Boiler safety assessment analysis method and system based on residual life

Abstract

The invention provides a boiler safety assessment analysis method and system based on residual life, and belongs to the technical field of safety assessment. The risk association target of the residual life in the evaluation target is determined in combination with interval node data of different credible test nodes and adjacent credible test nodes, and the evaluation processing period is determined according to the distribution data of the credible test nodes; and on the basis of the distribution data and the deviation condition of the evaluation processing result of the residual life in each evaluation processing period, an evaluation processing strategy of the boiler safety evaluation analysis result based on the residual life is determined, and the processing efficiency of boiler safety evaluation analysis is improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of safety evaluation, and particularly relates to a boiler safety evaluation analysis method and system based on residual life. BACKGROUND

[0002] At present, in China's thermal power enterprises, more and more units are in service beyond the designed life, and at the same time, with the increase of the capacity of new units, the old units are in shutdown or low load operation for a long time, and in the peak regulation period, they need to be in high load operation, so that this batch of boilers are faced with the situation of frequent start-stop and unstable operation conditions, thereby accelerating the aging of the units and increasing the failure rate.

[0003] Therefore, in order to evaluate the residual life of the boiler, the existing technical solutions often focus on test data, such as the thickness of the inner wall oxide layer of the pipe, the pipe wall thinning rate, the conventional stress, the metal wall thickness, the pipe outer diameter expansion, and the pipe wall temperature, and the finite element calculation software (such as ANSYS) is used to analyze the temperature field and stress field under different conditions, thereby providing a theoretical basis for residual life evaluation, but the above technical solutions have the following technical problems: In the safety evaluation process of the boiler, there are evaluation targets in multiple dimensions, so the existing technical solutions often use a fixed safety evaluation processing strategy to evaluate the safety of the boiler, and once the residual life of the boiler changes, the fixed safety evaluation processing strategy cannot guarantee the reliability of the safety evaluation processing, so how to determine the safety evaluation analysis strategy of the boiler combined with the residual life becomes a technical problem to be solved.

[0004] To solve the above technical problems, the application provides a boiler safety evaluation analysis method and system based on residual life. SUMMARY

[0005] To achieve the purpose of the application, the application adopts the following technical solutions: Specifically, the application provides a boiler safety evaluation analysis method based on residual life, which specifically comprises the following steps: S1, determining the change of the evaluation target in different dimensions in different test nodes based on the analysis result of the test data, and determining the reliable test node in the test node based on the matching degree of the change and the operation data of the boiler; S2, determining that the next step is entered when the safety evaluation analysis of the boiler needs to use the residual life based on the distribution data and the distribution coincidence data of the reliable test node of the evaluation target in different dimensions; S3 determines the risk correlation target of the residual life in the evaluation target according to the analysis result of the inspection data of the trusted inspection node of the evaluation target in different dimensions and the interval node data between different trusted inspection nodes and adjacent trusted inspection nodes; S4 determines the evaluation processing period based on the distribution data of the trusted inspection nodes, and determines the evaluation processing strategy of the boiler safety evaluation analysis result based on the residual life based on the deviation of the evaluation processing result of the residual life in each evaluation processing period.

[0006] The beneficial effects of the present application are: According to the analysis result of the inspection data of the trusted inspection node of the evaluation target in different dimensions and the interval node data between different trusted inspection nodes and adjacent trusted inspection nodes, the risk correlation target of the residual life in the evaluation target is determined, which not only considers the variation trend of the residual life corresponding to the inspection data of the trusted inspection node, but also considers the influence of the number of interval nodes between the previous trusted inspection node on the data credibility and the influence of the uniformity of the distribution of the trusted inspection node, so as to realize the screening of the risk correlation index with poor variation trend of the residual life and high credibility.

[0007] Based on the distribution data and the deviation of the evaluation processing result of the residual life in each evaluation processing period, the evaluation processing strategy of the boiler safety evaluation analysis result based on the residual life is determined, which fully considers the deviation of the evaluation processing result of the residual life due to the proportion of the number of trusted test nodes in each evaluation processing period and the deviation of the inspection data in the non-trusted test nodes, realizes the evaluation processing strategy of the boiler safety evaluation analysis result based on the residual life from the perspective of data credibility, improves the efficiency of safety evaluation analysis processing, and also ensures the reliability of safety evaluation analysis processing.

