Intelligent building weak current control method based on intelligent networking

Abstract

The application relates to the technical field of weak current control, in particular to a weak current control method for intelligent buildings based on intelligent networking, which comprises the following steps: collecting the running state data of a plurality of weak current equipment in a building, sequentially performing pretreatment and feature extraction on the running state data, and transmitting the state features to a cloud platform through the Internet of Things; training an initial model, performing state analysis on the running state data, and regulating and controlling the weak current equipment based on the analysis result; acquiring the effective proportion of the running state data and the number of abnormal jumps of the running state data in a unit time to determine whether the collection accuracy of the running state data meets the requirements; acquiring the response delay length of the regulation and control instruction to determine whether the real-time performance of the weak current regulation and control meets the requirements; determining whether to increase the steady-state trend pre-intervention depth of the weak current equipment; and acquiring the regulation and control oscillation rate of the weak current equipment to determine the coupling influence coefficient of the weak current equipment regulation and control; and the application improves the stability of weak current control.

Description

Technical Field

[0001] This invention relates to the field of low-voltage control technology, and in particular to a smart building low-voltage control method based on intelligent network connectivity. Background Technology

[0002] In existing technologies, building low-voltage control generally adopts a distributed architecture, with the building automation system as the core. Through the independent deployment and local control of subsystems, it realizes the automated management of building electromechanical equipment. However, there are problems such as a lack of interoperability and collaborative linkage between devices, multiple devices making independent decisions, and energy collision when the directions are opposite, resulting in ineffective regulation and operational oscillation. It also lacks the ability to adapt to environmental disturbances and personnel dynamics in real time, which limits the control accuracy and real-time performance, and makes it difficult to meet the stability requirements of low-voltage control.

[0003] Chinese Patent Publication Application No. CN120995325A discloses a low-voltage intelligent building control and management system, comprising: sensors: multiple sets of sensors are installed inside the building to monitor internal environmental parameters; a data collection module: the data collection module is electrically connected to the multiple sets of sensors, and is used to collect data collected by the sensors and convert environmental parameter data; a data storage module: the data storage module is used to store historical data of the sensors in the data collection module, and to build a blockchain network in the data storage module to store different data collected by multiple sensors in the blockchain network using corresponding storage nodes; a data comparison and elimination module: the historical data in the data storage module is compared with the environmental parameter data collected by the sensors, and the accuracy of the environmental parameter data collected by the sensors is determined by cross-validation, and erroneous data from the sensors is eliminated; an emergency management module: the emergency management module is used to manage abnormal data from the sensors. When the emergency management module receives sensor data exceeding a set threshold, it is defined as abnormal data, and an alarm is triggered by the communication module when the emergency management module receives abnormal data; and a control center: the control center is connected to the emergency management module and interacts with building equipment. It is evident that the aforementioned intelligent building control and management system for low-voltage electrical systems suffers from several problems. Due to the lack of electromagnetic noise filtering and timing deviation calibration for the data collected by sensors, it is difficult to accurately identify data distortion by simply comparing historical data. Furthermore, the system lacks steady-state constraints and pre-intervention adjustment mechanisms for the control behavior of low-voltage electrical equipment, leading to a decline in the stability of low-voltage electrical control. Summary of the Invention

[0004] To address this, the present invention provides an intelligent building low-voltage control method based on intelligent network connectivity, which overcomes the problems in the prior art where electromagnetic noise filtering and timing deviation calibration are not performed on the data collected by sensors, making it difficult to accurately identify data distortion by simply comparing historical data, and lacking steady-state constraints and pre-intervention adjustment mechanisms for the control behavior of low-voltage equipment, resulting in decreased stability of low-voltage control.

[0005] To achieve the above objectives, the present invention provides a smart building low-voltage control method based on intelligent network connectivity, comprising: The system collects operational status data from several low-voltage electrical devices in a building, and performs preprocessing and feature extraction on the operational status data to obtain status features. The status features are then transmitted to a cloud platform via the Internet of Things. The initial model is trained based on the state characteristics to obtain a deep learning model. The operating state data is analyzed based on the deep learning model to obtain analysis results. The weak current equipment is then controlled based on the analysis results. The effective proportion of the operating status data and the number of abnormal fluctuations in the operating status data per unit time are obtained to determine the steady-state characterization value of the data, and the accuracy of the collection of the operating status data is determined based on the steady-state characterization value of the data. If the accuracy of the collected operating status data does not meet the requirements, the response delay of the control command is used to determine whether the real-time performance of the weak current control meets the requirements. If the real-time performance of the weak current control does not meet the requirements, then determine whether to increase the steady-state trend pre-intervention depth of the weak current equipment; If it is not necessary to increase the pre-intervention depth of the steady-state trend of the weak current equipment, then the coupling influence coefficient of the weak current equipment regulation is determined by obtaining the regulation oscillation rate of the weak current equipment.

