Temperature control method and system for air preheater

Abstract

The invention discloses a temperature control method and system for an air preheater, and relates to the technical field of temperature control, temperature data of different parts in the air preheater are collected in real time to form a data set, after data normalization processing is carried out, a temperature data analysis model is established through a deep learning neural network, and the temperature data analysis model is analyzed; the model is used for analyzing and processing data to obtain temperature early warning and adjusting information, self-adaptive PID control is adopted to adjust the temperature in real time according to an analysis result, and an alarm signal is sent to a mobile phone APP according to the early warning information to remind an operator. The system can quickly and accurately respond to temperature change, improve control precision, avoid damage to equipment parts, shortening of the service life of equipment and increase of maintenance cost due to too high temperature, and can also prevent reduction of energy utilization efficiency due to too low temperature, thereby improving stability and economical efficiency of the whole production system.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control, and more particularly to a temperature control method and system for an air preheater. Background Art

[0002] At present, air preheaters are widely used in industrial production. Their function is to use the waste heat of flue gas discharged from the heating furnace / boiler to heat the air required for combustion, thereby improving the thermal efficiency of the heating furnace / boiler and reducing fuel consumption. However, in the actual operation process, the temperature control of the air preheater is very important. If the temperature is too high, it will cause damage to equipment components, shorten the service life of the equipment, and increase maintenance costs; if the temperature is too low, the role of waste heat recovery cannot be fully utilized, reducing energy utilization efficiency.

[0003] However, the existing air preheater temperature control system has many shortcomings. Some systems use a simple combination of temperature sensors and regulating valves, which are integrated into the DCS of the entire device unit. The control accuracy is low and it cannot respond to temperature changes quickly and accurately, affecting the stability and economy of the entire production system.

[0004] Therefore, how to quickly and accurately respond to temperature changes and maintain stable temperature control is an urgent problem that technicians in this field need to solve. Summary of the invention

[0005] In view of this, the present invention provides a temperature control method and system for an air preheater to solve the problems existing in the background technology.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: A temperature control method for an air preheater, comprising: Collect temperature data of different parts in the air preheater in real time to form a temperature data set; Establishing a temperature data analysis model to analyze and process the temperature data set to obtain analysis results, wherein the analysis results include temperature warning information and temperature adjustment information; According to the analysis results, the temperature of the air preheater is adjusted in real time using adaptive PID control; An alarm signal is generated based on the temperature warning information and sent to the mobile phone APP, which immediately reminds the operator to take measures.

[0007] Optionally, normalization processing of the temperature data collected in real time is also included, specifically including:

[0008] Where Z represents the normalized temperature value, T minrepresents the minimum temperature value in the data set, T max represents the maximum temperature value in the data set, T Represents the original temperature value to be normalized. The normalized value ranges from [0,1].

[0009] Optionally, the establishing of the temperature data analysis model specifically includes: Through deep learning neural network, a temperature data analysis model is established. The historical temperature data is set to contain observation values ​​of n time steps, and X is used to represent the input feature vector. Represents the corresponding temperature prediction value, which specifically includes the following steps: Input layer: historical temperature data is used as input feature vector; Hidden layer: Design multiple hidden layers according to requirements and select sigmoid activation function; Output layer: output temperature prediction value; Model training: Use time-marked historical temperature data for model training. Historical temperature data represents the temperature value records over a period of time in the past. Use the gradient descent method to minimize the loss function to adjust the weights and bias parameters of the neural network model.

[0010] Optionally, the analysis process includes: The temperature data analysis model is used to obtain the air preheater temperature prediction data; According to the air preheater temperature prediction data and the preset maximum temperature threshold and minimum temperature threshold, it is judged whether the air preheater temperature is abnormal. If the air preheater temperature prediction data is between the maximum temperature threshold and the minimum temperature threshold, the air preheater temperature is normal; If the air preheater temperature prediction data is higher than the maximum temperature threshold or the air preheater temperature prediction data is lower than the minimum temperature threshold, the air preheater temperature is abnormal and a temperature warning message is generated; According to the air preheater temperature prediction data, the air preheater temperature is dynamically adjusted until the air preheater temperature prediction value is between the maximum temperature threshold and the minimum temperature threshold, and the temperature adjustment information is obtained.

