A method for dynamic management of energy consumption of an apparatus for the entire process of electric pole manufacturing

Abstract

This invention relates to the field of pole manufacturing technology and discloses a method for dynamic energy consumption management of equipment throughout the entire pole manufacturing process. The method includes: dividing the energy consumption into stages based on the process flow of pole manufacturing to obtain multiple energy consumption management stages; combining equipment operation data and environmental monitoring data to predict the energy consumption environment for each energy consumption management stage, obtaining the predicted energy consumption environment; calculating the benchmark energy consumption parameters of the corresponding equipment configuration scheme for each energy consumption management stage based on energy consumption benchmark factors, and determining the energy consumption benchmark vector; based on the energy consumption benchmark vector, using an energy consumption prediction model to predict energy consumption losses in the predicted energy consumption environment, establishing an energy consumption loss vector; optimizing and adjusting the equipment operating parameter set according to the energy consumption loss vector to generate an energy consumption optimization strategy, and controlling the equipment operating parameter set according to the strategy to achieve adaptive energy consumption management of the pole manufacturing process.

Description

Technical Field

[0001] This invention relates to the field of pole manufacturing technology, specifically to a method for dynamic management of equipment energy consumption throughout the entire pole manufacturing process. Background Technology

[0002] In the pole manufacturing industry, with the continuous growth of energy demand and increasingly stringent environmental protection requirements, equipment energy consumption management has gradually become an indispensable aspect of industry development. The pole manufacturing process encompasses multiple steps, including raw material mixing, rebar cage fabrication, casting, steam curing, and demolding. These different steps involve diverse types of equipment, including mixing equipment, molding equipment, heating equipment, and conveying equipment, each with significantly different energy consumption characteristics. Currently, most pole manufacturers still employ a traditional, extensive approach to energy consumption management, lacking refined energy consumption control throughout the entire manufacturing process.

[0003] Current management methods typically only calculate the total energy consumption of the entire production cycle, failing to accurately segment the energy consumption stages corresponding to different processes. This makes it difficult to pinpoint high-energy-consuming links and sources of energy waste. During equipment operation, companies often set fixed operating parameters based on experience, failing to dynamically adjust them in conjunction with real-time equipment operating data and environmental monitoring data. For example, during the steam curing stage, changes in ambient temperature directly affect the heat consumption required for curing. If operation is continued at a fixed heating power, it can easily lead to excessive energy consumption or poor curing results.

[0004] Current technologies lack scientific methods for setting energy consumption benchmarks, making it difficult to define reasonable energy consumption ranges for different energy consumption stages. This results in an inability to accurately assess whether energy consumption at each stage is at a reasonable level, and an inability to effectively predict energy consumption trends under different operating conditions. When equipment experiences abnormal energy consumption, the lack of corresponding energy loss prediction mechanisms makes it difficult for companies to quickly determine the cause and extent of the abnormality, thus hindering timely and effective adjustment measures. This extensive energy management model not only causes significant energy waste and increases production costs but also reduces equipment operating efficiency and lifespan, which is detrimental to the sustainable development of the pole manufacturing industry.

[0005] As the pole manufacturing industry moves towards automation and intelligence, the complexity and integration of production equipment are constantly increasing. Traditional energy management methods can no longer meet the needs of modern production. There is an urgent need for a refined energy management method that can cover the entire pole manufacturing process and combine multi-dimensional data for dynamic control, in order to solve the problems of inaccurate energy control, untimely parameter adjustment, and unpredictable energy loss in existing technologies. Summary of the Invention

[0006] The purpose of this invention is to provide a method for dynamic management of equipment energy consumption throughout the entire process of pole manufacturing, so as to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides a method for dynamic management of equipment energy consumption throughout the entire pole manufacturing process, the method comprising: Based on the process flow of pole manufacturing, energy consumption stages are divided to obtain multiple energy management stages; Based on equipment operation data and environmental monitoring data, energy consumption environment is predicted for the multiple energy consumption management stages to obtain the predicted energy consumption environment for each energy consumption management stage. Based on the energy consumption benchmark factor, the benchmark energy consumption parameters of the equipment configuration schemes corresponding to the multiple energy consumption management stages are calculated to determine the energy consumption benchmark vector for each energy consumption management stage. Based on the energy consumption benchmark vectors of each energy consumption management stage, energy consumption loss is predicted for the predicted energy consumption environment of each energy consumption management stage according to the energy consumption prediction model, and energy consumption loss vectors of each energy consumption management stage are established. Based on the energy loss vector of each energy management stage, the set of equipment operating parameters is optimized and adjusted to generate an energy consumption optimization strategy. Adaptive energy management is performed on the pole manufacturing process based on the set of operating parameters of the control equipment according to the energy consumption optimization strategy.

[0008] Preferably, energy consumption environment prediction is performed on the multiple energy consumption management stages based on equipment operation data and environmental monitoring data to obtain the predicted energy consumption environment for each energy consumption management stage, including: Acquire equipment operation data during the pole manufacturing process, including motor power and transmission efficiency; The environmental monitoring data of the pole manufacturing process is obtained, including temperature data and humidity data. Based on the equipment operation data and environmental monitoring data, environmental change trend analysis is performed for each energy consumption management stage, and predicted energy consumption environment for each energy consumption management stage is generated.

