Maintenance alarm method and system for thermal power plant boiler

Abstract

The invention relates to the technical field of thermal power plant boilers, and discloses a maintenance alarm method and system for a thermal power plant boiler, and the method comprises the steps: obtaining the real-time feature data of the thermal power plant boiler, and dividing the real-time feature data into normal feature data and abnormal feature data; analyzing the normal feature data and the abnormal feature data, and determining an actual deviation coefficient between the normal feature data and the abnormal feature data; historical maintenance records of the thermal power plant boiler are collected and analyzed, and historical maintenance coefficients of the thermal power plant boiler are calculated based on analysis results; the maintenance alarm factor of the thermal power plant boiler is calculated according to the actual deviation coefficient and the historical maintenance coefficient, whether maintenance alarm reminding is sent out or not is judged according to the maintenance alarm factor, the boiler state can be monitored and early warned in real time, early fault detection, fault diagnosis and predictive maintenance are achieved, an alarm is given out in time, and the maintenance efficiency is improved. Preventive measures can be taken or maintenance can be arranged, so that accidental shutdown and potential safety hazards are avoided.

Description

Technical Field

[0001] The invention relates to the technical field of thermal power plant boilers, and in particular to a maintenance alarm method and system for thermal power plant boilers. Background Art

[0002] The boiler of a thermal power plant is a key energy conversion device. It generates high-temperature and high-pressure steam by burning fossil fuels, which drives the turbine to rotate and generate electricity. The stable operation of the boiler is crucial to the safety and efficiency of the entire power generation process. However, due to long-term operation in high temperature, high pressure and corrosive environments, boiler pipes, valves, pressure vessels and other components are prone to wear, corrosion and aging, which may lead to serious accidents such as leakage, rupture and even explosion. Therefore, the implementation of effective inspection and maintenance strategies is of great significance to ensure the safe operation of thermal power plants and improve economic benefits.

[0003] The current maintenance methods usually rely on regular inspections and post-maintenance, which is not only time-consuming and labor-intensive, but may also lead to sudden failures due to the failure to detect hidden dangers in a timely manner, thereby causing safety accidents or reducing equipment operation efficiency. Summary of the invention

[0004] The embodiment of the present invention provides a maintenance alarm method and system for a thermal power plant boiler, which can monitor and warn the boiler status in real time, realize early fault detection, fault diagnosis and predictive maintenance, and issue alarms in time so as to take preventive measures or arrange maintenance, thereby avoiding unexpected shutdown and potential safety hazards.

[0005] In order to achieve the above object, the present invention provides a maintenance alarm method for a thermal power plant boiler, comprising:

[0006] Acquire real-time characteristic data of a boiler in a thermal power plant, and divide the real-time characteristic data into normal characteristic data and abnormal characteristic data;

[0007] Analyzing the normal feature data and the abnormal feature data, and determining an actual deviation coefficient between the normal feature data and the abnormal feature data based on the analysis result;

[0008] Collecting historical maintenance records of the boiler of the thermal power plant, analyzing the historical maintenance records, and calculating the historical maintenance coefficient of the boiler of the thermal power plant based on the analysis results;

[0009] The maintenance alarm factor of the boiler of the thermal power plant is calculated according to the actual deviation coefficient and the historical maintenance coefficient, and it is determined whether to issue a maintenance alarm reminder according to the maintenance alarm factor.

[0010] Furthermore, when acquiring real-time characteristic data of a thermal power plant boiler and dividing the real-time characteristic data into normal characteristic data and abnormal characteristic data, it includes:

[0011] Retrieving a safety feature data range from a database corresponding to a boiler in a thermal power plant, and comparing the real-time feature data with the safety feature data range;

[0012] When the real-time feature data is within the range of the security feature data, the corresponding real-time feature data is used as normal feature data;

[0013] When the real-time feature data is not within the range of the safety feature data, the corresponding real-time feature data is used as abnormal feature data.

