Infrared imaging monitoring system of air pre-heater

By combining abnormal detection, temperature change rate and clustering algorithm in the air preloader monitoring system, combined with distributed monitoring and predictive control, the problems of high false alarm rate and lack of prediction capabilities of existing systems are solved, and high accuracy is achieved and stability of blockage detection and prevention reduces maintenance costs and downtime risks.

CN119043498APending Publication Date: 2024-11-29NANJING YUHUA INTELLIGENT TECH CO LTD

Patent Information

Application Number
CN202411177540.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-26
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The infrared imaging monitoring system of existing air preloaders relies on a single temperature threshold judgment and is susceptible to environmental noise and measurement errors, resulting in high false alarm rates and lack of prediction capabilities, making it difficult to deal with abnormal conditions in advance, resulting in equipment downtime and high maintenance costs.

Method used

Adopt a multi-level and multi-dimensional comprehensive analysis system, combining anomaly detection algorithm, temperature change rate detection algorithm and clustering algorithm, and through distributed monitoring modules and predictive control, an intelligent operation adjustment mechanism is formed to achieve all-round monitoring and prediction. Sexual control.

Benefits of technology

It significantly improves the accuracy and reliability of blockage detection, reduces maintenance costs and downtime, improves the safety and stability of system operation, and ensures that the equipment is always operating in the optimal state.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119043498A_ABST
    Figure CN119043498A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of thermal equipment monitoring, and discloses an infrared imaging monitoring system of an air pre-heater, which comprises an infrared imaging module, a data processing module, a storage and recording module, a display and alarm module, a control and feedback module, a distributed monitoring module and a remote monitoring and management module, the infrared imaging module is used for acquiring surface temperature images of different areas of the air pre-heater; the data processing module is used for analyzing the temperature image acquired by the infrared imaging module and performing fusion analysis in combination with data of multiple detection modes; and the storage and recording module is used for storing temperature image data and analysis results, and storing and managing historical data. Through combination of anomaly detection, temperature change rate detection and a clustering algorithm, the system can accurately identify and position the blockage area of the air pre-heater, the accuracy of blockage detection is effectively improved through multi-dimensional analysis, false alarms are reduced, and the safety and stability of system operation are ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of thermal equipment monitoring, in particular to an infrared imaging monitoring system for an air preheater. Background Art

[0002] The infrared imaging monitoring system of the air preheater is an advanced monitoring technology specially used to monitor and manage the operating status of the air preheater (air preheater). The system collects temperature data on the surface of the equipment in real time through infrared cameras installed at key positions of the air preheater, and converts these data into thermal imaging images. Through monitoring and analysis of temperature distribution, the system can fully understand the heat exchange effect of the air preheater, and help operators to grasp the operating status of the equipment in a timely manner through intuitive thermal images. The monitoring system usually includes data processing, storage, display and alarm modules, which can display temperature information in real time and issue alarms when abnormal temperature changes are detected. Through continuous monitoring and data analysis, the system provides a scientific basis for equipment maintenance and helps to improve the operating efficiency and safety of the air preheater. However, there are still some problems that need to be solved in the actual use of the existing infrared imaging monitoring system for air preheaters.

[0003] First, traditional air preheater monitoring systems often rely on a single temperature threshold to identify blockage problems. This method is easily affected by environmental noise and measurement errors, resulting in a high false alarm rate and insufficient accuracy. In addition, a single monitoring method is difficult to fully capture the complex pattern of temperature anomalies, and it is easy to miss early signs of blockage, resulting in failure to prevent failures in time, which may eventually lead to unplanned equipment downtime and high maintenance costs.

[0004] Secondly, in traditional air preheater control systems, the adjustment of operating parameters is usually a passive response method based on real-time feedback, which makes it difficult to respond to impending abnormal conditions in advance. Due to the lack of predictive capabilities, the system can only be adjusted after a fault occurs, which often leads to delayed discovery and resolution of blockage problems, increasing the risk of equipment downtime and maintenance costs. At the same time, simple feedback adjustment strategies are difficult to ensure the optimal operating state of the system under various complex working conditions.

