Early warning system and method for new energy storage power station

Abstract

The invention provides an early warning system and method for a new energy storage power station. The early warning system comprises a sensor module, a data acquisition module, a data processing and analysis module and an early warning decision module. Through a mechanism of dynamically adjusting an early warning threshold value and dynamically adjusting the early warning threshold value based on historical data and seasonal changes, early warning parameters can be automatically adjusted according to actual operation data and environmental factors of the power station through dynamically adjusting the early warning threshold value, false alarm and missing alarm are reduced, and the operation state of the power station is simulated and analyzed in real time. According to the method, an early warning strategy and an emergency response plan can be optimized, various risk scenes can be simulated under the condition that actual power station operation is not affected, support is provided for formulating more effective early warning and emergency measures, edge calculation is integrated in an early warning system, data processing and analysis tasks are distributed at the edge of a network, and the efficiency is improved. The position is close to a data source. This may reduce latency, increase response speed, and mitigate the burden on the central server.

Description

Technical Field

[0001] The present invention relates to the field of power station early warning systems, and in particular to an early warning system and method for a new energy storage power station. Background Art

[0002] With the development of new energy, energy storage power stations, as an important part of the power system, play a key role in regulating the grid load and improving energy utilization efficiency. However, due to the overheating, short circuit, overcharge / over-discharge problems that may occur in the battery pack during operation, the safety issues of energy storage power stations have become increasingly prominent. Therefore, the development of a system that can monitor and warn of potential safety hazards in real time is crucial to ensure the safe operation of energy storage power stations; Chinese invention patent application number: CN202310060669.9 proposes an early warning method and system for a new energy storage power station, including the following steps: 1) The detection terminal collects parameter information on the battery box, compares the parameter information with the set warning value, and determines the warning information based on the comparison result; 2) The detection terminal sends the warning information to the aggregation terminal, and the aggregation terminal displays the warning information.

[0003] However, the existing power plant early warning system has some shortcomings in use and still needs to be improved. First of all, the existing system often relies on the central server for data processing and analysis. The processing speed is limited by the server capacity and network latency, and it cannot achieve rapid response. The computing resources at the edge of the network cannot be fully utilized, which reduces the data processing efficiency and response speed. The system has poor scalability and flexibility, and it is difficult to adapt to the growing amount of data and complex analysis tasks. When faced with large-scale data, the central server can easily become a bottleneck, limiting the depth and breadth of data analysis and affecting the accuracy of the early warning.

[0004] Secondly, the warning thresholds in the existing technology are often static and do not adjust with the actual operating conditions and environmental factors, which may lead to false alarms and missed alarms. Static thresholds cannot accurately reflect the impact of factors such as seasonal changes, reducing the reliability and effectiveness of the warning system. Therefore, we make improvements to this and propose an early warning system and method for new energy storage power stations. Summary of the invention

[0005] The purpose of the present invention is to address the problems raised in the current background. In order to achieve the above invention purpose, the present invention provides the following scheme: an early warning system for a new energy storage power station, including a sensor module, wherein the temperature sensors, voltage sensors, and current sensors deployed at different locations of the energy storage power station are used to collect the operation data of the energy storage power station, the temperature sensor range is 40°C to +85°C, the voltage sensor range is 0V to rated voltage; the current sensor range is 0A to rated current;

[0006] The sensor module is connected to the data acquisition module, which receives the data collected by the sensor network and performs preliminary processing. The sampling frequency is to collect data at least once per second. The data storage capacity is to store one week's data and back it up.

[0007] The data acquisition module is data-connected to the data processing and analysis module, which performs in-depth analysis and processing on the received data to identify abnormal patterns; an edge computing unit is provided in the data processing and analysis module, which integrates edge computing in the early warning system and distributes data processing and analysis tasks at the edge of the network, close to the data source; this can reduce latency, improve response speed, and reduce the burden on the central server;

[0008] The data processing and analysis module is data-connected with the early warning decision module, and the early warning decision module determines whether there is a potential safety hazard and determines the early warning level according to the data processing results; a dynamic early warning threshold adjustment unit is provided in the early warning decision module, and the dynamic early warning threshold adjustment unit is a mechanism for dynamically adjusting the early warning threshold based on historical data and seasonal changes. The mechanism can automatically adjust the early warning parameters according to the actual operation data and environmental factors of the power station to reduce false alarms and missed alarms;

[0009] The early warning decision module is data-connected with the early warning output module, and the early warning output module notifies the operation and maintenance personnel of the early warning information through sound, light signal, SMS, or email;

[0010] As a preferred solution of the present invention, the battery temperature threshold of the dynamic warning threshold adjustment unit is set to 45°C. If the battery temperature exceeds this threshold, the system will trigger a warning and take heat dissipation measures;

[0011] Voltage threshold: According to the battery specifications, the upper limit is set to 4.2V and the lower limit is set to 2.5V. Once this range is exceeded, the system will issue an early warning.

