Intelligent building energy-saving control system

Through multimodal sensors and deep learning models, real-time monitoring and analysis of industrial plant environments and intelligently control the status of equipment, the problems of incomplete environmental monitoring, inaccurate user perception and insufficient energy consumption management are solved, and precise energy saving and balanced equipment use are achieved. Improves energy efficiency and user experience.

CN118938783AInactive Publication Date: 2024-11-12SUZHOU SHUIMU TECH CO LTD

Patent Information

Application Number
CN202411268916.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-11
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing intelligent environmental monitoring system for industrial factory buildings cannot fully and accurately reflect environmental changes, user perception is inaccurate, equipment control strategies are simple, and there is a lack of effective energy consumption abnormality detection and management, resulting in waste of resources and equipment overload.

Method used

Multimodal sensors are used to monitor environmental data in real time, judge the user's existence status through convolutional neural networks and deep learning models, control the working status of smart devices, build an energy consumption prediction model to identify abnormalities, and formulate equipment rotation rules for balanced use.

Benefits of technology

It realizes comprehensive perception and intelligent management of the built environment, accurately monitors environmental changes, reduces energy consumption, ensures balanced use of equipment and timely management of energy consumption abnormalities, and improves energy utilization efficiency and user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118938783A_ABST
    Figure CN118938783A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent building energy-saving control system, and relates to the technical field of intelligent building energy-saving control, and the system comprises the steps: controlling the working state and the dormant state of intelligent equipment in an intelligent building based on the existence state of a user; retrieving and recording all intelligent equipment information associated with the intelligent building; constructing an energy consumption prediction model based on the intelligent equipment information, and according to the energy consumption data, judging an energy consumption range and identifying the intelligent equipment with abnormal energy consumption; according to the intelligent equipment with the abnormal energy consumption, the state of the intelligent equipment with the energy consumption exceeding the range is adjusted; an alternating rule is made based on the state of the intelligent device, and the intelligent device works according to the preset alternating rule. By integrating key technologies such as environment monitoring, user perception, intelligent equipment control and management, energy consumption prediction and abnormity management, comprehensive perception and intelligent management of the building environment are realized, the equipment state is intelligently controlled, the energy utilization efficiency is remarkably improved, the operation cost is reduced, and technical support is provided for energy conservation and emission reduction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of intelligent building energy-saving control, in particular to an intelligent building energy-saving control system. Background Art

[0002] With the rapid development of information technology, the building intelligence of industrial plants has become an important part of modern cities. The building intelligence of industrial plants can not only improve working comfort, but also significantly reduce energy consumption and promote sustainable development. In recent years, the application of technologies such as the Internet of Things (IoT), artificial intelligence (AI) and big data analysis has greatly improved the automation level and energy management efficiency of industrial plant building intelligence. In terms of environmental monitoring, comprehensive perception of the internal environment of the building can be achieved through the integration of sensor networks and advanced image processing technology. However, in this area, there are still some technical challenges and room for improvement.

[0003] Although certain progress has been made in the field of building intelligence for industrial plants, there are still some problems that need to be solved. First, the existing environmental monitoring systems often rely on a single type of sensor, which makes it difficult to fully and accurately reflect real environmental changes. Secondly, in terms of user perception, traditional methods rely only on simple sensor triggers, which cannot accurately judge the user's real needs and behavior patterns, resulting in waste of resources. In addition, the control strategies of most current smart devices are relatively simple, lacking intelligent energy consumption management and equipment rotation mechanisms, which can easily cause equipment overload or uneven resource allocation. Finally, the existing industrial plant building intelligent management system lacks effective energy consumption anomaly detection and management methods, and cannot promptly identify and correct energy consumption anomalies, which in turn affects overall energy efficiency. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent building energy-saving control system to solve the problems of incomplete environmental monitoring, inaccurate user perception, simple equipment control strategy and insufficient abnormal energy consumption management in the prior art.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, an embodiment of the present invention provides an intelligent building energy-saving control system, which includes: an environmental monitoring module: real-time monitoring and collection of environmental data of a target area corresponding to the intelligent building; a user perception module: judging whether there is a user in the target area based on the data provided by the environmental monitoring module; a device control module: controlling the working state and sleep state of intelligent devices in the intelligent building based on the presence status of the user; an intelligent device management module: retrieving and recording all intelligent device information associated with the intelligent building; an energy consumption statistics module: constructing an energy consumption prediction model based on the intelligent device information, judging the energy consumption range and identifying intelligent devices with abnormal energy consumption according to the energy consumption data; an energy consumption abnormality management module: adjusting the state of intelligent devices with energy consumption exceeding the range according to the intelligent devices with abnormal energy consumption; a balanced rotation module: formulating rotation rules based on the state of the intelligent devices, and the intelligent devices work according to the preset rotation rules.