[0014] Further, when analyzing the normal feature data and the abnormal feature data, and determining the actual deviation coefficient between the normal feature data and the abnormal feature data based on the analysis result, it includes:

[0015] Normalizing the normal feature data to obtain a normal normalized sequence;

[0016] Normalizing the abnormal feature data to obtain an abnormal normalized sequence;

[0017] Performing clustering processing on the normal normalized sequence, determining a cluster center, and determining a normal cluster distance of each normal feature data;

[0018] Performing clustering processing on the abnormal normalized sequence, determining the cluster center, and determining the abnormal cluster distance of each abnormal feature data;

[0019] Calculate the normal average distance of all normal clustering distances, and calculate the first sum of all normal clustering distances greater than or equal to the normal average distance;

[0020] Calculating an abnormal average distance of all abnormal clustering distances, and calculating a second sum of all abnormal clustering distances greater than or equal to the abnormal average distance;

[0021] The sum ratio of the first sum value and the second sum value is calculated, and the actual deviation coefficient between the normal feature data and the abnormal feature data is calculated based on the first sum value, the second sum value and the sum ratio.

[0022] Further, when calculating the actual deviation coefficient between the normal feature data and the abnormal feature data according to the first sum value, the second sum value and the sum value ratio, it includes:

[0023] The normal reference and value corresponding to the normal characteristic data are calculated according to the following formula:

[0024]

[0025] Among them, w1 is the normal reference sum value corresponding to the normal feature data, n1 is the number of normal feature data, f is the first sum value, e i is the i-th normal feature data, g i is the weight corresponding to the i-th normal feature data;

[0026] The abnormal reference and value corresponding to the abnormal characteristic data are calculated according to the following formula:

[0027]

[0028] Among them, w2 is the abnormal reference and value corresponding to the abnormal feature data, n2 is the number of abnormal feature data, k j is the jth abnormal feature data, h j is the weight corresponding to the jth abnormal feature data;

[0029] calculating a reference sum value ratio between the normal reference sum value and the abnormal reference sum value;

[0030] Calculate the ratio of the first sum value to the normal reference sum value and use it as a normal deviation value, calculate the ratio of the second sum value to the abnormal reference ratio and use it as an abnormal deviation value, calculate the ratio of the sum value ratio to the reference sum value ratio and use it as a reference deviation value;

[0031] The actual deviation coefficient between the normal feature data and the abnormal feature data is calculated according to the following formula:

[0032]

[0033] Among them, L is the actual deviation coefficient between normal feature data and abnormal feature data, m1 is the normal deviation value, m2 is the abnormal deviation value, and m is the reference deviation value.

[0034] Furthermore, when collecting the historical maintenance records of the thermal power plant boiler, analyzing the historical maintenance records, and calculating the historical maintenance coefficient of the thermal power plant boiler based on the analysis results, it includes:

[0035] Analyze the historical maintenance records, determine the historical maintenance duration corresponding to each historical maintenance record, and construct a historical maintenance duration sequence;

[0036] Calculate the sequence mean and sequence standard deviation of the historical maintenance duration sequence;

[0037] Calculate the outlier degree of each historical maintenance duration according to the sequence mean and the sequence standard deviation;

[0038] The outlier degree of each historical maintenance duration is calculated according to the following formula:

[0039] P = (q1-q2) / q3;

[0040] Among them, P is the outlier degree, q1 is the historical maintenance duration, q2 is the sequence mean, and q3 is the sequence standard deviation;

[0041] The historical maintenance coefficient of the boiler of the thermal power plant is calculated according to all outliers.

[0042] Furthermore, when calculating the historical maintenance coefficient of the thermal power plant boiler according to all outliers, it includes:

[0043] The historical maintenance coefficient of the boiler in the thermal power plant is calculated according to the following formula:

[0044]

[0045] Among them, r is the historical maintenance coefficient of the thermal power plant boiler, u is the number of outliers, cmax is the maximum outlier, c y is the yth outlier degree, and cmin is the minimum outlier degree.