[0009] Preferably, based on the energy consumption benchmark factor, benchmark energy consumption parameters are calculated for the equipment configuration schemes corresponding to the multiple energy consumption management stages to determine the energy consumption benchmark vector for each energy consumption management stage, including: Based on the energy consumption benchmark factor, normal energy consumption samples are retrieved for the equipment configuration schemes in each energy consumption management stage to obtain the energy consumption sample set for each energy consumption management stage. Based on the energy consumption sample sets of each energy consumption management stage, the central value is calculated to obtain the energy consumption benchmark sequence for each energy consumption management stage. Construct an energy consumption benchmark vector for each energy consumption management stage based on the energy consumption benchmark sequence for each energy consumption management stage.

[0010] Preferably, based on the energy consumption baseline vector of each energy consumption management stage, energy loss is predicted for the predicted energy consumption environment of each energy consumption management stage according to the energy consumption prediction model, and an energy loss vector for each energy consumption management stage is established, including: The equipment configuration scheme for each energy management stage and the predicted energy consumption environment for each energy management stage are input into the energy consumption prediction model to obtain the energy consumption prediction vector for each energy management stage. Based on the energy consumption benchmark vector of each energy consumption management stage, the deviation of the energy consumption prediction vector of each energy consumption management stage is identified to obtain the energy consumption loss vector of each energy consumption management stage.

[0011] Preferably, the energy consumption optimization strategy is generated by optimizing the set of equipment operating parameters based on the energy loss vectors of each energy management stage, including: Obtain energy loss weighting conditions, which include power loss weights and efficiency loss weights; The energy loss vectors of each energy management stage are weighted according to the energy loss weight conditions to obtain the energy loss coefficient of each energy management stage. Determine whether the energy loss coefficient of each energy management stage is greater than or equal to the energy loss threshold; If the energy loss coefficient is greater than or equal to the energy loss threshold, the set of equipment operating parameters is optimized and adjusted according to the energy loss vector of each energy management stage to generate an energy optimization strategy for each energy management stage.

[0012] Preferably, the set of equipment operating parameters is optimized and adjusted based on the energy loss vector of each energy management stage to generate an energy optimization strategy for each energy management stage, including: Based on the energy loss vector of each energy management stage, the set of equipment operating parameters is adjusted and decisions are made to establish an energy adjustment space that meets the predetermined number of decisions. Based on the energy consumption prediction model and the energy loss weighting condition, the energy consumption adjustment space is optimized through optimization analysis to obtain the optimal energy consumption adjustment space. Based on the optimized energy consumption regulation space, variation optimization is carried out to expand and establish an extended energy consumption regulation space; Based on the expanded energy consumption adjustment space, the optimization strategy for minimizing energy loss is generated for each energy consumption management stage.

[0013] Preferably, based on the energy consumption prediction model and energy loss weighting conditions, an optimization analysis is performed on the energy consumption adjustment space to obtain an optimized energy consumption adjustment space, including: Energy consumption regulation decisions are extracted based on the energy consumption regulation space; Based on energy consumption regulation decisions, the predicted energy consumption environment at each stage of energy consumption management is predicted to change, and the predicted changing energy consumption environment is obtained. Input the equipment configuration scheme and predicted changes in energy consumption environment at each stage of energy management into the energy consumption prediction model to obtain the decision energy consumption prediction vector. The decision energy consumption prediction vector is weighted according to the energy consumption loss weight condition to obtain the decision energy consumption loss coefficient. Determine whether the energy loss coefficient of the decision is less than the energy loss threshold; If the energy loss coefficient of the decision is less than the energy loss threshold, the energy consumption adjustment decision will be added to the optimized energy consumption adjustment space.

[0014] Preferably, the optimized energy consumption adjustment space is expanded through variational optimization, establishing an extended energy consumption adjustment space, including: Construct a moderating variance value evaluation system based on the moderating variance value evaluation record set; The decision energy loss coefficient corresponding to each energy consumption regulation decision within the optimized energy consumption regulation space is input into the regulation variation value evaluation system to obtain each regulation variation value coefficient. The energy consumption adjustment space is mutated according to each adjustment variation value coefficient to obtain the initial mutated energy consumption space; Based on the energy consumption prediction model and the energy consumption loss weight conditions, the initial variable energy consumption space is optimized to obtain the optimized variable energy consumption space. Based on the optimization of the variable energy consumption space, the optimized energy consumption adjustment space is expanded, and an extended energy consumption adjustment space is established.

[0015] Preferably, the method of optimizing and adjusting the set of equipment operating parameters based on the energy loss vectors of each energy management stage to generate an energy optimization strategy further includes: Based on the energy consumption correlation calculation method, key stages are screened for each energy consumption management stage to obtain key energy consumption management stages. The set of equipment operating parameters is preferentially adjusted based on the energy loss vector of the key energy management phase.

[0016] Preferably, key energy management stages are selected based on energy consumption correlation calculation methods to obtain key energy consumption management stages, including: Calculate the energy consumption correlation degree based on the energy consumption baseline vector and energy consumption loss vector of each energy consumption management stage; The energy management stages are sorted and filtered according to their correlation with energy consumption to identify the key energy management stages.

[0017] Compared with the prior art, the beneficial effects of the present invention are: This dynamic energy consumption management method for the entire pole manufacturing process divides the manufacturing process into energy consumption stages. This breaks down the originally complex overall manufacturing process into several clearly defined energy management stages, enabling companies to implement targeted control based on the energy consumption characteristics of different stages. This overcomes the limitations of traditional extensive management methods that fail to identify high-energy-consuming processes. By clearly defining the process flow and equipment combination corresponding to each energy management stage, companies can clearly understand the energy consumption distribution at each stage, facilitating accurate identification of energy-wasting areas and providing a clear direction for subsequent energy optimization.

