Analysis method and system for preventing overtemperature of coal-fired boiler tube

Abstract

The invention discloses an analysis method and system for preventing overtemperature of a coal-fired boiler tube, and the method comprises the steps: collecting the operation parameter data of steam temperature, hearth temperature, pressure, fuel flow and feed water flow in a boiler in real time, and collecting the external environment data of environment temperature and humidity; preprocessing the operation parameter data and the external environment data; based on the historical operation data, the preprocessed operation parameter data and the external environment data, a machine learning algorithm is used for constructing a boiler temperature prediction model, and model training is carried out; and inputting the boiler pipe wall temperature value which is acquired and preprocessed in real time into the trained boiler temperature prediction model to obtain a boiler temperature value predicted in real time, and performing overtemperature risk analysis in combination with a preset boiler safety temperature threshold. The system comprises a data acquisition and collection module, a data preprocessing module, a prediction model building and training module and an overtemperature risk analysis module. According to the method, the boiler overtemperature condition is accurately predicted and effectively prevented.

Description

Technical Field

[0001] The present invention belongs to the technical field of coal-fired power plant boilers, and particularly relates to an analysis method and system for preventing over-temperature of coal-fired boiler tubes. Background Art

[0002] Boilers are widely used in industrial production, domestic heating and other fields. However, the phenomenon of boiler over-temperature occurs from time to time. Over-temperature not only affects the normal operation efficiency of the boiler, shortens the service life of the equipment, but may even cause safety accidents such as explosions in severe cases, posing a great threat to the lives and property safety of personnel. At present, most of the existing methods for preventing boiler over-temperature only rely on simple monitoring and control of a single parameter, lacking comprehensive and dynamic analysis of multiple factors in boiler operation, resulting in the inability to accurately and timely predict and prevent over-temperature situations. Therefore, there is an urgent need for a more scientific and comprehensive analysis method for preventing boiler over-temperature. Compared with traditional methods for boiler tube over-temperature, the following problems exist: Long-term over-temperature will accelerate the aging of boiler materials, resulting in deformation or cracking of components such as pipelines and furnace chambers. Over-temperature affects the heat exchange efficiency, increases fuel consumption, and reduces operating economy. Relying on threshold alarms, it is impossible to predict early abnormal trends. Summary of the Invention

[0003] The purpose of the present invention is to provide an analysis method and system for preventing over-temperature of coal-fired boiler tubes, which solves the problems in the prior art that there are a large number of boiler tubes, which are widely dispersed, and it is impossible to timely and effectively detect abnormalities, lacking intuitive monitoring of the status and life of each furnace tube. By comprehensively considering various factors affecting the boiler temperature, accurate prediction and effective prevention of boiler over-temperature are realized, and the safety and stability of boiler operation are improved.

[0004] In order to achieve the above purpose, the present invention adopts the following technical solutions: An analysis method for preventing over-temperature of coal-fired boiler tubes, comprising: Real-time collecting operation parameter data of steam temperature, furnace temperature, pressure, fuel flow rate and feed water flow rate inside the boiler, and collecting external environment data of ambient temperature and humidity; Preprocessing the operation parameter data and external environment data; Based on historical operation data, preprocessed operation parameter data and external environment data, using machine learning algorithms to construct a boiler temperature prediction model and perform model training; Inputting the preprocessed real-time collected boiler tube wall temperature value into the trained boiler temperature prediction model to obtain a real-time predicted boiler temperature value, and combining with a pre-set boiler safety temperature threshold to perform over-temperature risk analysis.

[0005] A further improvement of the present invention lies in that when collecting the operation parameter data of steam temperature, furnace temperature, pressure, fuel flow rate and feed water flow rate in the boiler in real time, it is obtained by using temperature sensors, pressure sensors and flow sensors distributed in different parts of the boiler.

[0006] A further improvement of the present invention lies in that preprocessing is performed on the operation parameter data and external environment data, including: Filtering the operation parameter data of steam temperature, furnace temperature, pressure, fuel flow rate and feed water flow rate collected in real time in the boiler, as well as collecting the external environment data of ambient temperature and humidity, to remove abnormal data points caused by sensor errors and interference; adopting a normalization method to convert various data with different dimensions into a unified numerical interval for subsequent analysis.

