A green building environment monitoring system, method and storage medium

Abstract

This invention relates to the field of green building environmental monitoring technology, and discloses a green building environmental monitoring system, method, and storage medium. The method includes continuously collecting environmental parameters such as thermodynamic parameters, humidity parameters, and gas concentration parameters through intelligent sensing nodes at multiple locations within the green building; transmitting these environmental parameters to a central processing unit, which combines pre-stored environmental standard values ​​with real-time data streams and uses an adaptive learning algorithm to generate environmental control commands; environmental execution devices carrying out environmental adjustment activities based on these commands; real-time monitoring of the execution sequence of adjustment activities, calculation of performance evaluation indicators, and generation of normal or abnormal performance status signals, automatically triggering an alarm process in case of an anomaly. This method constructs a complete environmental management closed loop, realizing comprehensive dynamic monitoring and precise adjustment of the green building environment, adapting to the core requirements of environmental protection and comfort in green buildings, and ensuring that the building's internal environment is in a suitable state.

Description

Technical Field

[0001] This invention relates to the field of green building environmental monitoring technology, specifically to a green building environmental monitoring system, method, and storage medium. Background Technology

[0002] As the construction industry shifts towards low-carbon and environmentally friendly practices, green building has become the mainstream trend in industry development. Its core lies in achieving the dual goals of efficient resource utilization and optimized living environment through scientific design and management. Environmental quality, as a key evaluation dimension of green building, is directly related to the physical and mental health of residents and the environmental performance of the building. Therefore, precise and continuous monitoring and control of the internal environment of green buildings has become an important aspect of green building operation and maintenance.

[0003] Currently, some existing green building environmental monitoring solutions use a single sensor node for data collection, which suffers from limited monitoring range and incomplete data coverage. This makes it difficult to reflect environmental differences in different areas within the building, resulting in a lack of targeted control measures. Other solutions, while using multiple sensor nodes, collect relatively limited types of environmental parameters, often focusing only on a few indicators such as temperature or humidity, neglecting parameters like gas concentrations that significantly impact human health and indoor air quality. This leads to incomplete monitoring results and fails to provide comprehensive data support for environmental regulation.

[0004] In the environmental control phase, most existing technologies use fixed control logic to generate adjustment commands, lacking the ability to dynamically adapt to real-time environmental data. This fixed logic struggles to cope with complex changes in the building's internal environment, such as sudden changes in environmental parameters caused by factors like personnel movement and external environmental fluctuations. This can easily lead to poor adjustment effects and an inability to promptly restore the environment to a suitable state. Furthermore, existing solutions lack effective monitoring mechanisms for the execution of environmental control activities, making it difficult to know the actual implementation and effectiveness of control measures, and to determine whether the control activities have achieved their intended goals.

[0005] Current environmental regulation performance assessment systems are inadequate, often only detecting problems when obvious environmental anomalies occur, lacking the ability to predict and provide timely warnings. Once environmental parameters exceed limits or regulation devices malfunction, alarm processes cannot be triggered quickly, potentially leading to persistent abnormal conditions that negatively impact occupants' experience and even endanger their health. These issues render existing green building environmental monitoring and control solutions insufficiently practical and reliable, failing to fully meet the high environmental quality standards required by green buildings and limiting the full realization of their environmental and comfort value. Summary of the Invention

[0006] The purpose of this invention is to provide a green building environmental monitoring system, method, and storage medium to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides a method for monitoring the environmental conditions of green buildings, the method comprising:

[0008] Environmental parameters, including thermodynamic parameters, humidity parameters, and gas concentration parameters, are continuously collected by intelligent sensing nodes distributed in multiple locations inside the green building.

[0009] The environmental parameters are sent to the central processing unit, which generates environmental control commands using an adaptive learning algorithm based on pre-stored environmental standard values ​​and real-time data streams.

[0010] The environmental actuator performs environmental adjustment activities according to the environmental control command;

[0011] The execution sequence of the environmental regulation activities is monitored in real time, performance evaluation indicators are calculated, and performance status signals are generated based on the performance evaluation indicators. The performance status signals include normal signals and abnormal signals.

[0012] When the performance status signal is an abnormal signal, an alarm process is triggered.

[0013] Preferably, the process of calculating performance evaluation metrics and generating performance status signals based on the performance evaluation metrics includes:

[0014] By applying hierarchical performance analysis technology, the environmental regulation activities are divided into optimized activities or non-optimized activities;

[0015] The non-optimal ratio is obtained by calculating the ratio of the frequency of non-optimal activities to the total number of activities within a fixed monitoring period.

[0016] If the non-optimization ratio is greater than the preset non-optimization threshold, an abnormal signal is output.

[0017] If the non-optimization ratio is not greater than a preset non-optimization threshold, then measure the delay time and energy consumption offset of the environmental regulation activity;

[0018] The delay time and energy consumption offset are normalized and fused to obtain the overall performance score;

[0019] If the overall performance score exceeds the preset performance limit, an abnormal signal is output; otherwise, a normal signal is output.

[0020] Preferably, the process of applying hierarchical performance analysis technology to classify the environmental regulation activities into optimized or non-optimized activities includes:

[0021] The time point at which the central processing unit issues an environmental control command is recorded as the start time, and the time point at which the environmental execution device completes the environmental adjustment activity is recorded as the end time. The duration between the start time and the end time is defined as the monitoring interval.

[0022] The ratio of the environmental control command to the monitoring interval is used as the command efficiency index, and the activity fluctuation index is obtained through the stability test method.

[0023] If the command efficiency index is not within the predefined efficiency range or the activity fluctuation index is higher than the predefined fluctuation limit, the environmental regulation activity will be marked as a non-optimal activity.

[0024] If the command efficiency index is within the predefined efficiency range and the activity fluctuation index is not higher than the predefined fluctuation limit, then the environmental adjustment activity is marked as an optimized activity.

[0025] Preferably, the stability testing method includes the following steps:

[0026] A two-dimensional coordinate system was constructed using the time dimension and the numerical dimension of environmental parameters to obtain the trajectory of environmental parameter changes during environmental regulation activities.

