A transformer and distribution air conditioner load monitoring terminal and method thereof

Abstract

The present invention discloses a transformer and distribution air conditioner load monitoring terminal and method thereof, comprising: a data acquisition monitoring module, an intelligent control and adjustment module, for receiving real-time data and automatically adjusting the operating state of the air conditioner according to an intelligent algorithm, including energy-saving mode adjustment based on the activity of people in the room; a communication interface module, a safety guarantee redundancy module, a user interface module, and a remote maintenance and upgrade module. The present invention greatly improves the energy efficiency management and user experience of the air conditioning system through comprehensive data acquisition, intelligent operation regulation, stable data transmission, perfect fault detection and recovery mechanism, friendly user interface design, and powerful remote maintenance and upgrade functions. Through the intelligent fault detection and recovery mechanism, the present invention can also dynamically adjust and optimize system parameters according to actual use conditions to meet the needs of different users and environments, and has broad application prospects and significant technical advantages in the field of air conditioning load monitoring and regulation.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning load monitoring, and in particular to a transformer and distribution air conditioning load monitoring terminal and method thereof. Background Art

[0002] Air conditioning systems are essential equipment in modern buildings, especially in summer and winter, and play a vital role in regulating indoor temperature and comfort. However, existing air conditioning load monitoring technologies still have many deficiencies in energy efficiency management, intelligent regulation, and user experience, as shown below:

[0003] Incomplete data collection: Existing air conditioning monitoring systems usually only collect limited parameters, such as temperature and humidity, while ignoring the monitoring of power parameters such as three-phase current and voltage. This makes it impossible for the system to fully grasp the actual operating status and energy consumption of air conditioning equipment, making it difficult to conduct accurate energy efficiency analysis and optimization.

[0004] Lack of intelligent control capabilities: Most current air conditioning control systems rely on preset fixed modes and cannot be dynamically adjusted based on real-time data. For example, when the activity of people in the room changes, the system cannot automatically adjust the operating status of the air conditioner, resulting in increased energy consumption or reduced user comfort.

[0005] Unstable communication and data transmission: The existing system also has certain problems in data transmission and communication, especially in the wireless communication environment, the stability and reliability of data transmission are difficult to guarantee. This will lead to inaccurate monitoring data and affect the overall performance of the system.

[0006] Imperfect fault detection and recovery mechanism: Existing air-conditioning systems often lack timely fault detection and switching mechanisms when the main power fails, and cannot ensure the continuous operation of the air-conditioning system. This not only affects the user experience, but may also cause equipment damage.

[0007] Unfriendly user interface design: Many existing air conditioning monitoring systems have complex user interfaces and inconvenient operations, making it difficult for users to intuitively understand the system status or perform operations through the interface. This unfriendly design greatly reduces the ease of use and user satisfaction of the system.

[0008] Insufficient remote maintenance and upgrade capabilities: Currently, most air conditioning systems do not have remote maintenance and upgrade capabilities, and users can only rely on on-site technicians for maintenance and updates. This not only increases maintenance costs, but may also result in the system being unable to expand and optimize functions in a timely manner. Summary of the invention

[0009] In order to solve the problems of incomplete data collection, lack of intelligent control capability, unstable communication and data transmission, imperfect fault detection and recovery mechanism, unfriendly user interface design, and insufficient remote maintenance and upgrade capabilities, the present invention proposes a transformer and distribution air-conditioning load monitoring terminal and method thereof, which greatly improves the energy efficiency management and user experience of the air-conditioning system through comprehensive data collection, intelligent operation control, stable data transmission, perfect fault detection and recovery mechanism, friendly user interface design, and remote maintenance and upgrade functions, and overcomes the shortcomings of the prior art.

[0010] In order to achieve the above object, the present invention is implemented by the following technical solutions:

[0011] A transformer and distribution air conditioner load monitoring terminal, the terminal comprising:

[0012] Data acquisition and monitoring module, used to collect three-phase current, voltage, and ambient temperature parameters in real time, and continuously monitor the operating status of the air-conditioning equipment, including but not limited to switch status, working mode, set temperature, wind speed and wind direction, and monitor the activities of people in the room;

[0013] The intelligent control and regulation module is connected to the data acquisition and monitoring module to receive real-time data and automatically adjust the operation status of the air conditioner according to the improved adaptive intelligent load control model, including energy-saving mode adjustment based on the activities of people in the room;

[0014] Communication interface module, used to realize data transmission and communication within and outside the system;

[0015] Safety assurance redundancy module, used to build the system's safety assurance system and provide fault detection and recovery mechanisms;

[0016] The user interface module is connected to the intelligent control and adjustment module and is used to display monitoring data, system status and user control options, providing an intuitive and easy-to-use operation interface;

[0017] The remote maintenance and upgrade module is connected to each module of the system to support remote maintenance and software upgrades.

[0018] Optionally, the passive infrared sensor PIR and the ultrasonic sensor in the data acquisition and monitoring module are used in the following combination:

[0019] The passive infrared sensor and ultrasonic sensor work simultaneously to detect the activities of people in the room and send the data to the data acquisition and monitoring module for data fusion processing;

[0020] Set the passive infrared sensor as the main sensor and the ultrasonic sensor as the auxiliary sensor;

[0021] According to the preset time period, the passive infrared sensor and ultrasonic sensor are alternately enabled to detect human activity.

