Boiler anti-abrasion and anti-explosion online early warning system based on sensor and big data

Abstract

The embodiment of the invention discloses a boiler anti-wear and anti-explosion online early warning system based on a sensor and big data, and relates to the technical field of boiler safety monitoring, and the system comprises a sensor module which collects operation parameters in a boiler in real time; the data acquisition module is used for summarizing various data acquired by the sensor module; the data processing module is used for carrying out processing, analysis and trend prediction on the collected real-time data through a big data analysis technology; the early warning module is used for evaluating the anti-abrasion and anti-explosion risk of the boiler according to the analysis result output by the data processing module and generating an alarm when a risk threshold value is exceeded; and the display and interaction module is used for displaying the boiler operation state, the risk assessment result and the early warning information to an operator. According to the invention, intelligent monitoring and risk early warning of boiler equipment can be realized, and through accurate data analysis and prediction, the operation safety of the boiler can be improved, the occurrence of safety accidents can be reduced, and the maintenance strategy of the boiler can be optimized.

Description

Technical Field

[0001] The present invention belongs to the technical field of boiler safety monitoring, and in particular relates to an online early warning system for boiler wear and explosion prevention based on sensors and big data. Background Art

[0002] As an important thermal energy equipment in industry, boilers are widely used in energy production, chemical industry, steel, cement, papermaking and other fields. During the operation of boilers, due to the high temperature and high pressure environment, various safety hazards are prone to occur, especially wear and explosion problems. These problems not only cause direct damage to boiler equipment, but also may cause serious safety accidents, resulting in casualties and property losses. Therefore, ensuring the safety of boiler operation, especially in preventing boiler wear and explosion, is of great practical significance.

[0003] Traditional boiler safety monitoring usually relies on manual inspections and a single monitoring method, which has problems such as poor real-time performance, limited monitoring accuracy, and failure to detect potential risks in a timely manner. With the development of sensor technology and big data analysis technology, an online early warning system for boiler wear and explosion prevention based on sensor data and big data technology has emerged. It can monitor and analyze various operating parameters of the boiler in real time, and timely predict possible failures or safety risks of the boiler, greatly improving the safety and reliability of boiler operation. At present, most boiler safety monitoring systems have not yet achieved comprehensive prediction and early warning of boiler wear and explosion prevention, and their data processing capabilities are limited. How to integrate information from multiple sensors, adopt advanced data analysis and prediction algorithms, and achieve efficient and intelligent risk prediction and early warning is an important technical problem to improve boiler safety. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art, and discloses an online early warning system for boiler wear and explosion prevention based on sensors and big data.

[0005] The embodiment of the present invention provides a boiler wear and explosion prevention online early warning system based on sensors and big data, including: Sensor module: collects the operating parameters in the boiler in real time, including boiler temperature, pressure, flow, combustion efficiency and flue gas composition; Data acquisition module: The data acquisition module is electrically connected to the sensor module, and is used to aggregate, store and transmit various types of data collected by the sensor module; Data processing module: The data processing module is electrically connected to the data acquisition module, and the data processing module is used to process, analyze and predict the trend of the collected real-time data through big data analysis technology; Early warning module: the early warning module is electrically connected to the data processing module, and is used to evaluate the boiler anti-wear and explosion-proof risks according to the analysis results output by the data processing module, and generate an alarm when the risk threshold is exceeded; Display and interaction module: The display and interaction module is electrically connected to the early warning module. The display and interaction module is used to display the boiler operation status, risk assessment results and early warning information to the operator and provide operation guidance.