[0046] Furthermore, when calculating the maintenance alarm factor of the thermal power plant boiler according to the actual deviation coefficient and the historical maintenance coefficient, it includes:

[0047] Obtain pre-set maintenance alarm factors;

[0048] The maintenance alarm factor of the boiler in the thermal power plant is calculated according to the following formula:

[0049] a=e( r+L ) ×lnΔe ;

[0050] Among them, a is the maintenance alarm factor of the thermal power plant boiler, and Δe is the preset maintenance alarm factor.

[0051] Further, when judging whether to issue a maintenance alarm reminder according to the maintenance alarm factor, it includes:

[0052] Determining whether to issue a maintenance alarm reminder based on the relationship between the maintenance alarm factor and the preset maintenance alarm factor;

[0053] When the maintenance alarm factor is less than the preset maintenance alarm factor, it is determined that no maintenance alarm reminder will be issued;

[0054] When the maintenance alarm factor is greater than or equal to the preset maintenance alarm factor, it is determined that a maintenance alarm reminder is issued.

[0055] In order to achieve the above object, the present invention also provides a maintenance alarm system for a thermal power plant boiler, comprising:

[0056] The first module is used to obtain real-time characteristic data of the boiler of the thermal power plant and divide the real-time characteristic data into normal characteristic data and abnormal characteristic data;

[0057] A second module is used to analyze the normal feature data and the abnormal feature data, and determine an actual deviation coefficient between the normal feature data and the abnormal feature data based on the analysis result;

[0058] The third module is used to collect the historical maintenance records of the boiler of the thermal power plant, analyze the historical maintenance records, and calculate the historical maintenance coefficient of the boiler of the thermal power plant based on the analysis results;

[0059] The fourth module is used to calculate the maintenance alarm factor of the boiler of the thermal power plant according to the actual deviation coefficient and the historical maintenance coefficient, and determine whether to issue a maintenance alarm reminder according to the maintenance alarm factor.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] The invention discloses a maintenance alarm method and system for a thermal power plant boiler, which obtains real-time characteristic data of the thermal power plant boiler, divides the real-time characteristic data into normal characteristic data and abnormal characteristic data; analyzes the normal characteristic data and the abnormal characteristic data, and determines the actual deviation coefficient between the normal characteristic data and the abnormal characteristic data; collects historical maintenance records of the thermal power plant boiler, analyzes the historical maintenance records, and calculates the historical maintenance coefficient of the thermal power plant boiler based on the analysis result; calculates the maintenance alarm factor of the thermal power plant boiler according to the actual deviation coefficient and the historical maintenance coefficient, and determines whether to issue a maintenance alarm reminder according to the maintenance alarm factor, so as to monitor and warn the boiler status in real time, realize early fault detection, fault diagnosis and predictive maintenance, and issue an alarm in time so as to take preventive measures or arrange maintenance, thereby avoiding unexpected shutdown and potential safety hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0063] Figure 1 A schematic flow chart of a maintenance alarm method for a thermal power plant boiler in an embodiment of the present invention is shown;

[0064] Figure 2The schematic diagram of the structure of the maintenance alarm system for a boiler in a thermal power plant according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0065] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0066] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0067] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0068] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0069] The following is a description of preferred embodiments of the present invention with reference to the accompanying drawings.

[0070] like Figure 1 As shown, an embodiment of the present invention discloses a maintenance alarm method for a thermal power plant boiler, comprising:

[0071] S110: Acquire real-time characteristic data of a boiler in a thermal power plant, and divide the real-time characteristic data into normal characteristic data and abnormal characteristic data;

[0072] In some embodiments of the present application, when real-time characteristic data of a boiler in a thermal power plant is acquired and the real-time characteristic data is divided into normal characteristic data and abnormal characteristic data, the method includes:

[0073] Retrieving a safety feature data range from a database corresponding to a boiler in a thermal power plant, and comparing the real-time feature data with the safety feature data range;

[0074] When the real-time feature data is within the range of the security feature data, the corresponding real-time feature data is used as normal feature data;

[0075] When the real-time feature data is not within the range of the safety feature data, the corresponding real-time feature data is used as abnormal feature data.

[0076] In this embodiment, the real-time characteristic data includes combustion chamber temperature, steam temperature, pressure inside the boiler, steam pressure, water flow, flow of fuel (such as coal or natural gas), etc.

