Building electrical equipment intelligent monitoring method and system based on Internet of Things

Abstract

The invention relates to the technical field of electrical equipment management, and particularly discloses a building electrical equipment intelligent monitoring method and system based on the Internet of Things, and the method comprises the steps: laying a sensor network in a building, and enabling the sensor network to be installed at the electrical equipment and corresponding environment monitoring points in the building, the data acquisition module is used for acquiring related data of electrical equipment and building environment in real time; an edge computing node is established in a sensor network or at an equipment end and is used for carrying out primary processing on data acquired in real time and transmitting the processed data to a cloud platform through a wireless communication technology; by deploying the sensor network and the edge computing node, real-time data acquisition, processing and analysis of the electrical equipment and the building environment are realized, and by adopting the adaptive data fusion algorithm, the deep neural network model and the global optimization decision engine, the running state of the electrical equipment can be dynamically monitored, and the real-time monitoring of the building environment can be realized. And intelligent regulation and control and energy efficiency optimization management can be carried out according to the equipment state and the building energy efficiency target.

Description

Technical Field

[0001] The present invention belongs to the technical field of electrical equipment management, and particularly relates to an intelligent monitoring method and system for building electrical equipment based on the Internet of Things. Background Art

[0002] With the increasing complexity of electrical equipment in buildings, the management and maintenance of building electrical equipment face more and more challenges. Most traditional building electrical equipment monitoring methods rely on manual inspections or traditional monitoring devices, making it difficult to achieve real-time dynamic monitoring and precise control of the status of electrical equipment. In addition, there are also certain limitations in building energy efficiency management. Existing energy efficiency optimization solutions mostly rely on static models and cannot flexibly respond to changing building electrical load demands and environmental factors.

[0003] With the development of Internet of Things technology, the intelligent monitoring of building electrical equipment has become possible. The Internet of Things connects electrical equipment with a computing platform through a sensor network, can collect various types of data in real time, monitor the operating status of the equipment, and thus achieve dynamic control and energy efficiency optimization of the equipment. However, existing Internet of Things-based building electrical equipment monitoring systems still face the following problems in data processing and analysis: the huge and complex amount of real-time data, how to efficiently process and integrate data from different sources; the limitation of the processing capacity of edge computing nodes, how to avoid information loss while ensuring the real-time and accuracy of data; and how to intelligently schedule electrical equipment according to the equipment status and building energy efficiency goals to achieve optimized management of energy efficiency.

[0004] Therefore, it is necessary to propose an intelligent monitoring method and system for building electrical equipment based on the Internet of Things to solve the problems of insufficient real-time and accuracy in the monitoring of building electrical equipment existing in the prior art.

[0005] The above information disclosed in this background art is only used to increase the understanding of the background art of the present invention. Therefore, it may include prior art that is not known to those of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide an intelligent monitoring method and system for building electrical equipment based on the Internet of Things to solve the problems raised in the above background art.

[0007] To achieve the above purpose, the present invention provides the following technical solutions:

[0008] An intelligent monitoring method for building electrical equipment based on the Internet of Things, comprising:

[0009] Deploy a sensor network in the building, and the sensor network is installed at electrical equipment in the building and corresponding environmental monitoring points for real-time collection of relevant data of the electrical equipment and the building environment;

[0010] An edge computing node is established within the sensor network or at the device side to perform preliminary processing on the real-time collected data and transmit the processed data to the cloud platform through wireless communication technology;

[0011] At the cloud platform, an adaptive data fusion algorithm based on artificial intelligence is applied to perform multi-level data fusion on the received data to obtain a fused electrical equipment dataset;

[0012] Multi-dimensional analysis and processing of the fused electrical equipment dataset is achieved through a deep neural network model to generate analysis results;

[0013] Based on the analysis results, the background server automatically generates control instructions for the status of electrical equipment, adjusts the operating parameters of electrical equipment through an intelligent perception mechanism, and realizes dynamic regulation of electrical equipment;

[0014] A global optimization decision engine is introduced to schedule the energy efficiency of electrical equipment in the building, optimize load distribution, energy storage strategies, and power scheduling, and combine with a real-time monitoring and feedback mechanism to realize dynamic optimization management of building energy efficiency.

