A method for monitoring and early warning of energy storage power station battery state

Abstract

The application discloses a kind of energy storage power station battery state monitoring and safety early warning method, it is related to energy storage power station technical field, including the following steps: obtaining the historical monitoring data of each parameter of battery in energy storage power station, determine the control limit of different parameters;Real-time detection of each parameter data of single battery in energy storage power station, compare each parameter data with corresponding control limit respectively;According to different comparison results, safety state evaluation is carried out, the early warning level is determined, and the corresponding early warning control instruction is sent out, and the energy storage power station is adjusted.The application can monitor the battery state of energy storage power station in real time, according to the battery related data monitored, the safety situation of energy storage power station is early warned in stages, and the all-round safety monitoring and management of energy storage power station are realized.

Description

Technical Field

[0001] This invention relates to the field of energy storage power station technology, and more specifically to a method for monitoring the battery status and providing safety early warning in energy storage power stations. Background Technology

[0002] Energy storage power stations are established to regulate peak and off-peak electricity demand. They store the electricity that would otherwise be wasted during off-peak hours and release it back into the grid during peak hours, thus achieving peak shaving and valley filling. There are many types of energy storage, including electrochemical energy storage (lithium-ion batteries, lead-carbon batteries, flow batteries, and sodium-sulfur batteries, etc.), mechanical energy storage (flywheel energy storage, compressed air energy storage, etc.), electromagnetic energy storage (superconducting energy storage, supercapacitor energy storage), and chemical energy storage (hydrogen energy storage), among others.

[0003] Electrochemical energy storage power stations achieve energy conversion by charging and discharging the positive and negative electrodes of batteries through chemical reactions. Currently, the performance of electrochemical energy storage technology is continuously improving, and its cost is steadily decreasing. The large-scale application of energy storage systems has reached a techno-economic inflection point for commercial operation, making it a key area for research and innovation in the energy storage industry. However, energy storage applications still face problems such as asymmetric and opaque equipment technical parameters, and the lack of unified and comprehensive technical standards. There is an emphasis on post-accident measures while neglecting pre-accident prevention. In recent years, electrochemical energy storage accidents have occurred frequently, causing significant social impact, and large-scale energy storage applications still face considerable safety risks. Therefore, strengthening fire safety supervision and fire fighting in electrochemical energy storage power stations has become a key focus for their development.

[0004] The invention patent CN114497810A, entitled "A Fire Safety Energy Storage Device for an Electrochemical Energy Storage Station," modifies the structure of the energy storage chamber and staggers the placement of energy storage batteries to avoid heat concentration. It also includes liquid pipelines between the batteries to control the temperature of the energy storage chamber, and auxiliary ventilation with fans and cooling fans. Additionally, it includes a fire-extinguishing storage chamber and an explosion-proof compartment to promptly extinguish localized fire hazards and reduce the explosion radius. However, this patent only addresses fire prevention measures for the building itself, neglecting real-time monitoring of the status of energy storage units such as lithium batteries. This resulted in the failure to detect abnormal lithium battery operation in a timely manner, leading to a safety accident.

[0005] Therefore, how to monitor the battery status of energy storage power stations in real time, predict the safety status of energy storage power stations based on the monitored battery data, and issue safety warnings before a fire occurs are technical problems that urgently need to be solved by those skilled in the art. Summary of the Invention

[0006] In view of this, the present invention provides a method for monitoring the status of batteries in energy storage power stations and providing safety early warnings, which can monitor the status of batteries in energy storage power stations in real time, provide graded early warnings for fire occurrences, and take timely action to avoid serious accidents.

[0007] To achieve the above object, the present application provides the following technical solutions:

[0008] A method for monitoring and early warning of the state of a battery in an energy storage power station, comprising the following steps:

[0009] Obtaining historical monitoring data of various parameters of the battery in the energy storage power station, and determining control limits for different parameters;

[0010] Real-time detection of various parameter data of the single battery in the energy storage power station, and comparison of each parameter data with the corresponding control limit;

[0011] Safety state assessment according to different comparison results, determination of a warning level, and issuance of corresponding warning and control instructions for adjusting the energy storage power station.