[0006] In some possible embodiments, the sensor module specifically includes: Temperature sensor unit: monitors the temperature of different parts of the boiler in real time, and monitors the boiler's combustion temperature, steam temperature, and flue gas temperature; Pressure sensor unit: monitors the real-time pressure of each pressure point of the boiler, including the pressure of steam and water in the boiler; Flow sensor unit: collects the flow data of boiler water, fuel and steam, and monitors the water flow, steam flow and fuel flow in the boiler in real time; Combustion efficiency sensor unit: collects combustion efficiency data in the boiler combustion chamber, including oxygen concentration, carbon dioxide concentration and the composition of combustion gases; Flue gas composition sensor unit: real-time monitoring of gas composition in boiler exhaust gas; Vibration sensor unit: monitors the vibration of the boiler and its supporting equipment; Corrosion sensor unit: monitors corrosion of the internal material surface and key pipelines of the boiler.

[0007] In some possible embodiments, the data acquisition module specifically includes: Data receiving unit: receives data from each sensor module and obtains the operating parameters of the boiler in real time; Data conversion unit: converts analog signals into digital data to ensure that all sensor data can be processed uniformly; Data aggregation unit: Aggregates data from different sensors into a unified data set based on a data aggregation formula, where the aggregation formula is:

[0008] In the formula, T is the arithmetic mean of the data, n is the number of data, i is the index variable, and x is the i is the i-th data point in the data set; Data storage unit: stores the aggregated data in a cloud database, and then stores the data in a time series database; Data transmission unit: transmits the stored data to the data processing module through the network interface for further data analysis and trend prediction.

[0009] In some possible embodiments, the data processing module specifically includes: Data analysis unit: Analyze the correlation between different variables based on the Pearson correlation coefficient formula, where the Pearson correlation coefficient formula is:

[0010] In the formula, r is the Pearson correlation coefficient, x i is the independent variable of the i-th sample, y i is the dependent variable of the ith sample, is the mean of the independent variable x, is the mean of the dependent variable y, and n is the total number of samples in the data set; Trend prediction and modeling unit: Based on the real-time data analysis results and autoregression, a boiler combustion state prediction model is established to predict the boiler combustion trend; Anomaly detection and risk assessment unit: evaluates whether the boiler is likely to fail through anomaly detection. A detection method based on standard deviation is used. When a data point deviates from the mean by more than a set multiple of the standard deviation, it is judged as abnormal. Risk Level Analysis Unit: Evaluate the wear and explosion risk of boilers and calculate the risk level using multivariate analysis.

[0011] In some possible embodiments, the boiler combustion state prediction model is established based on autoregression according to the real-time data analysis results to predict the boiler combustion trend, specifically including: Among them, the boiler combustion state prediction model formula is:

[0012] In the formula, is the predicted value for the future time at time t+h, t is the current time point, h is the prediction step length, Indicates the impact of the observed values ​​at the past p moments on the current predicted value, , is the autoregression coefficient, represents the predicted value at time t+h-1, represents the predicted value at time t+h-2, represents the predicted value at time t+hp, θ1 is the sliding average coefficient, θ q represents the error at the past q moments, is the error term at time t+h-1, is the error term at time t+hq.

[0013] In some possible embodiments, the anomaly detection and risk assessment unit specifically includes: Data acquisition unit: obtains the time series data of the boiler, including pressure, temperature and flow, obtains the mean and standard deviation of the data, and obtains the mean and standard deviation of the time window; Threshold setting unit: sets a threshold value and calculates the deviation degree of each data point based on the deviation degree calculation formula, wherein the deviation degree calculation formula is:

[0014] In the formula, Z t is the standardized deviation of the tth data point, Y t is the current observation value, μ is the mean, and σ is the standard deviation; If the deviation degree Z t If the absolute value of is greater than the set threshold, the data point is considered abnormal.

[0015] In some possible embodiments, the risk level analysis unit specifically includes: Risk Factors and Risk Level Definition Unit: Determine the key factors affecting wear and explosion protection, including wear risk and explosion risk; Risk level definition unit: Risk levels include low risk, medium risk and high risk, and the weights and thresholds of various factors are set based on historical data; Multivariate analysis unit: Dimension reduction based on principal component analysis formula, identification of key influencing factors and extraction of main components; Boiler risk prediction model building unit: Establish a boiler risk prediction model based on linear regression and output the risk level according to the evaluation results.

