Intelligent facility management control system based on 5g internet of things

Abstract

The application relates to the technical field of intelligent facility management, and discloses an intelligent facility management control system based on a 5G Internet of Things, which comprises a facility data acquisition module, a configuration module, a real-time monitoring module, an instruction matching module and an execution module. The facility data acquisition module collects data through a 5G terminal, generates a running characteristic value and a dynamic adjustment threshold parameter; the facility configuration module generates individualized parameters and a dynamic adaptation strategy according to the characteristic value; the real-time monitoring module acquires and screens real-time state data; the instruction matching module compares data to generate a correlation degree and select a target instruction; and the instruction execution module drives facility operation. The system is also provided with a threshold self-optimization module which optimizes threshold parameters through feedback data. The system realizes real-time monitoring, dynamic parameter adjustment, precise instruction matching and self-optimization, and improves the intelligentization, precision and self-adaptation capability of facility management.

Description

Technical Field

[0001] This invention relates to the field of intelligent facility management technology, specifically to an intelligent facility management and control system based on 5G Internet of Things. Background Technology

[0002] With the rapid development of IoT technology, intelligent facility management systems are increasingly widely used in industries such as manufacturing, construction, and transportation. Traditional facility management systems mainly rely on wired network connections and fixed threshold control strategies, which suffer from problems such as data transmission lag, poor environmental adaptability, and insufficient personalized equipment management. For example, traditional systems typically use preset fixed threshold parameters to control facilities, failing to dynamically adjust control strategies based on real-time environmental parameters and equipment operating status, leading to low equipment operating efficiency, excessive energy consumption, or frequent failures. Furthermore, when managing multiple devices collaboratively, traditional systems lack flexibility and real-time performance in data acquisition and command execution, making it difficult to meet the facility management needs of complex scenarios.

[0003] Before the widespread adoption of 5G technology, the data transmission rate and stability of IoT devices were limited, making it difficult to achieve real-time monitoring and precise control of large-scale facilities. With the development of 5G IoT technology, its high bandwidth, low latency, and massive connectivity provide a new technological path for intelligent facility management systems. However, existing 5G IoT-based facility management systems still have the following shortcomings: First, at the data acquisition level, there is a lack of in-depth analysis of historical operating data and environmental parameters, making it impossible to establish personalized operating characteristic models for the devices; second, at the control strategy level, the threshold parameter adjustment mechanism is simplistic and does not fully integrate real-time environmental data and device operating status for dynamic optimization; third, at the command matching level, the ability to correlate and analyze multi-source data is insufficient, making it difficult to achieve accurate matching and efficient execution of control commands; and fourth, at the system self-optimization level, there is a lack of feedback mechanisms for control effects, making it impossible to continuously improve the system's control accuracy and adaptability.

[0004] Furthermore, with the diversification and complexity of smart facilities, the control modes and priority requirements of different types of equipment vary significantly, making it difficult for traditional systems to achieve personalized configuration and dynamic adaptation. How to utilize 5G IoT technology to achieve real-time data collection of facility status, dynamic threshold adjustment, precise command matching, and system self-optimization has become a pressing technical challenge in the field of smart facility management. This invention aims to address the problems of data processing lag, rigid control strategies, and insufficient system adaptability in existing technologies by constructing a 5G IoT-based smart facility management and control system, thereby improving the intelligence, precision, and efficiency of facility management. Summary of the Invention

[0005] The purpose of this invention is to provide a smart facility management and control system based on 5G Internet of Things to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a smart facility management and control system based on 5G Internet of Things, the system comprising:

[0007] The facility data acquisition module is used to collect status monitoring data and environmental parameter data of the target facility through 5G IoT terminal devices, analyze and process the data to generate facility operation characteristic values ​​and environmental dynamic parameter characteristic values, and generate dynamic adjustment threshold parameters for each control command based on the initial threshold parameters of each control command stored in the 5G IoT platform.

[0008] The facility configuration module processes facility operation characteristic values ​​to obtain personalized configuration parameters for the facilities and generates dynamic adaptation control strategies for the facilities.

[0009] The real-time monitoring module is used to acquire real-time status data during facility operation through multi-source sensors, filter out valid real-time status data that meets the dynamic adjustment threshold, and send it to the instruction matching module.

[0010] The instruction matching module is used to compare the valid real-time status data with the dynamic adjustment threshold parameters of each control instruction to generate the correlation between the real-time data and each control instruction, and select the control instruction corresponding to the highest correlation as the target execution instruction.

[0011] The instruction execution module is used to receive the target execution instructions and index the preset instruction execution protocol in the 5G IoT platform to drive the target facility to complete the control operation.

[0012] Preferably, the specific process of collecting status monitoring data and environmental parameter data of the target facility through 5G IoT terminal equipment is as follows:

[0013] The 5G IoT device identifier of the target facility is used. If the facility is connected to the system for the first time, its basic operating parameters and environmental data are collected, including the facility's energy consumption baseline, operating temperature threshold and environmental humidity range. Based on the initial data, the facility's operating characteristic nodes are anchored and calibration operations are performed to generate facility operating characteristic values.

[0014] If the facility has been connected to the system multiple times, historical operating data and environmental parameter change curves are extracted. The historical operating data includes historical energy consumption fluctuation values, historical temperature deviation records, and historical response delay times, and is recorded as the initial state data of the facility for this time.

[0015] Preferably, the generation of dynamic adjustment threshold parameters for each control command based on the initial threshold parameters of each control command stored in the 5G IoT platform specifically includes:

[0016] The initial threshold standard set and threshold adjustment coefficient set of each control command are extracted from the 5G IoT platform. The initial threshold standard set includes: the upper limit value of energy consumption fluctuation, the temperature change tolerance range and the response time benchmark value corresponding to each control command.