[0015] Preferably, the edge computing node uses an embedded computing platform with a local operating system to process the real-time collected data;

[0016] The edge computing node uses a machine learning algorithm to perform intelligent cleaning and denoising preprocessing operations on the real-time collected data;

[0017] During the preprocessing operation, unsupervised feature learning is combined with a deep autoencoder to automatically remove noise from the real-time collected data;

[0018] Deep autoencoder formula:

[0019]

[0020] In the formula, X is the input data, is the predicted data, w is the weight of the autoencoder, and λ is the regularization parameter;

[0021] The edge computing node includes a local caching mechanism, and the local caching mechanism uses a circular buffer or an adaptive caching algorithm to temporarily store the real-time collected data to cope with data loss problems in case of communication failures or network congestion.

[0022] Preferably, the adaptive data fusion algorithm automatically adjusts the weights of different data streams according to the quality and availability of the received data to achieve data balance and accuracy during the fusion process;

[0023] The adaptive data fusion algorithm includes a data repair strategy that combines Kalman filtering and Bayesian inference to handle noise and data missingness during the fusion process;

[0024] Multi-level data fusion performs primary fusion on the same type of sensor data and secondary fusion on different types of sensor data, and optimizes and adjusts the relationships between different types of sensors through artificial intelligence algorithms to generate a comprehensive electrical equipment dataset.

[0025] Preferably, the deep neural network model includes CNN, LSTM, and a Transformer model based on the self-attention mechanism, which is selected according to the data characteristics of electrical equipment;

[0026] The network structure design of the deep neural network model includes an input layer, a CNN layer, an LSTM layer, a fully connected layer, and an output layer;

[0027] The deep neural network model uses the gradient descent algorithm to train the model, prevents overfitting through regularization methods, and tunes the hyperparameters;

[0028] The adaptive learning rate algorithm and gradient clipping technique are introduced to dynamically adjust the learning rate of each model parameter and limit the gradient update amplitude;

[0029] When the data is missing or unbalanced, GAN is used to generate synthetic data to augment the data for training. The loss functions of the GAN generator and discriminator are as follows:

[0030] Loss GAN =E[logD(x)]+E[log(1-D(G(z)))]

[0031] In the formula, D(x) is the output of the discriminator, and G(z) is the data generated by the generator;

[0032] The optimized deep neural network model is used for multi-dimensional analysis to identify the device health status, predict the device failure mode, and evaluate the energy efficiency performance, generating analysis results.

[0033] Preferably, the global optimization decision engine is located on the cloud platform, and comprehensively optimizes the load demand of building electrical equipment, the scheduling of energy storage equipment, and power scheduling by integrating multiple optimization algorithms;

[0034] The global optimization decision engine automatically adjusts the control strategy according to the real-time electrical equipment status and building energy efficiency goals to achieve dynamic scheduling and load balancing;

[0035] The multi-objective optimization algorithm is introduced to comprehensively consider energy cost, equipment efficiency, and environmental factors for global collaborative scheduling to achieve the optimal operating state of electrical equipment in the building;

[0036] The scheduling optimization is carried out using the following formula:

[0037] Set the objective functions f1(x), f2(x),..., f m (x), and under the constraint conditions, generate a set of Pareto optimal solutions x through the optimization process * ;

[0038]

[0039] Introduce the demand response strategy, and through the real-time monitoring and feedback mechanism, dynamically adjust the scheduling strategy according to the electricity market price or load demand.

[0040] The intelligent monitoring system for building electrical equipment based on the Internet of Things includes:

[0041] The sensor network, installed at the electrical equipment in the building and related environmental monitoring points, is used to collect relevant data of the electrical equipment and the building environment in real time;

[0042] The edge computing node, arranged within the sensor network or at the electrical equipment end, uses an embedded computing platform with a local operating system to perform preliminary processing on the real-time collected data and transmit the processed data to the cloud platform through a wireless communication protocol;

[0043] The cloud platform is used to receive and process the data from the sensor network, apply an adaptive data fusion algorithm based on artificial intelligence for multi-level data fusion, and generate a fused electrical equipment dataset;

[0044] The deep neural network model is used to perform multi-dimensional analysis on the fused electrical equipment dataset, identify the health status of the electrical equipment, predict the equipment failure mode, and evaluate the energy efficiency performance, and generate analysis results;

[0045] The background server is used to automatically generate control instructions based on the analysis results and adjust the operating parameters of the electrical equipment through the intelligent perception mechanism to achieve dynamic regulation of the electrical equipment;

[0046] The global optimization decision-making engine is used to combine the real-time monitoring and feedback mechanism to achieve dynamic optimization management of the energy efficiency of the electrical equipment in the building, and optimize the load distribution, energy storage strategy, and power scheduling.

