Building electricity utilization safety threshold and energy consumption management platform based on improved deep learning algorithm
By applying improved deep learning algorithms in the building power safety and energy consumption management platform, real-time monitoring and management of building power safety is achieved, and the problem of difficulty in comprehensively judging building power safety is solved in the existing technology, and the power safety and management efficiency are improved.
Patent Information
- Application Number
- CN202411819576.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-11
- Publication Date
- 2025-04-18
AI Technical Summary
The existing building power safety and energy consumption management platform is difficult to comprehensively judge the building power safety from the micro and macro perspective, which makes it difficult to follow up and add safety measures, affecting the building power safety.
The building electricity safety threshold and energy consumption management platform based on improved deep learning algorithms are adopted. Through data acquisition, processing and analysis, the electricity safety threshold is set, the electricity consumption data is monitored in real time, and the electricity consumption data is carried out. Combined with the electricity consumption mode analysis, it predicts future electricity consumption needs and formulates a more efficient electricity consumption strategy.
Real-time monitoring and management of building electricity safety is realized, and future electricity needs are predicted through deep learning models, helping to formulate more efficient electricity consumption strategies and reducing safety hazards.
Smart Images
Figure CN119849962A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of building electricity safety, and specifically to a building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm. Background Art
[0002] Building, a noun, means building or mansion (shà). The word "lou" in ancient Chinese means "building located at a high place", and the word "yu" in ancient Chinese also means house or eaves. Literally speaking, building refers to a tall building. With the continuous advancement of science and technology, buildings are becoming more and more intelligent, and people pay special attention to the safety of electricity use in buildings.
[0003] At present, it is difficult for the building electricity safety and energy consumption management platform to comprehensively judge the building electricity safety situation from the micro and macro perspectives, resulting in difficulty in following up and adding safety measures for building electricity safety, affecting building electricity safety.
[0004] Therefore, in view of this, the existing structure and deficiencies are studied and improved, and a building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm is proposed. Summary of the invention
[0005] In view of the shortcomings of the prior art, the present invention provides a building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm, which solves the problems raised in the above background technology.
[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm, including a data acquisition module and a platform terminal module, the output end of the data acquisition module is provided with a processing component for collecting and processing data, and the output end of the processing component is electrically connected to the data processing module, the output end of the data processing module is electrically provided with an auxiliary component for further processing the data, the output end of the auxiliary component is electrically connected to a model selection module, and the output end of the model selection module is electrically connected to a threshold selection module, the threshold selection module The output end is electrically connected to the energy consumption management module, the platform terminal module is electrically arranged at the output end of the energy consumption management module, an output end inside the threshold selection module is electrically connected to a threshold processing component for safety monitoring, and the threshold processing component includes a safety threshold setting module, a threshold monitoring module, a threshold alarm module and an alarm counting module, the output end of the safety threshold setting module is electrically connected to the threshold monitoring module, and the output end of the threshold monitoring module is electrically connected to the threshold alarm module, the output end of the threshold alarm module is electrically connected to the alarm counting module, an output end inside the energy consumption management module is electrically connected to the useful power analysis module, and The output end of the power consumption analysis module is electrically connected to the simulation prediction module. The safety threshold setting module is used to set the power consumption safety threshold based on the prediction results of historical data and models. The upper and lower limits predicted by the model or user-defined thresholds can be used. Then the threshold monitoring module is used to monitor the power consumption data in real time to determine whether the building power consumption exceeds the set threshold range. When the real-time monitoring data exceeds the set threshold range, the threshold alarm module will sound an alarm. At the same time, the alarm counting module can be used to count the number of alarms that occur, so as to judge whether the building's periodic power consumption safety has decreased through the number of alarms, so as to further make building power safety measures and reduce safety hazards. Hidden dangers, through the power consumption analysis module in the energy consumption management module and the model analyzing the power consumption pattern of the building, it is possible to identify peak and off-peak periods, which is convenient for understanding the current power consumption of the building, so that the simulation prediction module can be used based on the prediction and analysis results of the model, and the deep learning model can predict future power needs, which is conducive to formulating more efficient power consumption strategies. For the platform terminal module, it can display power consumption data, prediction results, alarm information, etc. through front-end development and back-end management, build a back-end management system, process data input, model call, threshold detection and other functions, integrate the deep learning model with the existing building management, and realize real-time monitoring and management.
