Enclosed space fire hazard on-line monitoring and advanced early warning method

Abstract

The invention discloses an enclosed space fire hazard on-line monitoring and advanced early warning method, and relates to the technical field of fire hazard monitoring and early warning, and the method comprises the steps: obtaining fire hazard monitoring data in real time through a sensor disposed in an enclosed space; performing denoising processing on the fire hazard monitoring data to obtain smoothed fire hazard monitoring data; calculating a feature fusion index according to the smoothed fire hazard monitoring data, and constructing a hazard classification decision function; identifying the fire hazard type according to the hazard classification decision function and the feature fusion index, and calculating the hazard intensity; and the hidden danger type and the hidden danger strength are sent to a monitoring center for advanced early warning. Through real-time monitoring, data fusion processing, accurate identification of fire hazard types, quantification of hidden danger severity, evaluation of insulation aging degree and provision of maintenance suggestions, advanced early warning and intelligent management of fire hazards of electrical equipment in a closed space are realized, and the safety, response efficiency and adaptability of the equipment are significantly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fire hazard monitoring and early warning, and in particular to an online monitoring and advance early warning method for fire hazards in a closed space. Background Art

[0002] With the development of power systems and industrial automation, electrical equipment in enclosed spaces, such as high-voltage ring network cabinets, switch cabinets, box-type substations, etc., are widely used in various power transmission and distribution scenarios. During the long-term operation of these devices, common hidden dangers include local overheating, insulation aging, and arc discharge. Traditional fire hazard detection methods, such as infrared imaging and wireless temperature measurement, are difficult to detect fire hazards generated during equipment operation in a timely manner due to their limited detection range, poor real-time performance, and complex installation, which can easily lead to equipment failure, tripping, and even fire accidents. Therefore, there is an urgent need for a technology that can realize real-time monitoring and advance warning of fire hazards in enclosed spaces.

[0003] Most of the existing fire monitoring methods are based on the detection of a single physical quantity, such as temperature, gas, smoke, etc., which makes it difficult to fully reflect the characteristics of hidden dangers in the complex environment inside the equipment. In addition, traditional methods often use empirical judgment to identify the types of hidden dangers, lack accurate calculation models, and are difficult to dynamically adjust and optimize the accuracy of hidden danger identification. Especially during the aging of insulation inside electrical equipment, due to the gradual degradation of insulating materials, it is often accompanied by the slow release of characteristic gases such as CO and H2S. These slowly changing hidden dangers are not easily identified by traditional detection methods, resulting in the accumulation of safety hazards and increased risks. Summary of the invention

[0004] Based on the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide an online monitoring and advance warning method for fire hazards in closed spaces to solve the above-mentioned technical problems.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solution: a method for online monitoring and advance warning of fire hazards in enclosed spaces, comprising:

[0006] Obtain fire hazard monitoring data in real time through sensors installed inside enclosed spaces;

[0007] De-noising the fire hazard monitoring data, removing noise by wavelet transform combined with an adaptive threshold algorithm to obtain smoothed fire hazard monitoring data;

[0008] Calculate a feature fusion index based on the smoothed fire hazard monitoring data, and construct a hazard classification decision function based on the feature fusion index;

[0009] According to the hidden danger classification decision function and feature fusion index, the fire hidden danger type is identified and the hidden danger intensity of the hidden danger type is calculated;

[0010] The hidden danger type and the hidden danger intensity are sent to the monitoring center for advance warning.

[0011] The present invention is further configured such that the sensor includes a particle sensor, a characteristic gas sensor and a temperature sensor; the fire hazard monitoring data includes particle concentration data, characteristic gas concentration data and temperature data, wherein the particle concentration data includes micron-level particle concentration data and nanometer-level particle concentration data, and the characteristic gas concentration data includes CO concentration data, H2S concentration data, O3 concentration data and NOx concentration data.

[0012] The present invention is further configured such that the calculation logic of the feature fusion index is: Among them, Φ t is the feature fusion index at time t, C t is the smoothed particle concentration data at time t, δC t is the rate of change of particle concentration data at time t, G t is the characteristic gas concentration data after smoothing at time t, δG t is the rate of change of characteristic gas concentration data at time t, T t is the smoothed temperature data at time t, T ref is the reference temperature set for the enclosed space, and α, β and γ are fusion coefficients, which are used to adjust the influence weights of different fire hazard monitoring data on the fusion index.

