Intelligent factory energy management system based on big data

Abstract

The invention discloses an intelligent factory energy management system based on big data. According to the invention, the real-time data analysis module carries out real-time monitoring and analysis by collecting energy data in a factory in real time and utilizing a big data processing technology. Due to the real-time performance, the system can quickly find abnormal conditions in energy use, such as sudden energy consumption peaks or abnormal low ebbs, so that measures can be taken in time for adjustment. Therefore, energy waste can be avoided, and the stability and safety of the production process can be ensured. In addition, real-time data analysis can also provide an instant energy use report for a factory management layer, support rapid decision making and optimize energy configuration. Meanwhile, the historical data analysis module is responsible for storing and analyzing energy data in a past period of time, the long-term trend and periodic change of energy use are revealed through the data mining and statistical analysis technology, key links and potential problems of energy consumption can be recognized, and therefore the purposes of saving energy and reducing consumption for a long time are achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of factory energy management, and specifically relates to an intelligent factory energy management system based on big data. Background Art

[0002] With the rapid development of industrialization, the demand for energy in factories is increasing day by day, and energy management has become a key factor affecting factory operation costs and efficiency. Traditional energy management methods often rely on manual monitoring and empirical judgment, lacking real-time performance and accuracy, resulting in energy waste and low efficiency. Factory energy management refers to a series of activities for effectively planning, organizing, controlling, and supervising various energies (such as water, electricity, gas, heat, etc.) required in the production process of an enterprise. Its purpose is to improve energy utilization efficiency, reduce energy consumption, reduce production costs, and achieve green and sustainable development. Factory energy management mainly includes aspects such as energy metering, energy monitoring, energy auditing, energy-saving transformation, and energy informatization construction. By adopting advanced technical means and management methods, energy is reasonably allocated and optimally used, thereby improving energy utilization rate, reducing energy waste, ensuring stable production, and promoting the dual improvement of the economic and environmental benefits of the enterprise.

[0003] However, existing intelligent energy management systems still have many deficiencies in real-time data analysis, historical data analysis, and energy consumption demand prediction. First of all, the real-time data analysis module often lacks efficient data processing capabilities and cannot quickly respond to abnormal situations in energy use, resulting in energy waste and unstable production. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent factory energy management system based on big data in order to solve the above-mentioned problems.

[0005] The technical solution adopted by the present invention is as follows: An intelligent factory energy management system based on big data, the system includes: a data acquisition module, a data management module, a data analysis and processing module, an energy monitoring visualization module, an energy decision support module, a system integration and interaction module, and a security and maintenance module;

[0006] A real-time data analysis module, a historical data analysis module, and an energy consumption demand prediction module are arranged inside the data analysis and processing module;

[0007] The output end of the data acquisition module is connected to the input end of the data storage and management module.

[0008] The output end of the data storage and management module is connected to the input end of the data analysis and processing module.

[0009] The output end of the data analysis and processing module is connected to the input end of the energy monitoring and visualization module.

[0010] The output end of the data analysis and processing module is simultaneously connected to the input end of the energy optimization and decision support module.

[0011] The output end of the energy optimization and decision support module is connected to the input end of the system integration and interaction module.

[0012] The output end of the system integration and interaction module is connected to the input ends of the data acquisition module, the data storage and management module, the data analysis and processing module, and the energy monitoring and visualization module.

[0013] The output end of the security and maintenance module is connected to the input ends of the data acquisition module, the data storage and management module, the data analysis and processing module, the energy monitoring and visualization module, the energy optimization and decision support module, and the system integration and interaction module.

[0014] In a preferred embodiment, the data acquisition module internally includes: a sensor network, a data acquisition terminal, a data transmission unit, and a data preprocessing unit. The sensor network is composed of various types of sensors, including electric energy sensors, water flow sensors, gas flow sensors, and temperature sensors.

[0015] In a preferred embodiment, the internal settings of the data management module include a data storage unit, a data cleaning unit, a data integration unit, and a data mining unit.