[0027] Multiple sampling points are set on the trajectory of environmental parameter changes. The difference in environmental parameters between adjacent sampling points is recorded as the fluctuation amplitude. The standard deviation of all fluctuation amplitudes is calculated as the fluctuation coefficient, and the proportion of fluctuation amplitudes exceeding the predetermined fluctuation range is counted as the anomaly coefficient.

[0028] The activity volatility index is derived by a linear combination of the volatility coefficient and the anomaly coefficient.

[0029] Preferably, the method further includes: performing auxiliary anomaly detection when generating a normal signal, wherein the auxiliary anomaly detection process includes:

[0030] Vibration amplitude data and sound pressure level data are collected during the operation of the environmental actuator. If the vibration amplitude data or sound pressure level data exceeds their respective preset safety limits, the environmental actuator is determined to have a potential malfunction.

[0031] The duration of potential faults is accumulated within the monitoring period, and its ratio to the total operating time of the environmental actuators is calculated to obtain the fault time percentage.

[0032] The number of cases in which the number of consecutive occurrences of potential faults exceeds a predetermined number within a statistical monitoring period is counted as high-frequency faults.

[0033] Record the longest duration of a single potential fault within the monitoring period as the maximum fault duration;

[0034] The fault assessment value is obtained by weighted summation of the failure time percentage, high-frequency failure count, and maximum failure duration.

[0035] If the fault assessment value is greater than the preset fault threshold, an auxiliary abnormality indication is generated; if the fault assessment value is not greater than the preset fault threshold, an auxiliary normal indication is generated.

[0036] Preferably, the auxiliary anomaly detection process further includes:

[0037] When an auxiliary anomaly indication is generated, further equipment health diagnostics are performed. The equipment health diagnostic process includes:

[0038] Obtain the manufacturing date of the environmental actuator and calculate the difference between the current date and the manufacturing date to determine the equipment's service life;

[0039] Extract the cumulative operating time of the environmental actuators from the historical database to obtain the total operating time of the equipment;

[0040] High-risk exposure times of environmental actuators are obtained through environmental risk analysis;

[0041] The number of times the maintenance interval of the environmental actuator exceeds the standard maintenance interval is retrieved from the maintenance record and recorded as non-standard maintenance times.

[0042] The equipment health index is calculated using a multilayer sensor model by taking into account the equipment's service life, total operating time, high-risk exposure time, and number of non-standard maintenance operations.

[0043] If the device's health index is lower than the preset health standard, a device replacement recommendation will be generated.

[0044] Preferably, the environmental risk analysis process includes:

[0045] Collect ambient temperature and humidity values ​​at the installation location of the environmental actuator, calculate the absolute error between the ambient temperature value and the ideal temperature value as the temperature deviation, and calculate the absolute error between the ambient humidity value and the ideal humidity value as the humidity deviation.

[0046] The concentration of suspended particulate matter at the installation location of the environmental actuator is collected and used as the dust concentration value.

[0047] Input the temperature deviation, humidity deviation, and dust concentration values ​​into the risk assessment function, and output the environmental risk coefficient;

[0048] If the environmental risk coefficient is greater than the preset risk standard, the environmental actuator is identified as being in a high-risk environment, and the total time spent in the high-risk environment is accumulated as the high-risk exposure time.

[0049] Preferably, the process by which the central processing unit generates environmental control commands using an adaptive learning algorithm includes:

[0050] The difference between environmental parameters and pre-stored environmental standard values ​​is input into a neural network model. The neural network model generates environmental control commands based on training data and real-time trends. The environmental control commands include adjustment type and adjustment intensity.

[0051] The adjustment type corresponds to heating, cooling, humidifying, dehumidifying, or air purification operation, and the adjustment intensity is expressed as a percentage.

[0052] Preferably, the present invention also includes a green building environmental monitoring system, the system including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor, when executing the computer program, implements the steps of the green building environmental monitoring method described above.

[0053] Preferably, the present invention further includes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the various steps of the green building environmental monitoring method described above.

[0054] Compared with the prior art, the beneficial effects of the present invention are:

[0055] By installing intelligent sensor nodes at multiple locations within the green building, comprehensive environmental parameter collection was achieved. These distributed sensor nodes cover different functional areas and spatial locations within the building, avoiding the limitations of single-node monitoring and ensuring that the collected data accurately reflects the overall and local environmental conditions within the building. Simultaneously, the collected parameters encompass thermodynamic parameters, humidity parameters, and gas concentration parameters, comprehensively covering key indicators affecting indoor environmental quality and occupant comfort. This provides a rich and complete data foundation for subsequent environmental regulation, making environmental control more scientific.

[0056] The central processing unit uses an adaptive learning algorithm to generate environmental control commands, breaking the limitations of traditional fixed control logic. This algorithm can combine pre-stored environmental standard values ​​with real-time data streams to continuously optimize control strategies. It can flexibly respond to dynamic changes in the building's internal environment, whether it's personnel movement, equipment operation, or parameter changes caused by external environmental fluctuations. It can quickly respond and generate adjustment commands adapted to the current state, making environmental regulation more targeted and flexible, and effectively improving the accuracy of environmental regulation.

[0057] Environmental actuators carry out regulatory activities based on control commands, while simultaneously employing a design that incorporates real-time monitoring of the execution sequence. By tracking the execution sequence of regulatory activities in real time, the implementation process of regulatory measures can be clearly understood, the operating status of the actuators can be monitored, and regulatory failures due to actuator malfunctions or incomplete execution can be avoided. The calculation of performance evaluation indicators can objectively reflect the actual effectiveness of regulatory activities, promptly identify problems in the regulatory process, and provide direction for subsequent optimization of regulatory strategies and improvement of actuator operating status, ensuring that environmental regulation activities continue to operate at a high efficiency.

