Electrical equipment control system and control method

Abstract

The invention discloses an electrical equipment control system and a control method, relates to the technical field of electrical equipment intelligent control, and solves the problems that the working time of an electrical appliance is set by using a timer in the existing technical solution, but the mode cannot be flexibly adjusted according to the actual use condition; the electrical equipment use reminding system comprises an integrated sensor module, a data processing module, a control module and an operation platform, the invention aims to provide the electrical equipment use reminding system which is more efficient, safer and easy to manage. The system can monitor the existence state of people in a room in real time through an advanced sensor technology and an intelligent algorithm, and automatically sends reminding information to prompt a user to turn off an electric appliance when it is detected that no one is in the room. Meanwhile, the system also has a remote control function, so that a manager can remotely monitor and control the state of the electrical equipment through the mobile equipment.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent control of electrical equipment, and in particular relates to an electrical equipment control system and a control method. Background Art

[0002] With the development of modern technology, electrical equipment plays an increasingly important role in our daily lives. From household appliances to office equipment to industrial equipment, electrical equipment is everywhere. However, the problem of safe use of electrical equipment has also become increasingly prominent. In particular, it is common for people to forget to turn off electrical equipment when they leave the room or the place where the equipment is used. This not only leads to energy waste, but may also cause safety hazards such as fire. The main problems of forgetting to turn off electrical equipment are the following three points: 1. Energy waste. When people leave the room or the place where the equipment is used, they often forget to turn off the electrical appliances, causing the appliances to be in standby or running state for a long time, resulting in a lot of energy waste; 2. Safety hazards. Electrical appliances that run for a long time may cause fires due to overheating, short circuits, etc., especially when there is no supervision, the safety hazards are huge; 3. Management difficulties: For large buildings or enterprises, managing a large number of electrical equipment is a challenge; traditional management methods often rely on manual inspections, which are inefficient and prone to errors;

[0003] In order to solve the above problems, the existing technical solution is to use a timer to set the working time of the electrical appliance, but this method cannot be flexibly adjusted according to actual usage; therefore, there is currently a lack of a more efficient, safe and easy-to-manage electrical equipment usage reminder system. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides an electrical equipment control system and control method, and the present invention aims to provide a more efficient, safe and easy-to-manage electrical equipment use reminder system. The system uses advanced sensor technology and intelligent algorithms to monitor the presence of people in the room in real time, and automatically sends reminder information when no one is detected, prompting the user to turn off the appliance. At the same time, the system also has a remote control function, and managers can remotely monitor and control the status of electrical equipment through mobile devices.

[0005] The technical solution adopted by the present invention is as follows:

[0006] An electrical equipment control system comprises an integrated sensor module, a data processing module, a control module and an operating platform; the sensor module is connected to the data processing module via radio signals, and the data processing module and the operating platform are respectively connected to the control system via radio signals.

[0007] Preferably, the integrated sensor module comprises a central processing unit, an infrared sensor and a motion sensor, there are a plurality of the infrared sensor and the motion sensor, and the plurality of the infrared sensors and the motion sensors are electrically connected to the central processing unit respectively.

[0008] Preferably, there is at least one operating platform.

[0009] An electrical equipment control method, using the above-mentioned electrical equipment control system, comprises the following steps:

[0010] Step 1: Use high-precision integrated sensor modules to monitor the presence and activity of people in the room;

[0011] Step 2: Collect data from the integrated sensor module and send it to the data processing module via electrical signals, using data analysis technology to identify human activity patterns and appliance usage;

[0012] Step 3: Use machine learning algorithms to analyze the collected data and build models to predict human behavior and appliance usage trends;

[0013] Step 4: The data processing module sends the analyzed data to the intelligent decision engine of the control module, and automatically adjusts the reminder strategy according to the prediction results;

[0014] Step 5: After the reminder strategy is determined, the control system issues reminders through the operating platform, which provides an intuitive user interface that enables users to easily receive reminders, view appliance status, and adjust reminder settings as needed;

[0015] Step 6: Establish a feedback mechanism to provide feedback to the control system and data processing system based on the user's actual usage through the operating system, so as to continuously learn and optimize, and allow users to set reminder parameters according to personal preferences, such as reminder frequency and method, etc.

[0016] Preferably, the high-precision integrated sensor module described in step 1 plans the number and installation location of each sensor according to the room layout and monitoring requirements, considers the detection angle and coverage of each sensor, and ensures that there are no blind spots and excessive coverage.