[0013] The present invention is further configured such that the calculation logic of the hidden danger classification decision function is: Among them, D t is the hidden danger classification decision function value at time t, sign() is the sign function used to distinguish the direction of temperature change, δT t is the rate of change of temperature data at time t, and η is the trade-off coefficient, which is used to control the influence of the particle concentration change rate and gas concentration change rate on the hidden danger classification decision function.

[0014] The present invention is further configured to identify the type of fire hazard according to the hazard classification decision function and the feature fusion index, including:

[0015] When the value of the hidden danger classification decision function is greater than the preset decision function threshold and the feature fusion index increases, the fire hidden danger type is identified as a local overheating hidden danger;

[0016] When the value of the hidden danger classification decision function is less than or equal to the preset decision function threshold and the feature fusion index increases, the particle concentration data and the characteristic gas concentration data are obtained. When the change rate of the micron-level particle concentration data is greater than that of the nano-level particle concentration data, and the CO concentration data and the H2S concentration data increase, the fire hidden danger type is identified as an insulation aging hidden danger.

[0017] When the change rate of the nano-particle concentration data is greater than that of the micron-particle concentration data, and the O3 concentration data and the NOx concentration data increase, the fire hazard type is identified as an arc discharge hazard.

[0018] The present invention is further configured such that the calculation logic of the hidden danger intensity is: Among them, I t is the hidden danger intensity at time t, n is the time window length, Φ t-k is the feature fusion index at time tk, D t-k is the hidden danger classification decision function value at time tk, T t-k is the temperature data at time tk, δC t-k is the rate of change of particle concentration data at time tk, δG t-k is the rate of change of the characteristic gas concentration data at time tk.

[0019] The present invention is further configured to send the hidden danger type and the hidden danger intensity to a monitoring center for early warning, including:

[0020] When the hidden danger intensity is greater than the first intensity threshold, the fire hidden danger is marked as high risk, and the high risk signal and hidden danger type are sent to the administrator, triggering the emergency processing process, and the equipment inside the closed space stops running;

[0021] When the hidden danger intensity is less than or equal to the first intensity threshold and greater than the second intensity threshold, the fire hidden danger is marked as medium risk, and a medium risk signal and the hidden danger type are sent to the administrator to prompt internal equipment maintenance;

[0022] When the hidden danger intensity is less than or equal to the second intensity threshold, the fire hidden danger is marked as low risk, and the low risk signal and hidden danger type are sent to the administrator for continuous monitoring and early warning.

[0023] The present invention is further configured such that, when the fire hazard type is identified as an insulation aging hazard, the method further comprises:

[0024] Calculate the CO concentration change rate and the H2S concentration change rate based on the CO concentration data and the H2S concentration data;

[0025] Calculate the insulation aging rate index and insulation aging degree cumulative index based on the CO concentration change rate and H2S concentration change rate;

[0026] The predicted value of the remaining insulation life is calculated based on the cumulative index of insulation aging degree, and a recommendation on the time of insulation replacement is provided based on the predicted value of the remaining insulation life.

[0027] The present invention is further configured such that the calculation logic of the insulation aging rate index is: Among them, I age,t is the insulation aging rate index at time t, G CO,t is the CO concentration data at time t, is the H2S concentration data at time t, is the reference concentration of H2S, i.e., the steady-state concentration of the insulating material; δ, ε, and ∈ are adjustment coefficients used to adjust the weights of CO concentration data and H2S concentration data in the insulation aging rate index;

[0028] The calculation logic of the insulation aging degree cumulative index is: Among them, S age,t is the cumulative index of insulation aging at time t, m is the length of the time window, T t-j is the temperature data at time tj;

[0029] The calculation logic of the insulation remaining life prediction value is: Among them, R life,t is the predicted value of the remaining insulation life at time t, and λ is the design life constant of the insulation material.

[0030] The present invention is further configured to provide insulation replacement time recommendations based on the insulation remaining life prediction value, including:

[0031] When the insulation remaining life prediction value is less than a preset insulation remaining life prediction threshold, an insulation material replacement signal is generated, and the insulation material replacement signal is sent to an administrator to replace the insulation material;

[0032] When the insulation remaining life prediction value is greater than or equal to a preset insulation remaining life prediction threshold, continuous monitoring and early warning are performed.

