Fire risk identification method and device, server and collector system

Abstract

The invention provides a fire risk identification method and device, a server and a collector system. The method comprises the following steps: firstly, receiving at least one kind of real-time parameter data used for representing an environment state in a closed wall; judging whether the real-time parameter data is abnormal fluctuation parameter data or not; and finally, under the condition that the abnormal fluctuation parameter data exists, at least inputting the abnormal fluctuation parameter data into a preset risk identification model for identification, and obtaining a risk identification result. According to the invention, by analyzing various parameter data such as gas, temperature, pressure difference and the like in real time, abnormal fluctuation is found in time, and then the fire risk is accurately evaluated through the risk identification model, so that the response speed and accuracy of fire early warning are remarkably improved, the technical problem that fire early warning is not timely in the prior art is solved, and the occurrence of fire hidden dangers is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of fire risk identification, and in particular to a fire risk identification method, device, server and collector system. Background Art

[0002] In the closed wall under the mine, due to its special closed environment, various harmful gases are easily accumulated, such as gas (methane), ethylene, acetylene, hydrogen sulfide and carbon monoxide. The accumulation of these gases will gradually increase over time, especially under high temperature conditions, these harmful gases are very likely to cause combustion and explosion, causing major safety hazards. Therefore, timely monitoring of gas concentrations and other environmental parameters (such as temperature, pressure difference, etc.) in the closed wall is a key link in fire prevention.

[0003] In the related technology, there is a technical problem of untimely fire warning inside a closed wall. Summary of the invention

[0004] The purpose of the present invention is to overcome the above-mentioned technical deficiencies and provide a fire risk identification method, device, server and collector system to solve the technical problem of untimely fire warning inside closed walls in the related art.

[0005] In order to achieve the above technical objectives, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for identifying fire risks, the method comprising: Receiving at least one real-time parameter data for characterizing the environmental state within the closed wall; Determining whether the real-time parameter data is parameter data with abnormal fluctuations; In the case where abnormal fluctuation parameter data exists, at least the abnormal fluctuation parameter data is input into a preset risk identification model for identification to obtain a risk identification result.

[0006] In a second aspect, the present invention provides a fire risk identification device, the device comprising: A receiving module, which is used to receive at least one real-time parameter data for characterizing the environmental state inside the closed wall; A judgment module, which is used to judge whether the real-time parameter data is parameter data with abnormal fluctuations; The identification module is used to input the abnormal fluctuation parameter data into a preset risk identification model for identification in the presence of abnormal fluctuation parameter data, so as to obtain a risk identification result.

[0007] In a third aspect, the present invention provides a server, comprising: a memory, and one or more processors communicatively coupled to the memory; The memory stores instructions that can be executed by the one or more processors. The instructions are executed by the one or more processors to enable the one or more processors to implement the above method.

[0008] In a fourth aspect, the present invention provides a collector system, the system comprising: A monitoring host, which is arranged outside the closed wall and is used to obtain real-time parameter data for characterizing the environmental status inside and outside the closed wall; A display device, the display device is used to display the real-time parameter data; The server is the server mentioned above.

[0009] Beneficial effects: The present invention realizes accurate monitoring and intelligent early warning of the environmental status inside the closed wall by receiving real-time parameter data and combining abnormal fluctuation detection with a preset risk identification model. Its beneficial effect is that by real-time analysis of multiple parameter data such as gas, temperature, pressure difference, etc., abnormal fluctuations can be discovered in time, and then the fire risk can be accurately assessed through the risk identification model, which significantly improves the reaction speed and accuracy of fire early warning, solves the technical problem of untimely fire early warning in the prior art, and effectively reduces the occurrence of fire hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flowchart of a fire risk identification method provided by an embodiment of the present invention; Figure 2 It is a flowchart of a fire risk identification method provided by an embodiment of the present invention; Figure 3 It is a flowchart of a fire risk identification method provided by an embodiment of the present invention; Figure 4 is a block diagram of a fire risk identification device used in an embodiment of the present invention; Figure 5 is a schematic diagram of a collector system used in an embodiment of the present invention; Figure 6 It is a block diagram of an electronic device used in an embodiment of the present invention. DETAILED DESCRIPTION

[0011] 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.