[0017] Preferably, in step 1, a high-precision integrated sensor module is used, in which the infrared sensor is used to detect thermal radiation emitted by a static or dynamic human body, and the motion sensor monitors the dynamic infrared radiation changes caused by human body movement, and the data of the two sensors are fused to improve the accuracy and robustness of detection.

[0018] Preferably, an algorithm is designed to identify and filter out false positives, such as those caused by pets, swinging curtains, etc.

[0019] Preferably, the step 3 of using a machine learning algorithm to analyze the collected data and establish a model to predict personnel behavior and appliance usage trends specifically includes the following steps:

[0020] Step 301: Integrate the personnel activity patterns and appliance usage data analyzed by the data processing module in step 2, perform data cleaning, process missing values, and normalize the data;

[0021] Step 302: Extract features that are helpful for model understanding from the raw data, including timestamps, activity duration, number of times the appliance is turned on and off, etc., and select the features that are most useful for the prediction task;

[0022] Step 303: Divide the data into a training set, a validation set, and a test set;

[0023] Step 304: Determine that the nature of the machine learning model is a deep belief network DBN;

[0024] Step 305: train the selected model using the training set in step 303;

[0025] Step 306: Test the final performance of the model on the test set, and deploy the trained model to actual applications to obtain accurate predictions of personnel behavior and appliance usage trends.

[0026] Step 305, after training the selected model with the training set, also includes a step of validating the model.

[0027] Preferably, in step 4, automatically adjusting the reminder strategy according to the prediction result specifically includes the following steps:

[0028] Step 401: energy saving, user convenience and safety are determined as goals of the intelligent decision engine;

[0029] Step 402: triggering a specific control strategy design decision logic and rules based on the prediction results of personnel behavior and appliance usage trends;

[0030] Step 403: Implement real-time data stream monitoring and processing so that the decision engine can respond to the latest situation immediately;

[0031] Step 404: establishing thresholds for different control strategies;

[0032] Step 405: Match the most appropriate control strategy according to the evaluation results and preset rules;

[0033] Step 406: The control module is electrically connected to the interfaces of each electrical appliance, and the control strategy matched in step 405 is executed, such as sending an instruction to shut down or reduce power, and the control strategy is synchronously sent to the operating platform.

[0034] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0035] 1. Use various types of advanced sensors (such as infrared and motion sensors) to collect data and realize real-time monitoring of the presence status of people in the room;

[0036] 2. By fusing data from different sensors, the system can provide more comprehensive and accurate environmental perception, improve detection accuracy and reduce misjudgment;

[0037] 3. Using machine learning and deep learning algorithms, the system can learn and predict people’s behavior patterns and appliance usage trends, thereby achieving intelligent decision support;

[0038] 4. Based on the prediction results and user behavior, the system automatically adjusts the reminder strategy, such as the frequency and method of reminders, to adapt to the needs and preferences of different users;

[0039] 5. Managers can remotely monitor and control the status of electrical equipment through mobile devices, which improves the flexibility and response speed of the system;

[0040] 6. The system has the ability to self-learn and self-optimize, and can continuously improve performance based on user feedback and new data;

[0041] 7. Through intelligent control, the system can reasonably control the opening and closing of various electrical equipment, which helps to reduce energy waste and achieve energy conservation and emission reduction;

[0042] 8. Realize real-time monitoring of room status and electrical appliance usage, and provide timely feedback to users and managers, enhancing the interactivity and practicality of the system;

[0043] 9. Allow users to adjust the sensitivity of sensors, types and frequency of reminders according to personal needs, thereby improving user satisfaction and the level of personalization of the system. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0045] Example 1

[0046] An electrical equipment control system comprises an integrated sensor module, a data processing module, a control module and an operating platform; the sensor module is connected to the data processing module via radio signals, and the data processing module and the operating platform are respectively connected to the control system via radio signals.

[0047] In this embodiment, the integrated sensor module includes a central processing unit, an infrared sensor and a motion sensor. There are multiple infrared sensors and motion sensors, and the multiple infrared sensors and motion sensors are electrically connected to the central processing unit respectively.

[0048] Among them, multiple infrared sensors and motion sensors are distributed in the room.

[0049] In this embodiment, there is at least one operating platform.

