Prompt information management method and device, storage medium and electronic device

Abstract

The invention discloses a prompt information management method and device, a storage medium and an electronic device. The method comprises the following steps: acquiring N groups of monitoring data uploaded by N types of sensing components; processing the N groups of monitoring data to obtain N groups of data features; the risk level of a target area monitored by using the N types of sensor assemblies is evaluated according to the N groups of data features, early warning prompt information is sent to a management object managing the target area based on the risk level, at least energy storage equipment exists in the target area, and N is a positive integer. By adopting the technical scheme, the problem that comprehensive fire risk monitoring of the energy storage power station cannot be realized is solved. And furthermore, the monitoring data uploaded by the N types of sensing assemblies are processed, the risk level of the target area is evaluated, and early warning information is sent. Through multi-dimensional monitoring and intelligent analysis, the accuracy and timeliness of early warning are improved, and the safe operation level of the energy storage power station is improved.

Description

Technical Field

[0001] The present application relates to the field of energy storage power station safety technology, and more specifically, to a prompt information management method and device, a storage medium, and an electronic device. Background Art

[0002] With the rapid development of new energy technologies, energy storage power stations, as the "power bank" of the power system, play an increasingly important role in balancing power supply and demand and improving the stability of the power grid. However, the safe operation of energy storage power stations also faces many challenges, especially the monitoring and management of the battery compartment level has become the key. The electric energy stored in the energy storage power station and the chemical energy storage media that may be used (such as lithium-ion batteries) are all subject to fire risks. In the battery compartment of the energy storage power station, the performance and safety of the battery directly affect the stable operation of the entire system. In order to monitor the various parameters in the battery compartment in real time and ensure that the battery operates within a safe range, a variety of sensor monitoring technologies have emerged. These sensors are like the "eyes" and "ears" of the energy storage system, constantly monitoring the key parameters such as temperature, pressure, flow, current, voltage and gas concentration in the battery compartment. Temperature sensors are an indispensable component. Traditional fire detection systems often rely on a single or a few sensors, which are difficult to fully cover various fire precursors and early fire characteristics, and there is a risk of missed reports and false reports.

[0003] With regard to the problem in related technologies that comprehensive fire risk monitoring of energy storage power stations cannot be achieved, no effective solution has been proposed so far.

[0004] Therefore, it is necessary to improve the related technology to overcome the above-mentioned defects in the related technology. Summary of the invention

[0005] The embodiments of the present application provide a method and device for managing prompt information, a storage medium, and an electronic device, so as to at least solve the problem that it is impossible to achieve comprehensive fire risk monitoring of energy storage power stations.

[0006] According to one aspect of an embodiment of the present application, a method for managing prompt information is provided, including: acquiring N groups of monitoring data uploaded by N types of sensor components; processing the N groups of monitoring data to obtain N groups of data features; evaluating the risk level of a target area monitored by the N types of sensor components according to the N groups of data features, and sending early warning prompt information to a management object of the target area based on the risk level, wherein there is at least energy storage equipment in the target area, and N is a positive integer.

[0007] In an exemplary embodiment, after evaluating the risk level of the target area monitored using N types of sensor components based on N groups of data features, the method further includes: determining the fire probability corresponding to the risk level; when the fire probability is greater than or equal to a preset trigger probability, linking the fire extinguishing equipment in the target area to control the fire extinguishing equipment to be in operation; when the fire probability is less than the preset trigger probability, sending an inspection reminder message to the management object, wherein the inspection reminder message is used to instruct the management object to issue a task to maintain the equipment in the target area to the maintenance object after receiving the early warning prompt for the target area.

[0008] In an exemplary embodiment, N groups of monitoring data are processed to obtain N groups of data features, including: performing data preprocessing on each group of monitoring data in the N groups of monitoring data to obtain N first data sets, wherein the data preprocessing includes one of the following operations: data cleaning, data standardization, data normalization, and data conversion; performing filtering processing on the N first data sets to obtain N second data sets, wherein the filtering processing is used to eliminate interference data in the first data sets; performing feature extraction based on the N second data sets to obtain N groups of data features, wherein the feature extraction includes at least one of the following extraction methods: time domain feature extraction method, frequency domain feature extraction method, time-frequency feature extraction method, and statistical feature extraction method.

[0009] In an exemplary embodiment, after processing N groups of monitoring data to obtain N groups of data features, the above method also includes: determining the collection types corresponding to the N groups of data features respectively; when there are matching types for multiple target collection types in a preset chart database, recording the target monitoring data corresponding to the current matching type and the target chart template associated with the current matching type; determining the target type sensor component corresponding to the target monitoring data; and recording all real-time data uploaded by the target type sensor component after the preset collection period.

[0010] In an exemplary embodiment, all real-time data uploaded by the target type sensor component after a preset collection period is recorded, including: inputting all real-time data into a target chart template to obtain a visual monitoring chart corresponding to the target type sensor; synchronizing the visual monitoring chart to a visual interface that allows management object operations, and receiving operation instructions input from the visual interface to adjust the display of the visual monitoring chart.

[0011] In an exemplary embodiment, after evaluating the risk level of a target area monitored using N types of sensor components according to N groups of data features, and sending early warning information to a management object that manages the target area based on the risk level, the method further includes: obtaining a management strategy generated by the management object for the early warning information, and determining an execution result of the management strategy; determining whether the early warning information is valid according to the execution result, so as to adjust the information content of the early warning information.