[0012] In the related art, some detection methods manually collect gas samples in the closed wall at regular intervals and obtain the gas concentration through laboratory analysis. This method is not only time-consuming and laborious, but also due to the limited frequency of collection, it is easy to miss the moment when the gas concentration changes rapidly, resulting in delayed warning. Some detection methods may not be able to reflect the environmental changes in the closed wall in time due to the low monitoring frequency or delayed data transmission and processing, especially the abnormal fluctuations in gas concentration, even if they use automated monitoring equipment, resulting in delayed risk warning. Therefore, the existing technology has the technical problem of untimely fire warning, and cannot provide relevant managers with sufficient time and information to prevent fire risks in advance. This delayed fire warning mechanism causes the accumulation of harmful gases in the closed wall, which brings greater fire hazards.

[0013] like Figure 1 As shown, this embodiment provides a fire risk identification method, which can be applied in a server and may include: Step S102: receiving at least one real-time parameter data for characterizing the environmental state inside the closed wall.

[0014] In this embodiment, the receiving action can be represented as the server receiving the real-time parameter data transmitted from the monitoring host. Specifically, the server can actively send a data request to the monitoring host, and obtain the environmental state parameter data in the closed wall from the monitoring host in real time. The server can also periodically receive the real-time parameter data in the closed wall from the monitoring host according to a preset time interval or timing strategy. Therefore, it can be understood that the receiving action is automatic receiving.

[0015] The monitoring host can be configured outside the closed wall to obtain real-time parameter data for characterizing the environmental state inside the closed wall. The real-time parameter data may include: physical environmental state parameter data and gas environmental state parameter data. The physical environmental state parameter data may include the internal and external pressure difference of the closed wall or the temperature inside and outside the closed wall. The gas environmental state parameter data may include: oxygen, methane, carbon monoxide, carbon dioxide, hydrogen sulfide, acetylene or ethylene. The temperature inside and outside the closed wall may be the temperature inside the closed wall and the temperature outside the closed wall.

[0016] In some embodiments, the monitoring host can be configured with a gas pipe extending into the closed wall to absorb the gas in the closed area, and then configured with multiple sensors to sense the absorbed gas, so as to obtain the above-mentioned gas environment state parameter data, such as the gas concentration value of oxygen, methane, carbon monoxide, carbon dioxide, hydrogen sulfide, acetylene or ethylene in the current closed area.

[0017] In some embodiments, the monitoring host can be configured with a pressure difference sensor and a temperature sensor to monitor the pressure difference and current temperature inside and outside the closed area, respectively. Specifically, in some embodiments, a temperature sensor can be set at the end of the air pipe, such as the end of the air pipe extending into the closed area, to collect the temperature inside the closed wall. A temperature sensor can be set inside the monitoring host or outside the shell to collect the temperature outside the closed wall.

[0018] Step S104: Determine whether the real-time parameter data is parameter data with abnormal fluctuations.

[0019] In this embodiment, the action of determining can be represented by the server analyzing and comparing the real-time parameter data to determine whether the real-time parameter data contains abnormal fluctuation parameter data.

[0020] In this embodiment, the abnormal fluctuation parameter data can be represented as real-time parameter data that is significantly different from the expected normal state, which may reflect that an abnormal change has occurred in the environmental state inside the closed wall. Specifically, the abnormal fluctuation parameter data can be parameter data that exceeds a safety threshold. When one or more parameter data (such as gas concentration, temperature, pressure difference) exceeds a preset normal range or a preset safety threshold, it can be judged as abnormal fluctuation parameter data. For example, the methane concentration exceeds the safety threshold, or the temperature rise exceeds the safety threshold.

[0021] The abnormal fluctuation parameter data may also be real-time parameter data whose variation exceeds the variation threshold. For example, the real-time parameter data changes dramatically in a short period of time, and its variation trend does not conform to the normal fluctuation range. For example, the concentration of one or more of the above oxygen, methane, carbon monoxide, carbon dioxide, hydrogen sulfide, acetylene or ethylene suddenly increases or the pressure difference fluctuates significantly. Although the value after the fluctuation may exceed the safety threshold, it may not exceed the safety threshold.