[0006] Furthermore, based on the steady-state characterization values ​​of the data, it is determined whether the accuracy of the collected operational status data meets the requirements, including: The steady-state characterization value of the data is determined by the ratio of the effective proportion of the operating status data to the number of abnormal fluctuations in the operating status data per unit time. The steady-state characterization value of the data is compared with the preset characterization value; If the steady-state characterization value of the data is greater than or equal to the preset characterization value, then the accuracy of the data collection for the operating status is determined to meet the requirements. If the steady-state characterization value of the data is less than the preset characterization value, then it is determined that the accuracy of the collected operating status data does not meet the requirements.

[0007] Furthermore, if the accuracy of the collected operating status data does not meet the requirements, the real-time performance of the weak current control is determined based on the response delay of the control command.

[0008] Furthermore, the real-time performance of low-voltage control is determined based on the response delay of the control command, including: The response delay of the control command is compared with a preset first delay. If the response delay of the control command is less than or equal to the preset first delay, then the real-time performance of the weak current control is determined to meet the requirements. If the response delay of the control command is greater than the preset first delay, then the real-time performance of the weak current control is determined to be unsatisfactory.

[0009] Furthermore, determine whether to increase the depth of pre-intervention in the steady-state trend of low-voltage equipment, including: The response delay of the control command is compared with the preset first delay and the preset second delay, respectively; If the response delay of the control command is greater than the preset first delay and less than or equal to the preset second delay, then it is determined that the steady-state trend pre-intervention depth of the weak current equipment needs to be increased. If the response delay of the control command is greater than the preset second delay, it is determined that it is not necessary to increase the steady-state trend pre-intervention depth of the weak current equipment.

[0010] Furthermore, the increase in the steady-state trend pre-intervention depth of the weak current equipment is determined by the difference between the response delay of the control command and the preset first delay.

[0011] Furthermore, based on the condition that the response delay of the control command is greater than the preset second delay, it is determined whether the control coordination of the building's weak current system meets the requirements based on the control oscillation rate of the weak current equipment.

[0012] Furthermore, the coupling influence coefficient of the control of weak current equipment is determined based on the control oscillation rate of the weak current equipment, including: Compare the regulated oscillation rate of the low-voltage equipment with the preset oscillation rate; If the oscillation rate of the low-voltage equipment is less than or equal to the preset oscillation rate, then the control coordination of the building's low-voltage system is determined to meet the requirements. If the oscillation rate of the low-voltage equipment is greater than the preset oscillation rate, it is determined that the control coordination of the building's low-voltage system does not meet the requirements, and the coupling influence coefficient of the low-voltage equipment regulation is reduced.

[0013] Furthermore, the oscillation rate of the low-voltage equipment is the ratio of the number of times the low-voltage equipment oscillates during regulation to the total number of times the low-voltage equipment is regulated.

