A steel wire heat treatment furnace energy consumption monitoring and control system based on data analysis

Abstract

The application discloses a kind of steel wire heat treatment furnace energy consumption monitoring and control system based on data analysis, it is related to energy consumption monitoring technical field, including the data acquisition module for real-time collection steel wire heat treatment furnace operation data when working;For the pre-processing data pre-processing module to the operation data collected;For the energy consumption monitoring module for constructing energy consumption prediction model by pre-processing data;For the energy consumption control module of the operation data of steel wire heat treatment furnace is regulated according to the judging result of energy consumption judging module.Judgment module is set to energy consumption, so that the system can adjust the energy consumption of steel wire heat treatment furnace to normal state in time when judging that steel wire heat treatment furnace energy consumption is abnormal, realize the optimization control of energy consumption, in addition, the determination of regulation sequence considers the influence degree of different operation data on energy consumption, so that regulation is more targeted, so that the energy consumption of steel wire heat treatment furnace can recover to normal state as soon as possible.

Description

Technical Field

[0001] This invention relates to the field of energy consumption monitoring technology, and in particular to an energy consumption monitoring and control system for steel wire heat treatment furnaces based on data analysis. Background Technology

[0002] A steel wire heat treatment furnace is a specialized piece of equipment used for the heat treatment of steel wire. Its main function is to alter the internal structure of the steel wire through processes such as heating, holding, and cooling, thereby improving its mechanical properties and service life. As a key piece of equipment in metal processing, the energy consumption of steel wire heat treatment furnaces has always been a focus of industry attention. Traditional steel wire heat treatment furnaces often lack effective energy consumption monitoring and control methods, meaning that when abnormal energy consumption occurs, staff are often unable to adjust the system in a timely manner. This increases operating costs for enterprises and also imposes unnecessary burdens on the environment. Summary of the Invention

[0003] In view of the shortcomings of the existing technology, the purpose of this invention is to provide a data analysis-based energy consumption monitoring and control system for steel wire heat treatment furnaces, aiming to solve the above-mentioned technical problems.

[0004] To achieve the above objectives, the present invention adopts the following technical solution:

[0005] A data analysis-based energy consumption monitoring and control system for a steel wire heat treatment furnace includes a data acquisition module, a data preprocessing module, an energy consumption monitoring module, an energy consumption judgment module, and an energy consumption control module.

[0006] The data acquisition module is used to collect real-time operating data of the steel wire heat treatment furnace during operation.

[0007] A data preprocessing module is used to preprocess the collected running data to obtain preprocessed data.

[0008] An energy consumption monitoring module is used to construct an energy consumption prediction model through preprocessed data, thereby obtaining an energy consumption prediction model suitable for steel wire heat treatment furnaces.

[0009] An energy consumption judgment module is used to judge whether the energy consumption prediction model for the energy consumption of the steel wire heat treatment furnace is normal.

[0010] An energy consumption control module is used to regulate the operating data of the steel wire heat treatment furnace according to the judgment result of the energy consumption judgment module until the energy consumption of the steel wire heat treatment furnace returns to normal.

[0011] Preferably, the operating data includes the furnace temperature. Heating speed Cooling speed and furnace pressure Furnace energy consumption .

[0012] Preferably, the data preprocessing module is used to preprocess the collected operational data to obtain preprocessed data, including the following steps:

[0013] The collected operational data are arranged in chronological order to obtain furnace temperature dataset, heating rate dataset, cooling rate dataset, furnace pressure dataset, and furnace energy consumption dataset. The furnace energy consumption data in the furnace energy consumption dataset corresponds one-to-one with the furnace temperature data in the furnace temperature dataset, the heating rate data in the heating rate dataset, the cooling rate data in the cooling rate dataset, and the furnace pressure data in the furnace pressure dataset.

[0014] Taking the furnace temperature dataset as an example, the furnace temperature dataset is divided by a sliding window to obtain multiple subsets of the furnace temperature dataset. Let the length of the sliding window be k and the step size be g. Then, after the e-th sliding step, the subset of the furnace temperature dataset collected by the sliding window is represented as follows: , where k, g, and e are all positive integers, and satisfy k≥4, 0.5k≤g≤k;

[0015] Calculate the average temperature of the temperature data in the subset of the furnace temperature dataset. and standard deviation This can be achieved through the following formula. , ,in It is a positive integer;

[0016] for The process involves checking each subset of furnace temperature data for anomalies. If anomalies are found, the abnormal temperature data is deleted and replaced with the average temperature of the set. After all the temperature data in all subsets of furnace temperature data have been checked and replaced, a preprocessed furnace temperature dataset is obtained. The same method is used for the heating rate dataset, cooling rate dataset, furnace pressure dataset, and furnace energy consumption dataset to obtain the corresponding preprocessed heating rate dataset, preprocessed cooling rate dataset, preprocessed furnace pressure dataset, and preprocessed furnace energy consumption dataset.