[0022] Optionally, the improved adaptive intelligent load control model includes the following modules:

[0023] Step 1: Data preprocessing and feature extraction module, used to collect and standardize input data and historical air conditioning operation data. The standardized x′ formula is:

[0024]

[0025] Among them, x is the original data, μ is the mean of the data, and σ is the standard deviation of the data;

[0026] Step 2: LSTM prediction module, combined with CNN and Attention mechanism, is used to predict the air conditioner operation status based on standardized data. The LSTM prediction module adopts the following formula:

[0027] Forget Gate:

[0028] f t =σ(W f ·[h t-1 ,x t ]+b f )

[0029] Input Gate:

[0030] i t =σ(W i ·[h t-1 ,x t ]+b i )

[0031]

[0032] Status Update:

[0033]

[0034] Output Gate:

[0035] o t =σ(W o ·[h t-1 ,x t ]+b o )

[0036] h t =o t ·tanh(S t )

[0037] Among them, f t is the forget gate at time step t, it is the input gate at time step t, o t is the output gate at time step t, is the candidate state, S t is the air conditioning state, σ is the Sigmoid activation function, tanh is the hyperbolic tangent activation function, W f ,W i ,W c ,W o are the weight matrices of the forget gate, input gate, candidate state, and output gate respectively; b f ,b i ,b c ,b o are the bias vectors of the forget gate, input gate, candidate state and output gate respectively; [h t-1 ,x t ] is the concatenation of the hidden state of the previous time step t-1 and the input of the current time step t;

[0038] Step 3: DQN control decision module is used to select the optimal control action based on the air conditioner operation state predicted by LSTM. The DQN control module adopts the following formula:

[0039] Q value update formula:

[0040] Q(s t ,a t )=Q(s t ,a t )+α[r t +γmaxQ(s t+1 ,a)-Q(s t ,a t )]

[0041] Among them, s t is the current state, a t is the current action, r t is the current reward, γ is the discount factor, and α is the learning rate;

[0042] The specific implementation steps are as follows:

[0043] a. Take the air conditioning state predicted by LSTM as the current state S t ;

[0044] b. Define air conditioning control action a t ;

[0045] c. Design reward function r based on energy consumption and user comfort t ;

[0046] d. Iteratively update the Q value table through the Q value update formula;

[0047] e. Select the optimal action a according to the Q value table t ;

[0048] Step 4: Execute the control module to adjust the air conditioner operation state according to the output of the DQN control decision module;

[0049] Step 5: Feedback optimization and parameter adjustment module, which is used to monitor real-time data, and continuously adjust and optimize the algorithm parameters of the LSTM prediction module and the DQN control decision module according to the feedback results, for air conditioning load monitoring and control;

[0050] Step 6: Edge computing and model compression module is used to improve the efficiency and response speed of the system during air conditioning load monitoring. It specifically includes the following sub-steps: data preprocessing and distribution, model segmentation and deployment, edge computing and decision-making, data feedback and optimization; model pruning, model quantization, knowledge distillation, model sharding and loading.

[0051] Optionally, the improved adaptive intelligent load control model further includes:

[0052] a. Preprocess the collected data, remove noise and standardize the data;

[0053] b. Based on the user usage pattern, a clustering algorithm is used for pattern recognition, including the following steps:

[0054] 1) Initialize multiple cluster centers;

[0055] 2) Assign data points to the nearest cluster center;

[0056] 3) Recalculate the location of the cluster center;

[0057] 4) Repeat the data point allocation and cluster center calculation until the cluster center no longer changes;

[0058] c. Based on the recognition results of user usage patterns, the Bayesian network is used to predict future air conditioning usage. The Bayesian network model includes the following formulas:

[0059]

[0060] Where X is the unobserved situation, Y is the current mode; P(X|Y) is the conditional probability of X when Y is known, P(Y|X) is the conditional probability of Y when X is known; P(X) is the prior probability of X; P(Y) is the prior probability of Y;

[0061] d. Dynamically adjust the operating status of the air conditioner, including temperature setting and wind speed adjustment, based on the Bayesian network prediction results;

[0062] e. Dynamically adjust the prediction model and operating status according to actual usage.

[0063] Optionally, the communication interface module also includes a wireless communication unit for wireless communication via Wi-Fi, Bluetooth and Zigbee protocols.

[0064] Optionally, the safety assurance redundant module includes one or more redundant power supply modules, which are used to provide backup power supply when the main power supply fails, and the redundant power supply module includes:

[0065] A power monitoring module that monitors the main power status in real time and triggers the backup power switch in case of failure;

[0066] A switch control module that automatically switches to backup power when the main power fails and ensures a seamless transition;

[0067] A backup power module that includes a battery pack or uninterruptible power supply (UPS) with sufficient capacity and supports charge and discharge management;

[0068] A status feedback module that provides real-time feedback on the power status and automatically switches back to the main power supply after the main power supply is restored;

[0069] Fault detection and alarm module that alerts the user in the event of a power failure and records all events;

[0070] A periodic self-check module that periodically self-checks the status of the backup power supply and feeds back the results.

[0071] Optionally, the user interface module includes a touch screen and a voice recognition unit, which are used for the user to control and view the air conditioner operating status and parameters through touch operation or voice command.

[0072] Optionally, the remote maintenance and upgrade module includes a cloud platform interface for connecting to the cloud platform via the Internet to achieve remote data storage, analysis and system updates.