[0007] Furthermore, the processing component includes a data collection module, a data cleaning module and a data storage module, and the output end of the data collection module is electrically connected to the data cleaning module, and the output end of the data cleaning module is electrically connected to the data storage module.
[0008] Furthermore, the data collection module and the data cleaning module are connected in series, and the data cleaning module and the data storage module are connected in series.
[0009] Furthermore, the auxiliary component includes a data format conversion module and a data feature extraction module, and the output end of the data format conversion module is electrically connected to the data feature extraction module.
[0010] Furthermore, the data processing module is connected in series with the processing component, and the data processing module is connected in series with the auxiliary component.
[0011] Furthermore, an output terminal inside the model selection module is electrically connected to a model processing component for conducting building electricity safety learning, and the model processing component is connected in series with the model selection module.
[0012] Furthermore, the model processing component includes a model module and a model construction and training module, and the output end of the model module is electrically connected to the model construction and training module.
[0013] Furthermore, the model processing component also includes a model testing and verification module and a model confirmation module, and the output end of the model construction and training module is electrically connected to the model testing and verification module, and the output end of the model testing and verification module is electrically connected to the model confirmation module.
[0014] Furthermore, the output end of the platform terminal module is electrically connected to a test module, and the output end of the test module is electrically connected to a recording module.
[0015] Furthermore, the threshold selection module is connected in series with the threshold processing component, and the threshold processing component, the safety threshold setting module, the threshold monitoring module, the threshold alarm module and the alarm counting module are connected in series.
[0016] The present invention provides a building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm, which has the following beneficial effects: 1. The building electricity safety threshold and energy consumption management platform based on the improved deep learning algorithm, the safety threshold setting module is used to set the electricity safety threshold based on the historical data and model prediction results. The upper and lower limits predicted by the model or the user-defined threshold can be used. Then the threshold monitoring module is used to monitor the electricity data in real time to determine whether the building electricity consumption exceeds the set threshold range. When the real-time monitoring data exceeds the set threshold range, the threshold alarm module will sound an alarm. At the same time, the alarm counting module can be used to count the number of alarms that occur, so as to judge from a macro perspective whether the phased electricity safety of the building has decreased through the number of alarms, so as to further make building electricity safety measures and reduce safety hazards.
[0017] 2. The building electricity safety threshold and energy consumption management platform based on the improved deep learning algorithm can identify peak hours and valley hours through the electricity analysis module in the energy consumption management module and the model analysis of the building's electricity consumption pattern, so as to understand the current building electricity consumption situation. The simulation prediction module can use the prediction and analysis results based on the model, and the deep learning model can predict future electricity needs, which is conducive to formulating more efficient electricity consumption strategies. For the platform terminal module, it can display electricity consumption data, prediction results, alarm information, etc. through front-end development and back-end management, build a back-end management system, process data input, model call, threshold detection and other functions, integrate the deep learning model with the existing building management, and realize real-time monitoring and management.
[0018] 3. This building electricity safety threshold and energy consumption management platform based on the improved deep learning algorithm can use the deep learning framework to build a model through the design of model processing components, and use historical electricity consumption data for training. After the final deep learning model is selected after training, it can be reconfirmed using the model confirmation module to avoid affecting the calculation of subsequent electricity safety thresholds and improve the safety of building electricity use. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1 A schematic diagram of the system structure of a building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm of the present invention; Figure 2 A schematic diagram of the structure of a model processing component of a building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm according to the present invention; Figure 3 A schematic diagram of the structure of a threshold processing component of a building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm according to the present invention; Figure 4 A schematic diagram of the connection structure of the energy consumption management module of the building electricity safety threshold and the energy consumption management platform based on the improved deep learning algorithm of the present invention; Figure 5 This is a schematic diagram of the connection structure of the maintenance module of the building electricity safety threshold and energy consumption management platform based on the improved deep learning algorithm of the present invention.