[0058] The performance status signal settings and alarm triggering mechanism enable rapid response to environmental anomalies. When performance evaluation indicators reflect poor adjustment effects or abnormal environmental parameters, an anomaly signal is generated promptly and an alarm is triggered, allowing relevant personnel to be aware of the problem immediately and facilitating rapid investigation and handling measures to prevent the abnormal state from spreading or prolonging. This timely early warning and alarm mechanism can minimize the impact of environmental anomalies on the health of residents, ensuring that the indoor environment is always in a safe and suitable state. Attached Figure Description

[0059] Figure 1 This is a schematic diagram illustrating the working principle of the green building environmental monitoring method described in this invention.

[0060] Figure 2 A flowchart for dividing environmental regulation activities;

[0061] Figure 3 Here is a flowchart of the stability testing method;

[0062] Figure 4 A bar chart comparing equipment failure assessment indicators;

[0063] Figure 5 Heat map of factors affecting equipment health. Detailed Implementation

[0064] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0065] Please see Figure 1This invention provides a method for environmental monitoring in green buildings. The method includes: continuously collecting environmental parameters, including thermodynamic parameters, humidity parameters, and gas concentration parameters, through intelligent sensor nodes distributed at multiple locations within the green building. The intelligent sensor nodes send the collected environmental parameters to a central processing unit. The central processing unit generates environmental control commands using an adaptive learning algorithm based on pre-stored environmental standard values ​​and real-time data streams. Environmental execution devices perform environmental adjustment activities according to the received environmental control commands. The system monitors the execution sequence of environmental adjustment activities in real time, calculates performance evaluation indicators, and generates performance status signals based on the performance evaluation indicators. The performance status signals include normal signals and abnormal signals. When the performance status signal is an abnormal signal, the system triggers an alarm process to notify relevant personnel to take action.

[0066] Example 1: See Figure 2 In practical implementation, the process of generating performance status signals begins with the classification of a series of environmental regulation activities. The system applies hierarchical performance analysis technology to divide each complete environmental regulation activity into optimized or non-optimized activities. Specifically, hierarchical performance analysis records the precise time point at which the central processing unit issues an environmental control command to the environmental execution device; this time point is defined as the start time. Simultaneously, the system records the time point at which the environmental execution device completely completes the environmental regulation activity required by the environmental control command; this time point is defined as the end time. The time length between the start time and the end time is explicitly defined as the monitoring interval, which characterizes the total time consumed from the issuance of the command to the complete completion of a single environmental regulation activity.

[0067] In practical implementation, the classification process requires calculating two key indicators. The system defines the ratio of the adjustment intensity inherent in the environmental control command itself to the monitoring interval as the command efficiency index, which reflects the execution effectiveness of environmental control activities per unit time. The system obtains another indicator in parallel through a stability test method: the activity fluctuation index. The specific operation of the stability test method involves constructing a two-dimensional coordinate system based on the time dimension and the environmental parameter value dimension. Based on this, the actual change trajectory of relevant environmental parameters during the environmental control activity from start to finish is obtained. On the environmental parameter change trajectory, the system sets multiple sampling points at fixed or adaptive intervals, calculates the difference in environmental parameter values ​​between adjacent sampling points, and records this difference as the fluctuation amplitude. The system calculates the standard deviation of all fluctuation amplitudes and defines this standard deviation as the fluctuation coefficient. Simultaneously, the system statistically analyzes the proportion of fluctuation amplitudes whose absolute value exceeds a predetermined fluctuation range, defining this proportion as the anomaly coefficient. Finally, the activity fluctuation index is derived through a linear combination of the fluctuation coefficient and the anomaly coefficient, with the weighting coefficient of the linear combination being a pre-set fixed value.

[0068] In practice, after calculating the command efficiency index and activity fluctuation index, the system executes classification and judgment logic. The system internally stores a predefined efficiency range and a predefined fluctuation upper limit. If the calculated command efficiency index value is outside the predefined efficiency range, or the calculated activity fluctuation index value is higher than the predefined fluctuation upper limit, the system marks the current environmental adjustment activity as a non-optimal activity. Conversely, if the command efficiency index value is within the predefined efficiency range and the activity fluctuation index value is not higher than the predefined fluctuation upper limit, the system marks the current environmental adjustment activity as an optimized activity. Each environmental adjustment activity receives a clear classification label.

[0069] In some embodiments, the system performs an overall performance evaluation within a fixed monitoring period. This fixed monitoring period can be set to 24 hours or one week. Within this fixed monitoring period, the system counts the frequency of all environmental control activities marked as non-optimal activities and calculates the ratio of the frequency of non-optimal activities to the total number of environmental control activities within the fixed monitoring period. This ratio is defined as the non-optimal ratio. The non-optimal ratio quantitatively describes the proportion of activities that result in poor system environmental control performance within the fixed monitoring period.

[0070] In some embodiments, the system compares the calculated non-optimization ratio with a preset non-optimization threshold. The preset non-optimization threshold is a threshold pre-set according to system reliability requirements. If the non-optimization ratio is greater than the preset non-optimization threshold, the system directly determines that the overall performance is poor and immediately outputs an abnormal signal. If the non-optimization ratio is not greater than the preset non-optimization threshold, it indicates that most activities are normal, but the system needs to further analyze the quality of qualified activities, at which point the performance evaluation enters a more refined stage.

[0071] Optionally, if the non-optimization ratio is acceptable, the system will measure two more granular performance metrics for all environmental control activities marked as optimized activities within a fixed monitoring period. The first metric is latency, which refers to the time interval between the environmental actuator receiving the environmental control command from the central processing unit and actually starting to execute the action. The second metric is energy consumption offset, which is the absolute difference between the actual energy consumption of the environmental actuator in completing a single environmental control activity and the expected energy consumption calculated based on historical data or models.

[0072] Optionally, the system needs to standardize the measured delay time and energy consumption offsets to eliminate the influence of dimensions. The system employs a normalization method, mapping the delay time and energy consumption offsets to a numerical range of zero to one. After normalization, the system uses a weighted fusion algorithm to combine the normalized delay time and energy consumption offset values ​​into a single numerical index, called the overall performance score. The weights assigned to the delay time and energy consumption offsets in the weighted fusion algorithm are pre-set based on their importance to the overall system performance.

