Energy consumption control method and system for oxygen-free copper rod up-drawing process

Abstract

The invention relates to the technical field of metal processing control, in particular to an energy consumption control method and system for an oxygen-free copper rod up-drawing process, and the method comprises the steps: dividing the up-drawing process, and defining core energy efficiency parameters of each stage; collecting core energy efficiency parameters of each stage in real time, and generating a core energy consumption parameter set; comparing the core energy consumption parameter set with a preset energy consumption reference model, and identifying an abnormal mode existing in each stage; adjusting weights are dynamically distributed, and a temperature-speed-flow composite optimization instruction is generated; correcting parameters of the energy consumption reference model based on historical regulation and control data, and generating an energy efficiency control rule set adaptive to process state change; and performing real-time dynamic control on the energy consumption of each stage according to the updated energy efficiency control rule set and the composite optimization instruction. By means of the method, the problems of energy efficiency unbalance and static rule stiffness caused by multi-stage parameter isolated regulation and control in a traditional process are effectively solved, full-process self-adaptive parameter collaboration is achieved, power consumption per ton is remarkably reduced, and quality stability is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of metal processing control, and in particular to an energy consumption control method and system for an oxygen-free copper rod lifting process. Background Art

[0002] In the oxygen-free copper rod continuous casting process, energy consumption control and process stability are key factors restricting production efficiency and product quality. Traditional control methods often adopt a phased independent control strategy, treating the parameters of the smelting, pulling, cooling and other links as isolated variables for management. Although this fragmented control mode can achieve local parameter optimization, it ignores the dynamic coupling effect of the parameters in each stage. For example, the increase in pulling speed will change the flow characteristics of the molten copper liquid, which will in turn affect the temperature field distribution of the smelting furnace. The adjustment of the cooling flow rate needs to be coordinated with the release rate of the smelting waste heat, otherwise it will easily lead to thermodynamic imbalance. Due to the lack of a dynamic compensation mechanism across stages, the existing technology frequently experiences a sharp increase in energy consumption and energy efficiency fluctuations.

[0003] Current systems generally rely on static rule bases to adjust process parameters. Their control logic is based on idealized steady-state models and cannot adapt to dynamic conditions such as fluctuations in raw material properties and environmental interference. When the purity of the raw copper shifts or the ambient temperature and humidity suddenly change, the adjustment instructions of the fixed rule base are misaligned with actual needs, resulting in accumulated control deviations. For example, when the raw material purity decreases, the optimal ratio relationship between melting temperature and cooling flow rate changes nonlinearly, but the static rules still use the preset parameter combination, resulting in a sharp drop in cooling efficiency and an increase in energy consumption. In addition, the drift of mechanical properties caused by equipment aging is not incorporated into the control model, further exacerbating the mismatch of process parameters. This rigid control mode not only limits the room for energy efficiency improvement, but also leads to fluctuations in product quality, making it difficult to meet the stringent requirements of high-end applications for copper rod surface finish and crystal uniformity. Summary of the Invention

[0004] The present invention provides an energy consumption control method and system for an oxygen-free copper rod pulling process, thereby effectively solving the problems pointed out in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is: An energy consumption control method for an oxygen-free copper rod pulling process, comprising: The pull-up process is divided into the melting stage, the pulling stage and the cooling stage, and the core energy efficiency parameters of each stage are defined; Real-time collection of core energy efficiency parameters at each stage, data synchronization, and generation of core energy consumption parameter sets; Comparing the core energy consumption parameter set with a preset energy consumption benchmark model to identify abnormal patterns in each stage; Dynamically assign adjustment weights based on abnormal mode types and generate temperature-speed-flow composite optimization instructions; Correct the energy consumption benchmark model parameters based on historical control data to generate an energy efficiency control rule set that adapts to changes in process status; According to the updated energy efficiency control rule set and the temperature-speed-flow composite optimization instruction, the energy consumption of each stage of the upstream process is dynamically controlled in real time.

[0006] Furthermore, the core energy consumption parameter set is compared with a preset energy consumption benchmark model to identify abnormal patterns in each stage, including: Sliding window smoothing is performed on the melting temperature gradient data, and the high-frequency harmonic energy ratio of the traction power is extracted through time-frequency transformation; Comparing the smoothed temperature gradient with the dynamic threshold baseline, matching the high-frequency harmonic energy ratio with the equipment loss feature library, and simultaneously calculating the deviation rate of the cooling efficiency relative to the historical mean; The processed parameter set is input into the energy consumption benchmark model for multi-dimensional comparison. When the comparison result of any dimension exceeds the preset ratio range of the corresponding benchmark value, an abnormal flag of the corresponding stage is triggered.

[0007] Furthermore, after the abnormal flag of the corresponding stage is triggered, it also includes: Allocate control resources in order of priority based on the abnormal stage type and generate cross-stage linkage process parameter compensation instructions; Verifying the effectiveness of the compensation instruction based on the real-time collected energy consumption data, and when the unit product energy consumption reduction rate does not reach a preset threshold, reversely correcting the parameter association weights in the energy efficiency control rule set; The verified valid parameter compensation instructions are bound to the current process state characteristics and then stored in the energy efficiency control rule set.

