An intelligent factory device energy efficiency optimization system

Abstract

The present application relates to the technical field of device control optimization, and more particularly to a kind of intelligent factory equipment energy efficiency optimization system, the present application proposes the following scheme, the wall thickness distribution data of steel pipe, local residual stress and temperature gradient field in straightening process are collected, the actual yield strength of each section of steel pipe is calculated using the preset plastic mechanics model and the theoretical straightening energy threshold value, to generate the straightening parameter set of steel pipe straightening machine. Further correct the straightening parameter set according to the temperature gradient field, to optimize the elimination of energy consumption. By dividing the straightening area of steel pipe, the heat-sensitive area and low-temperature hardening area are identified, and the correction weight is allocated according to the area difference of these areas, and then the corrected straightening parameter set is generated, to optimize the straightening process of steel pipe.

Description

A smart factory equipment energy efficiency optimization system Technical Field

[0001] This invention relates to the field of equipment control optimization technology, and in particular to an intelligent factory equipment energy efficiency optimization system. Background Technology

[0002] Steel pipe straightening machines play a crucial role in the steel pipe production process, used to correct the bending deformation of steel pipes. Traditional straightening processes typically rely on empirical formulas and fixed straightening parameters, making it difficult to accurately match the actual characteristics of the steel pipe material, thus leading to energy waste and over-processing.

[0003] The problem raised in this background technology is that under conditions of large temperature variations, the yield strength and deformation characteristics of steel pipes are difficult to predict accurately, which affects the straightening quality and wastes energy. To solve the above problems, this application designs an intelligent factory equipment energy efficiency optimization system. Summary of the Invention

[0004] The technical problem this invention aims to solve is to address the shortcomings of existing technologies by providing an intelligent factory equipment energy efficiency optimization system. This system collects wall thickness distribution data, local residual stress, and temperature gradient field during the straightening process of steel pipes. Using a pre-set plasticity model, it calculates the actual yield strength and theoretical straightening energy threshold of each segment of the steel pipe, thereby generating a straightening parameter set for the steel pipe straightening machine. The straightening parameter set is further modified based on the temperature gradient field to optimize and eliminate energy consumption. By dividing the steel pipe straightening area, identifying heat-sensitive and low-temperature hardening areas, and assigning correction weights based on the area differences of these areas, a modified straightening parameter set is generated, thus optimizing the steel pipe straightening process.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] An intelligent factory equipment energy efficiency optimization system is applied to a steel pipe straightening machine. The steel pipe straightening machine is equipped with a detection device. The intelligent factory equipment energy efficiency optimization system includes a data acquisition module, a data processing module, and a data correction module, wherein:

[0007] The data acquisition module is used to acquire wall thickness distribution data, local residual stress, and temperature gradient field during the straightening process of the steel pipe through the detection device.

[0008] The data processing module is used to calculate the actual yield strength and theoretical straightening energy threshold of each segment of the steel pipe according to the output of the data acquisition module, and generate the straightening parameter set of the steel pipe straightening machine according to the actual yield strength and theoretical straightening energy threshold.

[0009] The data correction module is used to correct the straightening parameter set according to the temperature gradient field in order to reduce energy consumption for elimination.

[0010] The data processing module includes:

[0011] The plasticity calculation unit is used to calculate the actual yield strength of each segment of the steel pipe using the yield criterion and stress-strain relationship;

[0012] An energy threshold calculation unit is used to calculate the theoretical straightening energy threshold based on the output of the plasticity calculation unit and the hardening law.

[0013] The parameter generation unit is used to generate a set of straightening parameters for the steel pipe straightening machine based on the calculated actual yield strength and the theoretical straightening energy threshold.

[0014] The parameter generation unit includes:

[0015] Determine the ideal straightening stress and bending angle for each segment during the steel pipe straightening process;

[0016] Based on the ideal straightening stress and bending angle, the actual working parameter set of the steel pipe straightening machine is optimized by a reinforcement learning algorithm to generate a straightening parameter set, wherein the straightening parameter set includes the straightening speed, roller pressure and roller spacing of the steel pipe straightening machine.

[0017] The optimization of the actual working parameter set of the steel pipe straightening machine using reinforcement learning algorithms includes:

[0018] Preliminary parameters for the steel pipe straightening process are calculated using the ideal straightening stress and bending angle.

[0019] The steel pipe straightening process was virtually simulated based on the preliminary parameters to obtain the straightening effect.

[0020] Based on the straightening effect, the straightening speed, roller pressure, and roller spacing of the steel pipe straightening machine are adjusted using a reward function to generate a straightening parameter set.

[0021] The data correction module includes:

[0022] Temperature field modeling unit, used to construct nonlinear material response model of steel pipe under temperature gradient field conditions;

[0023] The correction factor calculation unit is used to calculate the thermal stress correction factor caused by the temperature gradient field based on the actual yield strength of each segment of the steel pipe according to the nonlinear material response model.

[0024] The correction parameter calculation unit is used to correct the straightening parameter set according to the thermal stress correction factor and generate the correction parameter set.

[0025] The temperature field modeling unit includes:

[0026] Temperature fluctuation feature matrices at different spatial frequencies were extracted by wavelet multi-scale decomposition.

[0027] The temperature fluctuation feature matrix is ​​input into a preset cyclic plasticity model, and the output is a piecewise differentiated thermal stress relationship, wherein the cyclic plasticity model includes a temperature-dependent hardening function and a dynamic recovery term;

[0028] Identify the local austenitization phenomenon in the thermal stress relationship, calculate the martensitic transformation volume fraction of the local austenitization phenomenon, and correct the thermal stress relationship based on the martensitic transformation volume fraction.

[0029] A nonlinear material response model is generated based on the corrected thermal stress relationship.

[0030] The temperature fluctuation feature matrix is ​​input into a preset cyclic plasticity model, and the output is a piecewise differentiated thermal stress relationship, including:

[0031] Perform time-frequency joint analysis on the temperature fluctuation feature matrix to generate thermal shock events;

[0032] Based on the thermal shock event, the temperature-dependent hardening function of the cyclic plasticity model is spatially adaptively adjusted;

[0033] Based on non-thermal shock events, the dynamic recovery term of the cyclic plasticity model is historically coupled and adjusted;

[0034] The thermal stress relationship is output based on the adjusted temperature-dependent hardening function and dynamic recovery term.