[0018] In the energy consumption environment prediction stage, this method combines equipment operation data and environmental monitoring data to analyze the predicted energy consumption environment at each stage of energy management. It fully considers the impact of real-time operating conditions and environmental factors on energy consumption, breaking the limitations of traditional management that relies on experience to set fixed parameters. For example, in the raw material mixing stage, if equipment operation data reveals a high load rate on the mixing motor and increased raw material viscosity due to high ambient humidity, it can be predicted in advance that energy consumption at this stage may be higher than usual. This provides lead time for subsequent parameter adjustments, avoiding energy waste or decreased production efficiency. This data-driven prediction approach makes energy management more forward-looking, effectively responding to energy consumption changes under different operating conditions and improving the flexibility and adaptability of energy consumption control.

[0019] By calculating energy consumption benchmark vectors for each energy management stage using energy consumption benchmark factors, a scientific and reasonable energy consumption reference standard is established for each stage, solving the problems of missing or unreasonable energy consumption benchmarks in existing technologies. The energy consumption benchmark vector accurately reflects the reasonable energy consumption range of each stage under normal operating conditions. Enterprises can quickly determine whether the energy consumption of each stage is at a reasonable level based on this benchmark vector, and can promptly detect and intervene when energy consumption exceeds the benchmark range. At the same time, this benchmark vector also provides a unified standard for comparing energy consumption across different energy consumption stages, facilitating horizontal comparisons of energy consumption in different production batches at the same stage, and vertical analysis of energy consumption trends at different times within the same stage, helping enterprises continuously optimize their energy management strategies.

[0020] By predicting energy losses and establishing energy loss vectors based on energy consumption baseline vectors and energy consumption prediction models, enterprises can anticipate potential energy losses at each stage of energy management under predicted energy consumption environments. Quantifying energy losses allows enterprises to clearly understand the extent and causes of energy losses under different operating conditions, avoiding the problems of undetected and unquantifiable energy losses in traditional management. For example, during the casting and molding stage, if the predicted energy consumption environment indicates excessive equipment load, the additional energy losses that may occur at this stage can be predicted using the energy consumption baseline vector. Enterprises can then take preventative measures to adjust equipment operating conditions and reduce unnecessary energy consumption. This proactive prediction and intervention model effectively reduces energy losses and improves energy efficiency.

[0021] In terms of optimizing and adjusting equipment operating parameters, this method optimizes the set of equipment operating parameters based on the energy loss vectors at each stage, generating targeted energy consumption optimization strategies to ensure that equipment operating parameters match the current energy consumption environment. Unlike traditional experience-based parameter setting methods, this optimization strategy is generated based on actual energy loss data, providing a scientific basis and enabling dynamic adjustment of equipment operating parameters. For example, in the demolding stage, if the energy loss vector shows increased energy loss due to excessive equipment operating speed, the optimization strategy can specifically reduce the operating speed of the demolding equipment, reducing energy consumption while ensuring demolding efficiency. This dynamic parameter adjustment method ensures that the equipment is always in a low-energy, high-efficiency operating state, reducing energy waste and improving the equipment's operational stability and service life.

[0022] By implementing adaptive energy management of the pole manufacturing process through energy consumption optimization strategies and controlling equipment operating parameter sets, closed-loop energy consumption control can be achieved throughout the entire pole manufacturing process. The entire management process, from energy consumption stage segmentation and energy environment prediction to energy consumption benchmark calculation, energy loss prediction, parameter optimization, and adaptive control, forms a complete management chain. This chain continuously adjusts management strategies based on real-time operating data and environmental changes, avoiding the problems of fixed parameters and inability to adapt to environmental changes in traditional management. This adaptive management model not only continuously reduces the overall energy consumption of the pole manufacturing process and lowers production costs for enterprises, but also improves production efficiency and product quality, helping enterprises meet national energy conservation and emission reduction policies and promoting the pole manufacturing industry towards green, efficient, and sustainable development. Simultaneously, the application of this method can enhance the competitiveness of enterprises within the industry, laying the foundation for intelligent and refined production management and adapting to the development needs of modern pole manufacturing. Attached Figure Description

[0023] Figure 1 This is a schematic diagram illustrating the working principle of the dynamic energy consumption management method for the entire pole manufacturing process described in this invention. Figure 2 A flowchart for predicting energy consumption and environmental data acquisition at each stage of energy management; Figure 3 A flowchart for establishing energy loss vectors for each energy management stage; Figure 4 This is a flowchart for space optimization based on energy consumption regulation. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] Please see Figure 1 This invention provides a method for dynamic management of equipment energy consumption throughout the entire pole manufacturing process, the method comprising: The energy consumption process is divided into multiple stages based on the pole manufacturing process, resulting in multiple energy management stages. Equipment operation data and environmental monitoring data are used to predict the energy consumption environment for each stage, generating predicted energy consumption environments for each stage. Energy consumption benchmark factors are used to calculate benchmark energy consumption parameters for the equipment configuration schemes corresponding to each stage, determining the energy consumption benchmark vector for each stage. Based on the energy consumption benchmark vectors for each stage, the energy consumption prediction model predicts energy losses for the predicted energy consumption environment of each stage, establishing energy loss vectors for each stage. The energy loss vectors for each stage are used to optimize and adjust the equipment operating parameter set, generating an energy consumption optimization strategy. The energy consumption optimization strategy controls the equipment operating parameter set to perform adaptive energy consumption management in the pole manufacturing process.