[0008] Furthermore, adjustment weights are dynamically allocated according to the abnormal mode type to generate temperature-speed-flow composite optimization instructions, including: Assign adjustment weights based on abnormal pattern types. For smelting abnormalities, the main adjustment item is temperature parameters; for traction abnormalities, the main adjustment item is speed parameters; and for cooling abnormalities, the main adjustment item is flow parameters. Generate coordinated compensation amounts for temperature, speed, and flow rate based on the adjustment amplitude of the main adjustment item and the dynamic constraint relationship between process parameters; The collaborative compensation amounts are synthesized into composite optimization instructions according to weight ratios, the effectiveness of the instructions is verified through real-time energy consumption data, and the weight allocation strategy is iteratively updated based on the verification results.

[0009] Furthermore, the energy consumption benchmark model parameters are modified based on historical control data to generate an energy efficiency control rule set that adapts to changes in process status, including: Accumulate the temperature compensation, speed correction coefficient and flow adjustment amplitude in the historical control records, and select the effective control records that meet the preset energy consumption reduction conditions; Extracting correlation rules between process parameters in the effective control records and updating parameters of the energy consumption benchmark model; Based on the updated energy consumption benchmark model, a subset of energy efficiency control rules associated with process state characteristics is generated; The energy efficiency control rule subset is matched with the real-time process status data to generate an optimized parameter set adapted to the current working conditions.

[0010] Furthermore, according to the updated energy efficiency control rule set and the temperature-speed-flow composite optimization instruction, the energy consumption of each stage of the upstream process is dynamically controlled in real time, including: Identify the current process stage, and call a rule subset corresponding to the stage from the energy efficiency control rule set; Generate a process parameter adjustment instruction for the current stage based on the dynamic constraint relationship in the rule subset and the synergistic compensation amount in the composite optimization instruction; The execution result of the parameter adjustment instruction is fed back to the energy efficiency control rule set as historical control data to drive the update iteration of the rule subset.

[0011] Furthermore, the method further comprises: When generating the composite optimization instruction, synchronously calculating the impact value of the parameter adjustment on the constraint conditions of each dimension; When any dimension is detected to exceed the safety threshold, the dynamic limiting mechanism of the parameter adjustment range is automatically triggered; The historical control records that meet the multi-dimensional constraint conditions are marked as high-value data, and the decision weight of the high-value data in the energy efficiency control rule set is increased.

[0012] Furthermore, when generating the composite optimization instruction, the impact of the parameter adjustment on the constraints of each dimension is calculated synchronously, including: Establish a multi-dimensional prediction model based on the dynamic coupling relationship between process parameters; Input the temperature compensation amount, speed correction coefficient and flow adjustment amplitude in the composite optimization instruction into the prediction model, and output the prediction deviation value of each dimensional constraint condition; When the predicted deviation value exceeds the safety threshold of the corresponding dimension, a dynamic limiting instruction for the parameter adjustment range is generated.

[0013] An energy consumption control system for an oxygen-free copper rod lifting process, comprising: The core parameter definition module divides the pull-up process into the melting stage, the pulling stage, and the cooling stage, and defines the core energy efficiency parameters of each stage: The core parameter collection module collects the core energy efficiency parameters of each stage in real time, synchronizes the data, and generates a core energy consumption parameter set; An abnormal pattern recognition module compares the core energy consumption parameter set with a preset energy consumption benchmark model to identify abnormal patterns in each stage; The optimization instruction generation module dynamically allocates adjustment weights according to the abnormal pattern type and generates temperature-speed-flow composite optimization instructions; The rule set generation module modifies the energy consumption benchmark model parameters based on historical control data and generates an energy efficiency control rule set that adapts to changes in process status; The energy consumption real-time control module performs real-time dynamic control of the energy consumption of each stage of the upstream process according to the updated energy efficiency control rule set and the temperature-speed-flow composite optimization instruction.

[0014] Furthermore, the abnormal pattern recognition module includes: The temperature stability sequence extraction unit performs sliding window smoothing on the melting temperature gradient data and extracts the high-frequency harmonic energy ratio of the traction power through time-frequency transformation; A threshold feature registration unit compares the smoothed temperature gradient with the dynamic threshold baseline, matches the high-frequency harmonic energy ratio with the equipment loss feature library, and simultaneously calculates the deviation rate of the cooling efficiency relative to the historical mean; The abnormal stage marking unit inputs the processed parameter set into the energy consumption benchmark model for multi-dimensional comparison. When the comparison result of any dimension exceeds the preset ratio range of the corresponding benchmark value, the abnormal mark of the corresponding stage is triggered.

