A method and system for intelligent monitoring of spatial microenvironment

Abstract

The present invention discloses a method and system for intelligent monitoring of a small space environment, which relates to the field of intelligent monitoring technology. The method and system include a multi-source acquisition module, a multi-source fusion module, a status detection module, an intelligent control module, an automatic calibration module, and an early warning module. The multi-source acquisition module acquires status information of a distribution cabinet and environmental parameter information in the small space environment. By monitoring the status information of the distribution cabinet and the environmental parameter information, errors, missing values, and abnormal values ​​in the multi-source data are removed, and the average value is used as the final environmental parameter information to realize multi-source fusion of the monitoring information, dynamically allocate environmental parameter weights based on the power factor, calculate the environmental parameter impact value, and intelligently link the monitoring of the environmental parameter impact results and the quality detection results. Based on the abnormal situation, graded early warning is given, the environmental parameter settings are automatically adjusted, the abnormal sensor offset error is eliminated, and the stability and accuracy of long-term monitoring of the small environment of the distribution cabinet are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology, and in particular to a method and system for intelligent monitoring of a spatial microenvironment. Background Art

[0002] As society becomes increasingly information-based, the stability and safety of distribution cabinets, a crucial component of power systems, are becoming increasingly crucial. The microenvironment within distribution cabinets, where parameters such as temperature, humidity, current, and voltage interact with each other, makes it difficult to fully assess risks through single monitoring. This has a direct impact on the normal operation of distribution cabinets and power load balancing.

[0003] Traditional monitoring methods often rely on manual inspections, which are not only inefficient but also suffer from data fragmentation and isolation. Each parameter is collected independently, lacking the ability to fuse and analyze multi-source data. In addition, there is a lack of self-calibration mechanism for sensor drift, and long-term monitoring stability is insufficient, which seriously affects the monitoring accuracy and stability of spatial microenvironment intelligent monitoring methods and systems. Summary of the Invention

[0004] In response to the above situation, the present invention monitors the status information and environmental parameter information of the distribution cabinet, integrates the monitoring information from multiple sources, intelligently monitors the environmental parameter impact results and status detection results, and automatically adjusts the environmental parameter settings based on graded warnings of abnormal situations to eliminate abnormal sensor offset errors.

[0005] The technical solution is a method for intelligently monitoring a small spatial environment. The specific steps are as follows: S1: align heterogeneous information streams, synchronize temperature, humidity, ozone concentration, and particulate matter concentration sampling points based on the working hours of the distribution cabinet, and collect distribution cabinet status information and environmental parameter information in the small spatial environment. The distribution cabinet status information includes three-phase voltage U and power factor W, and the environmental parameter information includes temperature A, humidity B, ozone concentration C, and particulate matter concentration D.

[0006] S2, extract the corresponding temperature threshold A1, humidity threshold B1, ozone concentration threshold C1, and particulate matter concentration threshold D1, and calculate the temperature quantization value A2, A2 = |A1-A| ÷ A1, the humidity quantization value B2, B2 = |B1-B| ÷ B1, the ozone concentration quantization value C2, C2 = |C1-C| ÷ C1, and the particulate matter concentration quantization value D2, D2 = |D1-D| ÷ D1;

[0007] Dynamically assign environmental parameter weights based on the power factor. A power factor W greater than 0.95 is considered high, a power factor greater than or equal to 0.9 and less than or equal to 0.95 is considered normal, and a power factor less than 0.9 is considered low. Calculate the environmental parameter impact value M, which is: M = A2 × temperature weight + B2 × humidity weight + C2 × ozone concentration weight + D2 × particulate matter concentration weight.