[0073] Understandably, after obtaining the overall performance score, the system compares it to a preset performance threshold. This threshold is used to distinguish between excellent performance and critical performance. If the overall performance score exceeds the preset threshold, it indicates observable degradation in execution efficiency or energy consumption control, even in environments categorized as optimization activities, and the system outputs an abnormal signal. If the overall performance score does not exceed the preset threshold, it indicates that the system is currently operating well, and the system outputs a normal signal.

[0074] The entire performance evaluation process is understandably structured as a hierarchical evaluation framework. It begins with an initial screening based on the non-optimized ratio, followed by a deeper evaluation of optimization activities. This hierarchical performance analysis technique ensures a comprehensive and efficient assessment of system performance, enabling the timely detection of even minor performance degradation trends and providing a data foundation for preventative maintenance. The entire process is fully automated, requiring no manual intervention. The evaluation results are output as performance status signals, directly determining whether to trigger subsequent alarm procedures.

[0075] Example 2: See Figure 3 The stability verification method begins with the construction of the data space. The system constructs a two-dimensional coordinate system with time and environmental parameter numerical dimensions. The time dimension is expressed in standard time units, covering the entire duration from the start to the end of the environmental control activity. The environmental parameter numerical dimension depends on the specific monitoring object and can be physical quantities such as temperature, humidity, or specific gas concentration. In this two-dimensional coordinate system, the system plots the trajectory of the continuous changes in the monitored environmental parameters from the start to the end of the environmental control activity. This trajectory consists of a series of data points arranged in chronological order, with each data point containing a timestamp and a corresponding environmental parameter sample value.

[0076] In practical implementation, after acquiring the trajectory of environmental parameter changes, the system sets multiple sampling points along the time axis on this trajectory. The sampling point setting strategy can employ equal time intervals or an adaptive interval approach based on the severity of environmental parameter changes, setting sparser sampling points in areas of gentle change and denser sampling points in areas of rapid change. The system calculates the difference in environmental parameter values ​​between adjacent sampling points and defines this difference as the fluctuation amplitude. The fluctuation amplitude is a positive or negative value; a positive value indicates an increase in environmental parameters, and a negative value indicates a decrease. Its absolute value reflects the severity of environmental parameter changes between adjacent sampling times.

[0077] In its implementation, the system performs two independent statistical analyses based on the calculated numerical sequences of all fluctuation amplitudes. The first analysis calculates the standard deviation of all fluctuation amplitudes, defined as the fluctuation coefficient. The fluctuation coefficient is a dimensionless statistic that quantifies the dispersion of the rate of change of environmental parameters throughout the entire environmental regulation activity; a high fluctuation coefficient indicates that the environmental parameters are highly unstable, sometimes drastic and sometimes slow. The second analysis sets a predetermined fluctuation range, a numerical range pre-defined based on historical normal data and environmental control precision requirements. The system then calculates the proportion of fluctuation amplitudes whose absolute values ​​exceed the predetermined fluctuation range out of the total number of fluctuation amplitudes; this proportion is defined as the anomaly coefficient. The anomaly coefficient directly reflects the frequency of abnormally drastic fluctuations during the change of environmental parameters.

[0078] In some embodiments, the predetermined fluctuation range is set based on multiple factors. The lower and upper limits of the predetermined fluctuation range are derived from the analysis of long-term historical data of green buildings under stable operating conditions, typically taking the average of the normal fluctuation range plus a certain number of standard deviations. For different environmental parameters, such as temperature, humidity, and carbon dioxide concentration, the numerical range of the predetermined fluctuation range is different. The system maintains an independent predetermined fluctuation range parameter table for each monitored environmental parameter, and calls the corresponding parameter values ​​for calculation during stability testing.

[0079] In some embodiments, after calculating the volatility coefficient and the anomaly coefficient, the system merges the volatility coefficient and the anomaly coefficient into a single index, namely the active volatility index, using a linear combination formula. The linear combination formula is expressed as: the active volatility index equals weight A multiplied by the volatility coefficient, plus weight B multiplied by the anomaly coefficient. Weights A and B are pre-set fixed coefficients. The values ​​of weights A and B are determined by analyzing the impact of the volatility coefficient and the anomaly coefficient on system stability in historical data. The sum of weights A and B is not necessarily 1; the key is that weights A and B can reasonably reflect the relative importance of the volatility coefficient and the anomaly coefficient in the overall instability assessment.

[0080] Optionally, the calculation process for the activity volatility index also includes a standardization step. Since the volatility coefficient and the anomaly coefficient may have different orders of magnitude, a direct linear combination could lead to one dominating. Therefore, before combination, the system normalizes the volatility coefficient and the anomaly coefficient separately, mapping them to a comparable numerical scale between zero and one, and then applies weights A and B for linear combination to ensure the fairness and accuracy of the activity volatility index.

[0081] Optionally, the activity fluctuation index, once calculated, is primarily used for subsequent classification of environmental control activities. As a quantitative indicator measuring the stability of a single environmental control process, the activity fluctuation index, along with the command efficiency index, is used to determine whether the activity should be classified as optimized or non-optimized. A high activity fluctuation index indicates that the environmental parameter control process is accompanied by significant fluctuations or abnormal jumps, which usually signifies interference in the execution process or a decline in equipment performance.

[0082] Understandably, the core of stability testing methods lies in transforming continuous environmental parameter variation curves into quantifiable stability indicators. By calculating the fluctuation coefficient and anomaly coefficient, the method assesses the stationarity of the regulation process from two dimensions: the consistency of change and the probability of outliers. This method does not rely on a single statistic and can more comprehensively capture the unstable characteristics in the change trajectory, providing a crucial basis for accurately assessing the performance status of environmental actuators.

[0083] Understandably, stability testing methods are a crucial component of the entire hierarchical performance analysis technique. The activity fluctuation index and command efficiency index complement each other; one focuses on the efficiency of the regulation process, and the other on its stability, together forming the basis for a comprehensive evaluation of the quality of environmental regulation activities. This data-driven approach can effectively identify non-optimal activities that, while ultimately achieving the regulation goals, have inherent process problems, thus improving the sensitivity of system fault early warning.