[0047] Preferably, the sensor network adopts a redundant design, sets multiple data acquisition points, and repeatedly collects data on key electrical equipment and the building environment to prevent data loss caused by the failure of a single acquisition point;

[0048] The sensor network has a self-diagnosis function. When a fault occurs or communication is lost, it automatically switches to a backup plan and reports the fault information to the cloud platform for remote diagnosis and repair.

[0049] Preferably, the edge computing node includes a local caching mechanism. The local caching mechanism adopts a circular buffer or an adaptive caching algorithm to temporarily store the real-time collected data to address the data loss problem in case of communication failures or network congestion.

[0050] The edge computing node dynamically adjusts the data transmission rate, packet size, and encoding method according to the network conditions through low-power wireless communication protocols such as LoRa, NB-IoT, or Zigbee to achieve stable data transmission to the cloud platform.

[0051] Preferably, the system further includes an intelligent decision-making module for self-learning and adaptive adjustment of the operating mode of electrical equipment using reinforcement learning algorithms.

[0052] Based on historical operation data and real-time monitoring data, the intelligent decision-making module predicts the working state of electrical equipment and automatically adjusts the load distribution and start-stop strategy of electrical equipment in combination with the changing power demands in different areas of the building.

[0053] The intelligent decision-making module optimizes the building energy efficiency through an integrated multi-objective optimization algorithm to achieve low-energy consumption and high-efficiency operation and maintenance of electrical equipment.

[0054] The multi-objective optimization algorithm comprehensively considers the power consumption, operating life, load fluctuations, and maintenance costs of electrical equipment to provide the optimal operation scheduling strategy.

[0055] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0056] By deploying a sensor network and edge computing nodes, the present invention realizes real-time data collection, processing, and analysis of electrical equipment and the building environment. Moreover, by adopting an adaptive data fusion algorithm, a deep neural network model, and a global optimization decision-making engine, it can not only dynamically monitor the operating state of electrical equipment but also perform intelligent control and energy efficiency optimization management according to the equipment state and building energy efficiency goals. Control instructions are automatically generated based on the analysis results, and electrical equipment is dynamically controlled through an intelligent sensing mechanism to optimize energy efficiency and load distribution. At the same time, a global optimization decision-making engine is introduced to achieve dynamic optimization management of the energy efficiency of building electrical equipment, solving the problems of insufficient real-time monitoring and accuracy in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flowchart of the intelligent monitoring method for building electrical equipment based on the Internet of Things of the present invention.

[0058] Figure 2 This is the framework diagram of the intelligent monitoring system for building electrical equipment based on the Internet of Things of the present invention. Specific implementation mode

[0059] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0060] Embodiment 1:

[0061] Please refer to Figure 1 As shown, the intelligent monitoring method for building electrical equipment based on the Internet of Things includes:

[0062] Deploy a sensor network in the building. The sensor network is installed at electrical equipment in the building and corresponding environmental monitoring points for real-time collection of relevant data of electrical equipment and the building environment;

[0063] Establish an edge computing node in the sensor network or at the device end for preliminary processing of the real-time collected data and transmitting the processed data to the cloud platform through wireless communication technology;

[0064] The edge computing node uses an embedded computing platform with a local operating system for processing the real-time collected data;

[0065] The edge computing node uses machine learning algorithms for intelligent cleaning and denoising preprocessing operations on the real-time collected data;

[0066] During the preprocessing operation, unsupervised feature learning is combined with a deep autoencoder to automatically remove noise in the real-time collected data;

[0067] The edge computing node includes a local caching mechanism. The local caching mechanism uses a circular buffer or an adaptive caching algorithm for temporarily storing the real-time collected data to cope with data loss problems in case of communication failures or network congestion.

[0068] Furthermore, by deploying an edge computing node in the sensor network or at the device end and combining an embedded computing platform and a local operating system, preliminary processing and intelligent preprocessing of real-time data are realized, significantly improving the data quality. Through the application of machine learning algorithms and deep autoencoders, noise in the data is effectively removed, ensuring the accuracy and reliability of the data. The combination of these technologies enhances the processing ability, fault tolerance, and efficiency in complex environments, ensuring the efficient transmission and processing of data.