[0012] Current threshold: set to 1C of the battery's rated capacity, that is, the charging and discharging currents do not exceed 1 times the battery capacity;

[0013] Ambient temperature and humidity threshold: set the ambient temperature range to 20℃ to 60℃, and the humidity range to 0% to 90%;

[0014] As a preferred solution of the present invention, the data processing frequency of the data processing and analysis module is set to collect and process data once every 5 minutes to ensure real-time monitoring;

[0015] The warning level of the early warning decision module: three levels are set, namely "yellow warning warning"; "orange emergency warning"; and "red danger warning"; response time: the system is required to issue a warning within 5 minutes after detecting a potential risk; historical data retention period: retain the historical data of the past year for analysis;

[0016] As a preferred solution of the present invention, the dynamic warning threshold adjustment unit adjusts the threshold by standard deviation to set a more sensitive and dynamic warning system. The standard deviation is an indicator describing the degree of data dispersion, and the calculation formula is:

[0017]

[0018] Among them, SD represents the standard deviation, μ is the mean of the data, and N represents the total number of data points;

[0019] X i Represents each data point. This formula essentially calculates the square root of the average of the squares of the deviations of each data point from the mean, reflecting the fluctuation range of the data set;

[0020] As a preferred solution of the present invention, the edge computing unit, each node can process data from up to 1000 sensors, each node has 1TB of storage space, and uses 1Gbps Ethernet connection;

[0021] As a preferred solution of the present invention, the edge computing formula is: Triggering an early warning;

[0022] Among them, E t is the warning value, x i is the data of the i-th sensor. The sensor data includes temperature, voltage, and w i is the corresponding weight coefficient, w i Represents different sensor data points x i For the warning value E t The degree of influence, w i The specific value of is obtained by looking up the influence degree table of different sensors, where n is the number of sensors;

[0023] E t If the preset threshold value T is exceeded, an early warning is triggered;

[0024] A method for early warning of a new energy storage power station, comprising the following, S1, system initialization and parameter setting;

[0025] S11, initializing the early warning system: starting the early warning system and performing necessary self-checks to ensure that each module is functioning normally;

[0026] S12. Setting warning parameters: According to the specific type of energy storage power station and historical performance data, the initial parameters of the warning system are set, including battery temperature threshold, voltage threshold, and current threshold;

[0027] S2. Real-time data collection:

[0028] S21. Install sensors: Install temperature sensors, voltage sensors, and current sensors at key locations of the energy storage power station to monitor the operating status of the power station in real time;

[0029] S22, data collection: collect the operation data of the power station in real time through sensors and data collection modules, including battery temperature, voltage, current, ambient temperature and humidity;

[0030] S3. Data processing and analysis:

[0031] S31. Data cleaning: pre-process the collected data to remove outliers and noise to improve the accuracy of the data;

[0032] S32, feature extraction: extract key features from the cleaned data, including temperature rise rate and voltage fluctuation frequency, for subsequent analysis;

[0033] S33. Trend analysis: Use time series analysis to analyze the changing trends of key parameters and identify whether there are abnormal fluctuations;

[0034] S34, Risk Assessment: Combine machine learning and statistical analysis methods to conduct risk assessment on the extracted features and determine the potential security risk level;

[0035] S4. Early warning judgment and notification:

[0036] S41. Early warning judgment: Based on the risk assessment results, determine whether to trigger an early warning; if the early warning conditions are met, determine the early warning level and generate early warning information;

[0037] S42. Early warning notification: The early warning system sends early warning information to the management personnel of the energy storage power station, and promptly conveys the early warning information to relevant personnel via SMS, email or automatic voice call.

