Building fire safety assessment method based on big data analysis
Through big data analysis and neural network model, the false breakthrough phenomenon of building electrical line temperature is identified and corrected, which improves the accuracy of building fire safety assessment, solves the problem of low evaluation accuracy in traditional methods, and enhances the risk of electrical fire recognition ability.
Patent Information
- Application Number
- CN202411244996.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-09-06
AI Technical Summary
When evaluating building electrical fire safety, traditional methods cannot accurately identify and deal with false breakthroughs in a short period of wire temperature, resulting in low evaluation accuracy and ineffective reduction of electrical fire risks.
By using a method based on big data analysis, the voltage, current and residual current data of electrical circuits are collected, the temperature is predicted using neural network models, the false breakthrough coefficient of conductor temperature is determined, the temperature sequence is corrected, the fire safety judgment coefficient is calculated, and the building fire safety is carried out. Evaluate.
It improves the accuracy of building electrical fire safety assessment, can identify and deal with false breakthroughs, enhances the accuracy of electrical conductor temperature, and reduces fire risk.
Smart Images

Figure CN118760834B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of electronic digital data processing technology, and in particular to a building fire safety assessment method based on big data analysis. Background Art
[0002] With the recent advancement of power technology, electricity has become an integral part of everyday life. However, the attendant electrical safety issues cannot be ignored. Therefore, building fire safety requires not only assessing the quantity and location of firefighting equipment, but also evaluating the building's electrical fire safety. When the temperature of a building's electrical wiring reaches flammable temperatures, a fire can occur. To reduce the risk of electrical fires in buildings and protect both personal and property safety, electrical wiring temperature monitoring is used to assess the safety of electrical fire protection in buildings.
[0003] Traditional methods assess electrical safety by averaging the temperature of wires over a specific period of time. Since wire temperatures fluctuate rather than being fixed, and temperature sensors typically measure only a single location, traditional methods typically use current and voltage data to predict wire temperature data. However, when using high-power electrical appliances, wire temperatures can briefly exceed fire-prone temperatures, a phenomenon known as a false breakout. Using fixed weights to estimate the short-term temperature of building wires is sensitive to short-term temperature fluctuations, resulting in low accuracy in false breakout estimates, which in turn reduces the accuracy of building fire safety assessments. Summary of the Invention
[0004] In order to solve the above technical problems, a building fire safety assessment method based on big data analysis is provided to solve the existing problems.
[0005] The solution to the technical problem in this application is to provide a building fire safety assessment method based on big data analysis, including the following steps:
[0006] Collect electrical parameter data of the electrical circuit, obtain the predicted temperature of the electrical circuit at each moment, and obtain the safe temperature series of the conductor;
[0007] According to the distribution difference of the temperature at each moment in the conductor safety temperature sequence, the conductor temperature false breakthrough coefficient is determined to obtain the false breakthrough temperature sequence;
[0008] According to the mapping distribution of the temperature at each moment in each false breakthrough temperature sequence and the false breakthrough coefficient of the conductor temperature, the corrected temperature at each moment in the conductor safety temperature sequence is determined to obtain a fire protection temperature assessment sequence;
[0009] Based on the corrected temperature at each moment in the fire temperature assessment sequence, the fire safety determination coefficient is determined to evaluate the building fire safety.
[0010] Preferably, the method for obtaining the conductor safety temperature sequence is:
[0011] The voltage, current and residual current collected in real time at each moment are used with a neural network model to obtain the predicted temperature of the electrical circuit at each moment;
[0012] Arrange the predicted temperatures at all times in chronological order to form a conductor safety temperature sequence.
