A method and device for controlling the water cooling of a hot rolling mill

Abstract

The application provides a hot rolling mill water cooling control method and device, and relates to the field of water cooling control. The method comprises the following steps: in response to a water cooling control operation of a target hot rolling mill, obtaining a cooling water flow adjustment parameter; performing feature extraction on the cooling water flow adjustment parameter, and obtaining a target feature parameter; taking the target feature parameter as input, outputting a target cooling water flow corresponding to the target hot rolling mill through a cooling water flow control model; and performing a water cooling control operation on the target hot rolling mill through an electric proportional valve according to the target cooling water flow. The application solves the problem that when a hand valve is used for controlling the cooling water pipeline of a hydraulic station, the cooling capacity cannot be accurately controlled, resulting in energy waste.

Description

Technical Field

[0001] This application relates to the field of water cooling control, and more particularly to a water cooling control method and apparatus for a hot rolling mill. Background Technology

[0002] Large motors and most hydraulic stations in copper and copper alloy processing enterprises typically use water cooling. Heat is carried away by circulating water to achieve cooling. The circulating water is supplied by the processing enterprise's pump station. After heat exchange, the circulating water is cooled by a cooling tower before returning to the pump station. The pump station's circulating water is supplied by multiple pumps. If the circulating water consumption increases, the pump speed is increased or a standby pump is activated; conversely, the speed is reduced or the pumps are shut down.

[0003] Many large motors and most hydraulic stations use manual valves to control the cooling water pipelines. In particular, during hot rolling mill production, cooling is controlled by manual valves. When the manual valves are fully open during production, the flow rate is too high, exceeding the cooling needs of the hydraulic station and main motor. At the same time, hot rolling equipment production is not continuous, with auxiliary times such as heat preservation, unloading, and coiling. Therefore, using manual valves to control the cooling water cannot accurately control the cooling amount, resulting in energy waste.

[0004] Therefore, there is an urgent need for a water-cooling control method and device for hot rolling mills. Summary of the Invention

[0005] This application provides a water cooling control method and device for hot rolling mills, which solves the problem of energy waste caused by the inability to accurately control the cooling amount when the cooling water pipeline of the hydraulic station is controlled by a manual valve.

[0006] The first aspect of this application provides a water-cooling control method for a hot rolling mill. The method includes: in response to a water-cooling control operation for a target hot rolling mill, acquiring cooling water flow rate adjustment parameters, including main motor load parameters, main motor temperature parameters, and main motor duty cycle parameters; extracting features from the cooling water flow rate adjustment parameters and acquiring target feature parameters; using the target feature parameters as input, outputting the target cooling water flow rate corresponding to the target hot rolling mill through a cooling water flow rate control model; and performing water-cooling control operation on the target hot rolling mill through an electric proportional valve according to the target cooling water flow rate.

[0007] Optionally, the target feature parameters include fused derived features, fused temporal features, and fused cross features. Feature extraction is performed on the cooling water flow regulation parameters to obtain the target feature parameters. Specifically, this includes: obtaining motor load parameters, temperature change rate parameters, and vibration intensity parameters from the cooling water flow regulation parameters; constructing fused derived features from the target feature parameters based on the motor load parameters, temperature change rate parameters, and vibration intensity parameters; obtaining historical cooling water flow parameters, historical temperature parameters, and historical power parameters from the cooling water flow regulation parameters; constructing fused temporal features from the target feature parameters based on the historical cooling water flow parameters, historical temperature parameters, and historical power parameters; obtaining cross-term parameters of temperature and load, and cross-term parameters of speed and ambient temperature from the cooling water flow regulation parameters; constructing fused cross features from the target feature parameters based on the cross-term parameters of temperature and load, and cross-term parameters of speed and ambient temperature; fusing the fused derived features, fused temporal features, and fused cross features, and using the feature parameters after feature parameter fusion as the target feature parameters.

[0008] Optionally, based on motor load parameters, temperature change rate parameters, and vibration intensity parameters, fused derived features are constructed from the target feature parameters. Specifically, this includes using a nonlinear mapping function to perform a first fusion operation on the cooling water flow rate adjustment parameters using the following formula, and obtaining the fused derived features:

[0009] f d =α1log(P motor +∈)+α2*exp(ΔT motor )+α3*A vibration 2 ;

[0010] Among them, f d To integrate derived features, P motor Here, α1 represents the weighting coefficient corresponding to the motor load parameter, and ΔT represents the motor load parameter. motor Let A be the temperature change rate parameter, α2 be the weighting coefficient corresponding to the temperature change rate parameter, and A be the weighting coefficient corresponding to the temperature change rate parameter. vibration Here, α3 is the weighting coefficient corresponding to the vibration intensity parameter, and ∈ is the adjustment factor used to avoid zero when taking the logarithm.