[0007] As a preferred solution of the intelligent building energy-saving control system of the present invention, the real-time monitoring and collection of environmental data of the target area corresponding to the intelligent building are specifically performed as follows: Capture live video stream via camera; Use background subtraction algorithms to remove the background from consecutive video frames and focus the image on potential dynamic elements; Use edge detection to identify body posture and facial features of people in images; Capture ambient sound through a microphone array to reduce background noise; Use fast Fourier transform to analyze the frequency components of sound and identify people's voices, footsteps, and door opening and closing sounds; The infrared signal is converted into a visual heat map through an infrared thermal imaging camera to obtain the temperature distribution; Analyze changes in heat maps to identify temperature peaks and movement patterns to determine if there is activity.

[0008] The collected data is transmitted to the central processor through the communication network.

[0009] As a preferred solution of the intelligent building energy-saving control system of the present invention, the specific steps of judging whether there is a user in the target area based on the data provided by the environmental monitoring module are as follows: Use a convolutional neural network to extract features including temperature data T, light intensity data L, audio data A, infrared imaging data I, and video frame data V from environmental data; A deep learning model is used and an attention mechanism is introduced to perform weighted fusion according to the importance of each environmental feature vector, and different environmental feature vectors are fused into a comprehensive feature vector, which is expressed as: ; Among them, FT (T) represents the feature extraction of temperature data T, F L (L) represents the feature extraction of light intensity L, AL is a multi-attention mechanism, F A (A) represents the feature extraction of audio signal A, F I (I) represents the feature extraction of infrared thermal image I, F V (V) represents feature extraction of video frame V; Based on the comprehensive feature vector F, it is determined whether there is a user in the target area. The expression is as follows: ; Among them, p represents the probability that there is a user in the target area, is the activation function, W f is the weight matrix of the decision layer, b f is the bias vector of the decision layer, and f represents the fused feature vector.

[0010] As a preferred solution of the intelligent building energy-saving control system of the present invention, wherein: the working state and sleep state of the intelligent devices in the intelligent building are controlled based on the user's presence state, and the specific steps are as follows: Based on the target scenario and requirements, define a user presence status threshold p th , the central controller is based on p th Determine the working status of smart devices in smart buildings; When p>p th When the user is considered to be in the target area, the smart device should enter the working state; When p is less than p th When the user is not in the target area, the smart device should enter the sleep state; Based on the target scenario and requirements, define a user presence status threshold p th , the central controller compares p th The size of and p determines the working status of the smart devices in the smart building; Control signals are transmitted to smart devices in the target area through the communication network of the smart building. The control module on the smart device analyzes the received control signal and extracts specific control instructions. According to the instructions in the signal, the smart device performs corresponding actions.

[0011] As a preferred solution of the intelligent building energy-saving control system of the present invention, the specific steps of retrieving and recording all intelligent device information associated with the intelligent building are as follows: Design a periodic update mechanism through event-driven to regularly check the status changes of smart devices; Create a device information database to store the basic information and operating status of all smart devices in the smart building; Generate regular reports using the information in the database to analyze the health status, energy consumption, and failure rate of smart devices.

[0012] As a preferred solution of the intelligent building energy-saving control system of the present invention, the energy consumption prediction model is constructed based on the intelligent device information, and the specific steps are as follows: In the latest state of the smart device, the power and current consumption data are continuously collected through the built-in power metering module of the smart device, and the power and current consumption data are sent to the central processor through the communication network; Based on the comprehensive feature vector F, the energy consumption model is constructed, and the expression is: ; Among them, ML represents the residual multilayer perceptron, W is the weight matrix, b is the bias vector, and E is the energy consumption of the smart device.

[0013] As a preferred solution of the intelligent building energy-saving control system of the present invention, the specific steps of judging the energy consumption range and identifying the intelligent devices with abnormal energy consumption according to the energy consumption data are as follows: The energy consumption range of a normal smart device in a normal working state is defined as a first energy consumption range, and the energy consumption range of the smart device in a dormant state is defined as a second energy consumption range; The central processing unit analyzes the energy consumption data through the result E of the energy consumption model to determine whether the electric energy consumption value and the current consumption value are within the preset first energy consumption range and the second energy consumption range; If the energy consumption value of the smart device falls within the first consumption range, the system will mark the smart device as being in a normal working state; If the energy consumption value exceeds one of the first consumption range and the second consumption range, it indicates that the smart device is faulty or overloaded, and the system will mark it as an abnormal state; If the energy consumption value of the smart device falls within the second consumption range, the system will mark it as a dormant state.

