A reservoir early warning method and early warning system based on operation and maintenance data

Abstract

This invention provides a reservoir early warning method and system based on operation and maintenance data. The method includes collecting historical data; generating abnormality warning rules; revising the abnormality warning rules based on data from different periods; and using the latest abnormality warning rules for early warning. This invention provides guidance for identifying maintenance points after an earthquake, improving safety and avoiding economic losses caused by neglected maintenance. It also avoids frequent and comprehensive maintenance, saving manpower and material resources.

Description

Technical Field

[0001] The present invention relates to the technical field of fault early warning, and in particular to a reservoir early warning method and early warning system based on operation and maintenance data. Background Art

[0002] During reservoir operation and maintenance, different equipment within a reservoir has different service lives. Inspections and routine maintenance based on recorded component lifespans should ensure reservoir safety. However, in actual operation, reservoirs are affected by earthquakes. These earthquakes can originate from nearby plate movements or are caused by the reservoir's own water storage. Their intensity and frequency vary and are random. Under the influence of earthquakes, existing maintenance schedules are unlikely to guarantee the safety of reservoir operations. Performing comprehensive inspections after every earthquake would significantly increase the workload. Therefore, a method and system that can predict faults and anomalies based on both operational and maintenance conditions and earthquake conditions would improve reservoir safety and reduce economic losses. Summary of the Invention

[0003] The present invention aims to overcome the shortcomings of the prior art and provide a reservoir early warning method and system based on operation and maintenance data, thereby resolving the technical problem of the prior art in that the operational safety of reservoirs under earthquake conditions is difficult to predict and efficiently handle.

[0004] The purpose of the present invention is achieved through the following technical solutions:

[0005] The present invention provides a reservoir early warning method based on operation and maintenance data, comprising the following steps:

[0006] S1. Collect historical operation data and maintenance data of reservoirs and reservoir-related facilities within period T1; collect historical earthquake data within period T1;

[0007] S2. Evaluate and classify the operating data and maintenance data that occur during the period; screen out multiple operating anomalies in the reservoir and its related facilities that meet the early warning criteria;

[0008] S3. Analyze the corresponding relationship between each abnormal operation point and the earthquake, and generate abnormal warning rules for each abnormal operation point;

[0009] S4, collection period T n The historical operation data and historical maintenance data of the abnormal operation points within the collection period T n Historical earthquake data within, where n=i+1, i is the number of times this step is repeated;

[0010] S5. Match the historical earthquake data collected in step S4 with abnormal warning rules to obtain a predicted abnormal operation schedule;

[0011] S6. Compare the historical operation data and historical maintenance data of the abnormal operation point collected in step S4 with the abnormal operation occurrence time table in step S5; when the historical abnormal occurrence time of an abnormal operation point is earlier than the predicted abnormal operation occurrence time, the abnormal operation point is T n The abnormal warning rules are revised based on the data. When the predicted abnormal time of an abnormal operation point arrives, the historical operation data and historical maintenance data prove that there is no abnormality. A false alarm number is accumulated for the abnormal operation point. When the false alarm number reaches m, the abnormal operation point is T n Data revision abnormal warning rules;

[0012] S7. Repeat steps S4-S6 for no less than 3m times; where m is an integer greater than 1;

[0013] S8. Based on the real-time recorded operation data, maintenance data and earthquake data of the current reservoir and its related facilities, and using the latest abnormal warning rules, a real-time prediction is made for each abnormal operation point. When an abnormal operation point is predicted to have an abnormal operation, the warning system outputs a predicted abnormal operation occurrence schedule and notifies the operation and maintenance personnel to handle it. When the abnormal operation point does not actually have an abnormality, a false alarm number is accumulated for the abnormal operation point. When the false alarm number reaches m, the abnormal operation point is alarmed for a period of T. R The abnormal warning rules for the operation data, maintenance data and earthquake data of the cycle T are revised. R The m most recent actual operation anomalies including the operation anomaly point.

[0014] Optionally or preferably, the categories containing historical operation data, historical maintenance data and historical earthquake data in the period T1 should account for more than 80% of the historical categories.

[0015] Optionally or preferably, the evaluation indicators in step S2 include abnormality occurrence frequency, failure rate, and abnormality occurrence consequences.

[0016] Optionally or preferably, the predicted operation anomaly occurrence timetable in step S5 includes a time point at which each operation anomaly point will occur under calculation of anomaly warning rules.

[0017] Optionally or preferably, the value range of m is: 5≤m≤30; the value of m in step S6 and step S7 is the same; the value of m in step S8 does not need to be the same as the value of m in step S6 and step S7.

[0018] Optionally or preferably, in step S6, the same abnormal operation point is counted as a false alarm only once in each operation period. 。

[0019] The present invention also provides a reservoir early warning system, which specifically includes:

[0020] A historical data acquisition module is used to acquire historical operation data, historical maintenance data and historical earthquake data;

[0021] The abnormal warning rule generation module is used to generate abnormal warning rules and update and revise the abnormal warning rules using the information obtained in the historical data acquisition module;

[0022] Real-time data acquisition module, used to obtain real-time operation data, real-time maintenance data and real-time earthquake data;

[0023] The abnormal operation warning module is used to determine whether an operation abnormality occurs, and when the abnormal warning rule determines that an operation abnormality occurs based on the data in the real-time data acquisition module, an early warning notification is issued.