[0011] Optionally, based on historical cooling water flow parameters, historical temperature parameters, and historical power parameters, a fused time-series feature is constructed from the target feature parameters. Specifically, this includes: using weighted sliding window processing, performing a second fusion operation on the cooling water flow adjustment parameters using the following formula, and obtaining the fused time-series feature:

[0012]

[0013] Among them, f t To integrate temporal features, ti represents a historical moment, and Q... history (ti) represents the historical cooling water flow rate parameter, T motor (ti) represents the historical temperature parameter, P motor (ti) n Historical power parameters, β1 is the weight corresponding to the historical cooling water flow rate parameter, β2 is the weight corresponding to the historical temperature parameter, and β3 is the weight corresponding to the historical power parameter.

[0014] Optionally, based on the cross-term parameters of temperature and load, and the cross-term parameters of speed and ambient temperature, a fused cross-feature in the target feature parameters is constructed. Specifically, this includes sampling a high-order cross-term polynomial combination, performing a third fusion operation on the cooling water flow rate regulation parameters using the following formula, and obtaining the fused cross-feature:

[0015] f mix =γ1*(T motor ·P motor )+γ2*(N motor ·T ambient )+γ3*(T motor 2 ·

[0016] P motor );

[0017] Among them, f mix To integrate cross features, N motor The main motor speed parameter is represented by ·, which indicates the element-wise operation between various cooling water flow adjustment parameters. γ1 is the weight corresponding to the cross-term parameter of temperature and load, γ2 is the weight corresponding to the cross-term parameter of speed and ambient temperature, and γ3 is the weight corresponding to the secondary cross-term of temperature and load.

[0018] Optionally, before using the target feature parameters as input and outputting the target cooling water flow rate corresponding to the target hot rolling mill through the cooling water flow control model, it is necessary to construct a cooling water flow control model, which specifically includes: obtaining historical cooling water flow adjustment parameters, including historical main motor load parameters, historical main motor temperature parameters, and historical main motor working cycle parameters; and constructing a cooling water flow control model based on the historical cooling water flow adjustment parameters.

[0019] Optionally, the target cooling water flow rate corresponding to the target hot rolling mill is output through the cooling water flow rate control model, specifically including: calculating the target cooling water flow rate according to the following formula:

[0020]

[0021] Among them, Q target Let d0 be the target cooling water flow rate, d0 be the bias term, X be the set of target characteristic parameters, and f be the value of f. i (X) is the output corresponding to the i-th target feature parameter, F i For the i-th postfix term, the postfix term includes higher-order cross terms and time-series information processing terms. The weight parameter is the one corresponding to the i-th post-item.

[0022] A second aspect of this application provides a water-cooling control device for a hot rolling mill, the device comprising an acquisition module and a processing module, wherein...

[0023] The acquisition module is used to acquire cooling water flow rate adjustment parameters in response to water cooling control operations for the target hot rolling mill. The cooling water flow rate adjustment parameters include main motor load parameters, main motor temperature parameters, and main motor working cycle parameters.

[0024] The processing module is used to extract features from the cooling water flow rate adjustment parameters and obtain target feature parameters; taking the target feature parameters as input, it outputs the target cooling water flow rate corresponding to the target hot rolling mill through the cooling water flow rate control model; and according to the target cooling water flow rate, it performs water cooling control operation on the target hot rolling mill through an electric proportional valve.

[0025] A third aspect of this application provides an electronic device including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform any of the methods described above.

[0026] A fourth aspect of this application provides a computer-readable storage medium storing a computer program, which is executed by a processor using the method described in any of the foregoing descriptions.

[0027] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0028] 1. Obtain cooling water flow rate adjustment parameters, extract features from the cooling water flow rate adjustment parameters, and obtain target feature parameters. Then, use the target feature parameters as input, and output the target cooling water flow rate corresponding to the target hot rolling mill through the cooling water flow rate control model. Based on the target cooling water flow rate, perform the water cooling control operation on the target hot rolling mill through an electric proportional valve, thereby saving circulating water consumption, reducing energy consumption, achieving green development, and effectively reducing the production energy consumption of copper processing enterprises.

[0029] 2. By labeling and classifying the target feature parameters into fused derived features, fused temporal features, and fused cross features, and extracting features from the cooling water flow regulation parameters, and refining the extracted feature parameters according to the classification results, we can more accurately capture the interrelationships and mechanisms of action among various features, reveal the interaction between multiple parameters, and provide strong feature data support for subsequent model processing.

