Pumped storage power station operation and maintenance site environment monitoring system and monitoring method

Abstract

The invention discloses a pumped storage power station operation and maintenance site environment monitoring system and monitoring method, and relates to the technical field of pumped storage power station management, and the system comprises a data collection module, a data transmission module, a data analysis module, an alarm and decision support module, and a visual display module. The data acquisition module is used for deploying a sensor network in a monitoring area and acquiring related data including air quality, water quality indexes, noise level, soil conditions and carbon emission in real time; the data transmission module is used for uploading the collected data to the central control platform through a wireless communication technology to ensure the stability and continuity of data transmission; the data analysis module is used for cleaning, storing and analyzing the received data and evaluating an environment state and a carbon emission trend; the alarm and decision support module is used for triggering an alarm when the environmental parameter or the carbon emission exceeds a preset threshold value; and the visual display module is used for displaying the real-time data and the evaluation result through a graphical interface. The key monitoring area is fully covered, and operation and maintenance personnel are helped to recognize potential problems in advance.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pumped storage power station management, in particular to a pumped storage power station operation and maintenance field environment monitoring system and monitoring method. BACKGROUND

[0002] Pumped storage power stations play an important role in the power system, especially in peak shaving and valley filling, and have irreplaceable value in promoting new energy consumption. However, in the process of operation and maintenance of the power station, its influence on the surrounding environment and the management of carbon emissions have become urgent problems to be solved. The existing technology has the following defects in the field of environmental monitoring and evaluation:

[0003] The data collection is not complete, and the current environmental monitoring method relies on a single sensor or manual inspection, which cannot fully cover the key areas of the power station, resulting in incomplete data collection and difficulty in accurately reflecting the environmental state.

[0004] The data analysis capability is insufficient, and the traditional method lacks intelligent analysis means, and can only provide simple parameter recording and alarm function, and cannot predict the trend of environmental parameter change or quantify the carbon footprint. This limitation makes it difficult for operation and maintenance personnel to take measures in advance, increasing the potential risk.

[0005] The ecological impact assessment is missing, and the existing technology usually only focuses on individual environmental indicators such as air quality or water quality, ignoring the overall impact of the power station operation on the surrounding ecosystem. For example, the tail water discharge may cause water eutrophication or biological habitat destruction, but these impacts are often not fully considered.

[0006] The system integration is low, and there is a lack of unified communication and management mechanism between various monitoring devices and modules, resulting in serious data island phenomenon and inability to work collaboratively. In addition, the unattended capability and remote upgrade function of the system are also weak, increasing the maintenance cost.

[0007] Under this background, the present application constructs a set of environmental monitoring system and monitoring method for the operation and maintenance field of pumped storage power station, especially focusing on environmental protection and carbon emission monitoring, which has important practical significance and technical value. SUMMARY

[0008] In view of the problems existing in the current pumped storage power station operation and maintenance field environment monitoring system and monitoring method, the present application is proposed.

[0009] Therefore, the problem to be solved by the present application is the incomplete data collection, insufficient data analysis capability, missing ecological impact assessment, and low system integration.

[0010] To solve the above technical problems, the present application provides the following technical solutions, a pumped storage power station operation and maintenance field environment monitoring system and monitoring method, comprising a data acquisition module, a data transmission module, a data analysis module, an alarm and decision support module, a visual display module;

[0011] The data acquisition module is used to monitor the region to deploy a sensor network, and to collect real-time data including air quality, water quality indicators, noise level, soil condition and carbon emission related data when the pumped storage power station enters the operation and maintenance period stage; the monitoring region includes the tail water system, the underground powerhouse and the key operation and maintenance region of the slope;

[0012] The data transmission module is used to upload the collected data to the central control platform through the heterogeneous wireless communication network technology of LoRa and 5G, to ensure the stability and continuity of data transmission; the edge gateway device is used to compress and cache the data to adapt to the complex environment of the operation and maintenance field;

[0013] The data analysis module is used to clean, store and use the time series analysis algorithm for the received data, to combine the real-time energy consumption data with the preset emission factor database, to quantify the carbon footprint in the operation process of the power station, and finally to generate a carbon emission evaluation report;

[0014] The alarm and decision support module outputs the trend prediction result and the carbon footprint quantification result based on the carbon emission evaluation report, and performs an alarm action;

[0015] The visual display module is used to display various data graphs and evaluation results through a graphical interface, and supports multi-terminal access; the various data graphs include real-time data graphs, trend prediction graphs and carbon footprint heat maps.