[0012] According to another aspect of an embodiment of the present application, a prompt information management device is also provided, including: a first acquisition module, used to acquire N groups of monitoring data uploaded by N types of sensor components; a processing module, used to process the N groups of monitoring data to obtain N groups of data features; an evaluation module, used to evaluate the risk level of a target area monitored using N types of sensor components according to the N groups of data features, and send early warning prompt information to a management object of the target area based on the risk level, wherein there is at least energy storage equipment in the target area, and N is a positive integer.

[0013] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned prompt information management method when running.

[0014] According to another aspect of an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the prompt information management method through the computer program.

[0015] According to another aspect of the embodiment of the present application, a computer program product is provided, including a computer program and a method for managing the above-mentioned prompt information when the computer program is executed by a processor.

[0016] Through this application, N groups of monitoring data uploaded by N types of sensor components are obtained; the N groups of monitoring data are processed to obtain N groups of data features; the risk level of the target area monitored by the N types of sensor components is evaluated according to the N groups of data features, and based on the risk level, early warning information is sent to the management object of the target area, wherein there is at least energy storage equipment in the target area, and N is a positive integer. The above technical solution solves the problem of being unable to achieve comprehensive fire risk monitoring of energy storage power stations. Furthermore, by processing the monitoring data uploaded by N types of sensor components, the risk level of the target area is evaluated and early warning information is sent. Through multi-dimensional monitoring and intelligent analysis, the accuracy and timeliness of early warnings are improved, and the safe operation level of energy storage power stations is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 It is a hardware structure block diagram of a computer terminal of a prompt information management method according to an embodiment of the present application;

[0020] Figure 2 is a flow chart of a method for managing prompt information according to an embodiment of the present application;

[0021] Figure 3 It is a structural schematic diagram of a fire detection sensor and management system based on multi-physical parameter data fusion according to an embodiment of the present application;

[0022] Figure 4 It is a structural block diagram of prompt information management according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal, a mobile terminal or a similar computing device. Taking running on a computer terminal as an example, Figure 1 1 is a hardware structure block diagram of a computer terminal according to a method for managing prompt information in an embodiment of the present application. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 The computer terminal includes a processor 102 (only one is shown in the figure) (the processor 102 may include but is not limited to a processing device such as a microprocessor (Central Processing Unit, CPU) or a programmable logic device (Field Programmable Gate Array, FPGA)) and a memory 104 for storing data, wherein the computer terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0026] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the management method of prompt information in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0027] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0028] In this embodiment, a method for managing prompt information is provided. Figure 2 is a flowchart of a method for managing prompt information according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps S202-S206:

[0029] Step S202: Acquire N groups of monitoring data uploaded by N types of sensor components;

[0030] Step S204: Processing the N groups of monitoring data to obtain N groups of data features;

[0031] Step S206: Evaluate the risk level of the target area monitored by the N types of sensor components according to the N groups of data features, and send early warning information to the management object that manages the target area based on the risk level, wherein there is at least energy storage equipment in the target area, and N is a positive integer.

[0032] The above steps obtain N groups of monitoring data uploaded by N types of sensor components; process the N groups of monitoring data to obtain N groups of data features; evaluate the risk level of the target area monitored by the N types of sensor components based on the N groups of data features, and send early warning information to the management object that manages the target area based on the risk level, wherein there is at least energy storage equipment in the target area, and N is a positive integer. The above technical solution solves the problem of being unable to achieve comprehensive fire risk monitoring of energy storage power stations. Furthermore, by processing the monitoring data uploaded by N types of sensor components, the risk level of the target area is evaluated and early warning information is sent. Through multi-dimensional monitoring and intelligent analysis, the accuracy and timeliness of early warnings are improved, and the safe operation level of energy storage power stations is improved.

[0033] In an exemplary embodiment, after evaluating the risk level of the target area monitored using N types of sensor components based on N groups of data features, the method further includes: determining the fire probability corresponding to the risk level; when the fire probability is greater than or equal to a preset trigger probability, linking the fire extinguishing equipment in the target area to control the fire extinguishing equipment to be in operation; when the fire probability is less than the preset trigger probability, sending an inspection reminder message to the management object, wherein the inspection reminder message is used to instruct the management object to issue a task to maintain the equipment in the target area to the maintenance object after receiving the early warning prompt for the target area.

[0034] Optionally, a certain energy storage power station uses an intelligent monitoring system to monitor the probability of fire in real time and determines the preset trigger probability to be 5%. When the system detects that the probability of fire is greater than or equal to 5%, it automatically links the fire extinguishing equipment in the target area to keep the equipment in operation to deal with potential fire risks. When the probability of fire is less than 5%, the system will send inspection reminder messages to managers to remind them to inspect the target area to ensure the normal operation of the equipment and reduce the possibility of failure. Through this step, the energy storage power station can effectively prevent fire risks and ensure the safe operation of equipment.

[0035] In an exemplary embodiment, N groups of monitoring data are processed to obtain N groups of data features, including: performing data preprocessing on each group of monitoring data in the N groups of monitoring data to obtain N first data sets, wherein the data preprocessing includes one of the following operations: data cleaning, data standardization, data normalization, and data conversion; performing filtering processing on the N first data sets to obtain N second data sets, wherein the filtering processing is used to eliminate interference data in the first data sets; performing feature extraction based on the N second data sets to obtain N groups of data features, wherein the feature extraction includes at least one of the following extraction methods: time domain feature extraction method, frequency domain feature extraction method, time-frequency feature extraction method, and statistical feature extraction method.