[0016] In some possible embodiments, the dimensionality reduction based on the principal component analysis formula, identifying key influencing factors and extracting main components specifically includes: The principal component analysis formula is:

[0017] Where C is the covariance matrix, n is the total number of samples, and X i is the observed value of the i-th sample, μ is the mean vector of the sample data, (X i -μ) represents the difference between the i-th sample point and the mean, (X i -μ) T is the transpose of the bias vector.

[0018] In some possible embodiments, establishing a boiler risk prediction model based on linear regression and outputting a risk level according to the evaluation result specifically include: Among them, the boiler risk prediction model formula is:

[0019] In the formula, Y is the risk level, X1 and X2 are influencing factors, and X n is the nth influencing factor, β0 is the intercept term, β1, β2, β n is the regression coefficient, is the error term.

[0020] In some possible embodiments, the early warning module specifically includes: Alarm generation unit: When the analysis results show that the wear or explosion risk of the boiler reaches or exceeds the set threshold, the early warning module triggers an alarm; Recording and reporting unit: After the alarm is triggered, the early warning module records the relevant risk data, thresholds and alarm time information in the log and generates a report. The report content includes the analysis process of risk assessment, the reason for triggering the alarm, relevant data and early warning response information.

[0021] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The boiler anti-wear and explosion-proof online early warning system based on sensors and big data proposed in the embodiment of the present invention can not only realize the intelligent monitoring and risk early warning of boiler equipment, but also improve the operating safety, economy and reliability of the boiler through accurate data analysis and prediction, reduce the occurrence of safety accidents, optimize the boiler maintenance strategy, and provide strong technical support for boiler operation management. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0023] Figure 1 This is a system framework diagram of a boiler anti-wear and explosion-proof online early warning system based on sensors and big data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work are within the scope of protection of the present invention.

[0025] Unless otherwise specified, the technical terms or scientific terms used in the embodiments of the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. "Including" or "comprising" used in the embodiments of the present invention neither limit the shapes, numbers, steps, actions, operations, components, originals and / or their groups mentioned, nor exclude the appearance or addition of one or more other different shapes, numbers, steps, actions, operations, components, originals and / or their groups, or the addition of these. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number and order of the indicated technical features. Thus, the features defined as "first" and "second" can explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0026] Unless otherwise specifically stated, the relative arrangement of the components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention. At the same time, it should be understood that for ease of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship, and the techniques, methods and devices known to ordinary technicians in the relevant fields may not be discussed in detail, but where appropriate, the techniques, methods and devices shown should be considered as part of the authorized specification. In all examples shown and discussed here, any specific other examples may have different values. It should be noted that similar symbols and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0027] In the description of the embodiments of the present invention, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In the embodiments of the present invention, the schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in the embodiments of the present invention and the features of the different embodiments or examples, without contradiction.

[0028] like Figure 1 As shown, the embodiment of the present invention relates to an online early warning system for boiler wear and explosion prevention based on sensors and big data, including: Sensor module: collects the operating parameters in the boiler in real time, including boiler temperature, pressure, flow, combustion efficiency and flue gas composition; Data acquisition module: The data acquisition module is electrically connected to the sensor module, and is used to aggregate, store and transmit various types of data collected by the sensor module; Data processing module: The data processing module is electrically connected to the data acquisition module, and the data processing module is used to process, analyze and predict the trend of the collected real-time data through big data analysis technology; Early warning module: the early warning module is electrically connected to the data processing module, and is used to evaluate the boiler anti-wear and explosion-proof risks according to the analysis results output by the data processing module, and generate an alarm when the risk threshold is exceeded; Display and interaction module: The display and interaction module is electrically connected to the early warning module. The display and interaction module is used to display the boiler operation status, risk assessment results and early warning information to the operator and provide operation guidance.