[0014] Furthermore, the reduction in the coupling influence coefficient of the weak current equipment control is determined by the difference between the control oscillation rate of the weak current equipment and the preset oscillation rate.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: The method of this invention determines whether the accuracy of the collected operational status data meets the requirements based on the steady-state characterization value of the data. Because the building environment is subject to occasional events such as transient equipment start-ups and shutdowns, short-term fluctuations in power load, and sudden disturbances from indoor airflow and local heat sources, causing instantaneous abnormal fluctuations in operational status data, determining the accuracy of the collected operational status data allows for the assessment of the degree of data contamination caused by these occasional events, identification of the frequency and duration of abnormal fluctuations, and differentiation between real environmental changes and false interference signals. This avoids erroneous control actions caused by misjudging abnormal fluctuations as real environmental changes. Due to network congestion and data packet queuing delays, both the uplink feedback data and the downlink control commands experience non-negligible transmission delays. Generating control strategies based on historical data and sending them to the edge gateway causes a lag in the system's response to environmental changes. By increasing the steady-state trend of the weak current equipment... Pre-intervention depth allows low-voltage equipment to make small, pre-emptive adjustments to its operating state based on its own steady-state laws earlier and to a greater extent, adapting to environmental changes in advance and offsetting response lag caused by network transmission delays. The coupling influence coefficient of low-voltage equipment control can be adjusted based on the control oscillation rate of the equipment. Since various terminal devices operate with independent self-control logic, each device makes adjustment decisions solely based on its own collected data, lacking communication and linkage mechanisms. Long-term independent operation and a lack of cross-device coordination and action checks and balances can easily lead to contradictory control directions and mutually canceling effects. By reducing the coupling influence coefficient of low-voltage equipment control, the negative disturbance correlation intensity of a single low-voltage device's control action on related devices in the same space and along the same link can be weakened, reducing the mutual restraint and reverse interference between control behaviors of devices, weakening parameter fluctuations and action offsetting caused by disordered control, forming an implicit action check and balance relationship across devices, and improving the stability of low-voltage control.

[0016] Furthermore, the method described in this invention determines whether the accuracy of the collected operating status data meets the requirements by setting preset characterization values. Since the building environment is affected by occasional events such as transient equipment start-up and shutdown, short-term fluctuations in power supply load, and sudden disturbances in indoor airflow and local heat sources, the operating status data may experience instantaneous abnormal fluctuations. By determining the accuracy of the collected operating status data, the degree of data contamination caused by occasional events can be assessed, the frequency and duration of abnormal fluctuations can be identified, and the real environmental changes and false interference signals can be distinguished. This avoids erroneous control actions caused by misjudging abnormal fluctuations as real environmental changes, and further improves the stability of low-voltage control.

[0017] Furthermore, the method of the present invention adjusts the pre-intervention depth of the steady-state trend of the weak current equipment by setting a preset first delay duration and a preset second delay duration. Due to network congestion and data packet queuing delay, there is a non-negligible transmission delay in both the sensing uplink feedback data and the control downlink command. Generating control strategies based on historical data and sending them to the edge gateway will cause the system's response to environmental changes to lag. By increasing the pre-intervention depth of the steady-state trend of the weak current equipment, the weak current equipment can make small adjustments to its operating state earlier and to a greater extent according to its own steady-state law, adapt to environmental changes in advance, offset the response lag caused by network transmission delay, and further improve the stability of weak current control.

[0018] Furthermore, the method described in this invention adjusts the coupling influence coefficient of weak current equipment control by setting a preset oscillation rate. Since all types of terminal devices operate with independent self-control logic, each device makes adjustment decisions based solely on its own collected data. There is no communication linkage mechanism between devices, and they operate independently for a long time. The lack of cross-device coordination and action checks and balances can easily lead to situations where control directions contradict each other and effects cancel each other out. By reducing the coupling influence coefficient of weak current equipment control, the negative disturbance correlation intensity of a single weak current device's control action on related devices in the same space and on the same link can be weakened, the mutual restraint and reverse interference of control behaviors between devices can be weakened, the parameter fluctuations and action offsets caused by disordered control can be weakened, and an implicit action check relationship across devices can be formed, further improving the stability of weak current control. Attached Figure Description

[0019] Figure 1 This is an overall flowchart of the intelligent building low-voltage control method based on intelligent network connectivity according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating the process of determining the accuracy of data collection for intelligent building low-voltage electrical control based on intelligent network in an embodiment of the present invention. Figure 3 This is a flowchart illustrating the process of determining whether to increase the steady-state trend pre-intervention depth of weak current equipment in the intelligent building weak current control method based on intelligent network according to an embodiment of the present invention. Figure 4 This is a flowchart illustrating the process of determining the coupling influence coefficient of low-voltage equipment control in an intelligent building low-voltage control method based on intelligent network connectivity, according to an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0021] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0022] Please see Figure 1 As shown, it is an overall flowchart of the intelligent building low-voltage control method based on intelligent network connection according to an embodiment of the present invention.