[0077] In this embodiment, the safety feature data range refers to a safety range set according to the boiler, such as the combustion chamber temperature safety range is [1200° C., 1300° C.].

[0078] The beneficial effect of the above technical solution is that the present invention obtains normal characteristic data and abnormal characteristic data according to the range of real-time characteristic data and safety characteristic data, thereby laying a foundation for the maintenance alarm analysis of thermal power plant boilers.

[0079] S120: Analyze the normal feature data and the abnormal feature data, and determine an actual deviation coefficient between the normal feature data and the abnormal feature data based on the analysis result;

[0080] In some embodiments of the present application, when analyzing the normal feature data and the abnormal feature data, and determining the actual deviation coefficient between the normal feature data and the abnormal feature data based on the analysis result, it includes:

[0081] Normalizing the normal feature data to obtain a normal normalized sequence;

[0082] Normalizing the abnormal feature data to obtain an abnormal normalized sequence;

[0083] Performing clustering processing on the normal normalized sequence, determining a cluster center, and determining a normal cluster distance of each normal feature data;

[0084] Performing clustering processing on the abnormal normalized sequence, determining the cluster center, and determining the abnormal cluster distance of each abnormal feature data;

[0085] Calculate the normal average distance of all normal clustering distances, and calculate the first sum of all normal clustering distances greater than or equal to the normal average distance;

[0086] Calculating an abnormal average distance of all abnormal clustering distances, and calculating a second sum of all abnormal clustering distances greater than or equal to the abnormal average distance;

[0087] The sum ratio of the first sum value and the second sum value is calculated, and the actual deviation coefficient between the normal feature data and the abnormal feature data is calculated based on the first sum value, the second sum value and the sum ratio.

[0088] In this embodiment, the method for determining the cluster center is complicated and mature, and will not be introduced in detail here.

[0089] In some embodiments of the present application, when calculating the actual deviation coefficient between the normal feature data and the abnormal feature data according to the first sum value, the second sum value and the sum value ratio, it includes:

[0090] The normal reference and value corresponding to the normal characteristic data are calculated according to the following formula:

[0091]

[0092] Among them, w1 is the normal reference sum value corresponding to the normal feature data, n1 is the number of normal feature data, f is the first sum value, e i is the i-th normal feature data, g i is the weight corresponding to the i-th normal feature data;

[0093] The abnormal reference and value corresponding to the abnormal characteristic data are calculated according to the following formula:

[0094]

[0095] Among them, w2 is the abnormal reference and value corresponding to the abnormal feature data, n2 is the number of abnormal feature data, k j is the jth abnormal feature data, h j is the weight corresponding to the jth abnormal feature data;

[0096] calculating a reference sum value ratio between the normal reference sum value and the abnormal reference sum value;

[0097] Calculate the ratio of the first sum value to the normal reference sum value and use it as a normal deviation value, calculate the ratio of the second sum value to the abnormal reference ratio and use it as an abnormal deviation value, calculate the ratio of the sum value ratio to the reference sum value ratio and use it as a reference deviation value;

[0098] The actual deviation coefficient between the normal feature data and the abnormal feature data is calculated according to the following formula:

[0099]

[0100] Among them, L is the actual deviation coefficient between normal feature data and abnormal feature data, m1 is the normal deviation value, m2 is the abnormal deviation value, and m is the reference deviation value.

[0101] The beneficial effect of the above technical solution is: the present invention calculates normal deviation values, abnormal deviation values ​​and reference deviation values, and then calculates the actual deviation coefficient between normal characteristic data and abnormal characteristic data, thereby ensuring the calculation accuracy of the actual deviation coefficient and avoiding errors, providing reliable data support for the maintenance alarm of the thermal power plant boiler, and ensuring the stable maintenance alarm of the thermal power plant boiler.