[0012] The above technical solution achieves the following technical effects: real-time monitoring of various parameter data of the battery in the energy storage power station, comparison with the control limit determined for possible faults, prediction of the state of the battery in the energy storage power station, graded warning, and corresponding countermeasures to avoid more serious accidents.

[0013] Optionally, the various parameters include voltage, current, temperature in the battery pack, and state of charge (SOC).

[0014] Optionally, the determination of the control limit for different parameters comprises the following steps:

[0015] Fixed-frequency collection of historical monitoring data of the energy storage power station, pre-processing of the historical monitoring data, and obtaining of normal operation data;

[0016] Based on the normal operation data, the control limit for each parameter of each single battery is determined by using a method of kernel density estimation of a probability density function.

[0017] Optionally, the pre-processing of the historical monitoring data comprises the following steps:

[0018] Cleaning of the collected historical monitoring data to remove missing data and data beyond the given range of parameters in the historical monitoring data;

[0019] Based on a historical fault information record table, the data corresponding to the fault time are removed, and the outlier data seriously deviating from the healthy data cluster are deleted by using a local outlier factor outlier detection algorithm;

[0020] Normalization processing of the cleaned data to construct a healthy data set for normal operation of the energy storage power station.

[0021] The technical effects achieved by the above technical solutions are that a data preprocessing method is disclosed, a health data set in normal operation is constructed, and control limits corresponding to different parameters are further confirmed to improve the prediction accuracy.

[0022] Optionally, the control limits of different parameters are determined, and the method specifically includes the following steps.

[0023] If the normal operation data is represented as X=[x1, x2, …, xN], and the control limits of different parameters are represented as Y=[y1, y2, …, yM], then the control limits of different parameters are determined based on the following formula: n ] T The kernel density estimation probability density function is:

[0024]

[0025] In the formula, Y represents a bandwidth matrix, |Y| represents the determinant of Y, K(·) represents a kernel function, and K(x)≥0,

[0026] The form of the kernel function is determined, and a diagonal matrix is selected The control limits of different parameters corresponding to the energy storage power station in normal operation are obtained based on the kernel density estimation probability density function and 95% confidence.

[0027] The technical effects achieved by the above technical solutions are that the acquisition method of the control limits of different parameters is disclosed, the safety of the real-time collected parameter data of the battery is evaluated, and it is confirmed whether the energy storage power station is likely to fail, so as to adjust the state of the energy storage power station in advance.

[0028] Optionally, the warning level is determined, and the method specifically includes the following steps.

[0029] The first threshold value and the second threshold value are set, and the first threshold value is less than the second threshold value.

[0030] When the difference between the real-time detected parameter data and the corresponding control limit is less than the first threshold value, the warning level is a first-level warning, a first-level alarm information is sent to the control center, the power supply is cut off, and the energy storage power station stops working.

[0031] When the difference between the real-time detected parameter data and the corresponding control limit is between the first threshold value and the second threshold value, the warning level is a second-level warning, a second-level alarm information is sent to the control center, an audible and visual alarm signal is emitted through an audible and visual alarm, and a gas extinguishing agent is sprayed for extinguishing.

[0032] When the difference between the real-time detected parameter data and the corresponding control limit is greater than the second threshold value, the warning level is a third-level warning, a third-level alarm information is sent to the control center, an audible and visual alarm signal is emitted through an audible and visual alarm, and a gas extinguishing agent and a fine water mist extinguishing agent are sprayed for extinguishing.

[0033] The technical effects achieved by the above technical scheme are that different levels of early warning conditions and disposal modes are disclosed, and hierarchical early warning can be realized to avoid causing greater safety accidents.