[0016] Further,

[0017] The time series analysis algorithm is based on historical data and real-time data to predict the trend of changes in key environmental parameters;

[0018] The time series analysis algorithm used by the data analysis module is an ARIMA model or an LSTM model.

[0019] Further,

[0020] The alarm and decision support module triggers an alarm when the environmental parameters or carbon emissions exceed the dynamic threshold value adaptively adjusted by the historical operation data and environmental conditions, and provides targeted optimization decisions including device operation mode adjustment, maintenance strategy and carbon reduction suggestions according to the specific type, location and trend of the anomaly;

[0021] The dynamic threshold of the alarm and decision support module is generated adaptively according to environmental seasonality and operation conditions through machine learning algorithm analysis on historical normal operation data.

[0022] Further,

[0023] The data acquisition module includes air quality sensors, water quality sensors, noise sensors, soil sensors, and energy consumption monitoring sensors.

[0024] The air quality sensors are used to detect PM2.5, PM10, CO2 concentration, etc.

[0025] The water quality sensors are used to detect pH value, dissolved oxygen, turbidity, etc.

[0026] The noise sensors are used to collect the surrounding noise distribution.

[0027] The soil sensors are used to monitor the slope stability and pollution.

[0028] The energy consumption monitoring sensors are used to record the operating power consumption of the pumped storage unit and auxiliary systems, and to quantify carbon emission data in combination with the emission factor database.

[0029] Further,

[0030] The data analysis module uses time series analysis algorithm to predict the trend of environmental parameters and to quantify carbon footprint in combination with energy consumption data and emission factor database.

[0031] Further,

[0032] It also includes an ecological impact assessment module.

[0033] The ecological impact assessment module is used to comprehensively analyze the water quality, soil, noise, and carbon emission data provided by the data analysis module, to quantify the risk of water eutrophication, vegetation cover change, and potential disturbance of biological diversity, and to generate an ecological impact assessment report containing specific ecological restoration and operation optimization suggestions.

[0034] Further,

[0035] The modules are connected through a wireless communication network.

[0036] A pumped storage power station operation and maintenance field environment monitoring method, comprising the following steps:

[0037] S1: Set monitoring points in the monitoring area of the pumped storage power station during operation and maintenance, deploy a sensor network, and collect multi-dimensional environmental data and energy consumption data in real time.

[0038] S2: The collected data is uploaded to the central control platform via the edge gateway through the heterogeneous wireless communication network of the fusion of LoRa and 5G;

[0039] S3: The data is cleaned, stored and analyzed on the central control platform, and the time series analysis algorithm is used to predict the change trend of the environmental parameters and quantify the carbon footprint;

[0040] S4: When the environmental parameter or carbon emission trend prediction result or real-time data exceeds the dynamically preset threshold, an alarm is triggered and a targeted optimization decision suggestion is provided; S5: Real-time data, prediction trend, carbon footprint and decision suggestion are synchronously and associatively displayed through a graphical interface, multi-terminal access is supported, and a closed-loop operation and maintenance management process covering environmental monitoring, trend prediction, carbon accounting, alarm and decision is formed.

[0041] 9. The pumped storage power station operation and maintenance field environment monitoring method of claim 6,

[0042] characterized in that,

[0043] the steps of cleaning, storing and analyzing the data in the step S3 include:

[0044] S3.1: removing outliers using the median+MAD method or the Z-score method;

[0045] S3.2: using linear interpolation or mean filling method;

[0046] S3.3: predicting the change trend of the environmental parameters based on the ARIMA or LSTM time series analysis algorithm; combining real-time energy consumption data and an emission factor database to quantify the carbon footprint and generate a carbon emission evaluation report.

[0047] The present application has the following advantages:

[0048] 1. The present application comprehensively covers key areas, and sensor networks are deployed in key areas such as tail water systems, underground powerhouses and slopes to collect air quality, water quality, noise, soil conditions and energy consumption data in real time, and multiple types of sensors such as air quality sensors, water quality sensors and noise sensors are integrated to ensure the comprehensiveness and accuracy of data collection.

[0049] 2. The present application performs intelligent data analysis, and the data analysis module uses the (ARIMA or LSTM) time series analysis algorithm to predict the change trend of the environmental parameters, helps the operation and maintenance personnel to identify potential problems in advance, and combines the energy consumption data and the emission factor database to accurately quantify the carbon footprint and generate a carbon emission evaluation report, providing a scientific basis for the realization of the "double carbon" goal.