[0033] The present invention provides a method for online monitoring and advanced warning of fire hazards in a closed space. The method obtains fire hazard monitoring data in real time through a sensor installed inside the closed space; performs denoising on the fire hazard monitoring data, removes noise through wavelet transform combined with an adaptive threshold algorithm, and obtains smoothed fire hazard monitoring data; calculates a feature fusion index based on the smoothed fire hazard monitoring data, and constructs a hazard classification decision function based on the feature fusion index; identifies the type of fire hazard based on the hazard classification decision function and the feature fusion index, and calculates the hazard intensity of the hazard type; sends the hazard type and the hazard intensity to a monitoring center for advanced warning, and the beneficial effects produced include:

[0034] 1. Accurately identify fire hazard types: By constructing feature fusion indicators and hazard classification decision functions, common fire hazard types such as local overheating, insulation aging and arc discharge can be accurately identified. Feature fusion indicators overcome the limitations of traditional single parameter detection through comprehensive analysis of particle concentration, gas concentration and their change rate, and achieve deep fusion of multi-dimensional data, providing a scientific basis for the accurate classification of fire hazards;

[0035] 2. Quantitative evaluation of hidden danger severity: Through the hidden danger severity evaluation model, the historical monitoring data is accumulated and quantified, and the dynamic evolution of hidden dangers is comprehensively analyzed. The evaluation results reflect the severity of fire hazards in a numerical way, and can determine in real time whether the hidden danger is in a minor, medium or serious state, providing scientific support for the hierarchical early warning and emergency treatment of hidden dangers, and significantly improving the response capability of the monitoring system;

[0036] 3. Insulation aging assessment and maintenance recommendations: To address the potential dangers of insulation aging, the present invention constructs an insulation aging rate index and a cumulative aging assessment model based on the concentration change rate of CO and H2S to accurately assess the aging degree of insulation materials. By calculating the predicted value of the remaining insulation life, reasonable insulation replacement or maintenance time recommendations are provided to operation and maintenance personnel, effectively extending the service life of the equipment and reducing equipment failure rate and maintenance costs.

[0037] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0039] Figure 1 The present invention is a flowchart of a method for online monitoring and advance warning of fire hazards in a closed space, showing an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0041] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0042] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0043] A method for online monitoring and advance warning of fire hazards in enclosed spaces, such as Figure 1 As shown, including:

[0044] Obtain fire hazard monitoring data in real time through sensors installed inside enclosed spaces;

[0045] De-noising the fire hazard monitoring data, removing noise by wavelet transform combined with an adaptive threshold algorithm to obtain smoothed fire hazard monitoring data;

[0046] Calculate a feature fusion index based on the smoothed fire hazard monitoring data, and construct a hazard classification decision function based on the feature fusion index;

[0047] According to the hidden danger classification decision function and feature fusion index, the fire hidden danger type is identified and the hidden danger intensity of the hidden danger type is calculated;

[0048] The hidden danger type and the hidden danger intensity are sent to the monitoring center for advance warning.

[0049] A variety of sensors are installed around the electrical equipment inside the closed space. The present invention is further configured that the sensors include a particle sensor, a characteristic gas sensor and a temperature sensor; the fire hazard monitoring data includes particle concentration data, characteristic gas concentration data and temperature data, wherein the particle concentration data includes micron-level particle concentration data and nanometer-level particle concentration data, and the characteristic gas concentration data includes CO concentration data, H2S concentration data, O3 concentration data and NOx concentration data. Specifically, particle sensors are used to detect particles suspended in the air, such as smoke or combustion particles, to identify overheating or discharge phenomena; particle concentration data is divided into micron-sized particles and nano-sized particles concentration data, which reflect the presence of larger and smaller particles respectively; micron-sized particles (such as smoke particles) are usually produced by local overheating or larger combustion phenomena, while nano-sized particles (such as particles produced by discharge) are mostly derived from high-energy events such as arc discharge; characteristic gas sensors are used to monitor characteristic gases released by insulation aging, material decomposition or arc discharge; CO concentration data: Carbon monoxide is a common gas released during combustion and material aging, and changes in its concentration can reflect local combustion or aging; H2S concentration data: Hydrogen sulfide is a typical byproduct of insulation material aging, and its concentration change is closely related to insulation aging; O3 concentration data: Ozone is usually produced by arc discharge or strong electric field action, and is an important indicator gas for electrical discharge hazards; NOx concentration data: Nitrogen oxides include gases such as NO and NO2, which are commonly found in material decomposition or discharge phenomena at high temperatures.

