Energy-saving building safety intelligent detection system

Abstract

The invention relates to the technical field of building safety detection, and discloses an energy-saving building safety intelligent detection system, which comprises a data acquisition module, a data processing module, a data analysis module, a safety evaluation module and a self-adaptive learning module, according to the invention, various environmental data such as temperature, humidity and the like are comprehensively collected, accurate cleaning is carried out by using a moving average filtering algorithm, and reliable data are provided for subsequent analysis; in the aspect of safety evaluation, a characteristic value is extracted by calculating an environmental data average value and a standard deviation, and a potential safety hazard is quickly and accurately judged by combining a score threshold; an environment threshold value is dynamically adjusted according to historical and real-time data, so that the system adapts to environment changes, and the detection accuracy is improved; the system also fuses multi-dimensional environment data for comprehensive analysis, so that the limitation of single data evaluation is avoided; in addition, the sensitivity and the stability of the sensor are considered when key parameters are calculated, and dynamic adjustment is carried out on the basis, so that the safety of the building environment can be accurately detected under different sensor performances.

Description

Technical Field

[0001] The present invention relates to the technical field of building safety detection, and particularly to an energy-saving building safety intelligent detection system. Background Art

[0002] With the intensification of the global energy crisis and the continuous improvement of people's attention to building safety, energy-saving buildings have become an important development direction in the construction industry. While achieving efficient energy utilization, the safety performance of energy-saving buildings cannot be ignored.

[0003] In the traditional field of building environment monitoring, there are many technical problems to be solved. The traditional safety assessment method lacks dynamic adaptability. The set safety scoring threshold is often fixed and does not take into account the changes in building environment due to factors such as time, season, and usage conditions, making it difficult to accurately reflect the true safety state of the building environment at different times. For example, during high-temperature periods in summer and cold periods in winter, the normal ranges of environmental parameters such as temperature and humidity inside the building are different, but the traditional monitoring system uses a unified threshold for assessment, which is prone to misjudgment.

[0004] In addition, the existing data processing and analysis methods are relatively simple and crude. For the collected data, there is a lack of effective preprocessing means, making it difficult to remove noise and outliers in the data, resulting in a significant reduction in the accuracy of subsequent data analysis. Moreover, during the data analysis process, it is impossible to accurately extract characteristic values that can reflect the safety status of the building environment, and it cannot provide strong support for safety assessment. For example, some monitoring systems only calculate the simple average of the data, ignoring the data fluctuations and unable to detect the safety risks indicated by abnormal fluctuations in environmental parameters in a timely manner.

[0005] In summary, the existing building environment monitoring technologies cannot meet the requirements of energy-saving buildings for comprehensive, real-time, accurate, and adaptive safety intelligent detection. There is an urgent need for a new energy-saving building safety intelligent detection system to solve the above technical problems. Summary of the Invention

[0006] The purpose of the present invention is to provide an energy-saving building safety intelligent detection system to solve the technical problems proposed in the background art.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] An energy-saving building safety intelligent detection system includes:

[0009] A data acquisition module for real-time acquisition of various environmental data in the building environment;

[0010] A data processing module, which is used to preprocess the environmental data collected by sensors. The preprocessing method is to filter and clean the environmental data at each acquisition time node by using a moving average filtering algorithm;

[0011] An analysis module, which is used to extract environmental safety feature values from the preprocessed environmental data. The method is to first calculate the average value of the environmental data, and then calculate the standard deviation of the environmental data combined with its average value to obtain the environmental safety feature values;

[0012] A safety evaluation module, which is used to calculate a safety evaluation score based on the extracted environmental safety feature values, and then judge the safety of the building environment according to the safety evaluation score;

[0013] An adaptive learning module, which is used to automatically learn and adjust the preset environmental threshold according to historical environmental data and real-time environmental data.

[0014] As a further solution of the present invention: The filtering and cleaning method is as follows:

[0015] Set a sliding window, and then obtain all the real-time collected environmental data within the sliding window, and mark it as X0 i，t ;

[0016] Wherein, e is the size of the sliding window, is the downward rounding symbol;

[0017] Then through:

[0018] Calculate the filtered and cleaned environmental data X1 at each acquisition time node i .

