing the total energy consumption of the process, calculate the current optimal process parameter settings.

[0011] Based on the status of material flow and order delivery dates, dynamically determine whether to activate the order merging strategy and calculate optimized instructions for adjusting equipment operating power and rhythm;

[0012] The drive execution module is communicatively connected to the optimization decision module. Based on the received optimization instructions, the drive execution module adjusts the operating status of the corresponding equipment through an independent control loop to achieve collaborative energy consumption optimization control of multiple processes.

[0013] Preferably, the step of dynamically determining whether to initiate an order consolidation strategy based on the status of the material flow and the order delivery date specifically includes:

[0014] Analyze the complete process path of all pending orders and group orders with identical parameters for specified high-energy-consuming processes into the same candidate cluster;

[0015] For orders within the same candidate cluster, calculate the estimated energy-saving benefits of merging them into specified high-energy-consuming processes by reducing the number of equipment start-ups and shutdowns and increasing the single-processing capacity.

[0016] The production flow after order consolidation is simulated to predict whether it will cause serious work-in-process inventory buildup or equipment waiting in downstream processes. If the estimated waiting cost is lower than the energy-saving benefits, the consolidation strategy is initiated.

[0017] Preferably, the calculation of optimization instructions for adjusting the operating power and rhythm of the equipment specifically includes:

[0018] Continuously track the current location of each work-in-process order and its estimated time to reach the target merging process;

[0019] When the first order arrives at the buffer of the target merging process, a configurable dynamic wait time window is initiated for it;

[0020] Within this dynamic waiting time window, other orders arriving successively under the order merging strategy will be dynamically combined into a temporary production batch;

[0021] When the equipment is available, the production sequence of the temporary production batches is determined based on the order information of all temporary production batches, and processing instructions are issued immediately.

[0022] Preferably, the length of the dynamic waiting time window is adaptively adjusted by a high-power-priority mechanism, which specifically includes:

[0023] Based on historical energy consumption data, the average power consumption per unit time for each mergeable process is calculated and classified into high, medium and low power consumption levels.

[0024] Different waiting window base durations are set for processes with different power consumption levels, with the base duration for high-power processes being longer than that for low-power processes;

[0025] During operation, the current energy-saving benefits and the cost of capacity delay caused by waiting are dynamically calculated. When the net benefit is positive, the actual waiting window is automatically extended.

[0026] Preferably, determining the production order of temporary production batches based on the order information of all temporary production batches and immediately issuing processing instructions specifically includes:

[0027] The ratio of the metal content of the temporary production batch to the maximum capacity of the equipment is used as the capacity utilization score of the temporary production batch.

[0028] Prioritize orders based on their delivery deadlines, and use the sum of the product of the priority of all orders in a temporary production batch and the metal quantity of that order as the processing priority score for that temporary production batch.

[0029] Based on the capacity utilization score and processing priority score of all temporary production batches, the TOPSIS method is used to determine the production order of each temporary production batch.

[0030] The highest-ranked temporary production batch is fed into the equipment, and the equipment operating power is set based on the process parameters of the temporary production batch.

[0031] Preferably, the step of establishing an energy consumption digital twin model for key equipment on the production line based on historical and real-time data specifically includes:

[0032] Using machine learning algorithms, a proxy model describing the nonlinear relationship between equipment energy consumption and key process parameters and material properties was trained.

[0033] The real-time collected runtime data is input into the model to calibrate the model's predictive output online.

[0034] The model parameters are updated regularly using accumulated new production data to adapt to the slow degradation of equipment performance.

[0035] Preferably, the optimization decision module further includes a demand-side response unit, which is configured as follows:

[0036] Real-time acquisition of time-of-use (TOU) or real-time (RTU) electricity price signals from the power grid;

[0037] While meeting delivery deadlines, production plans for high-energy-consuming processes will be shifted from peak electricity price periods to off-peak electricity price periods.

[0038] Forecast the total short-term power demand for the entire line and control the total power demand below the contracted demand by fine-tuning the operating time of non-critical equipment.