[0069] On the cloud platform, an adaptive data fusion algorithm based on artificial intelligence is applied to perform multi-level data fusion on the received data to obtain a fused electrical equipment dataset;

[0070] The adaptive data fusion algorithm automatically adjusts the weights of different data streams according to the quality and availability of the received data to achieve data balance and accuracy in the fusion process;

[0071] The adaptive data fusion algorithm includes a data repair strategy that combines Kalman filtering and Bayesian inference to handle noise and data missingness in the fusion process;

[0072] Multi-level data fusion performs primary fusion on the same type of sensor data and secondary fusion on different types of sensor data, and optimizes and adjusts the relationships between different types of sensors through artificial intelligence algorithms to generate a comprehensive electrical equipment dataset.

[0073] Furthermore, by applying an adaptive data fusion algorithm based on artificial intelligence on the cloud platform to perform multi-level fusion on the received electrical equipment data, the integrity and accuracy of the data are significantly improved. Through multi-level fusion, the data of different types of sensors are optimized, generating a comprehensive and reliable electrical equipment dataset, enhancing the intelligent analysis ability and decision support effect.

[0074] Perform multi-dimensional analysis and processing on the fused electrical equipment dataset through a deep neural network model to generate analysis results;

[0075] The deep neural network model includes CNN, LSTM, and the Transformer model based on the self-attention mechanism, which is selected according to the data characteristics of electrical equipment;

[0076] The network structure design of the deep neural network model includes an input layer, a CNN layer, an LSTM layer, a fully connected layer, and an output layer;

[0077] The deep neural network model uses the gradient descent algorithm to train the model, prevents overfitting through regularization methods, and tunes the hyperparameters;

[0078] Introduce an adaptive learning rate algorithm and gradient clipping technology to dynamically adjust the learning rate of each model parameter and limit the gradient update amplitude;

[0079] When the data is missing or unbalanced, use GAN to generate synthetic data to augment the data for training;

[0080] Use the optimized deep neural network model for multi-dimensional analysis to identify the equipment health status, predict the equipment failure mode, and evaluate the energy efficiency performance, generating analysis results.

[0081] Furthermore, through multi-dimensional analysis of the fused electrical equipment dataset by a deep neural network model, the accuracy of equipment status monitoring, fault prediction, and energy efficiency evaluation has been significantly improved.

[0082] Based on the analysis results, the background server automatically generates control instructions for the status of electrical equipment, adjusts the operating parameters of electrical equipment through an intelligent sensing mechanism, and realizes dynamic regulation of electrical equipment;

[0083] Introduce a global optimization decision engine to schedule the energy efficiency of electrical equipment in the building, optimize load distribution, energy storage strategies, and power scheduling, and combine real-time monitoring and feedback mechanisms to realize dynamic optimization management of building energy efficiency;

[0084] The global optimization decision engine is located on the cloud platform and comprehensively optimizes the load demand of building electrical equipment, the scheduling and power scheduling of energy storage equipment by integrating multiple optimization algorithms;

[0085] The global optimization decision engine automatically adjusts the control strategy according to the real-time electrical equipment status and building energy efficiency goals to achieve dynamic scheduling and load balancing;

[0086] Introduce a multi-objective optimization algorithm, comprehensively consider energy cost, equipment efficiency, and environmental factors, conduct global collaborative scheduling, and achieve the best operating state of electrical equipment in the building;

[0087] Introduce a demand response strategy, and through real-time monitoring and feedback mechanisms, dynamically adjust the scheduling strategy according to electricity market prices or load demands.

[0088] Furthermore, by introducing a global optimization decision engine, dynamic optimization management of the energy efficiency of electrical equipment in the building has been realized, effectively improving the energy use efficiency of the building. This engine is based on the cloud platform and integrates multiple optimization algorithms, comprehensively considering load demand, energy storage equipment scheduling, and power scheduling, ensuring the best operating state of electrical equipment. The real-time monitoring and feedback mechanism enables the system to automatically adjust the control strategy to achieve dynamic scheduling and load balancing, thereby optimizing energy costs and improving equipment efficiency.

[0089] Example 2:

[0090] Please refer to Figure 2 as shown, the Internet of Things-based intelligent monitoring system for building electrical equipment includes:

[0091] A sensor network installed at electrical equipment in the building and related environmental monitoring points for real-time collection of relevant data on electrical equipment and the building environment;

[0092] Edge computing nodes are deployed within the sensor network or at the electrical equipment terminal. They utilize an embedded computing platform with a local operating system to perform preliminary processing on the real-time collected data and transmit the processed data to the cloud platform through a wireless communication protocol.