[0026] Example 1: See Figure 2The manufacturing process of utility poles is typically divided into several consecutive energy management stages, such as raw material pretreatment, steel reinforcement cage preparation, concrete mixing and pouring, centrifugal molding, steam curing, and final demolding and curing. Each stage involves equipment combinations and operating modes, with significantly different energy consumption characteristics. The implementation process first requires the deployment of a complete sensor network and data acquisition system. For equipment operation data, power sensors are installed on motor drive equipment to monitor the motor's active power, reactive power, and operating current in real time. In transmission mechanisms such as gearboxes or belt drive systems, transmission efficiency data is obtained through torque and speed sensors or efficiency calculation models. Environmental monitoring data is acquired through temperature and humidity sensors distributed in key areas of the workshop. These sensors record the temperature and relative humidity of the manufacturing environment at a certain sampling frequency (e.g., once per minute). All data is transmitted to a central data processing system via an industrial IoT gateway for timestamp alignment and preprocessing, forming a structured time-series dataset.

[0027] After obtaining multi-source data, the system begins to analyze environmental change trends at each energy management stage to generate a predicted energy consumption environment. This analysis is not a simple data aggregation, but a dynamic extrapolation based on time-series forecasting technology. Taking the steam curing stage as an example, this stage is usually carried out in a closed curing pit, where the ambient temperature and humidity are affected by the steam valve opening, curing time, and the initial environmental conditions. The system extracts the initial temperature and humidity at the start of the current curing cycle, the current setting parameters of the steam valves, and the temperature and humidity change curves of historical similar curing processes. Using a moving average algorithm or an exponential smoothing model, the predicted values ​​of temperature and humidity in the curing pit for a future period (such as the next hour) are calculated. Simultaneously, equipment operation data for this stage, such as the motor power driving the opening and closing of the curing pit cover and the transmission efficiency of the circulating fan, are also included in the analysis. The system identifies that in high-temperature and high-humidity environments, the insulation performance of the motor may decrease, leading to increased copper losses, and changes in the lubrication conditions of the transmission mechanism may affect efficiency. These factors together constitute the predicted energy consumption environment for this stage, a comprehensive description including the expected temperature range, humidity range, and their potential impact on equipment energy efficiency. The same applies to other stages. For example, in the centrifugal molding stage, it is necessary to predict the power fluctuations of the spindle motor due to bearing temperature rise at high speed, as well as the impact of ambient humidity on the heat dissipation of the electrical control system.

[0028] The system calculates baseline energy consumption parameters for each stage based on energy consumption baseline factors. These baseline factors are a set of predefined or learned parameters used to define energy consumption levels under "normal" or "ideal" operating conditions. They may include equipment rated efficiency, theoretical minimum power, and standard environmental condition ranges. The system retrieves samples from the historical database that match the equipment configuration used in each energy management stage (e.g., the model of mixer used in the concrete mixing stage, its capacity, and speed settings) and whose environmental monitoring data are within the standard range. These samples constitute the energy consumption sample set for that stage. For example, for a 750-liter twin-shaft mixer configuration, the system will retrieve energy consumption records (power readings per minute) for all instances within the past three months where the ambient temperature was between 20-25 degrees Celsius, humidity between 50%-60%, and the same type of concrete mix was produced.

[0029] Centralized value calculations are performed on this energy consumption sample set. Instead of simply averaging all data, the calculation considers operational stability, potentially using the mean after removing outliers or the median energy consumption over a stable operating period. This results in a sequence representing the "normal" energy consumption level for this configuration: the energy consumption baseline sequence. This sequence might show that, under normal operating conditions, the mixer's power briefly rises to 45 kW during startup, remains at 38 kW during stable operation, and drops to 22 kW during unloading. Ultimately, this time series is constructed into a formalized energy consumption baseline vector, where each element represents the baseline energy consumption value at a specific time point or operational sub-stage. The entire implementation process, through continuous data sensing, trend inference, and statistical normalization, establishes a precise and dynamically updated reference standard for subsequent energy consumption anomaly diagnosis and optimization.

[0030] Example 2: See Figure 3The implementation process begins by inputting the equipment configuration schemes and predicted energy consumption environments for each energy management stage into a pre-trained energy consumption prediction model. This model is a machine learning model trained using historical manufacturing data, capable of simulating the energy consumption performance of specific equipment under specific environmental conditions. Taking the centrifugal forming stage of pole manufacturing as an example, the core equipment in this stage is a high-speed centrifuge. Its equipment configuration scheme includes the model and rated parameters of the main motor, the size and weight of the centrifugal mold, and the centrifugal speed and duration set for the pole specifications of the current production batch. The predicted energy consumption environment includes the expected range of ambient temperature and humidity fluctuations for this stage, such as the temperature rise in the surrounding area due to the main motor's prolonged high-speed operation, and the estimated impact of workshop ventilation conditions on heat dissipation efficiency. After receiving these inputs, the model outputs a time-series energy consumption prediction vector. This vector predicts in detail the expected power consumption at each point in time during the upcoming production cycle, from start-up, acceleration, steady-speed operation to deceleration and stop of the centrifuge. This prediction comprehensively considers the combined effects of mechanical friction, electrical losses, and ambient temperature and humidity on motor efficiency and transmission system performance.