[0073] Optionally, the data acquisition and monitoring module further includes a light sensor and a humidity sensor for monitoring ambient light and humidity parameters and adjusting the operating mode of the air conditioner according to these parameters.

[0074] A method for monitoring a transformer and distribution air conditioner load, the method comprising:

[0075] S1: The data acquisition and monitoring module collects three-phase current, voltage, and ambient temperature parameters in real time, and continuously monitors the operating status of the air-conditioning equipment, including but not limited to the switch status, working mode, set temperature, wind speed and wind direction, and monitors the activities of people in the room;

[0076] S2: The data collected by the data acquisition and monitoring module is transmitted to the intelligent control and regulation module for data preprocessing and feature extraction;

[0077] S3: Predict the air conditioner operation status based on the preprocessed data through the LSTM prediction module of the intelligent control and regulation module;

[0078] S4: According to the prediction results of the LSTM prediction module, the DQN control module selects the optimal control action to adjust the operating state of the air conditioner;

[0079] S5: Realize data transmission and communication inside and outside the system through the communication interface module;

[0080] S6: When the main power supply fails, the safety redundancy module automatically switches to the backup power supply and ensures seamless transition;

[0081] S7: Displays monitoring data, system status and user control options through the user interface module, providing an intuitive and easy-to-use operation interface;

[0082] S8: Connect to the cloud platform through the remote maintenance and upgrade module to perform remote data storage, analysis and system updates;

[0083] S9: Dynamically adjust the operating status of the air conditioner, including temperature setting and wind speed adjustment, and dynamically adjust the prediction model and operating status according to actual usage.

[0084] Compared with the prior art, the beneficial effects of the present invention are as follows: the data acquisition monitoring module of the present invention realizes comprehensive monitoring of air-conditioning equipment. This multi-parameter comprehensive monitoring method enables the system to more accurately grasp the actual operation status and energy consumption level of air-conditioning equipment, thereby performing more accurate energy efficiency analysis and optimization. The intelligent control and regulation module adopts the LSTM prediction algorithm and the DQN control algorithm, which can perform intelligent prediction and regulation based on real-time data. The system can dynamically adjust the operating state of the air conditioner according to the activities of people in the room, and realize automatic adjustment of the energy-saving mode. This intelligent control capability not only improves the energy efficiency of the system, but also enhances the comfort of the user. For example, when there is no one in the room, the system can automatically turn off the air conditioner to save energy; when people are active, the system can automatically adjust the temperature and wind speed to provide the best comfort. Support multiple wireless communication protocols (such as Wi-Fi, Bluetooth and Zigbee) to ensure the stability and reliability of data transmission and communication inside and outside the system. Even in a complex wireless communication environment, the system can maintain efficient and stable data transmission to ensure the accuracy of monitoring data. The safety guarantee redundancy module builds a complete safety guarantee system. When the main power supply fails, the system can monitor in real time and automatically switch to the backup power supply to ensure the continuous operation of the air-conditioning system. The module also includes fault detection and alarm functions, which can promptly send alarms to users and record fault events to facilitate subsequent troubleshooting and maintenance. The user interface module provides an intuitive touch screen and voice recognition function, allowing users to control and view the air conditioner operating status and parameters through simple touch operations or voice commands. This friendly interface design greatly improves the ease of use and user satisfaction of the system, allowing users to easily control the operation of the air conditioning system. The remote maintenance and upgrade module realizes remote data storage, analysis and system updates through the cloud platform interface. Users can perform remote diagnosis and maintenance through the Internet, reducing the cost and time of on-site maintenance. At the same time, the system can regularly update and optimize the software to ensure that the system is always in the best working condition to meet the ever-changing user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0086] in:

[0087] Figure 1 It is a modular structure diagram of an embodiment of the present invention;

[0088] Figure 2 A modular structure diagram of an adaptive intelligent load control module in an embodiment of the present invention;

[0089] Figure 3 Schematic diagram of the implementation steps of the intelligent control and regulation module in an embodiment of the present invention;

[0090] Figure 4 Schematic diagram of the implementation steps of the DQN control decision module in an embodiment of the present invention;

[0091] Figure 5 The figure is a flow chart of a method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0092] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0093] Example 1

[0094] like Figure 1 As shown in FIG. 1 , an embodiment of the present invention is provided, which provides a transformer and distribution air conditioner load monitoring terminal, including:

[0095] Data acquisition and monitoring module, used to collect three-phase current, voltage, and ambient temperature parameters in real time, and continuously monitor the operating status of the air-conditioning equipment, including but not limited to switch status, working mode, set temperature, wind speed and wind direction, and monitor the activities of people in the room;

[0096] Furthermore, the passive infrared sensor PIR and the ultrasonic sensor in the data acquisition and monitoring module are used in the following combination:

[0097] The passive infrared sensor and ultrasonic sensor work simultaneously to detect the activities of people in the room and send the data to the data acquisition and monitoring module for data fusion processing;

[0098] The passive infrared sensor (PIR) and ultrasonic sensor are turned on at the same time to detect the movement of people in the room independently. The PIR sensor detects changes in thermal radiation, and the ultrasonic sensor detects moving objects by emitting and receiving ultrasonic waves.

[0099] By using both sensors at the same time, the sensitivity and accuracy of human activity detection can be effectively improved. PIR sensors are sensitive to changes in thermal radiation, while ultrasonic sensors are sensitive to moving objects. The two complement each other and can more comprehensively monitor human activities in the room.