[0050] The monitoring data acquired in real time is denoised, and the noise signal in the data is removed by wavelet transform combined with adaptive threshold algorithm to obtain smoothed fire hazard monitoring data. Wavelet transform can effectively separate the noise and useful information in the signal, and the adaptive threshold algorithm can automatically adjust the denoising intensity according to the characteristics of the data; wavelet transform is a signal processing technology used to decompose data so that useful signals and noise can be distinguished in different frequency domains, which is convenient for selective noise removal. The adaptive threshold algorithm is used to dynamically adjust the denoising threshold, automatically optimize the denoising effect according to the data characteristics, and avoid the misjudgment that may be caused by the fixed threshold. The above logic improves the quality of monitoring data, eliminates the influence of external interference on the monitoring results, makes the subsequent hazard identification more accurate, and avoids misjudgment caused by data noise.

[0051] According to the denoised smoothed data, the feature fusion index is calculated. The feature fusion index particle concentration, gas concentration and its change rate improve the response sensitivity to the hidden danger characteristics through nonlinear modulation. The present invention is further configured that the calculation logic of the feature fusion index is: Among them, Φ t is the feature fusion index at time t, C t is the smoothed particle concentration data at time t, δC t is the rate of change of particle concentration data at time t, G t is the characteristic gas concentration data after smoothing at time t, δG t is the rate of change of characteristic gas concentration data at time t, T t is the smoothed temperature data at time t, T ref is the reference temperature set for the enclosed space, and α, β and γ are fusion coefficients used to adjust the weight of the influence of different fire hazard monitoring data on the fusion index. Specifically, the above calculation logic quantifies the characteristic intensity of fire hazards by comprehensively analyzing the particle concentration, characteristic gas concentration and its change rate and temperature data, providing a scientific basis for hazard classification and severity assessment. Through the combination of nonlinear functions, the change characteristics of different monitoring data are fused into one indicator to enhance the recognition and response capabilities of hazard types; the fusion coefficients α, β and γ range from 0 to 1, which are used to adjust the sensitivity of the characteristic fusion index to different monitoring data to optimize the accuracy of hazard identification; through the comprehensive analysis of particle, gas and temperature data, the recognition accuracy of fire hazards is effectively improved, avoiding the misjudgment that may be caused by a single detection parameter; the use of nonlinear modulation to combine different monitoring data can more sensitively reflect the characteristic changes of hazards, making the system more timely in responding to sudden hazards.

[0052] The present invention is further configured such that the calculation logic of the hidden danger classification decision function is: Among them, D t is the hidden danger classification decision function value at time t, sign() is the sign function used to distinguish the direction of temperature change, δT tis the rate of change of temperature data at time t, and η is the trade-off coefficient, which is used to control the influence of the change rate of particle concentration and the change rate of gas concentration on the hidden danger classification decision function. Specifically, the above calculation logic constructs a hidden danger classification decision function, which is used to comprehensively evaluate the types of fire hazards. Through multi-parameter combination and nonlinear modulation, the temperature change rate, feature fusion index, and the change rate of particle and gas concentration are unified and integrated to form a unified decision indicator. Through sensitive response to different monitoring data, it can accurately identify the type of hidden danger and quantify the threat level of hidden danger; the trade-off coefficient η ranges from 0.1 to 1, which is used to adjust the influence of particle and gas changes on the decision results and optimize the classification accuracy; the hidden danger classification decision function can integrate multiple monitoring data in real time, and accurately identify the type and severity of hidden dangers by dynamically adjusting the response of temperature, particle and gas concentration changes to hidden dangers.

[0053] The present invention is further configured to identify the type of fire hazard according to the hazard classification decision function and the feature fusion index, including:

[0054] When the value of the hidden danger classification decision function is greater than the preset decision function threshold and the feature fusion index increases, the fire hazard type is identified as a local overheating hazard; specifically, the local overheating hazard is manifested as an abnormal increase in the local temperature of the internal equipment, which will not cause obvious gas release or particle generation in a short period of time, so its characteristics are mainly manifested by temperature changes. The temperature rise caused by local overheating is rapid and significant, and is not accompanied by large fluctuations in particle or gas concentrations. Therefore, by judging that the value of the hidden danger classification decision function is greater than the preset decision function threshold and the feature fusion index increases, local overheating hazards can be accurately identified, rather than other types of hazards.