[0050] 3、The application has ecological impact comprehensive evaluation, introduces an ecological impact evaluation module, combines environmental data and carbon emission data, evaluates the influence of power station operation on the surrounding ecosystem, and the ecological impact evaluation report covers water body eutrophication, vegetation coverage change, biodiversity influence and the like, thereby providing decision support for green operation and maintenance.

[0051] 4、The application has high integration and unattended design, each module is connected through a wireless communication network, realizes real-time transmission and cooperative work of data, supports unattended operation, and can realize remote upgrade and optimization of system function, thereby significantly reducing maintenance cost. BRIEF DESCRIPTION OF DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor. Among them:

[0053] Figure 1 The scene diagram of the pumped storage power station operation and maintenance field environment monitoring method. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0055] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0056] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. "In one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.

[0057] The application is described in detail in combination with the schematic diagram, and in the detailed description of the embodiments of the application, the cross-sectional view of the device structure is partially enlarged without the general proportion for the convenience of illustration, and the schematic diagram is only an example, which should not limit the scope of protection of the application herein. In addition, the three-dimensional spatial dimensions of length, width and depth should be included in actual production.

[0058] Meanwhile, in the description of the application, it should be noted that the terms "upper, lower, inner and outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the application. In addition, the terms "first, second or third" are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0059] Unless otherwise specifically defined and limited, the terms "mounting, connecting, connecting" in the application should be understood broadly, for example: it can be fixed connection, detachable connection or integral connection; it can also be mechanical connection, electrical connection or direct connection, it can also be indirectly connected through intermediate medium, or it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the application can be understood according to the specific circumstances.

[0060] Embodiment 1

[0061] The embodiment provides a pumped storage power station operation and maintenance field environment monitoring system, comprising a data acquisition module, a data transmission module, a data analysis module, an alarm and decision support module, and a visualization display module.

[0062] The data acquisition module is used to deploy a sensor network in a monitoring area in the pumped storage power station entering the operation and maintenance period stage, and to collect real-time data including air quality, water quality indicators, noise level, soil condition and carbon emission related data; the monitoring area includes tail water system, underground powerhouse and slope key operation and maintenance area;

[0063] The data transmission module is used to upload the collected data to the central control platform through the heterogeneous wireless communication network technology of LoRa and 5G, to ensure the stability and continuity of data transmission; the edge gateway device is used to compress and cache the data to adapt to the complex environment of the operation and maintenance field;

[0064] The data analysis module is used to clean, store and adopt time series analysis algorithm for the received data, to combine real-time energy consumption data with preset emission factor database, to quantify carbon footprint in the operation process of the power station, and finally to generate carbon emission evaluation report;

[0065] The alarm and decision support module performs alarm actions based on the trend prediction results and carbon footprint quantification results output by the carbon emission assessment report;

[0066] The visualization display module displays various data graphs and assessment results through a graphical interface, supporting multi-terminal access; the various data graphs include real-time data graphs, trend prediction graphs, and carbon footprint heat maps.

[0067] The time series analysis algorithm is used to predict the change trend of key environmental parameters based on historical data and real-time data;

[0068] The time series analysis algorithm used by the data analysis module is an ARIMA model or an LSTM model.

[0069] The alarm and decision support module triggers an alarm when the environmental parameters or carbon emissions exceed the dynamic threshold value adaptively adjusted by historical operation data and environmental conditions, and provides targeted optimization decisions including device operation mode adjustment, maintenance strategy, and carbon reduction suggestions according to the specific type, location, and trend of the anomaly;

[0070] The dynamic threshold value of the alarm and decision support module is adaptively generated based on environmental seasonality and operating conditions through machine learning algorithms analyzing historical normal operation data.

[0071] The data collection module includes air quality sensors, water quality sensors, noise sensors, soil sensors, and energy consumption monitoring sensors.

[0072] The air quality sensor is used to detect PM2.5, PM10, CO2 concentration, etc.

[0073] The water quality sensor is used to detect pH, dissolved oxygen, turbidity, etc.

[0074] The noise sensor is used to collect the surrounding noise distribution;

[0075] The soil sensor is used to monitor the slope stability and pollution;

[0076] The energy consumption monitoring sensor is used to record the operating power consumption of the pumped storage unit and auxiliary systems, and to quantify carbon emission data in combination with the emission factor database.