[0017] The threshold adjustment coefficient set includes the energy consumption dynamic correction coefficient, temperature gradient compensation coefficient, and response time weight parameter for each control command.

[0018] Based on the real-time environmental parameter characteristic values, the initial threshold standard set of each control command is dynamically adjusted, and the processed parameter set is recorded as the dynamically adjusted threshold parameter.

[0019] The dynamically adjusted threshold parameters include the energy consumption dynamic threshold, temperature adaptability threshold, and response time optimization threshold for each control command.

[0020] Preferably, the process of obtaining personalized configuration parameters for the facility based on facility operation characteristic values ​​and generating a dynamic adaptation control strategy for the facility specifically includes:

[0021] The control mode priority list of the facility is determined by mapping and matching the facility operation characteristic values ​​with the preset facility type characteristic library;

[0022] A dynamic adaptive control strategy is generated based on the control mode priority list, which includes instruction triggering conditions, execution order rules, and exception handling mechanisms.

[0023] Preferably, the acquisition of real-time status data during facility operation via multi-source sensors specifically includes:

[0024] The real-time data stream of the monitoring facility's operational characteristic nodes includes instantaneous energy consumption values, core component temperature values, and operation response time;

[0025] When the real-time data stream exceeds the preset safe operating range, an abnormal data marker is activated and the status data within the abnormal period is extracted as valid real-time status data.

[0026] Preferably, the step of comparing the effective real-time status data with the dynamic adjustment threshold parameters of each control command to generate the correlation between the real-time data and each control command specifically includes:

[0027] The energy consumption fluctuation amplitude, temperature change gradient and response delay duration in the effective real-time status data are analyzed, and the difference between them and the energy consumption dynamic threshold, temperature adaptability threshold and response time optimization threshold of each control command are calculated.

[0028] Based on the difference calculation results, a three-dimensional correlation index between real-time data and each control command is generated.

[0029] Preferably, selecting the control instruction corresponding to the highest correlation as the target execution instruction specifically includes:

[0030] Establish a sorted queue of the correlation of each control instruction, and select the control instruction corresponding to the first correlation of the queue.

[0031] If the correlation between the first and second instruction is lower than the preset execution trigger threshold, the backup instruction set will be activated and the correlation will be recalculated.

[0032] Preferably, the specific processing procedure for generating the three-dimensional correlation index between real-time data and each control command is as follows:

[0033] A normalization algorithm is used to weight the energy consumption fluctuation difference, temperature gradient difference, and response time difference to generate a standardized correlation value in the range [0,1].

[0034] The closer the correlation value is to 1, the higher the degree of matching between real-time status data and control commands.

[0035] Preferably, it also includes a threshold self-optimization module, specifically including:

[0036] Record facility status feedback data after each control command is executed, including actual energy consumption changes, temperature control effectiveness, and response efficiency improvement rate;

[0037] The feedback data is back-verified with the dynamically adjusted threshold parameters to generate threshold correction coefficients and update the threshold adjustment coefficient set of the 5G IoT platform.

[0038] Preferably, the generation of the threshold correction coefficient specifically includes:

[0039] Based on the deviation between the feedback data and the expected control results, calculate the energy consumption correction coefficient, temperature compensation coefficient, and response time optimization weight.

[0040] A moving average algorithm is used to dynamically smooth the historical correction coefficients, generating a new set of threshold adjustment coefficients.

[0041] Compared with the prior art, the beneficial effects of the present invention are:

[0042] In terms of data acquisition and processing, the facility data acquisition module can perform differentiated processing based on the number of times a facility connects to the system: for facilities connecting for the first time, it collects basic operating parameters and environmental correlation data, anchors operating characteristic nodes and completes calibration, generating accurate operating characteristic values; for facilities connecting multiple times, it extracts historical operating data and environmental parameter change curves, providing rich historical references for subsequent dynamic adjustments. This hierarchical processing approach ensures that the system can quickly and accurately establish personalized data models for equipment, laying the foundation for precise control.

[0043] Regarding dynamic threshold adjustment, the system generates dynamic threshold parameters for each control command based on the initial threshold standard set and threshold adjustment coefficient set of the 5G IoT platform, combined with real-time environmental parameter characteristics. These parameters include dynamic energy consumption thresholds, temperature adaptability thresholds, and response time optimization thresholds. Compared to traditional fixed threshold control, this mechanism can respond to environmental changes in real time, making control commands more aligned with the actual operating needs of the equipment. This effectively improves the equipment's adaptability to complex environments and reduces the risk of equipment failure due to environmental fluctuations.

[0044] The facility configuration module determines the control mode priority list by mapping and matching facility operating characteristic values ​​with a preset facility type characteristic library, and generates a dynamically adaptable control strategy that includes instruction triggering conditions, execution order rules, and exception handling mechanisms. This design fully considers the personalized needs of different types of equipment, realizes dynamic switching and optimization of control strategies, ensures that equipment can operate in the optimal mode under various operating conditions, and improves equipment operating efficiency and stability.

[0045] The real-time monitoring module acquires real-time status data of facility operation through multi-source sensors and filters out valid data that meets dynamic adjustment thresholds. Combined with an anomaly data marking mechanism, it ensures that the system only processes critical data, reducing interference from invalid data and improving data processing efficiency and command matching accuracy. The command matching module achieves precise matching of control commands through three-dimensional correlation index calculation and correlation ranking queue. It also sets up a backup command set to handle low correlation situations, ensuring the system's reliability and robustness.