[0036] Optionally, data cleaning is to remove or correct outliers, missing values ​​or erroneous data; data standardization is to scale the data to a uniform range, such as 0 to 1 or -1 to 1, to eliminate the impact of different dimensions; data normalization is to convert the data into a distribution with zero mean and unit variance, which helps the performance of some algorithms; data transformation may include logarithmic transformation, square root transformation, etc. to reduce the skewness of the data.

[0037] Optionally, the N first data sets are filtered, and the filters used include but are not limited to one of the following: a low-pass filter, a high-pass filter, a band-pass filter, a band-stop filter, and a Kalman filter; wherein the low-pass filter is used to remove high-frequency noise and retain the low-frequency components of the signal; the high-pass filter is used to remove low-frequency components and retain high-frequency signals; the band-pass filter allows signals within a specific frequency range to pass while suppressing signals of other frequencies; the band-stop filter blocks signals within a specific frequency range and allows signals of other frequencies to pass; the Kalman filter is a recursive filter used to estimate the state of a linear dynamic system and can handle noise and uncertainty.

[0038] Optionally, in the above embodiments, the time domain feature extraction method is to extract features directly from time series data, such as mean, variance, peak, etc.; the frequency domain feature extraction method is to extract features from the frequency components of the signal through methods such as Fourier transform; the time-frequency feature extraction method is to combine time domain and frequency domain analysis, such as wavelet transform, which can consider time and frequency information at the same time; the statistical feature extraction method is to extract features based on statistical methods, such as mean, standard deviation, skewness, kurtosis, etc.

[0039] Optionally, morphological features and machine learning features are also commonly used features for feature extraction. Specifically, morphological features are features that describe the shape of a signal, such as the peaks and troughs of a signal; machine learning features are features extracted using machine learning algorithms (such as principal component analysis PCA, linear discriminant analysis LDA, etc.).

[0040] In an exemplary embodiment, after processing N groups of monitoring data to obtain N groups of data features, the above method also includes: determining the collection types corresponding to the N groups of data features respectively; when there are matching types for multiple target collection types in a preset chart database, recording the target monitoring data corresponding to the current matching type and the target chart template associated with the current matching type; determining the target type sensor component corresponding to the target monitoring data; and recording all real-time data uploaded by the target type sensor component after the preset collection period.

[0041] Optionally, a set of energy storage power station monitoring data is processed to determine the characteristics of each data. These characteristics are then matched with the preset collection type to determine the collection type corresponding to each set of data, such as CO concentration, smoke concentration, etc. After determining the collection type, chart templates matching these two collection types are found in the preset chart database, namely, CO concentration alarm chart and smoke concentration monitoring chart. At the same time, the target sensing components corresponding to the CO sensor and optical smoke sensor are determined to be the electrochemical CO sensor and the optical smoke sensor, respectively, and the real-time data uploaded by them are recorded. Through the above steps, we can have a clearer understanding of the characteristics and collection types of this set of energy storage power station monitoring data, as well as the related target monitoring data and sensor components, which provide a basis and basis for subsequent data analysis and monitoring.

[0042] In an exemplary embodiment, all real-time data uploaded by the target type sensor component after a preset collection period is recorded, including: inputting all real-time data into a target chart template to obtain a visual monitoring chart corresponding to the target type sensor; synchronizing the visual monitoring chart to a visual interface that allows management object operations, and receiving operation instructions input from the visual interface to adjust the display of the visual monitoring chart.

[0043] Optionally, if the target sensing component in the above embodiment is an audio sensor, the preset acquisition period is 10 minutes. After 10 minutes, all real-time data collected by the sensor are input into the audio burst analysis monitoring chart template to obtain a visual monitoring chart corresponding to the audio sensor. The monitoring chart is then synchronized to the visual interface, and the user can input operation instructions through the interface to zoom in, zoom out, switch, and perform other operations on the monitoring chart, so as to more clearly observe the changing trend of the audio waveform and adjust the display mode of the monitoring chart in time. Through this process, the user can easily monitor the data of the audio sensor and perform corresponding operations and processing according to the display of the monitoring chart.

[0044] In an exemplary embodiment, after evaluating the risk level of a target area monitored using N types of sensor components according to N groups of data features, and sending early warning information to a management object that manages the target area based on the risk level, the method further includes: obtaining a management strategy generated by the management object for the early warning information, and determining an execution result of the management strategy; determining whether the early warning information is valid according to the execution result, so as to adjust the information content of the early warning information.

[0045] Optionally, if the temperature of the battery in the energy storage power station rises abnormally, the system will generate early warning information based on the collected data, indicating that the battery may be faulty. Based on this information, a management strategy is formulated: immediately stop the battery charging and discharging operations, arrange maintenance personnel to check the battery status, and replace the damaged battery module. After executing the management strategy, it was found that the battery was indeed faulty. After timely replacement, the energy storage power station resumed normal operation. By checking the execution results, it was determined that the early warning information was effective, and the management strategy was adjusted to prevent possible accidents.

