A remote wireless heating valve control system based on the Internet of Things

Abstract

The present invention discloses a remote wireless heating valve control system based on the Internet of Things, which includes an intelligent communication management module, a real-time environment perception module, an adaptive frequency allocation and spectrum management module, a device control and execution module, and a system monitoring and maintenance module. This remote wireless heating valve control system based on the Internet of Things effectively solves the problem of unstable transmission of control instructions caused by wireless interference in complex environments through adaptive multi-band dynamic switching and intelligent interference recognition technology. This system not only improves the reliability and stability of heating control data transmission, but also optimizes heat energy distribution and resource utilization, reduces system operation costs, and significantly enhances the competitiveness and adaptability of the system in the fields of central heating, commercial buildings, and large residential areas.

Description

Technical Field

[0001] The present invention relates to the application of heating systems, and specifically to a remote wireless heating valve control system based on the Internet of Things. Background Art

[0002] Currently, in central heating systems, commercial buildings or large residential areas, wireless heating valve control systems based on the Internet of Things are commonly used to automatically control the operation of hot water boilers, heating distribution systems or central heating equipment; however, due to the complex pipe network structure, metal heat exchange equipment and other heat source interferences in the heating system, wireless signal interference is likely to occur, resulting in unstable or ineffective transmission of remote control instructions; this will not only affect the normal operation of the heating system, but may also lead to equipment failures, uneven heat energy distribution or resource waste. Summary of the Invention

[0003] (I) Technical Problems to be Solved

[0004] In view of the deficiencies of the prior art, the present invention provides a remote wireless heating valve control system based on the Internet of Things. By adopting a hybrid communication protocol technology that combines adaptive multi-band dynamic switching and intelligent interference recognition, for the problem of unstable control signal transmission caused by complex pipe network structures and equipment interferences in central heating systems, precise control of heating valves, efficient transmission of heat media and overall stable operation of the system are achieved, thereby improving heating efficiency and reducing operating costs.

[0005] (II) Technical Solutions

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A remote wireless heating valve control system based on the Internet of Things, including an intelligent communication management module, a real-time environment perception module, an adaptive frequency allocation and spectrum management module, an equipment control and execution module, and a system monitoring and maintenance module. Among them, data exchange and collaborative work are carried out between each module through wired or wireless communication interfaces. The system includes:

[0007] The intelligent communication management module is used to implement a hybrid communication protocol that combines adaptive multi-band dynamic switching and intelligent interference recognition to maintain communication stability and ensure the real-time and accuracy of heating equipment control data; when high interference is detected in the current communication band, it automatically switches to a low interference band to maintain communication stability and ensure the real-time and accurate transmission of heating equipment control data;

[0008] The real-time environment perception module is used to collect and analyze the system operating environment data. The system operating environment data refers to a comprehensive data set composed of temperature, humidity, vibration, light, pressure and flow rate of the heating medium, as well as wireless signal strength, signal-to-noise ratio, and bit error rate, which is used to monitor the environmental status in real time, predict interference, and guide the system to adaptively adjust communication and heating control strategies; in addition to monitoring environmental temperature, humidity, vibration, and light parameters, it also collects key parameters (such as temperature, pressure, and flow rate) in the heating system; based on the output of the interference prediction model, the real-time environment perception module adjusts the communication strategy in advance to avoid potential interference and ensure the stable transmission of heating control instructions;

[0009] The adaptive frequency allocation and spectrum management module is used to cooperate between different control nodes to avoid frequency band conflicts and congestion, thereby ensuring the efficient transmission of heating system control instructions;

[0010] This adaptive frequency allocation and spectrum management module includes a dynamic frequency selection algorithm and an adaptive modulation and encoder. By real-time evaluating the 2.4GHz, 5GHz, and 900MHz wireless frequency bands, it intelligently selects the current optimal communication frequency band and triggers a switching mechanism when the channel quality deteriorates;

[0011] The device control and execution module is used to accurately control the start and stop of the wireless heating valve according to the received control instructions;

[0012] The device control and execution module is equipped with a wireless control interface, a heating valve drive unit, and a feedback sensor; the heating valve drive unit drives the heating valve according to the control instructions to realize the flow regulation of the heating medium (such as hot water or steam); the feedback sensor monitors the working state of the heating valve in real time and feeds back the state information to the intelligent communication management module to realize closed-loop control;

[0013] The system monitoring and maintenance module is used to monitor the operation status of the entire heating control system in real time, and centrally display the operation status of each module, communication quality, and the working conditions of heating equipment;

[0014] At the same time, it provides functions of remote maintenance, fault detection and alarm, data storage and log management, which is convenient for technicians to perform system configuration, upgrade, and fault diagnosis through the remote maintenance interface.

[0015] Preferably, the intelligent communication management module includes:

[0016] A multi-band wireless communication interface configured to support at least two different wireless frequency bands, including 2.4GHz, 5GHz, 900MHz, and used for dynamic switching between the frequency bands;

[0017] An intelligent interference identification unit that uses machine learning algorithms to analyze the wireless communication environment in real time and identify the types and sources of interference;

[0018] A protocol adaptation engine dynamically adjusts communication parameters according to the output of the intelligent interference recognition unit, including modulation mode, transmission rate, and transmit power.

[0019] Preferably, the real-time environment perception module includes:

[0020] A multi-sensor integration device configured to include a temperature sensor, a humidity sensor, a vibration sensor, and a light sensor for comprehensively monitoring the operating state of the heat medium in the heating system;

[0021] A data acquisition and processing circuit continuously acquires data from the sensors and transmits it to the data processing center in real time;

[0022] An environment data analyzer establishes an interference prediction model through machine learning algorithms, predicts future interference situations based on historical and real-time environment data, and outputs interference prediction results.