[0102] S130: collecting historical maintenance records of the boiler of the thermal power plant, analyzing the historical maintenance records, and calculating a historical maintenance coefficient of the boiler of the thermal power plant based on the analysis results;

[0103] In some embodiments of the present application, when collecting the historical maintenance records of the thermal power plant boiler, analyzing the historical maintenance records, and calculating the historical maintenance coefficient of the thermal power plant boiler based on the analysis results, it includes:

[0104] Analyze the historical maintenance records, determine the historical maintenance duration corresponding to each historical maintenance record, and construct a historical maintenance duration sequence;

[0105] Calculate the sequence mean and sequence standard deviation of the historical maintenance duration sequence;

[0106] Calculate the outlier degree of each historical maintenance duration according to the sequence mean and the sequence standard deviation;

[0107] The outlier degree of each historical maintenance duration is calculated according to the following formula:

[0108] P = (q1-q2) / q3;

[0109] Among them, P is the outlier degree, q1 is the historical maintenance duration, q2 is the sequence mean, and q3 is the sequence standard deviation;

[0110] The historical maintenance coefficient of the boiler of the thermal power plant is calculated according to all outliers.

[0111] In this embodiment, each maintenance corresponds to an actual maintenance time, that is, the time from receiving the maintenance instruction to completing the maintenance.

[0112] The beneficial effect of the above technical solution is that the present invention calculates the historical maintenance coefficient of the thermal power plant boiler according to all outliers, which can reflect the historical maintenance situation and historical maintenance difficulty of the thermal power plant boiler, while ensuring the accuracy of the maintenance alarm of the thermal power plant boiler and avoiding errors caused by human participation.

[0113] In some embodiments of the present application, when calculating the historical maintenance coefficient of the thermal power plant boiler according to all outliers, it includes:

[0114] The historical maintenance coefficient of the boiler in the thermal power plant is calculated according to the following formula:

[0115]

[0116] Among them, r is the historical maintenance coefficient of the thermal power plant boiler, u is the number of outliers, cmax is the maximum outlier, c y is the yth outlier degree, and cmin is the minimum outlier degree.

[0117] S140: Calculate the maintenance alarm factor of the boiler of the thermal power plant according to the actual deviation coefficient and the historical maintenance coefficient, and determine whether to issue a maintenance alarm reminder according to the maintenance alarm factor.

[0118] In some embodiments of the present application, when calculating the maintenance alarm factor of the thermal power plant boiler according to the actual deviation coefficient and the historical maintenance coefficient, it includes:

[0119] Obtain pre-set maintenance alarm factors;

[0120] The maintenance alarm factor of the boiler in the thermal power plant is calculated according to the following formula:

[0121] a=e( r+L ) ×lnΔe ;

[0122] Among them, a is the maintenance alarm factor of the thermal power plant boiler, and Δe is the preset maintenance alarm factor.

[0123] The beneficial effect of the above technical solution is that the present invention comprehensively calculates the maintenance alarm factor of the thermal power plant boiler based on the actual deviation coefficient and the historical maintenance coefficient, which can ensure the comprehensiveness and accuracy of the calculation of the maintenance alarm factor. Combined with real-time characteristic data and historical maintenance records, it can accurately determine whether a maintenance alarm is needed.

[0124] In some embodiments of the present application, when judging whether to issue a maintenance alarm reminder according to the maintenance alarm factor, it includes:

[0125] Determining whether to issue a maintenance alarm reminder based on the relationship between the maintenance alarm factor and the preset maintenance alarm factor;

[0126] When the maintenance alarm factor is less than the preset maintenance alarm factor, it is determined that no maintenance alarm reminder will be issued;

[0127] When the maintenance alarm factor is greater than or equal to the preset maintenance alarm factor, it is determined that a maintenance alarm reminder is issued.

[0128] The beneficial effects of the above technical solution are: it can monitor and warn the boiler status in real time, realize early fault detection, fault diagnosis and predictive maintenance, and issue alarms in time so as to take preventive measures or arrange maintenance, thereby avoiding unexpected shutdowns and potential safety hazards.

[0129] In order to further explain the technical idea of ​​the present invention, the technical solution of the present invention is now described in combination with specific application scenarios.