[0046] The threshold self-optimization module records facility status feedback data after control command execution, performs reverse verification with dynamically adjusted threshold parameters, generates threshold correction coefficients, and updates the platform. This closed-loop feedback mechanism enables the system to continuously optimize threshold parameters based on actual control effects, forming a virtuous cycle of "monitoring-control-feedback-optimization," continuously improving the system's control accuracy and adaptability, extending equipment lifespan, and reducing operation and maintenance costs.

[0047] Overall, this system achieves real-time data collection and efficient transmission of facility data through 5G IoT technology. Combined with core technologies such as dynamic threshold adjustment, personalized control strategy generation, precise command matching, and system self-optimization, it comprehensively solves the problems of poor adaptability, low control precision, and insufficient self-optimization capability of traditional facility management systems. It provides a more efficient and reliable technical solution for the field of intelligent facility management, with significant economic and social benefits. Attached Figure Description

[0048] Figure 1 This is a schematic diagram illustrating the working principle of the intelligent facility management and control system based on 5G Internet of Things as described in this invention.

[0049] Figure 2 Design drawings for the facility data acquisition process;

[0050] Figure 3 Design diagram for real-time status data monitoring;

[0051] Figure 4 Design diagram for the correlation calculation process;

[0052] Figure 5 Design diagram generated for threshold correction coefficient. Detailed Implementation

[0053] 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.

[0054] Please see Figures 1-5 The present invention relates to a smart facility management and control system based on 5G Internet of Things (IoT). The system includes: a facility data acquisition module, a facility configuration module, a real-time monitoring module, an instruction matching module, and an instruction execution module. Each module achieves data interaction and collaborative control through a 5G IoT platform. The specific implementation steps are as follows:

[0055] The facility data acquisition module collects status monitoring data and environmental parameter data of the target facility through 5G IoT terminal devices. After analyzing and processing the data, it generates facility operation characteristic values ​​and environmental dynamic parameter characteristic values. Based on the initial threshold parameters of each control command stored in the 5G IoT platform, it generates dynamic adjustment threshold parameters for each control command.

[0056] The facility configuration module processes facility operation characteristic values ​​to obtain personalized configuration parameters for the facility and generates dynamic adaptation control strategies for the facility.

[0057] The real-time monitoring module acquires real-time status data during facility operation through multi-source sensors, filters out valid real-time status data that meets the dynamic adjustment threshold, and sends it to the instruction matching module.

[0058] The instruction matching module compares the effective real-time status data with the dynamic adjustment threshold parameters of each control instruction to generate the correlation between the real-time data and each control instruction, and selects the control instruction corresponding to the highest correlation as the target execution instruction.

[0059] The instruction execution module receives the target execution instruction and indexes the preset instruction execution protocol in the 5G IoT platform to drive the target facility to complete the control operation.

[0060] The technical solution of the present invention will be further described in detail below with reference to specific embodiments.

[0061] Example 1:

[0062] This embodiment relates to a detailed implementation of the facility data acquisition module, specifically including differentiated data acquisition processes for the first and multiple accesses of the target facility, as well as a mechanism for generating dynamically adjusted threshold parameters.

[0063] During facility data collection, the system first identifies the target facility using 5G IoT terminal devices, based on the facility's unique 5G IoT device identifier. If the facility is accessing the system for the first time, the system initiates an initial data collection process: acquiring the facility's basic operating parameters and environmental data through 5G IoT terminal devices deployed in key parts of the facility, such as embedded sensors and smart meters. Basic operating parameters include the facility's energy consumption baseline (e.g., rated power, average energy consumption), operating temperature thresholds (e.g., upper and lower limits of the normal operating temperature range), and environmental humidity range (e.g., the humidity range suitable for facility operation). Environmental data is collected through environmental monitoring sensors, including real-time ambient temperature, humidity, and light intensity.

[0064] Based on the initial data, the system performs feature node anchoring and calibration operations. During feature node anchoring, the system analyzes the distribution patterns of basic operating parameters to identify key points reflecting the core operating characteristics of the facility, such as peak points of energy consumption curves (corresponding to full-load operation) and critical points of temperature fluctuations (nodes approaching operating temperature thresholds). The calibration operation compares the initial data with typical operating parameters of similar facilities to calibrate the anchored feature nodes. For example, it compares the initial energy consumption baseline of a facility with the average energy consumption baseline of the same model of equipment. If the deviation exceeds a preset threshold (e.g., ±10%), the initial data is corrected using a weighted average algorithm to generate facility operating characteristic values. After calibration, the system stores the initial data and calibrated feature values ​​in the initial feature library of the 5G IoT platform as a benchmark for subsequent data processing.

[0065] If the target facility has been connected to the system multiple times, the system extracts its historical operating data and environmental parameter change curves from the 5G IoT platform. Historical operating data includes historical energy consumption fluctuation values ​​(such as the maximum, minimum, and average energy consumption over the past 30 days), historical temperature deviation records (such as the sequence of deviations between actual operating temperature and set temperature), and historical response delay times (such as the time interval between the issuance of a control command and the completion of its execution). Environmental parameter change curves record the trends of environmental parameters such as temperature and humidity over time during facility operation. The system uses this historical data as the initial state data for the current facility and preprocesses it: first, it uses a sliding filter algorithm to remove outliers (such as energy consumption fluctuation values ​​that significantly exceed the normal range); then, it uses cubic spline interpolation to complete missing data points; and finally, it uses normalization to unify data from different dimensions to the same unit range to improve the accuracy of subsequent data processing.