[0022] In some embodiments, the abnormal fluctuation parameter data may also be a plurality of real-time parameter data with an associated relationship that simultaneously exceeds the safety threshold or the variation amplitude simultaneously exceeds the variation amplitude threshold, and the plurality of real-time parameter data with an associated relationship may be judged as abnormal fluctuation parameter data. In other words, in this embodiment, only a single real-time parameter data exceeds the safety threshold or the variation amplitude exceeds the variation amplitude threshold, which is not necessarily defined as abnormal fluctuation parameter data. This method of judging abnormal multi-parameter linkage is more accurate than a single judgment, and can effectively reduce false alarms and improve the ability to identify abnormal states. Specifically, the plurality of real-time parameter data with an associated relationship may be an association between gas concentration and temperature. For example, in a specific scenario example, the safety threshold of methane concentration may be 1.0%, and the safety threshold of oxygen concentration may be 19.5%. The safety threshold of temperature may be 50°C. Under normal circumstances, the methane concentration is 0.5%, the oxygen concentration is 20.9%, and the temperature is 40°C. In an abnormal situation, when the methane concentration rises to 1.2% (exceeding the 1.0% threshold), the oxygen concentration drops to 18.8% (below the 19.5% threshold), and the temperature rises to 55°C (exceeding the 50°C threshold), these parameters with associated relationships simultaneously exceed their safety thresholds, and the server can determine that it is abnormal fluctuation parameter data. It can be understood that there is a strong correlation between the increase in methane concentration, the decrease in oxygen concentration, and the increase in temperature. Generally, an increase in methane concentration may be accompanied by a decrease in oxygen and an increase in temperature, which may be a signal of fire risk or explosion hazard. Therefore, the simultaneous excess of multiple associated parameters over the safety threshold is a clear indication of abnormal fluctuation. Correspondingly, the association relationship can also be the association between gas concentration and pressure difference, such as the association between carbon monoxide, carbon dioxide, and pressure difference. For example, the simultaneous increase in carbon dioxide and carbon monoxide concentrations, accompanied by changes in the pressure difference between the inside and outside of the closed wall, may mean that the ventilation state in the closed wall is abnormal or there is a gas leak. There is a certain correlation between these parameters, so when they exceed the safety range at the same time, it indicates a potential dangerous state. The association relationship can also be the association between hydrogen sulfide and acetylene.

[0023] In this embodiment, whether the real-time parameter data is abnormal fluctuation parameter data can be determined by presetting a safety threshold. Specifically, first, the preset safety threshold of each real-time parameter data is obtained from the database. Then, each real-time parameter data is compared with its corresponding threshold. If the value of a certain parameter exceeds its preset safety threshold, it is determined that the parameter has abnormal fluctuation. Accordingly, the parameter is determined as abnormal fluctuation parameter data.

[0024] In this embodiment, it is also possible to determine whether the real-time parameter data has abnormal fluctuations by analyzing the historical trend of the parameter data. Specifically, first, the historical parameter data can be retrieved from the database to establish a time series model. Then, a time series analysis is performed on the currently received real-time parameter data to determine whether its change trend deviates from the historical trend. Next, the real-time parameter data that deviates from the historical trend is further analyzed to see whether it is significantly different from the historical parameter data. For example, a differential analysis algorithm can be used for further analysis. Finally, if it deviates from the historical normal trend range, it is determined to be abnormal fluctuation parameter data. The analysis method based on the time series model can effectively identify short-term and long-term abnormal fluctuations and reduce false alarms.

[0025] In this embodiment, abnormal fluctuation parameter data can also be identified by the correlation between multiple real-time parameter data. Specifically, first, multiple real-time parameter data are time-aligned and synchronized to ensure that multiple real-time parameter data can be analyzed in a linked manner within the same time range. Then, a single abnormal fluctuation judgment is performed on each real-time parameter data to identify whether there is an abnormal fluctuation of a single real-time parameter data. Next, based on the historical correlation between each real-time parameter, the degree of correlation between each real-time parameter is calculated to determine whether there is a linked abnormal fluctuation. Next, when abnormal fluctuations of multiple real-time parameter data occur at the same time, the fluctuation amplitudes of each real-time parameter data are weighted and calculated to obtain comprehensive fluctuation difference data; finally, based on the comprehensive fluctuation difference data, determine whether there is a linked abnormal fluctuation.