[0038] As a preferred solution of the present invention, S5, early warning processing and response

[0039] S51, early warning processing: After receiving the early warning information, the energy storage power station manager will immediately confirm it and take corresponding preventive measures, including adjusting the battery working status and starting the cooling system;

[0040] S52. Emergency response: For high-risk warnings, activate the emergency response plan and conduct emergency processing to prevent the situation from escalating.

[0041] As a preferred solution of the present invention, S6, early warning feedback and system optimization:

[0042] S61, Early Warning Feedback: Record the early warning processing process and results, and feed back relevant information to the early warning system;

[0043] S62. System optimization: Based on the early warning feedback, optimize and adjust the early warning system, revise the early warning threshold, and update the risk assessment model to improve the accuracy and effectiveness of the early warning.

[0044] As a preferred solution of the present invention, S21, the temperature sensor accuracy sets the measurement accuracy of the temperature sensor to ±0.5°C; the voltage monitoring range sets the measurement range of the voltage monitor to 0-10V; and the current detection sets the measurement accuracy of the current detector to ±1%.

[0045] Compared with the existing ones, the beneficial effects of the present invention are as follows: In the scheme of the present invention: through dynamic early warning threshold adjustment, a mechanism for dynamically adjusting the early warning threshold based on historical data and seasonal changes, this mechanism can automatically adjust the early warning parameters according to the actual operation data of the power station and environmental factors, reducing false alarms and missed alarms.

[0046] Edge computing is integrated into the early warning system to distribute data processing and analysis tasks at the edge of the network, close to the source of data. This can reduce latency, increase response speed, and reduce the burden on central servers.

[0047] Digital twin model uses digital twins to create a virtual copy of the energy storage power station, simulate and analyze the operating status of the power station in real time, and optimize early warning strategies and emergency response plans by simulating different risk scenarios.

[0048] By creating a virtual copy of the energy storage power station, the operating status of the power station can be simulated and analyzed in real time. This can not only optimize the early warning strategy and emergency response plan, but also simulate various risk scenarios without affecting the actual operation of the power station, providing support for the formulation of more effective early warning and emergency measures.

[0049] By recording the warning process and results and feeding back relevant information to the warning system, the warning system is continuously optimized. This feedback-based self-optimization mechanism helps to continuously correct the warning threshold and update the risk assessment model, thereby improving the accuracy and effectiveness of the warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a diagram of system experimental data provided by the present invention. DETAILED DESCRIPTION

[0051] To make the purpose, scheme and advantages of the embodiments of the present invention clearer, the schemes in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them.

[0052] Therefore, the following detailed description of the embodiments of the present invention is not intended to limit the scope of the invention claimed for protection, but only represents some embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work are within the scope of protection of the present invention. It should be noted that the embodiments of the present invention and the features and schemes in the embodiments can be combined with each other without conflict. It should be noted that similar numbers and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0053] Example 1: Please refer to Figure 1 , an early warning system for a new energy storage power station, including a sensor module, wherein the temperature sensors, voltage sensors, and current sensors deployed at different locations of the energy storage power station are used to collect the operation data of the energy storage power station, wherein the temperature sensor range is 40°C to +85°C, the voltage sensor range is 0V to the rated voltage; the current sensor range is 0A to the rated current;

[0054] The sensor module is connected to the data acquisition module. The data acquisition module receives the data collected by the sensor network and performs preliminary processing. The sampling frequency is to collect data at least once per second. The data storage capacity is to store one week's data and back it up.

[0055] The data acquisition module is connected to the data processing and analysis module. The data processing and analysis module performs in-depth analysis and processing on the received data to identify abnormal patterns. The data processing and analysis module is equipped with an edge computing unit. The edge computing unit integrates edge computing in the early warning system and distributes data processing and analysis tasks at the edge of the network, close to the data source. This can reduce latency, improve response speed, and reduce the burden on the central server.

[0056] The data processing and analysis module is connected to the early warning decision module. The early warning decision module determines whether there are safety hazards based on the data processing results and determines the warning level. The early warning decision module is equipped with a dynamic early warning threshold adjustment unit. The dynamic early warning threshold adjustment unit dynamically adjusts the early warning threshold based on historical data and seasonal changes. This mechanism can automatically adjust the early warning parameters according to the actual operation data and environmental factors of the power station to reduce false alarms and missed alarms.