[0066] When generating dynamic threshold adjustment parameters, the system retrieves the initial threshold standard set and threshold adjustment coefficient set for each control command from the 5G IoT platform. The initial threshold standard set is a pre-set control parameter benchmark for various facilities. For example, for control commands of ventilation equipment, the initial threshold standard set may include: an upper limit for energy consumption fluctuation of ±20% of rated power, a temperature change tolerance range of 18℃±5℃, and a response time benchmark of 8 seconds. The threshold adjustment coefficient set contains correction parameters corresponding to the initial threshold standard set, specifically including the energy consumption dynamic correction coefficient (a coefficient used to adjust the energy consumption fluctuation threshold, such as ±0.1 / ℃), the temperature gradient compensation coefficient (a coefficient used to compensate for the impact of ambient temperature changes on facility operation, such as ±0.5℃ / hour), and the response time weight parameter (a weight used to adjust the response time threshold, such as 0.3, 0.5, etc.). These coefficients and parameters are generated through statistical analysis of historical operating data, for example, calculating the energy consumption dynamic correction coefficient based on the correlation between ambient temperature and facility energy consumption fluctuation over the past year.

[0067] The system dynamically adjusts the initial threshold standard set based on real-time collected environmental dynamic parameter feature values ​​(such as current ambient temperature, humidity, air pressure, etc.). Specifically, the adjustment process involves substituting the real-time environmental parameter feature values ​​into the corresponding threshold adjustment coefficient formula for the initial threshold parameter of each control command. For example, when calculating the dynamic energy consumption threshold, if the real-time ambient temperature is T℃, the initial energy consumption fluctuation upper limit is E0, and the energy consumption dynamic correction coefficient is k, then the dynamic energy consumption threshold...

[0068] E = E0 + k × (T - T0)

[0069] Where T0 is the baseline ambient temperature (e.g., 25℃). Similarly, the temperature adaptability threshold is adjusted by multiplying the initial temperature change tolerance range by the temperature gradient compensation coefficient, while the response time optimization threshold is calculated by weighting the response time weight parameters based on real-time environmental parameters. The adjusted parameter set constitutes the dynamically adjusted threshold parameters, including the energy consumption dynamic threshold, temperature adaptability threshold, and response time optimization threshold. These parameters will be updated in real time to the 5G IoT platform and used in the subsequent control command matching process.

[0070] During data acquisition and parameter generation, the system leverages the high-speed transmission capabilities of 5G IoT to ensure data real-time performance and transmission stability. For example, the acquisition frequency for real-time environmental parameters is set to once per second, historical data extraction and processing are completed within 500 milliseconds of receiving the facility access signal, and the generation cycle for dynamically adjusted threshold parameters is once per minute to adapt to the slow changing trends of environmental parameters. Simultaneously, the system establishes a data verification mechanism, performing CRC checks on the acquired raw data to ensure that the data has not been tampered with or lost during transmission. If a verification failure is detected, the data acquisition request is re-initiated until valid data is obtained.

[0071] Through the above process, the facility data acquisition module can dynamically adjust the data acquisition strategy based on the facility's access history and generate personalized dynamic adjustment threshold parameters in combination with real-time environmental parameters. This provides an accurate data foundation for subsequent facility configuration, real-time monitoring, and command matching, enabling refined management and dynamic control of the target facility's operating status.

[0072] Example 2:

[0073] This embodiment involves the collaborative implementation of the facility configuration module and the real-time monitoring module, specifically including the generation of personalized configuration parameters based on facility operation characteristic values, the formulation of dynamic adaptation control strategies, and the collection of real-time status data of facilities by multi-source sensors and the abnormal data filtering mechanism.

[0074] The core function of the facility configuration module is to generate personalized configuration parameters and dynamically adapted control strategies suitable for the target facility based on the facility's operational characteristic values. The system first maps and matches the facility's operational characteristic values ​​(such as energy consumption baselines and temperature fluctuation nodes) with a pre-defined facility type feature library. This library is categorized and stored according to the facility's function, model, and application scenario. For example, the feature library for motor equipment in industrial production scenarios includes parameters such as speed-torque curves and temperature rise characteristics, while the feature library for elevator equipment in commercial buildings includes parameters such as start-stop frequency and load weight distribution. The matching process uses a fuzzy matching algorithm. By calculating the Euclidean distance between the facility's operational characteristic values ​​and each type of template in the feature library, the type template with the smallest distance is selected as the matching result, thereby determining the facility's control mode priority list. For example, for air conditioning equipment in a hospital cleanroom, due to the extremely high requirements for temperature and humidity control accuracy, the "constant temperature and humidity control mode" has the highest priority in its control mode priority list, followed by the "energy consumption optimization mode," and finally the "fault warning mode."

[0075] Based on the control mode priority list, the system generates a dynamically adaptable control strategy. This strategy includes three core elements: command triggering conditions, execution order rules, and an exception handling mechanism. Command triggering conditions are directly related to dynamically adjusted threshold parameters. For example, when the instantaneous energy consumption value collected by the real-time monitoring module exceeds 110% of the dynamic energy consumption threshold, an "energy-saving adjustment command" is triggered; when the core component temperature value is below 90% of the lower limit of the temperature adaptability threshold, a "heating compensation command" is triggered. The execution order rules ensure that multiple control commands are executed in priority order. For example, when the facility simultaneously detects abnormal temperature and excessive energy consumption, the system prioritizes executing the "temperature abnormality alarm command," and then executes the "energy consumption optimization command" after the temperature returns to normal. The exception handling mechanism defines a multi-level response process when the facility operates abnormally. For example, when multiple source sensors detect that the core component temperature exceeds the upper limit of the safe operating range for 5 consecutive minutes, the system first initiates the "redundant cooling equipment start command." If the temperature does not drop to the safe range within 10 minutes, an "emergency shutdown command" is automatically triggered, and a fault warning message is sent to maintenance personnel.