[0035] The time-frequency joint analysis includes:

[0036] The wavelet modulus maxima detection algorithm is used to locate abrupt changes in the temperature fluctuation feature matrix where the rate of temperature change exceeds a preset threshold, and a set of spatiotemporal coordinates of thermal shock is generated.

[0037] Based on the aforementioned thermal shock spatiotemporal coordinate set and combined with the thermal fatigue characteristics of the steel pipe material, the cumulative thermal shock intensity index is calculated for each abrupt change point to generate a thermal shock event.

[0038] The correction factor calculation unit includes:

[0039] The nonlinear material response model is discretized using the finite volume method to construct a spatiotemporal evolution heat conduction equation.

[0040] Based on the heat conduction equation, the dynamic correction relationship between the temperature gradient field and the actual yield strength of each segment of the steel pipe is calculated.

[0041] The thermal stress correction factor for each segment of the steel pipe is calculated based on the dynamic correction relationship.

[0042] The correction parameter calculation unit includes:

[0043] The steel pipe straightening area is divided into a heat-sensitive area and a low-temperature hardening area.

[0044] Based on the area difference between the heat-sensitive region and the low-temperature hardening region, correction weights are assigned to the two regions;

[0045] A set of correction parameters is generated based on the correction weights.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] This invention, by rationally dividing the steel pipe straightening area and combining the differences between the heat-sensitive area and the low-temperature hardening area, can specifically adjust the operating parameters of the straightening machine, thus avoiding the problems of over-straightening or under-straightening caused by temperature differences in traditional methods. Attached Figure Description

[0048] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0049] Figure 1 is a block diagram of an intelligent factory equipment energy efficiency optimization system according to Embodiment 1 of the present invention;

[0050] Figure 2 is a flowchart illustrating an energy efficiency optimization method for intelligent factory equipment according to Embodiment 2 of the present invention;

[0051] Figure 3 is a schematic diagram of the construction process of the nonlinear material response model in Embodiment 2 of the present invention. Detailed Implementation

[0052] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0053] Example 1:

[0054] Please refer to Figure 1. One embodiment of the present invention provides: an intelligent factory equipment energy efficiency optimization system. The dashed line indicates the data transmission direction. This system is applied to a steel pipe straightening machine, which is equipped with a detection device. The intelligent factory equipment energy efficiency optimization system includes a data acquisition module, a data processing module, and a data correction module, wherein:

[0055] The data acquisition module is used to acquire wall thickness distribution data, local residual stress, and temperature gradient field during the straightening process of the steel pipe through the detection device.

[0056] The data processing module is used to calculate the actual yield strength and theoretical straightening energy threshold of each segment of the steel pipe according to the output of the data acquisition module, and generate the straightening parameter set of the steel pipe straightening machine according to the actual yield strength and theoretical straightening energy threshold.

[0057] The data correction module is used to correct the straightening parameter set according to the temperature gradient field in order to reduce energy consumption for elimination.

[0058] The data acquisition module includes a detection unit, which is used to configure the detection device to collect wall thickness distribution data, local residual stress, and temperature gradient field during the straightening process of the steel pipe.

[0059] The data processing module includes:

[0060] The plasticity calculation unit is used to calculate the actual yield strength of each segment of the steel pipe using the yield criterion and stress-strain relationship;

[0061] An energy threshold calculation unit is used to calculate the theoretical straightening energy threshold based on the output of the plasticity calculation unit and the hardening law.

[0062] The parameter generation unit is used to generate a set of straightening parameters for the steel pipe straightening machine based on the calculated actual yield strength and the theoretical straightening energy threshold.

[0063] The parameter generation unit includes:

[0064] Determine the ideal straightening stress and bending angle for each segment during the steel pipe straightening process;

[0065] Based on the ideal straightening stress and bending angle, the actual working parameter set of the steel pipe straightening machine is optimized by a reinforcement learning algorithm to generate a straightening parameter set, wherein the straightening parameter set includes the straightening speed, roller pressure and roller spacing of the steel pipe straightening machine.

[0066] The data correction module includes:

[0067] Temperature field modeling unit, used to construct nonlinear material response model of steel pipe under temperature gradient field conditions;

[0068] The correction factor calculation unit is used to calculate the thermal stress correction factor caused by the temperature gradient field based on the actual yield strength of each segment of the steel pipe according to the nonlinear material response model.

[0069] The correction parameter calculation unit is used to correct the straightening parameter set according to the thermal stress correction factor and generate the correction parameter set.

[0070] The temperature field modeling unit includes:

[0071] Temperature fluctuation feature matrices at different spatial frequencies were extracted by wavelet multi-scale decomposition.

[0072] The temperature fluctuation feature matrix is ​​input into a preset cyclic plasticity model, and the output is a piecewise differentiated thermal stress relationship, wherein the cyclic plasticity model includes a temperature-dependent hardening function and a dynamic recovery term;

[0073] Identify the local austenitization phenomenon in the thermal stress relationship, calculate the martensitic transformation volume fraction of the local austenitization phenomenon, and correct the thermal stress relationship based on the martensitic transformation volume fraction.

[0074] A nonlinear material response model is generated based on the corrected thermal stress relationship.

[0075] The correction factor calculation unit includes:

[0076] The nonlinear material response model is discretized using the finite volume method to construct a spatiotemporal evolution heat conduction equation.

[0077] Based on the heat conduction equation, the dynamic correction relationship between the temperature gradient field and the actual yield strength of each segment of the steel pipe is calculated.

[0078] The thermal stress correction factor for each segment of the steel pipe is calculated based on the dynamic correction relationship.

[0079] The correction parameter calculation unit includes:

[0080] The steel pipe straightening area is divided into a heat-sensitive area and a low-temperature hardening area.

