CN-122022485-A - Economizer pipeline blockage risk monitoring method and system based on intelligent recognition of working conditions

CN122022485ACN 122022485 ACN122022485 ACN 122022485ACN-122022485-A

Abstract

The application discloses an economizer pipeline blockage risk monitoring method and system based on intelligent recognition of working conditions, and relates to the technical field of flue gas treatment; the method comprises the steps of carrying out pipeline blockage risk prediction to obtain the current predicted pipeline blockage probability, calculating to obtain blockage risk deviation degree, adjusting working condition monitoring indexes and monitoring time windows to obtain optimized working condition monitoring indexes and optimized monitoring time windows, carrying out data monitoring and pipeline blockage risk prediction, and activating a jaw type disrotatory screening crusher to actively clear blockage if the predicted pipeline blockage probability exceeds a preset threshold value. The method solves the technical problems that the existing monitoring method for the pipeline blockage of the economizer depends on manual inspection or a traditional fixed threshold alarming mode, and the dynamic change of the operation working condition of the economizer and the difference of characteristic parameters in different blockage stages are ignored, so that the early warning accuracy and timeliness are insufficient.

Inventors

YIN BO
GU WENCHAO
Qiao Zixing
WANG ZHIHUI

Assignees

国家能源集团永州发电有限公司

Dates

Publication Date: 20260512
Application Date: 20260203

Claims (10)