[0019] As a further solution of the present invention: Among them:

[0020] When the value of i is 1, then At the same time:

[0021] When the value of i is n, then At the same time:

[0022] As a further solution of the present invention: The method for judging the safety of the building environment is as follows:

[0023] Calculate the safety evaluation score XS in the building environment through XS = XB × β;

[0024] In the formula, β is the preset weight value, and XB is the environmental safety feature value;

[0025] Subsequently, the safety assessment score XS is compared with the preset safety scoring threshold XSY:

[0026] When XS > XSY, it indicates that there are potential safety hazards in the building environment during the current observation period, and an environmental anomaly alarm is issued accordingly;

[0027] When XS ≤ XSY, it indicates that there are no potential safety hazards in the building environment during the current observation period, and no environmental anomaly alarm is issued.

[0028] As a further solution of the present invention: the automatic learning and adjustment method is as follows:

[0029] Extract the average value of all environmental data during the current observation period and label it as XP;

[0030] Subtract each historical environmental data from the average value of all environmental data during the current observation period to obtain the data change amount XC j , where j = 1, 2,... m, and m represents the number of collection time nodes corresponding to the historical environmental data within the historical specified time period;

[0031] Subsequently, calculate the average value of each data change amount and label it as XCP;

[0032] Then, combine each data change amount with its average value to calculate the standard deviation of each data change amount and label it as XCB;

[0033] Subsequently, calculate the adjustment coefficient α through: α = γ × XCB;

[0034] After that, through: XY new = XY old + α × XCP;

[0035] Calculate the new preset environmental data threshold XY new ;

[0036] [[ID=4l]]In the formula, XY old is the original preset environmental data threshold;

[0037] Finally, through: XSY new = XY old × β, calculate the new safety scoring threshold XSY of the building environment new .

[0038] As a further solution of the present invention: among them, the adjustment coefficient α is updated regularly at preset time intervals.

[0039] As a further solution of the present invention: the environmental data includes temperature data inside the building collected by a temperature sensor, humidity data inside the building collected by a humidity sensor, gas concentration data inside the building collected by a gas sensor, and smoke concentration data inside the building collected by a smoke sensor;

[0040] wherein, X i ∈ {T i , S i , Q i , Y i}, T i is the temperature data collected for the i-th time, S i is the humidity data collected for the i-th time, Q i is the gas concentration data collected for the i-th time, Y i is the smoke concentration data collected for the i-th time; XP ∈ {TP, SP, QP, YP}, TP is the average value of the temperature data, SP is the average value of the humidity data, QP is the average value of the gas concentration data, and YP is the average value of the smoke concentration data; XB ∈ {TB, SB, QB, YB}, TB is the temperature safety characteristic value, SB is the humidity safety characteristic value, QB is the gas concentration safety characteristic value, and YB is the smoke concentration safety characteristic value.

[0041] As a further solution of the present invention: wherein, the preset safety score threshold XY is determined by temperature threshold TY, humidity threshold SY, gas concentration threshold QY, and smoke concentration threshold YY preset based on temperature data, humidity data, gas concentration data, and smoke concentration data, and the determination method is as follows:

[0042] By: XSY = TY × β T + SY × β S + QY × β Q + YY × β Y ;

[0043] Calculate the safety score threshold XSY in the building environment.

[0044] As a further solution of the present invention: the method for obtaining the safety assessment score XS in the building environment is as follows:

[0045] XS = TB × β T + SB × β S + QB × β Q + YB × β Y ;

[0046] In the formula, β T , β S , β Q , β Yis the weight value preset based on temperature data, humidity data, gas concentration data, and smoke concentration data.

[0047] As a further solution of the present invention: The historical environmental data refers to the temperature data, humidity data, gas concentration data, and smoke concentration data within a historical specified time period, XL j ∈{TL j , SL j , QL j , YL j};

[0048] Among them, TL j is the temperature data collected for the jth time within the historical specified time period, SL j is the humidity data collected for the jth time within the historical specified time period, QL j is the gas concentration data collected for the jth time within the historical specified time period, YL j is the smoke concentration data collected for the jth time within the historical specified time period, XL j is the substitution vector of various environmental data collected for the jth time within the historical specified time period.