[0026] Step S106: In the case where abnormal fluctuation parameter data exists, at least the abnormal fluctuation parameter data is input into a preset risk identification model for identification to obtain a risk identification result.

[0027] In this embodiment, when there is abnormal fluctuation parameter data, only the abnormal fluctuation parameter data can be input into the preset risk identification model for identification to obtain the risk identification result. Alternatively, all currently obtained real-time parameter data can be input into the preset risk identification model for identification to obtain the risk identification result.

[0028] In some embodiments, the abnormal fluctuation parameter data (real-time parameter data) and the corresponding part of the historical parameter data can be input into a preset risk identification model for identification to obtain a risk identification result. For example, the safety threshold of methane concentration can be 1.0%. In a certain case, the real-time parameter data of methane concentration is 2.0%. Then, the real-time parameter data of methane concentration and the historical parameter data of methane concentration in the previous week can be input into a preset risk identification model for identification to obtain a risk identification result.

[0029] In some embodiments, all real-time parameter data and all partial historical parameter data may be input into a preset risk identification model for identification to obtain a risk identification result. For example, all currently acquired real-time parameter data and all historical parameter data stored within a week or three days may be input into a preset risk identification model for identification to obtain a risk identification result.

[0030] In this embodiment, the risk identification model is pre-trained. It can be a machine learning model, such as a decision tree model or a support vector machine model. It can also be a deep learning model, such as a convolutional neural network model or a time series model.

[0031] The risk identification model can be pre-trained by the following method: first, a data set is constructed. Specifically, real-time parameter data is collected from the monitoring host, including various physical environmental parameters such as gas concentration, temperature, and pressure difference. In order to construct a comprehensive data set, data in normal state, slightly abnormal state, and seriously abnormal state can be collected. Historical parameter data are extracted from past monitoring records, including parameter data collected by various sensors in different time periods. Corresponding annotations are extracted from event records in actual operations (such as fire, gas leakage, etc.) to help the model distinguish different risk levels. Then, data annotation is performed for the constructed data set, for example, it can be labeled as normal data, low-risk data, medium-risk data, and high-risk data. Normal data means that the data parameter changes are within the normal range and there is no risk. Low-risk data means that there are slight abnormal fluctuations, but it has not yet reached a serious risk state and needs to be monitored. Medium-risk data means that there are more obvious abnormal fluctuations, and there may be potential fire or other risks. Medium-risk data means that the parameter changes reach or exceed the danger threshold, and there is a high risk of fire or gas leakage. Specifically, manual labeling can be performed, that is, based on existing event records (such as fires and gas leaks), the data in the data set can be manually labeled as "high risk" or "medium risk". It is also possible to automatically label some data based on existing risk rule systems (such as threshold rules). For example, when the methane concentration exceeds 1.0%, it is automatically labeled as "medium risk" or "high risk". Next, the data set is divided into a training set, a validation set, and a test set. For example, 70% of the data can be used to train the model. The data in the training set will include normal, low risk, medium risk, and high risk. 15% of the data is used to verify the model effect. The validation set is used to evaluate the performance of the model on unseen data during the training process and adjust the hyperparameters. 15% of the data is used to finally test the model performance. The data in the test set is not involved in the model training at all and is used to evaluate the actual performance of the model. Finally, the data in the training set can be used to train the model to be trained. During the training process, the hyperparameters of the model (such as learning rate, number of hidden layers, regularization parameters, etc.) can be continuously adjusted to optimize the model performance. After each training cycle, the validation set can be used to evaluate the model effect to ensure that the model has good generalization ability on unseen data. After training is completed, the test set is used for the final evaluation of the model.

[0032] The above implementation method realizes accurate monitoring and intelligent early warning of the environmental status inside the closed wall by receiving real-time parameter data and combining abnormal fluctuation detection with a preset risk identification model. Its beneficial effect is that by analyzing multiple parameter data such as gas, temperature, and pressure difference in real time, abnormal fluctuations can be discovered in time, and then the fire risk can be accurately assessed through the risk identification model, which significantly improves the reaction speed and accuracy of fire early warning, solves the technical problem of untimely fire early warning in the prior art, and effectively reduces the occurrence of fire hazards.

[0033] It is understandable that the input action is automatically input.