[0016] In a preferred embodiment, the calculation formula for the moving window average value of the real-time data analysis module is:

[0017]

[0018] If then it is determined that the energy consumption data at time t is abnormal;

[0019] where W represents the size of the moving window, which is set according to actual needs. For example, it can be set as the number of data points within 10 minutes.

[0020] x_t represents the real-time energy consumption data at time t, which can be power consumption, water consumption, etc.

[0021] xˉt represents the average value within the moving window at time t, reflecting the overall level of recent energy consumption.

[0022] θ represents a preset abnormal threshold, which is set according to historical data and analysis experience and is used to determine whether the energy consumption data deviates from the normal range;

[0023] The algorithm implementation steps include:

[0024] ①. Initialize the moving window, and set the window size W and the abnormal threshold θ.

[0025] ②. Receive real-time energy consumption data \(x_t\).

[0026] ③. Add the new data to the sliding window, remove the oldest data in the window, and keep the window size unchanged.

[0027] ④. Calculate the average value \(\bar{x}_t\) of the data in the window.

[0028] ⑤. Determine whether the difference between the current data \(x_t\) and the average value \(\bar{x}_t\) exceeds the threshold \(\theta\).

[0029] ⑥. If it exceeds the threshold, issue an exception alarm and perform subsequent processing (such as recording the exception, analyzing the cause, etc.).

[0030] ⑦. Repeat steps 2 - 6 to continuously monitor the real-time energy consumption data.

[0031] In a preferred embodiment, the basic model of seasonal decomposition of the historical data analysis module is:

[0032] \(Y_t = T_t + S_t + I_t\);

[0033] Where: \(Y_t\) represents the historical energy consumption data at time \(t\).

[0034] \(T_t\) represents the trend component at time \(t\), reflecting the long-term change trend of energy consumption.

[0035] \(S_t\) represents the seasonal component at time \(t\), reflecting the seasonal fluctuation law of energy consumption.

[0036] \(I_t\) represents the residual component at time \(t\), reflecting the random fluctuation after removing the trend and seasonality.

[0037] In a preferred embodiment, the simple linear regression model of the energy consumption demand prediction module is:

[0038] \(Y = a + bX+\);

[0039] Where: \(Y\) represents the predicted value of future energy consumption demand.

[0040] \(X\) represents the independent variable affecting energy consumption demand.

[0041] \(a\) represents the intercept of the regression equation.

[0042] \(b\) represents the slope of the regression equation, indicating the degree of influence of the independent variable on the dependent variable.

[0043] represents the error term, indicating the random fluctuation that the model fails to explain.

[0044] In a preferred embodiment, a data interface unit, a real-time monitoring unit, a visualization display unit, and an alarm notification unit are provided inside the energy monitoring visualization module.

[0045] In a preferred embodiment, a data analysis unit, a model establishment unit, a decision generation unit, and a report output unit are provided inside the energy decision support module. The data analysis unit deeply analyzes historical and real-time energy consumption data to discover the patterns and trends of energy use. The model establishment unit, based on the analysis results, establishes energy consumption prediction models, optimization models, etc., to provide a scientific basis for decision-making. The decision generation unit generates specific energy management decision suggestions, such as equipment scheduling, energy procurement, and production plan adjustment, according to the model output and user requirements. The report output unit outputs the decision results and analysis reports in the form of documents or presentation materials for management reference and decision-making. For example, in a textile factory, the energy decision support module can analyze historical energy consumption data, establish a prediction model, predict the electricity demand for the next week, and generate corresponding energy procurement suggestions and equipment scheduling plans.

[0046] In a preferred embodiment, the internal settings of the system integration and interaction module include an interface adaptation unit, a data exchange unit, a system coordination unit, and a user interaction unit. The interface adaptation unit is responsible for docking with other systems in the factory (such as the production management system, equipment maintenance system, etc.) to ensure the compatibility of data formats and communication protocols. The data exchange unit realizes data exchange and sharing with other systems, breaking information silos. The system coordination unit coordinates the collaborative work of different systems to ensure the efficiency and consistency of the overall operation. The user interaction unit provides a user interface and interaction functions, enabling users to conveniently access system functions and obtain the required information. For example, in an automated logistics center, the system integration and interaction module can dock with the warehouse management system, transportation management system, etc., to realize the exchange and sharing of energy consumption data and logistics operation data, providing support for energy management and optimization in the logistics center.