[0023] Preferably, the process by which the environment data analyzer establishes an interference prediction model through machine learning algorithms, predicts future interference situations based on historical and real-time environment data, and outputs interference prediction results includes:

[0024] Collect the environment sensor data accumulated during the system operation as historical environment data, and at the same time collect the wireless communication performance metrics during the corresponding time period as communication performance data. The historical environment data includes temperature, humidity, vibration, and light parameters, and the communication performance data includes signal strength, bit error rate, and transmission rate. Deploy multiple environment sensors at the key nodes of the control system to monitor the environment parameters in real time, set the data acquisition frequency (such as per second, per minute) to capture the dynamic characteristics of the environment changes, and transmit the real-time acquired environment data to the data processing center through a wired or wireless communication interface, so as to obtain real-time environment data; clean and perform standardization and normalization processing on the obtained data, and then perform data synchronization and alignment, and perform feature extraction. When preprocessing the data, identify and remove the outliers in the sensor data, such as extreme values caused by sensor failures, and use interpolation methods to fill in the missing data points to ensure data integrity; convert the data of different sensors to a unified scale (such as zero mean unit variance) to eliminate the influence of dimensional differences, and scale the data to a specific range (such as 0 to 1) to improve the training efficiency and stability of machine learning algorithms;

[0025] Calculate the mean, variance, maximum, minimum, kurtosis, and skewness statistics of environmental parameters to capture the central tendency and dispersion of the data and obtain statistical features; extract the frequency characteristics of vibration and noise signals through Fourier transform or wavelet transform to identify periodic interference patterns and clarify frequency-domain features; analyze trends, seasonality, and mutation points in time-series data to capture the dynamic characteristics of environmental changes and obtain time-series features; evaluate the correlation between each feature and wireless communication performance indicators, select features with a correlation coefficient greater than 0.8, and apply principal component analysis (PCA) and linear discriminant analysis (LDA) to reduce the feature dimension, retain the main information, and reduce the model complexity. At the same time, use decision trees and random forests to evaluate the importance of features and select key features;

[0026] Divide the preprocessed dataset into a training set and a test set according to a ratio (e.g., 70% training set, 30% test set) for model training and evaluation. At the same time, adopt the K-fold cross-validation method to ensure the stability and generalization ability of the model on different data subsets. For supervised learning algorithms, select supervised learning algorithms suitable for interference prediction, including support vector machines, random forests, gradient boosting trees, and neural networks. For unsupervised learning algorithms, when needed, use clustering analysis to discover potential patterns and associations between environmental changes and communication performance; use the training set data to train the selected machine learning model. The machine learning model includes support vector machines (SVM), random forests, gradient boosting trees, and deep neural networks to build an interference prediction model. At the same time, decision trees, clustering algorithms, principal component analysis (PCA), and linear discriminant analysis (LDA) can also be combined for feature selection and dimensionality reduction to learn the relationship between environmental parameters and communication performance. Optimize the hyperparameters of the model through grid search, random search, or Bayesian optimization, and use the test set to evaluate the accuracy, precision, recall, and F1 score of the model, and select the model with the best performance;

[0027] Continuously receive real-time data from environmental sensors and perform the same preprocessing and feature extraction steps as during training. Based on the real-time data, construct a feature vector consistent with the training model to ensure the consistency and accuracy of the prediction. Input the feature vector extracted in real time into the trained interference prediction model to predict the interference situation. The model outputs the prediction result according to the input features, outputting the interference intensity, type, and possible communication performance indicators affected in the current or future period (such as signal attenuation and increased bit error rate);

[0028] Based on the model prediction results, evaluate the specific impact of environmental changes on wireless communication, such as the expected signal strength degradation or the increase in bit error rate; classify the predicted interference situations into three risk levels: low, medium, and high; according to the impact assessment results, propose corresponding suggestions for adjusting communication strategies, such as switching communication frequency bands, adjusting transmission power, changing modulation methods, and trigger a warning or alarm mechanism when detecting high-risk interference situations to notify the system administrator or automatically take emergency measures;

[0029] Transmit the decision-making suggestions to the intelligent communication management module to execute the corresponding communication strategy adjustments to optimize communication performance and stability. Through the feedback mechanism, continuously monitor the communication effect after adjustment to further optimize the interference prediction model and decision-making strategy, and enhance the overall anti-interference ability of the system.

[0030] Preferably, the adaptive frequency allocation and spectrum management module includes:

[0031] A dynamic frequency selection algorithm that intelligently selects the optimal communication frequency band based on the output of the real-time environment perception module;

[0032] An adaptive modulation and encoder that dynamically adjusts the modulation method and coding strategy according to the current communication environment.

[0033] Preferably, the process of the dynamic frequency selection algorithm intelligently selecting the optimal communication frequency band based on the output of the real-time environment perception module includes:

[0034] Conduct a comprehensive scan of the wireless frequency bands supported by the system, including 2.4 GHz, 5 GHz, and 900 MHz, detect the signal strength, interference level, and channel utilization rate of each frequency band to obtain the current channel state of the frequency band. Conduct a real-time evaluation of the current channel state of each frequency band, including measuring the signal-to-noise ratio (SNR), received signal strength indicator (RSSI), and the number of interference sources, to obtain the communication quality indicators of each frequency band. According to the system design requirements and application scenarios, preset the priority of each frequency band, including 2.4 GHz prior to 5 GHz, and 5 GHz prior to 900 MHz, formulate a frequency band selection strategy, determine the frequency band selection rules under different interference and channel utilization rate situations to optimize the overall communication performance and spectrum utilization efficiency, set a scoring mechanism, assign a comprehensive score to each frequency band, and the assignment process includes: a high signal strength gets a high score, a high signal-to-noise ratio gets a high score, a low interference level gets a high score, and a low channel utilization rate gets a high score; according to the preset priority and scoring mechanism, conduct a comprehensive evaluation of the frequency bands, and select the frequency band with the highest score and meeting the priority requirements as the current optimal communication frequency band;

[0035] Determine whether the communication quality of the currently used frequency band is lower than a preset threshold (such as the signal-to-noise ratio is lower than the set noise threshold or the interference level exceeds the interference threshold). When it is detected that the communication quality of the current frequency band is poor, trigger the frequency band switching process. According to the selected optimal frequency band, adjust the communication protocol parameters, such as frequency, bandwidth, and modulation method, to adapt to the characteristics of the new frequency band. Control the radio frequency front end of the multi-band wireless communication interface and switch to the selected frequency band, including adjusting the antenna, filter, and power amplifier, to ensure signal synchronization and data transmission coordination during the switching process and avoid data loss or communication interruption.