[0007] A further improvement of the present invention lies in that the machine learning algorithm adopts a neural network algorithm.

[0008] A further improvement of the present invention lies in that the input of the boiler temperature prediction model is the preprocessed operation parameter data and external environment data, and the output is the predicted boiler temperature value; during the model training process, the model parameters are continuously adjusted to minimize the error between the predicted value and the actual value to improve the accuracy of the model.

[0009] A further improvement of the present invention lies in that when performing over-temperature risk analysis, if the predicted temperature is close to or exceeds the safety temperature threshold, by comparing the current operation parameters with the historical normal operation data, analyze the factors that may cause over-temperature, including excessive fuel flow rate, insufficient feed water flow rate and abnormal heat dissipation.

[0010] A further improvement of the present invention lies in that it further includes: when analyzing the over-temperature risk and its causes, immediately issue a warning signal, and automatically or manually adjust the relevant operation parameters according to the analysis results.

[0011] An analysis system for preventing over-temperature of coal-fired boiler tubes, comprising: A data acquisition and collection module for collecting the operation parameter data of steam temperature, furnace temperature, pressure, fuel flow rate and feed water flow rate in the boiler in real time, and collecting the external environment data of ambient temperature and humidity; A data preprocessing module for preprocessing the operation parameter data and external environment data; A prediction model construction and training module for constructing a boiler temperature prediction model based on historical operation data, preprocessed operation parameter data and external environment data, and using a machine learning algorithm, and performing model training; An over-temperature risk analysis module for inputting the preprocessed boiler tube wall temperature value collected in real time into the trained boiler temperature prediction model to obtain the real-time predicted boiler temperature value, and combining with the preset boiler safety temperature threshold to perform over-temperature risk analysis.

[0012] A further improvement of the present invention lies in that in the data acquisition and collection module, when real-time collecting operation parameter data such as steam temperature, furnace temperature, pressure, fuel flow rate, and feed water flow rate in the boiler, it is obtained by using temperature sensors, pressure sensors, and flow sensors distributed in different parts of the boiler.

[0013] A further improvement of the present invention lies in that in the data preprocessing module, preprocessing is performed on the operation parameter data and external environment data, including: Performing filtering processing on the real-time collected operation parameter data of steam temperature, furnace temperature, pressure, fuel flow rate, and feed water flow rate in the boiler, as well as the collected external environment data of ambient temperature and humidity, to remove abnormal data points caused by sensor errors and interference; adopting a normalization method to convert various data with different dimensions into a unified numerical interval for subsequent analysis.

[0014] Compared with the prior art, the present invention has at least the following beneficial technical effects: An analysis method and system for preventing overheating of coal-fired boiler tubes provided by the present invention can comprehensively collect a variety of operation parameters and external environment data, and use machine learning algorithms to construct a prediction model, which can more comprehensively and accurately predict the temperature change trend of the boiler. Compared with the traditional single-parameter monitoring method, the accuracy of overheating prediction is greatly improved.

[0015] Furthermore, the real-time analysis and early warning regulation mechanism can quickly respond when the overheating risk appears, timely adjust the boiler operation parameters, effectively prevent the occurrence of boiler overheating phenomenon, ensure the safe and stable operation of the boiler, reduce the risk of safety accidents, and extend the service life of the boiler equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 It is the overall flowchart for the treatment of boiler tube overheating.

[0018] Figure 2 It is the calculation flowchart for boiler tube overheating.

[0019] Figure 3 It is the real-time temperature monitoring list.

[0020] Figure 4 It is the schematic diagram of the wall temperature map page.

[0021] Figure 5 It is a wall temperature trend chart.

[0022] Figure 6 It is a schematic diagram summarizing the history of metal overtemperature.

[0023] Figure 7 It is a schematic diagram showing the details of metal overtemperature.

