CN-122020590-A - Wastewater environment monitoring data analysis method and system

CN122020590ACN 122020590 ACN122020590 ACN 122020590ACN-122020590-A

Abstract

The embodiment of the application provides a method and a system for analyzing wastewater environment monitoring data, which relate to the technical field of wastewater environment monitoring, and the method comprises the steps of acquiring reporting information and actual execution records of sensor maintenance or calibration from a plurality of sources; the method comprises the steps of carrying out standardized processing on reporting information and actual execution records to obtain maintenance event data, obtaining historical emission data and production activity data, identifying high-load production time periods and high-pollution emission risk time periods, carrying out time comparison on maintenance time periods indicated in the maintenance event data to obtain associated judgment results, carrying out cross validation when data are missing in the maintenance time periods to obtain consistency judgment results, carrying out characteristic analysis on monitoring data of a sensor to obtain data stability evaluation results, and generating an early warning report according to the associated judgment results, the data stability evaluation results and the consistency judgment results. The application can improve the credibility and the supervision effectiveness of the wastewater environment monitoring data.

Inventors

XU NANHAO
WANG MING
ZHU SHUYI
LV NENG

Assignees

杭州市环境保护科学研究设计有限公司

Dates

Publication Date: 20260512
Application Date: 20260128

Claims (10)

1. A method for analyzing environmental monitoring data of wastewater, comprising: Acquiring declaration information and actual execution records of sensor maintenance or calibration from multiple sources; carrying out standardized processing on the declaration information and the actual execution record to obtain maintenance event data; Acquiring historical emission data and production activity data and identifying high-load production periods and high-pollution emission risk periods; The maintenance time periods indicated in the maintenance event data are respectively compared with the high-load production time periods and the high-pollution emission risk time periods in time to obtain an association judgment result; When the data is missing in the maintenance period, cross-verifying the data missing condition and the contemporaneous production activity record to obtain a consistency judgment result of the data missing and the production activity; After the maintenance period is finished, performing characteristic analysis on the monitoring data of the sensor to obtain a data stability evaluation result after maintenance; And generating an early warning report containing an event abstract, a suspicious reason and an evidence chain according to the association judgment result, the data stability evaluation result and the consistency judgment result.
2. The method of claim 1, wherein generating an early warning report including an event summary, a suspected cause, and a chain of evidence based on the association determination, the data stability assessment, and the consistency determination comprises: acquiring historical maintenance records of sensors of the same type, and establishing a group maintenance behavior mode according to the historical maintenance records; Comparing the maintenance behavior index of the sensor indicated in the maintenance event data with the group maintenance behavior mode to obtain a difference judgment result of the maintenance behavior and the group mode; And generating an early warning report containing an event abstract, a suspicious reason and an evidence chain according to the association judgment result, the data stability evaluation result, the consistency judgment result and the difference judgment result.
3. The method of claim 2, wherein the acquiring historical emissions data and production activity data and identifying high load production periods and high pollution emission risk periods comprises: Acquiring historical emission data, wherein the historical emission data comprises historical superscalar events and pollutant concentration peaks; acquiring production activity data, wherein the production activity data comprises a production load; Identifying a high load production period from the production load; and identifying a high pollutant emission risk period according to the historical exceeding standard event and the pollutant concentration peak value.
4. The method according to claim 1, wherein the comparing the maintenance period indicated in the maintenance event data with the high-load production period and the high-pollution discharge risk period in time respectively to obtain the correlation judgment result includes: The maintenance reporting starting time and the actual maintenance ending time in the maintenance event data; Obtaining a maintenance period according to the maintenance reporting starting time and the maintenance actual ending time; the maintenance time period is respectively compared with the high-load production time period and the high-pollution emission risk time period in time to obtain overlapping duration; and comparing the overlapping time length with a preset time length to obtain a correlation judgment result.
5. The method of claim 2, wherein the obtaining a historical maintenance record of the same type of sensor, and establishing a group maintenance behavior pattern based on the historical maintenance record, comprises: acquiring historical maintenance records of the sensors of the same type, and performing standard deviation calculation on monitoring data of the historical maintenance records to obtain standard deviation data; comparing the standard deviation data with a preset standard deviation to obtain initial stability; Obtaining the maximum value and the minimum value of the monitoring data of the history maintenance record, and obtaining an initial difference value range according to the maximum value and the minimum value; comparing the monitoring data of the history maintenance record with the average data of a plurality of sensors of the same type to obtain initial average relative deviation; And establishing a group maintenance behavior mode according to the initial stability, the initial difference range and the initial average relative deviation.
6. The method of claim 5, wherein obtaining a history maintenance record of the same type of sensor, and performing standard deviation calculation on monitoring data of the history maintenance record to obtain standard deviation data, comprises: Acquiring the calibration frequency, maintenance time length and data improvement rate of the same type of sensor; and carrying out standard deviation calculation on the calibration frequency, the maintenance time and the data improvement rate to obtain standard deviation data, wherein the standard deviation data comprises a frequency standard deviation, a time standard deviation and an improvement rate standard deviation.
7. The method of claim 5, wherein after the maintenance period is over, performing a characteristic analysis on the monitored data of the sensor to obtain a maintained data stability evaluation result, comprising: After the maintenance period is finished, recalculating the initial stability, the initial difference range and the initial average relative deviation in a preset period based on a preset frequency to obtain target stability, a target difference range and a target average deviation; And respectively comparing the target stability with the initial stability, the target difference range with the initial difference range, the target average deviation and the initial average relative deviation to obtain a data stability evaluation result after maintenance.
8. The method according to claim 1, wherein when there is a data loss in the maintenance period, the cross-verifying the data loss condition with the contemporaneous production activity record to obtain a consistency determination result of the data loss and the production activity, includes: determining that there is a data loss in the maintenance period when there is a continuous data point loss in the maintenance period or the data is marked as invalid; acquiring the production order state, the equipment operation log and the material consumption record of the sensors of the same type; and carrying out cross verification on the condition of the data loss, the production order state, the equipment operation log and the material consumption record to obtain a consistency judgment result of the data loss and the production activity.
9. The method of claim 1, wherein generating an early warning report including an event summary, a suspected cause, and a chain of evidence based on the association determination, the data stability assessment, and the consistency determination comprises: Obtaining event occurrence time, event ID, drain port number, sensor type, sensor ID, judgment logic, time axis, data chart and production record according to the association judgment result, the data stability evaluation result and the consistency judgment result; obtaining an event abstract according to the event occurrence time, the event ID, the sewage outlet number, the sensor type and the sensor ID; Obtaining suspicious reasons according to the judgment logic; obtaining a evidence chain according to the time axis, the data chart and the production record; and generating an early warning report containing the event abstract, the suspicious reasons and the evidence chain according to the event abstract, the suspicious reasons and the evidence chain.
10. A wastewater environmental monitoring data analysis system, comprising: a first acquisition module for acquiring declaration information and actual execution records of sensor maintenance or calibration from a plurality of sources; the processing module is used for carrying out standardized processing on the declaration information and the actual execution record to obtain maintenance event data; a second acquisition module for acquiring historical emission data and production activity data and identifying a high-load production period and a high-pollution emission risk period; the comparison module is used for comparing the maintenance time periods indicated in the maintenance event data with the high-load production time periods and the high-pollution emission risk time periods in time respectively to obtain a correlation judgment result; The cross verification acquisition module is used for carrying out cross verification on the condition of data missing and the contemporaneous production activity record when the data missing exists in the maintenance period, so as to obtain a consistency judgment result of the data missing and the production activity; The characteristic analysis module is used for carrying out characteristic analysis on the monitoring data of the sensor after the maintenance period is finished, so as to obtain a data stability evaluation result after maintenance; And the generation module is used for generating an early warning report containing an event abstract, a suspicious reason and an evidence chain according to the association judgment result, the data stability evaluation result and the consistency judgment result.