[0077] The data analysis module uses a time series analysis algorithm to predict the change trend of environmental parameters and quantifies the carbon footprint in combination with energy consumption data and the emission factor database.

[0078] It also includes an ecological impact assessment module.

[0079] The ecological impact assessment module is used to comprehensively analyze the water quality, soil, noise and carbon emission data provided by the data analysis module, to quantitatively evaluate the risk of water eutrophication, vegetation cover change and potential disturbance of biodiversity, and to generate an ecological impact assessment report containing specific ecological restoration and operation optimization suggestions.

[0080] The modules are connected through a wireless communication network.

[0081] Specifically, the specific sensor types include:

[0082] Air quality sensor: detects PM2.5, PM10, CO2 concentration, etc.

[0083] Water quality sensor: detects pH, dissolved oxygen, turbidity, etc.

[0084] Noise sensor: collects the distribution of ambient noise;

[0085] Soil sensor: monitors the stability of the slope and the pollution situation;

[0086] Energy consumption monitoring sensor: records the consumption of operating power as the basis for carbon emission calculation.

[0087] Data transmission module: through wireless communication technology LoRa, NB-IoT or 5G, upload the collected data to the central control platform to ensure the stability and continuity of data transmission. The edge gateway device performs preliminary processing and caching on the received data to reduce the computing pressure of the cloud.

[0088] After the data collection module receives the raw data, the data analysis module first performs data cleaning to remove outliers and fill in missing values to ensure data quality.

[0089] The cleaned data is stored in the database and saved in chronological order to support historical data query. This storage method facilitates subsequent trend prediction and anomaly analysis.

[0090] The data analysis module uses time series analysis algorithm to predict the trend of environmental parameters.

[0091] For example, predict the downward trend of dissolved oxygen in tailwater system to early warn the possible risk of water eutrophication; analyze the change rule of CO2 concentration in underground powerhouse to evaluate the operation effect of ventilation system;

[0092] At the same time, combined with the energy consumption data and emission factor database, the carbon footprint in the process of power plant operation is quantified, and a carbon emission assessment report is generated.

[0093] When the environmental parameters or carbon emissions exceed the preset threshold, the alarm and decision support module will immediately trigger an alarm signal and provide optimization suggestions according to the specific situation.

[0094] For example, if the tailwater system turbidity exceeds the standard, it is recommended to increase the cleaning frequency of the sedimentation tank; if the noise level in the underground powerhouse is too high, it is recommended to adjust the equipment operation time or increase the sound insulation measures.

[0095] The alarm mechanism uses dynamic threshold setting, which adjusts the alarm threshold adaptively based on historical data analysis to avoid false positives or false negatives caused by fixed thresholds.

[0096] The system also includes an ecological impact assessment module to comprehensively assess the impact of power plant operation on the surrounding ecosystem and generate an ecological impact assessment report. The assessment content covers:

[0097] Water body eutrophication degree, combined with dissolved oxygen, turbidity and other indicators of the tailwater system for analysis;

[0098] Vegetation coverage change, reflecting the health of vegetation through soil moisture, slope stability and other data;

[0099] Biodiversity impact, using noise, water quality and other data to assess the impact of power plant operation on animal habitats.

[0100] The ecological impact assessment report not only contains the analysis results of the current state, but also proposes improvement suggestions, such as optimizing the tailwater discharge process or adjusting the equipment operation mode to reduce the negative impact on the ecosystem.

[0101] The visualization display module presents all real-time data and assessment results through a graphical interface, supporting multi-terminal access such as Web and mobile. Interface functions include real-time data display, historical data comparison, multi-dimensional display;

[0102] Real-time data display, showing the trend of environmental parameters and carbon emissions in the form of dynamic curves or heat maps;

[0103] Historical data comparison, supporting time period query and analysis of historical data to help operation and maintenance personnel find potential problems;

[0104] Multi-dimensional display, showing air quality, water quality, noise and other multi-dimensional data at the same time, making it easy to grasp the overall environmental status.

[0105] All modules are connected through a wireless communication network, supporting unattended operation. For example:

[0106] The data collection module uploads sensor data to the edge gateway device through LoRa technology;

[0107] The edge gateway device transmits data to the cloud server through the 5G network;

[0108] After the cloud server completes data analysis, the results are sent to the visualization display module and the alarm and decision support module.

[0109] In addition, the system has a remote upgrade function, and the operation and maintenance personnel can update the module software through the Web or mobile terminal to optimize the system performance.