[0081] Based on the area difference between the heat-sensitive region and the low-temperature hardening region, correction weights are assigned to the two regions;

[0082] A set of correction parameters is generated based on the correction weights.

[0083] Example 2:

[0084] Please refer to Figure 2. This invention provides an embodiment: an energy efficiency optimization method for smart factory equipment based on lean manufacturing, applied to a steel pipe straightening machine. The steel pipe straightening machine is equipped with a detection device, which is used to collect wall thickness distribution data, local residual stress, and temperature gradient field during the straightening process of the steel pipe. The specific steps of the method are as follows:

[0085] S1: Input the collected wall thickness distribution data and local residual stress into the preset plasticity model to calculate the actual yield strength and theoretical straightening energy threshold of each segment of the steel pipe;

[0086] In this embodiment, the wall thickness distribution data and local residual stress of the steel pipe are first collected in real time by the detection device of the steel pipe straightening machine. This data is input into a preset plasticity mechanics model, which combines the yield criterion and stress-strain relationship to calculate the actual yield strength of each segment of the steel pipe. By combining the wall thickness distribution data and local residual stress of the steel pipe, the actual yield strength that each segment of the steel pipe may encounter during the straightening process is calculated, simulating the yield behavior of the steel pipe under different conditions. This provides data for optimizing the operating parameters of the steel pipe straightening machine, thereby avoiding excessive energy consumption and reducing equipment wear and tear.

[0087] S2: Generate the straightening parameter set of the steel pipe straightening machine based on the actual yield strength and the theoretical straightening energy threshold;

[0088] In this embodiment, a corresponding set of straightening parameters is generated based on the actual yield strength and theoretical straightening energy threshold of each steel pipe segment obtained from the plasticity mechanics model. These parameters include the straightening speed of the straightener, roller pressure, and roller spacing, aiming to ensure the optimal balance between energy efficiency and quality during the steel pipe straightening process. By comprehensively considering the yield strength and energy threshold of each steel pipe segment, the working state of the straightener can be optimized, ensuring that the steel pipe can be straightened smoothly without wasting energy and without excessive equipment wear. Controlling every aspect of the steel pipe process improves straightening quality and reduces unnecessary energy consumption.

[0089] S3: Correct the straightening parameter set according to the temperature gradient field to reduce energy consumption for elimination;

[0090] In this embodiment, the straightening parameter set is further modified by acquiring temperature gradient field data during the straightening process. Specifically, the temperature gradient field has a significant impact on the yield strength and deformation capacity of the steel pipe. Therefore, the operating parameters of the straightening machine, such as straightening speed and roller pressure, are adjusted according to real-time temperature data. By considering the performance changes of the steel pipe under different temperature conditions, the energy consumption during the straightening process can be dynamically optimized. Real-time adjustment based on actual temperature changes avoids over-straightening under unsuitable temperature conditions, thereby reducing unnecessary energy consumption and improving production efficiency and energy saving.

[0091] Specifically, this application optimizes the energy efficiency of the steel pipe straightening process by incorporating a temperature gradient field. By using a nonlinear material response model and a thermal stress correction factor, it effectively overcomes the deficiency in existing technologies where the yield strength and deformation characteristics of steel pipes are difficult to predict accurately under large temperature variations, thus affecting straightening quality and wasting energy.

[0092] Furthermore, this application monitors the temperature change of the steel pipe in real time during the straightening process and dynamically adjusts the working parameters of the straightening machine (such as straightening speed, roller pressure, etc.) based on these temperature data to ensure that each segment of the steel pipe straightening process can be straightened under the optimal temperature conditions, thereby minimizing energy consumption and improving the accuracy of steel pipe straightening.

[0093] For example, when the steel pipe exhibits different temperature distributions, this application can adjust the working state of the straightening machine in real time to adapt to these changes, thereby reducing unnecessary energy waste and improving production efficiency. Furthermore, this dynamic optimization method based on temperature gradients combines the actual yield strength of the steel pipe with the theoretical straightening energy threshold, enabling the straightening machine to operate precisely under different temperature conditions and avoiding instability in straightening quality caused by the influence of temperature changes on the steel pipe material.

[0094] The plasticity mechanical model is configured based on the material's yield criterion, stress-strain relationship, and hardening law.

[0095] The specific steps of S1 are as follows:

[0096] S1.1: Based on the wall thickness distribution data and the local residual stress, calculate the actual yield strength of each segment of the steel pipe using the yield criterion and the stress-strain relationship;

[0097] Specifically, during the actual production and manufacturing process of steel pipes, uneven cooling, differences in rolling precision, or deviations in manufacturing processes inevitably lead to non-uniform distribution of steel pipe wall thickness and the existence of local residual stress. These factors directly affect the material strength and plastic deformation behavior of various local areas during the straightening process of steel pipes. Therefore, simply using the average yield strength or standardized material strength parameters to calculate the straightening parameters will not achieve good straightening accuracy and quality.

[0098] In this embodiment, the plasticity mechanics model employs classical yield criteria such as Mises or Tresca. By accurately calculating the equivalent stress distribution of each segment of the steel pipe under multidimensional stress states, and combining this with the stress-strain relationship unique to the steel pipe material—specifically, the nonlinear variation trend within the elastic-plastic transition region determined experimentally—the most realistic and accurate actual yield strength of each segment of the steel pipe is determined. This allows the steel pipe straightening machine to accurately grasp the true deformation limit of each segment, avoiding insufficient or excessive plastic deformation during subsequent straightening processes, improving the accuracy of steel pipe straightening, and preventing material waste and equipment wear caused by over-straightening.

[0099] S1.2: Based on the actual yield strength, geometric parameters, and material properties of each segment of the steel pipe, the theoretical straightening energy threshold is calculated using the hardening law described above;

[0100] Specifically, during the actual straightening process of steel pipes, the internal crystal structure of the material undergoes significant changes as deformation progresses. In particular, with the accumulation of plastic deformation, strain hardening occurs. This hardening leads to a gradual increase in material strength, requiring greater external force and energy to achieve subsequent straightening actions. If this nonlinear hardening characteristic within the material is not considered, traditional methods that design straightening parameters solely based on the initial yield strength will result in energy consumption exceeding theoretical calculations during actual straightening, impacting equipment energy efficiency and increasing production costs.