[0057] The early warning decision module is connected with the early warning output module. The early warning output module notifies the operation and maintenance personnel of the early warning information through sound, light signal, SMS and email.

[0058] Dynamic warning threshold adjustment unit, battery temperature threshold: set to 45°C. If the battery temperature exceeds this threshold, the system will trigger a warning and take cooling measures;

[0059] Voltage threshold: According to the battery specifications, the upper limit is set to 4.2V and the lower limit is set to 2.5V. Once this range is exceeded, the system will issue an early warning.

[0060] Current threshold: set to 1C of the battery's rated capacity, that is, the charging and discharging currents do not exceed 1 times the battery capacity;

[0061] Ambient temperature and humidity threshold: set the ambient temperature range to 20℃ to 60℃, and the humidity range to 0% to 90%;

[0062] Data processing frequency of the data processing and analysis module: set to collect and process data every 5 minutes to ensure real-time monitoring;

[0063] Warning level of the early warning decision module: three levels are set, namely "yellow warning warning"; "orange emergency warning"; and "red danger warning"; response time: the system is required to issue a warning within 5 minutes after detecting a potential risk; historical data retention period: retain the historical data of the past year for analysis;

[0064] The dynamic warning threshold adjustment unit adjusts the threshold by standard deviation to set a more sensitive and dynamic warning system. The standard deviation is an indicator of the degree of data dispersion, and the calculation formula is:

[0065]

[0066] Among them, SD represents the standard deviation, μ is the mean of the data, and N represents the total number of data points;

[0067] X i Represents each data point. This formula essentially calculates the square root of the average of the squares of the deviations of each data point from the mean, reflecting the fluctuation range of the data set;

[0068] Edge computing units, each node can process data from up to 1,000 sensors, each node has 1TB of storage space and uses 1Gbps Ethernet connection;

[0069] Edge computing formula: Triggering an early warning;

[0070] Among them, E t is the warning value, x iis the data of the i-th sensor. The sensor data includes temperature, voltage, and w i is the corresponding weight coefficient, w i Represents different sensor data points x i For the warning value E t The degree of influence, w i The specific value of is obtained by looking up the influence degree table of different sensors, where n is the number of sensors;

[0071] E t If the preset threshold value T is exceeded, an early warning is triggered;

[0072] The application process of edge computing in the early warning system: Data acquisition: Sensors collect key data in the energy storage power station, including temperature, voltage, and current, and send the data to the nearest edge computing node. Data preprocessing: The edge computing node preprocesses the received data, including data cleaning, formatting, and compression operations. Local data analysis: The edge computing node runs a lightweight analysis algorithm to perform a preliminary analysis of the data. Early warning judgment: According to the preset early warning threshold and analysis results, the edge computing node determines whether an early warning needs to be issued. Data transmission: If the analysis result exceeds the preset threshold, the edge computing node sends the key data and early warning information to the central processing unit or directly triggers the early warning output unit. Response and feedback: The central processing unit or the early warning output unit receives the data and early warning information, takes corresponding response measures, and sends feedback information back to the edge computing node.

[0073] Specific parameters of edge computing: Processing power: Edge computing nodes have sufficient computing power to process data input from multiple sensors. For example, each node can process data from up to 1,000 sensors. Storage capacity: Nodes have local storage capabilities for caching data and storing analysis results. Storage capacity can be configured according to actual needs. For example, each node has 1TB of storage space. Communication speed: The communication speed between edge computing nodes and sensors and central processing units must be fast enough to ensure real-time data transmission. For example, a 1Gbps Ethernet connection is used. Energy consumption: The energy consumption of edge computing nodes must be low to ensure long-term stable operation. For example, the power consumption of each node does not exceed 50 watts.

[0074] Sensor network parameters: Temperature sensor accuracy: ±0.5°C, range of 40°C to +125°C, to capture temperature changes inside and outside the energy storage power station. Voltage sensor accuracy: ±0.5%, range of 0V to 1000V, to ensure the accuracy of battery pack voltage measurement. Current sensor accuracy: ±0.5%, range of 0A to 2000A, used to monitor the charge and discharge current of the battery pack.

[0075] Data acquisition unit parameters: Sampling frequency: configurable, up to 10 times per second to meet monitoring needs in different situations. Data resolution: 16-bit ADC resolution to ensure sufficient signal quantization level. Communication interface: supports Ethernet and wireless transmission to ensure the reliability and speed of data transmission.