[0031] The system compares the predicted energy consumption vectors for each energy management stage with a pre-calculated baseline energy consumption vector to identify deviations. The baseline energy consumption vector represents the ideal energy consumption level of the equipment under standard environmental conditions. The deviation identification process is not a simple numerical subtraction, but a comprehensive analysis of the shape, trend, and magnitude of the vector sequence. The system calculates the difference between the two vectors at each corresponding time point, thereby generating an energy loss vector. Each element of this vector represents the additional energy consumption or efficiency loss at the corresponding time point due to environmental factors deviating from standard conditions or the equipment being in an undesirable state. For example, during the centrifuge's steady-speed operation phase, the baseline vector shows that the power should be at the normal value, but the predicted vector may show that due to a higher predicted ambient temperature and worsened motor heat dissipation, the predicted power will increase to some extent. The magnitude and duration of this increase are recorded in the energy loss vector.

[0032] The system introduces energy loss weighting conditions for comprehensive evaluation. These weighting conditions include power loss weight and efficiency loss weight, which are set based on the actual operational goals and cost structure of the pole manufacturing company. The power loss weight is directly related to electricity costs, while the efficiency loss weight may focus more on the long-term reliability and maintenance costs of the equipment. The system performs weighted calculations on the energy loss vector, multiplying the power loss value at each time point in the vector by the power loss weight and the efficiency loss value by the efficiency loss weight. Then, it integrates or sums the weighted results for all time points to obtain a scalar value: the energy loss coefficient for each energy management stage. This coefficient comprehensively reflects the overall degree of energy consumption anomaly in that stage under the current predicted environment.

[0033] The system compares the energy loss coefficient with a preset energy loss threshold, which is a critical value set based on historical data analysis, industry standards, or enterprise energy efficiency targets. The judgment logic is as follows: if the loss coefficient is below the threshold, it indicates that the energy consumption deviation under the current prediction conditions is within an acceptable range, and no optimization adjustment is needed; if the loss coefficient is greater than or equal to the threshold, it indicates that the degree of energy consumption anomaly has exceeded the allowable range, and there is significant room for optimization and necessity. At this point, the system will determine that the set of equipment operating parameters for this stage needs to be optimized. The specific shape and numerical distribution of the energy loss vector itself indicate the direction for subsequent optimization adjustments. For example, it indicates in which sub-stage the loss is greatest—whether it is the startup process, stable operation, or deceleration phase—thus enabling the generated energy consumption optimization strategy to be highly targeted and effective. The entire implementation process, through accurate model prediction, refined vector comparison, and weighted evaluation, achieves early diagnosis and quantitative assessment of energy consumption anomalies in the manufacturing process, providing a solid basis for dynamic energy consumption management.

[0034] Example 3: See Figure 4 The implementation begins with adjusting the set of equipment operating parameters based on the energy loss vectors of each energy management stage. The set of equipment operating parameters includes all adjustable operational variables for that stage. For example, in the concrete mixing stage, the parameter set might include the mixer motor speed, mixing paddle angle, water valve opening, and mixing time; in the steam curing stage, it might include steam pressure, curing pit temperature setpoint, duration of each temperature rise stage, and ventilation fan frequency. The energy loss vector indicates the specific manifestation of current energy consumption anomalies, such as excessively high power peaks during a certain period in the mixing stage, or persistently exceeding energy limits during the constant temperature period in the curing stage. Based on this loss information, the system generates a series of targeted adjustment decisions. Each decision is a proposal to adjust one or more variables within the parameter set, such as "reducing the mixer motor speed from the current 30 rpm to 28 rpm" or "adjusting the constant temperature setpoint for the curing period from 75 degrees Celsius to 72 degrees Celsius and extending the constant temperature time by 20 minutes." The system generates a large number of such initial decisions, forming a set containing... The initial energy consumption adjustment space of the feasible adjustment scheme is as follows: ; in: Representing the A regulatory decision, It represents the entire decision-making space.

[0035] The system performs an initial optimization analysis on this vast initial space, aiming to filter out a subset of decisions that theoretically lead to energy efficiency improvements. The analysis process relies on an energy consumption prediction model and predetermined energy loss weights. For Each regulatory decision in The system simulates the execution of this decision: First, based on the content of the decision, it deduces the potential changes in the manufacturing environment caused by the change in equipment operating parameters. For example, reducing the stirring speed may reduce motor heating, thereby indirectly reducing the ambient temperature around the mixer; reducing the curing temperature setpoint will directly change the thermal environment within the curing pit. This impact on the environment is quantified as a predicted change in energy consumption environment. Subsequently, the adjusted equipment configuration scheme (including parameter changes) and the predicted change in energy consumption environment are input into the energy consumption prediction model. The model outputs the expected energy consumption performance after executing this decision, i.e., the decision energy consumption prediction vector. Afterward, the system uses the energy loss weighting conditions defined in Example 2 to perform a weighted calculation on the decision energy consumption prediction vector to obtain the decision energy loss coefficient. This coefficient characterizes the adoption decision. The expected overall energy loss level after the system will be determined. With energy loss threshold Compare. If If this indicates that the decision is expected to improve energy consumption to an acceptable level, it is included in a preliminary set of high-quality decisions, referred to as the energy consumption regulation space optimization. .