1. The economizer pipeline blockage risk monitoring method based on the intelligent recognition of the working conditions is characterized by comprising the following steps of: taking the starting time of the operation period of the economizer as a monitoring starting point, and collecting working condition monitoring data in a preset monitoring time window according to a lightweight chemical engineering monitoring index; predicting the risk of pipeline blockage of the economizer according to the working condition monitoring data, and obtaining the current predicted pipeline blockage probability; Calculating to obtain a blockage risk deviation degree according to the current predicted pipeline blockage probability by taking a preset blockage probability curve as a reference; Respectively adjusting a working condition monitoring index and a monitoring time window according to the working condition monitoring data, the current predicted pipeline blocking probability and the blocking risk deviation degree to obtain an optimized working condition monitoring index and an optimized monitoring time window; and in the optimized monitoring time window, carrying out data monitoring and pipeline blockage risk prediction according to the optimized working condition monitoring index, and if the predicted pipeline blockage probability exceeds a preset threshold value, activating a jaw type disrotatory screening crusher to actively clear blockage.
2. The economizer line blockage risk monitoring method based on the intelligent recognition of the working conditions according to claim 1, wherein the working condition monitoring data in a preset monitoring time window is collected according to the lightweight chemical engineering monitoring index, and the method comprises the following steps: A working condition monitoring index set is configured, wherein the working condition monitoring index set comprises a combustion working condition monitoring index, a heat transfer working condition monitoring index, a soot blowing working condition monitoring index and an ash conveying working condition monitoring index, the combustion working condition monitoring index comprises a hearth outlet smoke temperature, a total coal feeding amount/load instruction and a key air quantity ratio, the heat transfer working condition monitoring index comprises an economizer inlet smoke temperature, an economizer outlet smoke temperature and an economizer smoke temperature drop, the soot blowing working condition monitoring index comprises a soot blowing steam main pipe pressure and a single soot blower accumulated operation time, and the ash conveying working condition monitoring index at least comprises a bin pump conveying peak pressure, a pressure rising rate, a conveying stage duration, a ash hopper material level, a material level falling rate, a key valve action signal and a conveying air main pipe pressure; Selecting the flue gas temperature drop of the economizer and the peak pressure of the delivery of the bin pump in the working condition monitoring index set as light working condition monitoring indexes; And acquiring a light-weight chemical data sequence in a preset monitoring time window according to the light-weight chemical data monitoring index to serve as working condition monitoring data.
3. The method for monitoring the risk of the blockage of the pipeline of the economizer based on the intelligent recognition of the working conditions according to claim 2, wherein the step of predicting the risk of the blockage of the pipeline of the economizer according to the monitoring data of the working conditions to obtain the current predicted probability of the blockage of the pipeline comprises the following steps: Calling an adaptive pipeline blockage risk prediction model according to the lightweight chemical engineering monitoring index in a preset monitoring index-prediction model library; Inputting the lightweight chemical engineering data sequence into the pipeline blockage risk prediction model, and outputting the current predicted pipeline blockage probability; The construction process of the adaptive pipeline blockage risk prediction model comprises the following steps: taking the lightweight working condition monitoring index as constraint, collecting a sample lightweight working condition data sequence set, and obtaining the historical pipeline blockage event occupancy rate of the economizer pipeline in a preset future period under the scene of different sample lightweight working condition data sequences as sample pipeline blockage probability, so as to obtain a sample pipeline blockage probability set; and training the deep learning model until convergence by taking the sample lightweight chemical engineering data sequence set as training input and the sample pipeline blockage probability set as a supervision tag to generate an adaptive pipeline blockage risk prediction model.
4. The method for monitoring the risk of the blockage of the economizer pipeline based on the intelligent recognition of the working conditions according to claim 1 is characterized by taking a preset blockage probability curve as a reference, calculating the blockage risk deviation according to the current predicted pipeline blockage probability, and comprising the following steps: Based on the historical operation log of the economizer, analyzing and obtaining a plurality of historical blocking probability curves of the operation period of the economizer; In a two-dimensional space, carrying out mean fitting on the historical blocking probability curves at the same time to obtain a preset blocking probability curve; And acquiring a jam probability reference value in the preset jam probability curve at the current moment, and taking the ratio of the probability difference value of the current predicted pipeline jam probability and the jam probability reference value to the jam probability reference value as the jam risk deviation degree.
5. The method for monitoring the risk of the blockage of the economizer pipeline based on the intelligent recognition of the working conditions according to claim 2, wherein the working condition monitoring index and the monitoring time window are respectively adjusted according to the working condition monitoring data, the current predicted pipeline blockage probability and the blockage risk deviation degree, so as to obtain an optimized working condition monitoring index and an optimized monitoring time window, and the method comprises the following steps: Respectively carrying out characteristic fluctuation analysis on the economizer flue gas temperature drop sequence and the bin pump conveying peak pressure sequence in the lightweight working condition data sequence, calculating to obtain a temperature drop variation coefficient and a pressure variation coefficient, and calculating the average value to obtain a lightweight working condition fluctuation coefficient; Acquiring an initial working condition monitoring index and an initial monitoring time window according to the current predicted pipeline blocking probability in a matching way, wherein the time length of the initial monitoring time window is inversely related to the current predicted pipeline blocking probability; Adjusting the initial condition monitoring index according to the lightweight chemical condition fluctuation coefficient and the blockage risk deviation degree to obtain an optimized condition monitoring index; and adjusting the initial monitoring time window according to the lightweight chemical engineering fluctuation coefficient and the blockage risk deviation degree to obtain an optimized monitoring time window.