[0110] Embodiment 2

[0111] On the basis of the first embodiment, the embodiment further provides a pumped storage power station operation and maintenance field environment monitoring method, comprising the following steps,

[0112] S1: In the monitoring area of the pumped storage power station operation and maintenance period, set up monitoring points, deploy sensor network, and collect multi-dimensional environment data and energy consumption data in real time.

[0113] Specifically, the method is applied to the operation and maintenance period of the power station. In the three key operation and maintenance areas of tail water system, underground powerhouse and slope, the monitoring points are accurately set. The deployed sensor network includes water quality sensors (for pH value, dissolved oxygen, turbidity), air quality sensors (for PM2.5, PM10, CO2 concentration), noise sensors, soil sensors (for humidity, stability) and energy consumption monitoring sensors specially used for recording the operation of pumped storage units and auxiliary systems. Energy consumption. These sensors work in parallel to ensure the comprehensiveness of data collection.

[0114] S2: The collected data is uploaded to the central control platform through the edge gateway via the heterogeneous wireless communication network of LoRa and 5G.

[0115] Specifically, to solve the transmission problem in the complex environment of the operation and maintenance site, the heterogeneous wireless communication scheme of "LoRa + 5G" is adopted. The sensor data is first uploaded to the nearest edge gateway device through LoRa technology. The gateway compresses and caches the data to reduce the transmission load and cope with network fluctuations. Then, the processed data is transmitted to the central control platform through the high-speed 5G network.

[0116] S3: Clean, store and analyze the data on the central control platform, and use time series analysis algorithm to predict the trend of environmental parameter change and quantify carbon footprint.

[0117] Specific implementation: this step corresponds to claim 9. In the central control platform, the following sub-steps are executed:

[0118] S3.1 (outlier processing): Use the median + MAD method or Z-score method to clean the original data, effectively removing noise data caused by device interference or transient abnormalities.

[0119] S3.2 (Missing value filling): For the missing values that may occur in data transmission or storage, linear interpolation or mean filling method is used for reasonable filling to ensure the integrity of the data sequence.

[0120] S3.3 (Trend prediction and carbon footprint quantification): The cleaned and normalized data is stored in time series. Then, based on ARIMA or LSTM time series analysis algorithm, the trend of key environmental parameters (such as tail water dissolved oxygen, plant CO2 concentration) is predicted. At the same time, combined with real-time energy consumption data and pre-set emission factor database, the carbon footprint of the power station in a specific period is accurately quantified, and a structured carbon emission evaluation report is generated.

[0121] S4: When the trend prediction results or real-time data of environmental parameters or carbon emissions exceed the dynamically preset threshold, an alarm is triggered and targeted optimization decision suggestions are provided.

[0122] Specifically, the alarm mechanism of the method is not static. The system uses machine learning algorithms to analyze historical normal operation data to adaptively generate and adjust dynamic thresholds that take into account seasonal and operating conditions. Once the trend prediction results or real-time data flow in S3 step exceeds this dynamic threshold, the system immediately triggers an alarm. At the same time, according to the specific type of the anomaly (such as water quality, air, noise), location (tail water system, plant) and change trend, targeted optimization decisions including device operation mode adjustment, maintenance strategy and carbon reduction suggestions are provided. For example, if the tail water dissolved oxygen is predicted to decrease, it is recommended to "increase the operation time of the aeration device"; if the carbon emissions are abnormally high, it is recommended to "check the unit operation efficiency".

[0123] S5: Through a graphical interface, real-time data, prediction trends, carbon footprint and decision suggestions are synchronously and associated displayed, supporting multi-terminal access, forming a closed-loop operation and maintenance management process covering environmental monitoring, trend prediction, carbon accounting, alarm and decision-making.

[0124] Specifically, through a unified graphical interface (supporting Web and mobile), all the results of S1 to S4 steps are synchronously and associated displayed. Operation and maintenance personnel can view real-time data graphs, trend prediction graphs, carbon footprint heat maps and decision suggestions generated by S4 in the same interface. This not only provides an intuitive monitoring view, but also links all the links together, ultimately forming a closed-loop operation and maintenance management process from data collection to intelligent decision-making, significantly improving the initiative and intelligent level of operation and maintenance.

[0125] The embodiment details the specific implementation steps of the pumped storage power station operation and maintenance field environmental monitoring method, forming a complete closed-loop process. Through intelligent analysis and ecological impact assessment, this method not only improves the efficiency and accuracy of environmental monitoring, but also provides a scientific basis for the green operation of the power station.