[0013] Preferably, determining the conductor temperature false breakthrough coefficient to obtain the false breakthrough temperature sequence includes:
[0014] The conductor safety temperature sequence is evenly divided into multiple subsequences, which are recorded as breakthrough temperature sequences;
[0015] Obtain the range of each breakthrough temperature series separately to form a temperature range set;
[0016] Determining a judgment condition gain coefficient according to the difference characteristics between the quartile difference and the range of the temperature extreme difference set;
[0017] Calculate the mean of the temperature extreme difference set, and record it as the first mean;
[0018] The first mean value is combined with the judgment condition gain coefficient to determine the conductor temperature false breakthrough coefficient;
[0019] All breakthrough temperature sequences whose ranges are greater than the temperature false breakthrough judgment coefficient are recorded as false breakthrough temperature sequences.
[0020] Preferably, the determination of the judgment condition gain coefficient includes:
[0021] The ratio between twice the interquartile range of the temperature extreme difference set and the range of the temperature extreme difference set is recorded as a first ratio;
[0022] If the first ratio is greater than or equal to the preset judgment threshold, the judgment condition gain coefficient is the first ratio; if the first ratio is less than the preset judgment threshold or the range of the temperature extreme difference set is 0, the judgment condition gain coefficient is assigned a value of 1.
[0023] Preferably, determining the corrected temperature at each moment in the conductor safety temperature sequence to obtain a fire protection temperature assessment sequence includes:
[0024] Determining a fire protection temperature breakthrough index at each moment in each false breakthrough temperature sequence based on the temperature at each moment in the false breakthrough temperature sequence, the minimum value of the false breakthrough temperature sequence, and the false breakthrough coefficient of the conductor temperature;
[0025] The calculation result of the sigmoid function of the temperature at each moment in each false breakthrough temperature sequence is recorded as the first function value;
[0026] Determining a correction factor at each moment in each false breakthrough temperature sequence based on the minimum value of each false breakthrough temperature sequence, the fire protection temperature breakthrough index, and the first function value;
[0027] If the fire temperature breakthrough index is greater than or equal to 0, the temperature corrected at the corresponding moment is the correction factor; otherwise, the temperature at the corresponding moment remains unchanged; and the corrected temperature at each moment in the conductor safety temperature sequence is obtained;
[0028] The corrected temperatures at multiple moments are selected from the back to the front in the conductor safety temperature sequence to form a fire protection temperature assessment sequence.
[0029] Preferably, determining the fire protection temperature breakthrough index at each moment in each false breakthrough temperature sequence includes:
[0030] According to the difference between the temperature at each moment in each pseudo-breakthrough temperature sequence and the minimum value of the pseudo-breakthrough temperature sequence, the relative difference degree at each moment is determined;
[0031] The difference between the relative difference and the conductor temperature false breakthrough coefficient is used as the fire protection temperature breakthrough index at each moment in each false breakthrough temperature sequence.
[0032] Preferably, the correction factor at each moment in each false breakthrough temperature sequence is a fusion result of the minimum value of each false breakthrough temperature sequence, the conductor temperature false breakthrough coefficient, and the first function value.
[0033] Preferably, the determining of the fire safety determination coefficient and the assessment of building fire safety include:
[0034] Determining a fire weighting coefficient at each moment in the fire temperature evaluation sequence based on the corrected temperature at each moment in the fire temperature evaluation sequence;
[0035] Determining the adaptive weight at each moment in the fire temperature assessment sequence based on the fire weight assessment coefficient;
[0036] Based on the corrected temperature at each moment in the fire temperature assessment sequence and the adaptive weight at the corresponding moment, a weighted average algorithm is used to determine the fire safety determination coefficient;
[0037] The fire safety determination coefficient is normalized. If the normalized result is greater than a preset fire risk threshold, then there is a fire hazard in the building; otherwise, there is no fire hazard in the building.
[0038] Preferably, the determination of the fire weight evaluation coefficient at each moment in the fire temperature evaluation sequence includes:
[0039] Analyze the difference between the corrected value and the mean value at each moment in the fire temperature assessment sequence as the absolute temperature difference at each moment;
[0040] The fire protection weight assessment coefficient at each moment is positively correlated with the corrected temperature at the corresponding moment, and negatively correlated with the absolute temperature difference.
