Intelligent building environment monitoring system and monitoring method

Abstract

The invention relates to the technical field of building environment monitoring, and discloses an intelligent building environment monitoring system and method, and the method comprises the steps: S1, collecting the related environment information of each preset monitoring point in a warehouse through a first environment collection module; s2, comparing each acquired environment information parameter with a corresponding preset early warning threshold value, and if any environment information parameter exceeds the corresponding preset early warning threshold value, generating an abnormal early warning signal of the monitoring point; according to the method, warehouse monitoring point environment parameters are collected in real time through distributed sensors, single-point threshold comparison is performed firstly to trigger preliminary early warning, then environment characteristic values are calculated through multi-parameter weighting and compared with a historical abnormal range, high-density sampling analysis is performed on a characteristic value abnormal region through an inspection robot, and the abnormal region is subjected to early warning. The method overcomes the defects that a traditional warehouse environment monitoring mode is high in false alarm rate, lacks comprehensive evaluation, cannot perform dynamic inspection and the like.

Description

Technical Field

[0001] This application relates to the field of building environment monitoring technology, and in particular to an intelligent building environment monitoring system and monitoring method. Background Technology

[0002] Driven by the global wave of digital transformation, building intelligence technology is developing rapidly at an unprecedented pace, profoundly reshaping the operation mode and management concept of modern buildings. As a key place that carries a large amount of production materials, living materials and strategic reserves, the importance of warehouses is self-evident. The fluctuations in temperature and humidity, changes in air quality, differences in light intensity and concentration of harmful gases in their internal environment not only directly affect the quality and safety of stored goods, but also have a profound impact on the integrity, service life and potential value of the materials. Once environmental parameters are out of control, it is easy to cause problems such as goods getting damp and moldy, metal corrosion and electronic product performance degradation, which in turn bring incalculable economic losses and reputational crises to enterprises.

[0003] Traditional warehouse environment monitoring methods often employ single-point threshold monitoring, which involves setting fixed warning thresholds for individual environmental parameters such as temperature, humidity, and gas concentration. Once a parameter exceeds the threshold, an alert is issued. However, this approach has significant drawbacks: firstly, exceeding a single parameter may lead to false alarms due to local environmental fluctuations, lacking a comprehensive consideration of the overall environment; secondly, when multiple environmental parameters are in a critical state but have not exceeded the threshold, potential risks cannot be identified in advance, potentially leading to serious storage accidents.

[0004] In addition, existing monitoring systems mostly rely on fixed sensor networks and lack dynamic inspection mechanisms. When sensors detect anomalies, it is difficult to conduct detailed investigations of the abnormal areas and accurately determine the scope and severity of the anomalies. Summary of the Invention

[0005] To overcome the shortcomings of traditional warehouse environment monitoring methods, such as high false alarm rate, lack of comprehensive evaluation, and inability to conduct dynamic inspections, this application provides an intelligent building environment monitoring system and monitoring method.

[0006] Firstly, this application provides an intelligent building environment monitoring system and method, employing the following technical solution:

[0007] An intelligent building environment monitoring method, the method comprising:

[0008] S1. Collect relevant environmental information from various pre-set monitoring points within the warehouse using the first environmental acquisition module;

[0009] S2. Compare each collected environmental information parameter with its corresponding preset warning threshold. If any environmental information parameter exceeds its corresponding preset warning threshold, generate an abnormal warning signal for that monitoring point; otherwise, proceed to step S3.

[0010] S3. Perform a comprehensive analysis of all environmental information parameters at each monitoring point to obtain the environmental characteristic value of each monitoring point. Compare the environmental characteristic value with the preset abnormal threshold range. If the environmental characteristic value of any monitoring point is greater than the maximum value of the preset abnormal threshold range, generate an abnormal warning signal for that monitoring point. If the environmental characteristic value of any monitoring point is within the preset abnormal threshold range, proceed to step S4. If the environmental characteristic values ​​of all monitoring points are less than the minimum value of the preset abnormal threshold range, proceed to step S5.

[0011] S4. Control the inspection robot to move to the monitoring area corresponding to the monitoring point where the environmental feature value described in step S3 is within the preset abnormal threshold range. Collect environmental information from multiple collection points in the monitoring area through the second environmental acquisition module on the inspection robot. Further analyze all environmental information data collected from each collection point in the monitoring area to determine whether there is an abnormality in the environment of the monitoring point. If there is an abnormality, generate an abnormality warning signal for the monitoring point; otherwise, execute step S5.

[0012] S5. Perform statistical analysis on the analysis results of all monitoring points in the warehouse to determine whether the storage environment in the warehouse is abnormal. If it is abnormal, generate an early warning signal for abnormal warehouse environment.

[0013] By adopting the above technical solution, the method first collects environmental information from each monitoring point in the warehouse, performs three-level comparison and analysis, checks for anomalies at each level, and finally makes a comprehensive judgment on whether the warehouse environment is abnormal, thereby realizing intelligent monitoring and early warning.