[0076] The real-time monitoring module collects status data during facility operation in real time through multi-source sensors (such as current sensors, temperature sensors, pressure sensors, and displacement sensors) deployed at various key locations within the facility. The sensor deployment locations are determined based on the facility type and operating characteristics. For example, sensors for motor equipment are deployed on the stator windings (monitoring temperature), bearings (monitoring vibration and temperature), and power input terminals (monitoring current and voltage); sensors for air conditioning equipment are deployed on the compressor (monitoring operating pressure), air outlets (monitoring temperature and airflow), and electrical control boxes (monitoring energy consumption). The real-time data stream collected by the sensors includes key parameters such as instantaneous energy consumption (unit: kW), core component temperature (unit: °C), and operation response time (unit: ms). The data acquisition frequency is set according to the facility's operating characteristics; for high-speed equipment (such as industrial fans), the acquisition frequency is 10 times per second, and for low-speed equipment (such as elevators), the acquisition frequency is 2 times per second.

[0077] The system performs real-time monitoring and filtering of the real-time data stream. First, a preset safe operating range is established, determined based on the facility's design parameters and historical operating data. For example, the safe operating range for a certain type of motor is: instantaneous energy consumption ≤ 120% of rated power, core component temperature ≤ 75℃, and operation response time ≤ 500ms. When any parameter in the real-time data stream exceeds the safe operating range, the system immediately activates an anomaly data marking mechanism, recording the specific time of the anomaly with a timestamp and extracting the status data within the anomaly period as valid real-time status data. The scope of valid real-time status data extraction includes the complete data sequence from 3 minutes before the anomaly occurs to 2 minutes after the anomaly is resolved, ensuring complete capture of the anomaly's precursors, process, and subsequent recovery. For example, if the temperature of a core component of an air conditioner compressor exceeds the safe threshold at 14:00:00, the system starts extracting data from 13:57:00 until the temperature returns to normal at 14:05:00, forming a complete dataset containing the temperature rise trend, peak data, and the temperature drop process.

[0078] In the data transmission phase, the real-time monitoring module leverages the high bandwidth of 5G IoT to transmit valid real-time status data in encrypted format to the command matching module in real time. A QoS (Quality of Service) guarantee mechanism is employed during transmission, assigning the highest priority to abnormal data transmissions to ensure data is transmitted from the sensor to the system within 50ms, preventing control command delays due to latency. Simultaneously, the system performs integrity verification on the transmitted data, using the MD5 hash algorithm to verify that the data has not been tampered with during transmission. If verification fails, the data is automatically retransmitted until complete and valid data is obtained.

[0079] Through the collaborative operation of the facility configuration module and the real-time monitoring module, the system can formulate dynamic control strategies based on the personalized operating characteristics of the facilities. It also uses multi-source sensors to capture abnormal states in real time, providing precise data support for subsequent command matching and execution, thus achieving real-time monitoring and intelligent control of the facility's operating status. Throughout the process, the system leverages the low latency of 5G IoT to ensure timely response to control strategies, and uses data verification and transmission optimization mechanisms to guarantee data accuracy and reliability, thereby improving the overall efficiency of the intelligent facility management and control system.

[0080] Example 3:

[0081] This embodiment relates to the correlation calculation and target instruction selection mechanism of the instruction matching module, specifically including the parsing of effective real-time status data, difference calculation, generation of three-dimensional correlation index, and target execution instruction selection process based on correlation ranking.

[0082] After receiving valid real-time status data from the real-time monitoring module, the command matching module first performs structured parsing on the data. The parsing process extracts key parameters based on the data type and facility operating characteristics: for energy-related data, it extracts the energy consumption fluctuation amplitude (i.e., the percentage difference between the real-time energy consumption value and the facility's energy consumption baseline); for temperature-related data, it extracts the temperature change gradient (i.e., the rate of temperature change of core components per unit time, in °C / minute); for response time-related data, it extracts the response delay duration (i.e., the time difference between the issuance of a control command and the start of facility execution, in seconds). For example, if valid real-time status data includes an instantaneous energy consumption value of 120% of rated power, a core component temperature increase of 5 °C within 10 minutes, and an operation response time of 18 seconds, then the corresponding energy consumption fluctuation amplitude is +20%, the temperature change gradient is +0.5 °C / minute, and the response delay duration is +8 seconds (assuming a response time baseline of 10 seconds).

[0083] The system calculates the differences between the aforementioned key parameters and the dynamic adjustment threshold parameters of each control command. The dynamic adjustment threshold parameters include the energy consumption dynamic threshold, temperature adaptability threshold, and response time optimization threshold. These thresholds are generated by the facility data acquisition module based on real-time environmental parameters and facility operating characteristics. The specific method for calculating the differences is as follows: the parameter values ​​in the effective real-time status data are subtracted from the threshold parameters of the corresponding control commands to obtain the energy consumption fluctuation difference, temperature gradient difference, and response time difference. For example, if the energy consumption dynamic threshold of a certain control command is +15%, the temperature adaptability threshold is +0.3℃ / min, and the response time optimization threshold is +5 seconds, then the differences in the above example data are +5% (20% - 15%), +0.2℃ / min (0.5℃ / min - 0.3℃ / min), and +3 seconds (8 seconds - 5 seconds), respectively. The sign of the difference indicates the direction of the parameter's deviation from the threshold, and the absolute value indicates the degree of deviation.