[0029] In some embodiments, the sensor module specifically includes: Temperature sensor unit: monitors the temperature of different parts of the boiler in real time, and monitors the boiler's combustion temperature, steam temperature, and flue gas temperature; Pressure sensor unit: monitors the real-time pressure of each pressure point of the boiler, including the pressure of steam and water in the boiler; Flow sensor unit: collects the flow data of boiler water, fuel and steam, and monitors the water flow, steam flow and fuel flow in the boiler in real time; Combustion efficiency sensor unit: collects combustion efficiency data in the boiler combustion chamber, including oxygen concentration, carbon dioxide concentration and the composition of combustion gases; Flue gas composition sensor unit: real-time monitoring of gas composition in boiler exhaust gas; Vibration sensor unit: monitors the vibration of the boiler and its supporting equipment; Corrosion sensor unit: monitors corrosion of the internal material surface and key pipelines of the boiler.

[0030] In some embodiments, the data acquisition module specifically includes: Data receiving unit: receives data from each sensor module and obtains the operating parameters of the boiler in real time; Data conversion unit: converts analog signals into digital data to ensure that all sensor data can be processed uniformly; Data aggregation unit: Aggregates data from different sensors into a unified data set based on a data aggregation formula, where the aggregation formula is:

[0031] In the formula, T is the arithmetic mean of the data, n is the number of data, i is the index variable, and x is the i is the i-th data point in the data set; Data storage unit: stores the aggregated data in a cloud database, and then stores the data in a time series database; Data transmission unit: transmits the stored data to the data processing module through the network interface for further data analysis and trend prediction.

[0032] In some embodiments, the data processing module specifically includes: Data analysis unit: Analyze the correlation between different variables based on the Pearson correlation coefficient formula, where the Pearson correlation coefficient formula is:

[0033] In the formula, r is the Pearson correlation coefficient, x i is the independent variable of the i-th sample, y i is the dependent variable of the ith sample, is the mean of the independent variable x, is the mean of the dependent variable y, and n is the total number of samples in the data set; Trend prediction and modeling unit: Based on the real-time data analysis results and autoregression, a boiler combustion state prediction model is established to predict the boiler combustion trend; Anomaly detection and risk assessment unit: evaluates whether the boiler is likely to fail through anomaly detection. A detection method based on standard deviation is used. When a data point deviates from the mean by more than a set multiple of the standard deviation, it is judged as abnormal. Risk Level Analysis Unit: Evaluate the wear and explosion risk of boilers and calculate the risk level using multivariate analysis.

[0034] In some embodiments, the boiler combustion state prediction model is established based on autoregression according to the real-time data analysis results to predict the boiler combustion trend, specifically including: Among them, the boiler combustion state prediction model formula is:

[0035] In the formula, is the predicted value for the future time at time t+h, t is the current time point, h is the prediction step length, Indicates the impact of the observed values ​​at the past p moments on the current predicted value, , is the autoregression coefficient, represents the predicted value at time t+h-1, represents the predicted value at time t+h-2, represents the predicted value at time t+hp, θ1 is the sliding average coefficient, θ q represents the error at the past q moments, is the error term at time t+h-1, is the error term at time t+hq.

[0036] In some embodiments, the anomaly detection and risk assessment unit specifically includes: Data acquisition unit: obtains the time series data of the boiler, including pressure, temperature and flow, obtains the mean and standard deviation of the data, and obtains the mean and standard deviation of the time window; Threshold setting unit: sets a threshold value and calculates the deviation degree of each data point based on the deviation degree calculation formula, wherein the deviation degree calculation formula is:

[0037] In the formula, Z t is the standardized deviation of the tth data point, Y t is the current observation value, μ is the mean, and σ is the standard deviation; If the deviation degree Z t If the absolute value of is greater than the set threshold, the data point is considered abnormal.