[0014] Optionally, the process of comprehensively analyzing all environmental information parameters at each monitoring point includes:

[0015] The various environmental information parameters at the same monitoring point are normalized and mapped to the [0,1] interval;

[0016] Based on the weights of the impact of each environmental information parameter on the stored items, a weighted sum is calculated as the environmental characteristic value E for that monitoring point. i ;

[0017] The influence weight is dynamically adjusted according to the type of stored items;

[0018] Environmental characteristic value E i Compared with the preset abnormal threshold range [E] min E max Compare;

[0019] If there exists any E i >E max If so, an abnormal early warning signal will be generated for that monitoring point;

[0020] If there exists any E i ∈[E min E max If the condition is met, then proceed to step S4 to further analyze the monitoring area corresponding to the monitoring point.

[0021] If all E i <E min Then proceed to step S5 to perform a comprehensive analysis of the warehouse environment.

[0022] By adopting the above technical solution, after normalizing various environmental information parameters of the same monitoring point, the environmental characteristic value of the monitoring point is obtained by calculating the weighted sum based on the influence weight of each parameter on the stored items. The weight can be dynamically adjusted according to the type of stored items, making the assessment more accurate.

[0023] Optionally, the process of obtaining the environmental feature values ​​includes:

[0024]

[0025] The environmental characteristic value of the i-th monitoring point is obtained by analyzing and calculating using the above formula;

[0026] Where n is the number of environmental information parameters collected, j∈[1,n], W j,i W represents the measured value of the j-th environmental information parameter at the i-th monitoring point. j,max W represents the historical maximum value of the j-th environmental information parameter. j,min Let α be the historical minimum value of the j-th environmental information parameter. j is the influence weight coefficient corresponding to the j-th environmental information parameter.

[0027] By adopting the above technical solution, the collected environmental information parameters are normalized and weighted using formulas to obtain the environmental characteristic value of the i-th monitoring point. Combined with historical data and influence weights, a quantitative assessment of the environmental status is achieved.

[0028] Optionally, in step S4, the process of further analyzing all environmental information data collected from each collection point within the monitoring area includes:

[0029] S41. Calculate the average value of all environmental information parameters at all collection points within the monitoring area;

[0030] S42. Calculate the deviation between each environmental information parameter at each collection point and the average value of that environmental information parameter. If any deviation exceeds the preset fluctuation threshold, then the environmental information parameter at that collection point is determined to be abnormal.

[0031] S43. Perform trend analysis on the collection points with abnormal environmental information parameters, calculate the parameter change rate through continuous sampling, and if the change rate of any environmental information parameter at any collection point exceeds the preset change rate threshold, it is determined that the environmental information parameter at that collection point is abnormal.

[0032] S44. Perform statistical analysis on the data of all collection points with abnormal environmental information parameters in the monitoring area. When the environmental information parameters of collection points in the monitoring area exceeding a preset proportion are judged to be abnormal, the environment in the monitoring area is judged to be abnormal, and an abnormal warning signal for the corresponding monitoring point in the monitoring area is generated.

[0033] By adopting the above technical solution, the inspection robot intensively samples suspicious areas, calculates the average value, deviation value and change rate of parameters, and statistically analyzes the proportion of anomalies, thereby achieving a detailed analysis and anomaly determination of the monitored area environment.

[0034] Optionally, step S43, the process of determining that the environmental information parameter at the collection point is abnormal, includes:

[0035]

[0036] The transformation rate ΔQ of the j-th environmental information parameter at the data collection point with abnormal parameters is obtained through analysis and calculation using the above formula. j ;

[0037] Among them, Q j (t) represents the value of the j-th environmental information parameter at time t for that collection point, Q. j (t-Δt) represents the value of the j-th environmental information parameter at the time node t-Δt, where Δt is the preset sliding time window;

[0038] If |ΔQ j |>Q j,std If so, it is determined that the environmental information parameter at that collection point is abnormal;

[0039] Conversely, it is determined that there is no abnormality in that environmental information parameter at the collection point;

[0040] Among them, Q j,std This is the preset change threshold for the j-th environmental information parameter.

[0041] By adopting the above technical solution, the rate of change of environmental information parameters at the collection point within the sliding time window is calculated using a formula and compared with a preset threshold to accurately determine whether the parameters are abnormal and to capture environmental change trends in a timely manner.

[0042] Optionally, step S44, which involves statistically analyzing the data from all collection points within the monitoring area where environmental information parameters show anomalies, includes:

[0043]

[0044] The proportion ε of all environmental parameters at all collection points within the monitoring area that were determined to be abnormal sampling points was obtained through the above formula analysis and calculation.

[0045] Where m is the number of preset collection points in the monitoring area, k∈[1,m], ΔQ j,k The transformation rate of the j-th environmental information parameter at the k-th collection point within the monitoring area;

[0046] If ε > ε risk If the environment within the monitoring area is determined to be abnormal, an abnormal early warning signal for the corresponding monitoring point in the monitoring area will be generated.