[0030] 3. By acquiring various historical cooling water flow regulation parameters, such as historical main motor load parameters, historical main motor temperature parameters, and historical main motor working cycle parameters, we can fully understand the changes in the cooling demand of the motor under different operating conditions. Furthermore, by combining these multi-dimensional historical data to construct a cooling water flow control model, the prediction results of the model become more accurate. Attached Figure Description

[0031] Figure 1 This is a schematic flowchart of a water-cooling control method for a hot rolling mill provided in an embodiment of this application;

[0032] Figure 2 This is a schematic diagram of a hot rolling mill water cooling control device provided in an embodiment of this application;

[0033] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0034] Explanation of reference numerals in the attached figures: 21. Acquisition module; 22. Processing module; 301. Processor; 302. Communication bus; 303. User interface; 304. Network interface; 305. Memory. Detailed Implementation

[0035] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0036] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to and includes any or all possible combinations of one or more of the listed items.

[0037] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0038] To enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0039] Please refer to Figure 1 The diagram shows a flow chart of a hot rolling mill water cooling control method provided in the embodiment of this application. The flow chart mainly includes the following steps: S101 to S104.

[0040] Step S101: In response to the water cooling control operation for the target hot rolling mill, obtain the cooling water flow rate adjustment parameters, which include the main motor load parameters, the main motor temperature parameters, and the main motor working cycle parameters.

[0041] Specifically, by installing various types of sensors, the water cooling control of the target hot rolling mill is monitored in real time. Cooling water flow rate adjustment parameters are acquired through different types of sensors, including but not limited to: main motor load parameters, main motor temperature parameters, and main motor duty cycle parameters. The acquired cooling water flow rate adjustment parameters need to undergo certain preprocessing, such as filtering, noise reduction, and calibration, to ensure their accuracy and effectiveness. For example, the main motor load parameters can be calculated using current or power measurement equipment, while the main motor temperature parameters can be directly measured using temperature sensors.

[0042] Step S102: Extract features from the cooling water flow rate adjustment parameters and obtain the target feature parameters.

[0043] Specifically, target characteristic parameters are obtained by adjusting the acquired cooling water flow rate parameters. The core of this process is to transform the original cooling water flow rate adjustment parameters into meaningful features for subsequent input into the cooling water flow rate control model.

[0044] In one possible implementation, step S102 further includes: obtaining the motor load parameters, temperature change rate parameters, and vibration intensity parameters from the cooling water flow rate adjustment parameters;

[0045] Based on motor load parameters, temperature change rate parameters, and vibration intensity parameters, fused derived features are constructed in the target feature parameters; historical cooling water flow rate parameters, historical temperature parameters, and historical power parameters are obtained from the cooling water flow rate regulation parameters; based on the historical cooling water flow rate parameters, historical temperature parameters, and historical power parameters, fused temporal features are constructed in the target feature parameters; the cross-term parameters of temperature and load, and the cross-term parameters of speed and ambient temperature are obtained from the cooling water flow rate regulation parameters; based on the cross-term parameters of temperature and load, and the cross-term parameters of speed and ambient temperature, fused cross-features are constructed in the target feature parameters; feature parameters are fused from the fused derived features, fused temporal features, and fused cross-features, and the feature parameters after feature parameter fusion are used as the target feature parameters.

[0046] Specifically, firstly, the system acquires key indicators from the cooling water flow regulation parameters, such as motor load parameters, temperature change rate parameters, and vibration intensity parameters. These parameters reflect the basic state and abnormal characteristics of the motor during operation, providing fundamental information for cooling water flow regulation. Next, by processing these parameters, fused derived features from the target feature parameters are constructed. This includes synthesizing the motor load parameters, temperature change rate parameters, and vibration intensity parameters. This step is as follows: Using a nonlinear mapping function, the cooling water flow regulation parameters are fused using the following formula, and the fused derived features are obtained:

[0047] f d =α1log(P motor +∈)+α2*exp(ΔT motor )+α3*A vibration 2 ;

[0048] Among them, f d To integrate derived features, P motor Here, α1 represents the weighting coefficient corresponding to the motor load parameter, and ΔT represents the motor load parameter. motor Let A be the temperature change rate parameter, α2 be the weighting coefficient corresponding to the temperature change rate parameter, and A be the weighting coefficient corresponding to the temperature change rate parameter. vibration Here, α3 is the weighting coefficient corresponding to the vibration intensity parameter, ∈ is the adjustment factor used to avoid zero when taking the logarithm, and f dThis is used to reveal the complex relationship between motor operating status and cooling demand. Simultaneously, historical data from the cooling water flow rate regulation parameters is acquired, including historical cooling water flow rate parameters, historical temperature parameters, and historical power parameters. This historical data reflects the performance changes of the motor under different operating cycles. Using this historical data, the system can construct fused timing characteristics. The process steps are as follows: A weighted sliding window processing method is used to perform a second fusion operation on the cooling water flow rate regulation parameters using the following formula, and the fused timing characteristics are obtained:

[0049]

[0050] Among them, f t To integrate temporal features, ti represents a historical moment, and Q... history (ti) represents the historical cooling water flow rate parameter, T motor (ti) represents the historical temperature parameter, P motor (ti) n Historical power parameters, where β1 is the weight corresponding to the historical cooling water flow rate parameter, β2 is the weight corresponding to the historical temperature parameter, and β3 is the weight corresponding to the historical power parameter. t This is used to capture the trend of cooling water flow rate changes over time. Furthermore, cross-term features are extracted from the cooling water flow rate regulation parameters, including cross-term parameters of temperature and load, and cross-term parameters of speed and ambient temperature. These cross-term features reveal the interactions between several key parameters. The process involves the following steps: sampling high-order cross-term polynomial combinations, performing a third fusion operation on the cooling water flow rate regulation parameters using the following formula, and obtaining the fused cross-term features:

[0051] f mix =γ1*(T motor ·P motor )+γ2*(N motor ·T ambient )+γ3*(T motor 2 ·

[0052] P motor );

[0053] Among them, f mix To integrate cross features, N motor The main motor speed parameter, · indicates the element-wise operation between various cooling water flow adjustment parameters, γ1 is the weight corresponding to the cross-term parameter of temperature and load, γ2 is the weight corresponding to the cross-term parameter of speed and ambient temperature, γ3 is the weight corresponding to the secondary cross-term parameter of temperature and load, f mixThis provides more detailed input information for regulating cooling water flow. Finally, the derived features, temporal features, and cross-features are further fused using methods such as weighted averaging and nonlinear mapping. These feature parameters are then integrated into a comprehensive target feature parameter, which serves as the input to the subsequent cooling water flow control model. This fused target feature parameter comprehensively reflects the motor's load state, temperature changes, temporal variations, and interactions between parameters, thus providing a precise basis for optimizing cooling water flow regulation.

[0054] Step S103: Using the target feature parameter features as input, the target cooling water flow rate corresponding to the target hot rolling mill is output through the cooling water flow rate control model.

[0055] Specifically, the target feature parameters extracted and fused in step S102 are used as input to the cooling water flow control model to output the target cooling water flow rate corresponding to the target hot rolling mill. In essence, the cooling water flow control model accurately predicts and adjusts the cooling requirements of the hot rolling mill based on these target feature parameters. These feature parameters include motor load, temperature changes, historical time-series data, and the cross-influence between parameters, comprehensively reflecting the current operating status of the equipment and its cooling requirements. At the model's input end, the target feature parameters undergo a series of calculations and processing. Based on the different input feature parameters, the model uses a pre-trained algorithm to optimize the output cooling water flow rate, ensuring it adapts to the current load, temperature, and other operating conditions of the target hot rolling mill.

[0056] In one possible implementation, step S103 further includes: before taking the target feature parameter as input and outputting the target cooling water flow rate corresponding to the target hot rolling mill through the cooling water flow rate control model, it is necessary to construct a cooling water flow rate control model, specifically including: obtaining historical cooling water flow rate adjustment parameters, which include historical main motor load parameters, historical main motor temperature parameters, and historical main motor working cycle parameters; and constructing a cooling water flow rate control model based on the historical cooling water flow rate adjustment parameters.

[0057] Specifically, the construction process begins with acquiring historical cooling water flow regulation parameters, including historical main motor load parameters, historical main motor temperature parameters, and historical main motor duty cycle parameters. Collecting this historical data reveals patterns in motor load changes, temperature fluctuations, and duty cycles over different time periods, providing a foundation for subsequent modeling. Next, based on these historical cooling water flow regulation parameters, a cooling water flow control model is constructed using data analysis and modeling techniques. During the construction process, the model's structure and parameters are optimized by learning patterns and relationships from historical data, enabling it to accurately predict and regulate cooling water flow. This process may involve a training phase, where the model self-adjusts based on the correlation between changes in historical parameters and actual cooling demands to improve its predictive accuracy and response efficiency. Finally, the constructed and trained cooling water flow control model can calculate and output the target cooling water flow required by the target hot rolling mill in real time based on new input characteristics.