[0014] As a preferred solution of the intelligent building energy-saving control system of the present invention, wherein: the state of the intelligent device with energy consumption exceeding the range is adjusted according to the intelligent device with abnormal energy consumption, and the specific steps are as follows: For smart devices marked as abnormal, the system further analyzes the cause of abnormal energy consumption to distinguish whether it is caused by smart device failure, overload or improper configuration; According to the abnormal cause, the central processor formulates adjustment strategies for abnormal smart devices: If the abnormality is caused by overload, the output power of the smart device will be limited; If the abnormality is caused by improper configuration, optimize the operating parameters of the smart device; The control unit in the central processor generates specific control signals according to the adjustment strategy and sends the control signals to the smart devices with abnormal energy consumption through the communication network of the smart building; The control module on the abnormal energy consumption intelligent device receives and analyzes the control signal sent by the central processor, and performs corresponding adjustment operations according to the instructions in the signal.

[0015] As a preferred solution of the intelligent building energy-saving control system of the present invention, wherein: the rotation rules are formulated based on the status of the intelligent device, and the specific steps are as follows: Based on the usage frequency, workload, and maintenance cycle of smart devices, a set of rotation rules should be developed to give each smart device the opportunity to work under the same conditions and to avoid excessive use of some devices while other devices are idle for a long time.

[0016] As a preferred solution of the intelligent building energy-saving control system of the present invention, wherein: the rotation rules are formulated based on the status of the intelligent device, and the intelligent device works according to the rotation rules. The specific steps are as follows: Create a dormant device list based on the smart devices marked by the system as dormant; When the system detects that the working state of the device needs to be increased to cope with the increased load, the central processor generates a control signal, and the central processor selects a smart device from the list of dormant devices according to the rotation rule, wakes it up through the communication network of the smart building, and converts the selected smart device from the dormant state to the working state; Once the smart device is awakened and put into operation, the system will continuously monitor its operating status and performance indicators. If the smart device no longer meets the current needs, including failure and overload, the system will adjust the device status again, including putting the smart device that does not meet the needs into sleep mode and taking maintenance measures.

[0017] The beneficial effects of the present invention are as follows: the present invention realizes comprehensive perception and intelligent management of the building environment by integrating key technologies such as environmental monitoring, user perception, intelligent device control and management, energy consumption prediction and abnormal management. The system can accurately monitor environmental changes, judge the user's presence status, and intelligently control the working status of the equipment accordingly, effectively reducing energy consumption; at the same time, through the intelligent management of the equipment status, the balanced use of equipment and the timely management of energy consumption anomalies are realized, which significantly improves energy utilization efficiency, improves user experience, and effectively reduces operating costs, providing strong technical support for energy conservation and emission reduction. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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 work.

[0019] Figure 1 This is a flow chart of the intelligent building energy-saving control system in Example 1.

[0020] Figure 2 This is a flowchart in Example 1 for controlling the working state and sleeping state of smart devices in a smart building. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0023] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0024] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides an intelligent building energy-saving control system, comprising the following steps: S1. Real-time monitoring and collection of environmental data of the target area corresponding to the smart building.

[0025] Going a step further, real-time video streaming is captured through a camera; Use background subtraction algorithms to remove the background from consecutive video frames and focus the image on potential dynamic elements; Use edge detection to identify body posture and facial features of people in images; Capture ambient sound through a microphone array to reduce background noise; Use fast Fourier transform to analyze the frequency components of sound and identify people's voices, footsteps, and door opening and closing sounds; The infrared signal is converted into a visual heat map through an infrared thermal imaging camera to obtain the temperature distribution; Analyze changes in heat maps to identify temperature peaks and movement patterns to determine if there is activity.

[0026] The collected data is transmitted to the central processor via the communication network (Wi-Fi).

[0027] It should also be noted that a camera is used to capture a real-time video stream within the target area, and a background subtraction algorithm is used to remove the static background from the video frame in order to highlight the dynamic object.