[0047] In a preferred embodiment, the safety and maintenance module includes a data security unit, a system monitoring unit, a fault diagnosis unit, and a maintenance management unit. The data security unit is responsible for ensuring the security and integrity of system data, and preventing data leakage and unauthorized access through means such as encryption technology, access control, and security auditing. The system monitoring unit monitors the system operation status in real time and processes abnormal situations in a timely manner. The fault diagnosis unit diagnoses and analyzes system faults to determine the cause of the faults and the scope of influence. The maintenance management unit is responsible for the daily maintenance and upgrade of the system to ensure the stable operation and continuous improvement of the system. For example, in a chemical plant, the safety and maintenance module can monitor the operation status of the energy management system in real time. Once data anomalies or system faults are detected, the fault diagnosis program is immediately started, and maintenance personnel are notified for processing to ensure the stable operation and data security of the energy management system.

[0048] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are as follows:

[0049] 1. In the present invention, the real-time data analysis module collects energy data in the factory in real time, such as the consumption of electricity, water, gas, etc., and uses big data processing technology for real-time monitoring and analysis. This real-time nature enables the system to quickly detect abnormal situations in energy use, such as sudden energy consumption peaks or abnormal troughs, and thus take timely measures for adjustment. This not only helps to avoid energy waste but also ensures the stability and safety of the production process. In addition, real-time data analysis can also provide immediate energy use reports for the factory management, supporting rapid decision-making and optimizing energy allocation.

[0050] 2. In the present invention, the historical data analysis module is responsible for storing and analyzing energy data over a past period of time. Through data mining and statistical analysis techniques, it reveals the long-term trends and periodic changes in energy use. These in-depth analysis results provide valuable insights into energy use for the factory, helping to identify key links and potential problems in energy consumption. Based on these analyses, the factory can formulate more effective energy management strategies, such as adjusting production plans, optimizing equipment operation modes, etc., so as to achieve the goal of long-term energy conservation and consumption reduction. At the same time, historical data is also an important basis for energy consumption demand prediction.

[0051] 3. In the present invention, the energy consumption demand prediction module uses historical data and advanced prediction algorithms, such as time series analysis, machine learning, etc., to predict the energy demand in a future period. Accurate energy consumption demand prediction enables the factory to make an energy supply plan in advance, avoiding production interruptions or cost increases caused by insufficient or excessive energy supply. In addition, the prediction results can also be used to guide energy procurement and storage strategies, reducing energy costs. Through the comparative analysis of the prediction and the actual energy consumption, the factory can continuously optimize the prediction model, improve the prediction accuracy, and further enhance the intelligent level of energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is the overall system block diagram of the present invention;

[0053] Figure 2 is the system block diagram of the data analysis and processing module in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] Refer to Figure 1 ,

[0056] The intelligent factory energy management system based on big data, the system includes: a data acquisition module, a data management module, a data analysis and processing module, an energy monitoring and visualization module, an energy decision support module, a system integration and interaction module, and a security and maintenance module;

[0057] Inside the data analysis and processing module, there are a real-time data analysis module, a historical data analysis module, and an energy consumption demand prediction module;

[0058] The output end of the data acquisition module is connected to the input end of the data storage and management module, and is responsible for transmitting the collected real-time energy data to the big data platform for storage and management.

[0059] The output end of the data storage and management module is connected to the input end of the data analysis and processing module, providing the stored energy data for analysis and processing.

[0060] The output end of the data analysis and processing module is connected to the input end of the energy monitoring and visualization module, and displays the analyzed data in a visual form.

[0061] The output end of the data analysis and processing module is simultaneously connected to the input end of the energy optimization and decision support module, providing data support for formulating energy optimization strategies and decisions.

[0062] The output end of the energy optimization and decision support module is connected to the input end of the system integration and interaction module, and integrates the optimization strategy and decision-making results with other factory systems through the API interface to achieve data interaction and sharing.