[0058] In one possible implementation, step S103 further includes: calculating the target cooling water flow rate according to the following formula:

[0059]

[0060] Among them, Q target Let d0 be the target cooling water flow rate, d0 be the bias term, X be the set of target characteristic parameters, and f be the value of f. i (X) is the output corresponding to the i-th target feature parameter, a i F is the weight parameter corresponding to the output of the i-th target feature parameter. i For the i-th postfix term, the postfix term includes higher-order cross terms and time-series information processing terms. The weight parameter is the one corresponding to the i-th post-item.

[0061] Specifically, when calculating the target cooling water flow rate, in addition to using basic historical cooling water flow rate, temperature, load, and speed parameters, more advanced feedback factors, nonlinear relationships, and dynamic influences can be considered to improve accuracy and adaptability. By integrating multiple original features, a multi-dimensional feature vector X is constructed, where X is also a set of target feature parameters, X = [T] motor ,P motor N motor ,T ambient Q history ,…,f d ,f t ,f mixTo further enhance the model's complexity, a more sophisticated nonlinear mapping function is employed to map the multi-dimensional feature vector X to the target cooling water flow rate. Assuming a multi-layer neural network structure is used, with X as the input and Q as the output, the specific calculation process can be represented as Q. target The target cooling water flow rate, in conventional calculations, can be expressed as follows:

[0062]

[0063] Where σ is the activation function, W1, W2, and W3 are the weight matrices of the neural network, d1, d2, and d3 are bias terms, and h1 and h2 are the feature representations of the intermediate layers. Based on the above calculation process, a more accurate calculation method can be proposed to improve Q. target The accuracy of the calculation can be determined using the formula: Calculate Q target In the embodiments of this application, the process of complex calculations is denoted as a post-term. Post-terms can be added or removed. The number of post-terms depends on the actual application scenario; the more complex the calculation in the scenario, the more post-terms are needed. For example, considering that cooling water flow may be affected by historical operating conditions, environmental changes, and real-time feedback, a time-varying term and a dynamic update mechanism can be introduced into the model. That is, LSTM is used to process the time series relationship between historical cooling water flow and main motor load. Assuming that the first post-term is the processing of the time series relationship between historical cooling water flow and main motor load using LSTM, we can obtain:

[0064]

[0065] LSTM is used to capture temporal relationships; alternatively, combinations of higher-order cross terms can be added, which can reveal more complex physical relationships and interactions. Assuming that the combination of further higher-order cross terms is the second term of the post-term, we can obtain:

[0066]

[0067] Among them, X ij For the j-th item in the input features, θ is the weight parameter corresponding to the i-th input feature in the second postterm. ij The exponent corresponding to the j-th input feature is used to enhance or suppress the influence of the cross term.

[0068] Step S104: Based on the target cooling water flow rate, perform water cooling control operation on the target hot rolling mill through an electric proportional valve.

[0069] Specifically, based on the target cooling water flow rate output by the cooling water flow control model, the system uses this target cooling water flow rate as a reference value to perform precise water cooling control of the target hot rolling mill via an electric proportional valve. Specifically, the electric proportional valve adjusts the flow rate and pressure of the cooling water according to the set value of the target cooling water flow rate to ensure that the cooling system of the hot rolling mill can respond in real time to the needs of operating conditions such as motor load and temperature changes. By finely adjusting the water flow rate, the electric proportional valve enables the cooling system to dynamically adjust under different production conditions, ensuring that the equipment receives sufficient cooling under various operating conditions without over-cooling or under-cooling, thereby maintaining the operating temperature of the hot rolling mill within a safe range, improving production efficiency, and extending the service life of the equipment. During this process, the electric proportional valve continuously monitors the target cooling water flow rate and makes real-time adjustments based on feedback signals to ensure the stability and reliability of the target hot rolling mill's operation.

[0070] Based on practical application data, this invention can save 230m³ of water per hour during the hot rolling production process. 3 It can save approximately 1,181,280 cubic meters of water per year. 3 This invention significantly reduces the water consumption pressure on enterprises. By saving water resources and electricity, it can save enterprises approximately 190,000 yuan in electricity costs annually, significantly reducing the operating costs of hot rolling production lines. While improving water resource utilization efficiency, this invention also reduces wastewater discharge, which is beneficial to environmental protection and aligns with my country's energy conservation and emission reduction policies. Therefore, this invention has significant technical and economic benefits, providing a highly efficient, energy-saving, and environmentally friendly solution for the water-cooling control system of the main motor and hydraulic station of hot rolling mills.

[0071] This application uses the above method to obtain cooling water flow rate adjustment parameters, extracts features from the cooling water flow rate adjustment parameters, and obtains target feature parameters. These target feature parameters are then used as input, and a cooling water flow rate corresponding to the target hot rolling mill is output through a cooling water flow rate control model. Based on the target cooling water flow rate, the target hot rolling mill is subjected to water cooling control operation via an electric proportional valve. This saves circulating water consumption, reduces energy consumption, achieves green development, and effectively reduces the production energy consumption of copper processing enterprises.