[0005] Finally, most traditional air preheater monitoring systems use centralized data collection and processing methods, which have problems such as limited monitoring coverage, untimely data collection, and monitoring blind spots. In large or complex air preheater equipment, this centralized architecture is difficult to effectively cover all key areas, resulting in temperature anomalies or blockages in some local areas that cannot be detected in time. At the same time, when some sensors or acquisition units fail, the reliability of the entire system will be greatly affected, increasing the operating risk of the system. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides an infrared imaging monitoring system for an air preheater, which solves the problem that the system relies on a single temperature threshold to identify blockages and is prone to errors.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: an infrared imaging monitoring system for an air preheater, comprising an infrared imaging module, a data processing module, a storage and recording module, a display and alarm module, a control and feedback module, a distributed monitoring module and a remote monitoring and management module;

[0008] The infrared imaging module is used to obtain surface temperature images of different areas of the air preheater;

[0009] The data processing module is used to analyze the temperature image acquired by the infrared imaging module and perform fusion analysis in combination with data from multiple detection modes;

[0010] The storage and recording module is used to store temperature image data and analysis results, and to store and manage historical data;

[0011] The display and alarm module is used to display the monitoring results in real time and issue an alarm when an abnormality is detected by the algorithm;

[0012] The algorithm specifically includes an anomaly detection algorithm, a temperature change rate detection algorithm, and a clustering algorithm;

[0013] The anomaly detection algorithm formula is:

[0014]

[0015] Among them, X is the current temperature value, μ is the historical average temperature of the area, σ is the historical standard deviation of the area, and Z is considered abnormal if it is greater than ±3;

[0016] The temperature change rate detection algorithm formula is:

[0017] y=ax+b

[0018] Where y is the temperature value, xx is the time, and a is the rate of temperature change. If the absolute value a is greater than the set threshold, it is judged as a rate abnormality.

[0019] The clustering algorithm uses the following steps:

[0020] S1, collect data of multiple temperature points;

[0021] S2, cluster these data with K, and set an appropriate number of clusters K;

[0022] S3, judging K, if the temperature of a certain K deviates from the central value of other K, it is judged to be abnormal;

[0023] The control and feedback module is used to adjust the operating parameters of the air preheater according to the monitoring results and perform predictive control;

[0024] The distributed monitoring module is used to collect, process and analyze data from various areas inside the air preheater through multiple distributed intelligent nodes, and form a distributed monitoring network;

[0025] The remote monitoring and management module is used to remotely access and monitor the operating status of the system through the Internet and a dedicated network, allowing maintenance personnel and management personnel to perform remote fault diagnosis, parameter adjustment and data analysis.

[0026] Preferably, the infrared imaging module includes a multi-point infrared camera unit and a dynamic calibration unit;

[0027] The multi-point infrared camera unit is arranged in the key heat exchange area of ​​the air preheater to fully cover the temperature distribution inside the air preheater and is used to obtain temperature images of different areas;

[0028] The dynamic calibration unit is used to periodically calibrate the infrared camera unit through a built-in temperature reference source.

[0029] Preferably, the data processing module includes a multi-mode data fusion unit and an intelligent image processing unit;

[0030] The multi-mode data fusion unit is used to combine infrared imaging data with detection data of other modes such as sound waves, vibrations, and airflows for fusion analysis to improve the accuracy of abnormality identification;

[0031] The intelligent image processing unit is used to analyze the temperature image using a deep learning algorithm, identify and locate the temperature abnormality area, and further verify the abnormal situation in combination with data from other modes;

[0032] The deep learning algorithm uses a loss function to evaluate the image. The specific formula is:

[0033]

[0034] Among them, x i is the input image, To reconstruct an image, x is a representation of the input image, usually a two-dimensional array, each element represents the value of a pixel in the image, and n is the total number of pixels in the input image.

[0035] Preferably, the storage and recording module includes a data storage unit, a data management unit, a data storage unit and a data management unit;

[0036] The data storage unit is used to store temperature images, monitoring data and analysis results, and supports query and comparative analysis of historical data;

[0037] The data management unit is used to manage the stored historical data, provide data compression and backup functions, and ensure long-term retention and fast access to data;

[0038] The data storage unit is used to store temperature images, monitoring data and analysis results, and supports query and comparative analysis of historical data;

[0039] The data management unit is used to manage the stored historical data and provide data compression and backup functions.

[0040] Preferably, the data management unit includes a data encryption unit and a data backup and recovery unit;

[0041] The data encryption unit is used to encrypt the stored data;

[0042] The data backup and recovery unit is used to regularly back up key data and quickly recover data when it is lost or damaged.

[0043] Preferably, the display and alarm module includes a real-time display unit and an intelligent alarm unit;

[0044] The real-time display unit is used to display the temperature distribution diagram and monitoring results in real time on the monitoring interface, providing a comprehensive display of multi-mode data;

[0045] The intelligent alarm unit is used to send out graded alarm signals according to the severity of the temperature anomaly and supports multiple notification methods of alarm information.