[0036] Preferably, the adaptive modulation and encoder dynamically adjust the modulation method and coding strategy according to the current communication environment. The process is as follows: The adaptive modulation and encoder continuously monitor the state of the current communication channel, including signal strength (RSSI), signal-to-noise ratio (SNR), bit error rate (BER), and interference level, and obtain the environmental data provided by the real-time environment perception module, such as temperature, humidity, vibration, and light, to evaluate the potential impact of the environmental data on the communication channel; preset modulation schemes, including binary phase shift keying, quaternary phase shift keying, 16-QAM, and 64-QAM. Based on the current channel state and environmental data, evaluate the anti-interference ability, data transmission rate, and energy efficiency of each modulation method under the current conditions, and select the modulation method that can provide the best balance in the current communication environment. For example, select a high-order modulation method under high signal-to-noise ratio and low interference conditions to increase the data transmission rate; select a low-order modulation method under low signal-to-noise ratio or high interference conditions to enhance the anti-interference ability; preset coding schemes, including convolutional coding, low-density parity-check coding, and Turbo coding. According to the current communication environment, evaluate the impact of different coding rates on data integrity and transmission efficiency. Among them, a high coding rate is suitable for a high-interference environment to improve data reliability, and a low coding rate is suitable for a low-interference environment to increase the transmission rate. Select the coding strategy and coding rate suitable for the current channel conditions to ensure the accuracy and efficiency of data transmission and determine the optimal coding strategy; perform parameter configuration and implementation. According to the selected modulation method, adjust the communication protocol parameters, such as carrier frequency, phase offset, and amplitude modulation, to match the new modulation scheme and complete the modulation method configuration; according to the selected coding strategy and coding rate, configure the corresponding encoder and decoder parameters to ensure the correct encoding and decoding of data at the transmitting and receiving ends and complete the coding strategy configuration; ensure that the radio frequency front end and the communication processing unit support the switching of the selected modulation method and coding strategy and coordinate the hardware configuration and software control.

[0037] Preferably, the device control and execution module includes:

[0038] A wireless control interface that receives control instructions from the intelligent communication management module;

[0039] The heating valve drive unit drives the heating valve according to the control instruction to realize the flow control of liquid or gas;

[0040] The feedback sensor monitors the state (open / closed) of the heating valve and feeds back the state information to the system;

[0041] The local processor processes the control instruction and feedback data for local decision-making and optimization;

[0042] Among them, the feedback sensor feeds back the real-time state of the heating valve to the intelligent communication management module through the local processor to ensure the accurate execution of the control instruction.

[0043] Preferably, the system monitoring and maintenance module is configured with a remote monitoring platform, a fault detection and alarm system, a data storage and log management device, and a remote maintenance interface. The remote monitoring platform is used to centrally display the operating status, communication quality, and device status of each module of the system; the fault detection and alarm system is used to detect system anomalies in real time and issue alarms in a timely manner. The data storage and log management device records the system operation data and event logs, and the remote maintenance interface allows technicians to configure, upgrade, and maintain the system through the network.

[0044] Preferably, the system realizes the control process through the following steps:

[0045] S1: The intelligent communication management module selects the optimal communication frequency band and adjusts the communication parameters according to the current wireless environment;

[0046] S2: The real-time environment perception module continuously monitors the environmental changes and predicts potential interferences;

[0047] S3: The adaptive frequency allocation and spectrum management module optimizes the spectrum resource allocation based on the environmental perception results;

[0048] S4: The device control and execution module receives and executes the control instruction to adjust the state of the heating valve;

[0049] S5: The system monitoring and maintenance module monitors the system operation status in real time for fault detection and remote maintenance;

[0050] Among them, the above steps ensure the efficient, stable, and reliable operation of the system in a complex environment through the collaborative work of the modules.

[0051] (III) Beneficial effects

[0052] The present invention provides a remote wireless heating valve control system based on the Internet of Things. It has the following beneficial effects:

[0053] The present invention adopts a remote wireless heating valve control system based on the Internet of Things. Through adaptive multi-band dynamic switching and intelligent interference recognition technology, it effectively solves the problem of unstable transmission of control instructions caused by wireless interference in complex environments of the heating system. This system not only improves the reliability and stability of heating control data transmission, but also optimizes heat energy distribution and resource utilization, reduces system operation costs, and significantly enhances the competitiveness and adaptability of the system in the fields of central heating, commercial buildings, and large residential areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a schematic framework diagram of the whole of the present invention;

[0055] Figure 2 It is a schematic control flow diagram of this remote wireless heating valve control system. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0057] Please refer to Figure 1 and Figure 2 , the present invention provides a technical solution: a remote wireless heating valve control system based on the Internet of Things, including an intelligent communication management module, a real-time environment perception module, an adaptive frequency allocation and spectrum management module, a device control and execution module, and a system monitoring and maintenance module. Among them, data exchange and collaborative work are carried out between each module through wired or wireless communication interfaces. This system includes:

[0058] The intelligent communication management module is used to implement a hybrid communication protocol that combines adaptive multi-band dynamic switching and intelligent interference recognition. When the intelligent communication management module detects high interference in the current communication band, it automatically switches to another low-interference band to maintain communication stability. The real-time environment perception module is used to collect and analyze system operation environment data, and based on the output of the interference prediction model, adjusts the communication strategy in advance to avoid potential interference. The adaptive frequency allocation and spectrum management module is used to work collaboratively between different control nodes to avoid frequency band conflicts and congestion, optimize spectrum resource utilization, and ensure efficient digital information transmission. The device control and execution module is used to accurately control the opening and closing of the wireless heating valve according to the received control instructions. The system monitoring and maintenance module is used to monitor the operation status of the entire heating control system in real time and provide remote maintenance and fault diagnosis functions.