[0039] Preferably, the system operates as follows:

[0040] During system initialization, the energy consumption modeling unit loads or trains the energy consumption digital twin model for each key device;

[0041] During production line operation, the data acquisition module collects energy consumption, process and material data in real time through various sensors and sends them to the dynamic optimization unit;

[0042] The dynamic optimization unit receives real-time production plans and energy price signals. For each high-energy-consuming process, it dynamically calculates the optimal process parameters based on its energy consumption model and order status, determines whether to activate the order merging strategy, and generates optimization instructions.

[0043] Based on the received optimization instructions, the drive execution module adjusts the power and operating rhythm of the corresponding equipment through independent control loops to achieve multi-process collaborative energy consumption optimization control.

[0044] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0045] This invention achieves a leap from single-point local optimization to multi-process collaborative dynamic optimization of precious metal processing production lines by constructing an energy consumption digital twin model, introducing an order merging strategy based on a dynamic rolling window, and a high-power-consumption-focused mechanism. It can significantly reduce the ineffective operating time and idle losses of high-energy-consuming equipment, and minimize the total energy consumption of the entire line while ensuring production cycle and order delivery time, thereby effectively reducing production costs and improving energy utilization efficiency and green manufacturing level. Attached Figure Description

[0046] Figure 1 This is a block diagram of the multi-process energy consumption dynamic optimization control system for the precious metal processing production line proposed in this invention.

[0047] Figure 2 This is a flowchart of the method for dynamically determining whether to initiate an order merging strategy proposed in this invention;

[0048] Figure 3This is a flowchart of the method for calculating optimized instructions for adjusting the operating power and rhythm of equipment, as proposed in this invention.

[0049] Figure 4 This is a flowchart of the method for determining the production sequence of temporary production batches proposed in this invention;

[0050] Figure 5 This is a schematic diagram of the computer-readable storage medium structure in this scheme.

[0051] The numbers on the map are:

[0052] 500 - Electronic device; 501 - Bus; 502 - CPU; 503 - ROM; 504 - RAM; 505 - Communication port; 506 - Input / output component; 507 - Hard disk; 508 - User interface; 600 - Computer-readable storage medium. Detailed Implementation

[0053] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0054] Reference Figure 1 As shown, a multi-process energy consumption dynamic optimization control system for a precious metal processing production line includes:

[0055] The data acquisition module includes smart meters, process sensors, and material identification devices installed on equipment at each stage of the production line. It is used to collect energy consumption data, process parameters, and material flow data of the equipment in real time. By deploying multiple types of sensors, it achieves comprehensive and real-time data collection of the three core elements of "energy flow," "process flow," and "material flow" in the production process, providing an accurate and timely data foundation for subsequent optimization decisions and solving the problems of data silos and incomplete information in traditional energy management.

[0056] The optimization decision-making module communicates with the data acquisition module and includes an energy consumption modeling unit and a dynamic optimization unit. As the core processing unit, the optimization decision-making module receives real-time information from the data acquisition module and divides it into two functional units: "modeling" and "optimization." This division of labor clearly defines the complete decision-making logic chain from understanding the equipment's energy consumption characteristics to formulating specific energy-saving strategies, ensuring the scientific rigor and relevance of the optimization.

[0057] The energy consumption modeling unit is used to build digital twin models of energy consumption for key equipment on the production line based on historical and real-time data. Utilizing digital twin technology, it creates virtual models of key equipment that dynamically reflect the complex relationship between equipment energy consumption and various operating parameters. This allows the system not only to describe historical energy consumption but also to predict future energy consumption under different process settings, making it possible to find the optimal operating point.

[0058] The dynamic optimization unit receives real-time production plans and energy price signals, and performs the following operations independently for each high-energy-consuming process: based on its corresponding energy consumption model, it calculates the current optimal process parameter settings with the goal of minimizing the total energy consumption of the process.

[0059] Based on the status of material flow and order delivery dates, the system dynamically determines whether to activate the order merging strategy and calculates optimization instructions to adjust equipment operating power and rhythm. Through two main means, "process parameter optimization" and "order merging strategy", energy saving is achieved at the equipment operation level and production scheduling level, respectively, making optimization control more refined and comprehensive.