[0046] Preferably, the intelligent alarm unit includes a multi-level alarm strategy unit and a remote alarm notification unit;

[0047] The multi-level alarm strategy unit is used to dynamically adjust the alarm level and response strategy according to the monitored abnormality degree, duration and environmental conditions;

[0048] The remote alarm notification unit is used to send alarm information to remote maintenance personnel and management personnel via email, text message and mobile application when a major abnormality is detected.

[0049] Preferably, the control and feedback module includes a predictive control unit and a feedback adjustment unit;

[0050] The predictive control unit is used to establish a prediction model based on real-time monitoring data and historical trends to predict possible abnormalities and adjust the operating parameters of the air preheater in advance. The monitoring data includes temperature data, fan speed, flue gas flow, air pressure and humidity and equipment operating status. The historical trends include historical temperature change trends, historical fan speed trends, historical flue gas flow trends and operating event records. The operating parameters include fan speed and flue gas flow;

[0051] The prediction model establishment comprises the following steps:

[0052] S11, data acquisition: obtain the temperature data, fan speed, flue gas flow, air pressure, and humidity of the current air preheater operation from the system, and obtain the historical temperature data, fan speed, and flue gas flow key parameter change records of the air preheater under different operating conditions from the data storage module;

[0053] S22, data preprocessing: remove outliers and fill missing data from the acquired data, extract key features such as temperature change rate and flue gas flow fluctuation amplitude from real-time monitoring data and historical data, and finally standardize the data to eliminate dimensional differences between different features;

[0054] S33, select model: select one of the following models: ARI MA model, LSTM model and support vector regression model according to your needs;

[0055] S44, model training: first divide the historical data into training set and validation set, then use the training set to train the prediction model, and finally use the validation set to verify the accuracy of the model and adjust the model to avoid overfitting;

[0056] S55, model deployment: deploy the trained model to the system, use real-time monitoring data for prediction, and then judge the temperature anomaly and flue gas flow anomaly that may occur in the future based on the prediction results;

[0057] The feedback regulation unit is used to adjust the operating parameters according to the actual monitoring data and optimize the control strategy.

[0058] Preferably, the distributed monitoring module includes an intelligent node unit and a node communication unit:

[0059] The intelligent node unit is used to arrange multiple intelligent nodes inside and outside the air preheater, and these nodes have data collection, preliminary processing and analysis capabilities to form a distributed monitoring network;

[0060] The node communication unit is used to communicate data and analysis results between the intelligent nodes and with the central control unit.

[0061] Preferably, the infrared imaging module is electrically connected to the data processing module, the data processing module is electrically connected to the storage and recording module, the data processing module is electrically connected to the display and alarm module, the data processing module is electrically connected to the control and feedback module, the control and feedback module is electrically connected to the distributed monitoring module, the distributed monitoring module is electrically connected to the data processing module, the distributed monitoring module is electrically connected to the infrared imaging module, the storage and recording module is electrically connected to the remote monitoring and management module, the display and alarm module is electrically connected to the remote monitoring and management module, and the control and feedback module is electrically connected to the remote monitoring and management module.

[0062] The present invention provides an infrared imaging monitoring system for an air preheater. It has the following beneficial effects:

[0063] 1. The present invention forms a multi-level, multi-dimensional comprehensive analysis system by combining anomaly detection algorithm, temperature change rate detection algorithm and clustering algorithm. First, the anomaly detection algorithm can quickly identify abnormal points in temperature data and warn of possible operating abnormalities; secondly, the temperature change rate detection algorithm further analyzes the dynamic changes of temperature and detects areas with abnormal temperature changes; finally, through the clustering algorithm, the system can identify abnormal patterns of temperature distribution, further verify and locate blocked areas. This combination of multiple algorithms greatly improves the accuracy and reliability of air preheater blockage detection, can effectively prevent potential faults, reduce maintenance costs and downtime, and at the same time improve the safety of system operation.

[0064] 2. The present invention combines predictive control with feedback regulation to construct an intelligent operation adjustment mechanism. Through real-time monitoring data and analysis of historical trends, the predictive control unit can identify potential abnormal trends in advance and actively adjust the operating parameters of the air preheater, such as fan speed and flue gas flow, before the abnormality occurs, thereby effectively preventing the occurrence of problems such as blockage. The feedback regulation unit makes real-time adjustments based on the actual monitoring data to ensure that the system always remains in the optimal state during operation, thereby significantly improving the operating stability of the air preheater, reducing emergency shutdowns caused by blockage or other abnormalities, and also improving the overall efficiency of the equipment.