[0034] Optionally, the method further comprises:

[0035] The battery pack is arranged in the battery cabin, and the air suction type smoke detector and the laser detector are arranged in the battery cabin and uniformly distributed to actively suck in the air in the battery cabin to monitor the smoke concentration value in the battery cabin.

[0036] The technical effects achieved by the above technical scheme are that the air in the battery cabin can be directly detected, and when the smoke concentration exceeds the standard, the fire extinguishing device is directly started to extinguish the fire.

[0037] Optionally, the method further comprises:

[0038] The manual alarm button is arranged, and the manual alarm button is connected with the sound and light alarm. If the automatic early warning device fails, the staff can send alarm information through the manual alarm button after discovering the fire, and extinguish the fire of the energy storage power station.

[0039] Optionally, the method further comprises:

[0040] The explosion-proof system is arranged in the battery cabin, and when it is detected that the smoke concentration exceeds the standard, the explosion-proof electric fan in the battery cabin is started through the explosion-proof system to reduce the concentration of the combustible vapor and the combustible gas in the battery cabin.

[0041] According to the above technical scheme, compared with the prior art, the energy storage power station battery state monitoring and safety early warning method disclosed has the following beneficial effects:

[0042] (1) The energy storage power station battery can be monitored in real time, and the control limit of possible failure is determined to compare with each parameter data of the energy storage power station battery, to predict whether the fire occurs in the energy storage power station, to make hierarchical early warning and take corresponding measures to avoid causing more serious accidents;

[0043] (2) The normal operation health data set is constructed to further confirm the control limit corresponding to different parameters to improve the prediction accuracy, and the acquisition mode of the different parameter control limit is disclosed to safely evaluate the real-time collected battery parameter data;

[0044] (3) The air in the battery cabin can be directly detected, and when the smoke concentration exceeds the standard, the fire extinguishing device is directly started to extinguish the fire; in addition, if the automatic early warning device fails, the staff can send alarm information through the manual alarm button after discovering the fire, and extinguish the fire of the energy storage power station. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings described below only illustrate a part of the embodiments of the present application, and all other drawings obtained by those of ordinary skill in the art without creative effort based on the provided drawings also belong to the protection scope of the present application.

[0046] Figure 1 Flow chart of the battery state monitoring and safety warning method for the energy storage power station. DETAILED DESCRIPTION

[0047] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only represent a 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 of ordinary skill in the art without creative effort also belong to the protection scope of the present application.

[0048] With the rapid growth of energy storage projects at home and abroad, safety problems are increasingly prominent, and in particular, fire incidents have attracted high attention from all sectors of society. Therefore, it is necessary to objectively and rationally view the hidden dangers exposed by accidents, and to seriously do a good job in safety protection of energy storage projects.

[0049] Therefore, in order to monitor the energy storage power station in real time, the embodiments of the present application disclose a battery state monitoring and safety warning method for an energy storage power station, as shown in the following figure, which comprises the following steps: Figure 1

[0050] Obtain historical monitoring data of each parameter of the battery in the energy storage power station, and determine the control limit of different parameters;

[0051] Real-time detect each parameter data of the single battery in the energy storage power station, and compare each parameter data with the corresponding control limit;

[0052] According to different comparison results, safety state evaluation is carried out to determine the warning level, and corresponding warning and control instructions are issued to adjust the energy storage power station.

[0053] The technical solution is based on the previously recorded historical monitoring data to confirm the control limit of different parameters corresponding to the normal operation of the energy storage power station, to compare with the real-time collected monitoring data, to predict the state of the energy storage power station, and to grade the warning of the fire situation, so that disposal measures can be taken in advance to avoid causing more serious safety accidents.

[0054] Further, the parameters include voltage, current, temperature in the battery pack, and state of charge SOC.

[0055] ​Further, the control limit of different parameters is determined, specifically including the following steps:

[0056] The historical monitoring data of the energy storage power station is collected at a fixed frequency, and the historical monitoring data is preprocessed to obtain normal operation data.