[0059] The intelligent communication management module includes:

[0060] The intelligent communication management module contains multi-band wireless communication interfaces, supporting different wireless bands of 2.4 GHz, 5 GHz, and 900 MHz. It adopts adaptive multi-band dynamic switching technology to achieve anti-interference transmission. An intelligent interference recognition unit is provided in the intelligent communication management module, which analyzes the wireless communication environment in real time through machine learning algorithms to identify the types and sources of interference. The protocol adaptation engine dynamically adjusts communication parameters (including modulation mode, transmission rate, and transmit power) according to the interference recognition results to ensure the stability of the heat supply control data transmission.

[0061] It should be further noted that in the specific implementation process, the process of the protocol adaptation engine dynamically adjusting communication parameters, including modulation mode, transmission rate, and transmit power, according to the output of the intelligent interference recognition unit includes: receiving interference data from the intelligent interference recognition unit. The interference data includes interference intensity, interference type, and interference source location information. Among them, the receiving frequency and timestamp are synchronized to ensure the timeliness and accuracy of the interference data. Analyze the received interference data, evaluate the interference degree of the current communication link and its impact on signal strength and bit error rate in communication performance, determine the nature and source of the interference, identify whether it is co-channel interference, cross-channel interference, or impulse interference, and obtain the interference evaluation result. According to the interference evaluation result, through a preset decision algorithm, determine the communication parameters that need to be adjusted, set the adjustment priority, and determine the adjustment order. The adjustment priority includes adjusting the modulation mode first, then the transmission rate, and finally the transmit power; for the modulation mode adjustment, switch the modulation scheme, switch from BPSK (Binary Phase Shift Keying) to QPSK (Quadrature Phase Shift Keying) to improve the anti-interference ability.

[0062] Apply adaptive modulation, dynamically select the optimal modulation mode according to the current channel conditions. For the transmission rate adjustment, dynamically adjust the data transmission rate, reduce the rate in a high-interference environment to reduce the bit error rate, or increase the rate in a low-interference environment to improve data throughput. Adopt adaptive coding technology to adjust the coding mode according to the change of the transmission rate to ensure data integrity; for the transmit power adjustment, according to the distance and interference situation, increase the transmit power to enhance the signal coverage range, or reduce the transmit power to reduce interference to other devices, and implement power adaptive adjustment to balance communication quality and energy consumption.

[0063] Monitor the adjusted communication performance, where the communication performance includes signal strength, bit error rate, and transmission stability. Execute the feedback mechanism to feed back the adjusted communication performance data to the protocol adaptation engine, evaluate the adjustment effect, record the adjustment process and effect, and accumulate historical data for subsequent analysis and model optimization. Use machine learning algorithms to analyze the historical adjustment data, optimize the parameter adjustment strategy, improve the accuracy and response speed of future adjustments, and continuously optimize to ensure that the protocol adaptation engine can cope with the dynamically changing wireless environment and maintain the efficient operation of the communication system.

[0064] It should be further noted that in the specific implementation process, the multi-band wireless communication interface, configured to support at least two different wireless bands, including 2.4 GHz, 5 GHz, and 900 MHz, and the process for dynamic switching between bands includes: The multi-band wireless communication interface continuously scans and detects the currently supported wireless bands, including the channel status of 2.4 GHz, 5 GHz, and 900 MHz, including signal strength, interference level, and channel utilization, and monitors the environmental changes of each band in real time. When a new interference source appears, evaluate the availability and communication quality of each band. According to the preset band priority: 2.4 GHz is prior to 5 GHz, and 5 GHz is prior to 900 MHz, formulate an initial band selection strategy. According to the real-time monitoring results, dynamically evaluate the communication quality and interference status of each band, and adjust the band selection strategy to optimize the communication performance. When the interference level of the currently used band exceeds the preset interference threshold, trigger the band switching mechanism. Based on the real-time monitoring data and the band selection strategy, select the standby band with the least current interference and the best communication quality for switching. Confirm that the standby band has sufficient signal strength and low interference level during switching to ensure the communication stability after switching. According to the selected standby band, adjust the communication protocol parameters, including frequency, bandwidth, and modulation method, to match the characteristics of the new band. Control the radio frequency front end of the multi-band wireless communication interface to switch to the selected standby band, including adjusting the antenna, filter, and power amplifier, to ensure signal synchronization and data transmission coordination during the switching process, and avoid data loss or communication interruption. After switching to the standby band, immediately verify the communication quality to obtain the switching result, including signal strength, bit error rate, and transmission rate, to ensure the success of the switching. Feed back the switching result to the intelligent communication management module for updating the band selection strategy and optimizing future switching decisions. When the communication quality of the standby band resumes to a high level, the system can automatically switch back to the higher-priority primary band to optimize resource utilization. During the band switching process, send a notification to the system administrator or user to inform the switching status and the current communication band. When the band switching fails or the standby band cannot provide stable communication, trigger the alarm mechanism to prompt the need for manual intervention or system adjustment.