[0065] 3. The present invention introduces a distributed monitoring module, so that the system can use multiple distributed intelligent nodes to comprehensively monitor, process and analyze the data of various areas inside the air preheater. These intelligent nodes have local processing and preliminary analysis capabilities, and transmit and share real-time data with the central system through the network, forming an efficient distributed monitoring network. Through this distributed architecture, the system can achieve all-round, multi-point accurate monitoring, greatly improving the coverage and flexibility of data collection, and reducing the possibility of monitoring blind spots. At the same time, this architecture also improves the scalability and fault tolerance of the system, ensuring that the system can still maintain normal operation when some nodes fail, thereby further enhancing the reliability and stability of the air preheater monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is the module distribution diagram of the present invention;

[0067] Figure 2 is a schematic diagram of an infrared imaging module of the present invention;

[0068] Figure 3 It is a schematic diagram of a data processing module of the present invention;

[0069] Figure 4 It is a schematic diagram of the storage and recording module of the present invention;

[0070] Figure 5 It is a schematic diagram of the display and alarm module of the present invention;

[0071] Figure 6 It is a schematic diagram of the control and feedback module of the present invention;

[0072] Figure 7 It is a schematic diagram of the distributed monitoring module of the present invention. DETAILED DESCRIPTION

[0073] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings 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.

[0074] Example:

[0075] Please refer to the attached Figure 1 , an embodiment of the present invention provides an infrared imaging monitoring system for an air preheater, including an infrared imaging module, a data processing module, a storage and recording module, a display and alarm module, a control and feedback module, a distributed monitoring module and a remote monitoring and management module;

[0076] The infrared imaging module is used to obtain surface temperature images of different areas of the air preheater;

[0077] The data processing module is used to analyze the temperature image obtained by the infrared imaging module and perform fusion analysis based on the data of multiple detection modes;

[0078] The storage and recording module is used to store temperature image data and analysis results, and to store and manage historical data;

[0079] The display and alarm module is used to display the monitoring results in real time and issue an alarm when an abnormality is detected by the algorithm;

[0080] The algorithms specifically include anomaly detection algorithm, temperature change rate detection algorithm, and clustering algorithm;

[0081] The anomaly detection algorithm formula is:

[0082]

[0083] Among them, X is the current temperature value, μ is the historical average temperature of the area, σ is the historical standard deviation of the area, and Z is considered abnormal if it is greater than ±3;

[0084] The temperature change rate monitoring algorithm formula is:

[0085] y=ax+b

[0086] Where y is the temperature value, xx is the time, and a is the rate of temperature change. If the absolute value a is greater than the set threshold, it is judged as a rate abnormality.

[0087] The clustering algorithm uses the following steps:

[0088] S1, collect data of multiple temperature points;

[0089] S2, cluster these data with K, and set an appropriate number of clusters K;

[0090] S3, judging K, if the temperature of a certain K deviates from the central value of other K, it is judged to be abnormal;

[0091] The control and feedback module is used to adjust the operating parameters of the air preheater according to the monitoring results and perform predictive control;

[0092] The distributed monitoring module is used to collect, process and analyze the data of each area inside the air preheater through multiple distributed intelligent nodes, and form a distributed monitoring network;

[0093] The remote monitoring and management module is used to remotely access and monitor the operating status of the system through the Internet and a dedicated network, allowing maintenance personnel and management personnel to perform remote fault diagnosis, parameter adjustment, and data analysis;

[0094] The infrared imaging module is electrically connected to the data processing module, the data processing module is electrically connected to the storage and recording module, the data processing module is electrically connected to the display and alarm module, the data processing module is electrically connected to the control and feedback module, the control and feedback module is electrically connected to the distributed monitoring module, the distributed monitoring module is electrically connected to the data processing module, the distributed monitoring module is electrically connected to the infrared imaging module, the storage and recording module is electrically connected to the remote monitoring and management module, the display and alarm module is electrically connected to the remote monitoring and management module, and the control and feedback module is electrically connected to the remote monitoring and management module.