[0011] Optionally, the using of the gradient descent method specifically includes: a: define the loss function; b: calculate the gradient; c: Update model parameters, weights and bias update formulas; d: Iteratively repeat the above steps until the loss function is minimized.

[0012] Optionally, the loss function is specifically: ; In the formula, L ( W , b ) represents the mean square error loss function, W and b are the weight and bias of the model respectively, m represents the number of samples, y Indicates the actual temperature value. represents the predicted temperature value; The gradient is calculated as: ; in, and They represent the gradient of the loss function with respect to the weight matrix and bias vector of the hidden layer respectively.

[0013] Optionally, the weight and bias update formulas are as follows: ; In the formula, W' and b' denote weight update and bias update respectively, W and b are the weight and bias of the model, respectively. and They represent the gradient of the loss function to the weight matrix and bias vector of the hidden layer, respectively. α is the learning rate, which controls the step size of each update.

[0014] Optionally, the specific formula of the adaptive PID control is: ; in, represents the output of adaptive PID control, x represents the working time of air preheater, represents the proportional gain, represents the integral gain, represents the differential gain, , and represents the adaptive factor, Indicates the absolute value. represents the error of the system, It represents the integral of the deviation between the target control value and the actual control value.

[0015] A temperature control system for an air preheater, comprising: The data acquisition module collects temperature data of different parts in the air preheater in real time to form a temperature data set; A data analysis module, which establishes a temperature data analysis model to analyze and process the temperature data set to obtain analysis results, wherein the analysis results include temperature warning information and temperature adjustment information; The temperature adjustment module uses adaptive PID control to adjust the air preheater temperature in real time according to the analysis results; The temperature warning module generates an alarm signal based on the temperature warning information and sends it to the mobile phone APP. The mobile phone APP immediately reminds the operator to take measures.

[0016] It can be seen from the above technical solutions that compared with the prior art, the present invention discloses a temperature control method and system for an air preheater, which collects temperature data of different parts in the air preheater in real time to form a data set, normalizes the data, and establishes a temperature data analysis model through a deep learning neural network. The model is used to analyze and process the data to obtain temperature warning and adjustment information, and the temperature is adjusted in real time using adaptive PID control according to the analysis results, and an alarm signal is sent to the mobile phone APP to remind the operator according to the warning information. The present invention can respond to temperature changes quickly and accurately, improve control accuracy, avoid damage to equipment components due to excessively high temperature, shorten equipment service life and increase maintenance costs, and prevent energy utilization efficiency from being reduced due to excessively low temperature, thereby improving the stability and economy of the entire production system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0018] Figure 1 The present invention provides a flow chart of the method. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] The embodiment of the present invention discloses a temperature control method for an air preheater, such as Figure 1 As shown, including: Collect temperature data of different parts in the air preheater in real time to form a temperature data set; Establishing a temperature data analysis model to analyze and process the temperature data set to obtain analysis results, wherein the analysis results include temperature warning information and temperature adjustment information; According to the analysis results, the temperature of the air preheater is adjusted in real time using adaptive PID control; An alarm signal is generated based on the temperature warning information and sent to the mobile phone APP, which immediately reminds the operator to take measures.

[0021] In a specific embodiment, the temperature data collected in real time is normalized, which specifically includes:

[0022] Where Z represents the normalized temperature value, T min represents the minimum temperature value in the data set, T max represents the maximum temperature value in the data set, T Represents the original temperature value to be normalized. The normalized value ranges from [0,1].