[0100] Using two sensors simultaneously can reduce false alarms through data fusion processing. When one sensor detects activity, it can be verified by the data from the other sensor, reducing the number of false positives caused by a single sensor.

[0101] The two sensors working simultaneously can provide more real-time and accurate data on personnel activities, helping the air-conditioning system to adjust its operating status in a timely manner and improve energy efficiency.

[0102] Set the passive infrared sensor as the main sensor and the ultrasonic sensor as the auxiliary sensor;

[0103] In daily use, the passive infrared sensor is set as the primary sensor, and the ultrasonic sensor is used as an auxiliary sensor for supplementary detection. The primary sensor works continuously, and the auxiliary sensor is activated for secondary confirmation when the primary sensor detects activity.

[0104] Setting the PIR sensor as the main sensor can reduce the frequent activation of the ultrasonic sensor, thereby reducing system power consumption, extending the service life of the sensor, and achieving energy-saving effects.

[0105] The primary sensor works continuously to provide basic data. When activity is detected, the auxiliary sensor starts to perform secondary confirmation, which improves the accuracy of detection and avoids unnecessary adjustments caused by false alarms from a single sensor.

[0106] By reducing the frequent activation of ultrasonic sensors, the wear and aging of sensors can be reduced, the service life of the equipment can be extended, and maintenance costs can be reduced.

[0107] According to the preset time period, the passive infrared sensor and ultrasonic sensor are alternately enabled to detect human activity.

[0108] According to the preset time period, the PIR sensor and ultrasonic sensor are alternately enabled for human activity detection. During a specific time period, one sensor is enabled for detection and the other sensor is in standby mode.

[0109] By alternately enabling sensors at preset time periods, flexible adjustments can be made according to usage requirements at different time periods. For example, when there is a large flow of people during the day, the ultrasonic sensor is enabled to ensure high sensitivity; when there is a small flow of people at night, the PIR sensor is enabled to save energy.

[0110] Alternating the activation of sensors can effectively reduce the overall energy consumption of the system and avoid the increase in energy consumption caused by turning on all sensors for a long time. At the same time, it also reduces the continuous working time of the sensors and reduces the load on the equipment.

[0111] According to the characteristics of different time periods, selecting appropriate sensors for detection can optimize the monitoring effect and improve the intelligent control ability of the air conditioning system. During peak hours, the alternating operation of dual sensors can provide more accurate detection data and improve the system response speed and control effect.

[0112] The data acquisition and monitoring module further includes a light sensor and a humidity sensor for monitoring ambient light and humidity parameters and adjusting the operating mode of the air conditioner according to these parameters.

[0113] The data acquisition and monitoring module is mainly responsible for real-time acquisition and monitoring of various parameters of air-conditioning equipment. The specific functions are as follows:

[0114] Real-time collection of three-phase current and voltage: This module collects three-phase current and voltage data in real time through sensors to ensure that the system can accurately monitor the power consumption of air-conditioning equipment.

[0115] Ambient temperature parameters: The module also includes an ambient temperature sensor, which is used to monitor the ambient temperature around the air-conditioning equipment and provide reference data for system control.

[0116] Monitor the operating status of air conditioners: Continuously monitor the operating status of air conditioners, including but not limited to:

[0117] Switch status: Detect the switch status of the air conditioner.

[0118] Working mode: monitor the working mode of the air conditioner (such as cooling, heating, ventilation, etc.).

[0119] Set temperature: record and monitor the temperature value set by the air conditioner.

[0120] Wind force and direction: monitor the wind force and direction of the air outlet from the air conditioner.

[0121] Monitor the activities of people in the room: Passive infrared sensors (PIR) and ultrasonic sensors are used to detect the activities of people in the room to adjust the operating mode of the air conditioner and achieve energy saving.

[0122] In an alternative embodiment, Figure 2 As shown, the intelligent control and regulation module is used to receive real-time data and automatically adjust the operating status of the air conditioner according to the intelligent algorithm, including the adjustment of the energy-saving mode based on the activities of people in the room;

[0123] Furthermore, the improved adaptive intelligent load control model includes the following modules:

[0124] Step 1: Data preprocessing and feature extraction module, used to collect and standardize input data and historical air conditioning operation data. The standardization formula is:

[0125]

[0126] Among them, x is the original data, μ is the mean of the data, and σ is the standard deviation of the data;

[0127] Step 2: LSTM prediction module, combined with CNN and Attention mechanism, is used to predict the air conditioner operation status based on standardized data. The LSTM prediction module adopts the following formula:

[0128] Forget Gate:

[0129] f t =σ(W f ·[h t-1 ,x t ]+b f )

[0130] Input Gate:

[0131] i t =σ(W i ·[h t-1 ,x t ]+b i )

[0132]

[0133] Status Update:

[0134]

[0135] Output Gate:

[0136] o t =σ(W o ·[h t-1 ,x t ]+b o )

[0137] h t =o t ·tanh(S t )

[0138] Among them, f t is the forget gate at time step t, i t is the input gate at time step t, o t is the output gate at time step t, is the candidate state, S t is the air conditioning state, σ is the Sigmoid activation function, tanh is the hyperbolic tangent activation function, W f ,W i ,W c ,W o are the weight matrices of the forget gate, input gate, candidate state, and output gate respectively; bf ,b i ,b c ,b o are the bias vectors of the forget gate, input gate, candidate state and output gate respectively; [h t-1 ,x t ] is the concatenation of the hidden state of the previous time step t-1 and the input of the current time step t;