[0015] The technical solution of the present invention can achieve the following technical effects: It effectively solves the energy efficiency imbalance and static rule rigidity problems caused by the isolated control of multi-stage parameters in traditional processes, realizes adaptive parameter coordination throughout the entire process, significantly reduces electricity consumption per ton and improves quality stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 The figure is a flow chart of an energy consumption control method for an oxygen-free copper rod pulling process; Figure 2 A flowchart for identifying abnormal patterns at each stage; Figure 3 A flowchart of the steps after triggering the abnormality mark of the corresponding stage; Figure 4 A flow chart for generating temperature-speed-flow composite optimization instructions; Figure 5 Schematic diagram of the process for generating a set of energy efficiency control rules that adapt to changes in process status; Figure 6 A schematic diagram of a process for real-time dynamic control of energy consumption at each stage of the upstream process; Figure 7 Schematic diagram of a flow chart of subsequent optimization steps of an energy consumption control method for an oxygen-free copper rod pulling process; Figure 8 Flowchart showing how to adjust the impact of the constraints on each dimension for synchronous calculation of parameters. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. The terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0020] Example 1 like Figure 1 As shown, the present invention provides an energy consumption control method for an oxygen-free copper rod pulling process, the method comprising: S1: Divide the upward process into the melting stage, the pulling stage and the cooling stage, and define the core energy efficiency parameters of each stage; Specifically, in the smelting stage, the main focus is on temperature control. The core energy efficiency parameters in this stage include melting temperature, heating power and heating rate. By real-time monitoring of the melting temperature gradient and temperature change rate, the stability and efficiency of the smelting process can be ensured, thereby reducing energy waste and avoiding excessive energy consumption; in the traction stage, the core energy efficiency parameters are concentrated on the traction speed, traction power and mechanical load during the traction process. The optimization goal of this stage is to improve the stability of the traction speed while ensuring the efficient transmission of traction power to avoid affecting the overall energy efficiency due to excessive energy loss. By precisely controlling the energy transmission during the traction process, work efficiency can be significantly improved and unnecessary energy waste can be reduced; in the cooling stage, the core energy efficiency parameters include cooling water flow, cooling temperature and cooling rate. By optimizing the cooling flow and temperature gradient, the cooling effect of the copper rod can be effectively controlled, and energy efficiency waste caused by uneven cooling or excessive cooling can be avoided. Energy efficiency control at this stage plays a vital role in ensuring the quality of the copper rod and reducing energy loss.

[0021] S2: Real-time collection of core energy efficiency parameters at each stage, data synchronization, and generation of core energy consumption parameter sets; Specifically, by collecting core energy efficiency parameters (such as temperature, speed, power, flow, etc.) in the melting, pulling and cooling stages in real time and synchronizing these data, it is possible to ensure that the operating status of the process can be accurately grasped at any time. The synchronization of these data can eliminate the impact that may be caused by time differences between different stages, ensure the consistency and accuracy of the overall data, and summarize the energy efficiency information of each stage into a unified parameter set as the basis for subsequent energy efficiency evaluation and optimization decisions. This parameter set not only provides the necessary data support for comparing and diagnosing abnormal patterns in the process, but also provides real-time feedback for the dynamic adjustment of the energy efficiency control model, thereby achieving more accurate energy efficiency management and regulation.

[0022] S3: Compare the core energy consumption parameter set with the preset energy consumption benchmark model to identify abnormal patterns in each stage; Specifically, by comparing the real-time collected energy efficiency data with the preset benchmark model, deviations or anomalies in the process can be discovered in a timely manner. This comparative analysis can help identify potential energy efficiency issues in the process and provide a basis for subsequent adjustments and optimizations. By comparing the core energy consumption parameter set with the preset energy consumption benchmark model, it can be found which stages' energy consumption indicators exceed the normal range or differ significantly from historical data. These deviations may be caused by factors such as equipment failure, improper process parameter settings, or changes in the external environment. By identifying these abnormal patterns, problems can be discovered in advance and measures can be taken to prevent further energy efficiency losses or equipment damage. For example, if parameters such as melting temperature, traction power, and cooling flow rate deviate from the baseline values at each stage, it may indicate that the current process state is abnormal. Through this comparative analysis, the problem stage can be accurately located, providing a specific direction for subsequent optimization adjustments to ensure stable and efficient operation of the process.

[0023] S4: Dynamically assign adjustment weights based on the abnormal pattern type and generate temperature-speed-flow composite optimization instructions; Specifically, each abnormality pattern may affect different process parameters. For example, abnormalities in the smelting stage are usually manifested as improper temperature control, while abnormalities in the traction stage may manifest as unstable traction speed or power. By dynamically allocating adjustment weights based on the type of abnormality pattern, it is possible to ensure that the adjustment of each parameter can be concentrated on the most critical process link, thereby efficiently and accurately solving energy efficiency problems. The generated temperature-speed-flow composite optimization instructions are based on this weight allocation. Taking into account the dynamic relationship and constraints between the various parameters, the generated optimization instructions can coordinately adjust these three process parameters to achieve the best energy efficiency control effect. In this way, not only can the optimization of energy efficiency at each stage of the process be ensured, but also the maximum energy savings and improvement of process efficiency can be achieved while ensuring product quality.

[0024] S5: Modify the energy consumption benchmark model parameters based on historical control data to generate an energy efficiency control rule set that adapts to changes in process status; Specifically, during the production process, the process status may change due to equipment aging, changes in raw materials, environmental factors, etc. Therefore, it is necessary to regularly revise the parameters of the energy consumption benchmark model so that it can adapt to different process states. The core role of this step is to use historical control data as feedback information, and by comparing the energy efficiency performance under different process states, correct the key parameters in the model. Through such corrections, the energy consumption benchmark model can better reflect the actual needs of the current process and avoid energy efficiency instability or excessive adjustment due to inappropriate parameter settings.

[0025] S6: Based on the updated energy efficiency control rule set and the temperature-speed-flow composite optimization instructions, the energy consumption of each stage of the upstream process is dynamically controlled in real time.