[0084] Based on the difference calculation results, the system generates a three-dimensional correlation index between real-time data and various control commands. The generation process uses a normalization algorithm to weight the three differences. The specific steps are as follows: First, each difference is mapped to a standardized interval of [0,1]. The mapping rules are preset according to the facility type and control requirements. For example, the mapping range for energy consumption fluctuation difference is [-20%, +20%] corresponding to [0,1], the mapping range for temperature gradient difference is [-1℃ / minute, +1℃ / minute] corresponding to [0,1], and the mapping range for response time difference is [-10 seconds, +10 seconds] corresponding to [0,1]. Then, weight coefficients are assigned to each difference according to the control mode priority list. For example, in a scenario where temperature control is prioritized, the weight coefficient for temperature gradient difference is set to 0.5, and the weight coefficients for energy consumption fluctuation difference and response time difference are set to 0.3 and 0.2, respectively. Finally, the standardized differences are multiplied by the corresponding weight coefficients and summed to obtain a standardized correlation value in the range of [0,1]. The closer the correlation value is to 1, the higher the degree of matching between the real-time status data and the control command; the closer it is to 0, the lower the degree of matching.

[0085] After calculating the correlation of all control commands, the system establishes a correlation ranking queue, sorting the control commands from highest to lowest correlation value. The queue is generated based on the quicksort algorithm, ensuring the sorting operation is completed in the shortest possible time; for example, for a set of 10 control commands, the sorting time can be controlled within 10 milliseconds. The control command at the top of the queue is the one with the highest correlation, and the system selects it as the target execution command. For example, in a facility's control command set, command A has a correlation value of 0.85, command B has 0.72, and command C has 0.68. The queue order would be command A, command B, and command C, and the system would select command A as the target execution command.

[0086] If the correlation value of the first instruction in the queue is lower than the preset execution trigger threshold (e.g., 0.6), the system determines that the current set of control instructions cannot effectively handle real-time status data. In this case, the backup instruction set is activated and the correlation is recalculated. The backup instruction set includes emergency control instructions for extreme abnormal situations, such as emergency shutdown instructions, power cut-off instructions, and safety interlock instructions. The triggering conditions for these instructions are usually set based on the minimum standards for safe operation. For example, when energy consumption fluctuations exceed +50% or temperature changes exceed +2℃ / minute, the emergency shutdown instruction is triggered directly, regardless of other parameters. After activating the backup instruction set, the system first performs difference calculations and correlation generation for each instruction in the backup instruction set. Then, it reorders and selects the first instruction. If the newly generated first-instance correlation is still lower than the threshold, the above process is repeated until a valid instruction is found or the highest level of safety protection measures are executed.

[0087] Throughout the command matching process, the system leverages the low latency of 5G IoT to ensure real-time correlation calculation and command selection, with the total time from receiving valid real-time status data to completing the target command selection not exceeding 100 milliseconds. Simultaneously, a data caching mechanism is established to store the results of the most recent 10 correlation calculations, enabling rapid retrieval of historical matching records after system failure recovery, assisting maintenance personnel in analyzing the effectiveness of control strategies. Furthermore, the system supports manual intervention; when maintenance personnel discover abnormal correlation calculation results through the management terminal, they can manually adjust weighting coefficients or force the execution of a specified target command, enhancing the system's flexibility and reliability.

[0088] Through the above mechanism, the instruction matching module can generate a quantitative correlation index based on the accurate comparison of real-time status data and dynamic threshold parameters, and realize the intelligent selection of control instructions. This ensures that the target facility can obtain the optimal control strategy under different operating scenarios, thereby improving the response accuracy and operating efficiency of the intelligent facility management and control system.

[0089] Example 4:

[0090] This embodiment relates to the implementation mechanism of the threshold self-optimization module, specifically including the recording of facility status feedback data after the execution of control commands, the reverse verification of feedback data and dynamically adjusted threshold parameters, and the generation and updating process of threshold correction coefficients.

[0091] The core function of the threshold self-optimization module is to continuously collect feedback data after the execution of control commands and optimize dynamically adjusted threshold parameters to improve the adaptability of the system's control strategy. After each control command is executed, the system collects facility status feedback data in real time. Data types include actual energy consumption changes (i.e., the difference between facility energy consumption after command execution and before), temperature control effectiveness (such as temperature changes in core components and the time required for temperature stabilization), and response efficiency improvement rate (i.e., the ratio of the command execution time to the historical average execution time). Feedback data is collected through sensors and timers deployed in the facility; for example, smart meters monitor energy consumption changes, temperature sensors record temperature curves, and command execution logs obtain response time data.

[0092] The collected feedback data is transmitted to the 5G IoT platform for reverse verification against the corresponding dynamically adjusted threshold parameters. The purpose of reverse verification is to analyze the deviation between the actual execution effect of the control command and the expected result. Specifically, the process involves: comparing the actual energy consumption change value in the feedback data with the target value of the dynamic energy consumption threshold corresponding to the command, calculating the deviation direction (positive or negative deviation) and deviation magnitude (e.g., the actual energy consumption reduction is 10% less than expected); comparing the temperature control effect with the expected control range of the temperature adaptability threshold to determine whether the temperature change is within the preset range; and comparing the response efficiency improvement rate with the expected improvement target of the response time optimization threshold to evaluate whether the command execution speed meets the optimization requirements. For example, if the expected energy consumption reduction target of a certain energy-saving control command is 15%, and the actual feedback energy consumption reduction value is 12%, then the deviation magnitude is -3%, indicating that the actual effect did not meet expectations.