[0101] In this embodiment, a material-based nonlinear hardening model is specifically employed. The actual yield strength of each segment of the steel pipe, along with the material's geometric parameters and properties, are substituted into this hardening model. Through a step-by-step correction method, the theoretical straightening energy thresholds required for different deformation stages during the steel pipe straightening process are calculated. This enables the steel pipe straightening machine to obtain the most accurate theoretical straightening energy benchmark, improving the energy efficiency control precision in the subsequent actual straightening process. This reduces unnecessary energy loss during steel pipe production, minimizes equipment wear, and enhances the economic efficiency and energy performance of production.

[0102] The specific steps of S2 are as follows:

[0103] S2.1: Determine the ideal straightening stress and bending angle for each segment during the steel pipe straightening process based on the actual yield strength and the theoretical straightening energy threshold;

[0104] Specifically, the actual yield strength and the theoretical straightening energy threshold are the basic data for the minimum energy and deformation strength required during the straightening process of the steel pipe. The determination of the ideal straightening stress is based on the yield strength of each segment and the stress concentration in that area, combined with the geometry of the steel pipe (such as inner and outer diameters, wall thickness, etc.), to ensure that each segment can be optimized for straightening at its ultimate yield strength, thereby avoiding excessive or insufficient deformation of the steel pipe due to excessive or insufficient stress during the straightening process. The ideal bending angle is calculated based on the ideal straightening stress and the theoretical straightening energy threshold required during the straightening process, under the premise of ensuring that the steel pipe does not spring back or deform excessively.

[0105] S2.2: Based on the ideal straightening stress and bending angle, the actual working parameter set of the steel pipe straightening machine is optimized by a reinforcement learning algorithm to generate a straightening parameter set, wherein the straightening parameter set includes the straightening speed, roller pressure and roller spacing of the steel pipe straightening machine;

[0106] Specifically, based on the ideal straightening stress and bending angle of each segment of the steel pipe, the reinforcement learning algorithm simulates the straightening effect of the steel pipe under different working parameters, and dynamically optimizes parameters such as the straightening speed, roller pressure and roller spacing of the straightening machine to ensure that the steel pipe achieves the best balance between energy efficiency and quality in the actual straightening process.

[0107] Preferred, the reinforcement learning algorithm employed goes beyond simply solving an optimization problem; it dynamically adjusts the process in real time based on the specific production environment and actual feedback information during the pipe straightening process. This adjustment includes the gradual correction of various important parameters of the pipe straightener. For example, adjusting the straightening speed directly affects the deformation rate of the pipe during straightening; adjusting the roller pressure affects the contact force and deformation between the pipe and the rollers; and adjusting the roller spacing affects the pipe's curvature and deformation uniformity. Through dynamic optimization using the reinforcement learning algorithm, the pipe straightener can adaptively adjust parameters under different working conditions to achieve optimal production, avoiding the inefficiencies and errors that can occur with traditional manual adjustments.

[0108] The specific steps of S2.2 are as follows:

[0109] S2.2.1: Calculate the preliminary parameters during the steel pipe straightening process using the ideal straightening stress and bending angle;

[0110] Specifically, this embodiment determines the ideal stress and bending angle of each segment by accurately calculating the stress of different sections of the steel pipe. These parameters provide a theoretical basis for subsequent adjustments to the working state of the straightening machine. For example, the bending angle of the steel pipe affects the contact force and degree of bending between the steel pipe and the straightening machine rollers, while the ideal straightening stress directly relates to the magnitude of the pressure applied by the rollers and the deformation rate of the steel pipe. The specific preliminary parameter calculation methods can be determined by those skilled in the art through numerous repeated experiments.

[0111] S2.2.2: Perform virtual simulation of the steel pipe straightening process based on the preliminary parameters to obtain the straightening effect;

[0112] Specifically, virtual simulation can simulate the actual stress and deformation process of steel pipes in a straightening machine, and predict the straightening effect by simulating different working parameters. Through dynamic simulation of the straightening process, the deformation state, stress distribution, and potential localized uneven deformation of different steel pipe segments can be visually observed, providing crucial information for actual operation. For example, simulation can reveal whether certain steel pipe segments experience excessive or insufficient stress during actual straightening, or whether there is excessive or insufficient deformation in certain areas. Through simulation, the system can identify potential straightening problems in advance and adjust the simulation model input based on preliminary parameters to ensure that the straightening effect in actual operation meets expectations. The specific simulation process can also be determined by those skilled in the art using professional simulation software.

[0113] S2.2.3: Based on the straightening effect, the straightening speed, roller pressure, and roller spacing of the steel pipe straightening machine are adjusted using a reward function to generate a straightening parameter set;

[0114] Specifically, the reward function can provide corresponding reward values ​​based on the straightening effect (such as deformation uniformity, surface quality, energy efficiency, etc.) during the steel pipe straightening process, while the reinforcement learning algorithm generates the optimal straightening parameter set by iteratively adjusting working parameters such as straightening speed, roller pressure, and roller spacing.

[0115] Furthermore, the reward function comprehensively considers the surface quality of the steel pipe, energy consumption, and straightening accuracy, and can automatically provide corresponding feedback values ​​based on the straightening effect. For example, if defects appear on the steel pipe surface or the energy efficiency does not meet expectations, the reward function will provide negative feedback for this result, thereby guiding the reinforcement learning algorithm to gradually optimize the working parameters of the straightening machine, ensuring that the straightening process of each segment of the steel pipe achieves the best results. This improves the efficiency and accuracy of the steel pipe straightening process, avoids the risk of excessive energy and equipment consumption, and ensures the continuous stability of the straightening process.