[0060] The drive execution module communicates with the optimization decision module. Based on received optimization instructions, the drive execution module adjusts the operating status of corresponding equipment through independent control loops, achieving coordinated energy consumption optimization control across multiple processes. The "independent control loops" directly adjust the equipment, ensuring the speed and accuracy of instruction execution. The ultimate goal, "coordinated energy consumption optimization control across multiple processes," clarifies that the entire system does not optimize individual devices in isolation, but rather takes a holistic approach, considering the entire production line, to achieve system-wide energy efficiency improvements.

[0061] The workflow of the above system is as follows:

[0062] During system initialization, the energy consumption modeling unit loads or trains the energy consumption digital twin model for each key device;

[0063] During production line operation, the data acquisition module collects energy consumption, process and material data in real time through various sensors and sends them to the dynamic optimization unit;

[0064] The dynamic optimization unit receives real-time production plans and energy price signals. For each high-energy-consuming process, it dynamically calculates the optimal process parameters based on its energy consumption model and order status, determines whether to activate the order merging strategy, and generates optimization instructions.

[0065] Based on the received optimization instructions, the drive execution module adjusts the power and operating rhythm of the corresponding equipment through independent control loops to achieve multi-process collaborative energy consumption optimization control.

[0066] Specifically, refer to Figure 2As shown, the dynamic determination of whether to activate the order merging strategy based on the status of the material flow and the order delivery date specifically includes:

[0067] Analyze the complete process path of all pending orders and group orders with identical parameters for specified high-energy-consuming processes into the same candidate cluster;

[0068] For orders within the same candidate cluster, calculate the estimated energy-saving benefits of merging them into specified high-energy-consuming processes by reducing the number of equipment start-ups and shutdowns and increasing the single-processing capacity.

[0069] The production flow after order merging is simulated to predict whether it will cause serious work-in-process backlog or equipment waiting in downstream processes. If the estimated waiting cost is lower than the energy-saving benefits, the merging strategy is initiated. Specifically, when initiating the merging strategy, the subsequent processes of the merged orders need to have low overlap to ensure that there is no work-in-process backlog in downstream processes.

[0070] The intelligent decision-making logic of the order consolidation strategy is not simply order piling up, but a multi-stage evaluation process involving "identifying candidate clusters, quantifying energy-saving benefits, and assessing downstream impact." Its core lies in conducting a comprehensive cost-benefit analysis, using simulation and prediction to weigh the energy-saving benefits of high-energy-consuming processes against potential downstream production efficiency losses. Specifically, it introduces the key constraint of "low overlap in subsequent processes" to ensure that consolidation decisions do not transfer bottlenecks downstream, thus maintaining the overall smoothness and stability of the production flow while achieving energy savings. This effectively avoids the risk of sacrificing the overall production rhythm for the sake of energy saving in a single process. Through accurate simulation and prediction, it proactively identifies and avoids potential downstream congestion, thereby significantly reducing start-up and shutdown losses and unit consumption of high-energy-consuming equipment while ensuring the smooth execution of the entire production plan, achieving synergistic optimization of energy saving, cost reduction, and delivery efficiency.

[0071] Reference Figure 3 As shown, the specific optimization instructions for adjusting the operating power and rhythm of the equipment include:

[0072] Continuously track the current location of each work-in-process order and its estimated time to reach the target merging process;

[0073] When the first order arrives at the buffer of the target merging process, a configurable dynamic wait time window is initiated for it;

[0074] Within this dynamic waiting time window, other orders arriving successively under the order merging strategy will be dynamically combined into a temporary production batch;

[0075] When the equipment is available, the production sequence of the temporary production batches is determined based on the order information of all temporary production batches, and processing instructions are issued immediately.