[0026] Specifically, real-time dynamic control ensures that process parameters such as temperature, speed, and flow rate remain within the optimal range under different process conditions, effectively reducing unnecessary energy waste. The updated energy efficiency control rule set, combined with composite optimization instructions, ensures precise and timely energy efficiency adjustments at every stage of the process. This control method, based on real-time feedback, can quickly respond to sudden changes or abnormal conditions in the process, dynamically adjust process parameters, avoid energy waste, and optimize the overall process flow.

[0027] Through the present invention, the energy efficiency imbalance and static rule rigidity problems caused by the isolated regulation of multi-stage parameters in traditional processes are effectively solved, and the adaptive parameter coordination of the entire process is achieved, which significantly reduces the electricity consumption per ton and improves the quality stability.

[0028] As a preferred embodiment of the above, Figure 2 As shown, step S3 compares the core energy consumption parameter set with the preset energy consumption benchmark model to identify abnormal patterns in each stage, including: S31: performing sliding window smoothing on the melting temperature gradient data, and extracting the high-frequency harmonic energy ratio of the traction power through time-frequency transformation; S32: Compare the smoothed temperature gradient with the dynamic threshold baseline, match the high-frequency harmonic energy ratio with the equipment loss feature library, and simultaneously calculate the deviation rate of the cooling efficiency from the historical mean; S33: Input the processed parameter set into the energy consumption benchmark model for multi-dimensional comparison. When the comparison result of any dimension exceeds the preset ratio range of the corresponding benchmark value, an abnormal flag of the corresponding stage is triggered.

[0029] Specifically, in step S31, sliding window smoothing is first performed on the melting temperature gradient data. The purpose of sliding window smoothing is to remove high-frequency noise in the temperature data by calculating the average value within a certain range around the data point, making the data smoother and more stable. This helps to eliminate external fluctuations or measurement errors and obtain a more accurate temperature change trend; next, the high-frequency harmonic energy ratio of the traction power is extracted through time-frequency transformation technology. Time-frequency transformation is a method of converting signals from the time domain to the frequency domain. In this way, the high-frequency components in the traction power (usually fluctuations caused by unstable equipment operation or failures) can be identified, thereby effectively quantifying the impact of these fluctuations on energy efficiency. In step S32, the smoothed temperature gradient data is first compared with the dynamic threshold baseline. The dynamic threshold baseline is a reference value set based on historical data and process requirements, and is usually adjusted as process conditions change. The purpose of comparing the temperature gradient with the baseline is to check whether the current temperature change exceeds the allowable range. If it exceeds the predetermined range, it may indicate a process abnormality. Next, the high-frequency harmonic energy ratio of the traction power is matched with the equipment loss feature library. The equipment loss feature library contains the energy efficiency characteristics of the equipment during normal operation. Comparing the high-frequency harmonic energy ratio with the characteristics in the library can help identify whether there is equipment loss or abnormality. Finally, the deviation rate of the cooling efficiency from the historical mean is calculated. By comparing the deviation of the current cooling efficiency with the historical data, it can be evaluated whether the cooling process is effective and whether there is energy waste due to insufficient or uneven cooling. In step S33, the processed parameter set (including the smoothed temperature gradient, the high-frequency harmonic energy ratio of the traction power, and the cooling efficiency deviation) is input into the energy consumption benchmark model for multi-dimensional comparison. The energy consumption benchmark model is a model established by historical data and empirical values, which is used to predict energy efficiency parameters under normal conditions. Through multi-dimensional comparison, the system will compare the current value of each parameter with the benchmark value. If the comparison result of any dimension exceeds the preset ratio range, this indicates that there is an abnormality in the energy efficiency of this stage, which may require further optimization or adjustment. The triggered abnormal mark will indicate which part of the process has a problem, providing a basis for subsequent adjustments.

[0030] As a preferred embodiment of the above, Figure 3 As shown, after the exception mark of the corresponding stage is triggered, it also includes: A10: Allocate control resources in order of priority based on the abnormal stage type and generate cross-stage process parameter compensation instructions; A20: Verify the effectiveness of compensation instructions based on real-time collected energy consumption data. When the energy consumption reduction rate per unit product does not reach the preset threshold, reversely modify the parameter association weights in the energy efficiency control rule set. A30: Bind the verified valid parameter compensation instructions with the current process state characteristics and store them in the energy efficiency control rule set.