[0046] Obviously, the embodiments described above are only some embodiments of the present application, not all embodiments. In order to better understand the above method, the above process is described below in conjunction with the embodiments, but it is not intended to limit the technical solutions of the embodiments of the present application, specifically:

[0047] The optional embodiment of the present application provides a fire detection sensor and management method based on multi-physical parameter data fusion to solve the problem of being unable to achieve comprehensive fire risk monitoring of energy storage power stations. This method integrates multiple sensors, combines advanced signal processing technology and intelligent analysis algorithms, realizes all-round and multi-level monitoring of fire risks in energy storage power stations, and conducts real-time monitoring by designing seven monitoring charts, providing intuitive and accurate fire warning information for power station managers.

[0048] Optional, Figure 3It is a structural schematic diagram of a fire detection sensor and management system based on multi-physical parameter data fusion according to an embodiment of the present application. The above system includes at least: a semiconductor VOC sensor 31, a metal oxide semiconductor hydrogen sensor 32, an electrochemical CO sensor 33, an optical smoke sensor 34, an optical flame sensor 35, a high-definition camera 36, ​​and an audio sensor 37.

[0049] Optionally, semiconductor VOC sensor 31. Monitor the concentration of volatile organic compounds in the air and warn of potential combustion precursors. When VOC molecules in the air of the battery compartment enter the sensor and react or adsorb with the adsorption material, it will cause changes in the electronic structure inside the sensor, thereby changing the resistance of the sensor. The sensor contains electrodes, and the VOC concentration is determined by measuring the change in resistance. This change is proportional to the VOC concentration. Therefore, the VOC concentration in the air can be calculated by measuring the change in resistance value. According to the different working principles of VOC sensors, they can also be divided into electrochemical gas sensors (such as resistance, current, impedance, potential, etc.), optical sensors (including spectral absorption, fluorescence, visualization, etc.) and mass gas sensors (such as quartz crystal microbalance and surface acoustic wave gas sensors). Among them, the conductivity type VOC sensor based on semiconductor metal oxide is the most widely used. Its principle is to use the characteristics of changes in resistance or work function when the semiconductor contacts the gas to realize the detection of gas. The specific debugging steps are as follows:

[0050] Step 1: Connection and power supply. Connect the VOC sensor to the test equipment (such as data logger, computer, etc.) correctly, and ensure that the sensor has a stable power supply. Pay attention to check whether the power supply voltage of the sensor meets the requirements, and avoid damage to the sensor due to excessive or low voltage.

[0051] Step 2: Calibration and testing. Before formal use, the VOC sensor needs to be calibrated. The calibration process usually involves placing the sensor in a VOC gas environment with a known concentration and adjusting the sensor's output value to match the actual concentration. After the calibration is completed, testing can be performed to verify the accuracy and stability of the sensor.

[0052] Step 3: Adjust parameters. Adjust the sensor's measurement range, sensitivity, response time and other parameters according to actual needs. The settings of these parameters will affect the sensor's performance indicators such as measurement accuracy and response time.

[0053] Step 4: Troubleshooting. During use, if the sensor fails or the measured value is abnormal, troubleshooting is required. Common faults include sensor damage, loose connection lines or poor contact. When troubleshooting, it is necessary to carefully check the various components and connection lines of the sensor and repair or replace them as needed.

[0054] Optionally, a metal oxide semiconductor hydrogen sensor 32 is used to monitor hydrogen leakage that may be generated by energy storage devices such as lithium batteries in real time. This sensor uses metal oxides (such as SnO2, ZnO, WO3, etc.) as gas-sensitive materials. When hydrogen is adsorbed on these materials, it releases electrons and combines with oxygen ions in the material, causing the carrier concentration to change, thereby changing the resistance of the material. By measuring the change in resistance, the concentration of hydrogen can be indirectly measured. The specific debugging steps are as follows:

[0055] Step 1: Initial condition setting. Before debugging, you need to ensure that the sensor is in the initial state, such as adjusting the bridge to make it in a balanced state, that is, the bridge output voltage is 0.

[0056] Step 2: Test environment preparation. Place the hydrogen sensor in the test chamber, and lead the power cord and the wires connected to the nodes to be tested from the base of the test chamber. Ensure that the test environment is stable and controllable for accurate testing.

[0057] Step 3: Concentration gradient test. Control the flow of hydrogen gas of known concentration and record the corresponding voltage value output by the amplifier circuit. According to the measured results, if the voltage needs to be further amplified, readjust the amplification factor of the amplifier circuit. Then, select a set of appropriate increasing hydrogen concentrations and adjust the n-level reference voltage values ​​of the conversion circuit to the output voltage values ​​of the amplifier circuit corresponding to these concentrations.

[0058] Step 4: Calibration and verification. After completing the concentration gradient test, the sensor needs to be calibrated and verified to ensure that the output signal of the sensor at different concentrations is accurate and reliable.

[0059] Step 5: Troubleshooting. If the sensor output is found to be abnormal or unstable during the debugging process, troubleshooting is required. Check whether the various components and connection lines of the sensor are working properly and eliminate possible fault factors.

[0060] Optional, electrochemical CO sensor 33. Detects carbon monoxide concentration as a key indicator of incomplete combustion or the early stages of a fire. The working principle of the CO sensor is mainly based on the chemical reaction of carbon monoxide and oxygen. Specifically, when carbon monoxide enters the interior of the sensor, it reacts chemically with oxygen on the working electrode to generate carbon dioxide and a certain amount of heat energy. This chemical reaction can be expressed as: 2CO+O2→2CO2+heat energy. In this process, the chemical reaction releases a certain amount of electrons, thereby generating a current signal. The size of this current signal is proportional to the concentration of carbon monoxide. Therefore, by measuring the size of this current signal, the concentration of carbon monoxide can be determined. The specific debugging steps are as follows:

[0061] Step 1: Appearance inspection and cleaning. Check the appearance of the sensor to see if it is intact, clean the dust on the surface and air chamber, and ensure that the sensor is in good working condition.