[0095] Specifically, the infrared imaging module collects surface temperature images of different areas of the air preheater in real time. These temperature images are transmitted to the data processing module through electrical connection. After receiving the image, the data processing module combines the anomaly detection algorithm, the temperature change rate detection algorithm and the clustering algorithm to conduct in-depth analysis of the temperature image to identify potential anomalies. The analysis results are then transmitted to the storage and recording module for data storage and historical record management. At the same time, the data processing module sends the analysis results to the display and alarm module to display the monitoring results in real time and send out an alarm signal when an anomaly is detected. If the system detects an anomaly or the temperature change rate exceeds the set threshold, the control and feedback module automatically adjusts the operating parameters of the air preheater according to the instructions of the data processing module, and implements predictive control to prevent failures. The distributed monitoring module continuously collects and analyzes data from each area through multiple distributed intelligent nodes to form a distributed monitoring network to ensure comprehensive monitoring of each area inside the air preheater. The operating status and data of all these modules can be remotely accessed and managed through the remote monitoring and management module, allowing maintenance personnel and management personnel to perform remote fault diagnosis, parameter adjustment and data analysis. Each module realizes seamless data transmission and rapid response to instructions through electrical connection to ensure efficient operation of the system and stable operation of the air preheater.

[0096] Please refer to the attached Figure 2 -Attached Figure 4 ,The infrared imaging module includes a multi-point infrared camera unit and a dynamic calibration unit;

[0097] Multi-point infrared camera units are arranged in the key heat exchange area of ​​the air preheater to fully cover the temperature distribution inside the air preheater and to obtain temperature images of different areas;

[0098] The dynamic calibration unit is used to calibrate the infrared camera unit regularly through the built-in temperature reference source;

[0099] The data processing module includes a multi-mode data fusion unit and an intelligent image processing unit;

[0100] The multi-mode data fusion unit is used to combine infrared imaging data with detection data of other modes such as sound waves, vibrations, and airflow for fusion analysis to improve the accuracy of abnormality identification;

[0101] The intelligent image processing unit is used to analyze temperature images using deep learning algorithms, identify and locate temperature anomaly areas, and further verify anomalies by combining data from other modes;

[0102] The deep learning algorithm uses a loss function to evaluate the image. The specific formula is:

[0103]

[0104] Among them, x i is the input image, To reconstruct an image, x is the representation of the input image, usually a two-dimensional array, each element represents the value of a pixel in the image, and n is the total number of pixels in the input image;

[0105] The storage and recording module includes a data storage unit, a data management unit, a data storage unit and a data management unit;

[0106] The data storage unit is used to store temperature images, detection data and analysis results, and supports query and comparative analysis of historical data;

[0107] The data management unit is used to manage the stored historical data, provide data compression and backup functions, and ensure long-term retention and fast access to data;

[0108] The data storage unit is used to store temperature images, detection data and analysis results, and supports query and comparative analysis of historical data;

[0109] The data management unit is used to manage the stored historical data and provide data compression and backup functions.

[0110] Specifically, during the operation of the system, multi-point infrared camera units are first arranged in the key heat exchange area of ​​the air preheater to fully cover the temperature distribution and obtain temperature images of different areas. In order to ensure the accuracy of the infrared imaging data, the dynamic calibration unit regularly calibrates these infrared camera units through the built-in temperature reference source to ensure the accurate measurement of the temperature data; the acquired temperature image data is transmitted to the multi-mode data fusion unit of the data processing module, which not only processes the infrared imaging data, but also combines the data of other detection modes such as sound waves, vibrations, and airflow for fusion analysis. This multi-mode data fusion helps to improve the accuracy of anomaly identification and avoid errors that may be caused by a single data source; in the data processing module, the intelligent image processing unit uses a deep learning algorithm to further analyze the temperature image, identify and locate temperature abnormality areas, and the algorithm evaluates the image through a loss function to ensure the accuracy of the analysis. The intelligent image processing unit also identifies the abnormalities. The regional data is cross-validated with data from other modes to more accurately confirm the existence of abnormal conditions; the analysis results and related data are then transmitted to the data storage unit and data management unit in the storage and recording module. The data storage unit is responsible for storing temperature images, monitoring data and analysis results, and provides historical data query and comparative analysis functions to support further trend analysis. The data management unit is responsible for managing these stored historical data, providing data compression and backup functions to ensure that the data can be retained for a long time and quickly accessed when needed; through the close collaboration between these units, the system can achieve comprehensive and accurate monitoring of the air preheater during operation, and the acquisition, analysis, storage and management of temperature data form a complete closed loop, ensuring that the system can issue early warnings in a timely manner when an abnormality is detected, and support further fault diagnosis and maintenance operations. The efficient cooperation of each unit not only improves the accuracy of monitoring, but also enhances the stability and reliability of the system.