[0017] Preferably, determining whether the temperature data in the furnace temperature dataset is abnormal specifically involves:

[0018] like Then determine This is abnormal temperature data;

[0019] like Then determine This is normal temperature data.

[0020] Preferably, the steps for the energy consumption monitoring module to construct an energy consumption prediction model through preprocessed data, thereby obtaining an energy consumption prediction model suitable for steel wire heat treatment furnaces, are as follows:

[0021] 70% of the furnace temperature data was randomly extracted from the preprocessed furnace temperature dataset. Then, corresponding heating rate data, cooling rate data, furnace pressure data, and furnace energy consumption data were extracted from the preprocessed heating rate dataset, preprocessed cooling rate dataset, preprocessed furnace pressure dataset, and preprocessed furnace energy consumption dataset, respectively, and combined to form the training set. The remaining 30% of the preprocessed furnace temperature dataset, preprocessed heating rate dataset, preprocessed cooling rate dataset, preprocessed furnace pressure dataset, and preprocessed furnace energy consumption dataset were combined to form the test set.

[0022] The energy consumption prediction model is trained using a training set and tested and evaluated using a test set, thus obtaining an energy consumption prediction model suitable for steel wire heat treatment furnaces.

[0023] Preferably, the energy consumption judgment module is used to judge whether the energy consumption prediction model for the energy consumption of the steel wire heat treatment furnace is normal, including the following steps:

[0024] Energy consumption prediction data from the energy consumption prediction model Compared with the standard energy consumption data in the preset energy consumption table If a comparison is made, ≤ If so, it is determined that the energy consumption of the steel wire heat treatment furnace is normal at this time; if > If the energy consumption of the steel wire heat treatment furnace is abnormal, the energy consumption control module will adjust the furnace temperature, heating rate, cooling rate and furnace pressure in the correct order.

[0025] Preferably, the control sequence is obtained through the following steps:

[0026] Build the runtime data matrix ,in Represented as a furnace temperature vector, Represented as a heating velocity vector, Represented as a cooling rate vector, Represented as the furnace pressure vector;

[0027] Normalize the running data matrix;

[0028] By successively increasing and decreasing each column vector in the normalized running data matrix by 10%, four new running data matrices are obtained. , and , and , and , ;

[0029] In sequence , and , and , and , The data is input into the energy consumption prediction model, resulting in four sets of corresponding energy consumption prediction values, which are as follows: , and , and , and , ;

[0030] Calculate the impact values ​​of the four new sets of running data matrices ;

[0031] The impact values ​​of the four new sets of running data matrices Arranged in order of size, the control sequence of furnace temperature, heating rate, cooling rate, and furnace pressure in the steel wire heat treatment furnace is obtained.

[0032] Preferably, the normalization of the running data matrix is ​​achieved using the following formula: ,in For running data matrix In OK Column elements, For running data matrix The The maximum value in the column, For running data matrix The The minimum value in the column.

[0033] Preferably, the influence values ​​of the four new sets of operating data matrices are calculated. This can be achieved using the following formula: = ,in The value is , , and , The values ​​are as follows: , , and .

[0034] Preferably, the system further includes a report generation module for generating an energy consumption report for the steel wire heat treatment furnace.

[0035] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0036] 1. By incorporating a data preprocessing module, this system can detect and replace abnormal data in the collected operational data, thereby improving data accuracy and providing a reliable basis for subsequent energy consumption prediction and judgment.

[0037] 2. By setting up an energy consumption judgment module, this system can promptly adjust the energy consumption of the steel wire heat treatment furnace to a normal state when it detects abnormal energy consumption, thereby achieving optimized energy consumption control. In addition, the determination of the control sequence takes into account the degree of influence of different operating data on energy consumption, making the control more targeted, so that the energy consumption of the steel wire heat treatment furnace can be restored to a normal state as soon as possible. Attached Figure Description

[0038] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 A schematic diagram of the composition structure of a data analysis-based energy consumption monitoring and control system for steel wire heat treatment furnaces is shown.