[0047] Conversely, no abnormal warning signal is generated;

[0048] Where, ε risk This is a preset threshold for the abnormal proportion.

[0049] By adopting the above technical solution, the proportion of abnormal collection points in the monitoring area is statistically analyzed and compared with a preset proportion threshold. If the threshold is exceeded, an early warning is generated, thereby realizing the scientific judgment and early warning of local environmental anomalies.

[0050] Optionally, step S5, which involves statistically analyzing the results of all monitoring points within the warehouse, includes:

[0051] Calculate the percentage of monitoring points whose environmental characteristic values ​​are within the preset abnormal threshold range to obtain the risk area ratio;

[0052] Perform time-series analysis on the proportion of risk areas within a continuous time window and calculate the rate of change of the proportion of risk areas at adjacent time points;

[0053] By comprehensively analyzing the proportion of risk areas and the rate of change of the proportion of risk areas, it is determined whether the storage environment in the warehouse is abnormal. If it is abnormal, an early warning signal of abnormal warehouse environment is generated.

[0054] By adopting the above technical solutions, the proportion and rate of change of risk areas are calculated. Using time series analysis and comprehensive evaluation models, combined with weighting coefficients, the overall environmental risk level of the warehouse is dynamically judged to achieve early warning.

[0055] Optionally, the process of comprehensively analyzing the proportion of the comprehensive analysis area and the rate of change of the proportion of the risk area includes:

[0056]

[0057] R = A risk (t)*ω1+IF(ΔA(t)>0,ΔA(t),0)*ω2

[0058] The abnormal characteristic value R of the warehouse storage environment is obtained by combining the above formulas and performing simultaneous analysis.

[0059] Among them, A risk (t) represents the proportion of risky areas within the warehouse at time t, C(t) represents the number of monitoring points whose environmental characteristic values ​​are within the preset abnormal threshold range at time t, N represents the total number of monitoring points within the warehouse, and ΔA(t) represents the rate of change of the proportion of risky areas within the warehouse at time t. risk (t-t1) represents the proportion of risk areas in the warehouse at time node t-t1, t1 is the continuous time window interval, and ω1 and ω2 are the weight coefficients corresponding to the abnormal influencing factors of the warehouse storage environment.

[0060] The abnormal characteristic value R of the warehouse storage environment is compared with the preset abnormal early warning threshold R of the warehouse storage environment. risk Perform a comparison;

[0061] If R≥R risk This will generate an early warning signal for abnormal warehouse environment.

[0062] By adopting the above technical solutions, the combined formula integrates the proportion and rate of change of risk areas, calculates the abnormal characteristic value of the warehouse, and compares it with the early warning threshold to achieve quantitative assessment and early warning of abnormalities in the overall warehouse environment.

[0063] Secondly, this application provides an intelligent building environment monitoring system, which adopts the following technical solution:

[0064] An intelligent building environment monitoring system, the system being used in any one of the intelligent building environment monitoring methods described above, the system comprising:

[0065] The first environmental data acquisition module is used to collect relevant environmental information from various pre-set monitoring points within the warehouse.

[0066] The initial analysis module is used to compare the collected environmental information parameters with their corresponding preset warning thresholds. If any environmental information parameter exceeds its corresponding preset warning threshold, an abnormal warning signal is generated for that monitoring point.

[0067] The secondary analysis module is used to comprehensively analyze all environmental information parameters of each monitoring point, compare the environmental feature values ​​obtained from the analysis with the preset abnormal threshold range, and generate an abnormal warning signal for the monitoring point if the environmental feature value of any monitoring point is greater than the maximum value of the preset abnormal threshold range. If the environmental feature value of any monitoring point is within the preset abnormal threshold range, the inspection module is controlled to move to the monitoring area corresponding to the monitoring point.

[0068] The inspection module includes an inspection robot and a second environmental acquisition module and a third analysis module mounted on it. The inspection robot is used to move and transport the second environmental acquisition module to the corresponding monitoring area and move it within multiple preset acquisition points. The second environmental acquisition module is used to collect environmental information from multiple acquisition points within the monitoring area. The third analysis module is used to further analyze all environmental information data collected from each acquisition point within the monitoring area to determine whether to generate an abnormal early warning signal for the corresponding monitoring point.

[0069] The comprehensive analysis module is used to perform statistical analysis on the analysis results of all monitoring points in the warehouse and determine whether to generate an early warning signal for abnormal warehouse environment.

[0070] The early warning module is used to execute early warning signals for abnormalities at monitoring points and for abnormalities in the warehouse environment.

[0071] By adopting the above technical solution, the system works in concert through five modules to achieve a three-level monitoring system from single-point monitoring to regional inspection and then to global analysis, generating early warning signals in a timely manner to ensure the safety of the warehouse storage environment.

[0072] Thirdly, this application provides a storage medium, which adopts the following technical solution:

[0073] A storage medium storing a program for an intelligent building environment monitoring method as described in any one of the above.