[0028] Edge detection technology is used to identify key features in the video, such as human outlines and facial details. At the same time, the system's microphone array can capture environmental sounds and use signal processing technology (such as fast Fourier transform) to analyze the sound spectrum to identify specific sound events, such as human conversations, footsteps, or the sound of doors opening and closing.

[0029] Infrared thermal imaging cameras are used to convert invisible infrared radiation into visible thermal images. By analyzing these thermal images, the temperature distribution and its changes can be tracked to infer whether there is human activity in the area.

[0030] All the data collected by these sensors will be compressed and transmitted to the central processor via wireless communication networks such as Wi-Fi for subsequent data processing and decision support.

[0031] S2. Based on the data provided by the environment monitoring module, determine whether there is a user in the target area.

[0032] Furthermore, a convolutional neural network is used to extract features including temperature data T, light intensity data L, audio data A, infrared imaging data I, and video frame data V from the environmental data; A deep learning model is used and an attention mechanism is introduced to perform weighted fusion according to the importance of each environmental feature vector, and different environmental feature vectors are fused into a comprehensive feature vector, which is expressed as: ; Among them, F T (T) represents the feature extraction of temperature data T, F L (L) represents the feature extraction of light intensity L, AL is a multi-attention mechanism, F A (A) represents the feature extraction of audio signal A, F I (I) represents the feature extraction of infrared thermal image I, F V (V) represents feature extraction of video frame V; Based on the comprehensive feature vector F, it is determined whether there is a user in the target area. The expression is as follows: ; Among them, p represents the probability that there is a user in the target area, is the activation function, W f is the weight matrix of the decision layer, b f is the bias vector of the decision layer, and f represents the fused feature vector.

[0033] It should also be noted that the model first preprocesses and extracts features for each type of input data separately. For example, for video frames I, convolutional neural networks (CNNs) are used to extract high-level visual features; for audio signals A, Mel-frequency cepstral coefficients (MFCCs) or other methods are used to extract sound features; for infrared images R, temperature distribution patterns are extracted as features.

[0034] Next, these features are concatenated together to form a multimodal feature vector. This vector then passes through a fully connected layer (decision layer) that contains the weight matrix W f and the bias vector b f Finally, through the activation function Output a value between 0 and 1, representing the probability that a user exists in the target area.

[0035] Such a multimodal fusion method can improve the robustness and accuracy of the model because it not only considers a single type of sensor data, but also comprehensively utilizes three different types of information: video, audio and infrared to make judgments.

[0036] S3. Based on the user's presence status, control the working state and sleep state of smart devices in the smart building.

[0037] Furthermore, based on the target scenario and requirements, a user presence state threshold p is defined th , the central controller compares p th The size of and p determines the working status of the smart devices in the smart building; When p>p th When the user is in the target area, the smart device should enter the working state, such as automatically adjusting the light to a suitable brightness and the air conditioner to a comfortable temperature. When p is less than p th When the user is not in the target area, the smart device should enter a dormant state to save energy; Among them, p th Adjust according to different scenarios and needs to ensure timely response to user needs and save energy when no one is around; The control unit (CU) in the central processor generates specific control signals according to the status of the smart device; The control signal is transmitted to the smart devices in the target area through the communication network (Wi-Fi) of the smart building. The control module on the smart device analyzes the received control signal and extracts specific control instructions. According to the instructions in the signal, the smart device performs corresponding actions.

[0038] It should also be noted that the corresponding actions performed by smart devices include: on / off commands: sent to smart devices such as lamps, sockets, curtains, etc. to control their opening or closing; brightness adjustment: sent to dimmable lighting smart devices to set a specific brightness level; temperature setting: sent to smart devices such as air conditioners and heaters to set the indoor temperature; other advanced functions: such as scene mode switching, volume control, etc.

[0039] Control Unit (CU): It is one of the core components of the central processing unit (CPU). The main responsibility of the control unit is to coordinate and direct the entire processor and other components of the system to perform operations correctly according to the predetermined instruction sequence. When the smart device is in different working states, such as running applications, processing data, or interacting with other hardware components, the control unit generates specific control signals based on these states. These control signals guide the data flow, operation sequence, and operation of external devices within the CPU to ensure that all computing tasks can be completed in an orderly and efficient manner. In short, the control unit is like a traffic commander, issuing specific traffic instructions (i.e., control signals) based on the current traffic conditions (i.e., equipment status) to ensure that data and instructions flow smoothly on the correct path.

[0040] S4. Retrieve and record all smart device information associated with the smart building.