[0062] Step 2: Connection and preheating: Connect the sensor to the calibration platform and power it on for a period of time (usually 20 minutes) to ensure that the sensor reaches a stable working state.

[0063] Step 3: Zero point calibration. Calibrate the zero point of the sensor in fresh air and control the zero value range within a certain range (such as 0-3ppm). This step is to eliminate the background signal of the sensor itself and ensure the accuracy of the measurement.

[0064] Step 4: Accuracy adjustment. Use a calibration gas of known concentration (such as 500ppm CO gas) to calibrate the sensor. Adjust the sensor parameters so that the displayed value is consistent with the calibration gas concentration value. This step needs to be repeated until satisfactory accuracy is achieved.

[0065] Step 5: Determination of basic error. Introduce calibration gases of different concentrations (such as 50ppm, 250ppm, 900ppm) into the gas chamber in turn according to the flow rate during calibration, record the sensor display value or output signal value, and compare it with the value of the standard gas sample to calculate the basic error. This step is to evaluate the measurement accuracy of the sensor.

[0066] Step 6: Alarm test. Test the alarm function of the sensor, including the sound and light alarm. Ensure that the sensor can accurately send out an alarm signal when the preset alarm concentration is reached.

[0067] Step 7: Response time test. Use a stopwatch to measure the sensor's response time to the calibration gas, which is the time required for the displayed value to rise from zero to 90% of the maximum value. This step is to evaluate the sensor's response speed.

[0068] Step 8: Subsequent processing. After the calibration is completed, clean the dust on the sensor surface and adjust the sensor's hanging position to ensure that the sensor can maintain stable measurement performance in subsequent use.

[0069] Optionally, an optical smoke sensor 34 detects smoke particles in the battery compartment air by optical principles. The technical principle of the smoke sensor is mainly based on the scattering and absorption characteristics of smoke particles to light. Specifically, the smoke sensor is usually composed of the following key components:

[0070] (1) Light-emitting element: usually a light-emitting diode (LED) or other light source, used to emit light.

[0071] (2) Photosensitive elements: such as photoresistors, photodiodes or photodiodes, used to receive light and convert it into electrical signals.

[0072] (3) Signal processing circuit: used to process the electrical signal output by the photosensitive element and determine the smoke concentration by measuring the changes in light.

[0073] It should be noted that when there is no smoke, the light emitted by the light-emitting element will directly illuminate the photosensitive element, and the resistance value or current output of the photosensitive element will remain in a stable range. However, when there are smoke particles in the air, these particles will scatter and absorb light, resulting in a decrease in the light received by the photosensitive element. The resistance value or current output of the photosensitive element will change accordingly, and this change is proportional to the smoke concentration. By measuring the change in the resistance value or current output of the photosensitive element, the smoke concentration in the air can be determined. The specific debugging steps are as follows:

[0074] Step 1: Appearance inspection. First, check whether the appearance of the sensor is intact, without damage or corrosion. At the same time, check whether the connection line of the sensor is firm and reliable.

[0075] Step 2: Power supply check: Make sure the sensor has a stable power supply and check whether the power supply voltage meets the requirements.

[0076] Step 3: Zero point calibration. Perform zero point calibration on the sensor in a smoke-free environment to ensure that the output signal of the sensor is zero or close to zero when there is no smoke.

[0077] Step 4: Sensitivity adjustment. Adjust the sensitivity of the sensor according to actual needs. Too high sensitivity may cause false alarms, while too low sensitivity may not detect smoke in time. By adjusting the sensitivity, the sensor can accurately detect smoke in different environments.

[0078] Step 5: Functional test. Use smoke of known concentration or simulated smoke to test the sensor and observe whether its output signal is consistent with the smoke concentration. At the same time, test whether the alarm function of the sensor is normal.

[0079] Step 6: Stability test. Place the sensor in different environments for long-term stability test to observe whether its output signal is stable and reliable.

[0080] Optional, optical flame sensor 35. Use infrared or ultraviolet detection technology to identify flame radiation and achieve rapid fire confirmation. Optical sensing is one of the most common working principles of flame sensors. It uses optical sensitive elements (such as photodiodes, photoresistors or phototransistors) to detect visible light or infrared radiation generated by flames. When a flame is present, the flame will emit visible light and infrared radiation. These rays are received by the optical sensitive elements and converted into electrical signals. By analyzing the electrical signals, the presence of flames can be determined and the corresponding control actions can be triggered. The specific debugging steps are as follows:

[0081] Step 1: Connection and power supply. Connect the flame sensor to the fire host of the energy storage battery compartment correctly and ensure that the sensor has a stable power supply.

[0082] Step 2: Functional test. Test the output signal of the flame sensor in both the case of flame and no flame. Observe whether the output changes of the sensor in different states are in line with expectations.

[0083] Step 3: Sensitivity adjustment. Adjust the sensitivity of the flame sensor according to actual needs. Too high sensitivity may cause false alarms, while too low sensitivity may not detect the flame in time. Some flame sensors may have a sensitivity adjustment function, which can be adjusted by rotating the potentiometer or setting parameters.

[0084] Step 4: Alarm function test. Test whether the alarm function of the flame sensor is normal. When the sensor detects a flame, it should be able to trigger the corresponding alarm signal (such as sound and light alarm).