[0041] Preferably, determining the adaptive weight at each moment in the fire temperature assessment sequence includes:
[0042] The mean of the fire weight evaluation coefficients at all moments in the fire temperature evaluation sequence is recorded as the second mean;
[0043] The ratio of the fire weight evaluation coefficient at each moment in the fire temperature evaluation sequence to the second mean value is used as the adaptive weight at each moment in the fire temperature evaluation sequence.
[0044] This application has at least the following beneficial effects:
[0045] The present application predicts the temperature of the electrical circuit by using a neural network model based on the voltage, current and residual current collected in real time. The beneficial effect is that it avoids the error caused by obtaining the temperature of the electrical circuit at a certain point only through a temperature sensor, which is conducive to improving the accuracy of subsequent fire safety assessments; the false breakthrough coefficient of the conductor temperature is determined by the temperature of the electrical circuit at each moment, and a false breakthrough temperature sequence is obtained. The beneficial effect is that it can identify and distinguish temperature data with false breakthroughs; based on the temperature data with false breakthroughs, it is corrected to determine the corrected temperature at each moment in the conductor safety temperature sequence, and a fire temperature assessment sequence is obtained. The beneficial effect is that through By correcting the temperature with false breakthroughs, the influence of false breakthroughs is eliminated and the accuracy of fire safety assessment is improved; based on the corrected temperature at each moment in the fire temperature assessment sequence of the last period, the adaptive weight at each moment is calculated to determine the fire safety determination coefficient. The beneficial effect is that based on the different weights corresponding to the corrected temperatures at different moments, the fire safety of the building can be evaluated more accurately and comprehensively; based on the fire safety determination coefficient, the fire safety assessment coefficient is determined, the fire safety risk level is constructed, and the fire safety of the building is evaluated. The beneficial effect is that the accuracy of the temperature measurement of the building's electrical conductors is improved, thereby making the fire safety assessment of the building more accurate. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] The building fire safety assessment method based on big data analysis of this application is further described in detail below with reference to the accompanying drawings.
[0047] Figure 1 A flowchart of the steps of the building fire safety assessment method based on big data analysis provided for this application;
[0048] Figure 2 A flow chart of the steps for predicting the temperature of an electrical circuit provided for this application;
[0049] Figure 3 Schematic diagram of the false breakthrough of the predicted temperature of the electrical circuit provided for this application;
[0050] Figure 4 A flowchart of the steps of the method for obtaining the conductor temperature false breakthrough coefficient provided in this application;
[0051] Figure 5 This is a flowchart of the steps of the method for obtaining the fire safety determination coefficient provided in this application. DETAILED DESCRIPTION
[0052] To make the objectives, technical solutions, and advantages of this application more clearly understood, the following describes in further detail the building fire safety assessment method based on big data analysis proposed in this application, in conjunction with the accompanying drawings and implementation examples. It should be understood that the specific embodiments described herein are merely intended to explain this application and are not intended to limit this application.
[0053] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
[0054] See also Figure 1 , which shows a flowchart of a building fire safety assessment method based on big data analysis provided by an embodiment of the present application, the method comprising the following steps:
[0055] Step 1: Collect electrical parameter data of the electrical circuit, obtain the predicted temperature of the electrical circuit, and obtain the safe temperature sequence of the conductor.
[0056] By installing voltage sensors, current sensors, temperature sensors, and residual current devices (RCDs) on the building's electrical circuits, the voltage, current, temperature, and residual current of the building's electrical circuits are collected and transmitted to a big data platform. This data, including voltage, current, residual current, and temperature, is then trained using a neural network model. By inputting the real-time collected voltage, current, and residual current, a predicted temperature for the electrical circuits is generated.
[0057] Preferably, as one embodiment of the present application, a long short-term memory network is used for training, collecting voltage, current, and residual current data in real time. The network then acquires the predicted temperature of the building's electrical circuits. Real-time data collection occurs at a frequency of 0.5 seconds per acquisition, for a total acquisition duration of 10 minutes. All predicted temperatures are arranged in chronological order of data collection, and recorded as a conductor safety temperature sequence. The calculations for the long short-term memory network are well-known, and the detailed calculation process is omitted here.