[0020] In the figure: 1. Data acquisition module; 2. Data processing module; 3. Model selection module; 4. Threshold selection module; 5. Energy consumption management module; 6. Platform terminal module; 7. Maintenance module; 8. Processing component; 801. Receipt collection module; 802. Data cleaning module; 803. Data storage module; 9. Auxiliary component; 901. Data format conversion module; 902. Data feature extraction module; 10. Model processing component; 1001. Model module; 1002. Model construction and training module; 1003. Model testing and verification module; 1004. Model confirmation module; 11. Threshold processing component; 1101. Safety threshold setting module; 1102. Threshold monitoring module; 1103. Threshold alarm module; 1104. Alarm counting module; 12. Power consumption analysis module; 13. Simulation prediction module; 14. Test module; 15. Recording module. DETAILED DESCRIPTION
[0021] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.
[0022] like Figure 1-Figure 5As shown, the present invention provides a technical solution: a building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm, including a data acquisition module 1, a data processing module 2, a model selection module 3, a threshold selection module 4, an energy consumption management module 5, a platform terminal module 6, a maintenance module 7, a processing component 8, a receipt collection module 801, a data cleaning module 802, a data storage module 803, an auxiliary component 9, a data format conversion module 901, a data feature extraction module 902, a model processing component 10, a model module 1001, a model construction and training module 1002, a model testing and verification module 1003, a model confirmation module 1004, a threshold processing component 11, a safety threshold setting module 1101, and a threshold monitoring module 1102. Block 1102, threshold alarm module 1103, alarm counting module 1104, power consumption analysis module 12, simulation prediction module 13, test module 14 and recording module 15, the output end of the data acquisition module 1 is provided with a processing component 8 for collecting and processing data, and the output end of the processing component 8 is electrically connected to the data processing module 2, the output end of the data processing module 2 is electrically provided with an auxiliary component 9 for further processing the data, the output end of the auxiliary component 9 is electrically connected to the model selection module 3, and the output end of the model selection module 3 is electrically connected to the threshold selection module 4, the threshold selection module 4 is connected in series with the threshold processing component 11, the threshold processing component 11, the safety threshold setting module 1101, the threshold monitoring module 11 02, the threshold alarm module 1103 and the alarm counting module 1104 are connected in series, an output end inside the model selection module 3 is electrically connected to a model processing component 10 for building electricity safety learning, and the model processing component 10 is connected in series with the model selection module 3, including the model processing component 10 including a model module 1001 and a model construction and training module 1002, and the output end of the model module 1001 is electrically connected to the model construction and training module 1002, the model processing component 10 also includes a model testing and verification module 1003 and a model confirmation module 1004, and the output end of the model construction and training module 1002 is electrically connected to the model testing and verification module 1003, and the output of the model testing and verification module 1003 The end is electrically connected to a model confirmation module 1004. The model module 1001 is used to select a deep learning model suitable for time series analysis. The deep learning model includes a recurrent neural network for capturing the time series pattern of electricity consumption, a convolutional neural network for extracting local features, a hybrid model for improving the performance of the model, and an autoencoder for anomaly detection. If there is abnormal electricity consumption, the deep learning framework can be used to build a model and trained using historical electricity consumption data. After the training, the final deep learning model can be selected and reconfirmed using the model confirmation module 1004 to avoid affecting the calculation of the subsequent electricity safety threshold and improve the building electricity safety effect. The output end of the threshold selection module 4 is electrically connected to an energy consumption management module 5.The platform terminal module 6 is electrically arranged at the output end of the energy consumption management module 5, the output