[0023] This invention provides a smart building low-voltage control method based on intelligent network connectivity, comprising: Step S1: Collect the operating status data of several low-voltage electrical devices in the building, and perform preprocessing and feature extraction on the operating status data in sequence to obtain status features. Transmit the status features to the cloud platform through the Internet of Things. Step S2: Train the initial model based on the state features to obtain a deep learning model, perform state analysis on the operating state data based on the deep learning model to obtain analysis results, and regulate the weak current equipment based on the analysis results. Step S3: Obtain the effective proportion of the running status data and the number of abnormal fluctuations in the running status data per unit time to determine the steady-state characterization value of the data, and determine whether the accuracy of the collection of the running status data meets the requirements based on the steady-state characterization value of the data. Step S4: If the accuracy of the collected operating status data does not meet the requirements, the response delay of the control command is used to determine whether the real-time performance of the weak current control meets the requirements. Step S5: If the real-time performance of the weak current control does not meet the requirements, determine whether to increase the steady-state trend pre-intervention depth of the weak current equipment. Step S6: If it is not necessary to increase the steady-state trend pre-intervention depth of the weak current equipment, then obtain the control oscillation rate of the weak current equipment to determine the coupling influence coefficient of the control of the weak current equipment.

[0024] Specifically, low-voltage electrical equipment includes air conditioning equipment, access control equipment, and lighting equipment.

[0025] Specifically, the operational status data includes the return air temperature of the air conditioner, the card swipe records of the access control system, and the operating time of the lighting.

[0026] Specifically, preprocessing includes cleaning, noise reduction, and normalization.

[0027] Specifically, the status characteristics include the average return air temperature of the air conditioner per unit time, the daily flow of people passing through the access control system, and the average daily operating time of the lighting.

[0028] Specifically, the process of training an initial model based on state features to obtain a deep learning model involves constructing a time-series sample set of state features and dividing it into a training set, a validation set, and a test set. The training set is then input into the initial model for forward training and parameter iteration. Model parameters are tuned based on the validation set, and model performance is verified based on the test set to obtain the deep learning model.

[0029] Specifically, the initial model is a basic model framework that already has the ability to analyze state features and perform state analysis, but has not yet undergone parameter iteration optimization using data feature samples.

[0030] Specifically, the deep learning model can be a long short-term memory network model, a gated recurrent unit network model, or a Transformer model, with the preferred embodiment being a long short-term memory network model.

[0031] Specifically, the process of performing state analysis on operational status data based on a deep learning model to obtain analysis results involves inputting the operational status data into the deep learning model, fusing and calculating the state features, identifying the state of the weak current equipment, and outputting the corresponding analysis results.

[0032] Specifically, the analysis results included normal air conditioning operation, personnel entering and exiting at unusual times, and lighting equipment starting and stopping without reason.

[0033] Specifically, the process of regulating low-voltage equipment based on the analysis results involves converting the analysis results into executable regulation commands, sending them to the corresponding low-voltage equipment, continuously collecting the parameters to be regulated, evaluating deviations, dynamically correcting the regulation parameters, and iteratively implementing closed-loop regulation. This allows the low-voltage equipment to automatically switch to low-frequency operation after entering a reasonable range, thus stabilizing within a reasonable steady-state range.

[0034] Specifically, the steady-state trend pre-intervention depth of weak current equipment is the degree of proactive intervention that characterizes the weak current equipment's operating state before it deviates significantly from its operating state or receives control instructions. Based on its historical operating characteristics and steady-state change patterns, the equipment makes trend predictions on its own operating state in advance through trend fitting, historical state extrapolation, and steady-state change trajectory, and implements trend pre-correction to smoothly complete the transition of its working state.

[0035] Specifically, the coupling influence coefficient of weak current equipment control is a quantitative adjustment parameter that characterizes the strength of the negative interference effect of the control action of a single weak current device on the fluctuation of operating parameters, the degree of control oscillation, and the steady-state maintenance of surrounding related weak current devices under the same control link.