[0076] Data processing and analysis unit parameters: Processor speed: at least 4 core processors, main frequency above 2.0GHz to meet the needs of real-time data processing. Memory capacity: 8GB RAM or higher to ensure smoothness during data processing. Storage space: 256GB SSD or higher for storing historical data and analysis models. Warning decision unit parameters Warning response time: the time from detecting an anomaly to issuing a warning signal shall not exceed 5 seconds.

[0077] Warning output unit parameters: Sound alarm level: at least 85dB to ensure clear hearing in noisy environments. Light signal strength: LED indicator, visible distance more than 30 meters, suitable for long-distance visual warning. Notification method: SMS notification: automatically sent to the preset operation and maintenance personnel's mobile phone. Email: automatically sent to the operation and maintenance team's email address. Mobile application notification: real-time push notification sent through a dedicated operation and maintenance mobile application.

[0078] By deploying high-precision temperature, voltage and current sensors at key locations of the energy storage power station and setting high-frequency data collection (collecting data at least once per second), real-time monitoring of the power station's operating status and data accuracy are ensured. This high-frequency data update enables the system to respond quickly to any abnormal changes, thereby providing timely warnings.

[0079] Integrated edge computing distributes data analysis tasks on the edge nodes of the network, each of which has powerful data processing capabilities and storage space (for example, each node can process data from up to 1,000 sensors and has 1TB of storage space). This distributed processing architecture significantly reduces data transmission latency, improves data processing speed and efficiency, and reduces the burden on central servers.

[0080] The dynamic warning threshold adjustment unit dynamically adjusts the warning threshold based on historical data and seasonal changes. This mechanism can automatically adjust the warning parameters according to the actual operation data of the power plant and environmental factors, effectively reducing the risk of false alarms and missed alarms. In addition, the standard deviation is used to adjust the threshold, making the warning system more sensitive and adaptable to changes in actual operating conditions.

[0081] Warning information is conveyed to operation and maintenance personnel through a variety of means (sound, light signal, text message, email), ensuring timely transmission and reception of warning information. This diversified warning output method can meet different occasions and needs and improve warning efficiency and effectiveness.

[0082] By creating a virtual copy of the energy storage power station, the operating status of the power station can be simulated and analyzed in real time. This can not only optimize the early warning strategy and emergency response plan, but also simulate various risk scenarios without affecting the actual operation of the power station, providing support for the formulation of more effective early warning and emergency measures.

[0083] By recording the warning process and results and feeding back relevant information to the warning system, the warning system is continuously optimized. This feedback-based self-optimization mechanism helps to continuously correct the warning threshold and update the risk assessment model, thereby improving the accuracy and effectiveness of the warning.

[0084] Embodiment 2: A method for early warning of a new energy storage power station, comprising the following: S1, system initialization and parameter setting; S11, initialization of the early warning system: starting the early warning system and performing necessary self-checks to ensure that each module works normally; S12, setting early warning parameters: according to the specific type of the energy storage power station and historical performance data, setting the initial parameters of the early warning system, including battery temperature threshold, voltage threshold, and current threshold;

[0085] S2, real-time data collection; S21, sensor installation: temperature sensors, voltage sensors, and current sensors are installed at key locations of the energy storage power station to monitor the operating status of the power station in real time; S22, data collection: through sensors and data collection modules, the operating data of the power station is collected in real time, including battery temperature, voltage, current, ambient temperature and humidity;

[0086] S3. Data processing and analysis; S31. Data cleaning: pre-process the collected data to remove outliers and noise to improve data accuracy; S32. Feature extraction: extract key features from the cleaned data, including temperature rise rate and voltage fluctuation frequency, for subsequent analysis; S33. Trend analysis: use time series analysis to analyze the changing trends of key parameters and identify whether there are abnormal fluctuations; S34. Risk assessment: combine machine learning and statistical analysis methods to conduct risk assessment on the extracted features and determine the potential safety risk level;

[0087] S4. Early warning judgment and notification; S41. Early warning judgment: determine whether to trigger an early warning based on the risk assessment results; if the early warning conditions are met, determine the early warning level and generate early warning information; S42. Early warning notification: send early warning information to the energy storage power station management personnel through the early warning system, and convey the early warning information to relevant personnel in a timely manner through SMS, email or automatic voice call.