[0008] Further technical solutions are that the evaluation target includes a creep target, an overheating target, and a wear target.

[0009] Specifically, the creep target is determined according to the thickness of the inner wall oxide layer of the pipe, the overheating target is determined according to the pipe outer diameter expansion, and the wear target is determined according to the pipe wall thinning rate.

[0010] Further technical solutions are that the variation of the evaluation target is determined according to the variation amount of the evaluation result of the last evaluation target.

[0011] Further technical solutions are that the operation data of the boiler includes the operation load data and the coal quality blending data of the boiler.

[0012] A further technical solution is that the method for determining the trusted inspection node in the inspection node is: The variation amount of the evaluation target between the inspection node and the nearest trusted inspection node under the operation data of the boiler is determined according to the matching degree between the variation of the evaluation target and the operation data of the boiler, and is taken as the inspection variation amount; The variation amount between the evaluation processing result of the evaluation target and the nearest trusted inspection node is determined according to the variation of the evaluation target, and is taken as the measured variation amount; According to the deviation between the measured variation amount and the inspection variation amount, it is determined whether the inspection node is a trusted inspection node of the evaluation target.

[0013] A further technical solution is that the method for determining the evaluation processing strategy of the boiler safety evaluation analysis result based on the remaining life of the boiler is: The historical inspection data is divided into different evaluation processing periods based on the evaluation processing period; According to the deviation of the evaluation processing result of the remaining life in different evaluation processing periods, the deviation amount of the evaluation processing result of the remaining life of the risk correlation index of different inspection nodes in different evaluation processing periods is determined, and the abnormal influence node is determined based on the deviation amount; The evaluation processing strategy of the boiler safety evaluation analysis result based on the remaining life of the boiler is determined by the number of evaluation processing periods with abnormal influence nodes and the number of associated trusted nodes of the risk correlation index in different evaluation processing periods.

[0014] A further technical solution is that the evaluation processing period is based on the unit time corresponding to the evaluation processing period as the length of the evaluation processing period based on the current time, and the historical inspection data is divided into different evaluation processing periods based on the length of the evaluation processing period.

[0015] In a second aspect, the present application provides a computer system, comprising a memory and a processor connected in communication, and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to perform the above-mentioned boiler safety evaluation analysis method based on the remaining life.

[0016] Other features and advantages will be set forth in the following description of the application, and in part will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the application. The objects and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims.

[0017] In order to make the above objectives, characteristics and advantages of the present application more apparent, more comprehensible, the following preferred embodiments are specifically described in detail below, together with the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0018] The above and other features and advantages of the present application will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings in which:

[0019] Figure 1 is a flowchart of a method for updating data analysis processing of bridge inspection data; Figure 2 is a flowchart of a method for determining a trusted inspection node in an inspection node; Figure 3 is a flowchart of a method for determining a risk-related target for assessing the remaining life in a target; Figure 4 is a flowchart of a method for determining an evaluation processing strategy for a boiler safety evaluation analysis result based on the remaining life of a boiler. DETAILED DESCRIPTION

[0020] Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments, however, can be implemented in many different forms and should not be construed as limited to the implementations set forth herein; rather, these implementations are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. Like reference numerals refer to like elements throughout the drawings, and thus a detailed description of them will not be repeated.

[0021] The terms "one", "a", "an", "the", and "said" are used to indicate the existence of one or more than one element / portion / etc.; the terms "include" and "has" are used to indicate an open-ended inclusion and refer to the presence of additional elements / portions / etc. in addition to the listed elements / portions / etc.

[0022] Example 1 To solve the above problems, according to one aspect of the present application, as shown in Figure 1 a boiler safety evaluation analysis method based on the remaining life is provided, specifically comprising: S1 determines the change of the evaluation target in different dimensions in different inspection nodes based on the analysis result of the inspection data, and determines a trusted inspection node in the inspection node based on the matching degree of the change and the operation data of the boiler; Further, the evaluation target includes a creep target, an overheating target, and a wear target.

[0023] Specifically, the creep target is determined according to the thickness of the oxide layer on the inner wall of the pipe, the overheating target is determined according to the expansion of the outer diameter of the pipe, and the wear target is determined according to the pipe wall thinning rate.

[0024] Specifically, the variation of the evaluation target is determined according to the variation amount of the evaluation result of the evaluation target in the last time.