[0093] The cloud platform is used to receive and process data from the sensor network, apply an adaptive data fusion algorithm based on artificial intelligence for multi-level data fusion, and generate a fused electrical equipment dataset.

[0094] The deep neural network model is used to perform multi-dimensional analysis on the fused electrical equipment dataset, identify the health status of electrical equipment, predict equipment failure modes, and evaluate energy efficiency performance, generating analysis results.

[0095] The background server is used to automatically generate control instructions based on the analysis results and adjust the operating parameters of electrical equipment through an intelligent perception mechanism to achieve dynamic control of electrical equipment.

[0096] The global optimization decision engine is used to combine real-time monitoring and feedback mechanisms to achieve dynamic optimization management of the energy efficiency of electrical equipment in the building, optimizing load distribution, energy storage strategies, and power scheduling.

[0097] The sensor network adopts a redundant design, setting multiple data collection points and repeatedly collecting data on key electrical equipment and the building environment to prevent data loss caused by the failure of a single collection point.

[0098] The sensor network has a self-diagnosis function. When a failure or communication loss occurs, it automatically switches to a backup solution and reports the failure information to the cloud platform for remote diagnosis and repair.

[0099] The edge computing node includes a local caching mechanism. The local caching mechanism adopts a circular buffer or an adaptive caching algorithm to temporarily store real-time collected data to address data loss problems in case of communication failures or network congestion.

[0100] The edge computing node dynamically adjusts the data transmission rate, packet size, and coding method according to the network conditions through low-power wireless communication protocols such as LoRa, NB-IoT, or Zigbee to achieve stable data transmission to the cloud platform.

[0101] The system further includes an intelligent decision-making module used to perform self-learning and adaptive adjustment on the operating mode of electrical equipment using reinforcement learning algorithms.

[0102] Based on historical operation data and real-time monitoring data, the intelligent decision-making module predicts the working state of electrical equipment and automatically adjusts the load distribution and start-stop strategy of electrical equipment in combination with the changing power demand in different areas of the building.

[0103] The intelligent decision-making module optimizes building energy efficiency through an integrated multi-objective optimization algorithm to achieve low-energy consumption and high-efficiency operation and maintenance of electrical equipment.

[0104] The multi-objective optimization algorithm comprehensively considers the power consumption, operating life, load fluctuation, and maintenance cost of electrical equipment to provide an optimal operation scheduling strategy.

[0105] Application of the Internet of Things-based intelligent monitoring method and system for building electrical equipment in a hotel building:

[0106] I. Application background

[0107] A hotel building is a multi-functional building that includes guest rooms, dining areas, meeting rooms, public areas, and infrastructure such as heating, ventilation, and air conditioning. During the operation of the hotel, energy efficiency management and real-time monitoring of electrical equipment are crucial. The Internet of Things-based intelligent monitoring method and system can improve the working efficiency of electrical equipment, reduce energy waste, enhance the ability of equipment health management and fault prediction, and ensure safety at the same time.

[0108] II. System architecture

[0109] 1. Sensor network layout

[0110] Install a distributed sensor network in various areas of the hotel building. The sensors are placed in the following locations:

[0111] Electrical equipment monitoring points: such as air conditioners, refrigerators, laundry equipment, lighting systems, refrigeration equipment, etc., to collect real-time data on the operating status, power consumption, temperature, humidity, current, etc. of electrical equipment.

[0112] Environmental monitoring points: such as environmental parameters in each room, corridor, restaurant, and meeting room, including air quality, temperature and humidity, light intensity, etc.

[0113] 2. Edge computing nodes

[0114] Each key electrical equipment and environmental monitoring point is equipped with an edge computing node. The node uses an embedded computing platform with a local operating system to perform data preprocessing (denoising, cleaning, preliminary analysis). For example:

[0115] Perform real-time analysis on the power and temperature data of air conditioning equipment to detect whether the equipment is in a normal working state.

[0116] Perform intelligent analysis on the data of the lighting system to identify whether there are abnormalities (such as excessive power consumption).

[0117] The data is transmitted to the cloud platform through low-power wireless communication protocols such as LoRa, NB-IoT, or Zigbee to ensure stable data transmission.

[0118] 3. Cloud Platform and Adaptive Data Fusion

[0119] Data collected by all sensors is transmitted to the cloud platform, where an adaptive data fusion algorithm based on artificial intelligence is applied to fuse and optimize various types of sensor data. This process includes:

[0120] Multi-level data fusion: Primary fusion is performed on data from the same type of sensors, and secondary fusion is carried out on data from different types of sensors to generate a comprehensive electrical equipment dataset.