[0130] Correspondingly, such as Figure 2 As shown, the present application also provides a maintenance alarm system for a thermal power plant boiler, comprising:

[0131] The first module is used to obtain real-time characteristic data of the boiler of the thermal power plant and divide the real-time characteristic data into normal characteristic data and abnormal characteristic data;

[0132] A second module is used to analyze the normal feature data and the abnormal feature data, and determine an actual deviation coefficient between the normal feature data and the abnormal feature data based on the analysis result;

[0133] The third module is used to collect the historical maintenance records of the boiler of the thermal power plant, analyze the historical maintenance records, and calculate the historical maintenance coefficient of the boiler of the thermal power plant based on the analysis results;

[0134] The fourth module is used to calculate the maintenance alarm factor of the boiler of the thermal power plant according to the actual deviation coefficient and the historical maintenance coefficient, and determine whether to issue a maintenance alarm reminder according to the maintenance alarm factor.

[0135] In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0136] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed by the present invention may be used in combination with each other in any manner, and the fact that these combinations are not fully described in this specification is only for the sake of omitting space and saving resources.

[0137] Those skilled in the art can understand that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions recorded in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A maintenance alarm method for a thermal power plant boiler, characterized in that: include: Acquire real-time characteristic data of a boiler in a thermal power plant, and divide the real-time characteristic data into normal characteristic data and abnormal characteristic data; Analyzing the normal feature data and the abnormal feature data, and determining an actual deviation coefficient between the normal feature data and the abnormal feature data based on the analysis result; Collecting historical maintenance records of the boiler of the thermal power plant, analyzing the historical maintenance records, and calculating the historical maintenance coefficient of the boiler of the thermal power plant based on the analysis results; The maintenance alarm factor of the boiler of the thermal power plant is calculated according to the actual deviation coefficient and the historical maintenance coefficient, and it is determined whether to issue a maintenance alarm reminder according to the maintenance alarm factor.

2. The maintenance alarm method for a thermal power plant boiler according to claim 1, characterized in that: When real-time characteristic data of a boiler in a thermal power plant is obtained and the real-time characteristic data is divided into normal characteristic data and abnormal characteristic data, the method includes: Retrieving a safety feature data range from a database corresponding to a boiler in a thermal power plant, and comparing the real-time feature data with the safety feature data range; When the real-time feature data is within the range of the security feature data, the corresponding real-time feature data is used as normal feature data; When the real-time feature data is not within the range of the safety feature data, the corresponding real-time feature data is used as abnormal feature data.

3. The maintenance alarm method for a thermal power plant boiler according to claim 1, characterized in that: When analyzing the normal feature data and the abnormal feature data, and determining the actual deviation coefficient between the normal feature data and the abnormal feature data based on the analysis result, it includes: Normalizing the normal feature data to obtain a normal normalized sequence; Normalizing the abnormal feature data to obtain an abnormal normalized sequence; Performing clustering processing on the normal normalized sequence, determining a cluster center, and determining a normal cluster distance of each normal feature data; Performing clustering processing on the abnormal normalized sequence, determining the cluster center, and determining the abnormal cluster distance of each abnormal feature data; Calculate the normal average distance of all normal clustering distances, and calculate the first sum of all normal clustering distances greater than or equal to the normal average distance; Calculating an abnormal average distance of all abnormal clustering distances, and calculating a second sum of all abnormal clustering distances greater than or equal to the abnormal average distance; The sum ratio of the first sum value and the second sum value is calculated, and the actual deviation coefficient between the normal feature data and the abnormal feature data is calculated based on the first sum value, the second sum value and the sum ratio.