6. The economizer pipeline blockage risk monitoring method based on the working condition intelligent recognition according to claim 5, wherein the monitoring index number of the initial working condition monitoring indexes is positively correlated with the current predicted pipeline blockage probability, the initial working condition monitoring indexes are selected from a working condition monitoring index sequence from top to bottom according to the corresponding monitoring index number, and the working condition monitoring index sequence is obtained by sorting a plurality of working condition monitoring indexes in the working condition monitoring index set according to the degree of correlation with the economizer pipeline blockage from large to small.
7. The economizer line blockage risk monitoring method based on condition intelligent identification of claim 6, wherein adjusting the initial condition monitoring index according to the lightweight chemical fluctuation coefficient and the blockage risk deviation comprises: if the lightweight chemical industry fluctuation coefficient is smaller than or equal to a preset standard lightweight chemical industry fluctuation coefficient and the blockage risk deviation is smaller than or equal to 0, the initial working condition monitoring index is used as an optimized working condition monitoring index; If the lightweight chemical industry fluctuation coefficient is larger than the preset standard lightweight chemical industry fluctuation coefficient, dividing the ratio of the lightweight chemical industry fluctuation coefficient to the preset standard lightweight chemical industry fluctuation coefficient by K to obtain a first index compensation coefficient, wherein K is larger than or equal to 3 and smaller than or equal to 10; if the blockage risk deviation is less than or equal to 0, taking the first index compensation coefficient as an index compensation coefficient; If the blockage risk deviation degree is greater than 0, taking the sum of the blockage risk deviation degree and the first index compensation coefficient as an index compensation coefficient; And upwardly rounding the product of the index compensation coefficient and the monitoring index number of the initial working condition monitoring index to obtain the optimized monitoring index number, and re-selecting the optimized monitoring index number from the working condition monitoring index sequence according to the optimized monitoring index number to obtain the optimized working condition monitoring index.
8. The method for monitoring risk of blockage of an economizer line based on intelligent recognition of operating conditions according to claim 7, wherein adjusting the initial monitoring time window according to the lightweight chemical fluctuation coefficient and the blockage risk deviation comprises: If the lightweight chemical industry fluctuation coefficient is smaller than or equal to a preset standard lightweight chemical industry fluctuation coefficient and the blockage risk deviation is smaller than or equal to 0, the initial monitoring time window is used as an optimized monitoring time window; If the lightweight chemical industry fluctuation coefficient is larger than the preset standard lightweight chemical industry fluctuation coefficient, dividing the ratio of the preset standard lightweight working condition fluctuation coefficient to the lightweight chemical industry fluctuation coefficient by K to obtain a first window influence coefficient; if the blockage risk deviation is smaller than or equal to 0, subtracting the first window influence coefficient from 1 to obtain a window compensation coefficient; If the blockage risk deviation degree is greater than 0, adding the first window influence coefficient and the blockage risk deviation degree to obtain a window influence coefficient, and subtracting the window influence coefficient from 1 to obtain a window compensation coefficient; And taking the product of the window compensation coefficient and the initial monitoring time window as an optimized monitoring time window.
9. The method for monitoring the risk of pipe blockage of the economizer based on intelligent recognition of working conditions according to claim 1, wherein in the optimized monitoring time window, data monitoring and pipe blockage risk prediction are performed according to the optimized working condition monitoring index, and if the predicted pipe blockage probability exceeds a preset threshold, the jaw type disrotatory screening crusher is activated to perform active blockage clearing, which comprises the following steps: In the optimized monitoring time window, carrying out data monitoring and pipeline blockage risk prediction according to the optimized working condition monitoring index, and if the predicted pipeline blockage probability does not exceed a preset threshold value, carrying out optimized adjustment on the working condition monitoring index and the monitoring time window according to working condition monitoring data, predicted pipeline blockage probability and blockage risk deviation in the previous monitoring time window; If the predicted pipeline blocking probability exceeds a preset threshold value, activating a jaw type disrotatory screening crusher to actively clear the blockage, wherein the jaw type disrotatory screening crusher is installed between an ash hopper outlet of the coal economizer and an ash conveying bin pump in series, and the structure of the jaw type disrotatory screening crusher is sequentially integrated with a screening filter screen, a disrotatory crushing mechanism and a top-bottom round transition nipple from top to bottom.
10. The economizer pipeline blockage risk monitoring system based on the intelligent recognition of the working conditions is characterized by being used for executing the economizer pipeline blockage risk monitoring method based on the intelligent recognition of the working conditions, which is disclosed in any one of claims 1-9, and comprises the following steps: the data acquisition module is used for taking the starting time of the operation period of the economizer as a monitoring starting point and acquiring working condition monitoring data in a preset monitoring time window according to the lightweight chemical engineering monitoring index; the risk prediction module is used for predicting the risk of the pipeline blockage of the economizer according to the working condition monitoring data and obtaining the current predicted pipeline blockage probability; the deviation calculation module is used for calculating and obtaining the deviation of the blockage risk according to the current predicted pipeline blockage probability by taking a preset blockage probability curve as a reference; The parameter optimization module is used for respectively adjusting the working condition monitoring index and the monitoring time window according to the working condition monitoring data, the current predicted pipeline blocking probability and the blocking risk deviation degree to obtain an optimized working condition monitoring index and an optimized monitoring time window; And the blockage clearing execution module is used for carrying out data monitoring and pipeline blockage risk prediction according to the optimized working condition monitoring index in the optimized monitoring time window, and activating a jaw type disrotatory screening crusher to actively clear blockage if the predicted pipeline blockage probability exceeds a preset threshold.