[0008] S3, based on the power factor W, extracts the corresponding environmental parameter impact threshold M1 from the database, determines the environmental parameter impact result, calculates the environmental parameter impact quantization value M2, and then calculates the state detection value Q, Q = M2 × 0.6 + N × 0.4 + |U1 - U| ÷ U1, where N is 0.6 when the power factor is high, 0 when it is normal, and 0.5 when the power factor is low. U1 is the threshold corresponding to the three-phase voltage U;

[0009] S4, extracting the corresponding state detection threshold Q1 from the database based on the power factor. If Q is less than Q1, it indicates that the current state detection is normal. Conversely, if Q is greater than or equal to Q1, it indicates that the current state detection is abnormal;

[0010] The environmental parameter impact results and status detection results are intelligently linked and monitored, and graded warnings are issued based on abnormal situations to automatically adjust the environmental parameter settings.

[0011] Furthermore, in step S4, the environmental parameter impact result and the status detection result are intelligently linked and monitored. If the current status detection is normal and the environmental parameter impact is normal, it is recorded as a good state, and the current monitoring frequency and environmental parameter settings are maintained;

[0012] When the current state detection is normal and the environmental parameter impact is abnormal, a first-level alarm signal is issued, and the environmental parameter weight and / or environmental parameter impact threshold M1 are automatically adjusted;

[0013] When the current status detection is abnormal and the environmental parameters affect the normal state, a secondary alarm signal is issued to check the hardware failure of the power distribution cabinet. After eliminating the hardware failure factor, the monitoring frequency is increased;

[0014] When the current status detection is abnormal and the environmental parameters have abnormal effects, a three-level warning signal is issued to check the abnormal sensors of the temperature, humidity, ozone concentration, and particulate matter concentration sampling points, start the self-calibration instruction, eliminate the offset error of the abnormal sensor, and record the number of abnormal sensor offsets. When the offset condition occurs more than three times in a row, replace the abnormal sensor.

[0015] Furthermore, in step S1, the temperature, humidity, ozone concentration, and particulate matter concentration parameter information after the synchronous sampling point are first cleaned to remove errors, missing values, and outliers in the data, and then the average values ​​of the multi-source temperature, humidity, ozone concentration, and particulate matter concentration after data cleaning are calculated in turn, and recorded as temperature A, humidity B, ozone concentration C, and particulate matter concentration D, respectively. Temperature A, humidity B, ozone concentration C, and particulate matter concentration D are regarded as environmental parameter information collected in the spatial microenvironment.

[0016] Furthermore, in step S2, environmental parameter weights are dynamically allocated based on the power factor. The power factor is divided into: when the power factor W is greater than 0.95, it is considered to be in a high state; when W is greater than or equal to 0.9 and less than or equal to 0.95, it is considered to be in a normal state; when W is less than 0.9, it is considered to be in a low state. When the power factor is in a high state, the temperature weight is 0.4, the humidity weight is 0.2, the ozone concentration weight is 0.3, and the particulate matter concentration weight is 0.1; the logarithmic temperature weight is 0.30, the humidity weight is 0.35, the light weight is 0.20, and the oxygen concentration weight is 0.15; in a normal state, the temperature weight is 0.3, the humidity weight is 0.3, the light weight is 0.2, and the oxygen concentration weight is 0.2; when in a low state, the temperature weight is 0.2, the humidity weight is 0.4, the light weight is 0.1, and the oxygen concentration weight is 0.3.

[0017] Furthermore, in step S3, the corresponding environmental parameter impact threshold M1 in the database is extracted according to the power factor W. If M is greater than M1, it indicates that the current environmental parameter impact is abnormal. Otherwise, it indicates that the current environmental parameter impact is normal.

[0018] Calculate the quantitative value M2 of the environmental parameter impact, M2 = (M-M1) ÷ M1. When the current environmental parameter impact is normal, M2 is 0.

[0019] Furthermore, in step S2, the temperature threshold A1, the humidity threshold B1, the light threshold C1, and the oxygen concentration threshold D1 are range values. The temperature threshold A1 is A11 to A12. If A is less than or equal to A11, A2 = |A11-A|÷A11. If A is greater than or equal to A12, A2 = |A12-A|÷A12. When A is greater than A11 and less than A12, A2 is 0.

[0020] Humidity threshold B1 is between B11 and B12. If B is less than or equal to B11, B2 = |B11-B|÷B11. If B is greater than or equal to B12, B2 = |B12-B|÷B12. If B is greater than B11 but less than B12, B2 is 0.