[0088] S5. Early warning processing and response; S51. Early warning processing: After receiving the early warning information, the energy storage power station manager will immediately confirm it and take corresponding preventive measures, including adjusting the battery working status and starting the cooling system; S52. Emergency response: For high-risk early warnings, the emergency response plan will be activated and emergency processing will be carried out to prevent the situation from escalating.

[0089] S6. Early warning feedback and system optimization; S61. Early warning feedback: record the early warning processing process and results, and feed back relevant information to the early warning system; S62. System optimization: based on the early warning feedback, optimize and adjust the early warning system, revise the early warning threshold, and update the risk assessment model to improve the accuracy and effectiveness of the early warning.

[0090] S21. The temperature sensor accuracy sets the measuring accuracy of the temperature sensor to ±0.5°C; the voltage monitoring range sets the measuring range of the voltage monitor to 0-10V; the current detection sets the measuring accuracy of the current detector to ±1%.

[0091] Adjusting the threshold by the standard deviation method is a means of utilizing data volatility to set up a more sensitive and dynamic early warning system. The standard deviation is a key indicator in statistics that describes the degree of data dispersion. Its calculation formula is:

[0092]

[0093] Among them, SD represents the standard deviation, μ is the mean of the data, and N represents the total number of data points;

[0094] X i Represents each data point. This formula essentially calculates the square root of the average of the squares of the deviations of each data point from the mean, reflecting the fluctuation range of the data set.

[0095] When the standard deviation method is used to adjust the warning threshold in the early warning system of a new energy storage power station, the threshold can be set dynamically based on the standard deviation calculated from real-time data. For example, if the standard deviation of the temperature data of an energy storage unit suddenly increases, this may mean that some abnormalities or unstable operation of the equipment have occurred. At this time, the threshold can be lowered to make the early warning system more sensitive to temperature changes, ensuring that potential problems are discovered in time to take preventive measures.

[0096] The advantage of using the standard deviation method to dynamically adjust the threshold is that it can adapt to real-time changes in data. As the data distribution changes, the standard deviation is adjusted accordingly, which in turn affects the setting of the threshold, making the early warning system more accurate and timely. In addition, by analyzing the changing trend of the standard deviation, operation and maintenance personnel can understand the stability of equipment operation and provide data support for equipment maintenance and optimization. Adjusting the threshold of the early warning system of new energy storage power stations through the standard deviation method can not only improve the accuracy and timeliness of the warning, but also provide valuable data support for the operation and maintenance decisions of the power station. This method is of great significance for achieving efficient and safe operation of energy storage power stations.

[0097] During use, the present invention starts the early warning system and performs necessary self-checks to ensure that each module works normally; according to the specific type of the energy storage power station and historical performance data, the initial parameters of the early warning system are set, including battery temperature threshold, voltage threshold, and current threshold; temperature sensors, voltage sensors, and current sensors are installed at key locations of the energy storage power station to monitor the operating status of the power station in real time; S22, data collection: through sensors and data collection modules, the operating data of the power station is collected in real time, including battery temperature, voltage, current, ambient temperature and humidity; the collected data is preprocessed to remove outliers and noise to improve the accuracy of the data; key features are extracted from the cleaned data, including the temperature rise rate and voltage fluctuation frequency, for subsequent analysis; time series analysis is used to analyze the changing trends of key parameters and identify whether there are abnormal fluctuations; combined with machine learning and statistical analysis methods, the extracted features are risk assessed to determine the potential safety risk level;

[0098] According to the risk assessment results, determine whether to trigger an early warning; if the early warning conditions are met, determine the early warning level and generate early warning information; send early warning information to the energy storage power station managers through the early warning system, and convey the early warning information to relevant personnel in a timely manner through text messages, emails or automatic voice calls. : After receiving the early warning information, the energy storage power station managers will immediately confirm it and take corresponding preventive measures, including adjusting the battery working status and starting the cooling system; for high-risk early warnings, activate the emergency response plan and carry out emergency treatment to prevent the situation from escalating.

[0099] Record the warning processing process and results, and feed back relevant information to the warning system. Based on the warning feedback, optimize and adjust the warning system, correct the warning threshold, and update the risk assessment model to improve the accuracy and effectiveness of the warning.