[0058] Furthermore, the flowchart of the steps for predicting the temperature of the electrical circuit provided in the embodiment of the present application is as follows: Figure 2 shown.
[0059] At this point, the safe temperature sequence of the wire is obtained.
[0060] Step 2: According to the distribution difference of the temperature at each moment in the conductor safety temperature sequence, the conductor temperature false breakthrough coefficient is determined to obtain the false breakthrough temperature sequence.
[0061] Ensuring circuit safety is crucial in building electrical systems, especially in fire protection design. The sudden connection of high-power electrical appliances, such as central air conditioning systems, can cause a sharp increase in the current flowing through the circuit. According to Joule's law, when current flows through a conductor, heat is generated, proportional to the square of the current, the conductor's resistance, and the duration of the current. Since conductor temperature is calculated based on current and voltage, the calculated conductor temperature will increase. Once the appliance is activated, the current returns to normal levels. Therefore, a building's conductor temperature may temporarily exceed a preset range, but this remains within normal limits.
[0062] Because building conductor temperature spikes occur over a very short period of time, these short-term temperature spikes are called false spikes. These false spikes do not pose a safety risk to firefighting. Therefore, the impact of these false spikes should be eliminated when assessing building fire safety.
[0063] Furthermore, the schematic diagram of the false breakthrough of the electrical circuit temperature prediction provided by this application is as follows Figure 3 shown.
[0064] The conductor safety temperature sequence is evenly divided into multiple subsequences, which are recorded as breakthrough temperature sequences;
[0065] Preferably, as an embodiment of the present application, the wire safety temperature sequence is evenly divided into 60 subsequences. As other implementation methods, the implementer can set the number of subsequences according to actual conditions, and this embodiment does not impose any special restrictions on this.
[0066] Obtain the range of each breakthrough temperature sequence respectively, and form all the ranges into a temperature range set;
[0067] When a false breakthrough occurs, the range of the breakthrough temperature sequence in the false breakthrough area will be very large, and there will be a large difference between the range values of the conductor temperature in other normal areas. Therefore, the judgment condition gain coefficient is calculated based on the difference between the range values, which is specifically:
[0068] The ratio between twice the interquartile range of the temperature extreme difference set and the range of the temperature extreme difference set is recorded as a first ratio;
[0069] If the first ratio is greater than or equal to a preset determination threshold, the determination condition gain coefficient is the first ratio; if the first ratio is less than the preset determination threshold or the range of the temperature extreme difference set is 0, the determination condition gain coefficient is assigned a value of 1;
[0070] Preferably, as an embodiment of the present application, the preset determination threshold value is 1; wherein, the calculation method of the interquartile range is a well-known technology and will not be described in detail.
[0071] It should be noted that a first ratio greater than or equal to 1 indicates that the ranges in the temperature range set are relatively close and distributed more concentratedly, which means that the range data fluctuates less and the possibility of false breakouts is low. Conversely, when the first ratio is less than 1, it indicates that there are significant outliers in the temperature range set. These outliers may represent abnormal fluctuations or false breakouts, thereby increasing the probability of false breakouts.
[0072] Data with false breakthrough characteristics refers to the characteristics of short-term and high values in the conductor temperature. Therefore, false breakthrough data has the characteristics of outliers. In order to identify whether the breakthrough temperature series is a false breakthrough temperature, the conductor temperature false breakthrough coefficient is calculated. Specifically, it is:
[0073] Calculate the mean of the temperature range set and record it as the first mean;
[0074] The first mean value is combined with the judgment condition gain coefficient to determine the conductor temperature false breakthrough coefficient;
[0075] It is understandable that fusion can represent a multiplication relationship, an addition relationship, and the idempotence of an exponential function, and this application does not impose any special restrictions on this.