[0034] like Figure 2 As shown, in some embodiments, the step of determining whether the real-time parameter data is parameter data with abnormal fluctuations includes: Step S1042: Retrieve historical parameter data for characterizing the environmental status inside the closed wall from the database.

[0035] In this embodiment, all historical parameter data can be retrieved, or historical parameter data that meets the time window can be retrieved. The time window can be historical parameter data within a week, or it can be historical parameter data within three days or within a day. It is understandable that the selection of the time window can be based on the accuracy and real-time requirements of the required analysis. For more sophisticated short-term trend analysis, you can choose to retrieve historical data in a shorter period of time (such as one day or three days); and for the identification of long-term trend changes, you can choose to retrieve data in a longer period of time (such as one week).

[0036] In some embodiments, the time window may also be a dynamic time window, which can automatically expand or reduce the time range according to the degree of fluctuation of the real-time parameter data to capture more flexible trend changes. For example, when a slight abnormal fluctuation is detected, only historical data within one day may be retrieved; when a larger fluctuation is detected, the time window may be extended to one week for more in-depth analysis. Specifically, after the server obtains the current gas concentration value, temperature value and pressure difference value of oxygen, methane, carbon monoxide, carbon dioxide, hydrogen sulfide, acetylene or ethylene, the server needs to first evaluate the change range of these parameters and the difference from the historical normal value. This process determines the size of the dynamic time window. The server compares the current real-time parameter data with the most recent historical reference value (such as data one hour ago) and calculates the change range of each real-time parameter data. For example, whether the methane concentration increases beyond the preset normal fluctuation range. If the change range of the current real-time parameter data is small, a shorter time window can be set. For example, retrieve historical parameter data for the past 24 hours or the past three days. If the current real-time parameter data changes by more than some thresholds but does not reach a serious fluctuation, you can select a medium time window, such as retrieving historical data from the past week. If the current real-time parameter data changes by more than the set threshold, a longer time window will be set, such as retrieving historical data from the past month or longer, to capture long-term trends and potential risks.

[0037] Step S1044: Calculate fluctuation parameter data based on the historical parameter data and the real-time parameter data.

[0038] In this embodiment, the fluctuation parameter data can be expressed as the absolute difference and relative change percentage between the historical parameter data and the real-time parameter data. These two indicators can be used to quantify the degree of fluctuation of the current real-time parameter data relative to the historical parameter data.

[0039] This step S1044 may include: for each real-time parameter data (such as methane concentration, oxygen concentration, temperature, etc.), performing a difference calculation between the real-time parameter data and the corresponding historical average value. The difference calculation may be an absolute difference, such as: absolute difference = real-time parameter data - historical average value. The difference calculation may also be a relative change percentage, such as: relative change percentage = difference value / historical average value × 100%. After calculating the fluctuation of each real-time parameter data, these data may be generated as fluctuation parameter data.

[0040] Step S1046: Compare the fluctuation parameter data with a preset fluctuation threshold. If the fluctuation parameter data is greater than the fluctuation threshold, it is determined that abnormal fluctuation parameter data exists.

[0041] In this embodiment, a corresponding fluctuation threshold value may be set in advance for each real-time parameter data, indicating the fluctuation range of the parameter under normal circumstances. For example, the fluctuation threshold value of methane concentration may be set to 0.2%.

[0042] In this embodiment, each fluctuation parameter data can be compared with its corresponding fluctuation threshold. If the fluctuation parameter data (difference value or relative change percentage) exceeds the set fluctuation threshold, it is considered that the fluctuation of the real-time parameter data is abnormal. Therefore, the real-time parameter data can be judged as abnormal fluctuation parameter data.

[0043] This implementation method can effectively improve the accuracy of abnormal fluctuation detection by combining historical parameter data with real-time parameter data, calculating and comparing fluctuation differences with preset thresholds. By retrieving historical parameter data from the database, a reference baseline can be provided, so that the server not only relies on the instantaneous changes of real-time data, but also conducts a more comprehensive analysis based on historical trends to avoid false alarms caused by short-term fluctuations or noise data. In addition, the setting of preset thresholds ensures that the judgment of fluctuation differences is more accurate, which helps to timely discover potential risks and improve the timeliness and reliability of fire warnings.