[0076] By tracking order progress in real time and introducing a "dynamic waiting time window" mechanism, the merging intent at the planning level is transformed into executable dynamic batches. This method doesn't rigidly wait for all orders to arrive; instead, it uses the first arriving order as a trigger point, flexibly aggregating orders within a limited, controllable window. This creates opportunities for batch processing to achieve energy savings, while the window constraint avoids the risk of delivery delays caused by indefinite order waiting. Finally, when equipment is available, an intelligent sorting algorithm quickly determines the processing order, ensuring that optimized instructions are implemented rapidly. Based on real-time location tracking and a dynamic window instruction generation mechanism, the feasibility and efficiency of the order merging strategy are significantly improved. By achieving a precise balance between time and efficiency, it fully utilizes waiting time to form more economical production batches, effectively reducing the energy consumption of equipment start-up and shutdown per unit product. Furthermore, through rapid response and immediate scheduling when equipment is available, it minimizes the time orders spend in the buffer zone, thus achieving energy-saving goals while ensuring production line responsiveness and on-time order delivery.

[0077] The length of the dynamic wait time window is adaptively adjusted by a high-power-priority mechanism, which specifically includes:

[0078] Based on historical energy consumption data, the average power consumption per unit time for each mergeable process is calculated and classified into high, medium and low power consumption levels.

[0079] Different waiting window base durations are set for processes with different power consumption levels, with the base duration for high-power processes being longer than that for low-power processes;

[0080] During operation, the current energy-saving benefits and the cost of capacity delay caused by waiting are dynamically calculated. When the net benefit is positive, the actual waiting window is automatically extended.

[0081] The high-power consumption focus mechanism reflects the refinement and economy of the system optimization strategy. Instead of adopting a fixed waiting duration, it establishes an intelligent decision-making model of "benchmark + dynamic adjustment". This mechanism first treats processes differently based on the importance of energy consumption, acknowledging that high-power consumption processes have greater energy-saving potential and are worthy of investing more waiting time. Furthermore, during operation, it introduces real-time cost-benefit analysis, converting abstract waiting into quantifiable "energy-saving benefits" and "delay costs", and taking the net benefit as positive as the only criterion for extending the waiting time. This ensures that each adjustment of the waiting duration has clear economic rationality, achieving a dynamic optimal balance between energy conservation and production efficiency. The adaptive adjustment mechanism can accurately allocate limited waiting resources to the links with the greatest energy-saving benefits, thereby significantly improving the overall energy-saving efficiency. By dynamically weighing real-time benefits and costs, it avoids the drawbacks of the "one-size-fits-all" strategy. It can obtain the maximum energy-saving benefits by appropriately extending the window for high-power consumption processes and terminate unnecessary waiting in a timely manner when the net benefit decreases, effectively preventing production capacity losses or delivery risks caused by excessive merging. Ultimately, it maximizes the overall energy efficiency of the system while ensuring the smoothness of production.

[0082] Refer to Figure 4 As shown, based on the order information of all temporary production batches, determining the production order of the temporary production batches and immediately issuing processing instructions specifically includes:

[0083] Taking the ratio of the metal quantity of the temporary production batch to the maximum production capacity of the equipment as the production capacity utilization score of the temporary production batch. The production capacity utilization score represents the utilization rate of this processing for the equipment and can effectively avoid the situation of equipment idling.

[0084] Attaching priorities to orders based on the order delivery time limit, and taking the sum of the products of the priorities of all orders in the temporary production batch and the metal quantity of this order as the processing priority score of the temporary production batch. The processing priority score represents the urgency of the orders under this batch. For orders with a high degree of urgency, production and processing need to be carried out first.

[0085] Based on the production capacity utilization scores of all temporary production batches and the processing priority scores of the temporary production batches, using the TOPSIS method to determine the production order of each temporary production batch.

[0086] Sending the temporary production batch ranked at the top to the equipment and setting the operating power of the equipment based on the process parameters of the temporary production batch.

[0087] Specifically, the specific steps of the TOPSIS method are as follows:

[0088] Normalizing the production capacity utilization scores of all temporary production batches to obtain the production capacity utilization standard scores of the temporary production batches.

[0089] The processing priority score of the temporary production batch is normalized to obtain the processing priority standard score of the temporary production batch.

[0090] The maximum value of the capacity utilization standard score and the maximum value of the processing priority standard score of all temporary production batches are selected as the ideal optimal solution.

[0091] The minimum value of the capacity utilization standard score and the minimum value of the processing priority standard score of all temporary production batches are selected as the ideal worst solution.