[0121] Kalman filtering and Bayesian inference: Used to process noise and missing values in the data to ensure data accuracy.

[0122] Intelligent data repair and supplementation: When device sensors fail, the system predicts and repairs lost data through historical data.

[0123] 4. Deep Neural Network Analysis and Prediction

[0124] The cloud platform uses a deep neural network model to analyze the fused electrical equipment dataset, identify the health status of the equipment, predict device failure modes, and evaluate energy efficiency performance. For example:

[0125] Using LSTM or Transformer models for predictive maintenance of hotel central air conditioning systems, predicting system failures and maintenance requirements.

[0126] Using a CNN model for fault mode recognition of lighting equipment to determine if there are circuit problems.

[0127] 5. Intelligent Control and Global Optimization Decision Engine

[0128] Based on the deep learning analysis results, the background server automatically generates control instructions to adjust the operating parameters of electrical equipment. For example:

[0129] Air conditioning control: Intelligently adjust the start / stop and working temperature of the air conditioning system according to the environmental temperature, number of guest rooms, and actual demand to optimize energy efficiency.

[0130] Lighting system adjustment: Automatically adjust the light brightness and switches according to the light intensity and area usage.

[0131] At the same time, the global optimization decision engine in the cloud performs energy efficiency optimization:

[0132] Load distribution and scheduling: Schedule the electrical equipment loads on different floors and areas to balance the electricity demand and avoid local overload.

[0133] Energy Storage and Power Scheduling: Intelligently schedule energy storage devices (such as battery energy storage systems), dynamically adjust according to real-time electricity market prices, and reduce electricity costs.

[0134] 6. Intelligent Decision-making and Adaptive Learning

[0135] The system conducts self-learning based on historical data and real-time monitoring data. The intelligent decision-making module adopts reinforcement learning algorithms:

[0136] Adaptive Adjustment: Automatically adjust the load distribution and start / stop strategies of devices according to the occupancy rate of guest rooms, electricity consumption in the dining area, and power demands in public areas such as meeting rooms.

[0137] Building Energy Efficiency Optimization: Through multi-objective optimization algorithms, optimize the scheduling of air conditioners, elevators, lighting systems, etc., and balance energy costs and equipment efficiency.

[0138] III. Application Examples

[0139] 1. Air Conditioning System Optimization:

[0140] Each guest room and air conditioning equipment in public areas are equipped with temperature sensors and power sensors, which transmit data in real-time to the edge computing node for preliminary processing.

[0141] The cloud platform fuses the data of all air conditioning equipment, uses a deep neural network model to predict equipment failures, and conducts maintenance in advance.

[0142] According to the real-time environmental temperature and the number of guests in the room, intelligently adjust the air conditioning temperature and operating status, optimize energy efficiency, and reduce power consumption.

[0143] 2. Lighting System Management:

[0144] Light sensors in corridors, meeting rooms, and restaurants monitor the light intensity in real-time and transmit it to the cloud platform for data analysis.

[0145] Automatically adjust the lighting intensity under low light conditions to avoid ineffective energy consumption.

[0146] Automatically turn off the lights during idle time or when there is no one.

[0147] 3. Energy Efficiency Management and Fault Prediction:

[0148] The operating data of all electrical equipment (including air conditioners, elevators, lights, etc.) are collected in real-time through sensor networks and edge computing nodes.

[0149] The system analyzes this data through a deep learning model, automatically identifies anomalies, and adjusts the operating mode of the equipment through intelligent control, predicts possible faults, and issues early warnings.

[0150] For example, if the energy efficiency of an air conditioning device decreases or signs of overload appear, the system will automatically notify the maintenance staff for inspection and repair.

[0151] 4. Comprehensive Optimization and Demand Response:

[0152] According to the fluctuations in electricity market prices, the system dynamically adjusts the start and stop of devices such as air conditioners and elevators in combination with the hotel's electricity demand and energy efficiency goals, reducing the electricity consumption cost during peak hours.

[0153] When the power supply is insufficient, the system will automatically adjust the load distribution, reduce the use of high-power-consuming devices, and give priority to ensuring the operation of key devices.

[0154] IV. Results and Benefits:

[0155] Energy Conservation: By optimizing the use of electrical equipment, energy consumption has been reduced, saving operating costs.