[0065] The process by which the environmental data analyzer establishes an interference prediction model through machine learning algorithms, predicts future interference situations based on historical and real-time environmental data, and outputs interference prediction results includes: collecting environmental sensor data accumulated during system operation as historical environmental data, and at the same time collecting wireless communication performance metrics during the corresponding time period as communication performance data. The historical environmental data includes temperature, humidity, vibration, and light parameters, and the communication performance data includes signal strength, bit error rate, and transmission rate. Deploy multiple environmental sensors at key nodes of the control system to monitor environmental parameters in real time, capture the dynamic characteristics of environmental changes once per second, and transmit the real-time collected environmental data to the data processing center through a wired or wireless communication interface, thereby obtaining real-time environmental data; clean and perform standardization and normalization processing on the obtained data, then perform data synchronization and alignment, and perform feature extraction. When preprocessing the data, identify and remove extreme values caused by sensor failures, and use interpolation methods to fill in missing data points to ensure data integrity; convert the data of different sensors into a unified scale with zero mean and unit variance to eliminate the influence of dimensional differences, and scale the data to the range of 0 to 1 to improve the training efficiency and stability of machine learning algorithms.

[0066] Calculate the statistical quantities of the mean, variance, maximum value, minimum value, kurtosis, and skewness of environmental parameters to capture the central tendency and dispersion degree of the data and obtain statistical features; extract the frequency characteristics of vibration and noise signals through Fourier transform or wavelet transform to identify periodic interference patterns and clarify frequency domain features; analyze the trends, seasonality, and mutation points in time series data to capture the dynamic characteristics of environmental changes and obtain time series features; evaluate the correlation between each feature and wireless communication performance metrics, select features with a correlation coefficient greater than 0.8, and apply principal component analysis (PCA) and linear discriminant analysis (LDA) to reduce the feature dimension, retain the main information, and reduce the model complexity. At the same time, use decision trees and random forests to evaluate the importance of features and select key features.

[0067] Divide the preprocessed data set into a training set and a test set according to 70% training set and 30% test set for model training and evaluation. At the same time, adopt the K-fold cross-validation method to ensure the stability and generalization ability of the model on different data subsets. For supervised learning algorithms, select supervised learning algorithms suitable for interference prediction, including support vector machines, random forests, gradient boosting trees, and neural networks. For unsupervised learning algorithms, when needed, use clustering analysis to discover potential patterns and associations between environmental changes and communication performance; use the training set data to train the selected machine learning model to learn the relationship between environmental parameters and communication performance, optimize the hyperparameters of the model through grid search, random search, or Bayesian optimization, and use the test set to evaluate the accuracy, precision, recall, and F1 score of the model, and select the model with the best performance.

[0068] Continuously receive real-time data from environmental sensors, and perform the same preprocessing and feature extraction steps as during training. Based on the real-time data, construct a feature vector consistent with the training model to ensure the consistency and accuracy of predictions. Input the feature vector extracted in real time into the trained interference prediction model to predict the interference situation. The model outputs the prediction results according to the input features, including the interference intensity, type, and possible communication performance metrics that may be affected in a future period: signal attenuation and increased bit error rate.

[0069] Based on the model prediction results, evaluate the specific impact of environmental changes on wireless communication, such as the expected decrease in signal strength or increase in bit error rate; classify the predicted interference situation into three risk levels: low, medium, and high; according to the impact assessment results, propose corresponding suggestions for adjusting communication strategies, such as switching communication frequency bands, adjusting transmission power, and changing modulation methods. When a high-risk interference situation is detected, trigger an early warning or alarm mechanism to notify the system administrator or automatically take emergency measures; transmit the decision-making suggestions to the intelligent communication management module to execute the corresponding communication strategy adjustments to optimize communication performance and stability. Through a feedback mechanism, continuously monitor the communication effect after adjustment to further optimize the interference prediction model and decision-making strategy, and enhance the overall anti-interference ability of the system.

[0070] Continuously store the real-time monitored environmental data and communication performance data to form an ever-expanding historical data set, providing a rich data basis for model retraining; label the new data according to the actual communication performance, including normal, mild interference, and severe interference labels, enrich the training data, and improve the supervised learning effect of the model; regularly retrain the machine learning model with the latest historical data to enhance the adaptability and accuracy of the model, ensuring that it can cope with environmental changes and newly emerging interference patterns. Introduce an online learning algorithm to enable the model to update in real time in the data stream, quickly adapt to environmental changes, and maintain the real-time and accuracy of prediction capabilities. According to the feedback during system operation, dynamically adjust the data analysis and prediction model, optimize feature selection, model parameters, and prediction algorithms to ensure that the interference prediction model always has the best performance; continuously monitor the prediction accuracy and response speed of the model, promptly discover and solve problems with model performance degradation, and ensure the long-term stable operation of the system.

[0071] The process of the dynamic frequency selection algorithm, which intelligently selects the optimal communication frequency band based on the output of the real-time environment perception module, includes: comprehensively scanning the wireless frequency bands supported by the system, including 2.4 GHz, 5 GHz, and 900 MHz, detecting the signal strength, interference level, and channel utilization rate of each frequency band to obtain the current channel state of the frequency band, and conducting real-time evaluation of the current channel state of each frequency band, including measuring the signal-to-noise ratio (SNR), signal strength (RSSI), and the number of interference sources, to obtain the communication quality indicators of each frequency band. According to the system design requirements and application scenarios, preset the priorities of each frequency band, including 2.4 GHz prior to 5 GHz, and 5 GHz prior to 900 MHz, formulate a frequency band selection strategy, and determine the frequency band selection rules under different interference and channel utilization rate conditions to optimize the overall communication performance and spectrum utilization efficiency. Set a scoring mechanism to assign a comprehensive score to each frequency band. The assignment process includes: a high signal strength gets a high score, a high signal-to-noise ratio gets a high score, a low interference level gets a high score, and a low channel utilization rate gets a high score. According to the preset priorities and scoring mechanism, comprehensively evaluate the frequency bands, and select the frequency band with the highest score and meeting the priority requirements as the current optimal communication frequency band.