[0076] Preferably, as an embodiment of the present application, the product of the first mean value and the determination condition gain coefficient is used as the conductor temperature false breakthrough coefficient.
[0077] Furthermore, the present application provides a flowchart of the steps of the method for obtaining the conductor temperature pseudo-breakthrough coefficient. Figure 4 shown.
[0078] All breakthrough temperature sequences whose range is greater than the temperature false breakthrough judgment coefficient are recorded as false breakthrough temperature sequences;
[0079] It should be noted that the first mean value can reflect the intermediate data characteristics of the conductor temperature. Secondly, when no false breakthrough occurs, the first mean value cannot guarantee that all data is normal. Therefore, the mean value is corrected using the gain coefficient of the breakthrough temperature sequence judgment condition, so that normal data can be classified as normal data based on the conductor temperature false breakthrough coefficient. When the range of the breakthrough temperature sequence is greater than the conductor temperature false breakthrough coefficient, it indicates that the data in the breakthrough temperature sequence may be false breakthrough data. The greater the difference between the range of the breakthrough temperature sequence and the conductor temperature false breakthrough coefficient, the higher the probability of a false breakthrough in the breakthrough temperature sequence.
[0080] At this point, the conductor temperature false breakthrough coefficient is obtained and the false breakthrough temperature sequence is determined.
[0081] Step 3: According to the mapping distribution of the temperature at each moment in each false breakthrough temperature sequence and the false breakthrough coefficient of the conductor temperature, the corrected temperature at each moment in the conductor safety temperature sequence is determined to obtain a fire protection temperature assessment sequence.
[0082] For the breakthrough temperature sequence with false breakthrough, it is actually within the normal range for the safety of wires in fire fighting, and the fire fighting risk is relatively low. Therefore, the data in the breakthrough temperature sequence with false breakthrough can be corrected as follows:
[0083] Determining the relative difference between each moment in each pseudo-breakthrough temperature sequence according to the difference between the temperature at each moment in each pseudo-breakthrough temperature sequence and the minimum value of the pseudo-breakthrough temperature sequence;
[0084] Preferably, as an embodiment of the present application, the relative difference between each moment in each false breakthrough temperature sequence is the difference between the temperature at each moment in each false breakthrough temperature sequence and the minimum value of the false breakthrough temperature sequence.
[0085] The difference between the relative difference and the conductor temperature false breakthrough coefficient is used as the fire protection temperature breakthrough index at each moment in each false breakthrough temperature sequence.
[0086] Preferably, as an embodiment of the present application, the fire protection temperature breakthrough index at each moment in each false breakthrough temperature sequence is the difference between the relative difference and the conductor temperature false breakthrough coefficient.
[0087] It should be noted that the smaller the fire temperature breakthrough index is, the smaller the gap between the temperature at each moment in the false breakthrough temperature sequence and the temperature false breakthrough judgment coefficient is, thereby increasing the possibility that it belongs to normal temperature fluctuations, and thus representing that the temperature at that moment is more likely to be normal data.
[0088] Furthermore, based on the fire temperature breakthrough index, the temperature at each moment in the false breakthrough temperature sequence is corrected, specifically:
[0089] The calculation result of the sigmoid function of the temperature at each moment in each false breakthrough temperature sequence is recorded as the first function value;
[0090] The minimum value of each false breakthrough temperature sequence, the conductor temperature false breakthrough coefficient and the first function value are combined to determine the correction factor at each moment in each false breakthrough temperature sequence;
[0091] Preferably, as an embodiment of the present application, the product of the first function value and the wire temperature false breakthrough coefficient at each moment in each false breakthrough temperature sequence is recorded as the first product at each moment in each false breakthrough temperature sequence, and the first product and the minimum value of each false breakthrough temperature sequence are used as the correction factor at each moment in each false breakthrough temperature sequence.