[0072] Please refer to Figure 2 The diagram illustrates a module schematic of a hot rolling mill water cooling control device according to an embodiment of this application. The device includes an acquisition module 21 and a processing module 22, wherein...

[0073] The acquisition module 21 is used to acquire cooling water flow rate adjustment parameters in response to the water cooling control operation for the target hot rolling mill. The cooling water flow rate adjustment parameters include main motor load parameters, main motor temperature parameters, and main motor working cycle parameters.

[0074] The processing module 22 is used to extract features from the cooling water flow rate adjustment parameters and obtain target feature parameters; take the target feature parameters as input and output the target cooling water flow rate corresponding to the target hot rolling mill through the cooling water flow rate control model; and perform water cooling control operation on the target hot rolling mill through an electric proportional valve according to the target cooling water flow rate.

[0075] In one possible implementation, the target feature parameters include fused derived features, fused temporal features, and fused cross features. The processing module 22 is used to extract features from the cooling water flow regulation parameters and obtain the target feature parameters. Specifically, this includes: obtaining the motor load parameters, temperature change rate parameters, and vibration intensity parameters from the cooling water flow regulation parameters; constructing fused derived features from the target feature parameters based on the motor load parameters, temperature change rate parameters, and vibration intensity parameters; obtaining the historical cooling water flow parameters, historical temperature parameters, and historical power parameters from the cooling water flow regulation parameters; constructing fused temporal features from the target feature parameters based on the historical cooling water flow parameters, historical temperature parameters, and historical power parameters; obtaining the cross-term parameters of temperature and load, and the cross-term parameters of speed and ambient temperature from the cooling water flow regulation parameters; constructing fused cross features from the target feature parameters based on the cross-term parameters of temperature and load, and the cross-term parameters of speed and ambient temperature; fusing the fused derived features, fused temporal features, and fused cross features, and using the feature parameters after feature parameter fusion as the target feature parameters.

[0076] In one possible implementation, the processing module 22 is used to construct fused derived features from the target feature parameters based on the motor load parameters, temperature change rate parameters, and vibration intensity parameters. Specifically, this includes: using a nonlinear mapping function, performing a first fusion operation on the cooling water flow rate adjustment parameters using the following formula, and obtaining the fused derived features:

[0077] f d =α1log(P motor +∈)+α2*exp(ΔT motor )+α3*A vibration 2 ;

[0078] Among them, f d To integrate derived features, P motor Here, α1 represents the weighting coefficient corresponding to the motor load parameter, and ΔT represents the motor load parameter. motor Let A be the temperature change rate parameter, α2 be the weighting coefficient corresponding to the temperature change rate parameter, and A be the weighting coefficient corresponding to the temperature change rate parameter. vibration Here, α3 is the weighting coefficient corresponding to the vibration intensity parameter, and ∈ is the adjustment factor used to avoid zero when taking the logarithm.

[0079] In one possible implementation, the processing module 22 is used to construct a fused time-series feature from the target feature parameters based on historical cooling water flow parameters, historical temperature parameters, and historical power parameters. Specifically, this includes: using weighted sliding window processing, performing a second fusion operation on the cooling water flow adjustment parameters using the following formula, and obtaining the fused time-series feature:

[0080]

[0081] Among them, f t To integrate temporal features, ti represents a historical moment, and Q... history (ti) represents the historical cooling water flow rate parameter, T motor (ti) represents the historical temperature parameter, P motor (ti) n Historical power parameters, β1 is the weight corresponding to the historical cooling water flow rate parameter, β2 is the weight corresponding to the historical temperature parameter, and β3 is the weight corresponding to the historical power parameter.

[0082] In one possible implementation, the processing module 22 is used to construct fused cross features in the target feature parameters based on the cross-term parameters of temperature and load, and the cross-term parameters of speed and ambient temperature. Specifically, this includes: sampling a high-order cross-term polynomial combination, performing a third fusion operation on the cooling water flow rate adjustment parameters using the following formula, and obtaining the fused cross features:

[0083] f mix =γ1*(T motor ·P motor )+γ2*(N motor ·T ambient )+γ3*(T motor 2 ·

[0084] P motor );

[0085] Among them, f mix To integrate cross features, N motor The main motor speed parameter is represented by ·, which indicates the element-wise operation between various cooling water flow adjustment parameters. γ1 is the weight corresponding to the cross-term parameter of temperature and load, γ2 is the weight corresponding to the cross-term parameter of speed and ambient temperature, and γ3 is the weight corresponding to the secondary cross-term of temperature and load.