[0031] Specifically, first, in step A10, the system allocates control resources in order of priority based on the identified abnormality types (such as abnormalities in the melting, traction or cooling stages). Different abnormality types will be prioritized according to the degree of their impact on the overall process flow, and priority will be given to abnormal stages that have a greater impact on energy efficiency. For example, temperature abnormalities in the melting stage may have a greater impact on the entire process, so the melting stage will be allocated higher control resources. According to the allocated priority, the system generates cross-stage linkage process parameter compensation instructions to ensure that the parameter adjustments of each process stage can cooperate and coordinate with each other to achieve the effect of overall optimization. For example, abnormalities in the traction process may need to be compensated by adjusting the melting temperature or cooling flow rate to maintain the balance of the entire process; next, in step A20, the effectiveness of the generated compensation instructions is verified through the energy consumption data collected in real time, the energy consumption reduction rate per unit product is calculated, and the compensation is checked. Whether the compensation instruction successfully reduces the energy consumption per unit product. If the energy consumption reduction rate does not reach the preset threshold, it means that the compensation instruction fails to effectively solve the problem. Then a reverse correction is performed to adjust the parameter association weights in the energy efficiency control rule set, that is, the priority and adjustment range in the rule are re-corrected to provide more accurate compensation instructions for similar abnormal situations in the future. In this way, the system continuously optimizes the control strategy to improve the effectiveness of future compensation instructions. Finally, in step A30, the verified and effective parameter compensation instructions will be bound to the current process state characteristics, which will combine the compensation instructions with the real-time temperature, speed, flow and other parameters in the process to ensure that the instructions can accurately adapt to the current production conditions. After binding, the compensation instructions will be stored in the energy efficiency control rule set and become part of the rule set. In this way, when similar abnormalities occur in the future, a quick response can be made according to the stored instructions, thereby achieving more efficient and accurate energy efficiency control.

[0032] As a preferred embodiment of the above, Figure 4 As shown, step S4 dynamically allocates adjustment weights according to the abnormal mode type and generates a temperature-speed-flow composite optimization instruction, including: S41: assigning adjustment weights based on the abnormality mode type, wherein the temperature parameter is the main adjustment item for smelting abnormalities, the speed parameter is the main adjustment item for traction abnormalities, and the flow parameter is the main adjustment item for cooling abnormalities; S42: Generate coordinated compensation amounts for temperature, speed, and flow rate based on the adjustment amplitude of the main adjustment item and the dynamic constraint relationship between the process parameters; S43: Synthesize the collaborative compensation amount into a composite optimization instruction according to the weight ratio, verify the effectiveness of the instruction through real-time energy consumption data, and iteratively update the weight allocation strategy based on the verification results.

[0033] Specifically, first, in step S41, adjustment weights are assigned to various process parameters according to different abnormal pattern types. Specifically, when an abnormality occurs in the smelting stage, the temperature parameter will be given a higher adjustment weight, because temperature control in the smelting process is crucial; when an abnormality occurs in the traction stage, the speed parameter will become the main adjustment item, because the traction speed has a greater impact on energy efficiency; and when an abnormality occurs in the cooling stage, the flow parameter is the main adjustment object, because the cooling flow directly determines the optimization of the cooling effect and energy efficiency. In this way, by classifying the abnormalities in different stages, it can be ensured that the core problems of each stage are solved first; then, in step S42, according to the adjustment range of the main adjustment item and the dynamic constraint relationship between the process parameters, the adjustment weights are generated. The collaborative compensation of temperature, speed and flow rate. During this process, the adjustment of the melting temperature may affect the pulling speed, and the change of the pulling speed may affect the cooling flow rate. Therefore, it is necessary to consider the interdependence between the various process parameters. According to these constraints, the collaborative compensation will ensure that the various adjustments are coordinated with each other to avoid the imbalance of other parameters caused by adjusting a certain parameter alone, thereby optimizing the overall energy efficiency control effect; finally, in step S43, these collaborative compensation amounts are synthesized into composite optimization instructions of temperature, speed and flow rate according to the pre-set weight ratio. These instructions will be verified for their effectiveness through real-time energy consumption data. If the energy consumption can be effectively reduced, the instructions will continue to be executed; if the energy consumption reduction does not meet expectations, it will be adjusted according to the verification results and the weight distribution strategy will be updated.

[0034] As a preferred embodiment of the above, Figure 5 As shown, step S5, based on the historical control data, the energy consumption benchmark model parameters are corrected to generate an energy efficiency control rule set that adapts to the process state changes, including: S51: Accumulating the temperature compensation amount, speed correction coefficient, and flow adjustment amplitude in the historical control records, and selecting effective control records that meet the preset energy consumption reduction conditions; S52: extracting correlation patterns between process parameters in the effective control records and updating parameters of the energy consumption benchmark model; S53: Based on the updated energy consumption benchmark model, generate a subset of energy efficiency control rules associated with process state characteristics; S54: Match the energy efficiency control rule subset with the real-time process status data to generate an optimized parameter set adapted to the current working conditions.

[0035] Specifically, in step S51, historical control records, such as temperature compensation, speed correction coefficients, and flow rate adjustment amplitudes, are first accumulated. These historical records reflect the adjustments made to various parameters under different process conditions. Next, effective control records that meet the preset energy consumption reduction criteria are selected. Effective control records are those that significantly improve energy efficiency, providing reliable data support for subsequent revisions to the benchmark model. In step S52, correlation patterns between process parameters are extracted from the selected effective control records. This step analyzes the relationships between different parameters to help identify which parameter adjustments can effectively impact energy efficiency. For example, temperature and speed adjustments may have a direct impact on traction power and cooling efficiency. Extracting these patterns provides a basis for updating the energy consumption benchmark model, thereby optimizing model parameters to better reflect energy efficiency variations in the actual process. Next, in step S53, based on the updated energy consumption benchmark model, a subset of energy efficiency control rules related to process state characteristics is generated. These rule subsets reflect how to achieve optimal energy efficiency by adjusting specific process parameters (such as temperature, speed, and flow rate) under different process states. The updated model generates more accurate and adaptable control rules. Finally, in step S54, the generated energy efficiency control rule subset is matched with real-time process status data. The purpose of this step is to select the most appropriate set of optimized parameters for adjustment based on the current process status. Real-time process status data includes parameters such as current temperature, speed, and flow rate. By comparing this data with the control rule subset, an optimized parameter set adapted to the current operating conditions is generated and applied in actual production to ensure maximum energy efficiency.