[0036] In implementation, the method of this invention determines whether the accuracy of the collected operational status data meets the requirements based on the steady-state characterization value of the data. Because the building environment is affected by transient equipment start-ups and shutdowns, short-term fluctuations in power load, and sudden disturbances from indoor airflow and local heat sources, occasional events can cause instantaneous abnormal fluctuations in the operational status data. By determining the accuracy of the collected operational status data, the degree of data contamination caused by these occasional events can be assessed, the frequency and duration of abnormal fluctuations can be identified, and the difference between real environmental changes and false interference signals can be distinguished. This avoids erroneous control actions caused by misjudging abnormal fluctuations as real environmental changes. Due to network congestion and data packet queuing delays, there are non-negligible transmission delays in both the sensing uplink feedback data and the control downlink commands. Generating control strategies based on historical data and sending them to the edge gateway can cause a lag in the system's response to environmental changes. By increasing the depth of steady-state trend pre-intervention of weak current equipment, [the following measures can be taken]. This approach allows low-voltage equipment to pre-correct its operating state earlier and more significantly based on its own steady-state laws, adapting to environmental changes in advance and offsetting response lag caused by network transmission delays. The coupling influence coefficient of low-voltage equipment control is adjusted based on the control oscillation rate of the equipment. Since various terminal devices operate with independent self-control logic, each device makes adjustment decisions solely based on its own collected data. There is no communication linkage mechanism between devices, leading to long-term independent operation and a lack of cross-device coordination and action checks and balances. This can easily result in conflicting control directions and mutually canceling effects. By reducing the coupling influence coefficient of low-voltage equipment control, the negative disturbance correlation intensity of a single low-voltage device's control action on related devices in the same space and along the same link can be weakened. This reduces the mutual restraint and reverse interference between control behaviors of devices, weakens parameter fluctuations and action offsetting caused by disordered control, forms an implicit action check relationship across devices, and improves the stability of low-voltage control.

[0037] Please continue reading. Figure 2 As shown, it is a logical flowchart of the process for determining the accuracy of data collection of operating status in the intelligent building weak current control method based on intelligent network according to an embodiment of the present invention.

[0038] Specifically, determining whether the accuracy of the collected operational status data meets the requirements based on the steady-state characterization values ​​includes: The steady-state characterization value of the data is determined by the ratio of the effective proportion of the operating status data to the number of abnormal fluctuations in the operating status data per unit time. The steady-state characterization value of the data is compared with the preset characterization value; If the steady-state characterization value of the data is greater than or equal to the preset characterization value, then the accuracy of the data collection for the operating status is determined to meet the requirements. If the steady-state characterization value of the data is less than the preset characterization value, then it is determined that the accuracy of the collected operating status data does not meet the requirements.

[0039] Understandably, in intelligent building low-voltage control methods, the core logic of using preset characterization values ​​to characterize whether the accuracy of operational status data acquisition meets requirements is to convert the accuracy of operational status data acquisition into quantifiable characterization values ​​for judgment. The preset characterization value serves as the dividing line for determining whether the accuracy of operational status data acquisition meets requirements. The preset characterization value can be set according to actual operating conditions. The preset characterization value aims to ensure the stability and practicality of low-voltage control. Optionally, the preset characterization value is determined through a limited number of tests by evaluating the effect of different characterization values ​​on low-voltage control. The determined preset characterization value should satisfy the condition that it is neither too small nor causes excessive interference to the low-voltage control process. For example, the preset characterization value is generally selected within the range of [2% / test, 10% / test].

[0040] Preferably, the preferred embodiment of the preset characterization value is 6% / time.

[0041] Specifically, % / time is the unit of steady-state characterization value of data, which means percentage per time.

[0042] Specifically, the effective proportion of operational status data is the ratio of the number of effective operational status data to the total number of operational status data.

[0043] Specifically, effective operating status data refers to operating status data that can accurately represent the indoor environment and can be directly used for low-voltage control strategy calculations.

[0044] Specifically, the number of abnormal fluctuations in the operating status data per unit time is the number of times the operating status data fluctuates randomly and repeatedly without reasonable cause, deviating from the gradual and smooth change pattern of the environment within a unit time.

[0045] In practice, the method described in this invention determines whether the accuracy of the collected operating status data meets the requirements by setting preset characterization values. Due to occasional events such as transient start-stop of equipment, short-term fluctuations in power supply load, and sudden disturbances in indoor airflow and local heat sources, the operating status data may experience instantaneous abnormal fluctuations. By determining the accuracy of the collected operating status data, the degree of data contamination caused by occasional events can be assessed, the frequency and duration of abnormal fluctuations can be identified, and the real environmental changes and false interference signals can be distinguished. This avoids erroneous control actions caused by misjudging abnormal fluctuations as real environmental changes, and further improves the stability of low-voltage control.