[0038] In some embodiments, the risk level analysis unit specifically includes: Risk Factors and Risk Level Definition Unit: Determine the key factors affecting wear and explosion protection, including wear risk and explosion risk; Risk level definition unit: Risk levels include low risk, medium risk and high risk, and the weights and thresholds of various factors are set based on historical data; Multivariate analysis unit: Dimension reduction based on principal component analysis formula, identification of key influencing factors and extraction of main components; Boiler risk prediction model building unit: Establish a boiler risk prediction model based on linear regression and output the risk level according to the evaluation results.

[0039] In some embodiments, the dimensionality reduction based on the principal component analysis formula, identifying key influencing factors and extracting main components specifically includes: The principal component analysis formula is:

[0040] Where C is the covariance matrix, n is the total number of samples, and X i is the observed value of the i-th sample, μ is the mean vector of the sample data, (X i -μ) represents the difference between the i-th sample point and the mean, (X i -μ) Tis the transpose of the bias vector.

[0041] In some embodiments, the boiler risk prediction model is established based on linear regression, and the risk level is output according to the evaluation result, specifically including: Among them, the boiler risk prediction model formula is:

[0042] In the formula, Y is the risk level, X1 and X2 are influencing factors, and X n is the nth influencing factor, β0 is the intercept term, β1, β2, β n is the regression coefficient, is the error term.

[0043] In some embodiments, the early warning module specifically includes: Alarm generation unit: When the analysis results show that the wear or explosion risk of the boiler reaches or exceeds the set threshold, the early warning module triggers an alarm; Recording and reporting unit: After the alarm is triggered, the early warning module records the relevant risk data, thresholds and alarm time information in the log and generates a report. The report content includes the analysis process of risk assessment, the reason for triggering the alarm, relevant data and early warning response information.

[0044] In summary, the advantages of the boiler wear and explosion prevention online early warning system based on sensors and big data in the embodiment of the present invention are: The system can comprehensively monitor the operation status of the boiler by collecting real-time multi-dimensional data such as boiler temperature, pressure, flow, combustion efficiency, flue gas composition, vibration, corrosion, etc. Once abnormal boiler parameters are detected, the system can generate an early warning in time to remind the operator to take corresponding measures to reduce the risk of failure or safety accidents; The system combines big data analysis technology to conduct in-depth analysis of large amounts of real-time data and discover potential problems in boiler operation. Through advanced trend prediction methods such as autoregressive models, the system can predict the combustion status and trend of the boiler, and issue early warnings for possible wear or explosion risks, helping managers take precautions in advance to avoid accidents. Through comprehensive analysis of multiple operating parameters of the boiler, the system can evaluate the risk level of boiler wear and explosion prevention, and use multivariate analysis, principal component analysis and other methods to identify key factors affecting boiler safety. The system can manage risks at different levels and take different countermeasures based on the evaluation results, thereby improving the safety and stability of boiler operation. The system uses an anomaly detection method based on standard deviation to continuously monitor the real-time data of the boiler. Once it detects that the deviation of certain parameters exceeds the preset threshold, the system will trigger an alarm to indicate that the boiler may have a malfunction or accident, thus avoiding losses caused by failure to detect problems in time. Through the display and interaction module, the system can intuitively display real-time monitoring results, risk assessment reports, early warning information and other contents to boiler operators, helping them to quickly understand the operating status and potential risks of the boiler. At the same time, the system also provides operation guidance to guide operators to make effective interventions and adjustments to optimize the operating parameters of the boiler. The system can store all kinds of collected data and alarm information in the cloud database in real time, which is convenient for later query and analysis. By generating a detailed risk assessment report, operators can conduct a comprehensive review and analysis of the historical operation of the boiler, providing a basis for subsequent repairs, maintenance, optimization, etc. Through real-time monitoring and predictive analysis of boiler combustion efficiency, the system can help boiler operators optimize the combustion process, improve energy efficiency, reduce unnecessary energy consumption, reduce operating costs, and improve the overall economy of the boiler; Through automated data collection, analysis and early warning, the system can effectively reduce human errors and avoid potential safety hazards that may be missed during traditional manual inspections. Through intelligent wear and explosion prevention predictions, it can reduce the risk of accidents caused by equipment failure or wear, and improve the long-term reliability and service life of the boiler. Through continuous monitoring and risk warning, the system can detect potential failures of boiler equipment early and perform repairs or replace parts in advance, thereby avoiding production losses caused by sudden boiler shutdowns. Through data-driven predictive maintenance strategies, it can effectively reduce maintenance costs, reduce boiler downtime, and improve production efficiency.