[0041] Furthermore, a periodic update mechanism is designed through event-driven to regularly check the status changes of smart devices; Create a device information database to store the basic information and operating status of all smart devices in the smart building, including but not limited to device type, location, unique identifier (such as MAC address), manufacturer, model, firmware version, connection status, last maintenance date, etc.; Generate regular reports using information from the database to analyze the health status, energy consumption, and failure rate of smart devices to facilitate predictive maintenance and optimize resource allocation.

[0042] It should also be noted that the design of a periodic update mechanism through event-driven means that this mechanism is usually driven by a timer or a scheduled task, and automatically starts the inspection process at a predetermined time interval. Whenever the set time point is reached, the system will automatically initiate an event, which will check the status information of the smart device after the event is triggered, and update the information to the device information database. This method ensures that the system can obtain the latest device status in a timely manner, and at the same time, through the event-driven method, it reduces unnecessary resource consumption and improves the efficiency and response speed of the system.

[0043] Create a device information database. Specifically, this database will contain basic information about each device, such as device type, installation location, unique identifier (such as MAC address), manufacturer, model, firmware version, current connection status, and the most recent maintenance date. With such a database, managers can easily track and manage the status of each device, perform data analysis, and evaluate the health status and energy consumption level of the device, thereby achieving predictive maintenance and optimizing resource allocation.

[0044] S5. Build an energy consumption prediction model based on the information of smart devices, determine the energy consumption range and identify smart devices with abnormal energy consumption based on the energy consumption data.

[0045] Furthermore, in the latest state of the smart device, the power and current consumption data are continuously collected through the built-in power metering module of the smart device, and the power and current consumption data are sent to the central processor through the communication network (Wi-Fi).

[0046] The transmitted data packet contains the device ID, timestamp, power consumption value and current consumption value, and possible status identification (working or sleeping); Based on the comprehensive feature vector F, the energy consumption model is constructed, and the expression is: ; Among them, ML represents the residual multilayer perceptron, W is the weight matrix, b is the bias vector, and E is the energy consumption of the smart device.

[0047] The energy consumption range of a normal smart device in a normal working state is defined as a first energy consumption range, and the energy consumption range of the smart device in a dormant state is defined as a second energy consumption range; The central processing unit analyzes the energy consumption data through the result E of the energy consumption model to determine whether the electric energy consumption value and the current consumption value are within the preset first energy consumption range and the second energy consumption range; If the energy consumption value of the smart device falls within the first consumption range, the system will mark the smart device as being in a normal working state; If the energy consumption value exceeds one of the first consumption range and the second consumption range, it indicates that the smart device is faulty or overloaded, and the system will mark it as an abnormal state; If the energy consumption value of the smart device falls within the second consumption range, the system will mark it as a dormant state.

[0048] It should also be noted that the CPU uses the received data to analyze the data in combination with an energy consumption model based on machine learning. The model uses a residual multi-layer perceptron (MLP) structure and processes the data through a weight matrix W and a bias vector b to predict the energy consumption E of the smart device. This process can be represented as a function F that receives data from the smart device as input and outputs a predicted energy consumption value.

[0049] S6. According to the smart devices with abnormal energy consumption, adjust the status of the smart devices with energy consumption exceeding the range.

[0050] Furthermore, for smart devices marked as abnormal, the system further analyzes the cause of abnormal energy consumption and distinguishes whether it is caused by smart device failure, overload use or improper configuration; According to the abnormal cause, the central processor formulates adjustment strategies for abnormal smart devices: If the abnormality is caused by overload, the output power of the smart device will be limited; If the abnormality is caused by improper configuration, optimize the operating parameters of the smart device; The control unit (CU) in the central processor generates specific control signals according to the adjustment strategy and sends the control signals to the smart devices with abnormal energy consumption through the communication network (Wi-Fi) of the smart building; The control module on the abnormal energy consumption intelligent device receives and analyzes the control signal sent by the central processor, and performs corresponding adjustment operations according to the instructions in the signal.

[0051] It should also be noted that the system further analyzes the specific reasons for the abnormal energy consumption when the system marks the smart device as abnormal. This usually involves in-depth mining of historical data, such as checking the device's usage pattern, load change trends, and data comparison with normal devices. The system may use data analysis techniques, such as statistical analysis or machine learning algorithms to identify the root cause of the abnormality, such as device failure, overload use, or improper configuration.