[0085] Step 5: Stability test. Perform stability test on the flame sensor over a long period of time to observe whether its output signal is stable and reliable. Ensure that the sensor will not have false alarms or missed alarms during long-term use.

[0086] Step 6: Troubleshooting. If the flame sensor is found to have a fault or abnormality during the debugging process, troubleshooting should be carried out in a timely manner. Check the sensor's connection line, power supply, and whether the sensor itself is damaged.

[0087] Optional, high-definition camera 36. Not only used for video surveillance, but also combined with image recognition technology, automatically identify abnormal phenomena such as smoke. Technical principle The technical principle of high-definition camera to identify smoke mainly relies on image processing and artificial intelligence technology. The specific process includes:

[0088] (1) Image acquisition. The high-definition camera captures images in the energy storage battery compartment. These images contain various information about the environment, including possible smoke.

[0089] (2) Image preprocessing. The collected images are preprocessed, including denoising, image enhancement and other operations, to improve the accuracy and efficiency of subsequent processing. The preprocessing step helps to reduce interference factors in the image, such as lighting changes, shadows, etc.

[0090] (3) Feature extraction. Through image processing algorithms, key features related to smoke in the image are extracted. These features may include the color, texture, shape, movement pattern, etc. of the smoke. Feature extraction is a key step in identifying smoke, which determines whether the algorithm can accurately distinguish smoke from other similar objects.

[0091] (4) Classification and recognition. The extracted features are compared with the pre-trained model, and the classification and recognition algorithm is used to determine whether there is smoke in the image. This step usually uses advanced technologies such as deep learning, such as convolutional neural networks (CNNs). These models are trained with a large amount of data and can accurately identify smoke.

[0092] (5) Alarm and response. Once smoke is detected, the system will immediately trigger the alarm mechanism and send an alarm message to relevant personnel or security personnel. This can be achieved through sound alarms, linkage with other safety equipment (such as fire protection systems), or sending alarm messages to mobile phones.

[0093] Optionally, the specific debugging steps of the high-definition camera 36 are as follows:

[0094] Step 1: Equipment inspection. First, check whether the HD camera and its related equipment (such as image processing unit, alarm system, etc.) are installed correctly and connected stably. Make sure the equipment is in good working condition.

[0095] Step 2: Software configuration. According to the device manual or software guide, configure the corresponding software parameters. This includes setting the resolution, frame rate and other parameters of image acquisition, as well as configuring the trigger conditions and response methods of the alarm system.

[0096] Step 3: Functional test. Perform a functional test in a smoke-free environment to check whether the camera can normally capture images and transmit them to the processing unit. At the same time, test whether the alarm system can be triggered and responded normally.

[0097] Step 4: Sensitivity adjustment. Adjust the sensitivity of smoke recognition according to actual needs. Too high sensitivity may lead to false alarms (such as misjudging water vapor, dust, etc. as smoke), while too low sensitivity may not detect smoke in time. Find the best balance by adjusting the sensitivity parameters.

[0098] Step 5: Actual scene testing. Test the HD camera’s ability to identify smoke in actual scenes. This includes testing under different lighting conditions, different smoke concentrations, and different types of smoke. Through actual testing, evaluate the accuracy and reliability of the system, and make necessary adjustments and optimizations based on the test results.

[0099] Step 6: Troubleshooting. If any fault or abnormality is found in the system during the test (such as false alarm, missed alarm, etc.), troubleshooting should be carried out in a timely manner. Check whether there are any problems in the camera, processing unit, alarm system, etc., and take appropriate measures to repair or replace them.

[0100] Optionally, audio sensor 37. Monitor abnormal sounds during power station operation, such as the sound of a valve explosion before a serious failure of a battery cell, and identify the explosion sound in combination with an audio analysis algorithm. Technical principle Audio acquisition: The system first requires a highly sensitive audio acquisition device, such as a microphone or an audio sensor, to capture sound signals near the battery cell explosion-proof valve. The collected audio signal will be transmitted to the processing unit for preprocessing (such as noise reduction, filtering) and feature extraction. Feature extraction may include spectrum analysis, waveform characteristics, etc. of the sound to identify specific audio patterns associated with abnormal states of the battery cell. Use machine learning or deep learning algorithms to perform pattern recognition on the extracted audio features. These algorithms may have been trained to identify specific audio signals generated by abnormal states such as the opening of the battery cell explosion-proof valve and gas release. Once the abnormal state of the battery cell is identified, the system will immediately trigger the alarm mechanism to notify relevant personnel or initiate emergency response measures. The specific debugging steps are as follows:

[0101] Step 1: Equipment check: Check whether the audio acquisition device (such as microphone) is installed correctly, connected stably, and ensure that it can work properly.

[0102] Step 2: Environmental testing: In the absence of battery abnormalities, test the performance of the audio acquisition and processing system to ensure that the background noise is within an acceptable range and adjust the parameters to reduce noise interference.

[0103] Step 3: Simulation test. Use simulated equipment or known abnormal cell conditions to test the system's recognition capabilities. Ensure that the system can accurately recognize and respond to simulated abnormal audio signals.

[0104] Step 4: Sensitivity adjustment. Adjust the sensitivity parameters of the system according to the test results. Too high sensitivity may cause normal sounds to be misjudged as abnormal sounds and alarm, while too low sensitivity may not detect abnormalities in time.