[0100] Experimental example

[0101] Purpose

[0102] Verify the performance of the early warning system of the new energy storage power station in real-time monitoring, dynamic warning threshold adjustment, edge computing integration, and warning accuracy.

[0103] Experimental environment

[0104] Location: New energy storage power station;

[0105] Weather: Changeable, including sunny, cloudy, rainy and other weather conditions;

[0106] Equipment: sensor module (temperature, voltage, current sensor), data acquisition module, data processing and analysis module, early warning decision module, early warning output module;

[0107] Experimental steps:

[0108] 1. System deployment: Install temperature sensors, voltage sensors, and current sensors at key locations of the energy storage power station to ensure coverage of all key monitoring points.

[0109] 2. Parameter setting: According to the historical data and operating characteristics of the energy storage power station, set the initial warning threshold (battery temperature threshold 45°C, voltage threshold 2.5V to 4.2V, current threshold 1C).

[0110] 3. Data collection: Start the early warning system, start collecting data in real time, and set the data collection frequency to once every 5 minutes.

[0111] 4. Data analysis and early warning: The data processing and analysis module receives data and performs preprocessing, feature extraction and risk assessment. The early warning decision module determines whether to trigger an early warning based on the calculation results of the dynamic early warning threshold adjustment unit and determines the early warning level.

[0112] 5. Warning output: The warning output module notifies the operation and maintenance personnel of the warning information by sound, light signal, SMS and email.

[0113] 6. Early warning response: After receiving the early warning, the operation and maintenance personnel will immediately take corresponding preventive measures, including adjusting the battery working status, starting the cooling system, etc.

[0114] 7. Data recording and system optimization: record the early warning processing process and results, and provide feedback and optimization for the early warning system.

[0115] Experimental data

[0116]

[0117] Experimental Results

[0118] Real-time: The system can monitor the operating status of the energy storage power station in real time and issue early warnings at critical moments.

[0119] Accuracy: Through dynamic early warning threshold adjustment, the system accurately reflects the actual operating risks of the power station, effectively reducing false alarms and missed alarms.

[0120] Data processing capability: The application of edge computing technology improves data processing speed and response speed, and reduces the burden on central servers.

[0121] Diversity of warning output: Multiple warning output methods ensure that warning information can be conveyed to operation and maintenance personnel in a timely manner.

[0122] Self-optimization capability: The system makes effective optimization adjustments based on early warning feedback, improving the accuracy and effectiveness of early warning.

[0123] Conclusion: The early warning system and method of the new energy storage power station of the present invention performed well in the experiment, and possessed excellent characteristics such as real-time monitoring, dynamic warning, rapid response, accurate warning and self-optimization, which significantly improved the safety management capability of the energy storage power station and helped to ensure the stability and reliability of energy supply.

[0124] The above embodiments are only used to illustrate the present invention and are not intended to limit the solutions described in the present invention. Although the present invention has been described in detail with reference to the above embodiments, the present invention is not limited to the above specific implementation methods. Therefore, any modification or replacement of the present invention; and all solutions and improvements that do not depart from the spirit and scope of the invention are included in the scope of the claims of the present invention.

Claims

1. An early warning system for a new energy storage power station, comprising a sensor module, characterized in that: The sensor module includes a temperature sensor, a voltage sensor, and a current sensor deployed in the energy storage power station to collect the operation data of the energy storage power station. The temperature sensor range is 40°C to +85°C, the voltage sensor range is 0V to the rated voltage; the current sensor range is 0A to the rated current; The sensor module is data-connected to the data acquisition module, which is used to receive data collected by the sensor network. The sampling frequency of the data acquisition module is to collect data once per second. Data storage capacity: store one week's data and back it up. The data acquisition module is data-connected to the data processing and analysis module, which analyzes and processes the received data. An edge computing unit is provided in the data processing and analysis module. The data processing and analysis module is data-connected with the early warning decision module, in which a dynamic early warning threshold adjustment unit is provided, and the dynamic early warning threshold adjustment unit dynamically adjusts the early warning threshold based on historical data and seasonal changes; the early warning decision module is data-connected with the early warning output module, and the early warning output module notifies the operation and maintenance personnel of the early warning information.