[0156] Equipment Health Management: Predictive maintenance improves the availability of equipment, reduces equipment failure downtime, and extends the equipment life.

[0157] Operating Efficiency: The automated control system improves the operating efficiency of the hotel, ensuring the optimal operating state of each device.

[0158] Environmental Comfort: It provides a comfortable environment for guests while ensuring low energy consumption and low carbon emissions in hotel operations.

[0159] Example 3:

[0160] The embodiment of the present invention also provides a computer-readable storage medium. A program of the intelligent monitoring system for building electrical equipment based on the Internet of Things as described in any one of the above is stored on the computer-readable storage medium. When the program is executed by a processor, it realizes each process of the intelligent supervision system embodiment and can achieve the same technical effects. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium, such as Read-Only Memory (ROM for short), Random Access Memory (RAM for short), magnetic disk or optical disc, etc.

[0161] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0162] In the drawings of the disclosed embodiments of the present invention, only the structures related to the disclosed embodiments of the present invention are involved, and other structures can refer to the general design. Without conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0163] The flowcharts shown in the drawings are only illustrative examples, and do not necessarily include all the contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged, so the actual execution order may be changed according to the actual situation.

[0164] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent monitoring method for building electrical equipment based on the Internet of Things, characterized in that, Including: Deploy a sensor network within a building. The sensor network is installed on electrical equipment and corresponding environmental monitoring points within the building, and is used to collect relevant data of the electrical equipment and the building environment in real time; Establish edge computing nodes within the sensor network or at the device end, which are used to perform preliminary processing on the real-time collected data, and transmit the processed data to the cloud platform through wireless communication technology; On the cloud platform, apply an adaptive data fusion algorithm based on artificial intelligence to perform multi-level data fusion on the received data to obtain a fused electrical equipment dataset; Implement multi-dimensional analysis and processing of the fused electrical equipment dataset through a deep neural network model to generate an analysis result; Based on the analysis result, the background server automatically generates control instructions for the electrical equipment status, adjusts the operating parameters of the electrical equipment through an intelligent perception mechanism, and realizes dynamic regulation of the electrical equipment; Introduce a global optimization decision engine to schedule the energy efficiency of electrical equipment in the building, optimize load distribution, energy storage strategies, and power scheduling, and combine real-time monitoring and feedback mechanisms to realize dynamic optimization management of building energy efficiency; 2. The intelligent monitoring method for building electrical equipment based on the Internet of Things according to claim 1, wherein: The edge computing node adopts an embedded computing platform with a local operating system to process the real-time collected data; The edge computing node uses a machine learning algorithm to perform intelligent cleaning and denoising preprocessing operations on the real-time collected data; During the preprocessing operation, combined with a deep autoencoder for unsupervised feature learning, automatically remove the noise in the real-time collected data; Deep autoencoder formula: In the formula, X is the input data, X~ is the predicted data, w is the weight of the autoencoder, and λ is the regularization parameter; The edge computing node includes a local caching mechanism, and the local caching mechanism adopts a circular buffer or an adaptive caching algorithm to temporarily store the real-time collected data to cope with data loss problems in case of communication failures or network congestion; 3. The intelligent monitoring method for building electrical equipment based on the Internet of Things according to claim 2, characterized in that: The adaptive data fusion algorithm automatically adjusts the weights of different data streams according to the quality and availability of the received data, and is used to achieve data balance and accuracy in the fusion process; The adaptive data fusion algorithm includes a data repair strategy combining Kalman filtering and Bayesian inference, which is used to process the noise and data missing existing in the fusion process; The multi-level data fusion performs primary fusion on the same type of sensor data, secondary fusion on different types of sensor data, and optimizes and adjusts the relationship between different types of sensors through an artificial intelligence algorithm to generate a comprehensive electrical equipment dataset; 4. The intelligent monitoring method for building electrical equipment based on the Internet of Things according to claim 3, wherein: The deep neural network model includes CNN, LSTM, and a Transformer model based on a self-attention mechanism, which is used to be selected according to the data characteristics of electrical equipment; The network structure design of the deep neural network model includes an input layer, a CNN layer, an LSTM layer, a fully connected layer, and an output layer; The deep neural network model uses a gradient descent algorithm to train the model, prevents overfitting through a regularization method, and tunes the hyperparameters; The adaptive learning rate algorithm and gradient clipping technique are introduced to dynamically adjust the learning rate of each model parameter and limit the magnitude of gradient updates; When the data is missing or unbalanced, synthetic data generated by GAN is used to augment the data for training. The loss functions of the GAN generator and discriminator are as follows: Loss GAN = E[logD(x)] + E[log(1 - D(G(z)))] In the formula, D(x) is the output of the discriminator, and G(z) is the data generated by the generator; The optimized deep neural network model is used for multi-dimensional analysis to identify the health status of the device, predict the device failure mode, and evaluate the energy efficiency performance, and generate the analysis results.