[0046] Please continue reading. Figure 3 As shown, it is a flowchart illustrating the process of determining whether to increase the steady-state trend pre-intervention depth of weak current equipment in the intelligent building weak current control method based on intelligent network according to an embodiment of the present invention.

[0047] Specifically, if the accuracy of the collected operating status data does not meet the requirements, the real-time performance of the weak current control is determined based on the response delay of the control command.

[0048] Specifically, determining whether the real-time performance of low-voltage control meets requirements based on the response delay of control commands includes: The response delay of the control command is compared with a preset first delay. If the response delay of the control command is less than or equal to the preset first delay, then the real-time performance of the weak current control is determined to meet the requirements. If the response delay of the control command is greater than the preset first delay, then the real-time performance of the weak current control is determined to be unsatisfactory.

[0049] Specifically, determining whether to increase the depth of pre-intervention in the steady-state trend of low-voltage equipment includes: The response delay of the control command is compared with the preset first delay and the preset second delay, respectively; If the response delay of the control command is greater than the preset first delay and less than or equal to the preset second delay, then it is determined that the steady-state trend pre-intervention depth of the weak current equipment needs to be increased. If the response delay of the control command is greater than the preset second delay, it is determined that it is not necessary to increase the steady-state trend pre-intervention depth of the weak current equipment.

[0050] Understandably, in intelligent building low-voltage control methods, the use of preset first and second delay durations to characterize whether the accuracy of operational status data acquisition meets requirements is based on the core logic of converting the accuracy of operational status data acquisition into quantifiable delay durations for judgment. The preset first delay duration serves as the dividing line for judging whether the accuracy of operational status data acquisition meets requirements, while the preset second delay duration serves as the dividing line for judging the two reasons that lead to the inaccuracy of operational status data acquisition. The preset first and second delay durations can be set according to actual operating conditions. The preset first and second delay durations aim to ensure the stability and practicality of low-voltage control. Optionally, the preset first and second delay durations are determined through a limited number of experiments by evaluating the effect of different delay durations on low-voltage control. The determined preset delay durations should satisfy the condition that they are neither too small nor cause excessive interference to the low-voltage control process. For example, the preset first delay duration is generally selected in the range of [20ms, 50ms], and the preset second delay duration is generally selected in the range of [70ms, 100ms].

[0051] Preferably, the first preset delay duration is 30ms, and the second preset delay duration is 80ms.

[0052] Specifically, the increase in the steady-state trend pre-intervention depth of the weak current equipment is determined by the difference between the response delay of the control command and the preset first delay.

[0053] Specifically, the response delay of the control command is the difference between the actual response time of the weak current equipment after receiving the control command and the theoretical response time of the output control action.

[0054] Specifically, when the difference between the response delay of the control command and the preset first delay is within 3ms, the steady-state trend pre-intervention depth of the weak current equipment increases to 1.1 times the original value. When the difference between the response delay of the control command and the preset first delay exceeds 3ms, in addition to increasing to 1.1 times the original value, the steady-state trend pre-intervention depth of the weak current equipment increases by 0.5 for every 1ms exceeding the original value. For example, if the difference between the response delay of the control command and the preset first delay is 6ms, and the current steady-state trend pre-intervention depth of the weak current equipment is 5, the increased steady-state trend pre-intervention depth of the weak current equipment is 5×1.1+0.5×3=7.

[0055] In practice, the method of the present invention adjusts the pre-intervention depth of the steady-state trend of weak current equipment by setting a preset first delay duration and a preset second delay duration. Due to network congestion and data packet queuing delay, there is a non-negligible transmission delay in both the sensing uplink feedback data and the control downlink command. Generating control strategies based on historical data and sending them to the edge gateway will cause the system's response to environmental changes to lag. By increasing the pre-intervention depth of the steady-state trend of weak current equipment, the weak current equipment can make small adjustments to its operating state earlier and to a greater extent according to its own steady-state law, adapt to environmental changes in advance, offset the response lag caused by network transmission delay, and further improve the stability of weak current control.

[0056] Please continue reading. Figure 4 As shown, it is a logical flowchart of the process of determining the coupling influence coefficient of weak current equipment regulation in the intelligent building weak current control method based on intelligent network according to an embodiment of the present invention.

[0057] Specifically, based on the condition that the response delay of the control command is greater than the preset second delay, the control coordination of the building's weak current system is determined based on the control oscillation rate of the weak current equipment.