[0086] In one possible implementation, the processing module 22 is used to construct a cooling water flow control model before taking the target feature parameter as input and outputting the target cooling water flow corresponding to the target hot rolling mill through the cooling water flow control model. Specifically, this includes: obtaining historical cooling water flow adjustment parameters, which include historical main motor load parameters, historical main motor temperature parameters, and historical main motor working cycle parameters; and constructing a cooling water flow control model based on the historical cooling water flow adjustment parameters.

[0087] In one possible implementation, the processing module 22 is used to output the target cooling water flow rate corresponding to the target hot rolling mill through the cooling water flow rate control model, specifically including: calculating the target cooling water flow rate according to the following formula:

[0088]

[0089] Among them, Q target Let d0 be the target cooling water flow rate, d0 be the bias term, X be the set of target characteristic parameters, and f be the value of f. i (X) is the output corresponding to the i-th target feature parameter, F i For the i-th postfix term, the postfix term includes higher-order cross terms and time-series information processing terms. The weight parameter is the one corresponding to the i-th post-item.

[0090] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0091] This application also provides an electronic device. (See reference...) Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: at least one processor 301, at least one communication bus 302, a user interface 303, at least one network interface 304, and a memory 305.

[0092] The communication bus 302 is used to enable communication between these components.

[0093] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0094] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0095] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 301 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0096] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. (Refer to...) Figure 3 The memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a hot rolling mill water cooling control application.

[0097] exist Figure 3 In the illustrated electronic device, the user interface 303 is primarily used to provide an input interface for the user and acquire user input data; while the processor 301 can be used to call the hot rolling mill water cooling control application stored in the memory 305. When executed by one or more processors 301, the electronic device performs one or more of the methods described in the above embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simplicity, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0098] This application also provides a computer-readable storage medium storing instructions. When executed by one or more processors, these instructions cause an electronic device to perform one or more of the methods described in the above embodiments.

[0099] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0100] In the various embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.

[0101] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0102] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0103] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0104] The above description is merely an exemplary embodiment disclosed in this application and should not be construed as limiting the scope of this application. Any equivalent changes and modifications made in accordance with the teachings of this application shall still fall within the scope of this application. Those skilled in the art, upon considering the disclosure of the specification and practical truths, will readily conceive of other embodiments disclosed in this application.

[0105] This application is intended to cover any variations, uses, or adaptations disclosed herein that follow the general principles disclosed herein and include common knowledge or customary technical means in the art that are not described in this application.

Claims

1. A water-cooling control method for a hot rolling mill, characterized in that, The method includes: In response to the water cooling control operation for the target hot rolling mill, cooling water flow rate adjustment parameters are obtained, including main motor load parameters, main motor temperature parameters, and main motor duty cycle parameters. Feature extraction is performed on the cooling water flow rate regulation parameters to obtain target feature parameters, which include fused derived features, fused temporal features, and fused cross features. Specifically, this includes: obtaining motor load parameters, temperature change rate parameters, and vibration intensity parameters from the cooling water flow rate regulation parameters; constructing the fused derived features from the target feature parameters based on the motor load parameters, temperature change rate parameters, and vibration intensity parameters; obtaining historical cooling water flow rate parameters, historical temperature parameters, and historical power parameters from the cooling water flow rate regulation parameters; constructing the fused temporal features from the target feature parameters based on the historical cooling water flow rate parameters, historical temperature parameters, and historical power parameters; obtaining the cross-term parameters of temperature and load, and the cross-term parameters of speed and ambient temperature from the cooling water flow rate regulation parameters; constructing the fused cross features from the target feature parameters based on the cross-term parameters of temperature and load, and the cross-term parameters of speed and ambient temperature; fusing the fused derived features, the fused temporal features, and the fused cross features, and using the feature parameters after feature parameter fusion as the target feature parameters. Using the target feature parameters as input, the target cooling water flow rate corresponding to the target hot rolling mill is output through the cooling water flow rate control model. The water cooling control operation is performed on the target hot rolling mill via an electric proportional valve according to the target cooling water flow rate.

2. The method according to claim 1, characterized in that, The step of constructing the fused derived features in the target feature parameters based on the motor load parameters, the temperature change rate parameters, and the vibration intensity parameters specifically includes: A nonlinear mapping function is used to perform a first fusion operation on the cooling water flow rate adjustment parameters using the following formula, and the fusion-derived features are obtained: ； in, For the fusion-derived features, The motor load parameters are as follows. These are the weighting coefficients corresponding to the motor load parameters. The temperature change rate parameter is... The weighting coefficients corresponding to the temperature change rate parameter are: The vibration intensity parameter is... The weighting coefficients corresponding to the vibration intensity parameters are: This is an adjustment factor used to avoid zero values ​​when taking the logarithm.