[0092] Establish a Cartesian coordinate system with the capacity utilization standard score as the Y-axis and the processing priority standard score as the X-axis. Mark the capacity utilization standard score and processing priority standard score of all temporary production batches as coordinate points in the Cartesian coordinate system, and mark the ideal optimal solution and the ideal worst solution.

[0093] Calculate the distance between the coordinate point corresponding to each temporary production batch and the ideal optimal solution and the ideal worst solution, and calculate the priority score of the temporary production batch. Sort the production order of the temporary production batches in descending order of priority score.

[0094] Specifically, the formula for calculating priority score is as follows:

[0095] ;

[0096] In the formula, This represents the distance between the coordinates of the temporary production batch and the ideal optimal solution. Let be the distance between the coordinate point corresponding to the temporary production batch and the ideal worst solution. Priority scores are given to temporary production batches.

[0097] By quantifying the two key but potentially conflicting objectives of "capacity utilization" and "order delivery urgency" into comparable scores and eliminating the influence of dimensions through normalization, the core of this method lies in comprehensively evaluating the relative merits of batches by calculating the geometric distance between each batch and hypothetical "ideal optimal solution" and "ideal worst solution." This ranking mechanism does not simply prioritize a single indicator but seeks a balanced and relatively optimal solution between the two dimensions of objectives. This ensures that the ranking result simultaneously considers equipment energy efficiency and order delivery satisfaction. Employing the TOPSIS method for production sequence decision-making, it can scientifically and objectively coordinate the potential contradictions between equipment utilization efficiency and order delivery priority. Through mathematical modeling, it avoids the subjectivity of manual ranking, ensuring that the final determined processing sequence is the compromise optimal solution that is closest to both "maximum capacity utilization" and "maximum delivery priority." Thus, at the operational level, it achieves synergistic optimization of energy saving (by increasing the processing volume per batch) and ensuring delivery time (by prioritizing urgent orders), improving the intelligence level of production scheduling and overall economic efficiency.

[0098] Building energy consumption digital twin models for key equipment on the production line based on historical and real-time data specifically includes:

[0099] Using machine learning algorithms, a proxy model describing the nonlinear relationship between equipment energy consumption and key process parameters and material properties was trained.

[0100] The real-time collected runtime data is input into the model to calibrate the model's predictive output online.

[0101] The model parameters are updated regularly using accumulated new production data to adapt to the slow degradation of equipment performance.

[0102] The construction and maintenance of an energy consumption digital twin model is a dynamic, closed-loop, and continuous optimization process. It utilizes machine learning algorithms to extract complex nonlinear relationships from massive amounts of data that are difficult to describe using traditional mechanistic formulas, laying the foundation for high-precision energy consumption prediction. The online calibration mechanism acts like a "real-time navigation" system for the model, effectively correcting prediction deviations caused by instantaneous disturbances and ensuring consistency between its output and the physical world. Regular parameter updates enable the model to "learn and evolve," tracking gradual performance changes caused by aging and wear, ensuring consistent prediction accuracy throughout the entire equipment lifecycle. This effectively overcomes the shortcomings of traditional static models, such as insufficient accuracy and poor adaptability in complex industrial scenarios. The created digital twin model not only accurately simulates and predicts energy consumption under different operating conditions, providing a reliable basis for optimization decisions, but its self-calibration and updating characteristics also ensure the long-term effectiveness of optimization strategies. This provides a solid, reliable, and evolving digital foundation for continuous energy saving and consumption reduction on production lines.

[0103] In some preferred embodiments, the optimization decision module further includes a demand-side response unit, which is configured as follows:

[0104] Real-time acquisition of time-of-use (TOU) or real-time (RTU) electricity price signals from the power grid;

[0105] While meeting delivery deadlines, production plans for high-energy-consuming processes will be shifted from peak electricity price periods to off-peak electricity price periods.

[0106] Forecast the total short-term power demand for the entire line and control the total power demand below the contracted demand by fine-tuning the operating time of non-critical equipment.