[0139] Step 3: DQN control decision module is used to select the optimal control action based on the air conditioner operation state predicted by LSTM. The DQN control module adopts the following formula:

[0140] Q value update formula:

[0141] Q(s t ,a t )=Q(s t ,a t )+α[r t +γmaxQ(s t+1 ,a)-Q(s t ,a t )]

[0142] Among them, s t is the current state, a t is the current action, r t is the current reward, γ is the discount factor, and α is the learning rate;

[0143] like Figure 4 As shown in the figure, it is a schematic diagram of the implementation steps of the DQN control decision module. The specific implementation steps are as follows:

[0144] a. Take the air conditioning state predicted by LSTM as the current state S t ;

[0145] b. Define air conditioning control action a t ;

[0146] c. Design reward function r based on energy consumption and user comfort t ;

[0147] d. Iteratively update the Q value table through the Q value update formula;

[0148] e. Select the optimal action a according to the Q value table t ;

[0149] Step 4: Execute the control module to adjust the air conditioner operation state according to the output of the DQN control decision module;

[0150] Step 5: Feedback optimization and parameter adjustment module is used to monitor real-time data, and continuously adjust and optimize the algorithm parameters of the LSTM prediction module and the DQN control decision module according to the feedback results for air conditioning load monitoring and control.

[0151] Step 6: Edge computing and model compression module is used to improve the efficiency and response speed of the system during air conditioning load monitoring. It specifically includes the following sub-steps: data preprocessing and distribution, model segmentation and deployment, edge computing and decision-making, data feedback and optimization; model pruning, model quantization, knowledge distillation, model sharding and loading.

[0152] The edge computing module includes the following steps:

[0153] Data preprocessing and distribution: Perform preliminary data preprocessing on edge devices and distribute the preprocessed data to the corresponding computing modules.

[0154] Model segmentation and deployment: The improved adaptive intelligent load control model is segmented into multiple sub-models and deployed on edge devices and cloud servers respectively. Through the asynchronous communication mechanism, real-time synchronization of data and model parameters between edge devices and cloud servers is achieved.

[0155] Edge computing and decision-making: Run the deployed sub-models in real time on edge devices to quickly respond to environmental changes and make preliminary predictions and control decisions.

[0156] Data feedback and optimization: Send edge computing results and actual feedback data to the cloud server for global optimization and model parameter adjustment, and synchronize them back to the edge device.

[0157] The model compression module includes the following steps:

[0158] Model pruning: Remove neurons and connections with small weights in the improved adaptive intelligent load control model, and retrain and optimize it.

[0159] Model quantization: The floating-point weights and activation function values ​​of the improved adaptive intelligent load control model are quantized to low-precision representations, and calibrated and optimized.

[0160] Knowledge distillation: training a small “student model” to imitate the behavior of a large “teacher model” and optimizing and fine-tuning the student model.

[0161] Model sharding and loading: The compressed and improved adaptive intelligent load control model is divided into multiple sub-modules, and part of the model is selectively loaded and run according to the computing power and storage resources of the edge device.

[0162] Further, such as Figure 3As shown, the improved adaptive intelligent load control model also includes:

[0163] a. Preprocess the collected data, remove noise and standardize the data;

[0164] b. Based on the user usage pattern, a clustering algorithm is used for pattern recognition, including the following steps:

[0165] 1) Initialize multiple cluster centers;

[0166] 2) Assign data points to the nearest cluster center;

[0167] 3) Recalculate the location of the cluster center;

[0168] 4) Repeat the data point allocation and cluster center calculation until the cluster center no longer changes;

[0169] c. Based on the recognition results of user usage patterns, the Bayesian network is used to predict future air conditioning usage. The Bayesian network model includes the following formulas:

[0170]

[0171] Where X is the unobserved situation, Y is the current mode; P(X|Y) is the conditional probability of X when Y is known, P(Y|X) is the conditional probability of Y when X is known; P(X) is the prior probability of X; P(Y) is the prior probability of Y;

[0172] d. Dynamically adjust the operating status of the air conditioner, including temperature setting and wind speed adjustment, based on the Bayesian network prediction results;

[0173] e. Dynamically adjust the prediction model and operating status according to actual usage.

[0174] The intelligent control and regulation module is one of the core modules of the system, responsible for receiving and processing real-time data from the data acquisition and monitoring module, and performing intelligent regulation. Its specific functions include:

[0175] Data preprocessing and feature extraction: Preprocess the various collected data, remove noise and perform standardization for subsequent intelligent algorithm processing.

[0176] LSTM prediction module: Based on the prediction algorithm of long short-term memory network (LSTM), it analyzes and predicts the standardized data to determine the future operating status of the air conditioner.

[0177] DQN control module: Based on the control algorithm of deep Q network (DQN), it selects the optimal control action according to the results of LSTM prediction and adjusts the operating status of the air conditioner, including temperature setting and wind speed adjustment.

[0178] Energy-saving mode adjustment: According to the activities of people in the room, the air conditioner's operating mode is automatically adjusted to enter energy-saving mode to reduce unnecessary energy consumption.