2. The early warning system for a new energy storage power station according to claim 1, characterized in that: The battery temperature threshold in the dynamic warning threshold adjustment unit is set to 45°C; the voltage threshold is set to an upper limit of 4.2V and a lower limit of 2.5V; the current threshold is set to 1C of the rated capacity of the battery, and the charging and discharging current is less than 1 times the battery capacity; the ambient temperature and humidity threshold is set to an ambient temperature range of 20°C to 60°C, and a humidity range of 0% to 90%.

3. The early warning system for a new energy storage power station according to claim 1, characterized in that: The data processing frequency of the data processing and analysis module is set to collect and process data once every 5 minutes; the early warning decision module sets three warning levels: "yellow warning", "orange emergency warning", and "red danger warning"; response time: a warning is issued within 5 minutes after a potential risk is detected; historical data retention period: 1 year of historical data is retained.

4. The early warning system for a new energy storage power station according to claim 1, characterized in that: The dynamic warning threshold adjustment unit adjusts the threshold through the standard deviation to set a dynamic warning system; the standard deviation is an indicator describing the degree of data dispersion, and the calculation formula is: Among them, SD represents the standard deviation, μ is the mean of the data, and N represents the total number of data points; X i Represents each data point.

5. The early warning system for a new energy storage power station according to claim 1, characterized in that: Each node of the edge computing unit processes data from 1,000 sensors. Each node has 1TB of storage space and uses a 1Gbps Ethernet connection.

6. The early warning system for a new energy storage power station according to claim 5, characterized in that: The edge computing formula is expressed as: Triggering an early warning; Among them, E t is the warning value, x i is the data of the i-th sensor. The sensor data includes temperature, voltage, and w i is the corresponding weight coefficient, w i Represents different sensor data points x i For the warning value E t The degree of influence, w i The specific value of is obtained by looking up the influence degree table of different sensors, where n is the number of sensors; E t If the preset threshold value T is exceeded, an early warning is triggered.

7. A method for early warning of a new energy storage power station, characterized in that: The following steps are included: S1, system initialization and parameter setting: S11, initializing the early warning system: starting the early warning system and performing a system self-check to ensure that each module is working properly; S12. Setting warning parameters: According to the type of energy storage power station and historical performance data, set the initial parameters of the warning system, including battery temperature threshold, voltage threshold, and current threshold; S2. Real-time data collection: S21. Install sensors: Install temperature sensors, voltage sensors, and current sensors in the energy storage power station to monitor the operating status of the power station; S22, data collection: collect the operation data of the power station in real time through sensors and data collection modules, including battery temperature, voltage, current, ambient temperature and humidity; S3. Data processing and analysis: S31, data cleaning: pre-process the collected data to remove outliers and noise; S32, feature extraction: extracting features from the cleaned data, the features including temperature rise rate and voltage fluctuation frequency; S33. Trend analysis: Analyze the changing trend of key parameters through time series analysis to identify whether there are abnormal fluctuations; S34. Risk assessment: Perform risk assessment through extracted features to determine the safety risk level; S4. Early warning judgment and notification: S41. Early warning judgment: Determine whether to trigger an early warning based on the risk assessment results; When the warning conditions are met, the warning level is determined and warning information is generated; S42. Early warning notification: The early warning system sends early warning information to the management personnel of the energy storage power station, and promptly conveys the early warning information to relevant personnel via SMS, email or automatic voice call.

8. The method for early warning of a new energy storage power station according to claim 7, characterized in that: S5. Early warning processing and response: S51. Early warning processing: After receiving the early warning information, the energy storage power station manager will take preventive measures, including adjusting the battery working status and starting the cooling system; S52. Emergency response: For high-risk early warnings, initiate emergency response.

9. The method for early warning of a new energy storage power station according to claim 8, characterized in that: S6. Early warning feedback and system optimization: S61. Early warning feedback: record the early warning processing process and results, and feed back the result information to the early warning system; S62. System optimization: Based on the early warning feedback, optimize and adjust the early warning system, revise the early warning threshold, and update the risk assessment model.

10. The method for early warning of a new energy storage power station according to claim 9, characterized in that: S21. The temperature sensor accuracy sets the measuring accuracy of the temperature sensor to ±0.5°C; the voltage monitoring range sets the measuring range of the voltage monitor to 0-10V; the current detection sets the measuring accuracy of the current detector to ±1%.

Images