[0105] Step 5: Actual scenario testing. Test the system performance in actual usage scenarios, including audio acquisition effects, recognition accuracy, and response time in different environments. Make necessary adjustments and optimizations based on the test results.

[0106] Step 6: Fault diagnosis and troubleshooting. If a fault or abnormality is found in the system during testing or use, the fault diagnosis and troubleshooting should be carried out in a timely manner. Check whether there are any problems in the audio acquisition device, processing unit, alarm system, etc., and take appropriate measures to repair or replace them.

[0107] Optionally, the host processing unit receives the data collected by each sensor, performs preprocessing, filtering, feature extraction, etc., applies intelligent algorithms to analyze the data, identifies fire risks, generates warning signals, supports multiple communication protocols, and transmits the processed data and warning information to the power plant fire warning management system.

[0108] Optionally, the fire warning management system receives and stores data from the host, establishes a database for long-term recording and analysis, and designs seven monitoring charts, including VOC concentration trend chart, hydrogen leakage distribution chart, CO concentration alarm chart, smoke concentration monitoring chart, flame recognition dynamic chart, camera monitoring screen, audio explosion analysis chart, to achieve multi-dimensional real-time monitoring, provide a user interface, display monitoring charts, and send warning notifications to managers' mobile devices or workstations. The system automatically determines the fire risk level based on preset thresholds and algorithm logic, and sends warning information of different levels. It is linked with the power station fire protection system to automatically trigger the fire extinguishing device after confirming the fire, or notify relevant personnel to take emergency measures.

[0109] It should be noted that the design of the seven monitoring charts requires the reliability and accuracy of the charts so that users can clearly understand the monitoring status of the fire warning system. At the same time, the realization of multi-dimensional real-time monitoring requires the system to monitor various parameters in a timely and accurate manner and send early warning notifications to users in a timely manner. Sending early warning notifications to managers' mobile devices or workstations requires ensuring the timeliness and accuracy of the notifications so that managers can take appropriate measures to deal with fire risks in a timely manner.

[0110] In summary, the optional embodiments of the present application integrate multiple sensors, combine advanced signal processing technology and intelligent analysis algorithms, realize all-round and multi-level monitoring of the fire risk of energy storage power stations, and design seven monitoring charts for real-time monitoring to provide intuitive and accurate fire warning information for power station managers. By integrating multiple sensors, all-round monitoring of the fire risk of energy storage power stations is realized. Through intelligent algorithm analysis, the accuracy and timeliness of fire warnings are improved. The seven monitoring charts provide intuitive and comprehensive fire risk monitoring information. Linked with the fire protection system, a rapid emergency response is achieved after a fire occurs.

[0111] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0112] In the present embodiment, a management device for prompt information is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the equipment described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0113] Figure 4 : is a structural block diagram of a prompt information management device according to an embodiment of the present application, the device comprising:

[0114] A first acquisition module 42 is used to acquire N groups of monitoring data uploaded by N types of sensor components;

[0115] A processing module 44 is used to process the N groups of monitoring data to obtain N groups of data features;

[0116] The evaluation module 46 is used to evaluate the risk level of the target area monitored by the N types of sensor components according to the N groups of data features, and send early warning information to the management object that manages the target area based on the risk level, wherein there is at least energy storage equipment in the target area, and N is a positive integer.

[0117] The above-mentioned device obtains N groups of monitoring data uploaded by N types of sensor components; processes the N groups of monitoring data to obtain N groups of data features; evaluates the risk level of the target area monitored by the N types of sensor components based on the N groups of data features, and sends early warning information to the management object that manages the target area based on the risk level, wherein there is at least energy storage equipment in the target area, and N is a positive integer. The above-mentioned technical solution solves the problem of being unable to achieve comprehensive fire risk monitoring of energy storage power stations. Furthermore, by processing the monitoring data uploaded by N types of sensor components, the risk level of the target area is evaluated and early warning information is sent. Through multi-dimensional monitoring and intelligent analysis, the accuracy and timeliness of early warnings are improved, and the safe operation level of energy storage power stations is improved.

[0118] In an exemplary embodiment, the above-mentioned device also includes: a determination module, which is used to determine the fire probability corresponding to the risk level after evaluating the risk level of the target area monitored using N types of sensor components based on N groups of data features; when the fire probability is greater than or equal to the preset trigger probability, the fire-fighting equipment in the target area is linked to control the fire-fighting equipment to be in operation; when the fire probability is less than the preset trigger probability, an inspection reminder message is sent to the management object, wherein the inspection reminder message is used to instruct the management object to issue a task to maintain the equipment in the target area to the maintenance object after receiving the early warning prompt for the target area.

[0119] In an exemplary embodiment, the above-mentioned processing module is also used to perform data preprocessing on each group of monitoring data in N groups of monitoring data to obtain N first data sets, wherein the data preprocessing includes one of the following operations: data cleaning, data standardization, data normalization, data conversion; filtering the N first data sets to obtain N second data sets, wherein the filtering process is used to eliminate interference data in the first data sets; feature extraction is performed based on the N second data sets to obtain N groups of data features, wherein the feature extraction includes at least one of the following extraction methods: time domain feature extraction method, frequency domain feature extraction method, time-frequency feature extraction method, statistical feature extraction method.