[0092] If the fire temperature breakthrough index is greater than or equal to 0, the temperature corrected at the corresponding moment is the correction factor; if the fire temperature breakthrough index is less than 0, the temperature at the corresponding moment remains unchanged;
[0093] It should be noted that a higher corrected temperature at each moment in the false breakthrough temperature series indicates an abnormally high conductor temperature, increasing the risk of fire. Furthermore, higher temperatures may indicate a lower fire safety level. Therefore, corrected conductor temperatures can be used to assess building fire safety.
[0094] Based on the corrected temperature at each moment, the temperature at the corresponding moment in the conductor safety temperature sequence is replaced to obtain the corrected temperature at each moment in the conductor safety temperature sequence;
[0095] The corrected temperatures at multiple moments are selected from the conductor safety temperature sequence from the end to the beginning to form a fire protection temperature assessment sequence;
[0096] Preferably, as an embodiment of the present application, the corrected temperatures of the last 120 moments in the wire safety temperature sequence constitute a fire temperature assessment sequence, that is, the corrected temperatures of the last 1 minute constitute the fire temperature assessment sequence; as other implementation methods, the implementer can set the length of the fire temperature assessment sequence according to actual conditions.
[0097] At this point, the corrected temperature at each moment in the conductor safety temperature sequence is determined, and the fire protection temperature evaluation sequence is obtained.
[0098] Step 4: Based on the corrected temperature at each moment in the fire temperature assessment sequence, determine the fire safety determination coefficient and assess the building fire safety.
[0099] Furthermore, as conductor temperatures rise, their insulation performance may deteriorate, increasing the risk of current leakage and short circuits, thereby reducing fire safety. As temperatures continue to rise, the conductor material may soften or even melt, which can lead to poor contact at wire connections, further increasing the probability of fire. Therefore, the fire weighting factor is calculated based on the corrected temperature of the building's conductors at each moment, specifically:
[0100] determining an absolute temperature difference at each moment in the fire temperature evaluation sequence based on a difference between the corrected temperature at each moment in the fire temperature evaluation sequence and a mean value of the fire temperature evaluation sequence;
[0101] Preferably, as an embodiment of the present application, the absolute value of the difference between the corrected temperature at each moment in the fire temperature evaluation sequence and the mean of the fire temperature evaluation sequence is used as the absolute temperature difference at each moment in the fire temperature evaluation sequence.
[0102] The fire weight assessment coefficient at each moment in the fire temperature assessment sequence is positively correlated with the corrected temperature at the corresponding moment and negatively correlated with the absolute temperature difference;
[0103] Preferably, as an embodiment of the present application, the ratio between the corrected temperature at each moment in the fire temperature evaluation sequence and the absolute temperature difference is used as the fire weight evaluation coefficient at each moment in the fire temperature evaluation sequence.
[0104] Preferably, as another embodiment of the present application, the ratio of the corrected absolute temperature difference at each moment in the fire temperature assessment sequence is recorded as the second ratio; the calculation result of the exponential function with a natural constant as the base and the second ratio as the exponent is used as the fire weight assessment coefficient at each moment in the fire temperature assessment sequence.
[0105] It can be understood that a positive relationship indicates that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. The specific relationship in the process can be a multiplication relationship, an addition relationship, or the power of an exponential function, which is determined by actual application; a negative relationship indicates that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. The specific relationship can be a subtraction relationship, a division relationship, or a negative exponential power, which is determined by actual application, and this application does not impose any special restrictions on this.
[0106] It should be noted that the higher the corrected temperature at each moment in the fire temperature assessment sequence, the higher the fire risk at that moment. Furthermore, if the temperature at that moment is in a relatively concentrated part of the fire temperature assessment sequence, the fire risk at that moment is higher and the building fire safety is lower. Therefore, the larger the fire weighting coefficient, the higher the fire weighting coefficient.