[0049] As a further solution of the present invention: XCP ∈ {TCP, SCP, QCP, YCP}, TCP is the average value of the change in temperature data, SCP is the average value of the change in humidity data, QCP is the average value of the change in gas concentration data, and YCP is the average value of the change in smoke concentration data; XCB ∈ {TCB, SCB, QCB, YCB}, TCB is the standard deviation of the change in temperature data, SCB is the standard deviation of the change in humidity data, QCB is the standard deviation of the change in gas concentration data, and YCB is the standard deviation of the change in smoke concentration data.

[0050] As a further solution of the present invention: The adjustment coefficient α obtained based on XCB includes the adjustment coefficients corresponding to temperature data, humidity data, gas concentration data, and smoke concentration data respectively, and they are respectively marked as α T , α S , α Q , α Y .

[0051] As a further solution of the present invention: Among them, XY old ∈{TY, SY, QY, YY};

[0052] The environmental data threshold XY new includes the new temperature threshold TY new , humidity threshold SY new , gas concentration threshold QY new , smoke concentration threshold YY new ;

[0053] Among them, the new safety score threshold XY in the building environment new is calculated as follows:

[0054] XY new = TY new × β T + SY new × β S + QY new × β Q + YY new × β Y .

[0055] As a further solution of the present invention: Among them, γ is a proportionality coefficient, which is determined by the sensitivity and stability of each sensor in the data acquisition module;

[0056] That is, γ = sensitivity score / stability score;

[0057] When the sensitivity of each sensor in the data acquisition module is higher, the proportionality coefficient γ is larger. When the stability of each sensor in the data acquisition module is higher, the proportionality coefficient γ is smaller.

[0058] Advantages of the present invention:

[0059] In the present invention, the data acquisition module collects various environmental data in the building environment in real time, covering temperature, humidity, gas concentration, smoke concentration, etc., providing a rich and timely data basis for comprehensively understanding the building environment status.

[0060] In the present invention, the data processing module uses a moving average filtering algorithm to filter and clean the collected environmental data. This method can effectively remove noise and outliers in the data. By setting a moving window and calculating the data within the window, the filtered and cleaned environmental data at each acquisition time node is more accurate and reliable, providing high-quality data support for subsequent data analysis and improving the processing accuracy of the entire system for environmental data.

[0061] In the present invention, the data analysis module extracts environmental safety characteristic values by calculating the average value and standard deviation of environmental data. This method can quantitatively reflect the dispersion degree and overall trend of environmental data, accurately depicting the environmental safety status from multiple dimensions.

[0062] In the present invention, the safety assessment module calculates a safety assessment score based on the extracted environmental safety characteristic values and compares it with a pre-set safety score threshold to judge the safety of the building environment. This assessment method has a clear quantitative standard, can quickly and accurately identify whether there are safety hazards in the building environment, provides a strong basis for taking timely countermeasures, and helps to ensure the life and property safety of the people in the building and the normal operation of the building facilities.

[0063] In the present invention, the adaptive learning module automatically learns and adjusts the preset environmental thresholds according to historical environmental data and real-time environmental data. By extracting the average value of environmental data within the current observation period, comparing it with the historical environmental data to calculate the data change amount, its average value, and standard deviation, and then obtaining an adjustment coefficient to update the environmental data threshold and safety score threshold. This adaptive adjustment mechanism enables the system to better adapt to the dynamic changes of the building environment, continuously optimize the evaluation criteria over time, improve the accuracy and reliability of the detection system, and enable it to play a role in ensuring building safety stably in the long term.