3. The method according to claim 1, characterized in that, The step of constructing the fused time-series feature in the target feature parameters based on the historical cooling water flow rate parameters, the historical temperature parameters, and the historical power parameters specifically includes: A weighted sliding window processing method is used to perform a second fusion operation on the cooling water flow rate adjustment parameters using the following formula, and the fusion timing characteristics are obtained: ； in, For the fused temporal features, For a historic moment, The historical cooling water flow rate parameters, The temperature parameters at the historical time point are... The power parameters at the historical moment are... The weights corresponding to the historical cooling water flow rate parameters, The weights corresponding to the temperature parameters at the historical moments are: The weights corresponding to the power parameters at the historical time points. This represents the time weighting coefficient corresponding to the i-th historical moment within the sliding time window.

4. The method according to claim 1, characterized in that, The step of constructing the fused cross-feature in the target feature parameters based on the cross-term parameters of temperature and load, and the cross-term parameters of rotational speed and ambient temperature, specifically includes: By sampling higher-order cross-term polynomial combinations, a third fusion operation is performed on the cooling water flow rate adjustment parameters using the following formula, and the fusion cross-features are obtained: ； in, For the fusion cross feature, Main motor speed parameters This indicates that each of the aforementioned cooling water flow rate adjustment parameters is operated on an element-by-element basis. The weights corresponding to the cross-term parameters of temperature and load are... The weights corresponding to the cross-term parameters of the rotational speed and ambient temperature are... The weights are the quadratic cross terms of temperature and load. For motor load parameters, For motor temperature parameters, This refers to the ambient temperature parameter.

5. The method according to claim 1, characterized in that, Before using the target feature parameters as input and outputting the target cooling water flow rate corresponding to the target hot rolling mill through the cooling water flow rate control model, the cooling water flow rate control model needs to be constructed, specifically including: Obtain historical cooling water flow rate adjustment parameters, including historical main motor load parameters, historical main motor temperature parameters, and historical main motor duty cycle parameters; The cooling water flow control model is constructed based on the historical cooling water flow adjustment parameters.

6. The method according to claim 1, characterized in that, The step of outputting the target cooling water flow rate corresponding to the target hot rolling mill through the cooling water flow rate control model specifically includes: The target cooling water flow rate is calculated using the following formula: ； in, The target cooling water flow rate, For bias terms, The set of features of the target feature parameters. For the first The output corresponding to each of the target feature parameters. For the first The weight parameters corresponding to the output of each of the target feature parameters. For the first The post-item includes a higher-order cross term and a time-series information processing term. For the first The weight parameters corresponding to each of the following post-items.

7. A water-cooling control device for a hot rolling mill, characterized in that, The device includes an acquisition module and a processing module, wherein, The acquisition module is used to acquire cooling water flow rate adjustment parameters in response to water cooling control operations for the target hot rolling mill. The cooling water flow rate adjustment parameters include main motor load parameters, main motor temperature parameters, and main motor working cycle parameters. The processing module is used to extract features from the cooling water flow rate regulation parameters and obtain target feature parameters, which include fused derived features, fused temporal features, and fused cross features. Specifically, it includes: obtaining motor load parameters, temperature change rate parameters, and vibration intensity parameters from the cooling water flow rate regulation parameters; constructing the fused derived features from the target feature parameters based on the motor load parameters, temperature change rate parameters, and vibration intensity parameters; obtaining historical cooling water flow rate parameters, historical temperature parameters, and historical power parameters from the cooling water flow rate regulation parameters; and constructing the fused derived features from the target feature parameters based on the historical cooling water flow rate parameters, historical temperature parameters, and historical power parameters. The process involves: describing the fusion timing characteristics; obtaining the cross-term parameters of temperature and load, and the cross-term parameters of rotational speed and ambient temperature in the cooling water flow rate adjustment parameters; constructing the fusion cross-feature in the target feature parameters based on the cross-term parameters of temperature and load, and the cross-term parameters of rotational speed and ambient temperature; fusing the fusion derived features, the fusion timing characteristics, and the fusion cross-feature, and using the feature parameters after fusion as the target feature parameters; using the target feature parameters as input, outputting the target cooling water flow rate corresponding to the target hot rolling mill through the cooling water flow rate control model; and performing the water cooling control operation on the target hot rolling mill through an electric proportional valve based on the target cooling water flow rate.

8. An electronic device, characterized in that, The device includes a processor, a communication bus, a user interface, a network interface, and a memory. The memory is used to store instructions. The user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the method as described in any one of claims 1 to 6.

Images