[0055] When the value of the hidden danger classification decision function is less than or equal to the preset decision function threshold and the feature fusion index increases, the particle concentration data and the characteristic gas concentration data are obtained. When the change rate of the micron-level particle concentration data is greater than that of the nano-level particle concentration data, and the CO concentration data and the H2S concentration data increase, the fire hazard type is identified as the insulation aging hazard; specifically, when the value of the hidden danger classification decision function is less than or equal to the preset decision function threshold and the feature fusion index increases, it means that the current hidden danger feature strength is not obvious, especially the temperature change is relatively stable and has not reached the level that requires emergency treatment. Compared with the local overheating hazard, the insulation aging process is relatively slow and the temperature change is not drastic; the insulation aging hazard is mainly manifested as the slow wear or chemical aging of the insulation material, which is more obvious in micron-level particles and relatively less in nano-level particles or the change is not significant; therefore, the change rate of the micron-level particle concentration data is greater than that of the nano-level particle concentration data, which is the key feature for identifying the insulation aging hazard, and when the insulation material ages, the CO concentration data and the H2S concentration data gradually increase, reflecting the continuous process of insulation material degradation.

[0056] When the change rate of nano-particle concentration data is greater than that of micron-particle concentration data, and the O3 concentration data and NOx concentration data increase, the fire hazard type is identified as an arc discharge hazard. Specifically, nano-particles are usually produced by high-energy reactions such as arc discharge. These tiny particles are rapidly formed and dispersed in the air during the arc process due to their extremely fine particle size and large specific surface area; therefore, the rapid increase of nano-particles is a typical feature of arc discharge and an important sign that distinguishes it from other hazards. At the same time, O3 is a gas product unique to the arc discharge process. When air decomposes under a high electric field, oxygen molecules are excited by high-energy electrons to form ozone, and the concentration increases rapidly. During the high-temperature discharge process of NOx (nitrogen oxides), nitrogen and oxygen react at extremely high temperatures to form nitrogen oxides such as NO and NO2. The increase in the concentration of these gases is usually a direct response to arc discharge.

[0057] Through the comprehensive judgment of the hidden danger classification decision function and the characteristic fusion index, combined with the data changes of the particle concentration and the characteristic gas concentration, the specific types of fire hidden dangers can be accurately distinguished. By setting different discrimination conditions, local overheating, insulation aging and arc discharge hidden dangers can be accurately identified, so as to achieve targeted early warning and treatment; through multi-dimensional data fusion and dynamic analysis, it can accurately distinguish the three typical fire hidden danger types of local overheating, insulation aging and arc discharge, and provide targeted early warning and treatment measures for different hidden dangers; the above recognition logic can achieve early warning of fire risks in the early stage of hidden dangers through the analysis of characteristic change trends, and provide sufficient response time for equipment maintenance and risk control; by setting reasonable discrimination conditions, combined with the change rate of characteristic gas and particle concentration, it avoids the misjudgment or missed judgment caused by a single parameter in the traditional method, and significantly improves the intelligence and response accuracy of the system.

[0058] The present invention is further configured such that the calculation logic of the hidden danger intensity is: Among them, I t is the hidden danger intensity at time t, n is the time window length, Φ t-k is the feature fusion index at time tk, D t-k is the hidden danger classification decision function value at time tk, T t-k is the temperature data at time tk, δC t-k is the rate of change of particle concentration data at time tk, δG t-kis the rate of change of characteristic gas concentration data at time tk. Specifically, the above formula is used to calculate the intensity of hidden dangers, and comprehensively evaluate the severity of fire hazards through cumulative analysis of historical data. The calculation logic integrates the characteristic fusion indicators, hidden danger classification decision functions, particle and characteristic gas concentration change rates, and temperature changes at multiple moments into a cumulative model to reflect the overall intensity of hidden dangers at the current moment; by accumulating characteristic data at multiple moments, the hidden danger intensity calculation can capture the long-term evolution of hidden dangers, which is more comprehensive and accurate than the judgment at a single moment.