[0064] In the present invention, the system separately collects, processes, analyzes, and evaluates different types of environmental data (temperature, humidity, gas concentration, smoke concentration), and at the same time fuses these data to calculate the safety evaluation score and safety score threshold. This way of multi-dimensional data fusion and targeted analysis fully considers the comprehensive impact of different factors on safety in the building environment, avoids the limitations of single-data evaluation, and can evaluate the safety of the building environment more comprehensively and accurately, providing a more perfect solution for building safety protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The present invention will be further described below with reference to the accompanying drawings.

[0066] Figure 1 is a system block diagram of an energy-saving building safety intelligent detection system according to the present invention.

[0067] Figure 2 is a schematic flow chart of a safety evaluation module in an energy-saving building safety intelligent detection system according to the present invention.

[0068] Figure 3 is a schematic flow chart of an adaptive learning module in an energy-saving building safety intelligent detection system according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0069] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0070] Embodiment 1

[0071] Please refer to Figure 1 、 Figure 2 and Figure 3 shown, the present invention is an energy-saving building safety intelligent detection system, including:

[0072] The data acquisition module includes a temperature sensor, a humidity sensor, a gas sensor, and a smoke sensor, which are used to collect various environmental data in the building environment in real time;

[0073] The environmental data includes the temperature data inside the building collected by the temperature sensor, the humidity data inside the building collected by the humidity sensor, the gas concentration data inside the building collected by the gas sensor, and the smoke concentration data inside the building collected by the smoke sensor;

[0074] The data analysis module is used to extract environmental safety characteristic values from the collected environmental data;

[0075] The extraction method is as follows:

[0076] Divide the specified observation period into n acquisition time nodes, and then mark the temperature data, humidity data, gas concentration data, and smoke concentration data collected at the n acquisition time nodes as X i ∈{T i ,S i ,Q i ,Y i}, i = 1, 2,..., n;

[0077] Among them, T i is the temperature data collected at the i-th acquisition, S i is the humidity data collected at the i-th acquisition, Q i is the gas concentration data collected at the i-th acquisition, Y i is the smoke concentration data collected at the i-th acquisition, and X i is the substitution vector of various environmental data collected at the i-th acquisition;

[0078] Through: Calculate the average value XP of the environmental data;

[0079] Among them, XP∈{TP, SP, QP, YP}, TP is the average value of the temperature data, SP is the average value of the humidity data, QP is the average value of the gas concentration data, and YP is the average value of the smoke concentration data;

[0080] At the same time, through: Calculate the standard deviation XB of the environmental data, that is, the environmental safety characteristic value;

[0081] Among them, XB∈{TB, SB, QB, YB}, TB is the standard deviation of the temperature data, which is also recorded as the temperature safety characteristic value, SB is the standard deviation of the humidity data, which is also recorded as the humidity safety characteristic value, QB is the standard deviation of the gas concentration data, which is also recorded as the gas concentration safety characteristic value, and YB is the standard deviation of the smoke concentration data, which is also recorded as the smoke concentration safety characteristic value;

[0082] A safety assessment module, which is used to calculate a safety assessment score based on the extracted environmental safety characteristic values, and then judge the safety of the building environment according to the safety assessment score;

[0083] The method is as follows:

[0084] XS = XB × β; Calculate the safety assessment score XS in the building environment;

[0085] In the formula, β is a preset weight value;

[0086] Specifically:

[0087] By: XS = TB × β T + SB × β S + QB × β Q + YB × β Y ;

[0088] Calculate the safety assessment score XS in the building environment;

[0089] In the formula, β T 、β S 、β Q 、β Y Are preset weight values based on temperature data, humidity data, gas concentration data, and smoke concentration data;

[0090] Then compare the safety assessment score XS with the preset safety score threshold XSY:

[0091] When XS > XSY, it means that there are safety hazards in the building environment during the current observation period, and then an environmental anomaly alarm is issued;

[0092] When XS ≤ XSY, it means that there are no safety hazards in the building environment during the current observation period, and no environmental anomaly alarm is issued;

[0093] In this embodiment, a variety of environmental data in the building environment are collected in real time through temperature sensors, humidity sensors, gas sensors, and smoke sensors, which can comprehensively reflect the environmental conditions inside the building and provide a rich and accurate data basis for subsequent analysis and evaluation; The environmental safety characteristic values are extracted by calculating the average value and standard deviation, and the environmental data are quantitatively analyzed from multiple dimensions to make the description of the environmental safety characteristics more accurate and scientific; The safety assessment score is calculated according to the extracted environmental safety characteristic values and compared with the preset safety score threshold, which can quickly and accurately judge the safety of the building environment, timely discover potential safety hazards and issue alarms, and ensure the safety of personnel and property in the building.