[0084] Example 3: In specific implementation, the auxiliary anomaly detection process is initiated after the system generates a normal signal, serving as a redundant safety verification mechanism. The core of auxiliary anomaly detection lies in monitoring the operating status of the environmental actuator itself, rather than the adjustment effect of environmental parameters. The system continuously collects vibration amplitude data and sound pressure level data through dedicated sensors installed on or near the environmental actuator. Vibration amplitude data is acquired by an accelerometer, characterizing the vibration intensity of the mechanical components of the environmental actuator during operation; sound pressure level data is acquired by a microphone sensor, quantifying the sound pressure level of the noise generated by the environmental actuator during operation. These data are collected in real time at a high frequency and transmitted to the processing unit.

[0085] In practice, the system compares the real-time collected vibration amplitude and sound pressure level data with preset safety limits. These preset safety limits are thresholds pre-set based on the model and specifications of the environmental actuator and baseline data collected during long-term normal operation. For vibration amplitude data, there is a preset vibration safety limit; for sound pressure level data, there is a preset sound pressure safety limit. Throughout the entire operation of the environmental actuator, the system continuously monitors it: if the collected vibration amplitude data exceeds the preset vibration safety limit, or the collected sound pressure level data exceeds the preset sound pressure safety limit, the system immediately determines that the environmental actuator has a potential fault at that moment. A potential fault is a status indicator, suggesting that the equipment may be in an unhealthy operating state.

[0086] In some embodiments, the system continuously tracks potential faults throughout a complete monitoring cycle. The monitoring cycle is a fixed time period, such as 24 hours. The system accumulates the total duration of all states marked as potential faults within this monitoring cycle. Simultaneously, the system records the total operating time of the environmental actuators within the same monitoring cycle. The system calculates the ratio of the cumulative duration of potential faults to the total operating time of the environmental actuators, defining this ratio as the fault time percentage. The fault time percentage reflects the proportion of time the equipment is in an abnormal operating state.

[0087] In some embodiments, the system also statistically analyzes the clustering of potential faults within a monitoring period. The system sets a predetermined number of occurrences, such as detecting a potential fault in three consecutive sampling periods. The system scans the time-series data throughout the monitoring period and counts the number of cases where the number of consecutive occurrences of a potential fault exceeds the predetermined number. This number of cases is defined as the high-frequency fault count. The high-frequency fault count reveals that faults do not occur randomly or in isolation, but rather exhibit continuous and clustered characteristics, which may indicate a persistent equipment defect or external interference.

[0088] In some embodiments, the system also records the longest duration of a single potential fault event within the monitoring period. Specifically, the start and end points of each potential fault event are identified from the time-series data, the duration of each potential fault event is calculated, and then the longest duration among all potential fault events is identified and defined as the maximum fault duration. The maximum fault duration reflects the duration of the most severe abnormal state.

[0089] Optionally, after obtaining the three indicators—failure time percentage, high-frequency failure count, and maximum failure duration—the system calculates a comprehensive failure assessment value using a weighted summation model. The weighted summation model is expressed as:

[0090]

[0091] In this model, This represents the calculated fault assessment value. This represents the percentage of time spent in the downtime. It is the weight assigned to the percentage of downtime. Represents high-frequency fault count, It is the weight assigned to the high-frequency fault count. Represents the maximum downtime. These are the weights assigned to the longest possible failure time. , and These are constants and weights pre-set based on historical fault data analysis and expert experience. , and The values ​​reflect the differences in importance of the three indicators to the overall failure assessment.

[0092] In practice, after calculating the fault assessment value, the system compares it with a preset fault threshold. The preset fault threshold is a key criterion used to distinguish between normal and abnormal redundant signals. If the fault assessment value is greater than the preset fault threshold, it indicates that although the main performance evaluation indicators are normal, there is a significant risk to the equipment's physical condition, and the system generates an auxiliary anomaly indication. If the fault assessment value is not greater than the preset fault threshold, it indicates that the equipment's physical condition is basically normal, and the system generates an auxiliary normal indication. The auxiliary anomaly indication and the auxiliary normal indication constitute the output of the auxiliary anomaly detection.

[0093] Understandably, the auxiliary anomaly detection process is independent of the main evaluation process based on environmental regulation activity performance, providing a second layer of protection from the perspective of the equipment's physical condition. This redundant design enhances the system's reliability, enabling it to detect potential problems through the abnormal characteristics of the equipment itself when the main process fails to issue an alarm in a timely manner for some reason, thereby achieving earlier warning and intervention.

[0094] It is understandable that monitoring vibration and noise in the auxiliary anomaly detection process directly reflects the mechanical health status of the environmental actuator. The three indicators of failure time percentage, high-frequency failure count, and maximum failure duration are characterized from three dimensions: the total percentage of abnormal states, the clustering of occurrences, and the severity of individual failures, respectively. Then, a comprehensive evaluation value is obtained through weighted fusion. This method can capture early signs of equipment degradation more comprehensively and sensitively.

[0095] See Figure 4This chart, focusing on the auxiliary anomaly detection needs of green building environmental monitoring systems, uses equipment number as the horizontal axis and standardized values ​​as the vertical axis to quantify the fault characteristics of different environmental actuators from three dimensions: fault time percentage, high-frequency fault count, and maximum fault duration. This chart is a visual representation of the auxiliary anomaly detection process. Through the bar chart distribution of multiple indicators, it intuitively distinguishes the severity and characteristic differences of equipment faults, providing data support for the decision to generate auxiliary anomaly indications when the fault assessment value exceeds a preset threshold. It helps maintenance personnel quickly identify high-risk fault equipment, achieving efficient conversion from fault data to anomaly warnings. It is a direct presentation of the multi-dimensional quantitative fault characteristic technology solution in auxiliary anomaly detection.