[0025] It can be understood that the operation data of the boiler includes operation load data and coal quality blending data of the boiler.

[0026] Specifically, as shown in Figure 2 The method for determining the trusted inspection node in the inspection node is: The variation amount of the evaluation target between the inspection node and the last trusted inspection node under the operation data of the boiler is determined according to the matching degree of the variation of the evaluation target and the operation data of the boiler, and is taken as the inspection variation amount; Based on the variation of the evaluation target, the variation amount between the evaluation processing result of the evaluation target and the last trusted inspection node is determined, and is taken as the measured variation amount; According to the deviation of the measured variation amount and the inspection variation amount, it is determined whether the inspection node is a trusted inspection node of the evaluation target.

[0027] It should be noted that the first trusted inspection node is the time node when the boiler is installed.

[0028] In addition, it can be understood that the inspection variation amount is determined based on the prediction result of the prediction model by taking the operation load data and the coal quality blending data of the boiler as the input of the prediction model. The specific prediction model can be constructed by a neural network algorithm.

[0029] It can be understood that the prediction model is constructed by a BP neural network and an LSTM neural network.

[0030] Specifically, when the deviation amount of the measured variation amount and the inspection variation amount is greater than a preset deviation amount threshold, it is determined that the inspection node does not belong to the trusted inspection node of the evaluation target.

[0031] S2 determines, based on the distribution data and the distribution overlap data of the trusted inspection nodes of the evaluation targets in different dimensions, whether to enter the next step when the remaining life needs to be used for safety evaluation and analysis processing of the boiler. Specifically, it is determined that the remaining life does not need to be used for safety evaluation and analysis processing of the boiler, which specifically includes: The distribution coincidence data of the evaluation target of the trusted test node in different dimensions is used to determine the test node of the evaluation target in different dimensions that belongs to the trusted test node, and the test node is taken as the coincidence test node; The test node of the trusted test node of the evaluation target is obtained, and the test node is taken as the target node; The distribution data of the coincidence test node and the target node are used to determine whether the remaining life needs to be used for the safety evaluation and analysis processing of the boiler.

[0032] Specifically, when the number of coincidence test nodes and the number of target nodes meet the requirements, it is determined that the remaining life does not need to be used for the safety evaluation and analysis processing of the boiler. It can be understood that the test data of the evaluation target in different nodes is relatively accurate at this time, so the test data can be directly used for the safety evaluation and analysis processing of the boiler. In a possible embodiment, the number of coincidence test nodes and the number of target nodes are determined by the number threshold to determine whether they meet the requirements.

[0033] In another possible embodiment, it is determined that the remaining life needs to be used for the safety evaluation and analysis processing of the boiler, specifically including: S21 The distribution coincidence data of the evaluation target of the trusted test node in different dimensions is used to determine the test node of the evaluation target in different dimensions that belongs to the trusted test node, and the test node is taken as the coincidence test node, and the test node of the trusted test node of the evaluation target is obtained, and the test node is taken as the target node; It should be noted that in the above step, if there is no coincidence test node or the number of target nodes does not meet the requirements, specifically when the number of target nodes is less than 0.9, the detection accuracy of the evaluation target at this time cannot meet the requirements, so the remaining life needs to be used for the safety evaluation and analysis processing of the boiler.

[0034] In addition, it should be noted that if there is a coincidence test node and the number of target nodes meets the requirements, if the number of coincidence test nodes meets the requirements, that is, the number of coincidence test nodes is more than 0.7, the detection accuracy of the evaluation target at this time is high, so the remaining life does not need to be used for the safety evaluation and analysis processing of the boiler, and the evaluation target can be directly used for the safety evaluation and analysis processing of the boiler.

[0035] In addition, it should be noted that if the number of coincidence test nodes does not meet the requirements, especially when the number of coincidence test nodes is small, specifically less than 0.4, the detection accuracy of the evaluation target at this time cannot meet the requirements, so the remaining life needs to be used for the safety evaluation and analysis processing of the boiler. If the above conditions do not exist, the next step is entered.

[0036] S22 determines the number proportion of the trusted test nodes of the evaluation targets of different dimensions according to the distribution data of the trusted test nodes of the evaluation targets of different dimensions, and determines the data trust values of the evaluation targets of different dimensions in combination with the number of interval nodes between different trusted test nodes; In a possible embodiment, if there is an evaluation target whose number proportion of trusted test nodes does not meet the requirement, that is, the number proportion of trusted test nodes is less than 0.6, in the above step, the detection accuracy of the evaluation target is difficult to meet the requirement, and therefore the remaining life needs to be used for the safety evaluation and analysis processing of the boiler.