[0036] To further increase the likelihood of finding a better solution and avoid getting trapped in local optima, the system... Perform mutation to optimize and expand. The mutation operation is an optimization of existing high-quality decisions. By introducing small-amplitude random perturbations or parameter cross-combinations, a series of new candidate decisions can be generated. For example, a decision regarding temperature and time. Its variants may be ,in and These are small increments generated randomly within a reasonable range. All these newly generated mutation decisions constitute the initial mutation energy consumption space. The system then... For each decision, the same optimization analysis process described above is repeated: predict environmental changes, input the model to obtain a prediction vector, calculate the loss coefficient, and compare it with a threshold. The decisions that pass the test are those... The mutation decision is added to the space for optimizing mutation energy consumption. In the end, it will be... and By merging, a richer and more diverse space for extended energy consumption regulation can be formed. .

[0037] The system is in this extended space The process involves minimizing energy loss within the space. This process evaluates every decision in the space. The corresponding decision energy loss coefficient and find ways to make The decision with the smallest value: ; in: This represents the ultimately selected optimal energy consumption regulation strategy. Represents the expanded decision space. Representative decision The corresponding energy loss coefficient. This strategy is output as the final energy consumption optimization strategy for this energy management phase, directly guiding the parameter adjustment of production equipment. The entire implementation process, through generation, simulation, screening, mutation, and final selection, achieves a refined and automated energy efficiency optimization for complex manufacturing processes.

[0038] Example 4: The implementation process begins with utilizing a long-term accumulated record set of adjustment variation value evaluation records. This record systematically stores the actual effect data generated after each variation operation on energy consumption adjustment decisions throughout history. Each record not only contains the original decision parameters before variation and the type of variation operation used (such as parameter fine-tuning, parameter crossover, sequence recombination, etc.), but more importantly, it records the change in the actual energy consumption loss coefficient calculated through real-time monitoring after executing the variation decision. Based on this massive record set, the system uses data mining methods to construct an adjustment variation value evaluation system. This system is essentially a predictive model whose function is to evaluate the potential value or success probability of producing an even better decision (i.e., further reducing the energy consumption loss coefficient) after applying a certain type of variation operation to a given high-quality energy consumption adjustment decision.

[0039] The system inputs each energy consumption adjustment decision within the optimized energy consumption adjustment space and its corresponding energy loss coefficient into this evaluation system. The evaluation system generates one or more adjustment variation value coefficients for each decision. This coefficient is a value between zero and one; a higher value indicates that, based on historical experience, adjusting the decision is more likely to uncover potential strategies with better energy consumption performance. For example, for a decision to reduce energy consumption by lowering the stirring speed, if historical records show that in similar past situations, further fine-tuning the speed in conjunction with adjusting the stirring time has repeatedly yielded better results, then the evaluation system will assign a higher value coefficient to this type of variation operation, "speed fine-tuning," for that decision.

[0040] The system performs targeted mutation operations on the optimized energy consumption adjustment space based on these value coefficients. The value coefficient directly determines the resource allocation and exploration depth of the mutation operation. For decision-mutation type combinations with high value coefficients, the system generates more numerous and diverse variants for in-depth exploration; for combinations with low value coefficients, mutation attempts may be reduced or skipped entirely. The mutation operation involves making random perturbations or logical adjustments within a limited range based on the parameters of the original decision. For example, a decision about steam curing includes two parameters: temperature and duration. Its variant might be to add or subtract a small random fluctuation value from the original temperature value, while adjusting the duration parameter accordingly. All these newly generated mutation decisions constitute the initial mutated energy consumption space.

[0041] For each newly generated mutation decision in the initial mutated energy consumption space, the system performs the same rigorous optimization analysis process as in Example 3. This process is purely simulation-based: First, based on the parameter adjustments of the mutation decision, the potential changes to the manufacturing environment are predicted; then, the changed environmental parameters and the adjusted equipment configuration are input into the energy consumption prediction model to obtain the expected energy consumption performance data after adopting the mutation decision; next, the decision energy consumption loss coefficient corresponding to the decision is calculated using the energy consumption loss weight condition; finally, it is determined whether the coefficient is lower than the energy consumption loss threshold. Only those mutation decisions that pass the verification, i.e., those expected to control energy consumption within an acceptable range, are retained and enter the optimized mutated energy consumption space.

[0042] The system merges all these newly discovered and effective mutation decisions in the optimization mutation energy consumption space with the original optimization energy consumption adjustment space, thereby establishing an extended energy consumption adjustment space that is richer in quantity, more diverse in quality, and potentially superior in solution performance. This extended space provides a more solid and broader selection basis for the subsequent final minimization optimization.

[0043] Table 1: Record of evaluation of regulatory variation value.

[0044]

[0045] Refer to Table 1, which illustrates examples of historical data upon which the value assessment system relies. It records the actual effects of different mutation operations; for example, fine-tuning parameters (speed, temperature) often yields positive results, while some radical mutations (such as drastically reducing temperature) may be counterproductive due to their impact on the process. Coordinated adjustments to multiple parameters (such as pressure and fan frequency) demonstrate the potential for significant success. This historical experience is learned by the assessment system and used to guide the next round of mutation optimization.