[0021] The ozone concentration threshold C1 is between C11 and C12. If C is less than or equal to C11, C2 = |C11-C|÷C11. If C is greater than or equal to C12, C2 = |C12-C|÷C12. If C is greater than C11 but less than C12, C2 is 0.

[0022] The particle concentration threshold D1 is D11 to D12, D is less than or equal to D11, D2 = |D11-D| ÷ D11, D is greater than or equal to D12, D2 = |D12-D| ÷ D12, and when D is greater than D11 and less than D12, D2 is 0. Furthermore, the system is applied to a method for intelligent monitoring of a small space environment as described in any one of claims 1 to 7, comprising a multi-source acquisition module, a multi-source fusion module, a status detection module, an intelligent control module, an automatic calibration module, and an early warning module, wherein the multi-source acquisition module collects status information and environmental parameter information of a power distribution cabinet in a small space environment;

[0023] The multi-source fusion module calculates the temperature quantization value A2, the humidity quantization value B2, the ozone concentration quantization value C2, the particulate matter concentration quantization value D2, dynamically allocates environmental parameter weights based on the power factor, calculates the environmental parameter impact value M, and calculates the environmental parameter impact quantization value M2;

[0024] The state detection module calculates the state detection value Q and extracts the corresponding state detection threshold Q1 from the database according to the power factor. If Q is less than Q1, it indicates that the current state detection is normal. Otherwise, if Q is greater than or equal to Q1, it indicates that the current state detection is abnormal.

[0025] The intelligent control module intelligently monitors the environmental parameter impact results and the status detection results, and drives the early warning module to issue graded early warnings based on abnormal situations, while controlling the automatic calibration module to automatically adjust the environmental parameter settings.

[0026] Due to the adoption of the above technical solution, the present invention has the following advantages compared with the prior art: 1. By monitoring the status information and environmental parameter information of the distribution cabinet, errors, missing values ​​and abnormal values ​​in multi-source data are removed, and the average value is used as the final environmental parameter information to realize multi-source fusion of monitoring information, dynamically allocate environmental parameter weights based on power factor, calculate environmental parameter impact values, and intelligently link monitoring of environmental parameter impact results and quality detection results, and automatically adjust environmental parameter settings based on graded warnings of abnormal situations, eliminate abnormal sensor offset errors, and improve the stability and accuracy of long-term monitoring of the distribution cabinet microenvironment. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a flow chart of a method and system for intelligently monitoring a small spatial environment according to the present invention. DETAILED DESCRIPTION

[0028] The above and other technical contents, features and effects of the present invention are described below with reference to the attached Figure 1 The detailed description of the embodiments will clearly show that the structural contents mentioned in the following embodiments are all based on the accompanying drawings.

[0029] On the basis of existing technologies, in order to solve the problems of data fragmentation and isolation, the monitoring information is integrated from multiple sources. At the same time, the environmental parameter impact results and status detection results are intelligently linked for monitoring. According to the abnormal situation, graded warnings are given, and the environmental parameter settings are automatically adjusted to eliminate the abnormal sensor offset error. Specifically, S1 aligns heterogeneous information streams, takes the working time of the distribution cabinet as the benchmark, synchronizes the temperature, humidity, ozone concentration, and particulate matter concentration sampling points, and collects the distribution cabinet status information and environmental parameter information in the small space environment. The distribution cabinet status information includes three-phase voltage U and power factor W, and the environmental parameter information includes temperature A, humidity B, ozone concentration C, and particulate matter concentration D parameters;

[0030] S2, extract the corresponding temperature threshold A1, humidity threshold B1, ozone concentration threshold C1, and particulate matter concentration threshold D1, and calculate the temperature quantization value A2, A2 = |A1-A| ÷ A1, the humidity quantization value B2, B2 = |B1-B| ÷ B1, the ozone concentration quantization value C2, C2 = |C1-C| ÷ C1, and the particulate matter concentration quantization value D2, D2 = |D1-D| ÷ D1;

[0031] Dynamically assign environmental parameter weights based on the power factor. A power factor W greater than 0.95 is considered high, a power factor greater than or equal to 0.9 and less than or equal to 0.95 is considered normal, and a power factor less than 0.9 is considered low. Calculate the environmental parameter impact value M, which is: M = A2 × temperature weight + B2 × humidity weight + C2 × ozone concentration weight + D2 × particulate matter concentration weight.