[0179] In an optional embodiment, the communication interface module is used to realize data transmission and communication within and outside the system;

[0180] Furthermore, the communication interface module also includes a wireless communication unit for wireless communication via Wi-Fi, Bluetooth and Zigbee protocols.

[0181] The communication interface module is responsible for data transmission and communication within and outside the system. Its specific functions include:

[0182] Wireless communication: Supports wireless communication protocols such as Wi-Fi, Bluetooth and Zigbee to achieve stable data transmission.

[0183] Data transmission: The real-time data of the data acquisition and monitoring module is transmitted to the intelligent control and regulation module through the communication interface module, and the adjusted operating status is fed back to the user interface module.

[0184] System communication: Ensure the stability and reliability of data transmission and communication between various modules within the system.

[0185] In an optional embodiment, a safety assurance redundancy module is used to build a safety assurance system for the system and provide a fault detection and recovery mechanism;

[0186] Furthermore, the safety assurance redundant module includes one or more redundant power supply modules for providing backup power supply when the main power supply fails, and the redundant power supply module includes:

[0187] A power monitoring module that monitors the main power status in real time and triggers the backup power switch in case of failure;

[0188] A switch control module that automatically switches to backup power when the main power fails and ensures a seamless transition;

[0189] A backup power module that includes a battery pack or uninterruptible power supply (UPS) with sufficient capacity and supports charge and discharge management;

[0190] A status feedback module that provides real-time feedback on the power status and automatically switches back to the main power supply after the main power supply is restored;

[0191] Fault detection and alarm module that alerts the user in the event of a power failure and records all events;

[0192] A periodic self-check module that periodically self-checks the status of the backup power supply and feeds back the results.

[0193] The safety assurance redundancy module is used to build the system's safety assurance system and provide fault detection and recovery mechanisms. Its specific functions include:

[0194] Redundant power supply module: includes one or more backup power supply modules, which automatically switches to the backup power supply when the main power supply fails to ensure continuous operation of the system.

[0195] Power supply monitoring module: monitors the main power supply status in real time and triggers the switching of the backup power supply when the main power supply fails.

[0196] Fault detection and alarm: Alarms the user in the event of a power failure and logs all events for troubleshooting and maintenance.

[0197] Regular self-check: Regularly check the status of the backup power supply to ensure that it is available at any time and provide feedback on the self-check results.

[0198] In an optional embodiment, the user interface module is connected to the intelligent control and adjustment module to display monitoring data, system status and user control options, and provide an intuitive and easy-to-use operating interface;

[0199] Furthermore, the user interface module includes a touch screen and a voice recognition unit, which are used for the user to control and view the air conditioner operating status and parameters through touch operation or voice command.

[0200] The user interface module is connected to the intelligent control and adjustment module to display monitoring data, system status and user control options. The specific functions include:

[0201] Touch screen: Provides an intuitive touch screen interface, users can view system status and monitoring data, and set and adjust parameters through touch operations.

[0202] Voice recognition unit: supports voice commands. Users can control and view the air conditioner operating status and parameters through voice commands, providing a more convenient operating experience.

[0203] In an optional embodiment, a remote maintenance and upgrade module is connected to each module of the system to support remote maintenance and software upgrades.

[0204] Furthermore, the remote maintenance and upgrade module includes a cloud platform interface for connecting to the cloud platform via the Internet to achieve remote data storage, analysis and system updates.

[0205] The remote maintenance and upgrade module is connected to each module of the system to support remote maintenance and software upgrades. The specific functions include:

[0206] Cloud platform interface: Connect to the cloud platform via the Internet to achieve remote data storage, analysis and system updates.

[0207] Remote maintenance: Supports remote diagnosis and maintenance of the system, reducing the cost and time of on-site maintenance.

[0208] Software upgrade: Through the remote maintenance upgrade module, the system software can be updated and optimized regularly to ensure that the system is always in the best working condition.

[0209] Example 2

[0210] like Figure 5 As shown in FIG. 1 , another embodiment of the present invention is provided. The example provides a method for monitoring the load of a transformer and a distribution air conditioner. The method comprises:

[0211] S1: The data acquisition and monitoring module collects three-phase current, voltage, and ambient temperature parameters in real time, and continuously monitors the operating status of the air-conditioning equipment, including but not limited to the switch status, working mode, set temperature, wind speed and wind direction, and monitors the activities of people in the room;

[0212] S2: The data collected by the data acquisition and monitoring module is transmitted to the intelligent control and regulation module for data preprocessing and feature extraction;

[0213] S3: Predict the air conditioner operation status based on the preprocessed data through the LSTM prediction module of the intelligent control and regulation module;

[0214] S4: According to the prediction results of the LSTM prediction module, the DQN control module selects the optimal control action to adjust the operating state of the air conditioner;

[0215] S5: Realize data transmission and communication inside and outside the system through the communication interface module;

[0216] S6: When the main power supply fails, the safety redundancy module automatically switches to the backup power supply and ensures seamless transition;

[0217] S7: Displays monitoring data, system status and user control options through the user interface module, providing an intuitive and easy-to-use operation interface;

[0218] S8: Connect to the cloud platform through the remote maintenance and upgrade module to perform remote data storage, analysis and system updates;

[0219] S9: Dynamically adjust the operating status of the air conditioner, including temperature setting and wind speed adjustment, and dynamically adjust the prediction model and operating status according to actual usage.