[0072] Judge whether the signal-to-noise ratio in the communication quality of the currently used frequency band is lower than the set noise threshold. When it is detected that the communication quality of the current frequency band is poor, trigger the frequency band switching process. According to the selected optimal frequency band, adjust the frequency, bandwidth, and modulation method in the communication protocol parameters to adapt to the characteristics of the new frequency band. Control the radio frequency front end of the multi-band wireless communication interface and switch to the selected frequency band, including adjusting the antenna, filter, and power amplifier to ensure signal synchronization and data transmission coordination during the switching process, and avoid data loss or communication interruption. After switching to the new frequency band, immediately verify the communication quality, including measuring the signal strength, bit error rate, and transmission rate, to ensure that the switching is successful and the communication quality meets the requirements. Feed back the communication quality data after switching to the intelligent communication management module for updating the frequency band selection strategy and optimizing future switching decisions. When the communication quality in the new frequency band resumes to a high level, the system can automatically switch back to the higher-priority main frequency band to optimize the spectrum resource utilization and communication efficiency. Record in detail the time, reason, and communication quality indicators before and after each frequency band switching to form a frequency band switching log, analyze the historical data of frequency band switching, use machine learning algorithms to optimize the frequency band selection and switching strategy, improve the accuracy and efficiency of future switching decisions, predict possible future interference situations based on historical data and real-time monitoring results, formulate a switching plan in advance, and reduce the risk of sudden communication interruption. During the frequency band switching process, send a notification to the system administrator or user to inform the switching status and the current communication frequency band to ensure that the user understands the system operation status. When the frequency band switching fails or the standby frequency band cannot provide stable communication, trigger an alarm mechanism to prompt the need for manual intervention or system adjustment to ensure that the system responds to abnormal situations in a timely manner.

[0073] The process includes frequency band scanning and detection, frequency band priority setting and strategy formulation, optimal frequency band selection, frequency band switching decision-making and execution, post-switch verification and optimization, historical record and learning optimization, as well as user and system notifications. Through these steps, the dynamic frequency selection algorithm can intelligently select the optimal communication frequency band based on the output of the real-time environment perception module, optimize the stability and anti-interference ability of wireless communication, and ensure the efficient operation of the Internet of Things-based remote wireless heating valve control system in a complex wireless environment.

[0074] The adaptive modulator and encoder dynamically adjust the modulation method and coding strategy according to the current communication environment. The process is as follows: The adaptive modulator and encoder continuously monitor the state of the current communication channel, including key indicators: signal strength (RSSI), signal-to-noise ratio (SNR), bit error rate (BER), and interference level, and obtain the environmental data provided by the real-time environment perception module, including: temperature, humidity, vibration, and light, and evaluate the potential impact of the environmental data on the communication channel; preset modulation schemes, including binary phase shift keying, quaternary phase shift keying, 16-QAM, and 64-QAM, and based on the current channel state and environmental data, evaluate the anti-interference ability, data transmission rate, and energy efficiency of each modulation method under the current conditions, and select the modulation method that can provide the best balance in the current communication environment. Select high-order modulation methods under high SNR and low interference conditions to increase the data transmission rate; select low-order modulation methods under low SNR or high interference conditions to enhance the anti-interference ability; preset coding schemes, including convolutional coding, low-density parity-check coding, and Turbo coding, and according to the current communication environment, evaluate the impact of different coding rates on data integrity and transmission efficiency. Among them, high coding rates are suitable for high-interference environments to improve data reliability, and low coding rates are suitable for low-interference environments to increase the transmission rate. Select the coding strategy and coding rate suitable for the current channel conditions to ensure the accuracy and efficiency of data transmission, and determine the optimal coding strategy; perform parameter configuration and implementation. According to the selected modulation method, adjust the carrier frequency, phase offset, or amplitude modulation in the communication protocol parameters to match the new modulation scheme, and complete the modulation method configuration; according to the selected coding strategy and coding rate, configure the corresponding encoder and decoder parameters to ensure the correct encoding and decoding of data at the transmitting and receiving ends, and complete the coding strategy configuration; ensure that the radio frequency front end and communication processing unit support the switching of the selected modulation method and coding strategy, and coordinate the hardware configuration and software control.

[0075] During the process of dynamically adjusting the modulation method and coding strategy, it includes communication environment evaluation, modulation method selection, coding strategy adjustment, parameter configuration and implementation; thus, the adaptive modulator and encoder can dynamically select the most suitable modulation method and coding strategy according to the current communication environment, and optimize the stability, data transmission rate, and anti-interference ability of wireless communication.

[0076] The system monitoring and maintenance module is configured with a remote monitoring platform, a fault detection and alarm system, a data storage and log management device, and a remote maintenance interface. The remote monitoring platform is used to centrally display the operating status, communication quality, and device status of each module of the system; the fault detection and alarm system is used to detect system anomalies in real time and send alarms in a timely manner, the data storage and log management device records the system operation data and event logs, and the remote maintenance interface allows technicians to perform system configuration, upgrade, and maintenance through the network.

[0077] As Figure 2 shown, the system realizes the control process through the following steps: S1: The intelligent communication management module selects the optimal communication frequency band and adjusts the communication parameters according to the current wireless environment; S2: The real-time environment perception module continuously monitors the environmental changes and predicts potential interferences; S3: The adaptive frequency allocation and spectrum management module optimizes the spectrum resource allocation based on the environmental perception results; S4: The device control and execution module receives and executes the control instructions, adjusts the status of the heating valve, and realizes the precise control of the heat medium; S5: The system monitoring and maintenance module monitors the system operation status in real time, performs fault detection and remote maintenance; the entire process ensures the efficient, stable, and safe operation of the heating system in a complex environment.