[0058] Specifically, the coupling influence coefficient of weak current equipment regulation is determined based on the regulation oscillation rate of the weak current equipment, including: Compare the regulated oscillation rate of the low-voltage equipment with the preset oscillation rate; If the oscillation rate of the low-voltage equipment is less than or equal to the preset oscillation rate, then the control coordination of the building's low-voltage system is determined to meet the requirements. If the oscillation rate of the low-voltage equipment is greater than the preset oscillation rate, it is determined that the control coordination of the building's low-voltage system does not meet the requirements, and the coupling influence coefficient of the low-voltage equipment regulation is reduced.

[0059] Understandably, in intelligent building low-voltage electrical control methods, the preset oscillation rate is used to characterize whether the control coordination of the building's low-voltage electrical system meets the requirements. The core logic is to convert the control coordination of the building's low-voltage electrical system into a quantifiable oscillation rate for judgment, with the preset oscillation rate serving as the dividing line for determining whether the control coordination meets the requirements. The preset oscillation rate can be set according to actual operating conditions. The preset oscillation rate aims to ensure the stability and practicality of the low-voltage electrical control. Optionally, the preset oscillation rate is determined through a limited number of experiments by evaluating the effect of different oscillation rates on the low-voltage electrical control. The determined preset oscillation rate should satisfy the condition that it is neither too small nor causes excessive interference to the low-voltage electrical control process. For example, the preset oscillation rate is generally selected within the range of [5%, 15%].

[0060] Preferably, the preset oscillation rate is 10% in this preferred embodiment.

[0061] Specifically, the oscillation rate of the low-voltage equipment is the ratio of the number of times the low-voltage equipment oscillates during regulation to the total number of times the low-voltage equipment is regulated.

[0062] Specifically, the oscillation of low-voltage equipment control refers to the abnormal control behavior in which several low-voltage devices in a building, when performing control independently, exhibit excessive adjustment amplitude and overshoot due to the lack of coordination and checks and balances and the misalignment of control directions. This results in reverse pullback compensation, and the controlled physical quantity cannot quickly converge and stabilize within a reasonable range.

[0063] Specifically, the reduction in the coupling influence coefficient of the weak current equipment control is determined by the difference between the control oscillation rate of the weak current equipment and the preset oscillation rate.

[0064] Specifically, when the difference between the controlled oscillation rate and the preset oscillation rate of the weak current equipment is within 2%, the coupling influence coefficient of the weak current equipment control is reduced to 0.9 times the original value. When the difference between the controlled oscillation rate and the preset oscillation rate of the weak current equipment exceeds 2%, in addition to reducing it to 0.9 times the original value, for every 1% exceeding 2%, the coupling influence coefficient of the weak current equipment control decreases by 0.5. For example, if the difference between the controlled oscillation rate and the preset oscillation rate of the weak current equipment is 5%, and the current coupling influence coefficient of the weak current equipment control is 3, the reduced coupling influence coefficient of the weak current equipment control is 3×0.9-0.5×3=1.2.

[0065] In practice, the method described in this invention adjusts the coupling influence coefficient of weak current equipment control by setting a preset oscillation rate. Since all types of terminal devices operate with independent self-control logic, each device makes adjustment decisions based solely on its own collected data. There is no communication linkage mechanism between devices, and they operate independently for a long time. The lack of cross-device coordination and action checks and balances can easily lead to situations where control directions contradict each other and effects cancel each other out. By reducing the coupling influence coefficient of weak current equipment control, the negative disturbance correlation intensity of a single weak current device's control action on related devices in the same space and on the same link can be weakened, the mutual restraint and reverse interference of control behaviors between devices can be weakened, the parameter fluctuations and action offsets caused by disordered control can be weakened, and an implicit action check relationship across devices can be formed, further improving the stability of weak current control.