[0036] As a preferred embodiment of the above, Figure 6 As shown, step S6, based on the updated energy efficiency control rule set and the temperature-speed-flow composite optimization instruction, performs real-time dynamic control on the energy consumption of each stage of the above-mentioned process, including: S61: Identify the current process stage and call the rule subset of the corresponding stage from the energy efficiency control rule set; S62: Generate a process parameter adjustment instruction for the current stage based on the dynamic constraint relationship in the rule subset and the synergistic compensation amount in the composite optimization instruction; S63: Feedback the execution result of the parameter adjustment instruction as historical control data to the energy efficiency control rule set to drive the update and iteration of the rule subset.

[0037] Specifically, in step S61, it is first necessary to identify which process stage the current process is in, which may be the melting stage, the pulling stage or the cooling stage. Once the current process stage is determined, the rule subset corresponding to the stage is called from the energy efficiency control rule set. These rule subsets contain energy efficiency control strategies for specific process stages, which provide specific operational guidelines for adjusting process parameters; then, in step S62, based on the dynamic constraint relationship in the rule subset and the synergistic compensation amount in the composite optimization instruction, the process parameter adjustment instruction for the current stage is generated. There is a dynamic constraint relationship between the parameters of each process stage (such as temperature, speed, flow). These relationships determine the adjustment range and priority of each parameter. According to the synergistic compensation amount in the composite optimization instruction, the system will generate specific adjustment instructions. These instructions ensure that each parameter remains coordinated during the adjustment process, thereby optimizing energy efficiency. Finally, in step S63, the execution results of the parameter adjustment instructions are fed back to the energy efficiency control rule set as historical control data. The purpose of this step is to use the execution results as feedback to ensure that the rule set can be updated and optimized according to the actual operating conditions. Through this feedback mechanism, the energy efficiency control rule set will be continuously iterated and updated, so that when similar process conditions occur in the future, the process parameters can be adjusted more accurately to improve energy efficiency.

[0038] As a preferred embodiment of the above, Figure 7 As shown, the method further includes: B10: When generating a composite optimization instruction, the impact of parameter adjustment on the constraints of each dimension is simultaneously calculated; B20: When any dimension is detected to exceed the safety threshold, the dynamic limiting mechanism of the parameter adjustment range is automatically triggered; B30: Mark historical control records that meet multi-dimensional constraints as high-value data, and increase the decision weight of high-value data in the energy efficiency control rule set.

[0039] Specifically, in step B10, when generating compound optimization instructions, it is necessary to synchronously calculate the impact of parameter adjustments on the constraints of each dimension. The purpose of this step is to evaluate the impact of adjustments to process parameters such as temperature, speed, and flow on other process parameters and overall energy efficiency, and ensure that each adjustment is within the safety range of each dimension. By calculating these impact values, a more accurate adjustment plan can be provided for subsequent control instructions; then, in step B20, when it is detected that the adjustment of any dimension exceeds the safety threshold, the dynamic limiting mechanism of the parameter adjustment amplitude will be automatically triggered. The purpose of this mechanism is to ensure that during the adjustment process, changes in any process parameter will not excessively affect other parameters or cause process instability. By setting dynamic limits, the adjustment range can be flexibly adjusted according to the current process state and the relationship between the parameters, thereby avoiding the adverse consequences of excessive adjustment and ensuring the safe and stable operation of the process. Finally, in step B30, the historical control records that meet the multi-dimensional constraints are marked as high-value data. These data represent the control records that can effectively improve energy efficiency in the actual process and have a strong reference value. After marking these high-value data, their decision-making weight in the energy efficiency control rule set will be increased. This means that when encountering similar process states in the future, these high-value data will be given priority reference, so that parameter adjustments can be made more accurately, improving the accuracy and stability of energy efficiency control.

[0040] As a preferred embodiment of the above, Figure 8 As shown, step B10, when generating the composite optimization instruction, synchronously calculates the impact value of the parameter adjustment on the constraints of each dimension, including: B11: Establish a multi-dimensional prediction model based on the dynamic coupling relationship between process parameters; B12: Input the temperature compensation, speed correction coefficient, and flow adjustment amplitude in the composite optimization instruction into the prediction model, and output the prediction deviation value of each dimension constraint condition; B13: When the predicted deviation value exceeds the safety threshold of the corresponding dimension, a dynamic limit instruction for the parameter adjustment range is generated.