[0107] The larger the fire weight assessment coefficient is, the higher the fire risk is at that moment. Therefore, the adaptive weight at each moment is calculated based on the distribution of the fire weight assessment coefficient, specifically:
[0108] The mean of the fire weight evaluation coefficients at all moments in the fire temperature evaluation sequence is recorded as the second mean;
[0109] The ratio of the fire weight evaluation coefficient at each moment in the fire temperature evaluation sequence to the second mean value is used as the adaptive weight at each moment in the fire temperature evaluation sequence;
[0110] It should be noted that the larger the adaptive weight, the higher the temperature value at that moment, which means that the fire risk at that moment is higher than that at other moments in the fire temperature assessment sequence, and the fire safety is lower.
[0111] Based on the corrected temperature at each moment in the fire temperature assessment sequence and the adaptive weight at the corresponding moment, a moving weighted average algorithm is used to determine the fire safety determination coefficient;
[0112] Furthermore, the step flow chart of the method for obtaining the fire safety determination coefficient provided by this application is as follows: Figure 5 shown.
[0113] Furthermore, the fire safety of the building is evaluated based on the fire safety determination coefficient, specifically:
[0114] The fire safety determination coefficient is normalized. If the normalized result is greater than a preset fire risk threshold, there is a fire hazard in the building, and the wires are checked to prevent the occurrence of electrical fires. If the normalized result is greater than the preset fire risk threshold, there is no fire hazard in the building.
[0115] Preferably, as an embodiment of the present application, the preset fire risk threshold value is 0.4; due to the different materials used for the conductors of different electrical circuits, the fire risk temperature thresholds of the conductors are also different, that is, the fire risk temperature threshold is set according to the conductor material of the building. Therefore, as another implementation method, the implementer can set it according to actual conditions.
[0116] Therefore, the fire safety determination coefficient is calculated every once in a while to evaluate the fire safety of the building.
[0117] Preferably, as an embodiment of the present application, the fire safety of the building is assessed once every 1 minute. As other implementation methods, the implementer can set the interval time according to the actual situation.
[0118] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.
[0119] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0120] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the present application. It should be noted that a person skilled in the art can make various modifications and improvements without departing from the spirit of the present application. Therefore, any simple modifications, equivalent variations, and modifications to the above embodiments made in accordance with the technical essence of the present application without departing from the content of the present application's technical solution fall within the scope of protection of the present application's technical solution.
Claims
1. A building fire safety assessment method based on big data analysis, characterized in that: The method comprises the following steps: Collect electrical parameter data of electrical circuits, obtain predicted temperature of electrical circuits at each moment, and obtain safe temperature sequence of conductors; According to the distribution difference of the temperature at each moment in the conductor safety temperature sequence, the conductor temperature false breakthrough coefficient is determined to obtain the false breakthrough temperature sequence; According to the mapping distribution of the temperature at each moment in each false breakthrough temperature sequence and the false breakthrough coefficient of the conductor temperature, the corrected temperature at each moment in the conductor safety temperature sequence is determined to obtain a fire protection temperature evaluation sequence; Based on the corrected temperature at each moment in the fire temperature assessment sequence, the fire safety determination coefficient is determined to evaluate the building fire safety; The method of determining the false breakthrough coefficient of the conductor temperature and obtaining the false breakthrough temperature sequence includes: The conductor safety temperature sequence is evenly divided into multiple subsequences, which are recorded as breakthrough temperature sequences; Get the range of each breakthrough temperature series respectively to form a temperature range set; Determining a judgment condition gain coefficient according to the difference characteristics between the quartile difference and the range of the temperature range set; Calculate the mean of the temperature extreme difference set, and record it as the first mean; The first mean value is combined with the judgment condition gain coefficient to determine the conductor temperature false breakthrough coefficient; All breakthrough temperature sequences whose range is greater than the false temperature breakthrough judgment coefficient are recorded as false breakthrough temperature sequences; The step of determining the judgment condition gain coefficient comprises: Record the ratio of twice the interquartile difference of the temperature extreme difference set to the extreme difference of the temperature extreme difference set as a first ratio; If the first ratio is greater than or equal to a preset determination threshold, the determination condition gain coefficient is the first ratio; if the first ratio is less than the preset determination threshold or the extreme difference of the temperature extreme difference set is 0, the determination condition gain coefficient is assigned a value of 1; The method of determining the corrected temperature at each moment in the conductor safety temperature sequence to obtain a fire protection temperature assessment sequence includes: Determine the fire protection temperature breakthrough index at each moment in each false breakthrough temperature sequence based on the temperature at each moment in the false breakthrough temperature sequence, the minimum value of the false breakthrough temperature sequence and the false breakthrough coefficient of the conductor temperature; The calculation result of the sigmoid function of the temperature at each moment in each pseudo-breakthrough temperature sequence is recorded as the first function value; Determine the correction factor at each moment in each false breakthrough temperature sequence based on the minimum value of each false breakthrough temperature sequence, the fire protection temperature breakthrough index, and the first function value; If the fire temperature breakthrough index is greater than or equal to 0, the temperature corrected at the corresponding moment is the correction factor; otherwise, the temperature at the corresponding moment remains unchanged; and the corrected temperature at each moment in the conductor safety temperature sequence is obtained; The corrected temperatures at multiple moments are selected from the conductor safety temperature sequence from the back to the front to form a fire protection temperature assessment sequence.