[0111] Please see attached Figure 4 -Attached Figure 5 ,The data management unit includes a data encryption unit and a data backup and recovery unit;

[0112] The data encryption unit is used to encrypt the stored data;

[0113] The data backup and recovery unit is used to regularly back up key data and quickly restore data when it is lost or damaged;

[0114] The display and alarm module includes a real-time display unit and an intelligent alarm unit;

[0115] The real-time display unit is used to display the temperature distribution diagram and monitoring results in real time on the monitoring interface, providing a comprehensive display of multi-mode data;

[0116] The intelligent alarm unit is used to issue graded alarm signals according to the severity of temperature anomalies and supports multiple notification methods for alarm information;

[0117] The intelligent alarm unit includes a multi-level alarm strategy unit and a remote alarm notification unit;

[0118] The multi-level alarm strategy unit is used to dynamically adjust the alarm level and response strategy according to the monitored abnormality level, duration and environmental conditions;

[0119] The remote alarm notification unit is used to send alarm information to remote maintenance personnel and management personnel via email, SMS and mobile applications when major anomalies are detected.

[0120] Specifically, in this system, the data management unit encrypts all stored data through the data encryption unit to ensure the security of data during storage and transmission, and prevent unauthorized access and data leakage. At the same time, the data backup and recovery unit regularly backs up key data to ensure that it can be quickly restored when the data is lost or damaged, thereby ensuring the continuity of the system and the integrity of the data. The real-time display unit in the display and alarm module displays the temperature distribution map and monitoring results in real time on the monitoring interface, integrating multi-mode data to provide a more comprehensive monitoring view. When the intelligent alarm unit detects temperature anomalies, it dynamically adjusts the alarm level and response strategy through the multi-level alarm strategy unit according to the severity of the anomaly, thereby effectively distinguishing different degrees of failure risks and taking corresponding actions. When a major anomaly is detected, the remote alarm notification unit will promptly send the alarm information to remote maintenance personnel and management personnel through email, text messages and mobile applications to ensure that key personnel can respond quickly and take necessary maintenance or repair measures. The close cooperation between the units makes the system not only highly secure and reliable, but also able to achieve accurate real-time monitoring and rapid abnormal response, further improving the safety and efficiency of air preheater operation.

[0121] Please refer to the attached Figure 6 -Attached Figure 7 , the control and feedback module includes a predictive control unit and a feedback regulation unit;

[0122] The predictive control unit is used to establish a prediction model based on real-time monitoring data and historical trends to predict possible abnormalities and adjust the operating parameters of the air preheater in advance. The monitoring data includes temperature data, fan speed, flue gas flow, air pressure and humidity, and equipment operating status. The historical trends include historical temperature change trends, historical fan speed trends, historical flue gas flow trends, and operating event records. The operating parameters include fan speed and flue gas flow.

[0123] The prediction model building includes the following steps:

[0124] S11, data acquisition: obtain the temperature data, fan speed, flue gas flow, air pressure, and humidity of the current air preheater operation from the system, and obtain the historical temperature data, fan speed, and flue gas flow key parameter change records of the air preheater under different operating conditions from the data storage module;

[0125] S22, data preprocessing: remove outliers and fill missing data from the acquired data, extract key features such as temperature change rate and flue gas flow fluctuation amplitude from real-time monitoring data and historical data, and finally standardize the data to eliminate dimensional differences between different features;

[0126] S33, select model: select one of the following models: ARI MA model, LSTM model and support vector regression model according to your needs;

[0127] S44, model training: first divide the historical data into training set and validation set, then use the training set to train the prediction model, and finally use the validation set to verify the accuracy of the model and adjust the model to avoid overfitting;

[0128] S55, model deployment: deploy the trained model to the system, use real-time monitoring data for prediction, and then judge the temperature anomaly and flue gas flow anomaly that may occur in the future based on the prediction results;

[0129] The feedback regulation unit is used to adjust the operating parameters according to the actual monitoring data and optimize the control strategy;

[0130] The distributed monitoring module includes intelligent node units and node communication units:

[0131] The intelligent node unit is used to arrange multiple intelligent nodes inside and outside the air preheater. These nodes have the ability to collect data, perform preliminary processing and analysis, and form a distributed monitoring network.

[0132] The node communication unit is used to communicate data and analysis results between each intelligent node and with the central control unit.