[0220] Example 3

[0221] Another embodiment of the present invention verifies the effectiveness of the multi-parameter comprehensive monitoring function of the present invention. The three-phase current, voltage, ambient temperature and operating status parameters of the air-conditioning equipment are collected in real time through the data acquisition monitoring module, and the activities of people in the room are monitored.

[0222] Experimental process:

[0223] The power distribution air conditioner load monitoring terminal of the present invention is installed in an office.

[0224] Start the system and begin data collection, including three-phase current, voltage, ambient temperature, air conditioning operating status (switch status, working mode, set temperature, wind speed and wind direction), and personnel activities in the room.

[0225] Record the real-time data collected and compare it with actual usage to verify the accuracy and real-time nature of the data.

[0226] Performance data:

[0227] Table 1 shows some of the data recorded during the experiment (the experiment lasted 8 hours):

[0228]

[0229] It can be concluded from Table 1 that the data acquisition and monitoring module can accurately and real-time collect and record various parameters of air-conditioning operation. The system automatically turns off the air-conditioning when no one is in the room, effectively saving energy.

[0230] Example 4

[0231] Another embodiment of the present invention verifies the effect of the intelligent control and regulation module of the present invention in improving energy efficiency and user comfort. The experiment mainly tests the comprehensive performance of the LSTM prediction module and the DQN regulation module.

[0232] Experimental process:

[0233] The power distribution air conditioning load monitoring terminal of the present invention is installed in a laboratory environment and is equipped with an intelligent control and regulation module.

[0234] Set up experimental conditions, including changes in ambient temperature and personnel activities.

[0235] The system runs automatically, makes predictions and controls based on real-time data, and records the operating status and energy consumption of the air conditioner.

[0236] Performance data:

[0237] Table 2 shows some of the data recorded during the experiment (the experiment lasted 8 hours):

[0238]

[0239] As shown in Table 2, the LSTM prediction module can accurately predict future temperature changes, and the DQN control module adjusts the air conditioner operation status in real time according to the prediction results. Experiments show that under intelligent control, the energy efficiency of air conditioners is significantly improved, user comfort is guaranteed, and energy consumption is reduced.

[0240] In summary, the present invention greatly improves the energy efficiency management and user experience of the air-conditioning system through comprehensive data collection, intelligent operation control, stable data transmission, perfect fault detection and recovery mechanism, friendly user interface design and powerful remote maintenance and upgrade functions, and overcomes the shortcomings of the prior art. Specifically, the present invention not only improves the energy efficiency of the air-conditioning system and reduces energy consumption, but also significantly improves the user's operational convenience and comfort. At the same time, through the intelligent fault detection and recovery mechanism, the stable operation of the air-conditioning system in various working environments is ensured, and the maintenance cost and downtime are reduced. In addition, the present invention also has strong scalability and adaptability, and can dynamically adjust and optimize system parameters according to actual usage conditions to meet the needs of different users and environments. Therefore, the present invention has broad application prospects and significant technical advantages in the field of air-conditioning load monitoring and control.