[0032] S3, based on the power factor W, extracts the corresponding environmental parameter impact threshold M1 from the database, determines the environmental parameter impact result, calculates the environmental parameter impact quantization value M2, and then calculates the state detection value Q, Q = M2 × 0.6 + N × 0.4 + |U1 - U| ÷ U1, where N is 0.6 when the power factor is high, 0 when it is normal, and 0.5 when the power factor is low. U1 is the threshold corresponding to the three-phase voltage U;

[0033] S4, extracting the corresponding state detection threshold Q1 from the database based on the power factor. If Q is less than Q1, it indicates that the current state detection is normal. Conversely, if Q is greater than or equal to Q1, it indicates that the current state detection is abnormal;

[0034] The environmental parameter impact results and status detection results are intelligently linked and monitored, and graded warnings are issued based on abnormal situations to automatically adjust the environmental parameter settings.

[0035] Furthermore, in step S4, the environmental parameter impact result and the status detection result are intelligently linked and monitored. If the current status detection is normal and the environmental parameter impact is normal, it is recorded as a good state, and the current monitoring frequency and environmental parameter settings are maintained;

[0036] When the current state detection is normal and the environmental parameter impact is abnormal, a first-level alarm signal is issued, and the environmental parameter weight and / or environmental parameter impact threshold M1 are automatically adjusted;

[0037] When the current status detection is abnormal and the environmental parameters affect the normal state, a secondary alarm signal is issued to check the hardware failure of the power distribution cabinet. After eliminating the hardware failure factor, the monitoring frequency is increased;

[0038] When the current status detection is abnormal and the environmental parameters have abnormal effects, a three-level warning signal is issued to check the abnormal sensors of the temperature, humidity, ozone concentration, and particulate matter concentration sampling points, start the self-calibration instruction, eliminate the offset error of the abnormal sensor, and record the number of abnormal sensor offsets. When the offset condition occurs more than three times in a row, replace the abnormal sensor.

[0039] Furthermore, in step S1, the temperature, humidity, ozone concentration, and particulate matter concentration parameter information after the synchronous sampling point are first cleaned to remove errors, missing values, and outliers in the data, and then the average values ​​of the multi-source temperature, humidity, ozone concentration, and particulate matter concentration after data cleaning are calculated in turn, and recorded as temperature A, humidity B, ozone concentration C, and particulate matter concentration D, respectively. Temperature A, humidity B, ozone concentration C, and particulate matter concentration D are regarded as environmental parameter information collected in the spatial microenvironment.

[0040] Furthermore, in step S2, environmental parameter weights are dynamically allocated based on the power factor. The power factor is divided into: when the power factor W is greater than 0.95, it is considered to be in a high state; when W is greater than or equal to 0.9 and less than or equal to 0.95, it is considered to be in a normal state; when W is less than 0.9, it is considered to be in a low state. When the power factor is in a high state, the temperature weight is 0.4, the humidity weight is 0.2, the ozone concentration weight is 0.3, and the particulate matter concentration weight is 0.1; the logarithmic temperature weight is 0.30, the humidity weight is 0.35, the light weight is 0.20, and the oxygen concentration weight is 0.15; in a normal state, the temperature weight is 0.3, the humidity weight is 0.3, the light weight is 0.2, and the oxygen concentration weight is 0.2; when in a low state, the temperature weight is 0.2, the humidity weight is 0.4, the light weight is 0.1, and the oxygen concentration weight is 0.3.