[0093] Based on the deviation between feedback data and expected results, the system calculates energy consumption correction coefficients, temperature compensation coefficients, and response time optimization weights. The calculation logic of the correction coefficients is based on the nature and degree of the deviation. For example, when the actual energy consumption reduction is lower than expected, the system generates a positive energy consumption correction coefficient to increase the adjustment range of subsequent dynamic energy consumption thresholds; conversely, it generates a negative correction coefficient to reduce the adjustment range. When the temperature control effect exceeds the expected range, the system adjusts the temperature compensation coefficient according to the direction of the deviation. If the actual temperature drops too quickly, the temperature gradient compensation coefficient is reduced to slow down the control speed. The generation of these correction coefficients does not rely on fixed formulas but is dynamically determined through statistical regularities of historical data and machine learning algorithms (such as linear regression). For example, by analyzing the deviation data of the past 50 similar commands, a mapping model between deviation values ​​and correction coefficients is established.

[0094] To avoid the interference of randomness in single feedback data on threshold adjustments, the system employs a moving average algorithm to dynamically smooth historical correction coefficients. The specific implementation of the moving average algorithm is as follows: a time window is set (e.g., the execution cycles of the most recent 10 control commands), and the arithmetic mean of all correction coefficients within this window is calculated to generate a new threshold adjustment coefficient. For example, if the energy consumption correction coefficients for the past 10 times are +0.05, +0.03, -0.02, +0.04, etc., the system calculates their average value as +0.03, which is then used as the new dynamic energy consumption correction coefficient. The smoothed threshold adjustment coefficient is updated to the threshold adjustment coefficient set of the 5G IoT platform, replacing the original coefficient values, thereby achieving iterative optimization of the dynamically adjusted threshold parameters.

[0095] The operating cycle of the threshold self-optimization module is related to the execution frequency of control commands. Typically, an optimization process is triggered after each command execution and feedback data acquisition, ensuring that threshold parameters promptly reflect changes in the facility's operational status. For example, for a facility executing 20 control commands daily, the system performs threshold parameter optimization 20 times daily. Regarding data storage, the system retains the feedback data and correction coefficient records from the most recent 1000 times for long-term trend analysis and anomaly tracking. For instance, by comparing changes in correction coefficients across different seasons, the system can identify the influence of ambient temperature on the facility's operating thresholds.

[0096] Through the aforementioned mechanism, the threshold self-optimization module can continuously adjust threshold parameters based on actual control effects, enabling the system's control strategy to gradually adapt to the facility's personalized operating characteristics and environmental changes, avoiding control lag or over-adjustment issues caused by fixed thresholds. The entire optimization process requires no manual intervention and is achieved through automated data processing on the 5G IoT platform, thereby improving the system's intelligence level, reducing operation and maintenance costs, and enhancing the stability and energy efficiency of facility operation.

[0097] Example 5:

[0098] This embodiment relates to the generation mechanism of threshold correction coefficient in the threshold self-optimization module, specifically including feedback data recording, reverse verification process and coefficient generation logic based on moving average algorithm.

[0099] The system records facility status feedback data after each control command execution through a threshold self-optimization module. This feedback data includes actual energy consumption changes, temperature control effectiveness, and response efficiency improvement rates. For example, after a temperature control command is executed, the temperature of the facility's core components drops from an initial value T1 to T2; the actual temperature change is...

[0100] ΔT=T2-T1

[0101] The response time is t (in seconds), and the energy consumption change is ΔE (in kilowatt-hours). These data are collected in real time by sensors and transmitted to a 5G IoT platform for storage, forming a historical feedback dataset.

[0102] The reverse verification process between feedback data and dynamically adjusted threshold parameters aims to analyze the deviation between the actual effect of the control command and the expected target. Taking temperature control as an example, if the expected control target of the temperature adaptability threshold in the dynamically adjusted threshold parameters is ΔT... target (For example, if the target temperature drops by 5°C), then the deviation value

[0103] ΔD=ΔT-ΔT target

[0104] A positive deviation value indicates that the actual temperature change exceeds expectations; a negative deviation value indicates that the expected change is not met. Similarly, the deviation values ​​for energy consumption and response time are calculated by the difference between the actual values ​​and the corresponding threshold target values, respectively.

[0105] Based on the deviation value, the system calculates the energy consumption correction coefficient, temperature compensation coefficient, and response time optimization weight. To avoid the random influence of single deviations, the system uses a moving average algorithm to process historical correction coefficients and generate a new set of threshold adjustment coefficients. The specific implementation of the moving average algorithm is as follows: Set the moving window size to N (e.g., N=10), and take the correction coefficients C1, C2, ..., C from the most recent N deviations. n Calculate its average value as the new coefficient C. new The formula is:

[0106]

[0107] C new : Newly generated threshold adjustment coefficient; C1 to C n : Historical correction coefficients within the sliding window, corresponding to correction parameters for energy consumption, temperature, or response time, respectively; N: Number of samples in the sliding window, a positive integer. Taking the energy consumption correction coefficient as an example, if the historical coefficients for the most recent 10 times are 0.02, 0.03, -0.01, 0.04, 0.02, 0.01, -0.02, 0.03, 0.02, and 0.04, then...

[0108]

[0109] This value will be used as a new dynamic energy consumption correction factor to update the threshold adjustment factor set of the 5G IoT platform.

[0110] The generation logic for the temperature compensation coefficient and response time optimization weight is consistent with that for the energy consumption correction coefficient, both using a moving average algorithm to smooth historical data. The system periodically (e.g., after each control command execution) triggers a threshold self-optimization process, applying the newly generated threshold adjustment coefficient to the calculation of dynamically adjusted threshold parameters, ensuring that the threshold parameters for each control command are continuously optimized based on the actual operational performance of the facility.