4. The maintenance alarm method for a thermal power plant boiler according to claim 3, characterized in that: When calculating the actual deviation coefficient between the normal feature data and the abnormal feature data according to the first sum value, the second sum value and the sum value ratio, it includes: The normal reference and value corresponding to the normal characteristic data are calculated according to the following formula: Among them, w1 is the normal reference sum value corresponding to the normal feature data, n1 is the number of normal feature data, f is the first sum value, e i is the i-th normal feature data, g i is the weight corresponding to the i-th normal feature data; The abnormal reference and value corresponding to the abnormal characteristic data are calculated according to the following formula: Among them, w2 is the abnormal reference and value corresponding to the abnormal feature data, n2 is the number of abnormal feature data, k j is the jth abnormal feature data, h j is the weight corresponding to the jth abnormal feature data; calculating a reference sum value ratio between the normal reference sum value and the abnormal reference sum value; Calculate the ratio of the first sum value to the normal reference sum value and use it as a normal deviation value, calculate the ratio of the second sum value to the abnormal reference ratio and use it as an abnormal deviation value, calculate the ratio of the sum value ratio to the reference sum value ratio and use it as a reference deviation value; The actual deviation coefficient between the normal feature data and the abnormal feature data is calculated according to the following formula: Among them, L is the actual deviation coefficient between normal feature data and abnormal feature data, m1 is the normal deviation value, m2 is the abnormal deviation value, and m is the reference deviation value.

5. The maintenance alarm method for a thermal power plant boiler according to claim 4, characterized in that: When collecting the historical maintenance records of the thermal power plant boiler, analyzing the historical maintenance records, and calculating the historical maintenance coefficient of the thermal power plant boiler based on the analysis results, it includes: Analyze the historical maintenance records, determine the historical maintenance duration corresponding to each historical maintenance record, and construct a historical maintenance duration sequence; Calculate the sequence mean and sequence standard deviation of the historical maintenance duration sequence; Calculate the outlier degree of each historical maintenance duration according to the sequence mean and the sequence standard deviation; The outlier degree of each historical maintenance duration is calculated according to the following formula: P = (q1-q2) / q3; Among them, P is the outlier degree, q1 is the historical maintenance duration, q2 is the sequence mean, and q3 is the sequence standard deviation; The historical maintenance coefficient of the boiler of the thermal power plant is calculated according to all outliers.

6. The maintenance alarm method for a thermal power plant boiler according to claim 5, characterized in that: When calculating the historical maintenance coefficient of the thermal power plant boiler according to all outliers, it includes: The historical maintenance coefficient of the boiler in the thermal power plant is calculated according to the following formula: Among them, r is the historical maintenance coefficient of the thermal power plant boiler, u is the number of outliers, cmax is the maximum outlier, c y is the yth outlier degree, and cmin is the minimum outlier degree.

7. The maintenance alarm method for a thermal power plant boiler according to claim 6, characterized in that: When calculating the maintenance alarm factor of the thermal power plant boiler according to the actual deviation coefficient and the historical maintenance coefficient, it includes: Obtain pre-set maintenance alarm factors; The maintenance alarm factor of the boiler in the thermal power plant is calculated according to the following formula: a=e (r+L)×lnΔe ; Among them, a is the maintenance alarm factor of the thermal power plant boiler, and Δe is the preset maintenance alarm factor.

8. The maintenance alarm method for a thermal power plant boiler according to claim 7, characterized in that: When judging whether to issue a maintenance alarm reminder according to the maintenance alarm factor, it includes: Determining whether to issue a maintenance alarm reminder based on the relationship between the maintenance alarm factor and the preset maintenance alarm factor; When the maintenance alarm factor is less than the preset maintenance alarm factor, it is determined that no maintenance alarm reminder will be issued; When the maintenance alarm factor is greater than or equal to the preset maintenance alarm factor, it is determined that a maintenance alarm reminder is issued.

9. A maintenance alarm system for a thermal power plant boiler, characterized in that: include: The first module is used to obtain real-time characteristic data of the boiler of the thermal power plant and divide the real-time characteristic data into normal characteristic data and abnormal characteristic data; A second module is used to analyze the normal feature data and the abnormal feature data, and determine an actual deviation coefficient between the normal feature data and the abnormal feature data based on the analysis result; The third module is used to collect the historical maintenance records of the boiler of the thermal power plant, analyze the historical maintenance records, and calculate the historical maintenance coefficient of the boiler of the thermal power plant based on the analysis results; The fourth module is used to calculate the maintenance alarm factor of the boiler of the thermal power plant according to the actual deviation coefficient and the historical maintenance coefficient, and determine whether to issue a maintenance alarm reminder according to the maintenance alarm factor.

Images