[0046] Example 5: The implementation process first employs an energy consumption correlation calculation method. The core of this method lies in analyzing the intrinsic relationship between the energy consumption baseline vector and the energy consumption loss vector at each energy management stage. The energy consumption baseline vector characterizes the ideal energy consumption pattern under standard conditions at that stage, while the energy consumption loss vector records the degree and shape of deviation from the baseline under current predicted conditions. The correlation calculation does not examine the statistical characteristics of a single vector in isolation, but rather delves into the dynamic correlation patterns between vector sequences from different stages. The system analyzes whether abnormal energy consumption fluctuations in one stage will cause or accompany energy consumption changes in other stages. For example, in the steam curing stage of pole manufacturing, if its energy consumption loss vector shows a persistently high energy consumption during the constant temperature period, the system analyzes whether this anomaly is correlated in time or magnitude with the sudden increase in starting power shown in the energy consumption loss vector of the subsequent demolding stage. The calculation process may involve analyzing the covariance trend of the two vector sequences, the order of occurrence of abnormal events, or the recurrence frequency of specific patterns. Through this cross-stage analysis, the system calculates a correlation value for each possible pair of stage combinations, which quantifies the degree of mutual influence between their energy consumption fluctuations.

[0047] After obtaining pairwise correlations between all stages, the system proceeds to the critical stage screening process. This process first calculates a comprehensive correlation score for each energy management stage. This score may be based on the weighted sum of the correlations between that stage and all other stages, with weights set according to the stage's position in the process flow or its historical importance. For example, a stage located in the middle of the manufacturing process will have a higher comprehensive correlation score if its energy consumption fluctuations are calculated to significantly impact the energy consumption performance of upstream raw material preparation and downstream centrifugal molding. The system then ranks all energy management stages in descending order based on this comprehensive score. The top few stages with the highest scores are selected and defined as critical energy management stages. The number of stages selected is not fixed and may be dynamically adjusted according to the complexity of the manufacturing task; for example, the top three stages may be selected during full-load production, while only the top-ranked stage may be selected during normal operation.

[0048] After identifying the critical energy consumption management stages, the system implements a priority processing mechanism during the subsequent optimization and adjustment of equipment operating parameters. When energy loss vectors from multiple stages simultaneously trigger optimization needs, the system prioritizes processing the vectors from the critical stages. Specifically, when generating energy consumption optimization strategies, the system first extracts the energy loss vectors from the critical energy consumption management stages and immediately initiates the optimization and adjustment process for equipment operating parameters for that stage. This process fully follows the steps described in Examples 2 to 4: generating an adjustment decision space based on the loss vectors, simulating and evaluating through predictive models, performing optimization screening and mutation expansion, and finally selecting the optimal adjustment strategy. Only after generating optimization strategies for all critical stages will the system move on to processing the energy loss vectors of non-critical stages. This asymmetric processing order ensures that regulatory resources are tilted towards high-impact links. For example, if the steam curing stage is identified as a critical stage, its optimization strategies regarding temperature setpoints and ventilation duration will be generated and executed first; while parameter adjustments for non-critical stages such as steel reinforcement preparation may be performed later, or even, in some cases, maintained as is if their loss coefficients do not exceed a threshold. The entire implementation process constructs an energy efficiency optimization resource allocation mechanism based on systems thinking through quantitative correlation, sorting and screening, and priority scheduling.

[0049] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0050] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for dynamic management of equipment energy consumption throughout the entire pole manufacturing process, characterized in that, include: Based on the process flow of pole manufacturing, energy consumption stages are divided to obtain multiple energy management stages; Based on equipment operation data and environmental monitoring data, energy consumption environment is predicted for the multiple energy consumption management stages to obtain the predicted energy consumption environment for each energy consumption management stage. Based on the energy consumption benchmark factor, the benchmark energy consumption parameters of the equipment configuration schemes corresponding to the multiple energy consumption management stages are calculated to determine the energy consumption benchmark vector for each energy consumption management stage. Based on the energy consumption benchmark vectors of each energy consumption management stage, energy consumption loss is predicted for the predicted energy consumption environment of each energy consumption management stage according to the energy consumption prediction model, and energy consumption loss vectors of each energy consumption management stage are established. Based on the energy loss vector of each energy management stage, the set of equipment operating parameters is optimized and adjusted to generate an energy consumption optimization strategy. Adaptive energy management is performed on the pole manufacturing process based on the set of operating parameters of the control equipment according to the energy consumption optimization strategy.

2. The method for dynamic management of equipment energy consumption throughout the entire pole manufacturing process as described in claim 1, characterized in that, Based on equipment operation data and environmental monitoring data, energy consumption environment prediction is performed for the multiple energy consumption management stages to obtain the predicted energy consumption environment for each energy consumption management stage, including: Acquire equipment operation data during the pole manufacturing process, including motor power and transmission efficiency; The environmental monitoring data of the pole manufacturing process is obtained, including temperature data and humidity data. Based on the equipment operation data and environmental monitoring data, environmental change trend analysis is performed for each energy consumption management stage, and predicted energy consumption environment for each energy consumption management stage is generated.

3. The method for dynamic management of equipment energy consumption throughout the entire pole manufacturing process as described in claim 2, characterized in that, Based on the energy consumption benchmark factor, the benchmark energy consumption parameters of the equipment configuration schemes corresponding to the multiple energy consumption management stages are calculated to determine the energy consumption benchmark vector for each energy consumption management stage, including: Based on the energy consumption benchmark factor, normal energy consumption samples are retrieved for the equipment configuration schemes in each energy consumption management stage to obtain the energy consumption sample set for each energy consumption management stage. Based on the energy consumption sample sets of each energy consumption management stage, the central value is calculated to obtain the energy consumption benchmark sequence for each energy consumption management stage. Construct an energy consumption benchmark vector for each energy consumption management stage based on the energy consumption benchmark sequence for each energy consumption management stage.