[0024] Figure 8 It is a structural block diagram of an analysis system for preventing overtemperature of coal - fired boiler tubes according to the present invention. Detailed implementation manners

[0025] In the following, only some exemplary embodiments are briefly described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the spirit or scope of the present invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0026] It should be understood that when used in this specification and the appended claims, the terms "comprises" and "comprising" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0027] It should also be understood that the terms used in the specification of the present invention are for the purpose of describing particular embodiments only and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0028] It should be further understood that the term "and / or" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0029] Various structural schematic diagrams according to the disclosed embodiments of the present invention are shown in the drawings. These figures are not drawn to scale, where for the purpose of clear expression, some details are enlarged and some details may be omitted. The shapes of various regions and layers shown in the figures and their relative sizes and positional relationships are only exemplary. In practice, there may be deviations due to manufacturing tolerances or technical limitations, and those skilled in the art can design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0030] The embodiments of the present invention will be described in detail below with reference to the drawings.

[0031] Embodiment 1 An analysis method for preventing overheating of coal-fired boiler tubes provided by the present invention includes: Data acquisition step: Using temperature sensors, pressure sensors, flow sensors, etc. distributed in different parts of the boiler to collect operation parameter data such as steam temperature, furnace temperature, pressure, fuel flow rate, feed water flow rate, etc. in the boiler in real time. At the same time, collect external environment data such as ambient temperature and humidity.

[0032] Data preprocessing step: Filter the collected original data to remove abnormal data points caused by sensor errors, interference, etc. Adopt the normalization method to convert various data with different dimensions into a unified numerical interval for subsequent analysis.

[0033] Model establishment step: Based on historical operation data and preprocessed data, use machine learning algorithms such as neural network algorithms to construct a boiler temperature prediction model. The inputs of the model are the above-mentioned collected and preprocessed various operation parameters and environment data, and the output is the predicted boiler temperature value. During the model training process, continuously adjust the model parameters to minimize the error between the predicted value and the actual value to improve the accuracy of the model.

[0034] Real-time analysis step: Input the real-time collected and preprocessed boiler tube wall temperature value into the trained prediction model to obtain the real-time predicted boiler temperature value. At the same time, combine the preset boiler safety temperature threshold to conduct overheating risk analysis. If the predicted temperature is close to or exceeds the safety temperature threshold, analyze the factors that may cause overheating by comparing the current operation parameters with the historical normal operation data, such as excessive fuel flow rate, insufficient feed water flow rate, abnormal heat dissipation, etc.

[0035] Early warning and regulation step: Once the overheating risk and its causes are analyzed, immediately issue an early warning signal, such as audible and visual alarms, etc. At the same time, automatically or manually adjust the relevant operation parameters according to the analysis results. For example, if it is analyzed that the excessive fuel flow rate causes the overheating risk, automatically reduce the fuel supply; if the feed water flow rate is insufficient, increase the feed water flow rate, so as to realize the timely regulation of the boiler temperature and prevent overheating.

[0036] Embodiment 2 An analysis method for preventing overheating of coal-fired boiler tubes provided by the present invention includes: 1. Data acquisition: On a certain type of industrial boiler, install temperature sensors at predetermined positions in the furnace, steam pipes, etc., install pressure sensors at positions such as the steam drum, and use flow sensors to measure fuel and feed water flow rates respectively. At the same time, install ambient temperature and humidity sensors in the boiler room. Set the data acquisition frequency to collect various data once every [X] seconds.

[0037] 2. Data preprocessing: The collected data is transmitted to the data processing unit. First, the median filtering algorithm is used to remove abnormal data points. For example, for temperature data, if a certain collected value deviates too much from the adjacent collected values before and after and does not fall within the normal fluctuation range, it is determined as an abnormal point and replaced with the median of the data before and after it. Then, the min-max normalization method is adopted to uniformly transform data with different dimensions such as steam temperature (the range is assumed to be [100 - 500] °C) and pressure (the range is assumed to be [0 - 10] MPa) into the [0, 1] interval.