[0063] The output end of the system integration and interaction module is connected to the input ends of the data acquisition module, data storage and management module, data analysis and processing module, and energy monitoring and visualization module to achieve data exchange and feedback with other systems.

[0064] The security and maintenance module provides support for data security and stable operation of all modules. The output end of the security and maintenance module is connected to the input ends of the data acquisition module, data storage and management module, data analysis and processing module, energy monitoring and visualization module, energy optimization and decision support module, and system integration and interaction module.

[0065] The data acquisition module is internally equipped with a sensor network, a data acquisition terminal, a data transmission unit, and a data preprocessing unit. The sensor network consists of various types of sensors, such as power sensors, water flow sensors, gas flow sensors, and temperature sensors, etc. They are distributed at various key points in the factory and are responsible for real-time monitoring and collecting energy consumption-related data. The data acquisition terminal is responsible for receiving the data transmitted by the sensor network and performing preliminary sorting and formatting. The data transmission unit then transmits the sorted data to the central database through a wired or wireless network. The data preprocessing unit performs preliminary cleaning and screening on the transmitted data, removing obvious outliers and noise to ensure the accuracy of subsequent data processing and analysis. For example, in a food processing factory, the sensor network of the data acquisition module can real-time monitor the power consumption and temperature changes of refrigeration equipment. After the data acquisition terminal receives these data, it sends them to the central database through the data transmission unit, and the data preprocessing unit then performs preliminary cleaning on the data to provide high-quality data sources for subsequent modules.

[0066] The internal settings of the data management module include a data storage unit, a data cleaning unit, a data integration unit, and a data mining unit. The data storage unit adopts efficient data warehouse technology to be responsible for the storage and management of large-scale data, ensuring data security and accessibility. The data cleaning unit cleans the stored data through a series of algorithms and rules, removing duplicate, incorrect, and missing data to improve data quality. The data integration unit unifies and integrates data from different sources and formats to form a standardized data set for easy analysis and processing. The data mining unit uses advanced data mining techniques, such as association rule mining, clustering analysis, and predictive modeling, to extract valuable information and knowledge from large amounts of data. For example, in a pharmaceutical factory, the data management module can store and manage the energy consumption data over the years. Through data cleaning and integration, a unified data set is formed, and then data mining techniques are used to analyze the correlation between energy consumption and factors such as production batches and equipment usage time.

[0067] The real-time data analysis module uses the sliding window technique to continuously monitor the real-time energy consumption data. By calculating the average value of the data within the window and comparing it with a preset threshold, it detects whether there is abnormal energy consumption.

[0068] Let W be the size of the sliding window, that is, the number of data points contained within the window; x_t be the energy consumption data at time t; xˉt be the average value within the window at time t; θ be the preset abnormal threshold.

[0069] The calculation formula for the average value of the sliding window is:

[0070]

[0071] If then it is determined that the energy consumption data at time t is abnormal.

[0072] Among them, W represents the size of the sliding window, which is set according to actual needs. For example, it can be set to the number of data points within 10 minutes.

[0073] x_t represents the real-time energy consumption data at time t, which can be power consumption, water consumption, etc.

[0074] xˉt represents the average value within the sliding window at time t, reflecting the overall level of recent energy consumption.

[0075] θ represents the preset abnormal threshold, which is set according to historical data and analysis experience and is used to determine whether the energy consumption data deviates from the normal range.

[0076] The algorithm implementation steps include:

[0077] ①. Initialize the sliding window, set the window size W and the abnormal threshold θ.

[0078] ②. Receive real-time energy consumption data \(x_t\).

[0079] ③. Add the new data to the sliding window, remove the oldest data in the window, and keep the window size unchanged.

[0080] ④. Calculate the average value \(\bar{x}_t\) of the data in the window.

[0081] ⑤. Determine whether the difference between the current data \(x_t\) and the average value \(\bar{x}_t\) exceeds the threshold \(\theta\).