[0059] The present invention is further configured to send the hidden danger type and the hidden danger intensity to a monitoring center for early warning, including:

[0060] When the intensity of the hidden danger is greater than the first intensity threshold, the fire hazard is marked as high risk, and the high risk signal and hidden danger type are sent to the administrator, triggering the emergency handling process, and the equipment inside the closed space stops running; specifically, the first intensity threshold is a high risk judgment standard set according to the type of equipment and the operating environment, and is usually used to identify extreme or rapidly developing hidden dangers; the high risk mark indicates that the hidden danger is serious and may cause equipment damage, fire accidents or threats to personnel safety, so emergency measures need to be taken immediately. Triggering the emergency handling process includes stopping equipment operation, troubleshooting risk sources, starting the fire extinguishing system or other emergency response measures, which are not limited here.

[0061] When the hidden danger intensity is less than or equal to the first intensity threshold and greater than the second intensity threshold, the fire hazard is marked as medium risk, and the medium risk signal and hidden danger type are sent to the administrator, prompting internal equipment maintenance; specifically, the second intensity threshold is used to distinguish between medium risk and low risk hidden dangers, and the setting basis is the safety standard for equipment operation within an acceptable hidden danger intensity range. The medium risk mark indicates that the hidden danger has affected the normal operation of the equipment, but it will not cause immediate shutdown, and the risk can be reduced through maintenance and management measures; prompting equipment maintenance includes internal inspection, cleaning, replacement of damaged parts, etc., and the hidden danger is prevented from further deterioration through operation and maintenance means, which is not restricted here.

[0062] When the intensity of the hidden danger is less than or equal to the second intensity threshold, the fire hazard is marked as low risk, and the low risk signal and hidden danger type are sent to the administrator for continuous monitoring and early warning; the low risk mark indicates that the hidden danger intensity is within an acceptable range and does not affect the safe operation of the equipment, but it needs to be monitored to prevent its changes; the hidden danger characteristics are tracked through the real-time monitoring system to ensure that if the hidden danger intensity increases, the risk level and response measures can be adjusted in time. By conducting a graded assessment of the intensity of the hidden danger, the system can take corresponding measures according to the actual situation of the hidden danger, thereby avoiding overreaction or underreaction and ensuring the safe operation of the equipment; medium-risk and low-risk handling strategies can avoid frequent equipment shutdowns and large-scale repairs, reduce the impact of hidden dangers on equipment through maintenance and monitoring, and reduce downtime losses and maintenance costs; the high-risk handling solution can effectively prevent hidden dangers from deteriorating into fire accidents and protect personal and property safety through timely shutdown and emergency response; through the hierarchical management of hidden danger risks, operation and maintenance personnel can arrange maintenance plans and preventive measures more targetedly, and improve the overall operation and maintenance efficiency and equipment management level.

[0063] The present invention is further configured such that, when the fire hazard type is identified as an insulation aging hazard, the method further comprises:

[0064] Calculate the CO concentration change rate and the H2S concentration change rate based on the CO concentration data and the H2S concentration data;

[0065] The insulation aging rate index and the insulation aging degree cumulative index are calculated according to the CO concentration change rate and the H2S concentration change rate; the present invention is further configured that the calculation logic of the insulation aging rate index is: Among them, I age,t is the insulation aging rate index at time t, G CO,t is the CO concentration data at time t, is the H2S concentration data at time t, is the reference concentration of H2S, i.e., the steady-state concentration of the insulating material; δ, ε and ∈ are adjustment coefficients, which are used to adjust the weights of CO concentration data and H2S concentration data in the insulation aging rate index; the calculation logic of the insulation aging degree cumulative index is: Among them, S age,t is the cumulative index of insulation aging at time t, m is the length of the time window, T t-jis the temperature data at time tj; specifically, the calculation logic of the above formula is used to evaluate the aging degree of the insulation material. By analyzing the concentration change rate of CO and H2S, the insulation aging rate index and the insulation aging degree cumulative index are calculated, and the changes of the insulation material under different gas environments are comprehensively considered. Through nonlinear modulation and cumulative effects, the dynamic development trend of insulation aging is reflected, providing a scientific basis for insulation maintenance and replacement; the adjustment coefficients δ, ε and ∈ are in the range of 0.1 to 1, which are used to adjust the weight of different gases on aging assessment to adapt to the characteristics of different insulation materials. By calculating the aging rate index, the system can reflect the aging dynamics of the insulation material in real time and provide data support for predicting the insulation life; the insulation aging degree cumulative index can better capture the long-term changes of the aging process by accumulating historical data, and provide a comprehensive evaluation for insulation maintenance.