[0107] The demand-side response unit (DSR) expands the system's optimization scope from within a single production line to interaction with the external power grid environment. By responding to electricity price signals in real time, it performs more macro-level scheduling of energy consumption over time. Its core is implementing a "peak shaving and valley filling" strategy under strict delivery constraints. It not only shifts the main load of high-energy-consuming processes but also refines the total power curve by accurately predicting and fine-tuning the operating times of non-critical auxiliary equipment. This achieves dual control over the enterprise's overall electricity costs and grid demand charges. The DSR directly incorporates energy costs into the production control logic, effectively utilizing electricity price differences to proactively schedule high-energy-consuming production activities to low-price periods, significantly reducing the enterprise's electricity costs. Simultaneously, by precisely controlling the total power peak to not exceed contracted demand, it avoids hefty demand penalties. This not only brings direct economic benefits to the factory but also makes it a flexible grid interaction resource, contributing to the stable operation of the grid and achieving a balance between economic and social benefits.

[0108] Figure 5 This is a schematic diagram of a computer-readable storage medium structure provided in one embodiment of this application. Figure 5 The diagram illustrates a computer-readable storage medium 600 according to one embodiment of this application. The computer-readable storage medium 600 stores computer-readable instructions. When executed by a processor, these instructions can drive the operation of a multi-process energy consumption dynamic optimization control system for a precious metal processing production line according to an embodiment of this application, as described above with reference to the accompanying drawings. The computer-readable storage medium 600 includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0109] In summary, the advantages of this invention are as follows: by constructing an energy consumption digital twin model to achieve accurate energy consumption perception, and by integrating real-time production plans and energy price signals, process parameter settings are dynamically optimized on a process-by-process basis. At the same time, based on material flow status and order delivery dates, intelligent decision-making for order merging is made. Thus, while ensuring production delivery, the direct energy consumption of high-energy-consuming processes and equipment start-up and shutdown losses in precious metal processing are significantly reduced. Furthermore, the overall power load is smoothed through demand-side response, ultimately achieving a dual optimization of overall production line energy efficiency and comprehensive energy costs.

[0110] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A multi-process energy consumption dynamic optimization control system for a precious metal processing production line, characterized in that, The application relates to a production line energy consumption optimization system, comprising: a data acquisition module, which comprises intelligent electric meters, process sensors and material recognition devices arranged on production line equipment at each process, for real-time acquisition of equipment energy consumption data, process parameters and material flow data; an optimization decision module, which is in communication connection with the data acquisition module, and comprises an energy consumption modeling unit and a dynamic optimization unit; the energy consumption modeling unit is used for establishing an energy consumption digital twin model for key equipment on the production line based on historical data and real-time data; the dynamic optimization unit is used for receiving real-time production plans and energy price signals, and independently performing the following operations for each high-energy-consumption process: based on the corresponding energy consumption model, the optimal process parameter setting value is calculated with the target of minimizing the total energy consumption of the process; based on the state of the material flow and the order delivery period, it is dynamically judged whether to start the order merging strategy, and the optimization instructions for adjusting the running power and rhythm of the equipment are calculated; a driving execution module, which is in communication connection with the optimization decision module, and adjusts the running state of the corresponding equipment through an independent control loop according to the received optimization instructions, so as to realize collaborative energy consumption optimization control of multiple processes.

2. The multi-process energy consumption dynamic optimization control system of a precious metal processing production line according to claim 1, characterized in that, The dynamic judgment of whether to start the order merging strategy based on the state of the material flow and the order delivery period specifically comprises: analyzing the complete process paths of all to-be-processed orders, and grouping orders with the same specified high-energy-consumption process parameters into the same candidate cluster; for the orders in the same candidate cluster, the estimated energy-saving benefits brought by reducing the number of equipment start-stop times and improving the single processing capacity after merging the orders at the specified high-energy-consumption process are calculated; the production flow after order merging is simulated, and it is predicted whether it will cause serious work-in-process accumulation or equipment waiting at downstream processes, and if the estimated waiting cost is lower than the energy-saving benefits, it is determined that the merging strategy is started.