[0082] ⑥. If it exceeds the threshold, issue an exception alarm and perform subsequent processing (such as recording the exception, analyzing the cause, etc.).

[0083] ⑦. Repeat steps 2 - 6 to continuously monitor real-time energy consumption data.

[0084] The historical data analysis module uses the seasonal decomposition algorithm to analyze the seasonal component, trend component, and residual component in time series data. It is used to mine the seasonal patterns and long-term trends in historical energy consumption data;

[0085] Let \(Y_t\) be the energy consumption data at time \(t\), \(T_t\) be the trend component, \(S_t\) be the seasonal component, and \(I_t\) be the residual component (i.e., random fluctuations).

[0086] The basic model of seasonal decomposition is:

[0087] \(Y_t = T_t + S_t + I_t\);

[0088] Where: \(Y_t\) represents the historical energy consumption data at time \(t\).

[0089] \(T_t\) represents the trend component at time \(t\), reflecting the long-term change trend of energy consumption.

[0090] \(S_t\) represents the seasonal component at time \(t\), reflecting the seasonal fluctuation pattern of energy consumption.

[0091] \(I_t\) represents the residual component at time \(t\), reflecting the random fluctuations after removing the trend and seasonality.

[0092] The trend component \(T_t\) can be estimated by methods such as moving average method or linear regression. The seasonal component \(S_t\) can be estimated by calculating the average value of historical data in the same season. The residual component \(I_t\) is the remaining part after removing the trend and seasonality, reflecting random fluctuations;

[0093] The energy consumption demand prediction module uses the regression analysis algorithm. Let \(Y\) be the future energy consumption demand, \(X\) be the independent variable affecting the energy consumption demand, and \(a\) and \(b\) be the regression coefficients;

[0094] The simple linear regression model is:

[0095] Y = a + bX +

[0096] Where: Y represents the predicted value of future energy consumption demand.

[0097] X represents the independent variable that affects energy consumption demand.

[0098] a represents the intercept of the regression equation.

[0099] b represents the slope of the regression equation, indicating the degree of influence of the independent variable on the dependent variable.

[0100] represents the error term, indicating the random fluctuations that the model fails to explain;

[0101] The algorithm implementation steps are as follows:

[0102] Data preparation: Collect historical energy consumption data and related independent variable data (such as temperature, production volume, etc.).

[0103] Feature selection: Screen out the features that have a significant impact on energy consumption demand from the collected data as independent variables.

[0104] Model training: Use historical data to train a simple linear regression model to estimate the regression coefficients a and b. The commonly used estimation method is the least squares method, which estimates the coefficients by minimizing the sum of the squares of the errors between the predicted values and the actual values.

[0105] Model validation: Evaluate the performance of the trained model through cross-validation or other methods, such as using metrics like the coefficient of determination (R-squared), mean squared error (MSE), etc.

[0106] Predict future energy consumption demand: Substitute the values of future independent variable X into the trained regression model to predict future energy consumption demand Y.

[0107] Result analysis and application: Analyze the prediction results to provide decision-making support for energy management and optimization in intelligent factories

[0108] The internal settings of the energy monitoring visualization module include a data interface unit, a real-time monitoring unit, a visualization display unit, and an alarm notification unit. The data interface unit is responsible for docking with the data management module to obtain the latest energy consumption data in real time. The real-time monitoring unit conducts real-time analysis and monitoring of the obtained data and processes abnormal situations in a timely manner. The visualization display unit intuitively displays the energy consumption data to users in various forms such as charts, dashboards, and 3D models, facilitating users to quickly understand the energy usage situation. The alarm notification unit, when detecting abnormal energy consumption, promptly notifies relevant personnel by means of sound, text message, or email. For example, in a steel smelting plant, the energy monitoring visualization module can display the gas consumption and temperature changes of the blast furnace in real time. Once abnormal consumption is detected, an alarm notification is immediately issued so that the staff can take measures in a timely manner.