[0078] Among them, the above steps ensure the efficient, stable, and reliable operation of the system in a complex environment through the collaborative work of the modules; the intelligent communication management module and the real-time environment perception module continuously optimize the communication strategy and spectrum management through self-learning and adaptive mechanisms to adapt to the dynamically changing environmental conditions; among them, the self-learning and adaptive mechanism includes machine learning algorithms based on historical data and real-time data, which are used to continuously optimize interference recognition, frequency selection, and modulation strategies.

[0079] Through the implementation of the above technical solutions, the limitations of the existing anti-interference protocols in the prior art are solved, the single-frequency band dependence is avoided, the lack of flexibility of the fixed interference response strategy is avoided, and the problem that most anti-interference protocols fail to make full use of intelligent algorithms for interference recognition and classification, resulting in inaccurate interference response strategies and affecting communication efficiency, is solved. Through the implementation of the hybrid communication protocol technology that integrates adaptive multi-frequency band dynamic switching and intelligent interference recognition, the problems of unstable communication and insufficient anti-interference ability in the prior art in a complex environment are solved, and the problem that a large number of wireless devices and metal structures often present in the environment cause wireless signal interference, resulting in unstable or ineffective transmission of remote control instructions, is solved; it not only improves the communication reliability and stability of the system, but also optimizes resource utilization, reduces operating costs, and significantly enhances the competitiveness and adaptability of the system in practical applications.

[0080] It should be noted that, in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0081] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A remote wireless heating valve control system based on the Internet of Things, characterized in that, It includes an intelligent communication management module, a real-time environment perception module, an adaptive frequency allocation and spectrum management module, a device control and execution module, and a system monitoring and maintenance module. Among them, data exchange and collaborative work are carried out between the modules through wired or wireless communication interfaces; the intelligent communication management module is used to implement a hybrid communication protocol that integrates adaptive multi-band dynamic switching and intelligent interference identification, and is used to automatically switch to a low-interference frequency band when high interference is detected and dynamically adjust communication parameters; the intelligent communication management module integrates a multi-band wireless communication interface, supports 2.4GHz, 5GHz, and 900MHz frequency bands, and includes an intelligent interference identification unit, which uses a pre-trained neural network model to perform real-time data sampling, calculation of signal amplitude and signal-to-noise ratio on the received wireless signals, and analyze and quantify the interference intensity, type, and source; The real-time environment perception module is used to collect and analyze the system operation environment data, and based on the output of the interference prediction model, adjust the communication strategy in advance to avoid potential interference; the real-time environment perception module includes a multi-sensor integration device configured to include a temperature sensor, a humidity sensor, a vibration sensor, and a light sensor, and regularly collect key environmental parameters in the heating system and the operating state of the heating medium; the adaptive frequency allocation and spectrum management module is used to work collaboratively between different control nodes to avoid frequency band conflicts and congestion; the device control and execution module is used to accurately control the opening and closing of the wireless heating valve according to the received control instructions; the system monitoring and maintenance module is used to monitor the operation state of the entire heating control system in real time and provide remote maintenance and fault diagnosis functions; The intelligent communication management module includes: A protocol adaptation engine, which dynamically adjusts communication parameters according to the interference evaluation results output by the interference identification unit, including automatically switching between BPSK, QPSK, and 16-QAM modulation methods, adjusting the data transmission rate, and the transmit power, so as to achieve adaptive multi-band dynamic switching; The real-time environment perception module further includes: A data acquisition and processing circuit, which continuously collects the data of the sensors and transmits it to the data processing center in real time; An environmental data analyzer, which establishes an interference prediction model through machine learning algorithms, predicts future interference situations based on historical and real-time environmental data, and outputs interference prediction results; The adaptive frequency allocation and spectrum management module includes: A dynamic frequency selection algorithm, which intelligently selects the optimal communication frequency band based on the output of the real-time environment perception module; An adaptive modulation and encoder, which dynamically adjusts the modulation method and coding strategy according to the current communication environment; Among them, the process of the dynamic frequency selection algorithm intelligently selecting the optimal communication frequency band based on the output of the real-time environment perception module includes: Perform a comprehensive scan of the wireless frequency bands supported by the system, including 2.4 GHz, 5 GHz, and 900 MHz, detect the signal strength, interference level, and channel utilization rate of each frequency band, obtain the current channel state of the frequency band, and conduct real-time evaluation of the current channel state of each frequency band, including measuring the signal-to-noise ratio, signal strength, and the number of interference sources, obtain the communication quality indicators of each frequency band, preset the priorities of each frequency band according to the system design requirements and application scenarios, including 2.4 GHz prior to 5 GHz, and 5 GHz prior to 900 MHz, formulate a frequency band selection strategy, determine the frequency band selection rules under different interference and channel utilization rate conditions, set a scoring mechanism, assign a comprehensive score to each frequency band, and the assignment process includes: a high signal strength scores high, a high signal-to-noise ratio scores high, a low interference level scores high, and a low channel utilization rate scores high; according to the preset priorities and scoring mechanism, conduct a comprehensive evaluation of the frequency bands, and select the frequency band with the highest score and meeting the priority requirements as the current optimal communication frequency band; Judge whether the communication quality of the currently used frequency band is lower than the preset threshold. When it is detected that the communication quality of the current frequency band is poor, trigger the frequency band switching process, adjust the communication protocol parameters according to the selected optimal frequency band, control the radio frequency front end of the multi-band wireless communication interface, and switch to the selected frequency band.