[0052] The specific control signals are generated as follows: The control unit (CU) in the central processor formulates a specific adjustment strategy based on the analyzed abnormal causes. Once the measures to be taken are determined (such as limiting power output or optimizing operating parameters), the CU generates a set of specific control signals. These signals contain clear instructions, such as reducing the maximum power setting, changing the operating mode, or updating the device configuration parameters. The control signals are encoded and sent to the corresponding smart devices via the Wi-Fi network.

[0053] The corresponding adjustment operations include: if the control signal instructs the device to enter low power mode, the device's control module will adjust its internal settings to reduce power output; if the control signal requires optimization of operating parameters, the device will update these parameters to improve performance. In this way, through the automated feedback mechanism, the system can ensure that the energy consumption of smart devices remains within a reasonable range while improving the efficiency and stability of the overall system.

[0054] S7. Formulate rotation rules based on the status of the smart device, and the smart device works according to the preset rotation rules.

[0055] Furthermore, based on the frequency of use, workload, and maintenance cycle of smart devices, a set of rotation rules can be developed to give each smart device a chance to work under the same conditions and avoid overuse of some devices while other devices are idle for a long time.

[0056] Create a dormant device list based on the smart devices marked by the system as dormant; When the system detects that the working state of the device needs to be increased to cope with the increased load, the central processor generates a control signal, and the central processor selects a smart device from the list of dormant devices according to the rotation rule, wakes it up through the communication network (Wi-Fi) of the smart building, and converts the selected smart device from the dormant state to the working state; The control signal contains specific instructions required for device startup and initialization, such as preheating, calibration, or resetting; Once the smart device is awakened and put into operation, the system will continuously monitor its operating status and performance indicators, such as power consumption, efficiency, temperature, etc. If the smart device no longer meets the current needs, including failure and overload, the system will adjust the device status again, including putting the smart device that does not meet the needs into sleep mode and taking maintenance measures.

[0057] It should also be noted that in order to ensure that all smart devices are used evenly and to prevent early wear or failure of some devices due to overuse, the system will mark the smart devices in a dormant state and collect the information of these devices to form a dormant device list. This list contains all devices that are temporarily inactive but can be awakened at any time to share the load. The system tracks which devices are currently dormant by regularly updating this list, so that the appropriate devices can be selected to be awakened and put into use according to actual needs and rotation rules to cope with changing workload requirements.

[0058] In summary, the present invention achieves this by: collecting environmental data in real time based on multimodal sensors and accurately analyzing it to determine whether there are users in the area; then, based on the user's detection results, intelligently controlling the working status of the equipment in the building, thereby ensuring user experience and achieving energy conservation and emission reduction; in addition, by periodically updating the equipment information database and building an energy consumption prediction model, it is possible to promptly discover and resolve problems related to abnormal equipment energy consumption, and accordingly formulate reasonable equipment rotation rules to ensure balanced use of all equipment and extend its service life; in summary, the present invention significantly improves the safety, energy efficiency, and maintenance efficiency of smart buildings, and provides users with a more comfortable and efficient living or working environment.

[0059] Example 2, referring to Table 1, is the second example of the present invention. To further verify the advancement of the present invention, experimental simulation data of an intelligent building energy-saving control system is provided.

[0060] Simulate a smart building environment equipped with a variety of sensors and smart devices, including cameras, microphone arrays, infrared thermal imaging cameras, environmental monitoring modules, etc.

[0061] First, the environmental monitoring module is calibrated to ensure that it can accurately collect temperature, light intensity, sound, and infrared imaging data.

[0062] Next, a convolutional neural network model was deployed and an attention mechanism was trained to fuse multimodal data. In addition, a central controller was set up and a control unit (CU) was developed to generate and send control signals.

[0063] Secondly, during the data collection phase, we simulated multiple scenarios, including those with and without people, as well as different activity modes such as conversation, walking, and opening and closing doors. We recorded the corresponding sensor data for each scenario and analyzed it using a deep learning model to determine whether there were users in the target area.

[0064] Finally, define the user presence status threshold p th, and adjust the working state of the smart device according to this threshold. Build an energy consumption prediction model, and adjust the state of the smart device according to the model results. At the same time, formulate rotation rules to ensure the balanced use of smart devices.