[0057] Based on the normal operation data, the control limit corresponding to each parameter of each single battery is determined by using the method of kernel density estimation of probability density function.

[0058] Further, the historical monitoring data is preprocessed, specifically including the following steps:

[0059] The collected historical monitoring data is cleaned to remove missing data and data exceeding the given range of parameters in the historical monitoring data.

[0060] Based on the historical fault information record table, the data corresponding to the fault time is removed, and the outlier data seriously deviating from the health data cluster is deleted through the local outlier factor outlier detection algorithm.

[0061] The cleaned data is normalized to construct a health data set of normal operation of the energy storage power station.

[0062] Specifically, the cleaned data is normalized to eliminate the influence of dimension; normalization is a linear transformation of the original data, which makes the transformed result fall into the interval [0, 1], and the conversion function is as follows:

[0063]

[0064] Further, the control limit of different parameters is determined, specifically including the following steps:

[0065] If the normal operation data is represented as X=[x1,x2,…,x n ] T The kernel density estimation of probability density function is:

[0066]

[0067] In the formula: Y represents a bandwidth matrix, |Y| represents the determinant of Y; K(·) represents a kernel function, and K(x)≥0,

[0068] The form of the kernel function is determined and a diagonal matrix is selected Based on the kernel density estimation of probability density function and the 95% confidence, the control limit corresponding to different parameters of the energy storage power station in normal operation is obtained.

[0069] Further, the warning level is determined, specifically including the following steps:

[0070] Set the first threshold and the second threshold, the first threshold is less than the second threshold;

[0071] When the difference between the real-time detected parameter data and the corresponding control limit is less than the first threshold, the early warning level is first level early warning, the first level alarm information is sent to the control center, the power supply is cut off, and the energy storage power station stops working;

[0072] When the difference between the real-time detected parameter data and the corresponding control limit is between the first threshold and the second threshold, the early warning level is second level early warning, the second level alarm information is sent to the control center, the sound and light alarm signal is sent through the sound and light alarm, and the gas extinguishing agent is sprayed for fire extinguishing;

[0073] When the difference between the real-time detected parameter data and the corresponding control limit is greater than the second threshold, the early warning level is third level early warning, the third level alarm information is sent to the control center, the sound and light alarm signal is sent through the sound and light alarm, and the gas extinguishing agent and the water mist extinguishing agent are sprayed for fire extinguishing.

[0074] Through the above scheme, the embodiment can realize hierarchical early warning, send alarm signals of different levels to the control center, and take corresponding disposal measures, which can predict and handle the possible fire situation of the energy storage power station in advance, avoid causing more serious safety accidents, and cause personnel casualties.

[0075] Further, the method further comprises:

[0076] The battery pack is arranged in the battery cabin, and the air suction type smoke detector and the laser detector are uniformly arranged in the battery cabin to actively suck the air in the battery cabin to monitor the smoke concentration value in the battery cabin.

[0077] Further, an explosion-proof system can also be arranged in the battery cabin, and when the smoke concentration is detected to be excessive, the explosion-proof electric fan in the battery cabin is started through the explosion-proof system to reduce the concentration of flammable vapor and flammable gas in the battery cabin.

[0078] Based on the above arrangement, it can be understood that in addition to real-time monitoring of the battery state of the energy storage power station, the air in the battery cabin can also be directly monitored, and when the smoke concentration is excessive, the flammable gas concentration can be reduced through the explosion-proof electric fan.

[0079] Further, the method further comprises:

[0080] The manual alarm button is arranged, and the manual alarm button is connected to the sound and light alarm. If the automatic early warning device fails, the staff can directly send alarm information through the manual alarm button after discovering the fire situation, and double protection can further ensure that the fire of the energy storage power station will not cause more serious consequences.