[0109] The internal settings of the energy decision support module include a data analysis unit, a model building unit, a decision generation unit, and a report output unit. The data analysis unit deeply analyzes historical and real-time energy consumption data to discover the patterns and trends of energy use. The model building unit, based on the analysis results, builds energy consumption prediction models, optimization models, etc., providing a scientific basis for decision-making. The decision generation unit generates specific energy management decision suggestions according to the model output and user requirements, such as equipment scheduling, energy procurement, and production plan adjustment. The report output unit outputs the decision results and analysis reports in the form of documents or presentation materials for management reference and decision-making. For example, in a textile factory, the energy decision support module can analyze historical energy consumption data, build a prediction model, predict the electricity demand for the next week, and generate corresponding energy procurement suggestions and equipment scheduling plans.

[0110] The internal settings of the system integration and interaction module include an interface adaptation unit, a data exchange unit, a system coordination unit, and a user interaction unit. The interface adaptation unit is responsible for docking with other systems within the factory (such as the production management system, equipment maintenance system, etc.) to ensure the compatibility of data formats and communication protocols. The data exchange unit realizes data exchange and sharing with other systems, breaking information silos. The system coordination unit coordinates the collaborative work of different systems to ensure the efficiency and consistency of the overall operation. The user interaction unit provides a user interface and interaction functions, enabling users to conveniently access system functions and obtain the required information. For example, in an automated logistics center, the system integration and interaction module can dock with the warehouse management system, transportation management system, etc. to realize the exchange and sharing of energy consumption data and logistics operation data, providing support for the energy management and optimization of the logistics center.

[0111] The internal settings of the security and maintenance module include a data security unit, a system monitoring unit, a fault diagnosis unit, and a maintenance management unit. The data security unit is responsible for ensuring the security and integrity of system data, preventing data leakage and illegal access through means such as encryption technology, access control, and security auditing. The system monitoring unit monitors the system operation status in real time and processes abnormal situations in a timely manner. The fault diagnosis unit diagnoses and analyzes system faults to determine the cause and scope of influence of the faults. The maintenance management unit is responsible for the daily maintenance and upgrade work of the system to ensure the stable operation and continuous improvement of the system. For example, in a chemical factory, the security and maintenance module can monitor the operation status of the energy management system in real time. Once data anomalies or system faults are detected, it immediately starts the fault diagnosis program and notifies the maintenance personnel for handling to ensure the stable operation and data security of the energy management system.

[0112] In the present invention, the real-time data analysis module collects the energy data in the factory in real time, such as the consumption of electricity, water, gas, etc., and uses big data processing technology for real-time monitoring and analysis. This real-time nature enables the system to quickly detect abnormal situations in energy use, such as sudden energy consumption peaks or abnormal troughs, and thus take timely measures for adjustment. This not only helps to avoid energy waste, but also ensures the stability and safety of the production process. In addition, real-time data analysis can also provide immediate energy use reports for the factory management, support quick decision-making, and optimize energy allocation.

[0113] In the present invention, the historical data analysis module is responsible for storing and analyzing the energy data over a past period of time. Through data mining and statistical analysis techniques, it reveals the long-term trends and periodic changes in energy use. These in-depth analysis results provide valuable insights into energy use for the factory, helping to identify the key links and potential problems in energy consumption. Based on these analyses, the factory can formulate more effective energy management strategies, such as adjusting production plans, optimizing equipment operation modes, etc., so as to achieve the goal of long-term energy conservation and consumption reduction. At the same time, historical data is also an important basis for energy consumption demand forecasting.

[0114] In the present invention, the energy consumption demand forecasting module uses historical data and advanced forecasting algorithms, such as time series analysis, machine learning, etc., to forecast the energy demand over a future period of time. Accurate energy consumption demand forecasting enables the factory to make energy supply plans in advance, avoiding production interruptions or cost increases caused by insufficient or excessive energy supply. In addition, the forecasting results can also be used to guide energy procurement and storage strategies, reducing energy costs. Through the comparative analysis of the forecast and the actual energy consumption, the factory can continuously optimize the forecasting model, improve the forecasting accuracy, and further strengthen the intelligent level of energy management. Generally speaking, these three modules cooperate with each other and jointly constitute an efficient and intelligent energy management system, bringing significant energy-saving benefits and economic benefits to the factory.