[0044] In some embodiments, the real-time parameter data includes: physical environment state parameter data and gas environment state parameter data; wherein, the physical environment state parameter data includes the internal and external pressure difference of the closed wall or the temperature inside and outside the closed wall; the gas environment state parameter data includes: oxygen, methane, carbon monoxide, carbon dioxide, hydrogen sulfide, acetylene or ethylene.

[0045] In this embodiment, by subdividing the real-time parameter data into physical environment state parameter data (such as the internal and external pressure difference of the closed wall and the temperature inside and outside the closed wall) and gas environment state parameter data (such as oxygen, methane, carbon monoxide, etc.), the environmental state inside and outside the closed wall can be more finely monitored and analyzed. The beneficial effect of this data classification method is that it can not only comprehensively evaluate the changes in gas concentration and promptly detect abnormalities of toxic or flammable gases, but also monitor the pressure and temperature changes of the physical environment, which helps to detect fire hazards or structural problems of the closed wall earlier, thereby improving the accuracy and real-time nature of the overall risk warning.

[0046] like Figure 3 As shown, in some embodiments, the step of inputting at least the abnormal fluctuation parameter data into a preset risk identification model for identification to obtain a risk identification result includes: Step S1062: Determine the type of the abnormal fluctuation parameter data.

[0047] In this embodiment, the server can extract specific parameter types from the abnormal fluctuation parameter data. These parameter types can be specific parameter types: such as methane concentration, acetylene concentration, oxygen concentration, etc. They can also be large types, such as gas environment data (including all gas concentration parameters), physical environment data (such as temperature, pressure difference, etc.).

[0048] Step S1064: Determine a target risk identification model based on the type of the abnormal fluctuation parameter data.

[0049] In this embodiment, a risk identification model library may be configured in the server, and the risk identification model library may contain a variety of different risk identification models, each of which may be applicable to one or more corresponding parameter types or environmental states. Therefore, the target risk identification model that matches the current abnormal fluctuation parameter data type can be found by querying the risk identification model library. After the server completes the query and matching, the model identifier (such as model ID or model name) finally selected is used as the target risk identification model. The server records the matching result and prepares to input the abnormal fluctuation parameter data into the selected target risk identification model for further analysis and risk identification.

[0050] Specifically, if the type of abnormal fluctuation parameter data is a specific parameter (such as abnormal methane concentration), the server will give priority to the target risk identification model specifically for methane concentration risk. If a broader environmental state is detected (such as abnormal gas type or abnormal temperature type), the server will select a comprehensive risk identification model for the entire major category of environmental changes. For example, if multiple gases (such as oxygen, carbon monoxide, carbon dioxide, etc.) fluctuate abnormally at the same time, the server will select a target risk identification model for multi-gas concentration monitoring to specifically analyze the association between gas composition changes and fire or leakage risks.

[0051] More specifically, in some cases, the server may detect multiple different types of abnormal fluctuation data and require different target risk identification models. Therefore, in this case, if a certain type of parameter (such as methane concentration) is considered to have a higher risk, the server will give priority to the target risk identification model corresponding to that parameter type. If there are multiple high-priority parameter types (such as gas and temperature abnormalities at the same time), the server can select multiple target risk identification models for risk assessment, or use a comprehensive model for fusion analysis.

[0052] Step S1066: at least input the abnormal fluctuation parameter data into the target risk identification model for identification to obtain a risk identification result.

[0053] In this implementation, the server can configure multiple risk identification models. By first determining the type of abnormal fluctuation parameter data and then selecting the most suitable target risk identification model for identification, the accuracy and efficiency of risk assessment can be significantly improved. The beneficial effect of this method is that it can automatically match the most suitable model according to different types of abnormal fluctuations (such as abnormal gas concentration, temperature rise or pressure difference fluctuation), and specifically analyze and identify potential fire or leakage risks. This dynamic model selection mechanism can reduce the possibility of false alarms and missed alarms, and ensure more accurate risk warnings in complex and changing environments.

[0054] In some embodiments, in the absence of abnormal fluctuation parameter data, the method further comprises: At least based on the real-time parameter data, a corresponding graph or table is generated for display to the user.

[0055] In this embodiment, a corresponding graph or table may be generated based only on the real-time parameter data for display to the user. A corresponding graph or table may also be generated based on all or part of the historical parameter data and the real-time parameter data for display to the user. The part of the historical parameter data may be within a week, within three days, etc.