[0038] 3. Model establishment: Use the data of one-year historical operation, with 70% as the training set and 30% as the test set. The multi-layer neural network algorithm is selected to construct the boiler temperature prediction model. The number of nodes in the input layer of the model corresponds to the number of various operating parameters and environmental data. The hidden layer is set with [X] layers, and the number of nodes in each layer is determined according to experience and multiple experiments. The number of nodes in the output layer is the predicted boiler temperature value. The weights and biases of the model are continuously adjusted through the backpropagation algorithm to minimize the mean square error between the predicted value and the actual value on the training set. After multiple iterative trainings, the accuracy of the model is verified on the test set. If the mean square error meets the predetermined accuracy requirements, the model training is completed.

[0039] 4. Real-time analysis: During the operation of the boiler, the preprocessed real-time collected boiler tube wall temperature values are input into the trained model to obtain the real-time predicted temperature. Assume that the safety temperature threshold is set at 540 °C. If the predicted temperature reaches 500 °C, the system automatically compares the current operating parameters with the parameter data close to 500 °C during historical normal operation, analyzes the changing trends of each parameter, and determines the factors that may cause overheating.

[0040] 5. Early warning and regulation: When the overheating risk factors are analyzed, such as determining that the fuel flow is too large, the system immediately emits an audible and visual alarm signal, and at the same time automatically adjusts the fuel valve to reduce the fuel flow, so that the boiler temperature returns to the safe range. Continuously monitor and dynamically adjust according to the actual temperature change to ensure the safe operation of the boiler at all times.

[0041] Monitoring of the overheating risk of boiler tubes Real-time overheating monitoring Through the real-time monitoring of the boiler tube wall temperature, it can be displayed in the form of a list, a wall temperature graph, and a trend graph.

[0042] Among them, Figure 3 is the real-time temperature monitoring list, Figure 4 is the wall temperature graph page, Figure 5 is the wall temperature trend graph.

[0043] Figure 3It is the real-time wall temperature monitoring list information of boiler tubes. The monitoring points are numbered to facilitate the identification and management of each monitoring location. Monitoring location: It details the specific installation position of the temperature sensor on the boiler tube wall, which helps to accurately locate and analyze the temperature change situation. Sensor number: The unique identifier of each temperature sensor, used to distinguish sensors at different positions, facilitating data collection and management. Real-time wall temperature: It shows the actual temperature value of the boiler tube wall at the current moment, which is the data measured and transmitted in real time by the temperature sensor. Measurement time: It records the collection time of the real-time wall temperature data, accurate to the specific year, month, day, hour, minute, and second, in order to analyze the temperature change law over time. Normal temperature range: According to the design parameters and operation experience of the boiler, the normal operating temperature range is set for each monitoring location, which is the basis for judging whether the tube wall temperature is abnormal.

[0044] Figure 4 and Figure 5 The process is as follows: The temperature sensor collects the wall temperature data in real time and transmits it to the data acquisition system. The collection frequency is usually determined according to the operation requirements and monitoring accuracy of the boiler, generally once per second or once per minute. Using professional monitoring software or data processing system, a wall temperature monitoring graph is drawn based on the collected data. The software will match the temperature data with the location information according to the preset algorithms and models to generate the corresponding graph.

[0045] Among them, Figure 6 is the historical summary of metal over-temperature, Figure 7 is the details of metal over-temperature. It is drawn based on the data collected by the temperature sensor and reflects the change trend of the metal temperature over time. Each point on the curve represents the metal temperature value measured at the corresponding time point. One or more temperature threshold lines are set according to the characteristics of the metal material and the safety requirements of boiler operation. When the temperature curve exceeds these threshold lines, it indicates that the metal component is in an over-temperature state.

[0046] Embodiment 3 As Figure 8 shown, an analysis system for preventing over-temperature of coal-fired boiler tubes provided by the present invention includes: The data acquisition and collection module is used to collect the operation parameter data of the steam temperature, furnace temperature, pressure, fuel flow rate, and feed water flow rate in the boiler in real time, and collect the external environment data of the ambient temperature and humidity; The data preprocessing module is used to preprocess the operation parameter data and external environment data; The prediction model construction and training module is used to construct a boiler temperature prediction model based on the historical operation data, preprocessed operation parameter data, and external environment data, and perform model training by using machine learning algorithms; The over-temperature risk analysis module is used to input the real-time collected and preprocessed boiler tube wall temperature values into the trained boiler temperature prediction model to obtain the real-time predicted boiler temperature values, and combine them with the preset boiler safety temperature threshold to conduct over-temperature risk analysis.