[0045] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present invention, but the present invention is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered to be within the scope of protection of the present invention.

Claims

1. A boiler wear and explosion prevention online early warning system based on sensors and big data, characterized in that: include: Sensor module: collects the operating parameters in the boiler in real time, including boiler temperature, pressure, flow, combustion efficiency and flue gas composition; Data acquisition module: The data acquisition module is electrically connected to the sensor module, and is used to aggregate, store and transmit various types of data collected by the sensor module; Data processing module: The data processing module is electrically connected to the data acquisition module, and the data processing module is used to process, analyze and predict the trend of the collected real-time data through big data analysis technology; Early warning module: the early warning module is electrically connected to the data processing module, and is used to evaluate the boiler anti-wear and explosion-proof risks according to the analysis results output by the data processing module, and generate an alarm when the risk threshold is exceeded; Display and interaction module: The display and interaction module is electrically connected to the early warning module. The display and interaction module is used to display the boiler operation status, risk assessment results and early warning information to the operator and provide operation guidance.

2. The online early warning system for boiler wear and explosion prevention based on sensors and big data according to claim 1 is characterized in that: The sensor module specifically includes: Temperature sensor unit: monitors the temperature of different parts of the boiler in real time, and monitors the boiler's combustion temperature, steam temperature, and flue gas temperature; Pressure sensor unit: monitors the real-time pressure of each pressure point of the boiler, including the pressure of steam and water in the boiler; Flow sensor unit: collects the flow data of boiler water, fuel and steam, and monitors the water flow, steam flow and fuel flow in the boiler in real time; Combustion efficiency sensor unit: collects combustion efficiency data in the boiler combustion chamber, including oxygen concentration, carbon dioxide concentration and the composition of combustion gases; Flue gas composition sensor unit: real-time monitoring of gas composition in boiler exhaust gas; Vibration sensor unit: monitors the vibration of the boiler and its supporting equipment; Corrosion sensor unit: monitors corrosion of the internal material surface and key pipelines of the boiler.

3. The online early warning system for boiler wear and explosion prevention based on sensors and big data according to claim 2 is characterized in that: The data acquisition module specifically includes: Data receiving unit: receives data from each sensor module and obtains the operating parameters of the boiler in real time; Data conversion unit: converts analog signals into digital data to ensure that all sensor data can be processed uniformly; Data aggregation unit: Aggregates data from different sensors into a unified data set based on a data aggregation formula, where the aggregation formula is: In the formula, T is the arithmetic mean of the data, n is the number of data, i is the index variable, and x is the i is the i-th data point in the data set; Data storage unit: stores the aggregated data in a cloud database, and then stores the data in a time series database; Data transmission unit: transmits the stored data to the data processing module through the network interface for further data analysis and trend prediction.

4. The online early warning system for boiler wear and explosion prevention based on sensors and big data according to claim 2 is characterized in that: The data processing module specifically includes: Data analysis unit: Analyze the correlation between different variables based on the Pearson correlation coefficient formula, where the Pearson correlation coefficient formula is: In the formula, r is the Pearson correlation coefficient, x i is the independent variable of the i-th sample, y i is the dependent variable of the ith sample, is the mean of the independent variable x, is the mean of the dependent variable y, and n is the total number of samples in the data set; Trend prediction and modeling unit: Based on the real-time data analysis results and autoregression, a boiler combustion state prediction model is established to predict the boiler combustion trend; Anomaly detection and risk assessment unit: evaluates whether the boiler is likely to fail through anomaly detection. A detection method based on standard deviation is used. When a data point deviates from the mean by more than a set multiple of the standard deviation, it is judged as abnormal. Risk Level Analysis Unit: Evaluate the wear and explosion risk of boilers and calculate the risk level using multivariate analysis.