[0116] The specific steps for S3 are as follows:

[0117] S3.1: Construct a nonlinear material response model for the steel pipe under the stated temperature gradient field;

[0118] Specifically, in the actual straightening process, the temperature distribution, geometry, and material properties of the steel pipe vary, resulting in complex nonlinear characteristics in the deformation behavior and energy consumption of the steel pipe. Especially when the temperature gradient field is large, traditional linear models cannot accurately capture the influence of temperature on the yield strength, plastic deformation, and stress distribution of the steel pipe, and therefore cannot efficiently optimize the straightening parameters.

[0119] In this embodiment, a complex nonlinear material model (such as strain hardening and thermal expansion) is used to accurately describe the material response of the steel pipe during straightening, based on the steel pipe's material properties (e.g., elastic modulus, yield strength, hardening coefficient) and temperature gradients at different locations. The model considers the microstructural changes within the steel pipe under the influence of the temperature field, such as grain coarsening or phase transformations that may occur in localized high-temperature regions, leading to changes in stress distribution and material strength. Therefore, based on the nonlinear model, the deformation characteristics, yield behavior, and final energy efficiency of the steel pipe can be predicted more accurately, improving operational precision and energy efficiency optimization during the straightening process.

[0120] S3.2: Based on the aforementioned nonlinear material response model, calculate the thermal stress correction factor caused by the temperature gradient field for each segment of the steel pipe, taking into account the actual yield strength.

[0121] Specifically, in high-temperature or large-temperature-difference environments, temperature differences at different locations inside the steel pipe can lead to varying degrees of thermal stress in different areas. These thermal stresses significantly affect the deformation behavior of the steel pipe, thereby impacting the straightening quality. By introducing a thermal stress correction factor, the local stress differences in the steel pipe caused by the temperature gradient field can be effectively compensated, thus dynamically optimizing the energy consumption during the straightening process.

[0122] In this embodiment, the stress distribution of different steel pipe segments under a temperature gradient field is first accurately calculated based on a nonlinear material response model. Then, by considering the material hardening and thermal expansion effects caused by temperature changes, the stress state of each steel pipe segment is adjusted in real time. This avoids the energy waste or uneven straightening problems caused by neglecting thermal stress in traditional straightening processes, improves the stability and accuracy of the straightening process, and reduces surface defects and energy consumption of the steel pipe.

[0123] S3.3: Based on the thermal stress correction factor, the straightening parameter set is corrected to generate a corrected parameter set;

[0124] Specifically, the operating parameters are optimized in real time based on the constantly changing temperature and stress conditions during the steel pipe straightening process, thereby avoiding energy waste and low production efficiency caused by parameter mismatch in traditional straightening. Through this modified set of straightening parameters, the steel pipe straightening machine can more efficiently adapt to complex production environments, significantly reducing energy consumption and improving production efficiency while ensuring straightening quality.

[0125] Please refer to Figure 3, which is a schematic diagram of the nonlinear material response model construction process according to an embodiment of the present invention. The specific steps of S3.1 are as follows:

[0126] S3.1.1: Extract temperature fluctuation feature matrices at different spatial frequencies through wavelet multi-scale decomposition;

[0127] Specifically, the temperature distribution of steel pipes during actual straightening is usually complex, including temperature fluctuations at different spatial scales. These fluctuations may originate from temperature differences during the heating and cooling process of the steel pipe, or from changes in thermal stress caused by uneven stress in local areas during the straightening process.

[0128] In this embodiment, the temperature field signal during the steel pipe straightening process is decomposed into different frequency components, thereby capturing the influence of temperature fluctuations on the steel pipe at both macroscopic and microscopic scales. A temperature fluctuation feature matrix is ​​generated to identify the local temperature changes and spatial frequency characteristics of different parts of the steel pipe during the straightening process. This is particularly useful when dealing with complex temperature fields, where traditional methods often fail to effectively capture these complex temperature fluctuations. Wavelet multi-scale decomposition technology, through multi-scale analysis, enables accurate extraction of temperature fluctuations at different spatial scales, thus providing detailed temperature feature data for subsequent nonlinear material response modeling and stress correction.

[0129] S3.1.2: Input the temperature fluctuation feature matrix into the preset cyclic plasticity model and output the piecewise differentiated thermal stress relationship, wherein the cyclic plasticity model includes a temperature-dependent hardening function and a dynamic recovery term;

[0130] Specifically, during the straightening process, steel pipes undergo multiple plastic deformations and temperature fluctuations. Traditional stress-strain relationship models often fail to consider the impact of temperature field changes on the actual plastic deformation behavior of steel pipes. However, this embodiment achieves more accurate thermal stress simulation by introducing temperature-dependent hardening functions and dynamic recovery terms.

[0131] In this embodiment, a temperature-dependent hardening function is used to describe the hardening behavior of materials under different temperature conditions. The yield strength of the steel pipe changes with temperature, especially at high temperatures, where its hardening capacity and plastic deformation characteristics change significantly. This function dynamically adjusts the hardening characteristics based on the specific material of the steel pipe, the temperature gradient, and the historical deformation accumulation, thereby providing a hardening model that conforms to the effects of temperature.

[0132] In this embodiment, the dynamic recovery term is used to simulate the microstructural changes that occur in the steel pipe under high-temperature conditions, such as grain coarsening and phase transformation. These microstructural changes directly affect the deformation capacity of the steel pipe and the hardening characteristics of the material. The dynamic recovery term adjusts the recovery capacity of the steel pipe according to the actual working conditions, thereby accurately reflecting the elastic recovery and plastic deformation behavior of the material.

[0133] S3.1.3: Identify the local austenitization phenomenon in the thermal stress relationship, calculate the martensitic transformation volume fraction of the local austenitization phenomenon, and correct the thermal stress relationship based on the martensitic transformation volume fraction;

[0134] Specifically, during the straightening process of steel pipes, especially when the pipes are subjected to high temperatures, austenitization may occur. Austenitization is the process by which steel transforms from ferrite to austenite at high temperatures. When the steel pipe cools, the austenite may transform into martensite, which significantly alters the mechanical properties of the steel pipe, particularly its yield strength and hardening characteristics. This makes it impossible to accurately predict the thermal stress and deformation behavior of the material during actual straightening.