Description

Wastewater environment monitoring data analysis method and system Technical Field The application relates to the technical field of wastewater environment monitoring, in particular to a wastewater environment monitoring data analysis method and system. Background In industrial park wastewater environmental monitoring, as monitoring systems and analytical capabilities continue to increase, new, more challenging problems begin to emerge, which are no longer merely technical failures or environmental disturbances, but rather involve artifacts. A few enterprises in the campus begin to try to avoid monitoring after fully knowing the sampling frequency, alarm threshold and data analysis logic of the monitoring system. For example, they may be subjected to short-term, high-concentration pollutant emissions within the "dead zone" of the system sampling interval, such that the instantaneous overstocked wastewater will have been run off or diluted before the next sampling point arrives, thereby evading monitoring. Or they may utilize the flexibility of the production process to make temporary dilutions upstream of the monitoring point so that the monitored data meets the standard while untreated wastewater is discharged at other concealed discharge ports or non-monitored periods. Still further, some businesses may utilize the tolerance of the system for sensor maintenance to "coincidentally" schedule sensor maintenance or calibration during critical drain periods, resulting in loss or inefficiency of monitoring data for that period. These behaviors make it impossible to capture such "intelligent" and foreseeable evasive behaviors even if the system is able to accurately identify sensor faults and environmental disturbances, because they may all be "compliant" from a single monitoring data perspective, but present serious potential risks from an overall emissions behavior and environmental impact perspective. This utilization of the "rules" of the monitoring system makes data reliability again a serious challenge, for which traditional anomaly detection methods are not desirable. Disclosure of Invention The present application aims to solve at least one of the technical problems existing in the prior art. Therefore, the application provides a method and a system for analyzing wastewater environment monitoring data, which aim to improve the credibility and the supervision effectiveness of the wastewater environment monitoring data. In a first aspect, an embodiment of the present application provides a method for analyzing environmental monitoring data of wastewater, including: Acquiring declaration information and actual execution records of sensor maintenance or calibration from multiple sources; carrying out standardized processing on the declaration information and the actual execution record to obtain maintenance event data; Acquiring historical emission data and production activity data and identifying high-load production periods and high-pollution emission risk periods; The maintenance time periods indicated in the maintenance event data are respectively compared with the high-load production time periods and the high-pollution emission risk time periods in time to obtain an association judgment result; When the data is missing in the maintenance period, cross-verifying the data missing condition and the contemporaneous production activity record to obtain a consistency judgment result of the data missing and the production activity; After the maintenance period is finished, performing characteristic analysis on the monitoring data of the sensor to obtain a data stability evaluation result after maintenance; And generating an early warning report containing an event abstract, a suspicious reason and an evidence chain according to the association judgment result, the data stability evaluation result and the consistency judgment result. According to some embodiments of the application, the generating an early warning report including an event summary, a suspected reason and an evidence chain according to the association determination result, the data stability evaluation result and the consistency determination result includes: acquiring historical maintenance records of sensors of the same type, and establishing a group maintenance behavior mode according to the historical maintenance records; Comparing the maintenance behavior index of the sensor indicated in the maintenance event data with the group maintenance behavior mode to obtain a difference judgment result of the maintenance behavior and the group mode; And generating an early warning report containing an event abstract, a suspicious reason and an evidence chain according to the association judgment result, the data stability evaluation result, the consistency judgment result and the difference judgment result. According to some embodiments of the application, the acquiring historical emissions data and production activity data and identifying high load