[0050] Example 2

[0051] An electrical equipment control method, using the above-mentioned electrical equipment control system, comprises the following steps:

[0052] Step 1: Use high-precision integrated sensor modules to monitor the presence and activity of people in the room;

[0053] Step 2: Collect data from the integrated sensor module and send it to the data processing module via electrical signals, using data analysis technology to identify human activity patterns and appliance usage;

[0054] Step 3: Use machine learning algorithms to analyze the collected data and build models to predict human behavior and appliance usage trends;

[0055] Step 4: The data processing module sends the analyzed data to the intelligent decision engine of the control module. According to the prediction results, the reminder strategy is automatically adjusted, and an adaptive reminder system is designed to dynamically adjust the timing and content of the reminder according to the user's behavior pattern and the use of the appliance;

[0056] Step 5: After the reminder strategy is determined, the control system issues reminders through the operating platform. The operating platform provides an intuitive user interface that enables users to easily receive reminders, view appliance status, and adjust reminder settings as needed. Users can manually override automatic decisions through the interface or adjust settings to change decision-making behavior;

[0057] Step 6: Establish a feedback mechanism to provide feedback to the control system and data processing system based on the user's actual usage through the operating system, so as to continuously learn and optimize, and allow users to set reminder parameters according to personal preferences, such as reminder frequency and method, etc.

[0058] In this embodiment, the high-precision integrated sensor module described in step 1 plans the number and installation location of each sensor according to the room layout and monitoring requirements, considers the detection angle and coverage range of each sensor, and ensures that there are no blind spots and excessive coverage.

[0059] In this embodiment, in step 1, a high-precision integrated sensor module is used, in which the infrared sensor is used to detect the thermal radiation emitted by a static or dynamic human body, and the motion sensor monitors the dynamic infrared radiation changes caused by human body movement. The data of the two sensors are fused to improve the accuracy and robustness of detection.

[0060] In this embodiment, an algorithm is designed to identify and filter out false positives caused by various sensors in step 1, such as false positives caused by pets, swinging curtains, etc.

[0061] In this embodiment, the use of a machine learning algorithm to analyze the collected data and establish a model to predict personnel behavior and appliance usage trends in step 3 specifically includes the following steps:

[0062] Step 301: Integrate the personnel activity patterns and appliance usage data analyzed by the data processing module in step 2, perform data cleaning, process missing values, and normalize the data;

[0063] Step 302: Extract features that are helpful for model understanding from the raw data, including timestamps, activity duration, number of times the appliance is turned on and off, etc., and select the features that are most useful for the prediction task;

[0064] Step 303: Divide the data into a training set, a validation set, and a test set;

[0065] Step 304: Determine that the nature of the machine learning model is a deep belief network DBN, which can be used to extract features and make effective predictions;

[0066] Step 305: train the selected model using the training set in step 303;

[0067] Step 306: Test the final performance of the model on the test set, and deploy the trained model to actual applications to obtain accurate predictions of personnel behavior and appliance usage trends.

[0068] Step 305, after training the selected model with the training set, also includes a step of validating the model.

[0069] In this embodiment, in step 4, automatically adjusting the reminder strategy according to the prediction result specifically includes the following steps:

[0070] Step 401: energy saving, user convenience and safety are determined as goals of the intelligent decision engine;

[0071] Step 402: triggering a specific control strategy design decision logic and rules based on the prediction results of personnel behavior and appliance usage trends;

[0072] Among them, this application uses a rule engine to implement decision logic;

[0073] Step 403: Implement real-time data stream monitoring and processing so that the decision engine can respond to the latest situation immediately;

[0074] Step 404: establishing thresholds for different control strategies;

[0075] This application is set to automatically shut down the appliance when the room control time exceeds a certain threshold t;

[0076] Step 405: Match the most appropriate control strategy according to the evaluation results and preset rules;

[0077] Step 406: Execute the control strategy matched in step 405 through the interface between the control module and each electrical appliance, such as sending a command to shut down or reduce power, and synchronously send the control strategy to the operating platform.

[0078] Example 3

[0079] The specific steps to design an algorithm to identify and filter out false positives caused by various sensors in step 1, such as false positives caused by pets, curtain swings, etc., are:

[0080] Step a: Collect sensor data under normal conditions and false alarm conditions;

[0081] Step b: Extract features from the sensor data that help distinguish real activities from false positives, such as movement speed, movement posture, and temperature changes;

[0082] Step c: Use machine learning techniques to train a classifier to distinguish between real activities and false positives. The specific classifier training algorithm is as follows:

[0083]

[0084] Step d: Analyze which features contribute most to the performance of the classifier to optimize feature selection;

[0085] Step e: Set appropriate thresholds to determine when to trigger false positive filtering;

[0086] Step f: Design logical rules to integrate sensor data and contextual information to make the final judgment.