[0037] In addition, it needs to be noted that if there is no evaluation target whose number proportion of trusted test nodes does not meet the requirement, and the number proportion of trusted test nodes of different evaluation targets is all greater than 0.9, the detection accuracy of different evaluation targets is high at this time, and therefore the remaining life does not need to be used for the safety evaluation and analysis processing of the boiler, and the evaluation target can be directly used for the safety evaluation and analysis processing of the boiler.

[0038] In a possible embodiment, the data trust value in the above step can be determined according to the ratio of the number proportion of the trusted test nodes of the evaluation target to the average value of the number of interval nodes between different trusted test nodes, wherein when the data trust values of different evaluation targets are all greater than a preset trust threshold value, the detection accuracy of different evaluation targets is high, and therefore the remaining life does not need to be used for the safety evaluation and analysis processing of the boiler, and the evaluation target can be directly used for the safety evaluation and analysis processing of the boiler.

[0039] As long as the data trust value of any evaluation target does not meet the requirement, that is, is less than the preset threshold value, the remaining life needs to be used for the safety evaluation and analysis processing of the boiler at this time.

[0040] S23 determines whether the remaining life needs to be used for the safety evaluation and analysis processing of the boiler through the number proportion of the coincident test nodes and the data trust values of the evaluation targets of different dimensions.

[0041] It can be understood that in one possible embodiment, a comprehensive data trust value is determined according to the average value of the number proportion of the coincident test nodes and the data trust values of the evaluation targets of different dimensions, and when the comprehensive data trust value is greater than a trust preset value, it is determined that the remaining life does not need to be used for the safety evaluation and analysis processing of the boiler.

[0042] S3 determines the risk correlation target of the residual life of the evaluation target according to the analysis result of the inspection data of the trusted inspection node of the evaluation target in different dimensions, and determines the risk correlation target of the residual life of the evaluation target in different dimensions according to the interval node data between the trusted inspection node and the adjacent trusted inspection node. Specifically, as shown in Figure 3 The method for determining the risk correlation target of the residual life of the evaluation target is: According to the analysis result of the inspection data of the trusted inspection node of the evaluation target, the residual life of the boiler corresponding to the inspection data of the evaluation target at different trusted inspection nodes is determined, and is taken as the matching residual life. According to the variation of the matching residual life of the trusted inspection node and the previous trusted inspection node, the residual life variation is determined, and the variation inspection node is determined based on the residual life variation. According to the interval node data between the variation inspection node and the previous trusted inspection node, the interval node quantity is determined, and according to the interval node quantity of different variation inspection nodes, it is determined whether the evaluation target is a risk correlation index of residual life.

[0043] It can be understood that the variation inspection node is a trusted inspection node with a residual life variation greater than a preset variation threshold, wherein the residual life variation is determined according to the ratio of the variation of the matching residual life of the previous trusted inspection node and the interval time length between the previous trusted inspection node.

[0044] Specifically, the matching residual life is determined according to the preset residual life under the inspection data of the evaluation target. Specifically, the simulation result of the residual life of the simulation model of the boiler under the inspection data can be used to determine it, or the matching condition of the inspection data and the variation curve of the residual life of the boiler can be used to determine it.

[0045] Specifically, the risk correlation index is the evaluation target with the most variation inspection nodes, whose deviation amount of the matching residual life of the nearest coincident inspection node and the shortest matching residual life in the evaluation index is within a preset range and the interval node quantity is less than a preset node quantity threshold.

[0046] In another embodiment, the method for determining the risk correlation target of the residual life of the evaluation target is: S31 determines the residual life of the boiler corresponding to the inspection data of the evaluation target at different trusted inspection nodes according to the analysis result of the inspection data of the trusted inspection node of the evaluation target, and takes it as the matching residual life. The deviation amount of the matching residual life of the evaluation target of the nearest coincident inspection node and the shortest matching residual life in the evaluation index is taken as the residual life deviation amount. It can be understood that when the remaining life of the boiler corresponding to the inspection data of the latest coincident inspection node of different evaluation targets is greater than the preset remaining life threshold, the safety evaluation analysis of the boiler based on the remaining life is not required at this time, and only the determination of the trusted inspection node according to the preset time period is required, and the safety evaluation analysis of the boiler is performed by using the evaluation target of the trusted inspection node.