5. The online early warning system for boiler wear and explosion prevention based on sensors and big data according to claim 4 is characterized in that: According to the real-time data analysis results, based on autoregression, a boiler combustion state prediction model is established to predict the boiler combustion trend. include: Among them, the boiler combustion state prediction model formula is: In the formula, is the predicted value for the future time at time t+h, t is the current time point, h is the prediction step length, Indicates the impact of the observed values ​​at the past p moments on the current predicted value, , is the autoregression coefficient, represents the predicted value at time t+h-1, represents the predicted value at time t+h-2, represents the predicted value at time t+hp, θ1 is the sliding average coefficient, θ q represents the error at the past q moments, is the error term at time t+h-1, is the error term at time t+hq.

6. The online early warning system for boiler wear and explosion prevention based on sensors and big data according to claim 5 is characterized in that: The anomaly detection and risk assessment unit specifically includes: Data acquisition unit: obtains the time series data of the boiler, including pressure, temperature and flow, obtains the mean and standard deviation of the data, and obtains the mean and standard deviation of the time window; Threshold setting unit: sets a threshold value and calculates the deviation degree of each data point based on the deviation degree calculation formula, wherein the deviation degree calculation formula is: In the formula, Z t is the standardized deviation of the tth data point, Y t is the current observation value, μ is the mean, and σ is the standard deviation; If the deviation degree Z t If the absolute value of is greater than the set threshold, the data point is considered abnormal.

7. The online early warning system for boiler wear and explosion prevention based on sensors and big data according to claim 6 is characterized in that: The risk level analysis unit specifically includes: Risk Factors and Risk Level Definition Unit: Determine the key factors affecting wear and explosion protection, including wear risk and explosion risk; Risk level definition unit: Risk levels include low risk, medium risk and high risk, and the weights and thresholds of various factors are set based on historical data; Multivariate analysis unit: Dimension reduction based on principal component analysis formula, identification of key influencing factors and extraction of main components; Boiler risk prediction model building unit: Establish a boiler risk prediction model based on linear regression and output the risk level according to the evaluation results.

8. The online early warning system for boiler wear and explosion prevention based on sensors and big data according to claim 7 is characterized in that: The principal component analysis formula is used to reduce the dimension, identify key influencing factors and extract the main components. include: The principal component analysis formula is: Where C is the covariance matrix, n is the total number of samples, and X i is the observed value of the i-th sample, μ is the mean vector of the sample data, (X i -μ) represents the difference between the i-th sample point and the mean, (X i -μ) T is the transpose of the bias vector.

9. The online early warning system for boiler wear and explosion prevention based on sensors and big data according to claim 8 is characterized in that: The boiler risk prediction model is established based on linear regression, and the risk level is output according to the evaluation results. include: Among them, the boiler risk prediction model formula is: In the formula, Y is the risk level, X1 and X2 are influencing factors, and X n is the nth influencing factor, β0 is the intercept term, β1, β2, β n is the regression coefficient, is the error term.

10. The online early warning system for boiler wear and explosion prevention based on sensors and big data according to claim 9 is characterized in that: The early warning module specifically includes: Alarm generation unit: When the analysis results show that the wear or explosion risk of the boiler reaches or exceeds the set threshold, the early warning module triggers an alarm; Recording and reporting unit: After the alarm is triggered, the early warning module records the relevant risk data, thresholds and alarm time information in the log and generates a report. The report content includes the analysis process of risk assessment, the reason for triggering the alarm, relevant data and early warning response information.

Images