[0024] Optionally or preferably, a monitoring module is also included for monitoring the intensity and number of earthquakes and the operating status of the reservoir and reservoir-related facilities.

[0025] Based on the above technical solution, the following technical effects can be produced:

[0026] The present invention provides a reservoir early warning method and reservoir early warning system based on operation and maintenance data, which can obtain abnormal warning rules based on the acquired historical operation and maintenance information and historical earthquake information. The abnormal warning rules can be continuously revised and adjusted according to actual applications, providing guidance for the determination of post-earthquake maintenance points, which can not only improve safety and avoid economic losses caused by neglecting maintenance, but also avoid frequent and comprehensive maintenance and save manpower and material resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0028] Figure 1 Flowchart of the present invention. DETAILED DESCRIPTION

[0029] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0031] Example 1:

[0032] like Figure 1 As shown:

[0033] This embodiment provides a reservoir early warning method based on operation and maintenance data, including the following steps:

[0034] S1. Collect historical operation data and maintenance data of reservoirs and reservoir-related facilities within period T1; collect historical earthquake data within period T1;

[0035] S2. Evaluate and classify the operating data and maintenance data that occur during the period; screen out multiple operating anomalies in the reservoir and its related facilities that meet the early warning criteria;

[0036] S3. Analyze the corresponding relationship between each abnormal operation point and the earthquake, and generate abnormal warning rules for each abnormal operation point.

[0037] S4, collection period T n The historical operation data and historical maintenance data of the abnormal operation points within the collection period T n Historical earthquake data within, where n=i+1, i is the number of times this step is repeated;

[0038] S5. Match the historical earthquake data collected in step S4 with abnormal warning rules to obtain a predicted abnormal operation schedule;

[0039] S6. Compare the historical operation data and historical maintenance data of the abnormal operation point collected in step S4 with the abnormal operation occurrence time table in step S5; when the historical abnormal occurrence time of an abnormal operation point is earlier than the predicted abnormal operation occurrence time, the abnormal operation point is T n The abnormal warning rules are revised based on the data. When the predicted abnormal time of an abnormal operation point arrives, the historical operation data and historical maintenance data prove that there is no abnormality. A false alarm number e is accumulated for the abnormal operation point. When the false alarm number e reaches 10, the abnormal operation point is T n The data revision abnormal warning rule is set, and the initial value of the false alarm number e is 0;

[0040] S7, repeat steps S4-S6 thirty times;

[0041] S8. Based on the real-time recorded operation data, maintenance data and earthquake data of the current reservoir and its related facilities, and with the latest abnormal warning rules, make real-time predictions for each abnormal operation point. When an abnormal operation point is predicted to have an abnormal operation, the warning system outputs the predicted abnormal operation occurrence schedule and notifies the operation and maintenance personnel to handle it. When the abnormal operation point does not actually have an abnormality, a false alarm number is accumulated for the abnormal operation point. When the false alarm number reaches 15, the abnormal operation point is alarmed for a period of T R The abnormal warning rules for the operation data, maintenance data and earthquake data of the cycle T are revised. R The 15 most recent actual operation anomalies including the operation anomaly point.

[0042] The present invention provides a reservoir early warning system, comprising:

[0043] A historical data acquisition module is used to acquire historical operation data, historical maintenance data and historical earthquake data;

[0044] The abnormal warning rule generation module is used to generate abnormal warning rules and update and revise the abnormal warning rules using the information obtained in the historical data acquisition module;

[0045] Real-time data acquisition module, used to obtain real-time operation data, real-time maintenance data and real-time earthquake data;

[0046] The abnormal operation warning module is used to determine whether an operation abnormality occurs, and when the abnormal warning rule determines that an operation abnormality occurs based on the data in the real-time data acquisition module, an early warning notification is issued.

[0047] In this embodiment, a monitoring module is also included for monitoring the earthquake intensity, the number of earthquakes and the operating status of the reservoir and reservoir-related facilities.

[0048] Example 2:

[0049] In this embodiment, the abnormal operation point A1 that meets the warning standard is taken as an example;

[0050] The time during which the abnormal operation point A1 can operate normally in the absence of an earthquake is 200 days (theoretical lifespan); data from period T1 shows that the abnormal operation point A1 was confirmed to be normal during the inspection on the 150th day after experiencing 10 earthquakes of magnitude 2.5-2.9, and operated abnormally on the 180th day (it could not be confirmed whether it was normal during the period from the 151st day to the 179th day); the abnormal operation point A1 was confirmed to be normal during the inspection on the 150th day after experiencing 10 earthquakes of magnitude 2.0-2.4 and 10 earthquakes of magnitude 2.5-2.9, and operated abnormally on the 170th day; the abnormal warning rule is that the theoretical lifespan decreases by 10 days for every 10 earthquakes of magnitude 2.0-2.4, and decreases by 20 days for every 10 earthquakes of magnitude 2.5-3.0.