4. The method for dynamic management of equipment energy consumption throughout the entire pole manufacturing process as described in claim 3, characterized in that, Based on the energy consumption baseline vectors for each energy consumption management stage, energy loss is predicted for the predicted energy consumption environment of each energy consumption management stage according to the energy consumption prediction model, and an energy loss vector for each energy consumption management stage is established, including: The equipment configuration scheme for each energy management stage and the predicted energy consumption environment for each energy management stage are input into the energy consumption prediction model to obtain the energy consumption prediction vector for each energy management stage. Based on the energy consumption benchmark vector of each energy consumption management stage, the deviation of the energy consumption prediction vector of each energy consumption management stage is identified to obtain the energy consumption loss vector of each energy consumption management stage.

5. The method for dynamic management of equipment energy consumption throughout the entire pole manufacturing process as described in claim 4, characterized in that, Based on the energy loss vectors of each energy management stage, the set of equipment operating parameters is optimized and adjusted to generate an energy consumption optimization strategy, including: Obtain energy loss weighting conditions, which include power loss weights and efficiency loss weights; The energy loss vectors of each energy management stage are weighted according to the energy loss weight conditions to obtain the energy loss coefficient of each energy management stage. Determine whether the energy loss coefficient of each energy management stage is greater than or equal to the energy loss threshold; If the energy loss coefficient is greater than or equal to the energy loss threshold, the set of equipment operating parameters is optimized and adjusted according to the energy loss vector of each energy management stage to generate an energy optimization strategy for each energy management stage.

6. The method for dynamic management of equipment energy consumption throughout the entire pole manufacturing process as described in claim 5, characterized in that, Based on the energy loss vectors of each energy management stage, the set of equipment operating parameters is optimized and adjusted to generate energy optimization strategies for each energy management stage, including: Based on the energy loss vector of each energy management stage, the set of equipment operating parameters is adjusted and decisions are made to establish an energy adjustment space that meets the predetermined number of decisions. Based on the energy consumption prediction model and the energy loss weighting condition, the energy consumption adjustment space is optimized through optimization analysis to obtain the optimal energy consumption adjustment space. Based on the optimized energy consumption regulation space, variation optimization is carried out to expand and establish an extended energy consumption regulation space; Based on the expanded energy consumption adjustment space, the optimization strategy for minimizing energy loss is generated for each energy consumption management stage.

7. The method for dynamic management of equipment energy consumption throughout the entire pole manufacturing process as described in claim 6, characterized in that, Based on the energy consumption prediction model and energy loss weighting conditions, an optimization analysis is performed on the energy consumption adjustment space to obtain the optimized energy consumption adjustment space, including: Energy consumption regulation decisions are extracted based on the energy consumption regulation space; Based on energy consumption regulation decisions, the predicted energy consumption environment at each stage of energy consumption management is predicted to change, and the predicted changing energy consumption environment is obtained. Input the equipment configuration scheme and predicted changes in energy consumption environment at each stage of energy management into the energy consumption prediction model to obtain the decision energy consumption prediction vector. The decision energy consumption prediction vector is weighted according to the energy consumption loss weight condition to obtain the decision energy consumption loss coefficient. Determine whether the energy loss coefficient of the decision is less than the energy loss threshold; If the energy loss coefficient of the decision is less than the energy loss threshold, the energy consumption adjustment decision will be added to the optimized energy consumption adjustment space.

8. The method for dynamic management of energy consumption of the equipment for the entire process of pole manufacturing according to claim 7, characterized in that, Based on the optimized energy consumption regulation space, a variational optimization expansion is performed to establish an extended energy consumption regulation space, including: Construct a moderating variance value evaluation system based on the moderating variance value evaluation record set; The decision energy loss coefficient corresponding to each energy consumption regulation decision within the optimized energy consumption regulation space is input into the regulation variation value evaluation system to obtain each regulation variation value coefficient. The energy consumption adjustment space is mutated according to each adjustment variation value coefficient to obtain the initial mutated energy consumption space; Based on the energy consumption prediction model and the energy consumption loss weight conditions, the initial variable energy consumption space is optimized to obtain the optimized variable energy consumption space. Based on the optimization of the variable energy consumption space, the optimized energy consumption adjustment space is expanded, and an extended energy consumption adjustment space is established.

9. The method for dynamic management of energy consumption of the equipment for the entire process of pole manufacturing according to claim 8, characterized in that, Based on the energy loss vectors of each energy management stage, the set of equipment operating parameters is optimized and adjusted to generate an energy consumption optimization strategy, which also includes: Based on the energy consumption correlation calculation method, key stages are screened for each energy consumption management stage to obtain key energy consumption management stages. The set of equipment operating parameters is preferentially adjusted based on the energy loss vector of the key energy management phase.

10. The method for dynamic management of energy consumption of the equipment for the entire process of pole manufacturing according to claim 9, characterized in that, Based on the energy consumption correlation calculation method, key stages are screened for each energy consumption management stage to obtain the key energy consumption management stages, including: Calculate the energy consumption correlation degree based on the energy consumption baseline vector and energy consumption loss vector of each energy consumption management stage; According to the energy consumption correlation degree, each energy consumption management stage is sorted and screened to obtain a key energy consumption management stage.

Images