[0056] Specifically, the server can generate status charts of various parameters based only on the real-time parameter data at the current moment. For example, the current gas concentration, temperature, pressure difference and other data can be directly displayed in the form of charts. The server can also retrieve historical parameter data within a certain time window (such as one week or three days), and display the historical data in combination with the current real-time data to help users understand the trend changes and the comparison of the current status.

[0057] In this embodiment, a line graph may be generated, for example, trend lines of historical parameter data and real-time parameter data may be drawn on a time axis, for example, displaying a methane concentration change curve over the past week, or comparing the current oxygen concentration with the average value over the past three days.

[0058] In this embodiment, a bar graph may also be generated, for example, a bar graph may be used to represent the value of each gas concentration or temperature at the current moment. The average values ​​of the current day and the past few days may also be displayed side by side to show the range of change of a certain parameter.

[0059] In this implementation, even if no abnormal fluctuation parameter data is detected, the server still generates a chart based on the real-time parameter data and displays it to the user. The beneficial effect is that the user can intuitively understand the status of the current environment at any time and maintain continuous monitoring of key data. Through graphical display, users can promptly discover potential trend changes or abnormal signals to help prevent risks in advance. In addition, this method also improves the user's transparency of the operating status, which facilitates subsequent decision-making and formulation of countermeasures.

[0060] In some implementations, when the risk identification result indicates that a risk exists, the method further includes: The risk identification result is input into a preset fire risk handling strategy set to obtain a corresponding fire risk handling strategy; wherein the fire risk handling strategy set is configured with multiple fire risk handling strategies.

[0061] Specifically, the risk identification result may be slight risk, medium risk, high risk, etc.

[0062] In this embodiment, the fire risk handling strategy may include an early warning strategy. For example, when the server identifies that certain parameters (such as temperature, gas concentration, etc.) fluctuate abnormally but have not yet reached a serious risk, the server issues an early warning message. The fire risk handling strategy may also include an automatic ventilation strategy. For example, when it is detected that the gas concentration (such as methane, carbon dioxide, etc.) reaches a certain level, the server automatically starts or strengthens the ventilation system to reduce the concentration of harmful gases.

[0063] The fire risk management strategy may also include equipment self-inspection and shutdown strategies. For example, when it is identified that the equipment may be in an abnormal state, the equipment self-inspection or shutdown operation is automatically triggered.

[0064] In this embodiment, when the server identifies the existence of a fire risk, the risk identification result is input into the preset fire risk disposal strategy set, and the appropriate disposal plan is automatically matched according to the specific risk situation. The beneficial effect of this method is that the server can quickly and accurately provide corresponding disposal strategies for fire risks of different types and severity, ensuring the timeliness and pertinence of the response measures. Through the automatic selection of multiple disposal strategies, it can effectively reduce the delay of human decision-making, improve the efficiency and accuracy of risk response, and reduce the possibility of accident losses.

[0065] According to an embodiment of the present invention, a fire risk identification device is provided. Figure 4 , the device may include: A receiving module, which is used to receive at least one real-time parameter data for characterizing the environmental state inside the closed wall; A judgment module, which is used to judge whether the real-time parameter data is parameter data with abnormal fluctuations; The identification module is used to input the abnormal fluctuation parameter data into a preset risk identification model for identification in the presence of abnormal fluctuation parameter data, so as to obtain a risk identification result.

[0066] According to an embodiment of the present invention, there is provided a server, comprising: a memory, and one or more processors communicatively coupled to the memory; The memory stores instructions that can be executed by the one or more processors, and the instructions are executed by the one or more processors to enable the one or more processors to implement the method provided in the above embodiment.

[0067] like Figure 5 As shown, according to an embodiment of the present invention, a collector system is provided, the system comprising: A monitoring host is configured outside the closed wall and is used to obtain real-time parameter data for characterizing the environmental status inside and outside the closed wall.

[0068] A display device is used to display the real-time parameter data.

[0069] The server is the server mentioned above.

[0070] In some embodiments, the system further comprises: An alarm device, wherein the alarm device can execute an alarm action based on an instruction from the monitoring host or the server.