[0066] The insulation remaining life prediction value is calculated based on the insulation aging degree cumulative index, and insulation replacement time recommendations are provided based on the insulation remaining life prediction value. The calculation logic of the insulation remaining life prediction value is: Among them, R life,t is the predicted value of the remaining life of the insulation at time t, and λ is the design life constant of the insulation material. Specifically, the above calculation logic is used to predict the remaining life of the insulation material, and the actual life of the insulation material is evaluated by combining the cumulative calculation of the insulation aging degree and the influence of the key gas concentration. This logic dynamically adjusts the predicted value of the insulation material life to provide operation and maintenance personnel with time recommendations for insulation material replacement or maintenance, thereby ensuring the safe operation of the equipment; the design life constant λ of the insulation material represents the expected life of the insulation material under standard conditions of use, which is determined by the material of the insulation material and is the benchmark for life evaluation; by real-time evaluation of the cumulative calculation of aging and the key gas concentration, the system can provide a dynamic remaining life prediction value for the insulation material, helping the operation and maintenance personnel to arrange the insulation replacement plan according to the actual use status; compared with the fixed-cycle replacement strategy, the dynamic life evaluation can scientifically and reasonably recommend the replacement time according to the actual operating status and aging degree of the equipment, avoiding the replacement of insulation materials too early or too late.

[0067] The present invention is further configured to provide insulation replacement time recommendations based on the insulation remaining life prediction value, including:

[0068] When the insulation remaining life prediction value is less than a preset insulation remaining life prediction threshold, an insulation material replacement signal is generated, and the insulation material replacement signal is sent to an administrator to replace the insulation material;

[0069] When the predicted value of the remaining insulation life is greater than or equal to the preset threshold value of the predicted remaining insulation life, continuous monitoring and early warning are carried out. Specifically, through real-time evaluation of the remaining life, the system can intelligently recommend the replacement time, avoid human misjudgment, and reduce the uncertainty of maintenance work; the replacement signal generated in advance can prevent the sudden failure of the insulation material, thereby avoiding electrical accidents caused by insulation problems and improving the safe operation of the equipment; the replacement time is determined according to the actual state of the material, avoiding the waste of resources due to premature replacement, while avoiding the risks brought by late replacement, and optimizing the use of maintenance resources.

[0070] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0071] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0072] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0073] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0074] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0075] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0076] In the several embodiments provided in the present application, it should be understood that the disclosed system can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0077] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0078] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0079] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0080] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for online monitoring and advance warning of fire hazards in closed spaces, characterized in that: include: Obtain fire hazard monitoring data in real time through sensors installed inside enclosed spaces; De-noising the fire hazard monitoring data, removing noise by wavelet transform combined with an adaptive threshold algorithm to obtain smoothed fire hazard monitoring data; Calculate a feature fusion index based on the smoothed fire hazard monitoring data, and construct a hazard classification decision function based on the feature fusion index; According to the hidden danger classification decision function and feature fusion index, the fire hidden danger type is identified and the hidden danger intensity of the hidden danger type is calculated; The hidden danger type and the hidden danger intensity are sent to the monitoring center for advance warning.

2. The method for online monitoring and advance warning of fire hazards in enclosed spaces according to claim 1, characterized in that: The sensors include particle sensors, characteristic gas sensors and temperature sensors; the fire hazard monitoring data include particle concentration data, characteristic gas concentration data and temperature data, wherein the particle concentration data include micron-level particle concentration data and nanometer-level particle concentration data, and the characteristic gas concentration data include CO concentration data, H2S concentration data, O3 concentration data and NOx concentration data.

3. The method for online monitoring and advance warning of fire hazards in enclosed spaces according to claim 2, characterized in that: The calculation logic of the feature fusion index is: Among them, Φ t is the feature fusion index at time t, C t is the smoothed particle concentration data at time t, δC t is the rate of change of particle concentration data at time t, G t is the characteristic gas concentration data after smoothing at time t, δG t is the rate of change of characteristic gas concentration data at time t, T t is the smoothed temperature data at time t, T ref is the reference temperature set for the enclosed space, and α, β and γ are fusion coefficients, which are used to adjust the influence weights of different fire hazard monitoring data on the fusion index.

4. The method for online monitoring and advance warning of fire hazards in enclosed spaces according to claim 3 is characterized in that: The calculation logic of the hidden danger classification decision function is: Among them, D t is the hidden danger classification decision function value at time t, sign() is the sign function used to distinguish the direction of temperature change, δT t is the rate of change of temperature data at time t, and η is the trade-off coefficient, which is used to control the influence of the particle concentration change rate and gas concentration change rate on the hidden danger classification decision function.