[0135] Specifically, by dynamically monitoring the temperature field and stress state in different regions of the steel pipe, regions where austenitization may occur are identified, and the proportion of martensite in these regions is calculated. This provides a quantitative basis for subsequent correction of the thermal stress relationship, ensuring that the thermal stress correction of the steel pipe during actual straightening conforms to the actual deformation capacity of the material.

[0136] S3.1.4: Generate a nonlinear material response model based on the corrected thermal stress relationship.

[0137] The specific steps of S3.1.2 are as follows:

[0138] S3.1.2.1: Perform time-frequency joint analysis on the temperature fluctuation feature matrix to generate thermal shock events; wherein the time-frequency joint analysis includes:

[0139] In this embodiment, the introduction of time-frequency joint analysis is to address the complexity of temperature changes in the steel pipe during straightening. Traditional temperature analysis methods typically use simple time or frequency domain analysis, but this cannot effectively handle rapid temperature changes in the steel pipe, especially at high frequencies, where temperature fluctuations have a significant impact on the deformation behavior and thermal stress of the steel pipe.

[0140] The time-frequency joint analysis includes:

[0141] The wavelet modulus maxima detection algorithm is used to locate abrupt changes in the high-frequency components where the rate of temperature change exceeds a preset threshold, and a set of spatiotemporal coordinates of thermal shock is generated.

[0142] Specifically, wavelet transform is used to convert the temperature fluctuation signal into multiple frequency components to analyze the temperature fluctuations in different parts of the steel pipe. These high-frequency components represent rapid temperature changes in the steel pipe. During straightening, parts with faster temperature changes often generate higher thermal stress and therefore require special attention. Using a wavelet modulus maxima detection algorithm, abrupt changes where the rate of temperature change exceeds a preset threshold can be accurately identified. These abrupt changes typically correspond to sudden temperature rises or localized high-temperature phenomena in the steel pipe, forming thermal shock events.

[0143] Based on the thermal shock spatiotemporal coordinate set and combined with the thermal fatigue characteristics of the steel pipe material, the cumulative thermal shock intensity index of each abrupt change point is calculated to generate a thermal shock event.

[0144] Specifically, during the straightening process, steel pipes undergo repeated heating and cooling, which leads to the gradual accumulation of thermal stress inside the material, resulting in thermal fatigue.

[0145] In this embodiment, the spatiotemporal coordinate set of each thermal shock event provides temperature change data at different locations and time points of the steel pipe. This data can help calculate the intensity and cumulative effect of thermal shock at that location.

[0146] Furthermore, the thermal fatigue characteristics of steel pipes refer to the gradual accumulation of fatigue damage in materials under repeated thermal stress, which may lead to crack formation or structural failure. By combining temperature abrupt events with the thermal fatigue characteristics of steel pipes, the cumulative thermal shock intensity index at each abrupt event point can be calculated. This index represents the degree of damage to the steel pipe caused by temperature changes at a specific time and location. This index considers the superposition effect of multiple thermal shock events and can effectively simulate the damage accumulation of materials under long-term temperature fluctuations. The cumulative thermal shock intensity index is compared with a preset index threshold; if it exceeds the threshold, the coordinate is marked as a thermal shock event.

[0147] S3.1.2.2: Based on the thermal shock event, the temperature-dependent hardening function of the cyclic plasticity model is spatially adaptively adjusted;

[0148] Specifically, traditional hardening functions typically assume that the hardening ability of a material varies uniformly throughout the process. However, due to differences in the temperature field and stress state of steel pipes in different regions, their hardening characteristics also exhibit significant spatial variations.

[0149] In this embodiment, the hardening function for each segment of the steel pipe is adjusted based on the thermal shock strength index of that segment. Since the material hardness of the steel pipe may change significantly in areas of abrupt temperature changes or high thermal shock intensity, the correction of the temperature-dependent hardening function ensures that the hardening characteristics of the steel pipe dynamically adapt to temperature changes in these areas. For example, in areas with strong thermal shock, the hardening capacity of the steel pipe may decrease due to high temperatures; therefore, the hardening function needs to be adjusted accordingly to reflect this change.

[0150] S3.1.2.3: Based on non-thermal shock events, perform historical coupling adjustments on the dynamic recovery term of the cyclic plasticity model;

[0151] Specifically, in addition to thermal shock events, steel pipes may also experience non-thermal shock events during the straightening process, where the temperature changes relatively gradually, but these events still affect the deformation and material response of the steel pipes.

[0152] In this embodiment, the dynamic recovery term reflects the microstructural recovery capability of the steel pipe under thermal stress, including phenomena such as grain recovery and material softening. Non-thermal shock events may cause the material to remain in a state of stress accumulation for a long time, thus affecting the recovery process of the steel pipe. By coupling historical thermal stress and material deformation information with the dynamic recovery term, the recovery term can be adjusted in real time, ensuring that the model can accurately describe the stress and deformation process of the steel pipe under continuous temperature changes. This coupled adjustment can effectively avoid the problem of insufficient response to non-thermal shock events in traditional models, providing more accurate material response predictions.

[0153] S3.1.2.4: Output the thermal stress relationship based on the adjusted temperature-dependent hardening function and dynamic recovery term.

[0154] The specific steps of S3.2 are as follows:

[0155] S3.2.1: Discretize the nonlinear material response model using the finite volume method to construct the spatiotemporal evolution heat conduction equation;

[0156] Specifically, the thermal stress distribution and temperature changes experienced by steel pipes during straightening have significant spatial and temporal dependencies. Therefore, traditional continuity equations often cannot effectively describe such complex spatiotemporal variations. The Finite Volume Method (FVM), as a mature numerical calculation method, can decompose the entire heat conduction region into multiple small control volumes and numerically solve for the temperature distribution within each small volume, thereby obtaining accurate temperature field and heat flux distribution.