[0096] Example 4: In specific implementation, when the auxiliary anomaly detection process generates an auxiliary anomaly indication, the system automatically triggers a deeper equipment health diagnosis process. This process aims to assess the health status of the environmental actuator from multiple dimensions and generate maintenance decisions. The equipment health diagnosis process first requires collecting several basic data points from the environmental actuator. The system obtains the manufacturing date of the environmental actuator, which is typically stored in the equipment file or electronic tag. The system calculates the difference between the current date and the manufacturing date of the environmental actuator. This difference is defined as the equipment's service life, expressed in days or years, quantifying the length of time the environmental actuator has been in use.

[0097] In its implementation, the system extracts the cumulative operating time of the environmental actuators from a dedicated historical database. This database continuously records the start-up and shutdown times of each actuator. The cumulative operating time is the sum of all operating periods and is defined as the total operating time, expressed in hours, reflecting the actual mechanical wear and tear of the environmental actuators. The system uses an environmental risk analysis process to determine the high-risk exposure time of the environmental actuators. This process includes collecting ambient temperature and humidity values ​​at the actuator's installation location, continuously monitored by intelligent sensor nodes deployed near the actuators. The system calculates the absolute error between the ambient temperature and a preset ideal temperature, defining this as the temperature deviation; it also calculates the absolute error between the ambient humidity and a preset ideal humidity, defining this as the humidity deviation. Simultaneously, the system collects the concentration of suspended particulate matter at the actuator's installation location, defining this as the dust concentration. The system inputs the temperature deviation, humidity deviation, and dust concentration into a preset risk assessment function, which outputs a quantified environmental risk coefficient. See Table 1 for the correspondence between the environmental risk coefficient and the risk level.

[0098] Table 1: Correspondence between Environmental Risk Coefficient and Risk Level

[0099] Environmental risk coefficient range Risk level Should high-risk exposure time be included? 0.0-0.3 Low risk no 0.3-0.7 Medium risk no 0.7-1.0 High risk yes

[0100] If the environmental risk coefficient is greater than 0.7, the system will determine that the environmental actuator is currently in a high-risk environment and begin to accumulate the total time that the environmental actuator has been in a high-risk environment. This accumulated total time is defined as the high-risk exposure time, which reflects the history of the environmental actuator operating under harsh conditions.

[0101] In practice, the system also needs to query the historical maintenance information of the environmental actuator from the maintenance record database, which records the execution date of each maintenance. The system compares the actual time interval between two consecutive maintenance sessions with the standard maintenance interval recommended by the environmental actuator manufacturer. If the actual maintenance interval exceeds the standard maintenance interval, it is recorded as a non-standard maintenance event. The system counts the total number of non-standard maintenance events that occur throughout the entire lifecycle of the environmental actuator, defining this total number as the non-standard maintenance count. The non-standard maintenance count reflects the timeliness and standardization of preventive maintenance work.

[0102] In some embodiments, the core of the equipment health diagnosis process is calculating a comprehensive equipment health index. The system uses collected data on equipment service age, total equipment runtime, high-risk exposure time, and non-standard maintenance frequency as input features, feeding them into a pre-trained multilayer perceptron model. The multilayer perceptron model is an artificial neural network whose structure includes an input layer, at least one hidden layer, and an output layer. The input layer contains four neurons, corresponding to the four input features: equipment service age, total equipment runtime, high-risk exposure time, and non-standard maintenance frequency. The hidden layer contains multiple neurons, each performing a weighted sum of the input values ​​and applying a non-linear activation function. The output layer contains one neuron whose output value, after activation by a sigmoid function, is mapped to a value between 0 and 1; this value is the equipment health index. The closer the equipment health index is to 1, the better the health of the environmental actuator; the closer the equipment health index is to 0, the worse the health of the environmental actuator.

[0103] Optionally, the final step in the equipment health diagnosis process is to make a decision based on the equipment health index. The system has a preset equipment health standard value, a threshold between 0 and 1. The system compares the calculated equipment health index with this preset health standard value. If the equipment health index is lower than the preset health standard value, it indicates that the health status of the environmental actuator has deteriorated to a level requiring close monitoring, and the system automatically generates a device replacement recommendation. This recommendation may include information such as the equipment identifier, current health index, and assessment time, and is displayed through a human-machine interface or sent to maintenance personnel. If the equipment health index is not lower than the preset health standard value, the process ends, and no recommendation is generated.

[0104] Optionally, the training process for the multilayer perceptron model is offline. The training process requires a large amount of historical data, including feature data such as the service life of numerous environmental actuators, total equipment runtime, high-risk exposure time, and number of non-standard maintenance operations, as well as label data indicating whether these devices were ultimately scrapped normally or replaced prematurely due to malfunctions. Through optimization methods such as backpropagation, the weights and bias parameters in the multilayer perceptron model are continuously adjusted to ensure that the predicted output of the multilayer perceptron model is as close as possible to the true labels, thereby enabling the multilayer perceptron model to learn the ability to predict the health status of devices from input features.

[0105] It is understandable that the equipment health diagnostic process comprehensively considers information from multiple dimensions, including the usage time, workload, environmental severity, and maintenance history of the environmental actuators. Through nonlinear fusion using a neural network model, it can more comprehensively and accurately assess the equipment's potential remaining lifespan and health status. This data-driven predictive diagnostic helps shift maintenance strategies from reactive to proactive, avoiding losses caused by unexpected failures. The generated equipment replacement recommendations provide quantitative data support for maintenance decisions.

[0106] See Figure 5 This heatmap, designed to address the health diagnostic needs of environmental actuators in a green building environmental monitoring system, quantifies the health impact of six devices across four dimensions: service life, total runtime, high-risk exposure time, and number of non-standard maintenance operations. The vertical axis lists devices 1 through 6, while the horizontal axis corresponds to the four core influencing factors. Through multi-dimensional heat distribution, the map provides an intuitive and quantitative analytical tool for device health diagnostics: it can quickly identify high-risk and low-risk devices, pinpoint key influencing factors for each device, and assist maintenance personnel in developing targeted maintenance or replacement strategies. It is a visual representation of the technical solution for device health diagnostics based on a comprehensive analysis of service life, total runtime, high-risk exposure time, and number of non-standard maintenance operations, achieving efficient transformation from multi-dimensional data to decision-making support.