[0126] Example 3

[0127] The verification experiment and economic benefit calculation of the pumped storage power station operation site environment monitoring method are based on the first two examples. This example provides a pumped storage power station operation site environment monitoring method, and verifies its beneficial effects through simulation experiments and economic benefit calculation.

[0128] Experimental environment: Simulate the actual operation and maintenance scene of pumped storage power stations, build a test platform containing key areas such as tail water systems, underground workshops, and slopes.

[0129] Hardware configuration:

[0130] Water quality sensor, model: YSI EXO2: Detects pH, dissolved oxygen, turbidity, etc.

[0131] Air quality sensor, model: SenseAir K30: Detects PM2.5, PM10, CO2 concentration

[0132] Noise sensor, model: CEL-614: Collects surrounding noise distribution

[0133] Soil sensor, model: Decagon EC-5: Monitors slope stability and pollution

[0134] Energy consumption monitoring sensor, model: Eastron SDM320: Records running power consumption data as the basis for carbon emission calculation

[0135] Wireless communication module: Heterogeneous wireless communication combining LoRa gateway and 5G module, transmission distance up to 10km, ensuring real-time data transmission to the central control platform.

[0136] Software platform: Data analysis module based on time series analysis algorithms such as ARIMA or LSTM, predicts environmental parameter change trends

[0137] Ecological impact assessment module combines historical operation data recorded in industrial databases for dynamic threshold optimization.

[0138] Comparison method: Traditional environmental monitoring methods rely on manual inspection or single sensor deployment, with the following limitations:

[0139] Incomplete data collection, only providing local environmental information

[0140] Lack of intelligent analysis means, unable to provide early warning of potential problems

[0141] Fixed threshold setting for alarm mechanism, high false alarm rate (about 10%-15%), about 5% false negative rate

[0142] There is no comprehensive ecological impact assessment function, which is difficult to fully reflect the impact of power station operation on the surrounding ecosystem.

[0143] Evaluation indicators:

[0144] False alarm rate: the proportion of system error triggered alarms; response time: the time delay from detecting anomalies to taking measures; annual maintenance cost: including component replacement, manual maintenance and other expenses; correction success rate: the proportion of successful correction of environmental anomalies or reduction of carbon emissions; system robustness: the normal operation time under complex interference environment (such as heavy rain, low temperature, noise);

[0145] Data generation: create a simulated data set containing the following content:

[0146] Dynamic scenarios:

[0147] Tailwater system dissolved oxygen change range (4 mg / L-8 mg / L);

[0148] Underground powerhouse CO2 concentration fluctuation (600 ppm-1200 ppm);

[0149] Slope soil humidity random change (10%-30%).

[0150] Interference factors:

[0151] Heavy rain: simulate the increase of rainfall leading to the increase of turbidity in tailwater system;

[0152] Low temperature environment: simulate the impact of winter temperature drop on equipment operation;

[0153] High noise level: simulate the noise disturbance during equipment start-up or shutdown (80 dB-120 dB).

[0154] Method implementation:

[0155] This method:

[0156] Tailwater system monitoring: install water quality sensors in the tailwater system, collect data every hour; use edge gateway devices for preliminary processing (such as compression, caching), and upload to cloud server through LoRa technology; data analysis module predicts the downward trend of dissolved oxygen and warns of possible water eutrophication risk in advance.

[0157] Underground powerhouse monitoring: install air quality sensors and noise sensors in the underground powerhouse to collect CO2 concentration and noise level data in real time; dynamic threshold setting function adjusts the alarm threshold according to historical data analysis to avoid false alarms or missed alarms caused by fixed threshold.

[0158] Slope area monitoring: install soil sensors in the slope area to monitor humidity, stability and pollution.

[0159] Slope landslide risk assessment combined with weather data (e.g. rainfall, temperature changes).

[0160] Carbon emission quantification: Record the power consumption of the power plant in a certain period as 3000kWh, according to the emission factor database (0.5kg CO2 per kWh), calculate the carbon emission of this period as 1500kg CO2.

[0161] Ecological impact assessment: Comprehensive analysis of changes in dissolved oxygen, turbidity and other indicators of tailwater system, to assess the impact on downstream fish survival; use soil moisture, slope stability and other data to reflect vegetation growth and potential landslide risk.