[0041] Furthermore, in step S3, the corresponding environmental parameter impact threshold M1 in the database is extracted according to the power factor W. If M is greater than M1, it indicates that the current environmental parameter impact is abnormal. Otherwise, it indicates that the current environmental parameter impact is normal.

[0042] Calculate the quantitative value M2 of the environmental parameter impact, M2 = (M-M1) ÷ M1. When the current environmental parameter impact is normal, M2 is 0.

[0043] Furthermore, in step S2, the temperature threshold A1, the humidity threshold B1, the light threshold C1, and the oxygen concentration threshold D1 are range values. The temperature threshold A1 is A11 to A12. If A is less than or equal to A11, A2 = |A11-A|÷A11. If A is greater than or equal to A12, A2 = |A12-A|÷A12. When A is greater than A11 and less than A12, A2 is 0.

[0044] Humidity threshold B1 is between B11 and B12. If B is less than or equal to B11, B2 = |B11-B|÷B11. If B is greater than or equal to B12, B2 = |B12-B|÷B12. If B is greater than B11 but less than B12, B2 is 0.

[0045] The ozone concentration threshold C1 is between C11 and C12. If C is less than or equal to C11, C2 = |C11-C|÷C11. If C is greater than or equal to C12, C2 = |C12-C|÷C12. If C is greater than C11 but less than C12, C2 is 0.

[0046] The particle concentration threshold D1 is D11 to D12, D is less than or equal to D11, D2 = |D11-D| ÷ D11, D is greater than or equal to D12, D2 = |D12-D| ÷ D12, and when D is greater than D11 and less than D12, D2 is 0. Furthermore, the system is applied to a method for intelligent monitoring of a small space environment as described in any one of claims 1 to 7, comprising a multi-source acquisition module, a multi-source fusion module, a status detection module, an intelligent control module, an automatic calibration module, and an early warning module, wherein the multi-source acquisition module collects status information and environmental parameter information of a power distribution cabinet in a small space environment;

[0047] The multi-source fusion module calculates the temperature quantization value A2, the humidity quantization value B2, the ozone concentration quantization value C2, the particulate matter concentration quantization value D2, dynamically allocates environmental parameter weights based on the power factor, calculates the environmental parameter impact value M, and calculates the environmental parameter impact quantization value M2;

[0048] The state detection module calculates the state detection value Q and extracts the corresponding state detection threshold Q1 from the database according to the power factor. If Q is less than Q1, it indicates that the current state detection is normal. Otherwise, if Q is greater than or equal to Q1, it indicates that the current state detection is abnormal.

[0049] The intelligent control module intelligently monitors the environmental parameter impact results and the status detection results, and drives the early warning module to issue graded early warnings based on abnormal situations, while controlling the automatic calibration module to automatically adjust the environmental parameter settings.

[0050] When the present invention is used specifically, based on the existing technology, it includes a multi-source acquisition module, a multi-source fusion module, a status detection module and an intelligent control module, an automatic calibration module, and an early warning module. The multi-source acquisition module collects the status information and environmental parameter information of the power distribution cabinet in the small space environment;

[0051] The multi-source fusion module calculates the temperature quantization value A2, the humidity quantization value B2, the ozone concentration quantization value C2, the particulate matter concentration quantization value D2, dynamically allocates environmental parameter weights based on the power factor, calculates the environmental parameter impact value M, and calculates the environmental parameter impact quantization value M2;

[0052] The state detection module calculates the state detection value Q and extracts the corresponding state detection threshold Q1 from the database according to the power factor. If Q is less than Q1, it indicates that the current state detection is normal. Otherwise, if Q is greater than or equal to Q1, it indicates that the current state detection is abnormal.

[0053] The intelligent control module intelligently links and monitors environmental parameter impacts and status detection results, and drives the early warning module to issue graded warnings based on abnormalities. It also controls the automatic calibration module to automatically adjust environmental parameter settings. By integrating multi-source monitoring information, the intelligent linking of environmental parameter impacts and status detection results allows for graded warnings based on abnormalities, automatically adjusting environmental parameter settings and eliminating abnormal sensor offset errors.