[0241] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0242] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0243] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A transformer and distribution air conditioner load monitoring terminal, characterized in that: The terminal comprises: Data acquisition and monitoring module, used to collect three-phase current, voltage, and ambient temperature parameters in real time, and continuously monitor the operating status of the air-conditioning equipment, including but not limited to switch status, working mode, set temperature, wind speed and wind direction, and monitor the activities of people in the room; An intelligent control and regulation module, which receives real-time data and automatically adjusts the operation status of the air conditioner according to the improved adaptive intelligent load control model, including energy-saving mode adjustment based on the activity of people in the room; Communication interface module, used to realize data transmission and communication within and outside the system; Safety assurance redundancy module, used to build the system's safety assurance system and provide fault detection and recovery mechanisms; User interface module, used to display monitoring data, system status and user control options, providing an intuitive and easy-to-use operation interface; Remote maintenance and upgrade module, used to support remote maintenance and software upgrades; The passive infrared sensor PIR and ultrasonic sensor in the data acquisition monitoring module are used in the following combination: The passive infrared sensor and ultrasonic sensor work simultaneously to detect the activities of people in the room and send the data to the data acquisition and monitoring module for data fusion processing; Set the passive infrared sensor as the main sensor and the ultrasonic sensor as the auxiliary sensor; According to the preset time period, the passive infrared sensor and ultrasonic sensor are alternately enabled to detect human activity; The improved adaptive intelligent load control model includes the following modules: Step 1: Data preprocessing and feature extraction module, used to collect and standardize input data and historical air conditioning operation data. The standardized x′ formula is: Among them, x is the original data, μ is the mean of the data, and σ is the standard deviation of the data; Step 2: LSTM prediction module, combined with CNN and Attention mechanism, is used to predict the air conditioner operation status based on standardized data. The LSTM prediction module adopts the following formula: Forget Gate: f t =σ(W f ·[h t-1 ,x t ]+b f ) Input Gate: i t =σ(W i ·[h t-1 ,x t ]+b i ) Status Update: Output Gate: the t =σ(W o ·[h t-1 ,x t ]+b o ) h t =o t ·tanh(S t ) Among them, f t is the forget gate at time step t, i t is the input gate at time step t, o t is the output gate at time step t, is the candidate state, S t is the air conditioning state, σ is the Sigmoid activation function, tanh is the hyperbolic tangent activation function, W f ,W i ,W c ,W o are the weight matrices of the forget gate, input gate, candidate state, and output gate respectively; b f ,b i ,b c ,b o are the bias vectors of the forget gate, input gate, candidate state and output gate respectively; [h t-1 ,x t ] is the concatenation of the hidden state of the previous time step t-1 and the input of the current time step t; Step 3: A DQN control decision module is used to select the optimal control action based on the air conditioner operation state predicted by LSTM. The DQN control decision module adopts the following formula: Q value update formula: Q(s t ,a t )=Q(s t ,a t )+α[r t +γmaxQ(s t+1 ,a)-Q(s t ,a t )] Among them, s t is the current state, a t is the current action, r t is the current reward, γ is the discount factor, and α is the learning rate; The specific implementation steps are as follows: I. Take the air conditioning state predicted by LSTM as the current state S t ; II. Define air conditioning control action a t ; III. Designing reward function r based on energy consumption and user comfort t ; IV. Iteratively update the Q value table through the Q value update formula; V. Select the optimal action a according to the Q value table t ; Step 4: Execute the control module to adjust the air conditioner operation state according to the output of the DQN control decision module; Step 5: Feedback optimization and parameter adjustment module, which is used to monitor real-time data, and continuously adjust and optimize the algorithm parameters of the LSTM prediction module and the DQN control decision module according to the feedback results, for air conditioning load monitoring and control; Step 6: Edge computing and model compression module, used to improve the efficiency and response speed of the system during air conditioning load monitoring, including the following sub-steps: data preprocessing and distribution, model segmentation and deployment, edge computing and decision-making, data feedback and optimization; model pruning, model quantization, knowledge distillation, model sharding and loading; The user interface module includes a touch screen and a voice recognition unit, which is used for the user to control and view the operating status and parameters of the air conditioner through touch operation or voice command; The data acquisition and monitoring module also includes a light sensor and a humidity sensor for monitoring ambient light and humidity parameters and adjusting the operating mode of the air conditioner according to these parameters; The improved adaptive intelligent load control model also includes: a. Preprocess the collected data, remove noise and standardize the data; b. Based on the user usage pattern, a clustering algorithm is used for pattern recognition, including the following steps: 1) Initialize multiple cluster centers; 2) Assign data points to the nearest cluster center; 3) Recalculate the location of the cluster center; 4) Repeat the data point allocation and cluster center calculation until the cluster center no longer changes; c. Based on the recognition results of user usage patterns, the Bayesian network is used to predict future air conditioning usage. The Bayesian network model includes the following formulas: Where X is the unobserved situation, Y is the current mode; P(X|Y) is the conditional probability of X when Y is known, P(Y|X) is the conditional probability of Y when X is known; P(X) is the prior probability of X; P(Y) is the prior probability of Y; d. Dynamically adjust the operating status of the air conditioner, including temperature setting and wind speed adjustment, based on the Bayesian network prediction results; e. Dynamically adjust the prediction model and operating status according to actual usage.

2. The transformer and distribution air conditioner load monitoring terminal according to claim 1, characterized in that: The communication interface module also includes a wireless communication unit for wireless communication via Wi-Fi, Bluetooth and Zigbee protocols.

3. The transformer and air conditioner load monitoring terminal according to claim 1, characterized in that: The safety guarantee redundant module includes one or more redundant power supply modules, which are used to provide backup power supply when the main power supply fails. The redundant power supply module includes: A power monitoring module that monitors the main power status in real time and triggers the backup power switch in case of failure; A switch control module that automatically switches to backup power when the main power fails and ensures a seamless transition; A backup power module that includes a battery pack or uninterruptible power supply with sufficient capacity and supports charge and discharge management; A status feedback module that provides real-time feedback on the power status and automatically switches back to the main power supply after the main power supply is restored; Fault detection and alarm module that alerts the user in the event of a power failure and records all events; A periodic self-check module that periodically self-checks the status of the backup power supply and feeds back the results.

4. The transformer and distribution air conditioner load monitoring terminal according to claim 1, characterized in that: The remote maintenance and upgrade module includes a cloud platform interface, which is used to connect to the cloud platform via the Internet to achieve remote data storage, analysis and system updates.

5. A method for monitoring the load of a transformer and air conditioner according to any one of claims 1 to 4, characterized in that: The method comprises: S1: The data acquisition and monitoring module collects three-phase current, voltage, and ambient temperature parameters in real time, and continuously monitors the operating status of the air-conditioning equipment, including but not limited to the switch status, working mode, set temperature, wind speed and wind direction, and monitors the activities of people in the room; S2: The data collected by the data acquisition and monitoring module is transmitted to the intelligent control and regulation module for data preprocessing and feature extraction; S3: Predict the air conditioner operation status based on the preprocessed data through the LSTM prediction module of the intelligent control and regulation module; S4: According to the prediction results of the LSTM prediction module, the DQN control decision module selects the optimal control action to adjust the operating state of the air conditioner; S5: Realize data transmission and communication inside and outside the system through the communication interface module; S6: When the main power supply fails, the safety redundancy module automatically switches to the backup power supply and ensures seamless transition; S7: Displays monitoring data, system status and user control options through the user interface module, providing an intuitive and easy-to-use operation interface; S8: Connect to the cloud platform through the remote maintenance and upgrade module to perform remote data storage, analysis and system updates; S9: Dynamically adjust the operating status of the air conditioner, including temperature setting and wind speed adjustment, and dynamically adjust the prediction model and operating status according to actual usage.

Images