[0040] Legend:

[0041] 1. Data acquisition module; 2. Data preprocessing module; 3. Energy consumption monitoring module; 4. Energy consumption judgment module; 5. Energy consumption control module; 6. Report generation module. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] Reference Figure 1An embodiment of the energy consumption monitoring and control system for steel wire heat treatment furnace based on data analysis of the present invention will be further described.

[0044] A data analysis-based energy consumption monitoring and control system for a steel wire heat treatment furnace includes a data acquisition module 1, a data preprocessing module 2, an energy consumption monitoring module 3, an energy consumption judgment module 4, and an energy consumption control module 5.

[0045] Data acquisition module 1 is used to collect real-time operating data of the steel wire heat treatment furnace during operation; it should be noted that the operating data includes the furnace temperature. Heating speed Cooling speed and furnace pressure Furnace energy consumption .

[0046] Data preprocessing module 2, which is used to preprocess the collected running data to obtain preprocessed data, includes the following steps:

[0047] The collected operational data are arranged in chronological order to obtain furnace temperature dataset, heating rate dataset, cooling rate dataset, furnace pressure dataset, and furnace energy consumption dataset. The furnace energy consumption data in the furnace energy consumption dataset corresponds one-to-one with the furnace temperature data in the furnace temperature dataset, the heating rate data in the heating rate dataset, the cooling rate data in the cooling rate dataset, and the furnace pressure data in the furnace pressure dataset.

[0048] Taking the furnace temperature dataset as an example, the furnace temperature dataset is divided by a sliding window to obtain multiple subsets of the furnace temperature dataset. Let the length of the sliding window be k and the step size be g. Then, after the e-th sliding step, the subset of the furnace temperature dataset collected by the sliding window is represented as follows: , where k, g, and e are all positive integers, and satisfy k≥4, 0.5k≤g≤k;

[0049] Calculate the average temperature of the temperature data in the subset of the furnace temperature dataset. and standard deviation This can be achieved through the following formula. , ,in It is a positive integer;

[0050] for The process involves checking each subset of furnace temperature data for anomalies. If anomalies are found, the abnormal temperature data is deleted and replaced with the average temperature of the set. After all the temperature data in all subsets of furnace temperature data have been checked and replaced, a preprocessed furnace temperature dataset is obtained. The same method is used for the heating rate dataset, cooling rate dataset, furnace pressure dataset, and furnace energy consumption dataset to obtain the corresponding preprocessed heating rate dataset, preprocessed cooling rate dataset, preprocessed furnace pressure dataset, and preprocessed furnace energy consumption dataset.

[0051] The specific steps for determining whether the temperature data in the furnace temperature dataset is abnormal are as follows:

[0052] like Then determine This is abnormal temperature data;

[0053] like Then determine This is normal temperature data.

[0054] By incorporating a data preprocessing module 2, this system can detect and replace abnormal data in the collected operational data, thereby improving the accuracy of the data and providing a reliable basis for subsequent energy consumption prediction and judgment.

[0055] Energy consumption monitoring module 3 is used to construct an energy consumption prediction model through preprocessed data, thereby obtaining an energy consumption prediction model suitable for steel wire heat treatment furnaces. The specific steps are as follows:

[0056] 70% of the furnace temperature data was randomly extracted from the preprocessed furnace temperature dataset. Then, corresponding heating rate data, cooling rate data, furnace pressure data, and furnace energy consumption data were extracted from the preprocessed heating rate dataset, preprocessed cooling rate dataset, preprocessed furnace pressure dataset, and preprocessed furnace energy consumption dataset, respectively, and combined to form the training set. The remaining 30% of the preprocessed furnace temperature dataset, preprocessed heating rate dataset, preprocessed cooling rate dataset, preprocessed furnace pressure dataset, and preprocessed furnace energy consumption dataset were combined to form the test set.

[0057] The energy consumption prediction model is trained using a training set and tested and evaluated using a test set, thus obtaining an energy consumption prediction model suitable for steel wire heat treatment furnaces.