[0051] Data from period T2 showed that the abnormal operation point A1 was confirmed to be normal during the inspection on the 100th day after experiencing 10 earthquakes of magnitude 2.0-2.4 and 20 earthquakes of magnitude 2.5-2.9, but it operated abnormally on the 140th day. According to the previous abnormal warning rules, the abnormal operation would occur on the 150th day. Since the historical abnormality occurred earlier than the predicted abnormality (150th day), the abnormal warning rules were revised based on the operation and maintenance data of period T2.

[0052] Select T3, T4...T in turn 30 The abnormality warning rules are revised based on the operation and maintenance data and earthquake data. When the predicted operation anomaly occurs (day 120), the historical operation and maintenance data is confirmed to be normal during the 130th day inspection. At this time, a false alarm is accumulated. The initial value of the false alarm count is 0, and no further false alarm counts are accumulated until the next historical anomaly occurs. When the number of false alarms reaches 10, the abnormality warning rules for the operation anomaly point A1 are revised based on the data from the most recent cycle.

Claims

1. A reservoir early warning method based on operation and maintenance data, characterized by: The following steps are involved: S1. Collect historical operation data and maintenance data of reservoirs and reservoir-related facilities within period T1; collect historical earthquake data within period T1; S2. Evaluate and classify the operating data and maintenance data that occur during the period; screen out multiple operating anomalies in the reservoir and its related facilities that meet the early warning criteria; S3. Analyze the corresponding relationship between each abnormal operation point and the earthquake, and generate abnormal warning rules for each abnormal operation point; S4, collection period T n The historical operation data and historical maintenance data of the abnormal operation points within the collection period T n Historical earthquake data within, where n=i+1, i is the number of times this step is repeated; S5. Match the historical earthquake data collected in step S4 with abnormal warning rules to obtain a predicted abnormal operation schedule; S6. Compare the historical operation data and historical maintenance data of the abnormal operation point collected in step S4 with the abnormal operation occurrence time table in step S5; when the historical abnormal occurrence time of an abnormal operation point is earlier than the predicted abnormal operation occurrence time, the abnormal operation point is T n The abnormal warning rules are revised based on the data. When the predicted abnormal time of an abnormal operation point arrives, the historical operation data and historical maintenance data prove that there is no abnormality. A false alarm number is accumulated for the abnormal operation point. When the false alarm number reaches m, the abnormal operation point is T n Data revision abnormal warning rules; S7. Repeat steps S4-S6 for no less than 3m times; where m is an integer greater than 1; S8. Based on the real-time recorded operation data, maintenance data and earthquake data of the current reservoir and its related facilities, and using the latest abnormal warning rules, a real-time prediction is made for each abnormal operation point. When an abnormal operation point is predicted to have an abnormal operation, the warning system outputs a predicted abnormal operation occurrence schedule and notifies the operation and maintenance personnel to handle it. When the abnormal operation point does not actually have an abnormality, a false alarm number is accumulated for the abnormal operation point. When the false alarm number reaches m, the abnormal operation point is alarmed for a period of T. R The abnormal warning rules for the operation data, maintenance data and earthquake data of the cycle T are revised. R The m most recent actual operation anomalies including the operation anomaly point.

2. A reservoir early warning method based on operation and maintenance data according to claim 1, characterized in that: The types of historical operation data, historical maintenance data and historical earthquake data in the period T1 should account for more than 80% of the historical types.

3. The reservoir early warning method based on operation and maintenance data according to claim 1, characterized in that: The evaluation indicators in step S2 include abnormality occurrence frequency, failure rate, and abnormality occurrence consequences.

4. The reservoir early warning method based on operation and maintenance data according to claim 1, characterized in that: The predicted operation anomaly occurrence time table in step S5 includes the time point at which each operation anomaly point will occur under the calculation of the anomaly warning rule.

5. The reservoir early warning method based on operation and maintenance data according to claim 1 is characterized in that: The value range of m is: 5≤m≤30; the value of m in step S6 and step S7 is the same; the value of m in step S8 does not need to be the same as the value of m in step S6 and step S7.

6. The reservoir early warning method based on operation and maintenance data according to claim 1, characterized in that: In step S6, the same abnormal operation point will only be counted as a false alarm once in each operation period.

7. A reservoir early warning system, characterized by: The reservoir early warning method based on operation and maintenance data as claimed in claim 1 comprises: A historical data acquisition module is used to acquire historical operation data, historical maintenance data and historical earthquake data; The abnormal warning rule generation module is used to generate abnormal warning rules and update and revise the abnormal warning rules using the information obtained in the historical data acquisition module; Real-time data acquisition module, used to obtain real-time operation data, real-time maintenance data and real-time earthquake data; The abnormal operation warning module is used to determine whether an operation abnormality occurs, and when the abnormal warning rule determines that an operation abnormality occurs based on the data in the real-time data acquisition module, an early warning notification is issued.

8. A reservoir early warning system according to claim 7, characterized in that: It also includes a monitoring module for monitoring earthquake intensity, earthquake frequency and the operating status of reservoirs and reservoir-related facilities.

Images