[0047] In another possible embodiment, if the remaining life of the boiler corresponding to the inspection data of the latest coincident inspection node of different evaluation targets is greater than the preset remaining life threshold, and if there is no evaluation target in the latest coincident inspection node whose matching residual life and the shortest matching residual life in the evaluation index have a deviation within a preset range, the evaluation target corresponding to the shortest matching residual life is taken as a risk-related index.

[0048] In addition, it can be understood that if there is an evaluation target in the latest coincident inspection node whose matching residual life and the shortest matching residual life in the evaluation index have a deviation within a preset range, the evaluation target whose residual life deviation is within the preset range is taken as an alternative evaluation target, and the evaluation target whose residual life deviation is not within the preset range can be directly determined not to belong to the alternative evaluation target.

[0049] S32 determines the residual life variation amount according to the variation of the matching residual life of different trusted inspection nodes and the previous trusted inspection node, determines the variation inspection node in the trusted inspection node based on the residual life variation amount, and determines the interval node quantity through the interval node data between the variation inspection node and the previous trusted inspection node. Specifically, it can be understood that in the above step, if the alternative evaluation target does not have a variation inspection node, it means that the variation risk of the alternative evaluation target is not large, and therefore it can be directly determined that it does not belong to the risk-related index.

[0050] It needs to be further explained that when different alternative evaluation targets do not have a variation inspection node, the evaluation target corresponding to the shortest matching residual life is taken as a risk-related index.

[0051] In addition, it can be understood that when the alternative evaluation target has a variation inspection node, it is also necessary to determine whether the number of variation inspection nodes of the alternative evaluation target meets the requirements. Specifically, when the number of variation inspection nodes of the alternative evaluation target does not meet the requirements, i.e. the number is greater than the threshold, the alternative evaluation target with the largest number of variation inspection nodes is taken as a risk-related target.

[0052] Further, it needs to be further explained that, if there is no alternative evaluation target whose number of variation test nodes does not meet the requirement, it is further necessary to combine the number of interval nodes of different variation test nodes. It can be understood that, in the case of smaller number of interval nodes, the variation test node data is more reliable due to shorter variation time of load data.

[0053] Specifically, when the number of variation test nodes of the interval node number of the alternative evaluation target is less than the preset node number threshold is the largest and the deviation of the number of variation test nodes of the interval node number of the other alternative evaluation targets from the number of the alternative evaluation targets is greater than the preset deviation, the alternative evaluation target with the largest number of variation test nodes with interval node number less than the preset node number threshold can be directly selected as the risk correlation target. Otherwise, it goes to the next step.

[0054] S33 determines whether the evaluation target is a risk correlation indicator of the remaining life according to the interval node number of different variation test nodes and the remaining life deviation.

[0055] Specifically, the risk correlation indicator is the evaluation target with the largest number of variation test nodes with interval node number less than the preset node number threshold and the remaining life deviation within the preset range.

[0056] In another possible embodiment, the credibility value of different variation test nodes is determined according to the ratio of the preset proportion factor of different variation test nodes to the interval node number, and the risk value is determined according to the ratio between the sum of the credibility values of different variation test nodes and the sum of the remaining life deviation and 1. The evaluation target with the largest risk value is taken as the risk correlation indicator of the remaining life.

[0057] S4 determines the evaluation processing period based on the distribution data of the credible test nodes, and determines the evaluation processing strategy of the boiler safety evaluation analysis result of the boiler based on the remaining life based on the deviation of the evaluation processing result of the remaining life in each evaluation processing period based on the distribution data.

[0058] It needs to be noted that the evaluation processing period is the period with the shortest time when the proportion of the number of credible test nodes of the risk correlation indicator is above 0.6.

[0059] Specifically, as shown in Figure 4 The method for determining the evaluation processing strategy of the boiler safety evaluation analysis result of the boiler based on the remaining life is: The historical test data is divided into different evaluation processing periods based on the evaluation processing period; determine the deviation amount of the evaluation result of the residual life of the risk-related index of the different inspection nodes in different evaluation processing periods according to the deviation of the evaluation result of the residual life in different evaluation processing periods, and determine the abnormal influence node based on the deviation amount; determine the evaluation processing strategy of the boiler safety evaluation analysis result of the boiler based on the residual life of the boiler through the number of evaluation processing periods with abnormal influence nodes and the number of associated credible nodes of the risk-related index in different evaluation processing periods.