end of the platform terminal module 6 is electrically connected to the test module 14, and the output end of the test module 14 is electrically connected to the recording module 15, an output end inside the threshold selection module 4 is electrically connected to the threshold processing component 11 for safety monitoring, and the threshold processing component 11 includes a safety threshold setting module 1101, a threshold monitoring module 1102, a threshold alarm module 1103 and an alarm counting module 1104, and the output end of the safety threshold setting module 1101 is electrically connected to The threshold monitoring module 1102 is provided, and the output end of the threshold monitoring module 1102 is electrically connected to the threshold alarm module 1103, and the output end of the threshold alarm module 1103 is electrically connected to the alarm counting module 1104. An output end inside the energy consumption management module 5 is electrically connected to the power analysis module 12, and the output end of the power analysis module 12 is electrically connected to the simulation prediction module 13. The safety threshold setting module 1101 is used to set the power safety threshold based on the prediction results of the historical data and the model, and the upper and lower limits predicted by the model or the user-defined threshold can be used. The post-threshold monitoring module 1102 is used to monitor the power consumption data in real time and determine whether the power consumption of the building exceeds the set threshold range. When the real-time monitoring data exceeds the set threshold range, the threshold alarm module 1103 will sound a buzzer alarm. At the same time, the alarm counting module 1104 can be used to count the number of alarms that occur, so as to judge whether the phased power safety of the building has decreased from a macro perspective through the number of alarms, so as to further make building power safety measures and reduce safety hazards. Through the power consumption analysis module 12 in the energy consumption management module 5 and the power consumption pattern of the building through the model, it is possible to identify peak hours and valley hours, so as to understand the current power consumption of the building, so as to use the simulation prediction module 13 based on the prediction and analysis results of the model, and the deep learning model to predict future power needs, which is conducive to formulating a more efficient power consumption strategy. For the platform terminal module 6, it can display power consumption data, prediction results, alarm information, etc. through front-end development and back-end management, build a back-end management system, process data input, model call, threshold detection and other functions, integrate the deep learning model with the existing building management, and realize real-time monitoring and management.
[0023] like Figure 1As shown, the processing component 8 includes a data collection module 801, a data cleaning module 802 and a data storage module 803, and the output end of the data collection module 801 is electrically connected to the data cleaning module 802, and the output end of the data cleaning module 802 is electrically connected to the data storage module 803, the data collection module 801 and the data cleaning module 802 are connected in series, and the data cleaning module 802 and the data storage module 803 are connected in series, the data collection module 801 is used to collect the electricity consumption data of the building, including historical electricity consumption, electricity consumption fluctuations, equipment status, environmental data such as temperature and humidity, etc., the data cleaning module 802 is used to clean the collected data, remove abnormal values and missing values, mark safe / unsafe electricity consumption behaviors, etc., and then the data storage module 803 is used to store the data after the above processing to avoid the loss of the data after collection and processing.
[0024] like Figure 1 As shown, the auxiliary component 9 includes a data format conversion module 901 and a data feature extraction module 902, and the output end of the data format conversion module 901 is electrically connected to the data feature extraction module 902, the data processing module 2 is connected in series with the processing component 8, and the data processing module 2 is connected in series with the auxiliary component 9, and the data format conversion module 901 can convert the original data into a format suitable for deep learning model input, such as time series data, and the data feature extraction module 902 can extract key features, such as power consumption fluctuation amplitude, power factor, equipment usage time, etc., or automatically extract features through a deep learning model.