[0074] In summary, this application includes at least one of the following beneficial technical effects:

[0075] (1) This invention collects environmental parameters of warehouse monitoring points in real time through distributed sensors, firstly triggers preliminary early warning by comparing single-point thresholds, then calculates environmental feature values ​​by multi-parameter weighting and compares them with historical abnormal ranges, dispatches inspection robots to conduct high-density sampling and analysis of abnormal feature value areas, and finally calculates the overall risk ratio and time series changes to determine the overall environment. This method constructs a three-dimensional monitoring system, realizes multi-level screening and accurate early warning of warehouse environment anomalies, and overcomes the defects of traditional warehouse environment monitoring methods such as high false alarm rate, lack of comprehensive evaluation, and inability to conduct dynamic inspections. Attached Figure Description

[0076] Figure 1 This is a flowchart of the steps of an intelligent building environment monitoring method proposed in this invention;

[0077] Figure 2 This is a schematic diagram of an intelligent building environment monitoring system proposed in this invention. Detailed Implementation

[0078] The embodiments of this application are described in detail below, and examples of the embodiments are shown in the accompanying drawings.

[0079] In the description of this specification, the references to "certain embodiments," "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples" refer to specific features, structures, materials, or characteristics described in connection with the described embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0080] This application discloses an intelligent building environment monitoring method, referring to... Figure 1 The method includes:

[0081] S1. Collect relevant environmental information of each preset monitoring point in the warehouse through the first environmental acquisition module. The first environmental acquisition module includes temperature and humidity sensors, light sensors, gas concentration sensors, etc. distributed in the warehouse. The monitoring points are preset according to the warehouse layout, the type of stored items and fire protection regulations. Each sensor collects environmental information at a preset frequency. The raw data is filtered and denoised and then stored in the database.

[0082] S2. Compare each collected environmental information parameter with its corresponding preset warning threshold. If any environmental information parameter exceeds its corresponding preset warning threshold, generate an abnormal warning signal for that monitoring point. Otherwise, execute step S3. The preset warning threshold is set based on the characteristics of the stored items. For example, the temperature threshold for a pharmaceutical warehouse is 2-8℃, and the humidity threshold is 45%-75%RH. The threshold is stored in a knowledge base and can be dynamically adjusted through an expert system.

[0083] S3. Perform a comprehensive analysis of all environmental information parameters at each monitoring point to obtain the environmental characteristic value of each monitoring point. Compare the environmental characteristic value with the preset abnormal threshold range. If the environmental characteristic value of any monitoring point is greater than the maximum value of the preset abnormal threshold range, generate an abnormal warning signal for that monitoring point. If the environmental characteristic value of any monitoring point is within the preset abnormal threshold range, proceed to step S4. If the environmental characteristic values ​​of all monitoring points are less than the minimum value of the preset abnormal threshold range, proceed to step S5.

[0084] S4. Control the inspection robot to move to the monitoring area corresponding to the monitoring point whose environmental feature value is within the preset abnormal threshold range mentioned in step S3. Collect environmental information from multiple collection points in the monitoring area through the second environmental acquisition module on the inspection robot. Further analyze all environmental information data collected from each collection point in the monitoring area to determine whether there is an abnormality in the environment of the monitoring point. If there is an abnormality, generate an abnormality warning signal for the monitoring point. Otherwise, execute step S5. The second environmental acquisition module includes temperature and humidity sensors, light sensors, gas concentration sensors, etc., distributed on the inspection robot.

[0085] S5. Perform statistical analysis on the analysis results of all monitoring points in the warehouse to determine whether the storage environment in the warehouse is abnormal. If it is abnormal, generate an early warning signal for abnormal warehouse environment.

[0086] Through the above technical solution, this embodiment provides an intelligent building environment monitoring method. The method collects environmental parameters of warehouse monitoring points in real time through distributed sensors, firstly triggers preliminary early warning by comparing single-point thresholds, then calculates environmental feature values ​​by multi-parameter weighting and compares them with historical anomaly ranges, dispatches inspection robots to conduct high-density sampling and analysis of areas with abnormal feature values, and finally statistically analyzes the global risk ratio and time-series changes to determine the overall environment. This method constructs a three-dimensional monitoring system, realizes multi-level screening and accurate early warning of warehouse environment anomalies, and overcomes the defects of traditional warehouse environment monitoring methods such as high false alarm rate, lack of comprehensive evaluation, and inability to conduct dynamic inspections.

[0087] In one embodiment, the process of comprehensively analyzing all environmental information parameters at each monitoring point includes:

[0088] The various environmental information parameters at the same monitoring point are normalized and mapped to the [0,1] interval;

[0089] Based on the weights of the impact of each environmental information parameter on the stored items, a weighted sum is calculated as the environmental characteristic value E for that monitoring point. i ;

[0090] The influence weight is dynamically adjusted according to the type of stored items;

[0091] Environmental characteristic value E i Compared with the preset abnormal threshold range [E] min E max Compare;

[0092] If there exists any E i >E max If so, an abnormal early warning signal will be generated for that monitoring point;

[0093] If there exists any E i ∈[E min E max If the condition is met, then proceed to step S4 to further analyze the monitoring area corresponding to the monitoring point.