[0133] Specifically, in this system, the control and feedback module works together through the predictive control unit and the feedback adjustment unit to achieve intelligent control of the air preheater. The predictive control unit first establishes a prediction model based on real-time monitoring data and historical trends, using temperature data, fan speed, flue gas flow, air pressure, humidity and equipment operating status to predict possible anomalies. To this end, the system ensures the accuracy and practicality of the prediction model through steps such as data collection, data preprocessing, model selection, model training and model deployment. In the data collection stage, the system obtains the current operating data and historical key parameter change records; then, through the data preprocessing step, the data is used to remove outliers, fill in missing values, and extract key features, such as temperature change rate and flue gas flow fluctuation amplitude. The standardized data is used to select a suitable prediction model, and the model is trained and verified to ensure that the model has good prediction capabilities. After the trained model is deployed, the real-time monitoring data is used to predict future possible If the temperature and flue gas flow of the energy are abnormal, once the prediction results show potential abnormal risks, the system will adjust the operating parameters of the air preheater, such as fan speed and flue gas flow, in advance to prevent malfunctions; at the same time, the feedback regulation unit dynamically adjusts the operating parameters according to the actual monitoring data, and optimizes the control strategy to ensure that the air preheater can operate stably and efficiently under various working conditions. The distributed monitoring module forms a distributed monitoring network through intelligent node units and node communication units. The intelligent node unit arranges multiple intelligent nodes with data acquisition and preliminary processing capabilities inside and outside the air preheater to ensure comprehensive coverage of all key areas of the equipment. The node communication unit is responsible for transmitting data and analysis results between each intelligent node and between the central control unit to ensure efficient flow of information and overall coordinated operation of the system. The close cooperation between the units enables the system to automatically adjust through prediction and feedback mechanisms on the basis of real-time monitoring, greatly improving the operating safety and efficiency of the air preheater.

[0134] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An infrared imaging monitoring system for air preheater, It is characterized in that It includes infrared imaging module, data processing module, storage and recording module, display and alarm module, control and feedback module, distributed monitoring module and remote monitoring and management module; The infrared imaging module is used to obtain surface temperature images of different areas of the air preheater; The data processing module is used to analyze the temperature image acquired by the infrared imaging module and perform fusion analysis in combination with data from multiple detection modes; The storage and recording module is used to store temperature image data and analysis results, and to store and manage historical data; The display and alarm module is used to display the monitoring results in real time and issue an alarm when an abnormality is detected by the algorithm; The algorithm specifically includes an anomaly detection algorithm, a temperature change rate detection algorithm, and a clustering algorithm; The anomaly detection algorithm formula is: Among them, X is the current temperature value, μ is the historical average temperature of the area, σ is the historical standard deviation of the area, and Z is considered abnormal if it is greater than ±3; The temperature change rate detection algorithm formula is: y=ax+b Where y is the temperature value, xx is the time, and a is the rate of temperature change. If the absolute value a is greater than the set threshold, it is judged as a rate abnormality. The clustering algorithm uses the following steps: S1, collect data of multiple temperature points; S2, cluster these data with K, and set an appropriate number of clusters K; S3, judging K, if the temperature of a certain K deviates from the central value of other K, it is judged to be abnormal; The control and feedback module is used to adjust the operating parameters of the air preheater according to the monitoring results and perform predictive control; The distributed monitoring module is used to collect, process and analyze data from various areas inside the air preheater through multiple distributed intelligent nodes, and form a distributed monitoring network; The remote monitoring and management module is used to remotely access and monitor the operating status of the system through the Internet and a dedicated network, allowing maintenance personnel and management personnel to perform remote fault diagnosis, parameter adjustment and data analysis.

2. The infrared imaging monitoring system for an air preheater according to claim 1, It is characterized in that The infrared imaging module includes a multi-point infrared camera unit and a dynamic calibration unit; The multi-point infrared camera unit is arranged in the key heat exchange area of ​​the air preheater to fully cover the temperature distribution inside the air preheater and is used to obtain temperature images of different areas; The dynamic calibration unit is used to periodically calibrate the infrared camera unit through a built-in temperature reference source.

3. The infrared imaging monitoring system for an air preheater according to claim 1, It is characterized in that The data processing module includes a multi-mode data fusion unit and an intelligent image processing unit; The multi-mode data fusion unit is used to combine infrared imaging data with detection data of other modes such as sound waves, vibrations, and airflows for fusion analysis to improve the accuracy of abnormality identification; The intelligent image processing unit is used to analyze the temperature image using a deep learning algorithm, identify and locate the temperature abnormality area, and further verify the abnormal situation in combination with data from other modes; The deep learning algorithm uses a loss function to evaluate the image. The specific formula is: Among them, x i is the input image, To reconstruct an image, x is a representation of the input image, usually a two-dimensional array, each element represents the value of a pixel in the image, and n is the total number of pixels in the input image.