3. The multi-process energy consumption dynamic optimization control system of a precious metal processing production line according to claim 2, characterized in that, The calculation of the optimization instructions for adjusting the running power and rhythm of the equipment specifically comprises: continuously tracking the current position of each in-process order and the time of expected arrival at the target merging process; when the first order arrives at the buffer zone of the target merging process, a configurable dynamic waiting time window is started for the order; within the dynamic waiting time window, other orders under the order merging strategy that arrive successively are dynamically combined into a temporary production batch; when the equipment is available, the production order of the temporary production batch is determined based on the order information of all temporary production batches, and processing instructions are immediately issued.

4. The multi-process energy consumption dynamic optimization control system of a precious metal processing production line according to claim 3, characterized in that, The length of the dynamic waiting time window is adaptively adjusted by a high-power-side mechanism, and the mechanism specifically comprises: based on historical energy consumption data, the average power consumption per unit time of each mergable process is calculated, and the processes are divided into high, medium and low power consumption levels; different waiting window reference time lengths are set for processes of different power consumption levels, and the reference time length of a high-power-consumption process is longer than that of a low-power-consumption process; in runtime, the current energy-saving benefits and the production capacity delay cost caused by waiting are dynamically calculated, and when the net benefits are positive, the actual waiting window is automatically lengthened.

5. The multi-process energy consumption dynamic optimization control system of a precious metal processing production line according to claim 4, characterized in that, The determination of the production order of the temporary production batch based on the order information of all temporary production batches and the immediate issuance of processing instructions specifically comprise: The ratio of the metal amount of the temporary production batch to the maximum production capacity of the equipment is taken as the production capacity utilization score of the temporary production batch; The priority of the order is added based on the order delivery deadline, and the sum of the product of the priority of all orders of the temporary production batch and the metal amount of the order is taken as the processing priority score of the temporary production batch; Based on the production capacity utilization score of all temporary production batches and the processing priority score of the temporary production batch, the production order of each temporary production batch is determined by using the TOPSIS method; The temporary production batch with the highest ranking is sent to the equipment, and the running power of the equipment is set based on the process parameters of the temporary production batch.

6. The multi-process energy consumption dynamic optimization control system of a precious metal processing production line according to claim 5, characterized in that, The energy consumption digital twin model of the key equipment on the production line is established based on historical data and real-time data, and specifically includes: Using a machine learning algorithm, a proxy model is trained to describe the nonlinear relationship between device energy consumption and key process parameters and material properties; The real-time collected running data is input into the model, and the prediction output of the model is calibrated online; Periodically update the model parameters using accumulated new production data to adapt to the slow degradation of device performance.

7. The multi-process energy consumption dynamic optimization control system of a precious metal processing production line according to claim 6, characterized in that, The demand side response unit is configured to: Real-time acquisition of time-of-use electricity price or real-time electricity price signal of power grid; Shift the production plan of high-energy-consumption processes from the peak electricity price period to the valley electricity price period under the premise of meeting the delivery deadline constraint; Predict the short-term total power demand of the whole line, and control the total power demand below the contract demand by fine-tuning the running time of non-critical equipment.

8. The multi-process energy consumption dynamic optimization control system of a precious metal processing production line according to any one of claims 1-7, characterized in that, The working process of the system is: When the system is initialized, the energy consumption modeling unit loads or trains the energy consumption digital twin model of each key equipment; When the production line is running, the data acquisition module collects energy consumption, process and material data in real time through various sensors and sends them to the dynamic optimization unit; The dynamic optimization unit receives real-time production plans and energy price signals, dynamically calculates the optimal process parameters for each high-energy-consumption process based on its energy consumption model and order status, and judges whether to start the order merging strategy to generate optimization instructions; The driving execution module adjusts the power and running rhythm of the corresponding equipment through independent control loops according to the received optimization instructions, realizing multi-process collaborative energy consumption optimization control.

9. A computer-readable storage medium storing computer-readable instructions, the computer-readable instructions comprising: The computer readable instructions are executed by the processor to drive the operation of the multi-process energy consumption dynamic optimization control system of the precious metal processing production line according to any one of claims 1-7. The computer readable instructions are executed by the processor to drive the operation of the multi-process energy consumption dynamic optimization control system of the precious metal processing production line according to any one of claims 1-7.

Images