[0157] In this embodiment, the finite volume method applies the integral form of the heat conduction equation to each control volume, considering the temperature and heat flow within each control volume to obtain the local thermal conductivity and calculate the heat transfer within each control volume. Since the material response of the steel pipe is nonlinear, especially under large temperature variations, the material properties of the steel pipe will change. Therefore, a nonlinear material response model must be used in the discretization process to handle the heat conduction behavior of the steel pipe under different temperatures and stresses. The thermal conductivity and yield strength of the material are dynamically corrected with temperature changes, which enables the finite volume method to accurately calculate the temperature changes and heat flow transfer in different regions inside the steel pipe during the straightening process.

[0158] S3.2.2: Based on the heat conduction equation, calculate the dynamic correction relationship between the temperature gradient field and the actual yield strength of each segment of the steel pipe;

[0159] Specifically, the yield strength of steel pipes is not only affected by material properties but also changes significantly with temperature. Traditional methods for calculating thermal stress typically assume that the yield strength is constant or linearly variable. However, in actual production processes, steel pipes often experience temperature fluctuations in localized areas during straightening, leading to nonlinear changes in the material's hardening behavior. Therefore, establishing a dynamic correction relationship between temperature and yield strength is crucial to accurately reflect the true stress state of steel pipes under different temperature conditions.

[0160] In this embodiment, some sections of the steel pipe may be in a higher temperature region during straightening, leading to a decrease in the material's yield strength, while other regions may be in a lower temperature state with a relatively higher yield strength. By combining the temperature distribution and yield strength variation law of the steel pipe, the nonlinear relationship between temperature and yield strength is dynamically calculated. Based on the temperature field obtained by the finite volume method, a corresponding thermodynamic model is used to simulate the temperature-dependent yield strength variation of the steel pipe material and correlate it with the local temperature field of each section.

[0161] S3.2.3: Calculate the thermal stress correction factor for each segment of the steel pipe based on the aforementioned dynamic correction relationship;

[0162] Specifically, the thermal stress during the steel pipe straightening process is mainly determined by the temperature gradient field and the material's yield strength. Due to temperature fluctuations and material strength differences in different regions, the thermal stress correction factor for different segments during the steel pipe straightening process should be different to ensure that the straightening process of each segment accurately reflects its material and thermal stress characteristics.

[0163] In this embodiment, the thermal stress correction factor is quantitatively calculated based on the temperature field and corresponding yield strength of each steel pipe segment. The thermal stress correction coefficient is determined by comparing the difference between the actual yield strength and the theoretical yield strength. For areas with higher temperatures, the correction factor is usually larger, indicating that the thermal stress in that area is relatively large, while for areas with lower temperatures, the correction factor is smaller, indicating that the thermal stress in that area is small. This ensures that each segment of the steel pipe is straightened under optimal energy efficiency conditions. It also ensures that the steel pipe can effectively eliminate errors caused by temperature inhomogeneity and changes in material strength during the straightening process, so that the thermal stress of each segment of the steel pipe can be accurately corrected.

[0164] The specific steps of S3.3 are as follows:

[0165] S3.3.1: Divide the steel pipe straightening area into a heat-sensitive area and a low-temperature hardening area;

[0166] In this embodiment, the division of the steel pipe straightening area is based on the thermal stress correction factor. During the straightening process, the thermal stress generated by the steel pipe due to the influence of different temperature gradients also exhibits spatial distribution differences. Therefore, in order to more accurately adjust the working parameters during the straightening process, the steel pipe straightening area is divided according to the thermal stress correction factor, so as to carry out refined management of the material response characteristics of different areas.

[0167] Specifically, this correction factor quantifies the effect of temperature on the yield strength, plastic deformation, and material hardening of steel pipes. Generally, the thermal stress correction factor is larger in regions with higher temperatures or greater temperature variations, indicating a more significant thermal stress effect in these areas; conversely, the thermal stress correction factor is smaller in regions with lower or stable temperatures, indicating a weaker thermal stress effect. The calculated thermal stress correction factor effectively divides the steel pipe straightening area into heat-sensitive regions and low-temperature hardening regions.

[0168] Furthermore, heat-sensitive areas typically correspond to regions with higher temperatures and more drastic changes in thermal stress. In these areas, steel pipes may experience stress relaxation, phase transformation, or reduced hardening properties due to the high temperatures, leading to changes in the material's yield strength and deformation capacity. To ensure that the straightening process in these areas does not result in excessive deformation or failure, special treatment is required for these regions.

[0169] Furthermore, the low-temperature hardening region is typically located in areas of lower temperature, where the steel pipe material exhibits stronger hardening ability, resulting in higher yield strength and smaller plastic deformation. Therefore, the thermal stress effect in these regions is relatively small, but proper control is still crucial to avoid surface defects or uneven deformation of the steel pipe due to over-hardening.

[0170] S3.3.2: Assign correction weights to the two regions based on the area difference between the heat-sensitive region and the low-temperature hardening region;

[0171] Specifically, the temperature gradient field of each region is analyzed, and the local temperature gradient of each segment of the steel pipe (i.e., the rate of temperature change per unit length) is calculated.

[0172] Furthermore, the low-temperature hardening region, due to its strong hardening effect, requires a higher straightening force, while the heat-sensitive region at high temperatures may exhibit a softer behavior. Therefore, when calculating the correction weights, in addition to considering the difference in region area, it is also necessary to analyze the rate of change of the material hardening curve in each region, especially the difference in hardening behavior between the high and low temperature ranges.

[0173] Furthermore, based on the areas of the heat-sensitive region and the low-temperature hardening region, combined with their local temperature gradient and the rate of change of the hardening curve, the weighted area difference is calculated.

[0174] Furthermore, the allocation of correction weights is based on the calculated weighted area difference. In this process, the straightening area of ​​the steel pipe will be dynamically adjusted according to this weight ratio during the generation of the correction parameter set. Specifically, the correction weight of the heat-sensitive area will be appropriately enhanced based on a larger area and a higher temperature gradient, while the low-temperature hardening area will be adjusted relatively less based on a smaller area and a stronger hardening effect.