[0107] Example 5: The process by which the central processing unit (CPU) generates environmental control commands using an adaptive learning algorithm is a closed-loop control process that makes decisions based on real-time data and predetermined standards. The CPU continuously receives environmental parameters uploaded from intelligent sensor nodes distributed across multiple locations within the green building. These parameters include thermodynamic parameters, humidity parameters, and gas concentration parameters. The CPU pre-stores environmental standard values ​​corresponding to different regions and time periods, such as a comfortable room temperature range, an ideal humidity level, and a safe upper limit for carbon dioxide concentration. The first step in generating environmental control commands is to calculate the difference. The system compares the real-time collected environmental parameters with the pre-stored environmental standard values ​​to calculate the difference between the environmental parameters and the pre-stored environmental standard values. The difference can be a simple arithmetic difference, such as the difference between the current temperature and the target temperature, or it can be a relative difference or a standardized deviation value.

[0108] In practice, the calculated variance is fed as the primary input feature into a pre-trained neural network model. A neural network model is a mathematical model that simulates the connection patterns of neurons in the human brain. This specific neural network model operates based on two key pieces of information: training data from a historical dataset containing numerous successful past cases of environmental regulation, recording various environmental parameter deviations and their corresponding, validated environmental control commands; and real-time trends, obtained through real-time analysis of recent time-series environmental parameter data, such as whether environmental parameters are in an upward, downward, or stable state. The neural network model uses its multi-layered network structure to perform nonlinear transformations and feature extraction on the input variance and real-time trends, ultimately generating specific environmental control command parameters at the output layer.

[0109] In practical implementation, the environmental control commands output by the neural network model contain two core elements: adjustment type and adjustment intensity. The adjustment type specifies the essential category of the environmental adjustment operation to be performed, corresponding to basic operations such as heating, cooling, humidifying, dehumidifying, or air purification. The selection of the adjustment type is directly determined by the sign of the input difference and the type of environmental parameter being targeted; for example, if the temperature difference is negative (i.e., the current temperature is lower than the standard temperature), the adjustment type is heating; if the humidity difference is positive (i.e., the current humidity is higher than the standard humidity), the adjustment type is dehumidifying. The adjustment intensity quantifies the strength of the environmental adjustment operation, expressed as a percentage scale, continuously varying from 0% to 100%, where 0% represents no adjustment and 100% represents adjustment at the maximum capacity of the environmental actuator. The specific value of the adjustment intensity is determined by factors such as the absolute value of the difference and the slope of the real-time trend; generally, the larger the absolute value of the difference, the higher the required percentage of adjustment intensity.

[0110] In some embodiments, the neural network model is designed with an input layer, several hidden layers, and an output layer. The number of neurons in the input layer matches the number of input features, which include at least the variance of each environmental parameter. The hidden layers can be one or more, each containing multiple neurons. Each neuron performs a weighted summation of all its inputs and applies a non-linear activation function, such as ReLU or Sigmoid. The number of neurons in the output layer corresponds to the number of control parameters to be generated. For example, the output layer can have two neurons: one neuron's output is processed by a softmax function and mapped to discrete categories representing different modulation types, while the other neuron's output is mapped to a range of 0% to 100% to represent the modulation strength.

[0111] In some embodiments, the training process of the neural network model is crucial. The training process uses a historical dataset containing a large number of labeled samples. Each sample includes a set of input conditions (e.g., historical environmental parameter variations, historical trend data) and a set of desired outputs (i.e., the optimal environmental control commands taken under those input conditions in historical records, including the correct adjustment type and intensity). The training algorithm (e.g., backpropagation) iteratively adjusts the connection weights and biases between neurons in the neural network model to minimize the error (loss function) between the model's predicted output and the desired output for the training samples. Through sufficient training, the neural network model can learn the mapping relationship from complex environmental states to optimal control actions.

[0112] Optionally, a key characteristic of adaptive learning algorithms is the ability to fine-tune the model online. In addition to offline training on historical data, the system can also make small adjustments to the parameters of the neural network model based on real-time control feedback. For example, if an environmental control command causes environmental parameters to approach the standard value too quickly and excessively (overshoot), the system may record this unsatisfactory control and use this data as a new training sample. This data will then be used to optimize the weights in the next model parameter update, resulting in smoother generated commands. This demonstrates the algorithm's adaptive capability.

[0113] Optionally, the frequency of environmental control command generation can be set as needed. The system can be set to generate commands on a timed basis, such as calculating the difference and generating a command every five minutes; or it can be set to be event-driven, meaning that when the difference of a certain environmental parameter exceeds a specific threshold, the neural network model is immediately triggered to calculate and generate a new environmental control command. This flexible triggering mechanism ensures the timeliness of control.

[0114] Optionally, for complex situations where multiple environmental parameters simultaneously exceed standards and require adjustment, the neural network model needs to possess multi-objective decision-making capabilities. For example, when both temperature and humidity deviate from standard values, the neural network model needs to consider all factors comprehensively, and its output may be a combined command that includes both a judgment on the type of adjustment (e.g., prioritizing cooling or dehumidification) and an allocation of adjustment intensity for coordinating the work of multiple environmental actuators. This requires that the training data include cases of such complex scenarios, and that the neural network model has a sufficiently complex structure to learn these advanced strategies.

[0115] It is understandable that the central processing unit's use of adaptive learning algorithms to generate environmental control commands upgrades traditional rule-based controllers into intelligent decision-making centers with learning and adaptability. By processing the differences between environmental parameters and standard values ​​through neural network models and comprehensively considering real-time trends, the system can generate more accurate and efficient environmental control commands. This ensures environmental comfort while optimizing energy consumption and improving the overall intelligent operation level of green buildings. This approach enables environmental control systems to better cope with uncertainties such as changes in building usage patterns and external weather interference.