[0066] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A method for controlling low-voltage electrical systems in intelligent buildings based on intelligent network connectivity, characterized in that, include: The system collects operational status data from several low-voltage electrical devices in a building, and performs preprocessing and feature extraction on the operational status data to obtain status features. The status features are then transmitted to a cloud platform via the Internet of Things. The initial model is trained based on the state characteristics to obtain a deep learning model. The operating state data is analyzed based on the deep learning model to obtain analysis results. The weak current equipment is then controlled based on the analysis results. The effective proportion of the operating status data and the number of abnormal fluctuations in the operating status data per unit time are obtained to determine the steady-state characterization value of the data, and the accuracy of the collection of the operating status data is determined based on the steady-state characterization value of the data. If the accuracy of the collected operating status data does not meet the requirements, the response delay of the control command is used to determine whether the real-time performance of the weak current control meets the requirements. If the real-time performance of the weak current control does not meet the requirements, then determine whether to increase the steady-state trend pre-intervention depth of the weak current equipment; If it is not necessary to increase the pre-intervention depth of the steady-state trend of the weak current equipment, then the coupling influence coefficient of the weak current equipment regulation is determined by obtaining the regulation oscillation rate of the weak current equipment. Determine whether the accuracy of the collected operational status data meets the requirements based on the steady-state characterization values ​​of the data, including: The steady-state characterization value of the data is determined by the ratio of the effective proportion of the operating status data to the number of abnormal fluctuations in the operating status data per unit time. The steady-state characterization value of the data is compared with the preset characterization value; If the steady-state characterization value of the data is greater than or equal to the preset characterization value, then the accuracy of the data collection for the operating status is determined to meet the requirements. If the steady-state characterization value of the data is less than the preset characterization value, it is determined that the accuracy of the data collection for the operating status does not meet the requirements. The coupling influence coefficient of weak current equipment regulation is determined based on the regulation oscillation rate of the weak current equipment, including: Compare the regulated oscillation rate of the low-voltage equipment with the preset oscillation rate; If the oscillation rate of the low-voltage equipment is less than or equal to the preset oscillation rate, then the control coordination of the building's low-voltage system is determined to meet the requirements. If the oscillation rate of the low-voltage equipment is greater than the preset oscillation rate, it is determined that the control coordination of the building's low-voltage system does not meet the requirements, and the coupling influence coefficient of the low-voltage equipment regulation is reduced. The oscillation rate of the low-voltage equipment is the ratio of the number of times the low-voltage equipment oscillates during regulation to the total number of times the low-voltage equipment is regulated.

2. The intelligent building low-voltage control method based on intelligent network as described in claim 1, characterized in that, If the accuracy of the collected operating status data does not meet the requirements, the real-time performance of the weak current control is determined based on the response delay of the control command.

3. The intelligent building low-voltage control method based on intelligent network as described in claim 2, characterized in that, The real-time performance of low-voltage control is determined based on the response delay of control commands, including: The response delay of the control command is compared with a preset first delay. If the response delay of the control command is less than or equal to the preset first delay, then the real-time performance of the weak current control is determined to meet the requirements. If the response delay of the control command is greater than the preset first delay, then the real-time performance of the weak current control is determined to be unsatisfactory.

4. The intelligent building low-voltage control method based on intelligent network as described in claim 3, characterized in that, Determine whether to increase the depth of pre-intervention in the steady-state trend of low-voltage equipment, including: The response delay of the control command is compared with the preset first delay and the preset second delay, respectively; If the response delay of the control command is greater than the preset first delay and less than or equal to the preset second delay, then it is determined that the steady-state trend pre-intervention depth of the weak current equipment needs to be increased. If the response delay of the control command is greater than the preset second delay, it is determined that it is not necessary to increase the steady-state trend pre-intervention depth of the weak current equipment.

5. The intelligent building low-voltage control method based on intelligent network as described in claim 4, characterized in that, The increase in the steady-state trend pre-intervention depth of the weak current equipment is determined by the difference between the response delay of the control command and the preset first delay.

6. The intelligent building low-voltage control method based on intelligent network as described in claim 5, characterized in that, Based on the condition that the response delay of the control command is greater than the preset second delay, it is determined whether the control coordination of the building's weak current system meets the requirements based on the control oscillation rate of the weak current equipment.

7. The intelligent building low-voltage control method based on intelligent network as described in claim 6, characterized in that, The oscillation rate of the low-voltage equipment is the ratio of the number of times the low-voltage equipment oscillates during regulation to the total number of times the low-voltage equipment is regulated.

8. The intelligent building low-voltage control method based on intelligent network as described in claim 7, characterized in that, The reduction in the coupling influence coefficient of the weak current equipment control is determined by the difference between the control oscillation rate of the weak current equipment and the preset oscillation rate.

Images