[0041] Specifically, first, in step B11, based on the dynamic coupling relationship between process parameters, a multi-dimensional prediction model is established. The model takes into account the interdependence between process parameters such as temperature, speed, and flow, and analyzes how changes in these parameters affect changes in other parameters, as well as their combined impact on overall process efficiency and energy efficiency. The purpose of this step is to provide an accurate prediction basis for subsequent adjustments to ensure that the adjustment of each parameter does not exceed a reasonable range; then, in step B12, the temperature compensation amount, speed correction coefficient, and flow adjustment amplitude in the composite optimization instruction are input into the prediction model. The model calculates these input data and outputs the predicted deviation value of each dimensional constraint condition. The deviation The value indicates whether changes in process parameters such as temperature, speed and flow rate will cause deviations from the constraints of each dimension during the adjustment process, and whether such deviations exceed the acceptable range. In this way, the impact of each adjustment on process stability can be understood in advance. Finally, in step B13, when the predicted deviation value exceeds the safety threshold of the corresponding dimension, a dynamic limiting instruction for the parameter adjustment amplitude is generated. If the prediction result shows that the adjustment of a certain dimension will exceed the safety range, the limiting instruction will control the adjustment amplitude to prevent excessive adjustment from having a negative impact on the process or energy efficiency. Through this dynamic limiting mechanism, it can be ensured that during the complex process adjustment process, the process parameters are always kept within a safe and stable range.

[0042] Example 2 Based on the same inventive concept as the energy consumption control method of the oxygen-free copper rod pulling process in the aforementioned embodiment, the present invention also provides an energy consumption control system for the oxygen-free copper rod pulling process, the system comprising: The core parameter definition module divides the pull-up process into the melting stage, the pulling stage, and the cooling stage, and defines the core energy efficiency parameters of each stage: The core parameter collection module collects the core energy efficiency parameters of each stage in real time, synchronizes the data, and generates a core energy consumption parameter set; The abnormal pattern recognition module compares the core energy consumption parameter set with the preset energy consumption benchmark model to identify abnormal patterns in each stage; The optimization instruction generation module dynamically allocates adjustment weights according to the abnormal pattern type and generates temperature-speed-flow composite optimization instructions; The rule set generation module modifies the energy consumption benchmark model parameters based on historical control data and generates an energy efficiency control rule set that adapts to changes in process status; The energy consumption real-time control module performs real-time dynamic control of the energy consumption at each stage of the upstream process based on the updated energy efficiency control rule set and the temperature-speed-flow composite optimization instructions.

[0043] The control system in the present invention can effectively implement the energy consumption control method of the oxygen-free copper rod pulling process, and the technical effects that can be achieved are as described in the above embodiments and will not be repeated here.

[0044] As a preferred embodiment of the above, the abnormal pattern recognition module includes: The temperature stability extraction unit performs sliding window smoothing on the melting temperature gradient data and extracts the high-frequency harmonic energy ratio of the traction power through time-frequency transformation; The threshold feature registration unit compares the smoothed temperature gradient with the dynamic threshold baseline, matches the high-frequency harmonic energy ratio with the equipment loss feature library, and simultaneously calculates the deviation rate of the cooling efficiency relative to the historical mean; The abnormal stage marking unit inputs the processed parameter set into the energy consumption benchmark model for multi-dimensional comparison. When the comparison result of any dimension exceeds the preset proportion range of the corresponding benchmark value, the abnormal marking of the corresponding stage is triggered.

[0045] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the corresponding optimization effects of the method in Example 1, which will not be repeated here.

[0046] Although the present application has been described with reference to specific features and embodiments thereof, it is apparent that various modifications and combinations thereof may be made without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely illustrative of the present application as defined herein, and are intended to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A method for controlling energy consumption in an oxygen-free copper rod pulling process, characterized in that: include: The pull-up process is divided into the melting stage, the pulling stage and the cooling stage, and the core energy efficiency parameters of each stage are defined; Real-time collection of core energy efficiency parameters at each stage, data synchronization, and generation of core energy consumption parameter sets; Comparing the core energy consumption parameter set with a preset energy consumption benchmark model to identify abnormal patterns in each stage; Dynamically assign adjustment weights based on abnormal mode types and generate temperature-speed-flow composite optimization instructions; Correct the energy consumption benchmark model parameters based on historical control data to generate an energy efficiency control rule set that adapts to changes in process status; According to the updated energy efficiency control rule set and the temperature-speed-flow composite optimization instruction, the energy consumption of each stage of the upstream process is dynamically controlled in real time.

2. The energy consumption control method for the oxygen-free copper rod pulling process according to claim 1, characterized in that: Compare the core energy consumption parameter set with a preset energy consumption baseline model to identify abnormal patterns in each stage, including: Sliding window smoothing is performed on the melting temperature gradient data, and the high-frequency harmonic energy ratio of the traction power is extracted through time-frequency transformation; Comparing the smoothed temperature gradient with the dynamic threshold baseline, matching the high-frequency harmonic energy ratio with the equipment loss feature library, and simultaneously calculating the deviation rate of the cooling efficiency relative to the historical mean; The processed parameter set is input into the energy consumption benchmark model for multi-dimensional comparison. When the comparison result of any dimension exceeds the preset ratio range of the corresponding benchmark value, an abnormal flag of the corresponding stage is triggered.

3. The energy consumption control method for the oxygen-free copper rod pulling process according to claim 2, characterized in that: After the exception mark of the corresponding stage is triggered, it also includes: Allocate control resources in order of priority based on the abnormal stage type and generate cross-stage linkage process parameter compensation instructions; Verifying the effectiveness of the compensation instruction based on the real-time collected energy consumption data, and when the unit product energy consumption reduction rate does not reach a preset threshold, reversely correcting the parameter association weights in the energy efficiency control rule set; The verified valid parameter compensation instructions are bound to the current process state characteristics and then stored in the energy efficiency control rule set.