2. The building fire safety assessment method based on big data analysis according to claim 1 is characterized in that: The method for obtaining the wire safety temperature sequence is: The voltage, current and residual current collected in real time at each moment are subjected to a neural network model to obtain the predicted temperature of the electrical circuit at each moment; Arrange the predicted temperatures at all times in chronological order to form a conductor safety temperature sequence.
3. The building fire safety assessment method based on big data analysis according to claim 1 is characterized in that: Determining the fire protection temperature breakthrough index at each moment in each false breakthrough temperature sequence includes: According to the difference between the temperature at each moment in each pseudo-breakthrough temperature sequence and the minimum value of its pseudo-breakthrough temperature sequence, the relative difference degree at each moment is determined; The difference between the relative difference and the conductor temperature false breakthrough coefficient is used as the fire protection temperature breakthrough index at each moment in each false breakthrough temperature sequence.
4. The building fire safety assessment method based on big data analysis according to claim 1, characterized in that: The correction factor at each moment in each false breakthrough temperature sequence is a fusion result of the minimum value of each false breakthrough temperature sequence, the false breakthrough coefficient of the conductor temperature, and the first function value.
5. The building fire safety assessment method based on big data analysis according to claim 1, characterized in that: The determination of the fire safety determination coefficient and the assessment of building fire safety include: Determining a fire weight assessment coefficient at each moment in the fire temperature assessment sequence based on the corrected temperature at each moment in the fire temperature assessment sequence; Based on the fire weight assessment coefficient, determining the adaptive weight at each moment in the fire temperature assessment sequence; Based on the corrected temperature at each moment in the fire temperature assessment sequence and the adaptive weight at the corresponding moment, a weighted average algorithm is used to determine the fire safety determination coefficient; The fire safety determination coefficient is normalized. If the normalized result is greater than a preset fire risk threshold, there is a fire hazard in the building. Otherwise, there is no fire hazard in the building.
6. The building fire safety assessment method based on big data analysis according to claim 5 is characterized in that: The method of determining the fire weight evaluation coefficient at each moment in the fire temperature evaluation sequence includes: Analyze the difference between the corrected value and the mean value at each moment in the fire temperature assessment sequence as the absolute temperature difference at each moment; The fire weight assessment coefficient at each moment is positively correlated with the corrected temperature at the corresponding moment, and negatively correlated with the absolute temperature difference.
7. The building fire safety assessment method based on big data analysis according to claim 5, characterized in that: The step of determining the adaptive weight at each moment in the fire temperature assessment sequence includes: The mean of the fire weight assessment coefficients at all moments in the fire temperature assessment sequence is recorded as the second mean; The ratio of the fire weight evaluation coefficient at each moment in the fire temperature evaluation sequence to the second mean value is used as the adaptive weight at each moment in the fire temperature evaluation sequence.