[0047] In this embodiment, in the data acquisition and collection module, when real-time collecting the operation parameter data of the steam temperature, furnace temperature, pressure, fuel flow rate, and feed water flow rate in the boiler, it is obtained by using temperature sensors, pressure sensors, and flow sensors distributed in different parts of the boiler.

[0048] In this embodiment, in the data preprocessing module, preprocess the operation parameter data and external environment data, including: Filter the real-time collected operation parameter data of the steam temperature, furnace temperature, pressure, fuel flow rate, and feed water flow rate in the boiler, as well as the collected external environment data of the ambient temperature and humidity, to remove abnormal data points caused by sensor errors and interference; adopt the normalization method to convert various data with different dimensions into a unified numerical interval for subsequent analysis.

[0049] To avoid over-temperature of the boiler tubes, the following adjustment measures can be taken: 1. Balance the temperatures on both sides: Ensure that the temperature difference at the furnace outlet on the left and right sides of the boiler does not exceed the specified value (such as not exceeding 50°C), and adjust the burner damper or fuel supply amount to balance the furnace heat load.

[0050] 2. Operate at a stable load: Try to maintain the unit operating at a stable load level and avoid frequent large increases and decreases in load, because rapid changes in load are likely to cause violent fluctuations in the metal wall temperature.

[0051] 3. Monitor the temperature accurately: Real-time monitor the wall temperature changes at each point of the screen pass (superheater or reheater). Once a trend of over-temperature is found, immediately take measures to adjust.

[0052] 4. Adjust the coal feeding method: Adjust the coal feeding strategy according to the wall temperature situation, such as appropriately reducing the coal amount of the coal feeder in the middle of the furnace to control the metal tube wall temperature of the middle heating surface.

[0053] 5. Control the air volume and fluidization height: Reasonably adjust the primary air volume and reduce the fluidization height of the fluidized bed, which helps to reduce the flue gas temperature in the screen pass area and thus control the wall temperature.

[0054] 6. Use desuperheating water: Timely turn on or adjust the desuperheating water system, inject an appropriate amount of low-temperature water into the superheated steam to directly reduce the steam temperature and avoid over-temperature of the superheater.

[0055] 7. Optimize combustion: Fine-tune the ratio of fuel to air to achieve efficient and moderately temperature combustion and avoid local overheating.

[0056] 8. Improve heat exchange efficiency: Regularly clean the heated surface to remove ash deposits and scale, improve heat exchange efficiency, and reduce excessive local heat load.

[0057] 9. Adjust steam flow rate: By changing the pipeline configuration or installing throttling devices, balance the steam flow rate of each heated surface to avoid overheating caused by too low flow rate.

[0058] 10. Technical transformation: When necessary, according to the actual operation conditions of the boiler, carry out technical transformation, such as changing the pipeline connection method, increasing the pipe diameter or installing throttle orifice plates, etc., to improve the steam flow rate distribution and control the wall temperature.

[0059] The foregoing has shown and described the basic principles, main features and advantages of the present invention. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and without departing from the spirit or basic features of the present invention, the present invention can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to embrace all changes within the meaning and scope of the equivalent elements of the claims in the present invention. Any reference signs in the claims should not be construed as limiting the claimed invention.

[0060] In addition, it should be understood that although this specification is described in terms of embodiments, not every embodiment only contains an independent technical solution. This narrative way of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of the present invention, and the protection scope of the present invention cannot be limited thereby. Any modification made on the basis of the technical solution according to the technical idea proposed by the present invention falls within the protection scope of the claims of the present invention.