[0094] If all E i <E min Then proceed to step S5 to perform a comprehensive analysis of the warehouse environment.

[0095] The process of obtaining the environmental feature values ​​includes:

[0096]

[0097] The environmental characteristic value of the i-th monitoring point is obtained by analyzing and calculating using the above formula;

[0098] Where n is the number of environmental information parameters collected, obtained according to the data categories collected by the first environmental acquisition module, j∈[1,n], W j,i W is the measured value of the j-th environmental information parameter at the i-th monitoring point, obtained through the first environmental acquisition module. j,max W represents the historical maximum value of the j-th environmental information parameter. j,min The W represents the historical minimum value of the j-th environmental information parameter. j,max and W j,min Both methods can be implemented by extracting parameter data from a time-series database for a specific number of past months (e.g., 36 months), calculating extreme values ​​by grouping them by calendar month, and updating the data quarterly. α j Let be the influence weight coefficient corresponding to the j-th environmental information parameter. The initial value is set by the expert system and can be dynamically updated through a Bayesian network. For example, when the items stored in the warehouse change from ordinary goods to precision instruments, the weight coefficients of temperature and humidity increase from 0.3 and 0.2 to 0.5 and 0.3, respectively.

[0099] Through the above technical solution, this embodiment provides a dynamic weighted environmental feature value assessment method. The method normalizes multiple environmental parameters at the same monitoring point, dynamically adjusts the influence weights based on the type of stored items, and calculates the environmental feature value using a formula. This method solves the problem of differences in the dimensions of multiple parameters, realizes the quantitative assessment and dynamic adaptation of environmental quality, and improves the ability to accurately compare environmental risks and identify anomalies at monitoring points under different warehousing scenarios.

[0100] In one embodiment, step S4, the process of further analyzing all environmental information data collected from each collection point within the monitoring area, includes:

[0101] S41. Calculate the average value of all environmental information parameters at all collection points within the monitoring area;

[0102] S42. Calculate the deviation between each environmental information parameter at each collection point and the average value of that environmental information parameter. If any deviation exceeds the preset fluctuation threshold, then the environmental information parameter at that collection point is determined to be abnormal.

[0103] S43. Perform trend analysis on the collection points with abnormal environmental information parameters, calculate the parameter change rate through continuous sampling, and if the change rate of any environmental information parameter at any collection point exceeds the preset change rate threshold, it is determined that the environmental information parameter at that collection point is abnormal.

[0104] S44. Perform statistical analysis on the data of all collection points with abnormal environmental information parameters in the monitoring area. When the environmental information parameters of collection points in the monitoring area exceeding a preset proportion are judged to be abnormal, the environment in the monitoring area is judged to be abnormal, and an abnormal warning signal for the corresponding monitoring point in the monitoring area is generated.

[0105] Step S43, the process of determining that the environmental information parameter at the collection point is abnormal, includes:

[0106]

[0107] The transformation rate ΔQ of the j-th environmental information parameter at the data collection point with abnormal parameters is obtained through analysis and calculation using the above formula. j ;

[0108] Among them, Q j (t) represents the value of the j-th environmental information parameter at time t at this collection point, i.e., the value of the j-th environmental information parameter at the current time point, which can be obtained through sensor acquisition. Q j(t-Δt) is the value of the j-th environmental information parameter at the time node t-Δt, that is, the value of the j-th environmental information parameter at the time node Δt before the current time node. It can be obtained by reading historical data. Δt is a preset sliding time window, which can be set according to experience. It is generally set to the corresponding sensor acquisition interval.

[0109] If |ΔQ j |>Q j,std If so, it is determined that the environmental information parameter at that collection point is abnormal;

[0110] Conversely, it is determined that there is no abnormality in that environmental information parameter at the collection point;

[0111] Among them, Q j,std The preset change threshold for the j-th environmental information parameter can be determined by analyzing the normal fluctuation range.

[0112] Step S44, the process of statistically analyzing the data from all collection points with abnormal environmental information parameters within the monitoring area, includes:

[0113]

[0114] The proportion ε of all environmental parameters at all collection points within the monitoring area that were determined to be abnormal sampling points was obtained through the above formula analysis and calculation.

[0115] Where m is the number of preset collection points within the monitoring area, set according to the warehouse layout, the type of stored items, and the accuracy requirements of the monitoring, k∈[1,m], ΔQ j,k The transformation rate of the j-th environmental information parameter at the k-th collection point within the monitoring area;

[0116] If ε > ε risk If the environment within the monitoring area is determined to be abnormal, an abnormal early warning signal for the corresponding monitoring point in the monitoring area will be generated.

[0117] Conversely, no abnormal warning signal is generated;

[0118] Where, ε risk The preset abnormality ratio threshold can be set according to the sensitivity requirements for monitoring abnormalities.