[0060] It can be understood that the evaluation processing period is based on the current time, and the unit time corresponding to the evaluation processing period is taken as the length of the evaluation processing period. The historical inspection data is divided into different evaluation processing periods based on the length of the evaluation processing period.

[0061] Specifically, the deviation amount of the evaluation result of the residual life of the risk-related index is determined according to the deviation of the measured variation amount and the inspection variation amount of the risk-related index of the inspection node. Specifically, the deviation amount between the residual life corresponding to the measured amount of the risk-related index of the inspection node and the residual life corresponding to the predicted amount constructed by the sum of the inspection variation amount and the measured amount of the previous credible node is determined.

[0062] It can be understood that the abnormal influence node is the inspection node whose deviation amount is not within the preset deviation amount interval.

[0063] Specifically, the evaluation processing strategy of the boiler safety evaluation analysis result of the boiler based on the residual life of the boiler is determined through the number of evaluation processing periods with abnormal influence nodes and the number of associated credible nodes of the risk-related index in different evaluation processing periods, and specifically includes: determine the influence period number ratio based on the number of evaluation processing periods with abnormal influence nodes, and determine the associated node number ratio of different evaluation processing periods according to the number of associated credible nodes of the risk-related index in different evaluation processing periods; When the influence period number ratio is greater than the preset influence period number ratio, at this time, due to the greater interference risk, only when the number ratio of the variation inspection nodes of the residual life corresponding to the associated risk index in the evaluation processing period is greater than the first preset number ratio, the boiler safety evaluation analysis needs to be performed.

[0064] When the proportion of the number of influence periods is not greater than the preset proportion of the number of influence periods, at this time, due to the smaller interference risk, when the proportion of the number of associated nodes in different evaluation processing periods is greater than the preset proportion threshold, it is indicated that the credibility of the associated risk indicator is higher, and therefore, as long as the change test node of the remaining life of the associated risk indicator exists in the evaluation processing period, the evaluation analysis of the boiler safety is performed.

[0065] When the proportion of the number of associated nodes in different evaluation processing periods is not greater than the preset proportion threshold, and therefore, as long as the proportion of the number of change test nodes of the remaining life corresponding to the associated risk indicator in the evaluation processing period is above the target proportion, the evaluation analysis of the boiler safety needs to be performed.

[0066] In one possible embodiment, the target proportion is determined according to the difference between 1 and the average of the proportions of the number of associated nodes in different evaluation processing periods.

[0067] It can be understood that, in order to perform the evaluation analysis of the boiler safety, the determination of the credible test node in the current evaluation processing period is performed first, and based on the oxide layer thickness of the inner wall of the tube, the tube wall thinning rate, the conventional stress, the metal wall thickness, the tube outer diameter bulging, and the tube wall temperature of the latest credible test node, a safety evaluation analysis model is constructed to determine the evaluation analysis result of the boiler safety.

[0068] The input quantity of the safety evaluation analysis model is the oxide layer thickness of the inner wall of the tube, the tube wall thinning rate, the conventional stress, the metal wall thickness, the tube outer diameter bulging, and the tube wall temperature of the latest credible test node, and the output quantity is a safety evaluation factor, the value range of which is between 0 and 1, wherein the safety evaluation analysis model is constructed by using one or more of a BP neural network, an LSTM neural network, and an RNN neural network.

[0069] Embodiment 2 In a second aspect, the present application provides a computer system, comprising a memory and a processor connected in communication, and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to perform the above-mentioned boiler safety evaluation analysis method based on the remaining life.

[0070] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment mainly describes the difference from other embodiments. Especially, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the related parts can be referred to the part of the description of the method embodiments.

[0071] The above-described embodiments of the application have several aspects, no single one of which is solely responsible for the application's desirable attributes. Without limiting the scope of this application, several non-limiting examples of aspects of the application are described in the following paragraphs.

[0072] The foregoing is considered as illustrative only of the principles of the application. Numerous modifications and changes will readily occur to those skilled in the art, which modifications and changes are to be understood as intended to be embraced by the claims. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The scope of the application should be determined, not with reference to the above description, but rather with reference to the appended claims, along with their full scope of equivalents.