[0065] The details are shown in Table 1: Table 1 Intelligent building environment and energy consumption monitoring analysis table Test subject name Temperature (T) Light intensity (L) Audio(A) Infrared imaging (I) Video frame (V) User existence probability (p) Energy consumption (E) Device Status Region 1 22°C 300lux 70dB 26°C 30fps 0.85 120W Work Area 2 24°C 350lux 65dB 27°C 25fps 0.90 110W Work Area 3 21°C 280lux 75dB 25°C 35fps 0.78 130W Work Region 4 23°C 320lux 72dB 28°C 30fps 0.92 115W Work By analyzing the above table data, it can be clearly seen that the user presence probability (p) is strongly correlated with the environmental data. For example, in areas 1 and 4, higher temperatures and light intensity, as well as moderate audio levels, lead to higher user presence probabilities. Energy consumption (E) is related to user activities. In areas with higher user probabilities, energy consumption is also relatively high, which indicates that smart devices tend to be in working state when there are people. The device state is adjusted according to the user presence probability and energy consumption data. When the user presence probability is higher than the threshold pth, the device is in working state, otherwise, the device enters sleep state to save energy.

[0066] Through the intelligent building energy-saving control system of the present invention, not only can real-time monitoring and intelligent analysis of the internal environment of the building be achieved, but also the working status of the intelligent equipment can be automatically adjusted according to the monitoring results to optimize energy consumption. In particular, through the application of multimodal data fusion and deep learning models, the present invention significantly improves the accuracy of judging the user's presence status, and at the same time, energy consumption anomalies are discovered in time through the energy consumption prediction model, which reflects the innovation and practicality of the present invention in improving energy efficiency and user comfort.

[0067] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent building energy-saving control system, characterized in that: include, Environmental monitoring module: real-time monitoring and collection of environmental data of the target area corresponding to the smart building; User perception module: determines whether there are users in the target area based on the data provided by the environment monitoring module; Device control module: controls the working state and sleeping state of smart devices in smart buildings based on the user's presence status; Device management module: retrieve and record all smart device information associated with the smart building; Energy consumption statistics module: Build an energy consumption prediction model based on smart device information, determine the energy consumption range and identify smart devices with abnormal energy consumption based on energy consumption data; Abnormal energy consumption management module: adjust the status of the smart devices whose energy consumption exceeds the range according to the smart devices with abnormal energy consumption; Balanced rotation module: formulates rotation rules based on the status of smart devices, and smart devices work according to the preset rotation rules.

2. The intelligent building energy-saving control system according to claim 1, characterized in that: The specific steps of real-time monitoring and collecting environmental data of the target area corresponding to the intelligent building are as follows: Capture live video stream via camera; Use background subtraction algorithms to remove the background from consecutive video frames and focus the image on potential dynamic elements; Use edge detection to identify body posture and facial features of people in images; Capture ambient sound through a microphone array to reduce background noise; Use fast Fourier transform to analyze the frequency components of sound and identify people's voices, footsteps, and door opening and closing sounds; The infrared signal is converted into a visual heat map through an infrared thermal imaging camera to obtain the temperature distribution; Analyze changes in heat maps to identify temperature peaks and movement patterns to determine if there is activity; The collected data is transmitted to the central processor via the communication network.

3. The intelligent building energy-saving control system according to claim 2, characterized in that: The specific steps of judging whether there is a user in the target area based on the data provided by the environment monitoring module are as follows: Use a convolutional neural network to extract features including temperature data T, light intensity data L, audio data A, infrared imaging data I, and video frame data V from environmental data; A deep learning model is used and an attention mechanism is introduced to perform weighted fusion according to the importance of each environmental feature vector, and different environmental feature vectors are fused into a comprehensive feature vector, which is expressed as: ; Among them, F T (T) represents the feature extraction of temperature data T, F L (L) represents the feature extraction of light intensity L, AL is a multi-attention mechanism, F A (A) represents the feature extraction of audio signal A, F I (I) represents the feature extraction of infrared thermal image I, F V (V) represents feature extraction of video frame V; Based on the comprehensive feature vector F, it is determined whether there is a user in the target area. The expression is as follows: ; Among them, p represents the probability that there is a user in the target area, is the activation function, W f is the weight matrix of the decision layer, b f is the bias vector of the decision layer, and f represents the fused feature vector.

4. The intelligent building energy-saving control system according to claim 3, characterized in that: The specific steps of controlling the working state and the dormant state of the smart devices in the smart building based on the user's presence state are as follows: Based on the target scenario and requirements, define a user presence status threshold p th , the central controller compares p th The size of and p determines the working status of the smart devices in the smart building; When p>p th When the user is in the target area, the smart device should enter the working state; When p is less than p th When the user is not in the target area, the smart device should enter the sleep state; The control unit in the central processor generates specific control signals according to the status of the smart device; Control signals are transmitted to smart devices in the target area through the communication network of the smart building. The control module on the smart device analyzes the received control signal and extracts specific control instructions. According to the instructions in the signal, the smart device performs corresponding actions.