[0087] It should be noted that:

[0088] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An electrical equipment control system, characterized in that: It includes an integrated sensor module, a data processing module, a control module and an operating platform; the sensor module is connected to the data processing module via radio signals, and the data processing module and the operating platform are respectively connected to the control system via radio signals.

2. An electrical equipment control system according to claim 1, characterized in that: The integrated sensor module comprises a central processing unit, an infrared sensor and a motion sensor. There are a plurality of the infrared sensor and the motion sensor, and the plurality of the infrared sensors and the motion sensors are electrically connected to the central processing unit respectively.

3. An electrical equipment control system according to claim 1, characterized in that: There is at least one operating platform.

4. A method for controlling an electrical device, characterized in that: Using the electrical equipment control system described in claim 1, comprising the following steps: Step 1: Use high-precision integrated sensor modules to monitor the presence and activity of people in the room; Step 2: Collect data from the integrated sensor module and send it to the data processing module via electrical signals, using data analysis technology to identify human activity patterns and appliance usage; Step 3: Use machine learning algorithms to analyze the collected data and build models to predict human behavior and appliance usage trends; Step 4: The data processing module sends the analyzed data to the intelligent decision engine of the control module, and automatically adjusts the reminder strategy according to the prediction results; Step 5: After the reminder strategy is determined, the control system will issue a reminder through the operating platform. The operating platform provides an intuitive user interface so that users can easily receive reminders, view appliance status, and adjust reminder settings as needed; Step 6: Establish a feedback mechanism to provide feedback to the control system and data processing system based on the user's actual usage through the operating system, so as to continuously learn and optimize, and allow users to set reminder parameters according to personal preferences, such as reminder frequency and method, etc.

5. The electrical equipment control method according to claim 4, characterized in that: The high-precision integrated sensor module described in step 1 plans the number and installation location of each sensor according to the room layout and monitoring requirements, considers the detection angle and coverage of each sensor, and ensures that there are no blind spots and excessive coverage.

6. The electrical equipment control method according to claim 4, characterized in that: In step 1, a high-precision integrated sensor module is used. The infrared sensor is used to detect the thermal radiation emitted by a static or dynamic human body, and the motion sensor monitors the dynamic infrared radiation changes caused by human movement. The data of the two sensors are fused to improve the accuracy and robustness of the detection.

7. The electrical equipment control method according to claim 6, characterized in that: Design algorithms to identify and filter out false positives, such as those caused by pets, swinging curtains, etc.

8. The electrical equipment control method according to claim 4, characterized in that: The use of machine learning algorithms to analyze the collected data and establish a model to predict personnel behavior and appliance usage trends described in step 3 specifically includes the following steps: Step 301: Integrate the personnel activity patterns and appliance usage data analyzed by the data processing module in step 2, perform data cleaning, process missing values, and normalize the data; Step 302: Extract features that are helpful for model understanding from the raw data, including timestamps, activity duration, number of times the appliance is turned on and off, etc., and select the features that are most useful for the prediction task; Step 303: Divide the data into a training set, a validation set, and a test set; Step 304: Determine that the nature of the machine learning model is a deep belief network DBN; Step 305: train the selected model using the training set in step 303; Step 306: Test the final performance of the model on the test set, and deploy the trained model to actual applications to obtain accurate predictions of personnel behavior and appliance usage trends.

9. The electrical equipment control method according to claim 8, characterized in that: Step 305, after training the selected model with the training set, also includes a step of validating the model.

10. The electrical equipment control method according to claim 4, characterized in that: In step 4, according to the prediction results, the automatic adjustment of the reminder strategy specifically includes the following steps: Step 401: energy saving, user convenience and safety are determined as goals of the intelligent decision engine; Step 402: triggering a specific control strategy design decision logic and rules based on the prediction results of personnel behavior and appliance usage trends; Step 403: Implement real-time data stream monitoring and processing so that the decision engine can respond to the latest situation immediately; Step 404: establishing thresholds for different control strategies; Step 405: Match the most appropriate control strategy according to the evaluation results and preset rules; Step 406: Execute the control strategy matched in step 405 through the interface between the control module and each electrical appliance, such as sending a command to shut down or reduce power, and synchronously send the control strategy to the operating platform.

Images