[0025] In summary, if Figure 1-Figure 5As shown, the building electricity safety threshold and energy consumption management platform based on the improved deep learning algorithm, when in use, the data collection module 801 is used to collect the building's electricity consumption data, including historical electricity consumption, electricity consumption fluctuations, equipment status, environmental data such as temperature and humidity, etc., the data cleaning module 802 is used to clean the collected data, remove abnormal values, missing values, mark safe / unsafe electricity consumption behaviors, etc., and then the data storage module 803 is used to store the data after the above processing to avoid the loss of data after collection and processing, and then the data format conversion module 901 can convert the original data into a format suitable for deep learning model input, such as time series data, and the key features can be extracted through the data feature extraction module 902, Such as power consumption fluctuation amplitude, power factor, equipment usage time, etc., or automatically extract features through deep learning models, then model module 1001 is used to select a deep learning model suitable for time series analysis. The deep learning model includes a recurrent neural network for capturing the time series pattern of power consumption, a convolutional neural network for extracting local features, a hybrid model to improve the performance of the model, and an autoencoder for anomaly detection. If there is abnormal power consumption, then a deep learning framework can be used to build a model and trained using historical power consumption data. After training, the final deep learning model can be selected and reconfirmed using the model confirmation module 1004 to avoid affecting the calculation of subsequent power safety thresholds and improve the power safety effect of the building. The post-safety threshold setting module 1101 is used to set the power safety threshold based on the historical data and the prediction results of the model. The upper and lower limits predicted by the model or the user-defined threshold can be used. Then the threshold monitoring module 1102 is used to monitor the power consumption data in real time to determine whether the building power consumption exceeds the set threshold range. When the real-time monitoring data exceeds the set threshold range, the threshold alarm module 1103 will sound an alarm. At the same time, the alarm counting module 1104 can be used to count the number of alarms that occur, so as to judge from a macro perspective whether the phased power safety of the building has decreased through the number of alarms, so as to further make building power safety measures and reduce safety hazards. Through the power analysis module 12 in the energy consumption management module 5, and through the model analysis of the power consumption model of the building The model can identify peak hours and off-peak hours, which is convenient for understanding the current building electricity consumption. Therefore, the simulation prediction module 13 can be used to predict and analyze the results of the model based on the deep learning model to predict future electricity needs, which is conducive to formulating more efficient electricity consumption strategies. The platform terminal module 6 can display electricity consumption data, prediction results, alarm information, etc. through front-end development and back-end management, build a back-end management system, process data input, model call, threshold detection and other functions, integrate the deep learning model with the existing building management, and realize real-time monitoring and management. Finally, the maintenance module 7 regularly inspects and maintains the building power system, and can use the test module 14 to regularly test and detect the building system to determine the operation of the building system.In addition, the test quantity of the test module 14 is recorded through the design of the recording module 15 to avoid the occurrence of periodic test omissions.
[0026] The embodiments of the present invention are given for the purpose of illustration and description, and are not intended to be exhaustive or to limit the invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.