5. The intelligent building energy-saving control system according to claim 4, characterized in that: The specific steps of retrieving and recording all smart device information associated with the smart building are as follows: Design a periodic update mechanism through event-driven to regularly check the status changes of smart devices; Create a device information database to store the basic information and operating status of all smart devices in the smart building; Generate regular reports using the information in the database to analyze the health status, energy consumption, and failure rate of smart devices.

6. The intelligent building energy-saving control system according to claim 5, characterized in that: The specific steps of building an energy consumption prediction model based on smart device information are as follows: In the latest state of the smart device, the power and current consumption data are continuously collected through the built-in power metering module of the smart device, and the power and current consumption data are sent to the central processor through the communication network; Based on the comprehensive feature vector F, the energy consumption model is constructed, and the expression is: ; Among them, ML represents the residual multilayer perceptron, W is the weight matrix, b is the bias vector, and E is the energy consumption of the smart device.

7. The intelligent building energy-saving control system according to claim 6, characterized in that: The specific steps of judging the energy consumption range and identifying smart devices with abnormal energy consumption according to the energy consumption data are as follows: The energy consumption range of a normal smart device in a normal working state is defined as a first energy consumption range, and the energy consumption range of the smart device in a dormant state is defined as a second energy consumption range; The central processing unit analyzes the energy consumption data through the result E of the energy consumption model to determine whether the electric energy consumption value and the current consumption value are within the preset first energy consumption range and the second energy consumption range; If the energy consumption value of the smart device falls within the first consumption range, the system will mark the smart device as being in a normal working state; If the energy consumption value exceeds one of the first consumption range and the second consumption range, it indicates that the smart device is faulty or overloaded, and the system will mark it as an abnormal state; If the energy consumption value of the smart device falls within the second consumption range, the system will mark it as a dormant state.

8. The intelligent building energy-saving control system according to claim 7, characterized in that: The specific steps of adjusting the state of the smart device whose energy consumption exceeds the range according to the smart device with abnormal energy consumption are as follows: For smart devices marked as abnormal, the system further analyzes the cause of abnormal energy consumption to distinguish whether it is caused by smart device failure, overload or improper configuration; According to the abnormal cause, the central processor formulates adjustment strategies for abnormal smart devices: If the abnormality is caused by overload, the output power of the smart device will be limited; If the abnormality is caused by improper configuration, optimize the operating parameters of the smart device; The control unit in the central processor generates specific control signals according to the adjustment strategy and sends the control signals to the smart devices with abnormal energy consumption through the communication network of the smart building; The control module on the abnormal energy consumption intelligent device receives and analyzes the control signal sent by the central processor, and performs corresponding adjustment operations according to the instructions in the signal.

9. The intelligent building energy-saving control system according to claim 8, characterized in that: The specific steps of formulating rotation rules based on the status of smart devices are as follows: Based on the usage frequency, workload, and maintenance cycle of smart devices, a set of rotation rules should be developed to give each smart device the opportunity to work under the same conditions and to avoid excessive use of some devices while other devices are idle for a long time.

10. The intelligent building energy-saving control system according to claim 9, characterized in that: The rotation rules are formulated based on the status of the smart device, and the smart device works according to the rotation rules. The specific steps are as follows: Create a dormant device list based on the smart devices marked by the system as dormant; When the system detects that the working state of the device needs to be increased to cope with the increased load, the central processor generates a control signal, and the central processor selects a smart device from the list of dormant devices according to the rotation rule, wakes it up through the communication network (Wi-Fi) of the smart building, and converts the selected smart device from the dormant state to the working state; Once the smart device is awakened and put into operation, the system will continuously monitor its operating status and performance indicators. If the smart device no longer meets the current needs, including failure and overload, the system will adjust the device status again, including putting the smart device that does not meet the needs into sleep mode and taking maintenance measures.

Citation Information

Patent Citations

  • Human body image recognition method

    CN110457980A

  • Thermal imaging detection method and device, storage medium and terminal

    CN111198403A

  • Intelligent building energy-saving control method and system

    CN111913395A

  • Computer visual identification system and method

    CN116958771A

  • Smart park multi-source data dynamic monitoring and real-time analysis system and method

    CN118072255A

Cited By

  • Central air conditioner energy-saving control system based on Internet of Things

    CN119245159A