[0111] Throughout the process, the system ensures the real-time nature of feedback data through the high-speed data transmission capabilities of 5G IoT, and utilizes edge computing nodes to perform deviation calculations and moving average processing, reducing the computing pressure on the cloud. The threshold self-optimization module requires no manual intervention, achieving dynamic iteration of threshold parameters through automated data processing. This enhances the system's adaptability to the facility's operating environment and personalized characteristics, ensuring the accuracy and effectiveness of the control strategy.

[0112] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0113] 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 5G Internet of Things-based intelligent facility management control system, characterized in that, Comprise: Facility data acquisition module, for collecting target facility state monitoring data and environmental parameter data through 5G Internet of Things terminal equipment, analyzing and processing to generate facility operation characteristic value and environmental dynamic parameter characteristic value, and generating dynamic adjustment threshold parameter of each control instruction based on initial threshold parameter of each control instruction stored in 5G Internet of Things platform; Facility configuration module, based on facility operation characteristic value, processing to obtain individualized configuration parameter of facility and generating dynamic adaptive control strategy of facility; Real-time monitoring module, for obtaining real-time state data in facility operation process through multi-source sensor, screening out effective real-time state data meeting dynamic adjustment threshold parameter and sending to instruction matching module; Instruction matching module, for comparing effective real-time state data with dynamic adjustment threshold parameter of each control instruction to generate correlation degree of real-time data and each control instruction, and selecting control instruction corresponding to highest correlation degree as target execution instruction; Instruction execution module, for receiving target execution instruction and indexing preset instruction execution protocol in 5G Internet of Things platform, driving target facility to complete control operation; The dynamic adjustment threshold parameter of each control instruction based on the initial threshold parameter of each control instruction stored in the 5G Internet of Things platform, specifically includes: Extract the initial threshold standard set and the threshold adjustment coefficient set of each control instruction from the 5G Internet of Things platform, the initial threshold standard set includes: the energy consumption fluctuation upper limit value, the temperature change tolerance interval and the response time reference value corresponding to each control instruction; The threshold adjustment coefficient set includes the energy consumption dynamic correction coefficient, the temperature gradient compensation coefficient and the response time weight parameter of each control instruction; Based on the real-time environmental parameter characteristic value, dynamically adjust the initial threshold standard set of each control instruction, and the processed parameter set is called dynamic adjustment threshold parameter; The dynamic adjustment threshold parameter includes the energy consumption dynamic threshold, the temperature adaptability threshold and the response time optimization threshold of each control instruction; Based on the facility operation characteristic value, processing to obtain individualized configuration parameter of facility and generating dynamic adaptive control strategy of facility, specifically includes: According to the mapping matching of the facility operation characteristic value and the preset facility type characteristic library, the control mode priority list of the facility is determined; Based on the control mode priority list, a dynamic adaptive control strategy containing instruction trigger condition, execution sequence rule and exception handling mechanism is generated; The correlation degree of real-time data and each control instruction is generated by comparing the effective real-time state data with the dynamic adjustment threshold parameter of each control instruction, specifically including: Analyze the energy consumption fluctuation amplitude, temperature change gradient and response delay time length in the effective real-time state data, and perform difference calculation with the energy consumption dynamic threshold, temperature adaptability threshold and response time optimization threshold of each control instruction respectively; Based on the difference calculation result, a three-dimensional correlation degree index of real-time data and each control instruction is generated.

2. The intelligent facility management control system based on 5G Internet of Things according to claim 1, characterized in that: Obtain real-time state data in facility operation process through multi-source sensor, screen out effective real-time state data meeting dynamic adjustment threshold parameter, specifically including: Monitoring the real-time data stream of facility operation characteristic node, including instantaneous energy consumption value, core component temperature value and operation response time; When the real-time data stream exceeds the preset safe operation range, the abnormal data marker is activated, and the state data in the abnormal period is intercepted as valid real-time state data. 3.The 5G-IoT based smart facility management control system according to claim 1, wherein: The control instruction corresponding to the highest correlation degree is selected as the target execution instruction, specifically including: A correlation degree sorting queue of each control instruction is established, and the control instruction corresponding to the first correlation degree in the queue is selected; If the first correlation degree is lower than the preset execution trigger threshold, the standby instruction set is activated and the correlation degree calculation is performed again.

4. The intelligent facility management control system based on 5G-IoT of claim 1, wherein: The specific processing process of generating the three-dimensional correlation degree index of the real-time data and each control instruction is: The energy consumption fluctuation difference value, the temperature gradient difference value and the response time difference value are weighted calculated by using the normalization algorithm to generate the standardized correlation degree value in the range of [0, 1]; The closer the correlation degree value is to 1, the higher the matching degree of the real-time state data and the control instruction is.

5. The intelligent facility management control system based on 5G-IoT according to claim 1, characterized in that: It also includes a threshold self-optimization module, specifically including: Record the facility state feedback data after each control instruction execution, including actual energy consumption change value, temperature control effect and response efficiency improvement rate; The feedback data and the dynamic adjustment threshold parameter are checked in reverse to generate a threshold correction coefficient and update it to the threshold adjustment coefficient set of the 5G Internet of Things platform. 6.The 5G-IoT based smart facility management control system as claimed in claim 5, wherein: The specific process of generating the threshold correction coefficient includes: Based on the deviation value of the feedback data and the control expected result, the energy consumption correction coefficient, the temperature compensation coefficient and the response time optimization weight are calculated; The historical correction coefficients are dynamically smoothed by using the moving average algorithm to generate a new threshold adjustment coefficient set.

Images