[0071] In this embodiment, the monitoring host has an infrared thermoluminescence control function. When it detects someone approaching in the confined area, it can upload relevant information through the uplink interface, and the alarm device sends a voice alarm prompt message on the spot. The monitoring host can not only trigger the alarm device when it detects someone approaching, but also issue instructions through the server to let the alarm device sound and light alarm when the environmental parameters exceed the limit. This ensures that when the risk of fire or gas leakage increases, the system can promptly remind the staff to take corresponding measures.

[0072] According to an embodiment of the present invention, an electronic device is provided. Figure 6 The electronic device in this embodiment may include one or more of the following components: a processor, a network interface, a memory, a non-volatile memory, and one or more applications, wherein the one or more applications may be stored in the non-volatile memory and configured to be executed by one or more processors, and the one or more programs are configured to execute the method described in the aforementioned method embodiment.

[0073] According to an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a computer, the computer executes the method described in any of the above embodiments.

[0074] According to an embodiment of the present invention, a computer program product including instructions is further provided. When the instructions are executed by a computer, the computer executes a switch switching strategy execution method in any of the above embodiments.

[0075] 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.

[0076] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0077] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0078] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0079] 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 fire risk identification method, It is characterized in that The method comprises: Receiving at least one real-time parameter data for characterizing the environmental state within the closed wall; Determining whether the real-time parameter data is parameter data with abnormal fluctuations; In the case where abnormal fluctuation parameter data exists, at least the abnormal fluctuation parameter data is input into a preset risk identification model for identification to obtain a risk identification result.

2. The method according to claim 1, It is characterized in that The step of determining whether the real-time parameter data is parameter data with abnormal fluctuations includes: Retrieving historical parameter data for characterizing the environmental status inside the closed wall from a database; Calculating fluctuation parameter data based on the historical parameter data and the real-time parameter data; The fluctuation parameter data is compared with a preset fluctuation threshold, and when the fluctuation parameter data is greater than the fluctuation threshold, it is determined that abnormal fluctuation parameter data exists.

3. The method according to claim 1, It is characterized in that The real-time parameter data include: physical environment state parameter data and gas environment state parameter data; wherein, the physical environment state parameter data include the internal and external pressure difference of the closed wall or the temperature inside and outside the closed wall; the gas environment state parameter data include: oxygen, methane, carbon monoxide, carbon dioxide, hydrogen sulfide, acetylene or ethylene.

4. The method according to claim 3, It is characterized in that The step of inputting at least the abnormal fluctuation parameter data into a preset risk identification model for identification to obtain a risk identification result includes: Determining the type of the abnormal fluctuation parameter data; Determining a target risk identification model based on the type of the abnormal fluctuation parameter data; At least the abnormal fluctuation parameter data is input into the target risk identification model for identification to obtain a risk identification result.

5. The method according to claim 1, It is characterized in that In the absence of abnormal fluctuation parameter data, the method further includes: At least based on the real-time parameter data, a corresponding graph or table is generated for display to the user.

6. The method according to claim 1, It is characterized in that When the risk identification result indicates that there is a risk, the method further includes: The risk identification result is input into a preset fire risk handling strategy set to obtain a corresponding fire risk handling strategy; wherein the fire risk handling strategy set is configured with multiple fire risk handling strategies.

7. A fire risk identification device, It is characterized in that The device comprises: A receiving module, which is used to receive at least one real-time parameter data for characterizing the environmental state inside the closed wall; A judgment module, which is used to judge whether the real-time parameter data is parameter data with abnormal fluctuations; The identification module is used to input the abnormal fluctuation parameter data into a preset risk identification model for identification in the presence of abnormal fluctuation parameter data, so as to obtain a risk identification result.

8. A server, It is characterized in that include: a memory, and one or more processors communicatively coupled to the memory; The memory stores instructions that can be executed by the one or more processors. The instructions are executed by the one or more processors to enable the one or more processors to implement the method according to any one of claims 1 to 6.

9. A collector system, It is characterized in that The system comprises: A monitoring host, which is arranged outside the closed wall and is used to obtain real-time parameter data for characterizing the environmental status inside and outside the closed wall; A display device, the display device is used to display the real-time parameter data; The server is the server according to claim 8.

10. The collector system according to claim 9, It is characterized in that The system further comprises: An alarm device, wherein the alarm device can execute an alarm action based on an instruction from the monitoring host or the server.

Images