[0054] The above is a further detailed description of the present invention in combination with specific implementation methods, and it cannot be determined that the specific implementation of the present invention is limited to this; for technical personnel in the technical fields to which the present invention belongs and related technical fields, based on the technical solution ideas of the present invention, the expansion and replacement of operating methods and data should all fall within the scope of protection of the present invention.

Claims

1. A method for intelligent monitoring of a small space environment, characterized in that: The specific steps are as follows: S1: Align heterogeneous information flows, synchronize temperature, humidity, ozone concentration, and particulate matter concentration sampling points based on the working hours of the distribution cabinet, and collect distribution cabinet status information and environmental parameter information in the small space environment. The distribution cabinet status information includes three-phase voltage U and power factor W, and the environmental parameter information includes temperature A, humidity B, ozone concentration C, and particulate matter concentration D parameters; S2, extract the corresponding temperature threshold A1, humidity threshold B1, ozone concentration threshold C1, and particulate matter concentration threshold D1, and calculate the temperature quantization value A2, A2 = |A1-A| ÷ A1, the humidity quantization value B2, B2 = |B1-B| ÷ B1, the ozone concentration quantization value C2, C2 = |C1-C| ÷ C1, and the particulate matter concentration quantization value D2, D2 = |D1-D| ÷ D1; Dynamically assign environmental parameter weights based on the power factor. A power factor W greater than 0.95 is considered high, a power factor greater than or equal to 0.9 and less than or equal to 0.95 is considered normal, and a power factor less than 0.9 is considered low. Calculate the environmental parameter impact value M, which is: A²×temperature weight value + B²×humidity weight value + C²×ozone concentration weight value + D²×particulate matter concentration weight value. S3, based on the power factor W, extracts the corresponding environmental parameter impact threshold M1 from the database, determines the environmental parameter impact result, calculates the environmental parameter impact quantization value M2, and then calculates the state detection value Q, Q = M2 × 0.6 + N × 0.4 + |U1 - U| ÷ U1, where N is 0.6 when the power factor is high, 0 when it is normal, and 0.5 when the power factor is low. U1 is the threshold corresponding to the three-phase voltage U; S4, extracting the corresponding state detection threshold Q1 from the database based on the power factor. If Q is less than Q1, it indicates that the current state detection is normal. Conversely, if Q is greater than or equal to Q1, it indicates that the current state detection is abnormal; The environmental parameter impact results and status detection results are intelligently linked and monitored, and graded warnings are issued based on abnormal situations to automatically adjust the environmental parameter settings.

2. The method for intelligently monitoring a small space environment according to claim 1, characterized in that: In step S4, the environmental parameter impact result and the status detection result are intelligently linked and monitored. If the current status detection is normal and the environmental parameter impact is normal, it is recorded as a good state and the current monitoring frequency and environmental parameter settings are maintained; When the current state detection is normal and the environmental parameter impact is abnormal, a first-level alarm signal is issued, and the environmental parameter weight and / or environmental parameter impact threshold M1 are automatically adjusted; When the current status detection is abnormal and the environmental parameters affect the normal state, a secondary alarm signal is issued to check the hardware failure of the power distribution cabinet. After eliminating the hardware failure factor, the monitoring frequency is increased; When the current status detection is abnormal and the environmental parameters have abnormal effects, a three-level warning signal is issued to check the abnormal sensors of the temperature, humidity, ozone concentration, and particulate matter concentration sampling points, start the self-calibration instruction, eliminate the offset error of the abnormal sensor, and record the number of abnormal sensor offsets. When the offset condition occurs more than three times in a row, replace the abnormal sensor.

3. The method for intelligently monitoring a small space environment according to claim 1, characterized in that: In step S1, the temperature, humidity, ozone concentration, and particulate matter concentration parameter information after the synchronous sampling point are first cleaned to remove errors, missing values, and outliers in the data. Then, the average values ​​of the multi-source temperature, humidity, ozone concentration, and particulate matter concentration after data cleaning are calculated in turn, and recorded as temperature A, humidity B, ozone concentration C, and particulate matter concentration D, respectively. Temperature A, humidity B, ozone concentration C, and particulate matter concentration D are regarded as environmental parameter information collected in the spatial microenvironment.