[0058] Energy consumption judgment module 4, which is used to judge whether the energy consumption prediction model for the energy consumption of steel wire heat treatment furnace is normal, includes the following steps:

[0059] Energy consumption prediction data from the energy consumption prediction model Compared with the standard energy consumption data in the preset energy consumption table If a comparison is made, ≤ If so, it is determined that the energy consumption of the steel wire heat treatment furnace is normal at this time; if > If the energy consumption of the steel wire heat treatment furnace is abnormal, the energy consumption control module 5 will adjust the furnace temperature, heating rate, cooling rate and furnace pressure in the correct order.

[0060] The control sequence is obtained through the following steps:

[0061] Build the runtime data matrix ,in Represented as a furnace temperature vector, Represented as a heating velocity vector, Represented as a cooling rate vector, Represented as the furnace pressure vector;

[0062] Normalize the running data matrix;

[0063] It should be noted that the normalization of the running data matrix is ​​achieved using the following formula: ,in For running data matrix In OK Column elements, For running data matrix The The maximum value in the column, For running data matrix The The minimum value in the column.

[0064] By successively increasing and decreasing each column vector in the normalized running data matrix by 10%, four new running data matrices are obtained. , and , and , and , ;

[0065] In sequence , and , and , and , The data is input into the energy consumption prediction model, resulting in four sets of corresponding energy consumption prediction values, which are as follows: , and , and , and , ;

[0066] Calculate the impact values ​​of the four new sets of running data matrices ;

[0067] It should be noted that the impact values ​​of the four new sets of operating data matrices are calculated. This can be achieved using the following formula: = ,in The value is , , and , The values ​​are as follows: , , and .

[0068] The impact values ​​of the four new sets of running data matrices Arranged in order of size, the control sequence of furnace temperature, heating rate, cooling rate, and furnace pressure in the steel wire heat treatment furnace is obtained.

[0069] By incorporating an energy consumption judgment module 4, the system can promptly adjust the energy consumption of the steel wire heat treatment furnace to a normal state when it detects abnormal energy consumption, thereby achieving optimized energy consumption control. Furthermore, the determination of the control sequence takes into account the degree of influence of different operating data on energy consumption, making the control more targeted, thus enabling the energy consumption of the steel wire heat treatment furnace to recover to a normal state as quickly as possible.

[0070] Energy consumption control module 5 is used to regulate the operating data of the steel wire heat treatment furnace according to the judgment result of energy consumption judgment module 4 until the energy consumption of the steel wire heat treatment furnace returns to normal.

[0071] The system also includes a report generation module 6, which is used to generate an energy consumption report for the steel wire heat treatment furnace.

[0072] With the inclusion of a report generation module 6, this system is able to generate energy consumption reports for the steel wire heat treatment furnace, providing users with intuitive energy consumption data and analysis results. This helps users better understand the furnace's energy consumption status and make corresponding management decisions.