Description

Economizer pipeline blockage risk monitoring method and system based on intelligent recognition of working conditions Technical Field The application relates to the technical field of flue gas treatment, in particular to an economizer pipeline blockage risk monitoring method and system based on intelligent recognition of working conditions. Background Along with the increasingly strict environmental protection requirements and the continuous improvement of energy utilization efficiency, the economizer is used as important heat exchange equipment in a boiler system of a thermal power plant, and the running state of the economizer influences the thermal efficiency of the boiler and the safe and stable running of a unit. However, in the long-term operation process of the economizer, impurities such as fly ash, unburned carbon particles and the like carried in the flue gas are extremely easy to deposit and adhere on the inner wall of the pipeline, so that the flow cross section of the pipeline is reduced, and even the pipeline is blocked. However, in the prior art, the monitoring of the blockage of the economizer pipeline is mostly dependent on manual inspection or a traditional fixed threshold alarm mode, and the defects of strong subjectivity, long inspection period or insufficient early warning accuracy and timeliness are caused by neglecting the dynamic change of the operation working condition of the economizer and the difference of characteristic parameters in different blockage stages due to the fact that the alarm threshold is set only based on a single or a few fixed working condition parameters exist. Disclosure of Invention The embodiment of the application solves the technical problems that the existing method for monitoring the blockage of the pipeline of the economizer is mostly dependent on manual inspection or a traditional fixed threshold alarming mode, ignores the dynamic change of the operation condition of the economizer and the difference of characteristic parameters in different blockage stages, and causes insufficient early warning accuracy and timeliness by providing the method and the system for monitoring the blockage risk of the pipeline of the economizer based on the intelligent identification of the working condition. The technical scheme for solving the technical problems is as follows: In a first aspect, the application provides an economizer line blockage risk monitoring method based on intelligent recognition of working conditions, the method comprising the following steps: taking the starting time of the operation period of the economizer as a monitoring starting point, and collecting working condition monitoring data in a preset monitoring time window according to a lightweight chemical engineering monitoring index; predicting the risk of pipeline blockage of the economizer according to the working condition monitoring data, and obtaining the current predicted pipeline blockage probability; Calculating to obtain a blockage risk deviation degree according to the current predicted pipeline blockage probability by taking a preset blockage probability curve as a reference; Respectively adjusting a working condition monitoring index and a monitoring time window according to the working condition monitoring data, the current predicted pipeline blocking probability and the blocking risk deviation degree to obtain an optimized working condition monitoring index and an optimized monitoring time window; and in the optimized monitoring time window, carrying out data monitoring and pipeline blockage risk prediction according to the optimized working condition monitoring index, and if the predicted pipeline blockage probability exceeds a preset threshold value, activating a jaw type disrotatory screening crusher to actively clear blockage. In a second aspect, the application provides an economizer line blockage risk monitoring system based on intelligent recognition of working conditions, comprising: the data acquisition module is used for taking the starting time of the operation period of the economizer as a monitoring starting point and acquiring working condition monitoring data in a preset monitoring time window according to the lightweight chemical engineering monitoring index; the risk prediction module is used for predicting the risk of the pipeline blockage of the economizer according to the working condition monitoring data and obtaining the current predicted pipeline blockage probability; the deviation calculation module is used for calculating and obtaining the deviation of the blockage risk according to the current predicted pipeline blockage probability by taking a preset blockage probability curve as a reference; The parameter optimization module is used for respectively adjusting the working condition monitoring index and the monitoring time window according to the working condition monitoring data, the current predicted pipeline blocking probability and the blocking risk d