[0023] In a specific embodiment, the establishing of the temperature data analysis model specifically includes: Through deep learning neural network, a temperature data analysis model is established. The historical temperature data is set to contain observation values ​​of n time steps, and X is used to represent the input feature vector. Represents the corresponding temperature prediction value, which specifically includes the following steps: Input layer: Use historical temperature data as input feature vector, and the calculation formula is as follows: X =[ x 1 ，x 2 ，...，x n ]; in, X represents the input feature vector, x 1, x 2, ... , x n Represents historical temperature data; Hidden layer: Design multiple hidden layers according to requirements and select the sigmoid activation function. The specific calculation formula is as follows: First hidden layer:

[0024] Second hidden layer: ... The kth hidden layer:

[0026] in, represents the activation function, W k and b k Indicates k The weights and biases of the hidden layers, h k Indicates k Output of the hidden layer; Output layer: Output temperature prediction value. The specific calculation formula is as follows: ; in, represents the predicted temperature value, ( ) represents the activation function of the output layer, W k+1 and b k+1 represents the weight and bias of the (k+1)th hidden layer, h k represents the output of the kth hidden layer; Model training: Use time-marked historical temperature data for model training. Historical temperature data represents the temperature value records over a period of time in the past. Use the gradient descent method to minimize the loss function to adjust the weights and bias parameters of the neural network model.

[0027] The use of gradient descent method specifically includes: a: define the loss function; b: calculate the gradient; c: Update model parameters, weights and bias update formulas; d: Iteratively repeat the above steps until the loss function is minimized.

[0028] The loss function is specifically: ; In the formula, L ( W , b ) represents the mean square error loss function, W and b are the weight and bias of the model respectively, m represents the number of samples, y Indicates the actual temperature value. represents the predicted temperature value; The gradient is calculated as: ; in, and They represent the gradient of the loss function with respect to the weight matrix and bias vector of the hidden layer respectively.

[0029] The weight and bias update formulas are as follows: ; In the formula, W' and b' denote weight update and bias update respectively, W and b are the weight and bias of the model, respectively. and They represent the gradient of the loss function to the weight matrix and bias vector of the hidden layer, respectively. α is the learning rate, which controls the step size of each update.

[0030] In a specific embodiment, the analysis process includes: The temperature data analysis model is used to obtain the air preheater temperature prediction data; According to the air preheater temperature prediction data and the preset maximum temperature threshold and minimum temperature threshold, it is judged whether the air preheater temperature is abnormal. If the air preheater temperature prediction data is between the maximum temperature threshold and the minimum temperature threshold, the air preheater temperature is normal; If the air preheater temperature prediction data is higher than the maximum temperature threshold or the air preheater temperature prediction data is lower than the minimum temperature threshold, the air preheater temperature is abnormal and a temperature warning message is generated; According to the air preheater temperature prediction data, the air preheater temperature is dynamically adjusted until the air preheater temperature prediction value is between the maximum temperature threshold and the minimum temperature threshold, and the temperature adjustment information is obtained.

[0031] Specifically, it may also include visualizing the real-time monitoring data of the air preheater temperature and the air preheater temperature adjustment information to obtain the visualized data of the air preheater temperature; According to the air preheater temperature visualization data, determine whether the air preheater temperature regulation is abnormal. If so, output and display the air preheater temperature regulation warning information. If not, record the air preheater temperature visualization data.

[0032] Specifically, it includes: visualizing the real-time monitoring data of the air preheater temperature and the air preheater temperature adjustment information to obtain the air preheater temperature adjustment curve, wherein the air preheater temperature adjustment curve includes the real-time monitoring data curve of the air preheater temperature, the air preheater temperature early warning point information and the air preheater temperature adjustment point information; According to the air preheater temperature adjustment curve, the air preheater adjustment temperature data is obtained to determine whether the air preheater temperature is still in the warning state. If so, the air preheater temperature adjustment is abnormal. If not, the air preheater temperature adjustment frequency information is obtained according to the air preheater temperature adjustment curve. Based on actual usage requirements, obtain the air preheater temperature adjustment frequency threshold; According to the air preheater temperature adjustment frequency information and the air preheater temperature adjustment frequency threshold, determine whether the air preheater temperature adjustment frequency information exceeds the air preheater temperature adjustment frequency threshold. If so, the air preheater temperature adjustment is abnormal. If not, the air preheater temperature adjustment frequency information is recorded.