Claims
1. A building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm, comprising a data acquisition module (1) and a platform terminal module (6), characterized in that: The output end of the data acquisition module (1) is provided with a processing component (8) for collecting and processing data, and the output end of the processing component (8) is electrically connected to the data processing module (2), the output end of the data processing module (2) is electrically provided with an auxiliary component (9) for further processing the data, the output end of the auxiliary component (9) is electrically connected to the model selection module (3), and the output end of the model selection module (3) is electrically connected to the threshold selection module (4), the output end of the threshold selection module (4) is electrically connected to the energy consumption management module (5), the platform terminal module (6) is electrically provided at the output end of the energy consumption management module (5), and the threshold selection module (4) is internally connected to the energy consumption management module (5). The output end is electrically connected to a threshold processing component (11) for safety monitoring, and the threshold processing component (11) includes a safety threshold setting module (1101), a threshold monitoring module (1102), a threshold alarm module (1103) and an alarm counting module (1104), the output end of the safety threshold setting module (1101) is electrically connected to the threshold monitoring module (1102), and the output end of the threshold monitoring module (1102) is electrically connected to the threshold alarm module (1103), the output end of the threshold alarm module (1103) is electrically connected to the alarm counting module (1104), an output end inside the energy consumption management module (5) is electrically connected to the useful power analysis module (12), and The output end of the power consumption analysis module (12) is electrically connected to the simulation prediction module (13). The safety threshold setting module (1101) is used to set the power consumption safety threshold based on the historical data and the prediction results of the model. The upper and lower limits predicted by the model or the user-defined threshold can be used. Then, the threshold monitoring module (1102) is used to monitor the power consumption data in real time to determine whether the building power consumption exceeds the set threshold range. When the real-time monitoring data exceeds the set threshold range, the threshold alarm module (1103) will sound a buzzer alarm. At the same time, the alarm counting module (1104) can be used to count the number of alarms that occur, so as to judge from a macro perspective whether the building's periodic power consumption safety has decreased through the number of alarms, so as to further make building Electricity safety measures can reduce potential safety hazards. Through the electricity analysis module (12) in the energy consumption management module (5), the building's electricity consumption pattern can be analyzed through the model, and peak and off-peak periods can be identified, which is convenient for understanding the current building electricity consumption situation. Therefore, the simulation prediction module (13) can be used based on the prediction and analysis results of the model. The deep learning model predicts future electricity needs, which is conducive to formulating more efficient electricity strategies. For the platform terminal module (6), it can display electricity consumption data, prediction results, alarm information, etc. through front-end development and back-end management, build a back-end management system, process data input, model call, threshold detection and other functions, integrate the deep learning model with the existing building management, and realize real-time monitoring and management.
2. According to claim 1, a building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm is characterized by: The processing component (8) comprises a data collection module (801), a data cleaning module (802) and a data storage module (803), wherein the output end of the data collection module (801) is electrically connected to the data cleaning module (802), and the output end of the data cleaning module (802) is electrically connected to the data storage module (803).
3. A building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm according to claim 2, characterized in that: The receipt collection module (801) and the data cleaning module (802) are connected in series, and the data cleaning module (802) and the data storage module (803) are connected in series.
4. According to claim 1, a building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm is characterized by: The auxiliary component (9) comprises a data format conversion module (901) and a data feature extraction module (902), and the output end of the data format conversion module (901) is electrically connected to the data feature extraction module (902).
5. According to claim 1, a building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm is characterized in that: The data processing module (2) is connected in series with the processing component (8), and the data processing module (2) is connected in series with the auxiliary component (9).
6. The building electricity safety threshold and energy consumption management platform based on the improved deep learning algorithm according to claim 1 is characterized by: An output terminal inside the model selection module (3) is electrically connected to a model processing component (10) for conducting building electricity safety learning, and the model processing component (10) is connected in series with the model selection module (3).
7. A building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm according to claim 6, characterized in that: The model processing component (10) comprises a model module (1001) and a model building and training module (1002), and the output end of the model module (1001) is electrically connected to the model building and training module (1002).
8. A building electricity safety threshold and energy consumption management platform based on an improved deep learning algorithm according to claim 7, characterized in that: The model processing component (10) further comprises a model testing and verification module (1003) and a model confirmation module (1004), and the output end of the model building and training module (1002) is electrically connected to the model testing and verification module (1003), and the output end of the model testing and verification module (1003) is electrically connected to the model confirmation module (1004).
9. The building electricity safety threshold and energy consumption management platform based on the improved deep learning algorithm according to claim 1 is characterized by: The output end of the platform terminal module (6) is electrically connected to a test module (14), and the output end of the test module (14) is electrically connected to a recording module (15).
10. The building electricity safety threshold and energy consumption management platform based on the improved deep learning algorithm according to claim 1, characterized in that: The threshold selection module (4) is connected in series with the threshold processing component (11), and the threshold processing component (11), the safety threshold setting module (1101), the threshold monitoring module (1102), the threshold alarm module (1103) and the alarm counting module (1104) are connected in series.