4. The infrared imaging monitoring system for an air preheater according to claim 1, It is characterized in that The storage and recording module includes a data storage unit, a data management unit, a data storage unit and a data management unit; The data storage unit is used to store temperature images, monitoring data and analysis results, and supports query and comparative analysis of historical data; The data management unit is used to manage the stored historical data, provide data compression and backup functions, and ensure long-term retention and fast access to data; The data storage unit is used to store temperature images, monitoring data and analysis results, and supports query and comparative analysis of historical data; The data management unit is used to manage the stored historical data and provide data compression and backup functions.

5. The infrared imaging monitoring system for an air preheater according to claim 4, It is characterized in that The data management unit includes a data encryption unit and a data backup and recovery unit; The data encryption unit is used to encrypt the stored data; The data backup and recovery unit is used to regularly back up key data and quickly recover data when it is lost or damaged.

6. The infrared imaging monitoring system for air preheater according to claim 1, It is characterized in that The display and alarm module includes a real-time display unit and an intelligent alarm unit; The real-time display unit is used to display the temperature distribution diagram and monitoring results in real time on the monitoring interface, providing a comprehensive display of multi-mode data; The intelligent alarm unit is used to send out graded alarm signals according to the severity of the temperature anomaly and supports multiple notification methods of alarm information.

7. The infrared imaging monitoring system for air preheater according to claim 6, It is characterized in that The intelligent alarm unit includes a multi-level alarm strategy unit and a remote alarm notification unit; The multi-level alarm strategy unit is used to dynamically adjust the alarm level and response strategy according to the monitored abnormality degree, duration and environmental conditions; The remote alarm notification unit is used to send alarm information to remote maintenance personnel and management personnel via email, text message and mobile application when a major abnormality is detected.

8. The infrared imaging monitoring system for air preheater according to claim 1, It is characterized in that The control and feedback module includes a predictive control unit and a feedback adjustment unit; The predictive control unit is used to establish a prediction model based on real-time monitoring data and historical trends to predict possible abnormalities and adjust the operating parameters of the air preheater in advance. The monitoring data includes temperature data, fan speed, flue gas flow, air pressure and humidity and equipment operating status. The historical trends include historical temperature change trends, historical fan speed trends, historical flue gas flow trends and operating event records. The operating parameters include fan speed and flue gas flow; The prediction model establishment comprises the following steps: S11, data acquisition: obtain the temperature data, fan speed, flue gas flow, air pressure, and humidity of the current air preheater operation from the system, and obtain the historical temperature data, fan speed, and flue gas flow key parameter change records of the air preheater under different operating conditions from the data storage module; S22, data preprocessing: remove outliers and fill missing data from the acquired data, extract key features such as temperature change rate and flue gas flow fluctuation amplitude from real-time monitoring data and historical data, and finally standardize the data to eliminate dimensional differences between different features; S33, select model: select one of the following models: ARIMA model, LSTM model and support vector regression model according to your needs; S44, model training: first divide the historical data into training set and validation set, then use the training set to train the prediction model, and finally use the validation set to verify the accuracy of the model and adjust the model to avoid overfitting; S55, model deployment: deploy the trained model to the system, use real-time monitoring data for prediction, and then judge the temperature anomaly and flue gas flow anomaly that may occur in the future based on the prediction results; The feedback regulation unit is used to adjust the operating parameters according to the actual monitoring data and optimize the control strategy.

9. The infrared imaging monitoring system for air preheater according to claim 1, It is characterized in that The distributed monitoring module includes an intelligent node unit and a node communication unit: The intelligent node unit is used to arrange multiple intelligent nodes inside and outside the air preheater, and these nodes have data collection, preliminary processing and analysis capabilities to form a distributed monitoring network; The node communication unit is used to communicate data and analysis results between the intelligent nodes and with the central control unit.

10. The infrared imaging monitoring system for air preheater according to claim 1, It is characterized in that The infrared imaging module is electrically connected to the data processing module, the data processing module is electrically connected to the storage and recording module, the data processing module is electrically connected to the display and alarm module, the data processing module is electrically connected to the control and feedback module, the control and feedback module is electrically connected to the distributed monitoring module, the distributed monitoring module is electrically connected to the data processing module, the distributed monitoring module is electrically connected to the infrared imaging module, the storage and recording module is electrically connected to the remote monitoring and management module, the display and alarm module is electrically connected to the remote monitoring and management module, and the control and feedback module is electrically connected to the remote monitoring and management module.

Citation Information

Patent Citations

  • Method for realizing GIL protection based on thermal characteristic abnormity

    CN112103923A

  • Intelligent early warning monitoring management method for forest fire prevention

    CN115691026A

  • Image processing system based on infrared thermal image of electrical equipment

    CN117419814A

Cited By

  • Intelligent wiring control method of junction box

    CN119442120A