[0116] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring the environment of green buildings, characterized in that, The method includes: Environmental parameters, including thermodynamic parameters, humidity parameters, and gas concentration parameters, are continuously collected by intelligent sensing nodes distributed in multiple locations inside the green building. The environmental parameters are sent to the central processing unit, which generates environmental control commands using an adaptive learning algorithm based on pre-stored environmental standard values ​​and real-time data streams. The environmental actuator performs environmental adjustment activities according to the environmental control command; The process includes real-time monitoring of the execution sequence of the environmental regulation activities, calculation of performance evaluation indicators, and generation of performance status signals based on the performance evaluation indicators. Using hierarchical performance analysis technology, the environmental regulation activities are divided into optimized activities or non-optimized activities. Within a fixed monitoring period, the ratio of the frequency of non-optimized activities to the total number of activities is calculated to obtain the non-optimized ratio. If the non-optimized ratio is greater than a preset non-optimized threshold, an abnormal signal is output. If the non-optimized ratio is not greater than the preset non-optimized threshold, the delay time and energy consumption offset of the environmental regulation activities are measured. The delay time is the time interval between the environmental actuator receiving the environmental control command from the central processing unit and actually starting to execute the action. The energy consumption offset is the absolute difference between the actual energy consumption of the environmental actuator in completing a single environmental regulation activity and the expected energy consumption calculated based on historical data or models. The delay time and energy consumption offset are normalized and fused to obtain an overall performance score. If the overall performance score exceeds a preset performance limit, an abnormal signal is output; otherwise, a normal signal is output. The performance status signal includes both normal and abnormal signals. When the performance status signal is an abnormal signal, an alarm process is triggered; The process of using hierarchical performance analysis technology to classify environmental regulation activities into optimized or non-optimized activities includes: The time point when the central processing unit issues the environmental control command is recorded as the start time, and the time point when the environmental execution device completes the environmental adjustment activity is recorded as the end time. The duration between the start time and the end time is defined as the monitoring interval. The ratio of the environmental control command to the monitoring interval is used as the command efficiency index, and the activity fluctuation index is obtained through a stability test method. The process of the stability test method includes: A two-dimensional coordinate system is constructed using the time dimension and the environmental parameter numerical dimension to obtain the trajectory of environmental parameter changes during the environmental regulation activity. Multiple sampling points are set on the trajectory of environmental parameter changes, and the difference in environmental parameters between adjacent sampling points is recorded as the fluctuation amplitude. The standard deviation of all fluctuation amplitudes is calculated as the fluctuation coefficient, and the proportion of fluctuation amplitudes exceeding the predetermined fluctuation range is counted as the anomaly coefficient. The activity fluctuation index is derived by linear combination of the fluctuation coefficient and the anomaly coefficient. If the command efficiency index is not within the predefined efficiency range or the activity fluctuation index is higher than the predefined fluctuation upper limit, the environmental regulation activity is marked as a non-optimal activity. If the command efficiency index is within the predefined efficiency range and the activity fluctuation index is not higher than the predefined fluctuation upper limit, the environmental regulation activity is marked as an optimized activity.

2. The green building environmental monitoring method as described in claim 1, characterized in that, The method further includes: performing auxiliary anomaly detection when a normal signal is generated, wherein the auxiliary anomaly detection process includes: Vibration amplitude data and sound pressure level data are collected during the operation of the environmental actuator. If the vibration amplitude data or sound pressure level data exceeds their respective preset safety limits, the environmental actuator is determined to have a potential malfunction. The duration of potential faults is accumulated within the monitoring period, and its ratio to the total operating time of the environmental actuators is calculated to obtain the fault time percentage. The number of cases in which the number of consecutive occurrences of potential faults exceeds a predetermined number within a statistical monitoring period is counted as high-frequency faults. Record the longest duration of a single potential fault within the monitoring period as the maximum fault duration; The fault assessment value is obtained by weighted summation of the failure time percentage, high-frequency failure count, and maximum failure duration. If the fault assessment value is greater than the preset fault threshold, an auxiliary abnormality indication is generated; if the fault assessment value is not greater than the preset fault threshold, an auxiliary normal indication is generated.

3. The green building environmental monitoring method as described in claim 2, characterized in that, The auxiliary anomaly detection process also includes: When an auxiliary anomaly indication is generated, further equipment health diagnostics are performed. The equipment health diagnostic process includes: Obtain the manufacturing date of the environmental actuator and calculate the difference between the current date and the manufacturing date to determine the equipment's service life; Extract the cumulative operating time of the environmental actuators from the historical database to obtain the total operating time of the equipment; High-risk exposure times of environmental actuators are obtained through environmental risk analysis; The number of times the maintenance interval of the environmental actuator exceeds the standard maintenance interval is retrieved from the maintenance record and recorded as non-standard maintenance times. The equipment health index is calculated using a multilayer sensor model by taking into account the equipment's service life, total operating time, high-risk exposure time, and number of non-standard maintenance operations. If the device's health index is lower than the preset health standard, a device replacement recommendation will be generated.

4. The green building environmental monitoring method as described in claim 3, characterized in that, The environmental risk analysis process includes: Collect ambient temperature and humidity values ​​at the installation location of the environmental actuator, calculate the absolute error between the ambient temperature value and the ideal temperature value as the temperature deviation, and calculate the absolute error between the ambient humidity value and the ideal humidity value as the humidity deviation. The concentration of suspended particulate matter at the installation location of the environmental actuator is collected and used as the dust concentration value. Input the temperature deviation, humidity deviation, and dust concentration values ​​into the risk assessment function, and output the environmental risk coefficient; If the environmental risk coefficient is greater than the preset risk standard, the environmental actuator is identified as being in a high-risk environment, and the total time spent in the high-risk environment is accumulated as the high-risk exposure time.

5. The green building environmental monitoring method as described in claim 1, characterized in that, The process by which the central processing unit generates environment control commands using an adaptive learning algorithm includes: The difference between environmental parameters and pre-stored environmental standard values ​​is input into a neural network model. The neural network model generates environmental control commands based on training data and real-time trends. The environmental control commands include adjustment type and adjustment intensity. The adjustment type corresponds to heating, cooling, humidifying, dehumidifying, or air purification operation, and the adjustment intensity is expressed as a percentage.

6. A green building environmental monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the green building environmental monitoring method according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements each step of the green building environmental monitoring method as described in any one of claims 1 to 5.

Images