[0094] Embodiment 2

[0095] Please refer toFigure 1 , Figure 2 and Figure 3 As shown in Figure 1 , Figure 2 , and Figure 3 , as the second embodiment of the present invention, in the specific implementation of this application, compared with the first embodiment, the difference between the technical solution of this embodiment and that of the first embodiment is only that in this embodiment, the preset safety score threshold XY is determined by the temperature threshold TY, humidity threshold SY, gas concentration threshold QY, and smoke concentration threshold YY preset based on temperature data, humidity data, gas concentration data, and smoke concentration data, and its determination method is as follows:

[0096] By: XSY = TY × β T + SY × β S + QY × β Q + YY × β Y ;

[0097] Calculate the safety score threshold XSY in the building environment;

[0098] In this embodiment, the preset safety score threshold is determined by the temperature threshold, humidity threshold, gas concentration threshold, and smoke concentration threshold preset based on temperature data, humidity data, gas concentration data, and smoke concentration data, making the setting of the safety score threshold more in line with the actual situation of different environmental factors in the building environment, and improving the accuracy and pertinence of safety assessment.

[0099] Embodiment Three

[0100] Please refer to Figure 1 , Figure 2 and Figure 3 As shown, as the third embodiment of the present invention, in the specific implementation of this application, compared with the first and second embodiments, the technical solution of this embodiment is to combine and implement the solutions of the above first and second embodiments. The difference between the technical solution of this embodiment and those of the first and second embodiments is only that in this embodiment, it further includes:

[0101] An adaptive learning module for automatically learning and adjusting the temperature threshold, humidity threshold, gas concentration threshold, and smoke concentration threshold according to historical environmental data and real-time environmental data;

[0102] The method is as follows:

[0103] Collect various historical environmental data in the building environment; historical environmental data refers to temperature data, humidity data, gas concentration data, and smoke concentration data within a historical specified time period;

[0104] Divide the historical specified time period into m acquisition time nodes, and then mark the temperature data, humidity data, gas concentration data, and smoke concentration data collected at the m acquisition time nodes as XL j ∈ {TLj , SL j , QL j , YL j}, j = 1, 2,..., m;

[0105] Among them, TL j is the temperature data collected for the jth time within the historical specified time period, SL j is the humidity data collected for the jth time within the historical specified time period, QL j is the gas concentration data collected for the jth time within the historical specified time period, YL j is the smoke concentration data collected for the jth time within the historical specified time period, XL j is the substitution vector of various environmental data collected for the jth time within the historical specified time period;

[0106] Extract the average value XP of all environmental data within the current observation period;

[0107] Then through: XC j = XL j - XP;

[0108] Calculate the data change amount XC between the corresponding environmental data within the current observation period and each historical environmental data j ;

[0109] Then through: Calculate the average value XCP of each data change amount;

[0110] Among them, XCP ∈ {TCP, SCP, QCP, YCP}, TCP is the average value of the temperature data change amount, SCP is the average value of the humidity data change amount, QCP is the average value of the gas concentration data change amount, and YCP is the average value of the smoke concentration data change amount;

[0111] At the same time through: Calculate the standard deviation XCB of each data change amount;

[0112] Among them, XCB ∈ {TCB, SCB, QCB, YCB}, TCB is the standard deviation of the temperature data change amount, SCB is the standard deviation of the humidity data change amount, QCB is the standard deviation of the gas concentration data change amount, and YCB is the standard deviation of the smoke concentration data change amount;

[0113] Then through: α = γ × XCB, calculate the adjustment coefficient α;

[0114] In the formula, γ is a proportionality coefficient, which is determined by the sensitivity and stability of each sensor in the data acquisition module;

[0115] That is, γ = sensitivity score / stability score;

[0116] The higher the sensitivity of each sensor in the data acquisition module, the larger the proportionality coefficient γ. The higher the stability of each sensor in the data acquisition module, the smaller the proportionality coefficient γ.