[0119] Through the above technical solution, this embodiment provides a method for fine-grained determination of regional environmental anomalies based on multidimensional statistics. The method calculates the average value of parameters collected from the monitoring area, identifies single-point anomalies by combining the deviation value, calculates the parameter change rate using a sliding time window to analyze the trend, and finally determines whether the monitoring area is abnormal by statistically analyzing the proportion of anomalies. This method achieves rapid location and reliable determination of environmental anomalies through a three-level analysis of "single-point screening - trend verification - regional statistics" combined with edge computing localization processing, thereby reducing the risk of false alarms.

[0120] In one embodiment, step S5, the process of statistically analyzing the analysis results of all monitoring points within the warehouse, includes:

[0121] Calculate the percentage of monitoring points whose environmental characteristic values ​​are within the preset abnormal threshold range to obtain the risk area ratio;

[0122] Perform time-series analysis on the proportion of risk areas within a continuous time window and calculate the rate of change of the proportion of risk areas at adjacent time points;

[0123] By comprehensively analyzing the proportion of risk areas and the rate of change of the proportion of risk areas, it is determined whether the storage environment in the warehouse is abnormal. If it is abnormal, an early warning signal of abnormal warehouse environment is generated.

[0124] The process of comprehensively analyzing the changes in the proportion of the comprehensive analysis area and the proportion of the risk area includes:

[0125]

[0126] R = A risk (t)*ω1+IF(ΔA(t)>0,ΔA(t),0)*ω2

[0127] The abnormal characteristic value R of the warehouse storage environment is obtained by combining the above formulas and performing simultaneous analysis.

[0128] Among them, A risk (t) represents the proportion of risky areas in the warehouse at time t, i.e., the proportion of risky areas in the warehouse at the current time point. C(t) represents the number of monitoring points whose environmental characteristic values ​​are within the preset abnormal threshold range at time t, i.e., the number of monitoring points whose environmental characteristic values ​​are within the preset abnormal threshold range at the current time point, which can be obtained through statistical analysis of monitoring data in step S3. N represents the total number of monitoring points in the warehouse, which can be obtained by statistical analysis of the number set in the first environmental acquisition module. ΔA(t) represents the rate of change of the proportion of risky areas in the warehouse at time t. risk (t-t1) represents the proportion of risk areas in the warehouse at time t-t1, i.e., the proportion of risk areas in the warehouse t1 before the current time point. It can be obtained by reading historical data. t1 is the continuous time window interval, which is preset based on experience and is generally taken as 5 to 60 minutes. ω1 and ω2 are the weight coefficients corresponding to the abnormal factors affecting the warehouse storage environment, which can be set based on expert experience.

[0129] The abnormal characteristic value R of the warehouse storage environment is compared with the preset abnormal early warning threshold R of the warehouse storage environment. risk By comparison, the preset abnormal warehouse storage environment early warning threshold can be obtained by setting it based on expert experience;

[0130] If R≥R risk This will generate an early warning signal for abnormal warehouse environment.

[0131] Through the above technical solution, this embodiment provides a time-driven method for assessing the overall environmental risk of a warehouse. The method calculates the proportion of risk areas and their time change rate, uses a weighted formula for comprehensive assessment, and triggers a global early warning after comparing it with a preset threshold. This method combines the spatial distribution and temporal evolution characteristics of risks to construct a dynamic assessment model, realizes cross-scale correlation analysis from local anomalies to overall risks, and provides data support for systematic safety management.

[0132] This application also discloses an intelligent building environment monitoring system, as described in the embodiments below. Figure 2 The system is used in any one of the intelligent building environment monitoring methods described above, and the system includes:

[0133] The first environmental data acquisition module is used to collect relevant environmental information from various pre-set monitoring points within the warehouse.

[0134] The initial analysis module is used to compare the collected environmental information parameters with their corresponding preset warning thresholds. If any environmental information parameter exceeds its corresponding preset warning threshold, an abnormal warning signal is generated for that monitoring point.

[0135] The secondary analysis module is used to comprehensively analyze all environmental information parameters of each monitoring point, compare the environmental feature values ​​obtained from the analysis with the preset abnormal threshold range, and generate an abnormal warning signal for the monitoring point if the environmental feature value of any monitoring point is greater than the maximum value of the preset abnormal threshold range. If the environmental feature value of any monitoring point is within the preset abnormal threshold range, the inspection module is controlled to move to the monitoring area corresponding to the monitoring point.

[0136] The inspection module includes an inspection robot and a second environmental acquisition module and a third analysis module mounted on it. The inspection robot is used to move and transport the second environmental acquisition module to the corresponding monitoring area and move it within multiple preset acquisition points. The second environmental acquisition module is used to collect environmental information from multiple acquisition points within the monitoring area. The third analysis module is used to further analyze all environmental information data collected from each acquisition point within the monitoring area to determine whether to generate an abnormal early warning signal for the corresponding monitoring point.

[0137] The comprehensive analysis module is used to perform statistical analysis on the analysis results of all monitoring points in the warehouse and determine whether to generate an early warning signal for abnormal warehouse environment.