[0120] In an exemplary embodiment, the above-mentioned device also includes: a recording module, which is used to process N groups of monitoring data, and after obtaining N groups of data features, determine the collection types corresponding to the N groups of data features respectively; when there are matching types for multiple target collection types in a preset chart database, record the target monitoring data corresponding to the current matching type, and the target chart template associated with the current matching type; determine the target type sensor component corresponding to the target monitoring data; and record all real-time data uploaded by the target type sensor component after the preset collection period.

[0121] In an exemplary embodiment, the above-mentioned recording module is also used to input all real-time data into the target chart template to obtain a visual monitoring chart corresponding to the target type sensor; synchronize the visual monitoring chart to a visual interface that allows management object operations, and receive operation instructions input from the visual interface to adjust the display of the visual monitoring chart.

[0122] In an exemplary embodiment, the above-mentioned device also includes: a second acquisition module, which is used to evaluate the risk level of the target area monitored using N types of sensor components based on N groups of data features, and after sending early warning prompt information to the management object that manages the target area based on the risk level, obtain the management strategy generated by the management object for the early warning prompt information, and determine the execution result of the management strategy; determine whether the early warning prompt information is valid based on the execution result, so as to adjust the information content of the early warning prompt information.

[0123] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0124] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0125] S1. Obtain N groups of monitoring data uploaded by N types of sensor components;

[0126] S2. Processing the N groups of monitoring data to obtain N groups of data features;

[0127] S3. Evaluate the risk level of the target area monitored by the N types of sensor components according to the N groups of data features, and send early warning information to the management object that manages the target area based on the risk level, wherein there is at least energy storage equipment in the target area, and N is a positive integer.

[0128] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0129] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0130] An embodiment of the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps in any one of the above method embodiments are performed.

[0131] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0132] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0133] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0134] S1. Obtain N groups of monitoring data uploaded by N types of sensor components;

[0135] S2. Processing the N groups of monitoring data to obtain N groups of data features;

[0136] S3. Evaluate the risk level of the target area monitored by the N types of sensor components according to the N groups of data features, and send early warning information to the management object that manages the target area based on the risk level, wherein there is at least energy storage equipment in the target area, and N is a positive integer.

[0137] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0138] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0139] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0140] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for managing prompt information, characterized in that: include: Obtain N groups of monitoring data uploaded by N types of sensor components; Processing the N groups of monitoring data to obtain N groups of data features; The risk level of the target area monitored by the N types of sensor components is evaluated according to the N groups of data features, and an early warning message is sent to a management object that manages the target area based on the risk level, wherein at least energy storage equipment exists in the target area and N is a positive integer.

2. The method according to claim 1, characterized in that After evaluating the risk level of the target area monitored by the N types of sensor assemblies according to the N groups of data features, the method further includes: Determine the fire probability corresponding to the risk level; When the fire probability is greater than or equal to a preset trigger probability, the fire extinguishing equipment in the target area is linked to control the fire extinguishing equipment to be in an operating state; When the fire probability is less than the preset trigger probability, an inspection reminder message is sent to the management object, wherein the inspection reminder message is used to instruct the management object to issue a task to maintain the equipment in the target area to the maintenance object after receiving the early warning reminder for the target area.

3. The method according to claim 1, characterized in that The N groups of monitoring data are processed to obtain N groups of data features, including: Performing data preprocessing on each of the N groups of monitoring data to obtain N first data sets, wherein the data preprocessing includes one of the following operations: data cleaning, data standardization, data normalization, and data conversion; Performing filtering processing on the N first data sets to obtain N second data sets, wherein the filtering processing is used to eliminate interference data in the first data sets; Feature extraction is performed based on the N second data sets to obtain N groups of data features, wherein the feature extraction includes at least one of the following extraction methods: time domain feature extraction method, frequency domain feature extraction method, time-frequency feature extraction method, and statistical feature extraction method.

4. The method according to claim 1, characterized in that: After processing the N groups of monitoring data to obtain N groups of data features, the method further includes: Determine the collection types corresponding to the N groups of data features respectively; In the case where the acquisition type has a matching type among multiple target acquisition types in the preset chart database, recording the target monitoring data corresponding to the current matching type and the target chart template associated with the current matching type; Determine the target type sensor component corresponding to the target monitoring data; Record all real-time data uploaded by the target sensor component after a preset collection period.

5. The method according to claim 4, characterized in that Record all real-time data uploaded by the target sensor component after the preset collection period, including: Input all the real-time data into the target chart template to obtain a visual monitoring chart corresponding to the target sensor; The visual monitoring diagram is synchronized to a visual interface that allows management object operations, and operation instructions input from the visual interface are received to adjust the display of the visual monitoring diagram.

6. The method according to claim 1, characterized in that After evaluating the risk level of the target area monitored by the N types of sensor components according to the N groups of data features, and sending early warning information to a management object that manages the target area based on the risk level, the method further includes: Obtaining a management strategy generated by the management object for the early warning prompt information, and determining an execution result of the management strategy; Determine whether the early warning prompt information is valid according to the execution result, so as to adjust the information content of the early warning prompt information.

7. A management device for prompt information, characterized in that: include: A first acquisition module is used to acquire N groups of monitoring data uploaded by N types of sensor components; A processing module, used for processing the N groups of monitoring data to obtain N groups of data features; An evaluation module is used to evaluate the risk level of the target area monitored by the N types of sensor components according to the N groups of data features, and send early warning information to the management object that manages the target area based on the risk level, wherein there is at least energy storage equipment in the target area and N is a positive integer.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 6 when executed.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 6 through the computer program.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images