2. The remote wireless heating valve control system based on the Internet of Things according to claim 1, wherein: The process by which the environmental data analyzer establishes an interference prediction model through machine learning algorithms, predicts future interference situations based on historical and real-time environmental data, and outputs interference prediction results includes: Collect the environmental sensor data accumulated during the operation of the system as historical environmental data, and at the same time collect the wireless communication performance indicators during the corresponding time period as communication performance data. Deploy a variety of environmental sensors at the key nodes of the control system to monitor environmental parameters in real time, set the data acquisition frequency to capture the dynamic characteristics of environmental changes, and obtain real-time environmental data; clean, standardize, and normalize the obtained data, and then perform data synchronization and alignment, and perform feature extraction; Calculate the statistical quantities of the mean, variance, maximum value, minimum value, kurtosis, and skewness of the environmental parameters to capture the central tendency and dispersion degree of the data, and obtain statistical features; extract the frequency characteristics of vibration and noise signals through Fourier transform or wavelet transform to identify periodic interference patterns and clarify frequency domain features; analyze the trends, seasonality, and mutation points in the time series data to capture the dynamic characteristics of environmental changes and obtain time series features; evaluate the correlation between each feature and the wireless communication performance indicators, screen out the features with a correlation coefficient greater than 0.8, and apply principal component analysis and linear discriminant analysis to reduce the feature dimension and retain the main information. At the same time, use decision trees and random forests to evaluate the importance of the features and screen out the key features; The preprocessed dataset is divided into a training set and a test set according to a certain proportion for the training and evaluation of the model. For supervised learning algorithms, a supervised learning algorithm suitable for interference prediction is selected. For unsupervised learning algorithms, when necessary, clustering analysis is used to discover potential patterns and associations between environmental changes and communication performance. The selected machine learning model is trained using the training set data to learn the relationship between environmental parameters and communication performance. The hyperparameters of the model are optimized through grid search, random search, or Bayesian optimization. The accuracy, precision, recall, and F1 score of the model are evaluated using the test set, and the model with the best performance is selected. Continuously receive real-time data from environmental sensors and perform the same preprocessing and feature extraction steps as during training. Based on the real-time data, construct a feature vector consistent with the trained model. Input the real-time extracted feature vector into the trained interference prediction model to predict the interference situation. The model outputs a prediction result based on the input features. Based on the model prediction results, evaluate the specific impact of environmental changes on wireless communication. Classify the predicted interference situations into three risk levels: low, medium, and high. According to the impact evaluation results, propose corresponding suggestions for adjusting communication strategies. When a high-risk interference situation is detected, trigger a warning or alarm mechanism to notify the system administrator or automatically take emergency measures. Transfer the decision-making suggestions to the intelligent communication management module to execute the corresponding communication strategy adjustments to optimize communication performance and stability. Through a feedback mechanism, continuously monitor the communication effect after adjustment to further optimize the interference prediction model and decision-making strategy, and enhance the overall anti-interference ability of the system.

3. The remote wireless heating valve control system based on the Internet of Things according to claim 1, characterized in that: The adaptive modulation and encoder dynamically adjust the modulation method and coding strategy according to the current communication environment, and the process is as follows: The adaptive modulation and encoder continuously monitor the state of the current communication channel, obtain the environmental data provided by the real-time environment perception module, and evaluate the potential impact of the environmental data on the communication channel. Preset modulation schemes, including binary phase shift keying, quaternary phase shift keying, 16-QAM, and 64-QAM. Based on the current channel state and environmental data, evaluate the anti-interference ability, data transmission rate, and energy efficiency of each modulation method under the current conditions, and select the modulation method that can provide the best balance in the current communication environment. Preset coding schemes, including convolutional coding, low-density parity-check coding, and Turbo coding. According to the current communication environment, evaluate the impact of different coding rates on data integrity and transmission efficiency, select the coding strategy and coding rate suitable for the current channel conditions, and determine the optimal coding strategy. Perform parameter configuration and implementation. According to the selected modulation method, adjust the communication protocol parameters to match the new modulation scheme and complete the modulation method configuration. According to the selected coding strategy and coding rate, configure the corresponding encoder and decoder parameters to complete the coding strategy configuration.

4. The remote wireless heating valve control system based on the Internet of Things according to claim 3, wherein: The device control and execution module includes: A wireless control interface for receiving control instructions from the intelligent communication management module; A heating valve drive unit for driving the heating valve according to the control instructions to achieve the flow control of liquid or gas; A feedback sensor for monitoring the status of the heating valve and feeding back the status information to the system; A local processor for processing control instructions and feedback data, and making local decisions and optimizations; Among them, the feedback sensor is also used to feed back the real-time status of the heating valve to the intelligent communication management module through the local processor.

5. The remote wireless heating valve control system based on the Internet of Things according to claim 4, characterized in that: The system monitoring and maintenance module is configured with a remote monitoring platform, a fault detection and alarm system, a data storage and log management device, and a remote maintenance interface. The remote monitoring platform is used to centrally display the operating status, communication quality, and device status of each module of the system; the fault detection and alarm system is used to detect system anomalies in real time and issue alarms in a timely manner. The data storage and log management device records system operation data and event logs, and the remote maintenance interface allows technicians to configure, upgrade, and maintain the system through the network.

6. The remote wireless heating valve control system based on the Internet of Things according to claim 5, characterized in that: The system realizes the control process through the following steps: S1: The intelligent communication management module selects the optimal communication frequency band and adjusts communication parameters according to the current wireless environment; S2: The real-time environment perception module continuously monitors environmental changes and predicts potential interference; S3: The adaptive frequency allocation and spectrum management module optimizes the allocation of spectrum resources based on the results of environmental perception; S4: The device control and execution module receives and executes control instructions to adjust the status of the heating valve; S5: The system monitoring and maintenance module monitors the operating status of the system in real time, and performs fault detection and remote maintenance; Among them, the above steps ensure the efficient, stable, and reliable operation of the system in a complex environment through the collaborative work of the modules.

Images