[0138] The early warning module is used to execute early warning signals for abnormalities at monitoring points and for abnormalities in the warehouse environment.

[0139] Through the above technical solution, this embodiment provides an intelligent building environment monitoring system. The system adopts a collaborative working mechanism of full-domain data acquisition by the first environmental acquisition module, single-point threshold comparison by the initial analysis module, feature value calculation by the secondary analysis module, fine detection of suspicious areas by the inspection module, global risk assessment by the comprehensive analysis module, and hierarchical early warning by the early warning module. The system realizes full-process automation from data acquisition to anomaly handling, supports dynamic expansion and multi-system linkage, and provides an engineering solution for intelligent warehouse environment monitoring.

[0140] This application also discloses a storage medium storing a program for an intelligent building environment monitoring method as described in any one of the above embodiments.

[0141] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. An intelligent building environment monitoring method, characterized in that, The method includes: S1. Collect relevant environmental information from various pre-set monitoring points within the warehouse using the first environmental acquisition module; S2. Compare each collected environmental information parameter with its corresponding preset warning threshold. If any environmental information parameter exceeds its corresponding preset warning threshold, generate an abnormal warning signal for that monitoring point; otherwise, proceed to step S3. S3. Perform a comprehensive analysis of all environmental information parameters at each monitoring point to obtain the environmental characteristic value of each monitoring point. Compare the environmental characteristic value with the preset abnormal threshold range. If the environmental characteristic value of any monitoring point is greater than the maximum value of the preset abnormal threshold range, generate an abnormal warning signal for that monitoring point. If the environmental characteristic value of any monitoring point is within the preset abnormal threshold range, proceed to step S4. If the environmental characteristic values ​​of all monitoring points are less than the minimum value of the preset abnormal threshold range, proceed to step S5. S4. Control the inspection robot to move to the monitoring area corresponding to the monitoring point where the environmental feature value described in step S3 is within the preset abnormal threshold range. Collect environmental information from multiple collection points in the monitoring area through the second environmental acquisition module on the inspection robot. Further analyze all environmental information data collected from each collection point in the monitoring area to determine whether there is an abnormality in the environment of the monitoring point. If there is an abnormality, generate an abnormality warning signal for the monitoring point; otherwise, execute step S5. S5. Perform statistical analysis on the analysis results of all monitoring points in the warehouse to determine whether the storage environment in the warehouse is abnormal. If it is abnormal, generate an early warning signal for abnormal warehouse environment.

2. The intelligent building environment monitoring method according to claim 1, characterized in that, Step S3, the process of comprehensively analyzing all environmental information parameters at each monitoring point, includes: The various environmental information parameters at the same monitoring point are normalized and mapped to the [0,1] interval; Based on the weights of the impact of each environmental information parameter on the stored items, a weighted sum is calculated as the environmental characteristic value E for that monitoring point. i ; The influence weight is dynamically adjusted according to the type of stored items; Environmental characteristic value E i Compared with the preset abnormal threshold range [E] min E max Compare; If there exists any E i >E max If so, an abnormal early warning signal will be generated for that monitoring point; If there exists any E i ∈[E min E max If the condition is met, then proceed to step S4 to further analyze the monitoring area corresponding to the monitoring point. If all E i <E min Then proceed to step S5 to perform a comprehensive analysis of the warehouse environment.

3. The intelligent building environment monitoring method according to claim 2, characterized in that, The process of obtaining the environmental feature values ​​includes: The environmental characteristic value of the i-th monitoring point is obtained by analyzing and calculating using the above formula; Where n is the number of environmental information parameters collected, j∈[1,n], W j,i W represents the measured value of the j-th environmental information parameter at the i-th monitoring point. j,max W represents the historical maximum value of the j-th environmental information parameter. j,min Let α be the historical minimum value of the j-th environmental information parameter. j is the influence weight coefficient corresponding to the j-th environmental information parameter.

4. The intelligent building environment monitoring method according to claim 3, characterized in that, Step S4, the process of further analyzing all environmental information data collected from each collection point within the monitoring area, includes: S41. Calculate the average value of all environmental information parameters at all collection points within the monitoring area; S42. Calculate the deviation between each environmental information parameter at each collection point and the average value of that environmental information parameter. If any deviation exceeds the preset fluctuation threshold, then the environmental information parameter at that collection point is determined to be abnormal. S43. Perform trend analysis on the collection points with abnormal environmental information parameters, calculate the parameter change rate through continuous sampling, and if the change rate of any environmental information parameter at any collection point exceeds the preset change rate threshold, it is determined that the environmental information parameter at that collection point is abnormal. S44. Perform statistical analysis on the data of all collection points with abnormal environmental information parameters in the monitoring area. When the environmental information parameters of collection points in the monitoring area exceeding a preset proportion are judged to be abnormal, the environment in the monitoring area is judged to be abnormal, and an abnormal warning signal for the corresponding monitoring point in the monitoring area is generated.