Claims

1. A method for evaluating the safety of a boiler based on the remaining life, characterized by, Specifically comprising: With the analysis result of the test data, the variation of the evaluation target of different dimensions in different test nodes is determined, and the matching degree of the variation and the operation data of the boiler is used to determine the reliable test node in the test node; Based on the distribution data and the distribution overlap data of the reliable test node of the evaluation target of different dimensions, it is determined whether the next step needs to be entered when the safety evaluation and analysis processing of the boiler using the remaining life is required; According to the analysis result of the test data of the reliable test node of the evaluation target of different dimensions, and combined with the interval node data between different reliable test nodes and adjacent reliable test nodes, the risk correlation target of the remaining life in the evaluation target is determined; The evaluation processing period is determined according to the distribution data of the reliable test node, and the evaluation processing strategy of the boiler safety evaluation and analysis result of the boiler based on the remaining life is determined based on the distribution data and the deviation of the evaluation processing result of the remaining life in each evaluation processing period.

2. The method of claim 1, wherein the remaining life-based boiler safety assessment analysis is based on a remaining life of the boiler. The evaluation target includes creep target, overheating target and wear target.

3. The method of claim 1, wherein the remaining life-based boiler safety assessment analysis is based on a remaining life of the boiler. The variation of the evaluation target is determined according to the variation amount of the evaluation result of the latest evaluation target.

4. The method of claim 1, wherein the remaining life-based boiler safety assessment analysis is based on a remaining life of the boiler. The operation data of the boiler includes the operation load data and the coal quality blending data of the boiler.

5. The method for a remaining life based boiler safety evaluation analysis as claimed in claim 1, wherein, The method for determining the reliable test node in the test node is: The variation amount of the evaluation target between the test node and the nearest reliable test node under the operation data of the boiler is determined as the test variation amount according to the matching degree of the variation of the evaluation target and the operation data of the boiler; The variation amount between the evaluation processing result of the evaluation target and the nearest reliable test node is determined as the measured variation amount based on the variation of the evaluation target; According to the deviation of the measured variation amount and the test variation amount, it is determined whether the test node is the reliable test node of the evaluation target.

6. The method for the boiler safety assessment analysis based on the residual lifetime according to claim 5, characterized by, When the deviation amount of the measured variation amount and the test variation amount is greater than the preset deviation amount threshold, it is determined that the test node does not belong to the reliable test node of the evaluation target.

7. The method for the boiler safety assessment analysis based on the remaining life according to claim 1, characterized by, The method for determining the risk correlation target of the remaining life in the evaluation target is: The remaining life of the boiler corresponding to the test data of the evaluation target in different reliable test nodes is determined as the matching remaining life according to the analysis result of the test data of the reliable test node of the evaluation target; The remaining life variation amount is determined according to the variation of the matching remaining life between different reliable test nodes and the previous reliable test node, and the variation test node in the reliable test node is determined based on the remaining life variation amount; The interval node quantity is determined through the interval node data between the variation test node and the previous reliable test node, and whether the evaluation target is the risk correlation index of the remaining life is determined according to the interval node quantity of different variation test nodes.

8. The method for the boiler safety assessment analysis based on the residual lifetime according to claim 7, characterized by, The variation test node is the reliable test node with a remaining life variation amount greater than a preset variation amount threshold.

9. The method for the boiler safety assessment analysis based on the residual lifetime according to claim 1, characterized by, The method for determining the evaluation processing strategy of the boiler safety evaluation and analysis result of the boiler based on the remaining life is: dividing the historical inspection data into different evaluation processing time periods based on the evaluation processing period; determining the deviation amount of the evaluation processing result of the residual life of the risk-related index of the different inspection nodes in different evaluation processing time periods according to the deviation of the evaluation processing result of the residual life in different evaluation processing time periods, and determining the abnormal influence node based on the deviation amount; determining the evaluation processing strategy of the boiler safety evaluation analysis result of the residual life of the boiler based on the number of evaluation processing time periods with abnormal influence nodes and the number of associated reliable nodes of the risk-related index in different evaluation processing time periods.

10. A computer system comprising: A memory and a processor connected in communication, and a computer program stored on the memory and capable of running on the processor, characterized in that the processor executes the computer program to perform the method of any one of claims 1-9.

Images