4. The method for intelligently monitoring a small space environment according to claim 1, characterized in that: In step S2, the weight of the environmental parameters is dynamically assigned based on the power factor. The power factor is divided into: a power factor W greater than 0.95 is considered to be a high state; a power factor W greater than or equal to 0.9 and less than or equal to 0.95 is considered to be a normal state; a power factor W less than 0.9 is considered to be a low state. When the power factor is high, the temperature weight is 0.4, the humidity weight is 0.2, the ozone concentration weight is 0.3, and the particulate matter concentration weight is 0.

1. The logarithmic temperature weight is 0.30, the humidity weight is 0.35, the light weight is 0.20, and the oxygen concentration weight is 0.

15. In normal state, the temperature weight is 0.3, the humidity weight is 0.3, the light weight is 0.2, and the oxygen concentration weight is 0.

2. When the power factor is low, the temperature weight is 0.2, the humidity weight is 0.4, the light weight is 0.1, and the oxygen concentration weight is 0.

3.

5. The method for intelligently monitoring a small space environment according to claim 1, characterized in that: In step S3, the corresponding environmental parameter impact threshold M1 in the database is extracted according to the power factor W. If M is greater than M1, it indicates that the current environmental parameter impact is abnormal. Otherwise, it indicates that the current environmental parameter impact is normal. Calculate the quantitative value M2 of the environmental parameter impact, M2 = (M-M1) ÷ M1. When the current environmental parameter impact is normal, M2 is 0.

6. The method for intelligently monitoring a small space environment according to claim 1, characterized in that: In step S2, the temperature threshold A1, humidity threshold B1, light threshold C1, and oxygen concentration threshold D1 are range values. The temperature threshold A1 is A11 to A12. If A is less than or equal to A11, A2 = |A11-A|÷A11. If A is greater than or equal to A12, A2 = |A12-A|÷A12. When A is greater than A11 and less than A12, A2 is 0. Humidity threshold B1 is between B11 and B12. If B is less than or equal to B11, B2 = |B11-B|÷B11. If B is greater than or equal to B12, B2 = |B12-B|÷B12. If B is greater than B11 and less than B12, B2 is 0. The ozone concentration threshold C1 is C11~C12. If C is less than or equal to C11, C2=|C11-C|÷C11. If C is greater than or equal to C12, C2=|C12-C|÷C12. When C is greater than C11 and less than C12, C2 is 0. The particle matter concentration threshold D1 is D11~D12. When D is less than or equal to D11, D2=|D11-D|÷D11. When D is greater than or equal to D12, D2=|D12-D|÷D12. When D is greater than D11 and less than D12, D2 is 0.

7. A space micro-environment intelligent monitoring system, characterized in that: The system is applied to a method for intelligent monitoring of a small space environment as claimed in any one of claims 1 to 6, comprising a multi-source acquisition module, a multi-source fusion module, a status detection module, an intelligent control module, an automatic calibration module, and an early warning module. The multi-source acquisition module collects status information and environmental parameter information of a power distribution cabinet in a small space environment; The multi-source fusion module calculates the temperature quantization value A2, the humidity quantization value B2, the ozone concentration quantization value C2, the particulate matter concentration quantization value D2, dynamically allocates environmental parameter weights based on the power factor, calculates the environmental parameter impact value M, and calculates the environmental parameter impact quantization value M2; The state detection module calculates the state detection value Q and extracts the corresponding state detection threshold Q1 from the database according to the power factor. If Q is less than Q1, it indicates that the current state detection is normal. Otherwise, if Q is greater than or equal to Q1, it indicates that the current state detection is abnormal. The intelligent control module intelligently monitors the environmental parameter impact results and the status detection results, and drives the early warning module to issue graded early warnings based on abnormal situations, while controlling the automatic calibration module to automatically adjust the environmental parameter settings.

Images