5. The intelligent building environment monitoring method according to claim 4, characterized in that, Step S43, the process of determining that the environmental information parameter at the collection point is abnormal, includes: The transformation rate ΔQ of the j-th environmental information parameter at the data collection point with abnormal parameters is obtained through analysis and calculation using the above formula. j ; Among them, Q j (t) represents the value of the j-th environmental information parameter at time t for that collection point, Q. j (t-Δt) represents the value of the j-th environmental information parameter at the time node t-Δt, where Δt is the preset sliding time window; If |ΔQ j |>Q j,std If so, it is determined that the environmental information parameter at that collection point is abnormal; Conversely, it is determined that there is no abnormality in that environmental information parameter at the collection point; Among them, Q j,std This is the preset change threshold for the j-th environmental information parameter.

6. The intelligent building environment monitoring method according to claim 5, characterized in that, Step S44, the process of statistically analyzing the data from all collection points with abnormal environmental information parameters within the monitoring area, includes: The proportion ε of all environmental parameters at all collection points within the monitoring area that were determined to be abnormal sampling points was obtained through the above formula analysis and calculation. Where m is the number of preset collection points in the monitoring area, k∈[1,m], ΔQ j,k The transformation rate of the j-th environmental information parameter at the k-th collection point within the monitoring area; If ε > ε risk If the environment within the monitoring area is determined to be abnormal, an abnormal early warning signal for the corresponding monitoring point in the monitoring area will be generated. Conversely, no abnormal warning signal is generated; Where, ε risk This is a preset threshold for the abnormal proportion.

7. The intelligent building environment monitoring method according to claim 6, characterized in that, Step S5, the process of statistically analyzing the results of all monitoring points within the warehouse, includes: Calculate the percentage of monitoring points whose environmental characteristic values ​​are within the preset abnormal threshold range to obtain the risk area ratio; Perform time-series analysis on the proportion of risk areas within a continuous time window and calculate the rate of change of the proportion of risk areas at adjacent time points; By comprehensively analyzing the proportion of risk areas and the rate of change of the proportion of risk areas, it is determined whether the storage environment in the warehouse is abnormal. If it is abnormal, an early warning signal of abnormal warehouse environment is generated.

8. The intelligent building environment monitoring method according to claim 7, characterized in that, The process of comprehensively analyzing the changes in the proportion of the comprehensive analysis area and the proportion of the risk area includes: R=A risk (t)*ω1+IF(ΔA(t)>0,ΔA(t),0)*ω2 The abnormal characteristic value R of the warehouse storage environment is obtained by combining the above formulas and performing simultaneous analysis. Among them, A risk (t) represents the proportion of risky areas within the warehouse at time t, C(t) represents the number of monitoring points whose environmental characteristic values ​​are within the preset abnormal threshold range at time t, N represents the total number of monitoring points within the warehouse, and ΔA(t) represents the rate of change of the proportion of risky areas within the warehouse at time t. risk (t-t1) represents the proportion of risk areas in the warehouse at time node t-t1, t1 is the continuous time window interval, and ω1 and ω2 are the weight coefficients corresponding to the abnormal influencing factors of the warehouse storage environment. The abnormal characteristic value R of the warehouse storage environment is compared with the preset abnormal early warning threshold R of the warehouse storage environment. risk Perform a comparison; If R≥R risk This will generate an early warning signal for abnormal warehouse environment.

9. An intelligent building environment monitoring system, characterized in that, The system is used in an intelligent building environment monitoring method as described in any one of claims 1-8, the system comprising: The first environmental data acquisition module is used to collect relevant environmental information from various pre-set monitoring points within the warehouse. The initial analysis module is used to compare the collected environmental information parameters with their corresponding preset warning thresholds. If any environmental information parameter exceeds its corresponding preset warning threshold, an abnormal warning signal is generated for that monitoring point. The secondary analysis module is used to comprehensively analyze all environmental information parameters of each monitoring point, compare the environmental feature values ​​obtained from the analysis with the preset abnormal threshold range, and generate an abnormal warning signal for the monitoring point if the environmental feature value of any monitoring point is greater than the maximum value of the preset abnormal threshold range. If the environmental feature value of any monitoring point is within the preset abnormal threshold range, the inspection module is controlled to move to the monitoring area corresponding to the monitoring point. The inspection module includes an inspection robot and a second environmental acquisition module and a third analysis module mounted on it. The inspection robot is used to move and transport the second environmental acquisition module to the corresponding monitoring area and move it within multiple preset acquisition points. The second environmental acquisition module is used to collect environmental information from multiple acquisition points within the monitoring area. The third analysis module is used to further analyze all environmental information data collected from each acquisition point within the monitoring area to determine whether to generate an abnormal early warning signal for the corresponding monitoring point. The comprehensive analysis module is used to perform statistical analysis on the analysis results of all monitoring points in the warehouse and determine whether to generate an early warning signal for abnormal warehouse environment. The early warning module is used to execute early warning signals for abnormalities at monitoring points and for abnormalities in the warehouse environment.

10. A storage medium, characterized in that, The program stores a method for intelligent building environment monitoring as described in any one of claims 1-8.

Images