[0162] Traditional method:

[0163] Depend on manual inspection or single sensor deployment, data collection coverage is about 70%;

[0164] Fixed threshold setting, false positive rate is as high as 15%, false negative rate is about 5%;

[0165] No carbon emission quantification function, also lack of comprehensive ecological impact assessment ability.

[0166] Experimental execution: Test period, continuous operation for 72 hours, simulate 30 days of typical working conditions (including normal operation, mild abnormality, severe abnormality and interference environment).

[0167] Test process: Daily cycle, alternatingly set the following states:

[0168] Normal operation: Environmental parameters are within reasonable range;

[0169] Mild abnormality: Dissolved oxygen in tailwater system drops below 5mg / L, CO2 concentration in underground plant rises above 800ppm;

[0170] Severe abnormality: Turbidity in tailwater system exceeds 15NTU, soil moisture in slope reaches saturation state;

[0171] Interference environment: Simulate extreme working conditions such as heavy rain (rainfall 100mm / hour), low temperature (-5℃), high noise (120dB) etc.

[0172] Maintenance simulation: Record manual inspection frequency and sensor replacement requirements for traditional method; Record camera cleaning and algorithm calibration maintenance requirements for this method.

[0173] Data collection: Collect performance data of both methods on various evaluation indicators.

[0174] Analysis:

[0175] False positive rate is reduced:

[0176] Traditional methods have a false alarm rate of up to 15% due to fixed threshold settings and human judgment errors.

[0177] This method significantly improves anti-interference ability through dynamic threshold setting and multi-dimensional data analysis, reducing false alarm rate to 2%.

[0178] Response time is shortened:

[0179] Traditional methods require manual confirmation of alarm signals before taking measures, with an average time consumption of 30 seconds.

[0180] This method achieves automatic response through PLC linkage, shortening response time to <5 seconds.

[0181] Maintenance cost is optimized:

[0182] Traditional methods require frequent replacement of sensors or manual inspection, with an annual maintenance cost of about 30,000 yuan.

[0183] This method only needs to clean the camera regularly and update the algorithm, reducing the annual maintenance cost to 0.8 million yuan, significantly reducing the operation and maintenance burden.

[0184] Correction success rate is improved:

[0185] Traditional methods can only trigger alarms and require manual reset, with a correction success rate dependent on response speed, about 60%.

[0186] This method achieves a 95% success rate through dynamic threshold adjustment and active intervention, such as automatically increasing aeration device operation time or adjusting ventilation mode.

[0187] System robustness is enhanced:

[0188] Traditional methods are prone to failure in interference environments such as heavy rain and low temperature, and usually require downtime for maintenance after 12 hours of operation.

[0189] This method ensures continuous and stable operation of the system for up to 72 hours in complex interference environments through the combination of sensor networks and wireless communication technology.

[0190] Specific case analysis: Taking "tail water system dissolved oxygen drop" as an example:

[0191] Experimental conditions:

[0192] Simulate heavy rain weather, rainfall 100mm / hour;

[0193] The dissolved oxygen in the tail water system drops from 6mg / L to 4.5mg / L, and the turbidity rises to 12NTU.

[0194] Execution process of this method:

[0195] Data Collection: Water quality sensors collect data every hour and upload to edge gateway devices through LoRa technology;

[0196] Data Analysis: A continuous downward trend in dissolved oxygen is discovered, predicting a drop below 4 mg / L within the next 24 hours, triggering an alarm and recommending increasing aeration device operation time;

[0197] Ecological Impact Assessment: Considering the turbidity of the tailwater system rising to 12 NTU, the impact on downstream water organisms is assessed, and the tailwater discharge process is recommended for optimization;

[0198] Visual Presentation: Real-time data and assessment results are viewed through the web, and operation and maintenance personnel adjust the aeration device in time, successfully restoring dissolved oxygen to the normal range (5.2 mg / L), avoiding potential ecological damage.

[0199] It should be noted that the above examples are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and they should be included in the scope of the claims of the present application.

Claims

1. A pumped storage power station operation and maintenance field environment monitoring system, characterized in that, The system comprises a data acquisition module, a data transmission module, a data analysis module, an alarm and decision support module, and a visual display module. The data acquisition module is used to monitor the deployment of a sensor network in the monitoring area during the operation and maintenance period of the pumped storage power station, and to collect real-time data including air quality, water quality, noise level, soil condition, and carbon emission-related data. The data transmission module is used to upload the collected data to the central control platform via the edge gateway device through the heterogeneous wireless communication network technology of LoRa and 5G, to ensure the stability and continuity of data transmission. The edge gateway device is used to compress and cache the data to adapt to the complex environment of the operation and maintenance site. The data analysis module is used to clean and store the received data, and to use a time series analysis algorithm to combine real-time energy consumption data with a pre-set emission factor database to quantify the carbon footprint during the operation of the power station, and finally generate a carbon emission evaluation report. The alarm and decision support module outputs trend prediction results and carbon footprint quantification results based on the carbon emission evaluation report, and performs alarm actions. The visual display module is used to display various data graphs and evaluation results through a graphical interface, and supports multi-terminal access.