[0175] S3.3.3: Generate a set of correction parameters based on the corrected weights;

[0176] Specifically, the main operating parameters of a steel pipe straightening machine include straightening speed, roller pressure, and roller spacing. Straightening speed refers to the speed at which the steel pipe passes through the straightening machine, which directly affects the deformation rate of the steel pipe. Roller pressure is the compressive force acting on the steel pipe, which determines the degree of bending of the steel pipe. Roller spacing refers to the distance between the rollers, which directly affects the deformation range and bending angle of the steel pipe.

[0177] Furthermore, based on the overall correction coefficients for the heat-sensitive region and the low-temperature hardening region, the two correction weights are weighted and averaged to calculate the comprehensive correction weight.

[0178] Furthermore, the straightening speed, roller pressure, and roller spacing are adjusted sequentially based on the comprehensive correction weights.

[0179] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. An intelligent factory equipment energy efficiency optimization system, applied to a steel pipe straightening machine, wherein the steel pipe straightening machine is equipped with a detection device, characterized in that, The equipment energy efficiency optimization system includes a data acquisition module, a data processing module, and a data correction module, wherein: the data acquisition module is used to acquire wall thickness distribution data, local residual stress, and temperature gradient field during the straightening process of the steel pipe through the detection device; the data processing module is used to calculate the actual yield strength and theoretical straightening energy threshold of each segment of the steel pipe based on the output of the data acquisition module, and generate a straightening parameter set for the steel pipe straightening machine based on the actual yield strength and theoretical straightening energy threshold; the data correction module is used to correct the straightening parameter set based on the temperature gradient field; The data correction module includes: a temperature field modeling unit, used to construct a nonlinear material response model of the steel pipe under temperature gradient field conditions, configured to: extract temperature fluctuation feature matrices of different spatial frequencies through wavelet multi-scale decomposition; input the temperature fluctuation feature matrices into a preset cyclic plasticity model, outputting a piecewise differentiated thermal stress relationship, wherein the cyclic plasticity model includes a temperature-dependent hardening function and a dynamic recovery term; identify local austenitization phenomena in the thermal stress relationship, calculate the martensitic transformation volume fraction of the local austenitization phenomenon, and adjust the thermal stress relationship based on the martensitic transformation volume fraction. The process involves several steps: First, a correction is performed. Based on the corrected thermal stress relationship, a nonlinear material response model is generated. A correction factor calculation unit is used to calculate the thermal stress correction factor caused by the temperature gradient field, based on the actual yield strength of each segment of the steel pipe and the nonlinear material response model. This unit is configured to: discretize the nonlinear material response model using the finite volume method to construct a spatiotemporally evolving heat conduction equation; calculate the dynamic correction relationship between the temperature gradient field and the actual yield strength of each segment of the steel pipe based on the heat conduction equation; calculate the thermal stress correction factor for each segment of the steel pipe based on the dynamic correction relationship; and a correction parameter calculation unit is used to... According to the thermal stress correction factor, the straightening parameter set is corrected to generate a corrected parameter set, configured as follows: the steel pipe straightening area is divided into a heat-sensitive area and a low-temperature hardening area; based on the area difference between the heat-sensitive area and the low-temperature hardening area, correction weights are assigned to the two areas, including: analyzing the temperature gradient field of each area and calculating the local temperature gradient of each segment of the steel pipe; calculating the weighted area difference based on the area of ​​the heat-sensitive area and the low-temperature hardening area, combined with the change rate of their local temperature gradient and hardening curve; calculating the correction weight based on the weighted area difference; and generating the corrected parameter set based on the correction weights.

2. The intelligent factory equipment energy efficiency optimization system according to claim 1, characterized in that, The data processing module includes: a plasticity calculation unit for calculating the actual yield strength of each segment of the steel pipe using the yield criterion and stress-strain relationship; an energy threshold calculation unit for calculating the theoretical straightening energy threshold based on the output of the plasticity calculation unit using the hardening law; and a parameter generation unit for generating a straightening parameter set for the steel pipe straightening machine based on the calculated actual yield strength and the theoretical straightening energy threshold.

3. The intelligent factory equipment energy efficiency optimization system according to claim 2, characterized in that, The parameter generation unit includes: determining the ideal straightening stress and bending angle of each segment during the steel pipe straightening process; and optimizing the actual working parameter set of the steel pipe straightening machine through a reinforcement learning algorithm based on the ideal straightening stress and bending angle to generate a straightening parameter set, wherein the straightening parameter set includes the straightening speed, roller pressure, and roller spacing of the steel pipe straightening machine.

4. The intelligent factory equipment energy efficiency optimization system according to claim 3, characterized in that, The optimization of the actual working parameter set of the steel pipe straightening machine using a reinforcement learning algorithm includes: calculating preliminary parameters during the steel pipe straightening process using the ideal straightening stress and bending angle; performing virtual simulation of the steel pipe straightening process based on the preliminary parameters to obtain the straightening effect; and adjusting the straightening speed, roller pressure, and roller spacing of the steel pipe straightening machine using a reward function based on the straightening effect to generate a straightening parameter set.

5. The intelligent factory equipment energy efficiency optimization system according to claim 1, characterized in that, The temperature fluctuation feature matrix is ​​input into a preset cyclic plasticity model, and piecewise differentiated thermal stress relationships are output, including: performing time-frequency joint analysis on the temperature fluctuation feature matrix to generate thermal shock events; spatially adaptively adjusting the temperature-dependent hardening function of the cyclic plasticity model based on the thermal shock events; historically coupling adjusting the dynamic recovery term of the cyclic plasticity model based on non-thermal shock events; and outputting thermal stress relationships based on the adjusted temperature-dependent hardening function and dynamic recovery term.

6. The intelligent factory equipment energy efficiency optimization system according to claim 5, characterized in that, The time-frequency joint analysis includes: using a wavelet modulus maxima detection algorithm to locate abrupt changes in the temperature fluctuation feature matrix where the rate of temperature change exceeds a preset threshold, and generating a thermal shock spatiotemporal coordinate set; based on the thermal shock spatiotemporal coordinate set and combined with the thermal fatigue characteristics of the steel pipe material, calculating the cumulative thermal shock intensity index for each abrupt change point, and generating a thermal shock event.

Images