5. The method for online monitoring and advance warning of fire hazards in enclosed spaces according to claim 2, characterized in that: According to the hidden danger classification decision function and feature fusion index, the fire hidden danger types are identified, including: When the value of the hidden danger classification decision function is greater than the preset decision function threshold and the feature fusion index increases, the fire hidden danger type is identified as a local overheating hidden danger; When the value of the hidden danger classification decision function is less than or equal to the preset decision function threshold and the feature fusion index increases, the particle concentration data and the characteristic gas concentration data are obtained. When the change rate of the micron-level particle concentration data is greater than that of the nano-level particle concentration data, and the CO concentration data and the H2S concentration data increase, the fire hidden danger type is identified as an insulation aging hidden danger. When the change rate of the nano-particle concentration data is greater than that of the micron-particle concentration data, and the O3 concentration data and the NOx concentration data increase, the fire hazard type is identified as an arc discharge hazard.

6. The method for online monitoring and advance warning of fire hazards in enclosed spaces according to claim 2, characterized in that: The calculation logic of the hidden danger intensity is: Among them, I t is the hidden danger intensity at time t, n is the time window length, Φ t-k is the feature fusion index at time tk, D t-k is the hidden danger classification decision function value at time tk, T t-k is the temperature data at time tk, δC t-k is the rate of change of particle concentration data at time tk, δG t-k is the rate of change of the characteristic gas concentration data at time tk.

7. The method for online monitoring and advance warning of fire hazards in enclosed spaces according to claim 6, characterized in that: The hidden danger type and the hidden danger intensity are sent to the monitoring center for early warning, including: When the hidden danger intensity is greater than the first intensity threshold, the fire hidden danger is marked as high risk, and the high risk signal and hidden danger type are sent to the administrator, triggering the emergency processing process, and the equipment inside the closed space stops running; When the hidden danger intensity is less than or equal to the first intensity threshold and greater than the second intensity threshold, the fire hidden danger is marked as medium risk, and a medium risk signal and the hidden danger type are sent to the administrator to prompt internal equipment maintenance; When the hidden danger intensity is less than or equal to the second intensity threshold, the fire hidden danger is marked as low risk, and the low risk signal and hidden danger type are sent to the administrator for continuous monitoring and early warning.

8. The method for online monitoring and advance warning of fire hazards in enclosed spaces according to claim 5, characterized in that: When the fire hazard type is identified as insulation aging hazard, the method further includes: Calculate the CO concentration change rate and the H2S concentration change rate based on the CO concentration data and the H2S concentration data; Calculate the insulation aging rate index and insulation aging degree cumulative index based on the CO concentration change rate and H2S concentration change rate; The predicted value of the remaining insulation life is calculated based on the cumulative index of insulation aging degree, and a recommendation on the time of insulation replacement is provided based on the predicted value of the remaining insulation life.

9. The method for online monitoring and advance warning of fire hazards in enclosed spaces according to claim 8, characterized in that: The calculation logic of the insulation aging rate index is: Among them, I age,t is the insulation aging rate index at time t, G CO,t is the CO concentration data at time t, is the H2S concentration data at time t, is the reference concentration of H2S, i.e., the steady-state concentration of the insulating material; δ, ε, and ∈ are adjustment coefficients used to adjust the weights of CO concentration data and H2S concentration data in the insulation aging rate index; The calculation logic of the insulation aging degree cumulative index is: Among them, S age,t is the cumulative index of insulation aging at time t, m is the length of the time window, T t-j is the temperature data at time tj; The calculation logic of the insulation remaining life prediction value is: Among them, R life,t is the predicted value of the remaining insulation life at time t, and λ is the design life constant of the insulation material.

10. The method for online monitoring and advance warning of fire hazards in enclosed spaces according to claim 9, characterized in that: Provide insulation replacement time recommendations based on the predicted value of insulation remaining life, including: When the insulation remaining life prediction value is less than a preset insulation remaining life prediction threshold, an insulation material replacement signal is generated, and the insulation material replacement signal is sent to an administrator to replace the insulation material; When the insulation remaining life prediction value is greater than or equal to a preset insulation remaining life prediction threshold, continuous monitoring and early warning are performed.

Images