2. The pumped storage power station operation and maintenance site environment monitoring system of claim 1, characterized in that the time series analysis algorithm is based on historical data and real-time data to predict the trend of changes in key environmental parameters; the time series analysis algorithm used by the data analysis module is an ARIMA model or an LSTM model.

3. The pumped storage power station operation and maintenance site environment monitoring system of claim 1, characterized in that the alarm and decision support module triggers an alarm when the environmental parameters or carbon emissions exceed the dynamic threshold value adjusted by historical operation data and environmental conditions, and provides targeted optimization decisions including device operation mode adjustment, maintenance strategy, and carbon reduction suggestions according to the specific type, location, and trend of the anomaly; the dynamic threshold value of the alarm and decision support module is generated adaptively based on environmental seasonality and operating conditions through machine learning algorithm analysis of historical normal operation data.

4. The pumped storage power station operation and maintenance site environment monitoring system of claim 1, characterized in that the data acquisition module includes air quality sensors, water quality sensors, noise sensors, soil sensors, and energy consumption monitoring sensors; the air quality sensors are used to detect PM2.5, PM10, CO2 concentration, etc.; the water quality sensors are used to detect pH, dissolved oxygen, turbidity, etc.; the noise sensors are used to collect ambient noise distribution; the soil sensors are used to monitor the stability and pollution of the slope; the energy consumption monitoring sensors are used to record the operating power consumption of the pumped storage unit and auxiliary systems, and to quantify carbon emission data in combination with the emission factor database.

5. The pumped storage power station operation and maintenance site environment monitoring system of claim 1, Characterized in that, The data analysis module adopts a time series analysis algorithm to predict the trend of environmental parameter changes and quantifies the carbon footprint in combination with energy consumption data and an emission factor database.

6. The pumped storage power station operation site environment monitoring system of claim 1, Characterized in that, It further comprises an ecological impact assessment module; The ecological impact assessment module is used to comprehensively analyze the water quality, soil, noise and carbon emission data provided by the data analysis module, to quantitatively assess the water eutrophication risk, vegetation coverage change and potential disturbance to biodiversity, and to generate an ecological impact assessment report containing specific ecological restoration and operation optimization suggestions.

7. The pumped storage power station operation site environment monitoring system of claim 1, Characterized in that, The modules are connected through a wireless communication network.

8. A pumped storage power station operation site environment monitoring method, The pumped storage power station operation site environment monitoring system of any one of claims 1-7 is used, Characterized in that, It comprises the following steps: S1: Setting up monitoring sites in the monitoring area of the pumped storage power station during the operation period, deploying a sensor network, and collecting multi-dimensional environmental data and energy consumption data in real time; S2: Collecting data through a heterogeneous wireless communication network that fuses LoRa and 5G, and uploading the collected data to a central control platform via an edge gateway; S3: Cleaning, storing and analyzing data on the central control platform, and using a time series analysis algorithm to predict the trend of environmental parameter changes and quantify the carbon footprint; S4: When the trend prediction results or real-time data of environmental parameters or carbon emissions exceed the dynamically preset threshold, triggering an alarm and providing targeted optimization decision suggestions; S5: Through a graphical interface, synchronously and associatively displaying real-time data, prediction trends, carbon footprint and decision suggestions, supporting multi-terminal access, and forming a closed-loop operation and management process covering environmental monitoring, trend prediction, carbon accounting, alarm and decision-making.

9. The pumped storage power station operation site environment monitoring method of claim 6, Characterized in that, The steps of cleaning, storing and analyzing data in step S3 include: S3.1: Removing outliers using the median+MAD method or the Z-score method; S3.2: Using linear interpolation or mean filling method; S3.3: Predicting the trend of environmental parameter changes based on ARIMA or LSTM time series analysis algorithm; quantifying the carbon footprint in combination with real-time energy consumption data and an emission factor database, and generating a carbon emission assessment report.

Images