[0081] In view of the problems in the prior art, the technical scheme can monitor the various parameter data of the energy storage power station battery in real time, compare with the determined control limit that may fail, predict whether a fire occurs in the energy storage power station, grade the warning and take corresponding measures to avoid causing more serious accidents; the air in the battery cabin can also be directly detected, when the smoke concentration exceeds the standard, the fire extinguishing device is directly started to extinguish the fire; in addition, if the automatic warning device fails, the staff can send alarm information through the manual alarm button after discovering the fire, and extinguish the fire of the energy storage power station.

[0082] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same or similar parts between the various embodiments can be referred to each other. The above description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to the embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for monitoring and safety warning of energy storage power station battery state, characterized in that, The method comprises the following steps: acquiring historical monitoring data of each parameter of the battery in the energy storage power station, and determining control limits of different parameters; real-time detecting each parameter data of the single battery in the energy storage power station, and comparing each parameter data with the corresponding control limit; according to different comparison results, performing safety state evaluation to determine a warning level, and issuing a corresponding warning and control instruction to adjust the energy storage power station; determining the warning level, specifically comprising the following steps: setting a first threshold and a second threshold, the first threshold being smaller than the second threshold; when the difference between the real-time detected parameter data and the corresponding control limit is smaller than the first threshold, the warning level is a first-level warning, a first-level alarm information is sent to the control center, the power supply is cut off, and the energy storage power station stops working; when the difference between the real-time detected parameter data and the corresponding control limit is between the first threshold and the second threshold, the warning level is a second-level warning, a second-level alarm information is sent to the control center, an audible and light alarm signal is issued through the audible and light alarm, and a gas fire extinguishing agent is sprayed for fire extinguishing; when the difference between the real-time detected parameter data and the corresponding control limit is greater than the second threshold, the warning level is a third-level warning, a third-level alarm information is sent to the control center, an audible and light alarm signal is issued through the audible and light alarm, and a gas fire extinguishing agent and a water mist fire extinguishing agent are sprayed for fire extinguishing; The method further comprises: arranging the battery pack in the battery cabin, and uniformly arranging the air suction type smoke detector and the laser detector in the battery cabin to actively suck the air in the battery cabin to monitor the smoke concentration value in the battery cabin.

2. The method of claim 1, wherein, The parameters include voltage, current, temperature in the battery pack, and state of charge SOC.

3. The method of claim 1, wherein, The control limits of different parameters are determined, specifically comprising the following steps: collecting the historical monitoring data of the energy storage power station at a fixed frequency, pre-processing the historical monitoring data to obtain normal operation data; based on the normal operation data, the control limits of each parameter of each single battery are determined by using the method of kernel density estimation probability density function.

4. The method of claim 3, wherein the method further comprises: The pre-processing of the historical monitoring data specifically comprises the following steps: cleaning the collected historical monitoring data to remove missing data and data beyond the given range of parameters in the historical monitoring data; based on the historical fault information record table, the data corresponding to the fault time is removed, and the outlier data seriously deviating from the healthy data cluster is deleted through the local outlier factor outlier detection algorithm; normalizing the cleaned data to construct a healthy data set of normal operation of the energy storage power station.

5. The method of claim 3, wherein the method further comprises: The control limits of different parameters are determined, specifically comprising the following steps: If the normal operation data is denoted as The kernel density estimation probability density function is: ； where Y represents a bandwidth matrix, denotes the determinant of Y; denotes a kernel function, and , , ; Determining the form of the kernel function and selecting the diagonal matrix The control limits corresponding to different parameters in normal operation of the energy storage power station are obtained based on the kernel density estimation probability density function and 95% confidence.

6. The method of claim 1, wherein, The method further comprises: setting a manual alarm button, and connecting the manual alarm button with the audible and light alarm.

7. The method of claim 1, wherein, The method further comprises: setting an explosion-proof system in the battery cabin, and starting the explosion-proof electric fan in the battery cabin through the explosion-proof system when the smoke concentration is detected to be excessive, to reduce the concentration of flammable vapor and flammable gas in the battery cabin.

Images