4. The energy consumption control method for the oxygen-free copper rod pulling process according to claim 1, characterized in that: Dynamically assign adjustment weights based on abnormal pattern types and generate temperature-speed-flow composite optimization instructions, including: Assign adjustment weights based on abnormal pattern types. For smelting abnormalities, the main adjustment item is temperature parameters; for traction abnormalities, the main adjustment item is speed parameters; and for cooling abnormalities, the main adjustment item is flow parameters. Generate coordinated compensation amounts for temperature, speed, and flow rate based on the adjustment amplitude of the main adjustment item and the dynamic constraint relationship between process parameters; The collaborative compensation amounts are synthesized into composite optimization instructions according to weight ratios, the effectiveness of the instructions is verified through real-time energy consumption data, and the weight allocation strategy is iteratively updated based on the verification results.

5. The energy consumption control method for the oxygen-free copper rod pulling process according to claim 1, characterized in that: Based on historical control data, the energy consumption benchmark model parameters are modified to generate an energy efficiency control rule set that adapts to changes in process status, including: Accumulate the temperature compensation, speed correction coefficient and flow adjustment amplitude in the historical control records, and select the effective control records that meet the preset energy consumption reduction conditions; Extracting correlation rules between process parameters in the effective control records and updating parameters of the energy consumption benchmark model; Based on the updated energy consumption benchmark model, a subset of energy efficiency control rules associated with process state characteristics is generated; The energy efficiency control rule subset is matched with the real-time process status data to generate an optimized parameter set adapted to the current working conditions.

6. The energy consumption control method for the oxygen-free copper rod pulling process according to claim 1, characterized in that: Based on the updated energy efficiency control rule set and temperature-speed-flow composite optimization instructions, the energy consumption of each stage of the upstream process is dynamically controlled in real time, including: Identify the current process stage, and call a rule subset corresponding to the stage from the energy efficiency control rule set; Generate a process parameter adjustment instruction for the current stage based on the dynamic constraint relationship in the rule subset and the synergistic compensation amount in the composite optimization instruction; The execution result of the parameter adjustment instruction is fed back to the energy efficiency control rule set as historical control data to drive the update iteration of the rule subset.

7. The energy consumption control method for the oxygen-free copper rod pulling process according to claim 1, characterized in that: The method further comprises: When generating the composite optimization instruction, synchronously calculating the impact value of the parameter adjustment on the constraint conditions of each dimension; When any dimension is detected to exceed the safety threshold, the dynamic limiting mechanism of the parameter adjustment range is automatically triggered; The historical control records that meet the multi-dimensional constraint conditions are marked as high-value data, and the decision weight of the high-value data in the energy efficiency control rule set is increased.

8. The energy consumption control method for the oxygen-free copper rod pulling process according to claim 7, characterized in that: When generating the composite optimization instruction, the impact of the parameter adjustment on the constraints of each dimension is calculated simultaneously, including: Establish a multi-dimensional prediction model based on the dynamic coupling relationship between process parameters; Input the temperature compensation amount, speed correction coefficient and flow adjustment amplitude in the composite optimization instruction into the prediction model, and output the prediction deviation value of each dimensional constraint condition; When the predicted deviation value exceeds the safety threshold of the corresponding dimension, a dynamic limiting instruction for the parameter adjustment range is generated.

9. An energy consumption control system for an oxygen-free copper rod pulling process, characterized in that: include: The core parameter definition module divides the pull-up process into the melting stage, the pulling stage, and the cooling stage, and defines the core energy efficiency parameters of each stage: The core parameter collection module collects the core energy efficiency parameters of each stage in real time, synchronizes the data, and generates a core energy consumption parameter set; An abnormal pattern recognition module compares the core energy consumption parameter set with a preset energy consumption benchmark model to identify abnormal patterns in each stage; The optimization instruction generation module dynamically allocates adjustment weights according to the abnormal pattern type and generates temperature-speed-flow composite optimization instructions; The rule set generation module modifies the energy consumption benchmark model parameters based on historical control data and generates an energy efficiency control rule set that adapts to changes in process status; The energy consumption real-time control module performs real-time dynamic control of the energy consumption of each stage of the upstream process according to the updated energy efficiency control rule set and the temperature-speed-flow composite optimization instruction.

10. The energy consumption control system for the oxygen-free copper rod pulling process according to claim 9, characterized in that: The abnormal pattern recognition module includes: The temperature stability sequence extraction unit performs sliding window smoothing on the melting temperature gradient data and extracts the high-frequency harmonic energy ratio of the traction power through time-frequency transformation; A threshold feature registration unit compares the smoothed temperature gradient with the dynamic threshold baseline, matches the high-frequency harmonic energy ratio with the equipment loss feature library, and simultaneously calculates the deviation rate of the cooling efficiency relative to the historical mean; The abnormal stage marking unit inputs the processed parameter set into the energy consumption benchmark model for multi-dimensional comparison. When the comparison result of any dimension exceeds the preset ratio range of the corresponding benchmark value, the abnormal mark of the corresponding stage is triggered.

Images