[0073] The above description of the embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data analysis-based energy consumption monitoring and control system for steel wire heat treatment furnaces, characterized in that, It includes a data acquisition module (1), a data preprocessing module (2), an energy consumption monitoring module (3), an energy consumption judgment module (4), and an energy consumption control module (5); Data acquisition module (1), the data acquisition module (1) is used to collect the operating data of the steel wire heat treatment furnace in real time; Data preprocessing module (2), the data preprocessing module (2) is used to preprocess the collected running data to obtain preprocessed data; Energy consumption monitoring module (3), the energy consumption monitoring module (3) is used to construct an energy consumption prediction model through preprocessed data, and then obtain an energy consumption prediction model suitable for steel wire heat treatment furnace; Energy consumption judgment module (4), the energy consumption judgment module (4) is used to judge whether the energy consumption prediction model for the energy consumption of the steel wire heat treatment furnace is normal; Energy consumption control module (5), the energy consumption control module (5) is used to adjust the operating data of the steel wire heat treatment furnace according to the judgment result of the energy consumption judgment module (4) until the energy consumption of the steel wire heat treatment furnace returns to normal. The operational data includes furnace temperature. Heating speed Cooling speed and furnace pressure Furnace energy consumption ; The data preprocessing module (2) is used to preprocess the collected running data to obtain preprocessed data, including the following steps: The collected operational data are arranged in chronological order to obtain furnace temperature dataset, heating rate dataset, cooling rate dataset, furnace pressure dataset, and furnace energy consumption dataset. The furnace energy consumption data in the furnace energy consumption dataset corresponds one-to-one with the furnace temperature data in the furnace temperature dataset, the heating rate data in the heating rate dataset, the cooling rate data in the cooling rate dataset, and the furnace pressure data in the furnace pressure dataset. Taking the furnace temperature dataset as an example, the furnace temperature dataset is divided by a sliding window to obtain multiple subsets of the furnace temperature dataset. Let the length of the sliding window be k and the step size be g. Then, after the e-th sliding step, the subset of the furnace temperature dataset collected by the sliding window is represented as follows: , where k, g, and e are all positive integers, and satisfy k≥4, 0.5k≤g≤k; Calculate the average temperature of the temperature data in the subset of the furnace temperature dataset. and standard deviation This can be achieved through the following formula. , ,in It is a positive integer; for The process involves checking each subset of furnace temperature data for anomalies. If anomalies are found, the abnormal temperature data is deleted and replaced with the average temperature of the set. After all the temperature data in all subsets of furnace temperature data have been checked and replaced, a preprocessed furnace temperature dataset is obtained. The same method is used for heating rate dataset, cooling rate dataset, furnace pressure dataset, and furnace energy consumption dataset to obtain the corresponding preprocessed heating rate dataset, preprocessed cooling rate dataset, preprocessed furnace pressure dataset, and preprocessed furnace energy consumption dataset. The energy consumption judgment module (4) is used to judge whether the energy consumption prediction model for the energy consumption of the steel wire heat treatment furnace is normal, including the following steps: Energy consumption prediction data from the energy consumption prediction model Compared with the standard energy consumption data in the preset energy consumption table If a comparison is made, ≤ If so, it is determined that the energy consumption of the steel wire heat treatment furnace is normal at this time; if > If the energy consumption of the steel wire heat treatment furnace is abnormal, the energy consumption control module (5) will regulate the furnace temperature, heating rate, cooling rate and furnace pressure of the steel wire heat treatment furnace according to the regulation sequence. The control sequence is obtained through the following steps: Build the runtime data matrix ,in Represented as a furnace temperature vector, Represented as a heating velocity vector, Represented as a cooling rate vector, Represented as the furnace pressure vector; Normalize the running data matrix; By successively increasing and decreasing each column vector in the normalized running data matrix by 10%, four new running data matrices are obtained. , and , and , and , ; In sequence , and , and , and , The data is input into the energy consumption prediction model, resulting in four sets of corresponding energy consumption prediction values, which are as follows: , and , and , and , ; Calculate the impact values ​​of the four new sets of running data matrices ; The impact values ​​of the four new sets of running data matrices Arranged in order of size, the control order of furnace temperature, heating rate, cooling rate and furnace pressure in the steel wire heat treatment furnace is obtained; The normalization of the running data matrix is ​​achieved using the following formula: ,in For running data matrix In OK Column elements, For running data matrix The The maximum value in the column, For running data matrix The The minimum value in the column; Calculate the impact values ​​of the four new sets of running data matrices This can be achieved using the following formula: = ,in The value is , , and , The values ​​are as follows: , , and .

2. The energy consumption monitoring and control system for steel wire heat treatment furnace based on data analysis according to claim 1, characterized in that, Specifically, determining whether the temperature data in the furnace temperature dataset is abnormal involves: like Then determine This is abnormal temperature data; like Then determine This is normal temperature data.

3. The energy consumption monitoring and control system for a steel wire heat treatment furnace based on data analysis according to claim 2, characterized in that, The energy consumption monitoring module (3) is used to construct an energy consumption prediction model through preprocessed data, and the steps to obtain an energy consumption prediction model suitable for steel wire heat treatment furnace are as follows: 70% of the furnace temperature data was randomly extracted from the preprocessed furnace temperature dataset. Then, corresponding heating rate data, cooling rate data, furnace pressure data, and furnace energy consumption data were extracted from the preprocessed heating rate dataset, preprocessed cooling rate dataset, preprocessed furnace pressure dataset, and preprocessed furnace energy consumption dataset, respectively, and combined to form the training set. The remaining 30% of the preprocessed furnace temperature dataset, preprocessed heating rate dataset, preprocessed cooling rate dataset, preprocessed furnace pressure dataset, and preprocessed furnace energy consumption dataset were combined to form the test set. The energy consumption prediction model is trained using a training set and tested and evaluated using a test set, thus obtaining an energy consumption prediction model suitable for steel wire heat treatment furnaces.

4. The energy consumption monitoring and control system for a steel wire heat treatment furnace based on data analysis according to claim 3, characterized in that, The system also includes a report generation module (6) for generating energy consumption reports for the wire heat treatment furnace.

Images