[0033] In this solution, the real-time monitoring data of the air preheater temperature and the temperature adjustment information of the air preheater are visualized, and the temperature warning points and warning information are displayed in the displayed real-time change curve of the air preheater temperature, and the temperature adjustment points and adjustment information are displayed. According to the temperature change of the air preheater after the temperature adjustment, it is judged whether the temperature adjustment is abnormal. At the same time, the temperature adjustment frequency is analyzed to judge whether the temperature adjustment frequency is too high, so as to avoid the failure to adjust the air preheater temperature in time due to abnormal temperature adjustment and avoid the waste of resources caused by excessive temperature adjustment frequency.

[0034] Specifically, set the temperature threshold: analyze the historical data of the air preheater temperature, calculate the mean and standard deviation, and set the temperature threshold according to the trend of temperature change. The specific steps are as follows: The mean and standard deviation are calculated based on historical data. The specific calculation formula is as follows: ; in, represents the average temperature, represents the standard deviation, represents each sample value of the historical temperature data, and n represents the number of historical data; The temperature threshold formula is as follows: ; in, Indicates the maximum temperature threshold, Indicates the minimum temperature threshold.

[0035] In a specific embodiment, the specific formula of adaptive PID control is: ; in, represents the output of adaptive PID control, x represents the working time of air preheater, represents the proportional gain, represents the integral gain, represents the differential gain, , and represents the adaptive factor, Indicates the absolute value. represents the error of the system, It represents the integral of the deviation between the target control value and the actual control value.

[0036] When operators see the warning information, they can take the following measures: Check the equipment operation status: Check the relevant parts of the air preheater according to the abnormal temperature indicated by the warning. If the temperature is too high, check whether there are any deformation or damage signs of the parts due to overheating, and check whether the cooling system is working properly; if the temperature is too low, check whether there are any problems with the heating device and insulation layer.

[0037] Operate according to the adjustment information: operate the temperature adjustment device of the air preheater according to the temperature adjustment information given by the system, which may involve adjusting the heating power, cooling medium flow, ventilation volume, etc., to restore the air preheater temperature to a normal range.

[0038] Record relevant data: record in detail the time when the warning occurred, abnormal temperature (too high or too low, specific temperature values), operating measures taken and operating time, etc., to provide information for subsequent equipment maintenance and data analysis.

[0039] A temperature control system for an air preheater, comprising: The data acquisition module collects temperature data of different parts in the air preheater in real time to form a temperature data set; A data analysis module, which establishes a temperature data analysis model to analyze and process the temperature data set to obtain analysis results, wherein the analysis results include temperature warning information and temperature adjustment information; The temperature adjustment module uses adaptive PID control to adjust the air preheater temperature in real time according to the analysis results; The temperature warning module generates an alarm signal based on the temperature warning information and sends it to the mobile phone APP. The mobile phone APP immediately reminds the operator to take measures.

[0040] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0041] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one 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 present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A temperature control method for an air preheater, characterized in that: include: Collect temperature data of different parts in the air preheater in real time to form a temperature data set; Establishing a temperature data analysis model to analyze and process the temperature data set to obtain analysis results, wherein the analysis results include temperature warning information and temperature adjustment information; According to the analysis results, the temperature of the air preheater is adjusted in real time using adaptive PID control; An alarm signal is generated based on the temperature warning information and sent to the mobile phone APP, which immediately reminds the operator to take measures.