[0117] Among them, the adjustment coefficient α obtained based on XCB includes the adjustment coefficients corresponding to temperature data, humidity data, gas concentration data, and smoke concentration data, and they are respectively marked as α T 、α S 、α Q 、α Y ;

[0118] After that, through: XY new =XY old +α×XCP;

[0119] Calculate the new preset environmental data threshold XY new ;

[0120] In the formula, XY old ∈{TY, SY, QY, YY};

[0121] The environmental data threshold XY new Includes the new temperature threshold TY new 、humidity threshold SY new 、gas concentration threshold QY new 、smoke concentration threshold YY new ;

[0122] Then through: XY new =TY new ×β T +SY new ×β S +QY new ×β Q +YY new ×β Y ;

[0123] Calculate the new safety score threshold XY new ;

[0124] In this embodiment, the adjustment coefficient α is periodically updated at a preset time interval;

[0125] In this embodiment, the adaptive learning module automatically learns and adjusts the temperature threshold, humidity threshold, gas concentration threshold, and smoke concentration threshold based on historical environmental data and real-time environmental data, enabling the system to adapt to changes in the building environment, continuously optimize the safety assessment criteria, and improve the intelligence level of the system and its adaptability to environmental changes. During the process of adjusting the threshold, various factors such as historical data, real-time data, data change amount, and the sensitivity and stability of sensors are comprehensively considered, making the adjusted threshold more reasonable and accurate, and further improving the reliability of safety assessment.

[0126] Embodiment Four

[0127] Please refer to Figure 1 、 Figure 2 and Figure 3 As shown in, as Embodiment Four of the present invention, when this application is specifically implemented, compared with Embodiment One, Embodiment Two, and Embodiment Three, the difference between this embodiment and Embodiment One, Embodiment Two, and Embodiment Three is only that in this embodiment, it further includes:

[0128] A data processing module for preprocessing the data collected by the sensors, and the preprocessing method is as follows:

[0129] For the environmental data X at each acquisition time node i , a moving average filtering algorithm is used for filtering and cleaning, specifically:

[0130] Set a moving window, and then obtain all the real-time collected environmental data within this moving window and mark it as X0 i，t ;

[0131] Among them, e is the size of the moving window, is the downward rounding symbol;

[0132] Then through:

[0133] Calculate the filtered and cleaned environmental data X1 at each acquisition time node i ;

[0134] Where:

[0135] When the value of i is 1, then At the same time:

[0136] When the value of i is n, then At the same time:

[0137] Based on this embodiment, the data analysis module extracts environmental safety feature values from the preprocessed environmental data;

[0138] In this embodiment, the data processing module preprocesses the data collected by the sensor. By using the moving average filtering algorithm to filter and clean the data, it can effectively remove the noise and interference in the data, improve the quality and accuracy of the data, and provide more reliable data support for subsequent data analysis and feature extraction.

[0139] Embodiment Five

[0140] Please refer to Figure 1 、 Figure 2 and Figure 3 As shown in [relevant figures], as Embodiment Five of the present invention, in the specific implementation of this application, compared with Embodiment One, Embodiment Two, Embodiment Three, and Embodiment Four, the technical solution of this embodiment lies in combining the solutions of the above-mentioned Embodiment One, Embodiment Two, Embodiment Three, and Embodiment Four for implementation.

[0141] This embodiment combines the solutions of Embodiment One, Two, Three, and Four for implementation, integrating the advantages of each embodiment, achieving comprehensive data collection, scientific data analysis, targeted threshold setting, adaptive learning adjustment, and optimized data preprocessing, making the energy-saving building safety intelligent detection system more perfect and efficient, and being able to more accurately and timely detect potential safety hazards in the building environment, providing all-round guarantee for the safe operation of the building.