5. The intelligent monitoring method for building electrical equipment based on the Internet of Things according to claim 4, wherein: The global optimization decision engine is located on the cloud platform and comprehensively optimizes the load demand of building electrical equipment, the scheduling of energy storage equipment, and the power scheduling by integrating multiple optimization algorithms; The global optimization decision engine automatically adjusts the control strategy according to the real-time electrical equipment status and building energy efficiency target to achieve dynamic scheduling and load balancing; The multi-objective optimization algorithm is introduced to comprehensively consider the energy cost, equipment efficiency, and environmental factors for global collaborative scheduling to achieve the optimal operating state of the electrical equipment in the building; The following formula is used for scheduling optimization: Set the objective functions f1(x), f2(x),..., f m (x), and under the constraint conditions, generate a set of Pareto optimal solutions x * ; The demand response strategy is introduced, and through the real-time monitoring and feedback mechanism, the scheduling strategy is dynamically adjusted according to the electricity market price or load demand.

6. An intelligent monitoring system for building electrical equipment based on the Internet of Things, characterized in that, Including: The sensor network is installed at the electrical equipment in the building and related environmental monitoring points to collect relevant data of the electrical equipment and the building environment in real time; The edge computing nodes are arranged within the sensor network or at the electrical equipment end. Using an embedded computing platform with a local operating system, they are used to preliminarily process the real-time collected data and transmit the processed data to the cloud platform through a wireless communication protocol; The cloud platform is used to receive and process the data from the sensor network, apply an adaptive data fusion algorithm based on artificial intelligence for multi-level data fusion, and generate a fused electrical equipment dataset; The deep neural network model is used to perform multi-dimensional analysis on the fused electrical equipment dataset to identify the health status of the electrical equipment, predict the device failure mode, and evaluate the energy efficiency performance, and generate analysis results; The background server is used to automatically generate control instructions based on the analysis results and adjust the operating parameters of the electrical equipment through an intelligent sensing mechanism to achieve dynamic control of the electrical equipment; The global optimization decision engine is used to combine the real-time monitoring and feedback mechanism to achieve dynamic optimization management of the energy efficiency of the electrical equipment in the building, and optimize the load distribution, energy storage strategy, and power scheduling.

7. The intelligent monitoring system for building electrical equipment based on the Internet of Things according to claim 6, wherein: The sensor network adopts a redundant design, sets multiple data collection points, and repeatedly collects data on key electrical equipment and the building environment to prevent data loss caused by the failure of a single collection point; The sensor network has a self-diagnosis function. When a failure or communication loss occurs, it automatically switches to a backup solution and reports the failure information to the cloud platform for remote diagnosis and repair.

8. The intelligent monitoring system for building electrical equipment based on the Internet of Things according to claim 7, characterized in that: The edge computing node includes a local caching mechanism, and the local caching mechanism adopts a circular buffer or an adaptive caching algorithm to temporarily store the real-time collected data to cope with data loss problems in case of communication failures or network congestion; The edge computing node dynamically adjusts the data transmission rate, packet size, and coding method according to the network conditions through low-power wireless communication protocols such as LoRa, NB-IoT, or Zigbee to achieve stable data transmission to the cloud platform.

9. The intelligent monitoring system for building electrical equipment based on the Internet of Things according to claim 8, characterized in that: The system further includes an intelligent decision-making module for self-learning and adaptive adjustment of the operating mode of electrical equipment using reinforcement learning algorithms; Based on historical operation data and real-time monitoring data, the intelligent decision-making module predicts the working state of electrical equipment, and automatically adjusts the load distribution and start-stop strategy of electrical equipment in combination with the changes in power demand in different areas of the building; The intelligent decision-making module optimizes the building energy efficiency through an integrated multi-objective optimization algorithm to achieve low-energy and high-efficiency operation and maintenance of electrical equipment; The multi-objective optimization algorithm comprehensively considers the power consumption, operating life, load fluctuation, and maintenance cost of electrical equipment to provide the optimal operation scheduling strategy.

Images