2. A temperature control method for an air preheater according to claim 1, characterized in that: It also includes normalization of the temperature data collected in real time, including: ； Where Z represents the normalized temperature value, T min represents the minimum temperature value in the data set, T max represents the maximum temperature value in the data set, T Represents the original temperature value to be normalized. The normalized value ranges from [0,1].

3. A temperature control method for an air preheater according to claim 1, characterized in that: The establishment of the temperature data analysis model specifically includes: Through deep learning neural network, a temperature data analysis model is established. The historical temperature data is set to contain observation values ​​of n time steps, and X is used to represent the input feature vector. Represents the corresponding temperature prediction value, which specifically includes the following steps: Input layer: historical temperature data is used as input feature vector; Hidden layer: Design multiple hidden layers according to requirements and select sigmoid activation function; Output layer: output temperature prediction value; Model training: Use time-marked historical temperature data for model training. Historical temperature data represents the temperature value records over a period of time in the past. Use the gradient descent method to minimize the loss function to adjust the weights and bias parameters of the neural network model.

4. A temperature control method for an air preheater according to claim 1, characterized in that: The analysis process includes: The temperature data analysis model is used to obtain the air preheater temperature prediction data; According to the air preheater temperature prediction data and the preset maximum temperature threshold and minimum temperature threshold, it is judged whether the air preheater temperature is abnormal. If the air preheater temperature prediction data is between the maximum temperature threshold and the minimum temperature threshold, the air preheater temperature is normal; If the air preheater temperature prediction data is higher than the maximum temperature threshold or the air preheater temperature prediction data is lower than the minimum temperature threshold, the air preheater temperature is abnormal and a temperature warning message is generated; According to the air preheater temperature prediction data, the air preheater temperature is dynamically adjusted until the air preheater temperature prediction value is between the maximum temperature threshold and the minimum temperature threshold, and the temperature adjustment information is obtained.

5. A temperature control method for an air preheater according to claim 3, characterized in that: The use of the gradient descent method specifically includes: a: define the loss function; b: calculate the gradient; c: Update model parameters, weights and bias update formulas; d: Iteratively repeat the above steps until the loss function is minimized.

6. A temperature control method for an air preheater according to claim 5, characterized in that: The loss function is specifically: ； In the formula, L ( W , b ) represents the mean square error loss function, W and b are the weight and bias of the model, respectively. m represents the number of samples, y Indicates the actual temperature value. represents the predicted temperature value; The gradient is calculated as: ； in, and They represent the gradient of the loss function with respect to the weight matrix and bias vector of the hidden layer respectively.

7. A temperature control method for an air preheater according to claim 5, characterized in that: The weight and bias update formulas are as follows: ； In the formula, W' and b' denote weight update and bias update respectively, W and b are the weight and bias of the model respectively, and They represent the gradient of the loss function to the weight matrix and bias vector of the hidden layer, respectively. α is the learning rate, which controls the step size of each update.

8. A temperature control method for an air preheater according to claim 1, characterized in that: The specific formula of the adaptive PID control is: ； in, represents the output of adaptive PID control, x represents the working time of air preheater, represents the proportional gain, represents the integral gain, represents the differential gain, , and represents the adaptive factor, It means to find the absolute value. represents the error of the system, It represents the integral of the deviation between the target control value and the actual control value.

9. A temperature control system for an air preheater, characterized in that: A temperature control method for an air preheater according to any one of claims 1 to 8, comprising: The data acquisition module collects temperature data of different parts in the air preheater in real time to form a temperature data set; A data analysis module, which establishes a temperature data analysis model to analyze and process the temperature data set to obtain analysis results, wherein the analysis results include temperature warning information and temperature adjustment information; The temperature adjustment module uses adaptive PID control to adjust the air preheater temperature in real time according to the analysis results; The temperature warning module generates an alarm signal based on the temperature warning information and sends it to the mobile phone APP. The mobile phone APP immediately reminds the operator to take measures.

Images