Claims

1. An analysis method for preventing over-temperature of coal-fired boiler tubes, characterized in that, Including: Collecting in real time the operation parameter data of steam temperature, furnace temperature, pressure, fuel flow rate and feed water flow rate in the boiler, and collecting the external environment data of ambient temperature and humidity; Preprocessing the operation parameter data and external environment data; Based on the historical operation data, preprocessed operation parameter data and external environment data, using machine learning algorithms to construct a boiler temperature prediction model and conduct model training; Inputting the preprocessed boiler tube wall temperature value collected in real time into the trained boiler temperature prediction model to obtain the real-time predicted boiler temperature value, and combining with the preset boiler safety temperature threshold to conduct over-temperature risk analysis.

2. The analysis method for preventing over-temperature of coal-fired boiler tubes according to claim 1, characterized in that When collecting in real time the operation parameter data of steam temperature, furnace temperature, pressure, fuel flow rate and feed water flow rate in the boiler, it is obtained by using temperature sensors, pressure sensors and flow sensors distributed in different parts of the boiler.

3. The analysis method for preventing over-temperature of coal-fired boiler tubes according to claim 1, characterized in that, Preprocessing the operation parameter data and external environment data includes: Filtering the operation parameter data of steam temperature, furnace temperature, pressure, fuel flow rate and feed water flow rate collected in real time in the boiler, and the external environment data of ambient temperature and humidity collected, to remove abnormal data points caused by sensor errors and interference; adopting a normalization method to convert various data with different dimensions into a unified numerical interval for subsequent analysis.

4. The analysis method for preventing over-temperature of coal-fired boiler tubes according to claim 1, characterized in that The machine learning algorithm adopts a neural network algorithm.

5. The analysis method for preventing over-temperature of coal-fired boiler tubes according to claim 1, characterized in that, The input of the boiler temperature prediction model is the preprocessed operation parameter data and external environment data, and the output is the predicted boiler temperature value; during the model training process, continuously adjust the model parameters to minimize the error between the predicted value and the actual value to improve the accuracy of the model.

6. The analysis method for preventing overheating of coal-fired boiler tubes according to claim 1, characterized in that, When conducting over-temperature risk analysis, if the predicted temperature is close to or exceeds the safety temperature threshold, by comparing the current operation parameters with the historical normal operation data, analyze the factors that may cause over-temperature, including excessive fuel flow rate, insufficient feed water flow rate and abnormal heat dissipation.

7. An analysis method for preventing overheating of coal-fired boiler tubes according to claim 6, characterized in that, Also including: When analyzing the over-temperature risk and its causes, immediately issue a warning signal, and automatically or manually adjust the relevant operation parameters according to the analysis results.

8. An analysis system for preventing overheating of coal-fired boiler tubes, characterized in that, Including: A data acquisition and collection module for collecting in real time the operation parameter data of steam temperature, furnace temperature, pressure, fuel flow rate and feed water flow rate in the boiler, and collecting the external environment data of ambient temperature and humidity; A data preprocessing module for preprocessing the operation parameter data and external environment data; A prediction model construction and training module for constructing a boiler temperature prediction model and conducting model training based on the historical operation data, preprocessed operation parameter data and external environment data by using machine learning algorithms; An over-temperature risk analysis module for inputting the preprocessed boiler tube wall temperature value collected in real time into the trained boiler temperature prediction model to obtain the real-time predicted boiler temperature value, and combining with the preset boiler safety temperature threshold to conduct over-temperature risk analysis.

9. The analysis system for preventing over-temperature of coal-fired boiler tubes according to claim 8, wherein, In the data acquisition and collection module, when collecting in real time the operation parameter data of steam temperature, furnace temperature, pressure, fuel flow rate and feed water flow rate in the boiler, it is obtained by using temperature sensors, pressure sensors and flow sensors distributed in different parts of the boiler.

10. The analysis system for preventing overheating of coal-fired boiler tubes according to claim 8, characterized in that, In the data preprocessing module, the operating parameter data and external environment data are preprocessed, including: Filter the operation parameter data of steam temperature, furnace temperature, pressure, fuel flow rate, and feed water flow rate in the boiler collected in real time, as well as the external environment data of ambient temperature and humidity collected, to remove abnormal data points caused by sensor errors and interference; adopt the normalization method to convert various data with different dimensions into a unified numerical range for subsequent analysis.

Images