[0142] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by software simulation of a large amount of collected data to get a formula closest to the real situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0143] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claimed rights.

Claims

1. An energy-saving building safety intelligent detection system, characterized in that Including: A data acquisition module, which is used to collect various environmental data in the building environment in real time; A data processing module, which is used to preprocess the environmental data collected by sensors. The preprocessing method is to filter and clean the environmental data at each acquisition time node by using a moving average filtering algorithm; A data analysis module, which is used to extract environmental safety characteristic values from the preprocessed environmental data. The method is to first calculate the average value of the environmental data, and then calculate the standard deviation of the environmental data combined with its average value to obtain the environmental safety characteristic value; A safety assessment module, which is used to calculate a safety assessment score according to the extracted environmental safety characteristic values, and then judge the safety of the building environment based on the safety assessment score; An adaptive learning module, which is used to automatically learn and adjust the preset environmental threshold according to historical environmental data and real-time environmental data.

2. The energy-saving building safety intelligent detection system according to claim 1, wherein, The method for judging the safety of the building environment is as follows: Calculate the safety assessment score XS in the building environment through XS = XB × β; In the formula, β is the preset weight value, and XB is the environmental safety characteristic value; Then compare the safety assessment score XS with the preset safety score threshold XSY: When XS > XSY, it means that there are potential safety hazards in the building environment during the current observation period, and an environmental anomaly alarm is issued accordingly; When XS ≤ XSY, it means that there are no potential safety hazards in the building environment during the current observation period, and no environmental anomaly alarm is issued.

3. An energy-saving building safety intelligent detection system according to claim 1, characterized in that, The automatic learning and adjustment method is as follows: Extract the average value of all environmental data in the current observation period and mark it as XP; Subtract each historical environmental data from the average value of all environmental data in the current observation period, and obtain the data change amount XC j , where j = 1, 2,..., m, and m refers to the number of acquisition time nodes corresponding to the historical environmental data in the historical specified time period; Then obtain the average value of each data change amount and mark it as XCP; Then combine each data change amount with its average value, calculate the standard deviation of each data change amount, and mark it as XCB; Then calculate the adjustment coefficient α through: α = γ × XCB; After passing through: XY new = XY old + α × XCP; Calculate the new preset environmental data threshold XY new ; where XY old is the original pre-set environmental data threshold value; Finally, through: XSY new = XY old ×β, calculate the new safety score threshold XSY in the built environment new .

4. An energy-saving building safety intelligent detection system according to claim 2, characterized in that, Among them, γ is a proportionality coefficient, which is determined by the sensitivity and stability of each sensor in the data acquisition module.

5. An energy-saving building safety intelligent detection system according to claim 3, characterized in that, Among them, The adjustment coefficient α is updated regularly at a preset time interval.

6. The energy-saving building safety intelligent detection system according to claim 1, characterized in that, The filtering and cleaning method is as follows: Set a sliding window, and then obtain all the real-time collected environmental data within the sliding window and mark it as X0 i，t ; Among them, e is the size of the sliding window, is the floor function symbol; Followed by: Calculate the environmentally friendly data X1 after filtering and cleaning at each acquisition time node i .

7. An energy-saving building safety intelligent detection system according to claim 6, characterized in that, Among them: When the value of i is 1, then Meanwhile: When the value of i is n, then Meanwhile:

8. An energy-saving building safety intelligent detection system according to claim 1, characterized in that, The environmental data includes temperature data collected inside the building using a temperature sensor, humidity data collected inside the building using a humidity sensor, gas concentration data collected inside the building using a gas sensor, and smoke concentration data collected inside the building using a smoke sensor.

9. An energy-saving building safety intelligent detection system according to claim 8, characterized in that, Among them, The preset safety score threshold XY is determined by the preset temperature threshold TY, humidity threshold SY, gas concentration threshold QY, and smoke concentration threshold YY based on temperature data, humidity data, gas concentration data, and smoke concentration data. The determination method is as follows: Via: XSY = TY × β T + SY × β S + QY × β Q + YY × β Y ; Calculate the safety score threshold XSY in the building environment.

Images