[0115] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0116] 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 foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. Intelligent factory energy management system based on big data, characterized by: The system includes: a data acquisition module, a data management module, a data analysis and processing module, an energy monitoring visualization module, an energy decision support module, a system integration and interaction module, and a safety and maintenance module; The data analysis and processing module is internally provided with a real-time data analysis module, a historical data analysis module and an energy consumption demand prediction module; The output end of the data acquisition module is connected to the input end of the data storage and management module; The output end of the data storage and management module is connected to the input end of the data analysis and processing module; The output end of the data analysis and processing module is connected to the input end of the energy monitoring and visualization module; The output end of the data analysis and processing module is simultaneously connected to the input end of the energy optimization and decision support module; The output end of the energy optimization and decision support module is connected to the input end of the system integration and interaction module; The output end of the system integration and interaction module is connected to the input end of the data acquisition module, the data storage and management module, the data analysis and processing module and the energy monitoring and visualization module; The output end of the safety and maintenance module is connected to the input end of the data acquisition module, the data storage and management module, the data analysis and processing module, the energy monitoring and visualization module, the energy optimization and decision support module and the system integration and interaction module.

2. The smart factory energy management system based on big data as claimed in claim 1, characterized in that: The data acquisition module is internally provided with: a sensor network, a data acquisition terminal, a data transmission unit and a data preprocessing unit; the sensor network is composed of various types of sensors, including an electric energy sensor, a water flow sensor, a gas flow sensor and a temperature sensor.

3. The smart factory energy management system based on big data as claimed in claim 1, characterized in that: The internal configuration of the data management module includes a data storage unit, a data cleaning unit, a data integration unit and a data mining unit.

4. The smart factory energy management system based on big data as claimed in claim 1, characterized in that: The calculation formula of the sliding window average value of the real-time data analysis module is: if Then the energy consumption data at time t is judged to be abnormal; Where W represents the size of the sliding window, which can be set according to actual needs. For example, it can be set to the number of data points within 10 minutes. x_t represents the real-time energy consumption data at time t, which can be electricity consumption or water consumption; xˉt represents the average value in the sliding window at time t, reflecting the overall level of recent energy consumption; θ represents the preset abnormal threshold, which is set according to historical data and analysis experience and is used to determine whether the energy consumption data deviates from the normal range.

5. The smart factory energy management system based on big data as claimed in claim 1, characterized in that: The basic model of seasonal decomposition of the historical data analysis module is: Yt=Tt+St+It; Where: Yt represents the historical energy consumption data at time t; Tt represents the trend component at time t, reflecting the long-term trend of energy consumption; St represents the seasonal component at time t, reflecting the seasonal fluctuation of energy consumption; It represents the residual component at time t, reflecting the random fluctuations after removing the trend and seasonality.

6. The smart factory energy management system based on big data as claimed in claim 1, characterized in that: The simple linear regression model of the energy consumption demand prediction module is: Y = a + bX +; Where: Y represents the predicted value of future energy consumption demand; X represents the independent variable that affects energy demand; a represents the intercept of the regression equation; b represents the slope of the regression equation, which indicates the degree of influence of the independent variable on the dependent variable; represents the error term, which represents the random fluctuations that the model cannot explain.

7. The smart factory energy management system based on big data as claimed in claim 1, characterized in that: The energy monitoring visualization module is internally provided with a data interface unit, a real-time monitoring unit, a visualization display unit and an alarm notification unit.

8. The smart factory energy management system based on big data as claimed in claim 1, characterized in that: The energy decision support module is internally provided with a data analysis unit, a model building unit, a decision generation unit and a report output unit.

9. The smart factory energy management system based on big data as claimed in claim 1, characterized in that: The system integration and interaction module is internally provided with an interface adaptation unit, a data exchange unit, a system coordination unit and a user interaction unit.

10. The smart factory energy management system based on big data as claimed in claim 1, characterized in that: The security and maintenance module includes a data security unit, a system monitoring unit, a fault diagnosis unit and a maintenance management unit.

Images