Energy Consumption Optimization Method Based on Data Analysis

Abstract

The present application provides an energy consumption optimization method based on data analysis, which relates to the technical field of equipment energy management and includes: establishing an energy consumption database for the equipment life cycle; obtaining the basic information of the target equipment, traversing the energy consumption database for the equipment life cycle for screening and matching, and determining the energy consumption data set for the entire life cycle of the equipment; constructing an energy consumption model for the equipment life cycle, inputting the basic information of the target equipment into the energy consumption model for the equipment life cycle, and obtaining the simulated energy consumption data for the life cycle of the target equipment; performing anomaly identification on the simulated energy consumption data for the life cycle to determine the key points of equipment energy consumption; performing simulation based on the key points of equipment energy consumption to determine the simulated data of the key points of equipment energy consumption; and optimizing the energy consumption management strategy of the target equipment. The present application solves the technical problem in the prior art that the lack of complete data analysis for the entire life cycle of the equipment results in insufficiently comprehensive energy consumption optimization measures, and achieves the technical effect of improving the energy utilization efficiency of the entire life cycle of the equipment.

Description

Technical Field

[0001] The present application relates to the technical field of equipment energy management, and specifically to an energy consumption optimization method based on data analysis. Background Art

[0002] Energy consumption management of equipment is crucial in modern industry, especially in power equipment manufacturing companies. During the manufacturing and operation of photovoltaic, wind turbine, transformer and other equipment, the optimization of energy consumption directly affects production costs and energy efficiency. With the expansion of industrial scale and the increase of equipment complexity, traditional energy consumption management methods have gradually exposed their limitations.

[0003] Existing equipment energy consumption management methods usually rely on regular manual inspections and experience-based maintenance strategies. These methods rely on the current operating data of the equipment and are mostly based on set thresholds and rules. They cannot fully and accurately reflect the energy consumption of the equipment throughout its life cycle. At the same time, they lack dynamic predictions of the changing trends of equipment energy consumption and are difficult to effectively identify abnormal fluctuations in equipment energy consumption, resulting in lagging equipment energy consumption management strategies. Maintenance measures are often taken only after a failure occurs, increasing equipment failure rates and maintenance costs. Summary of the invention

[0004] The present application provides an energy consumption optimization method based on data analysis, which solves the technical problem that the energy consumption analysis of equipment in the prior art is often based on current or partial operating data energy consumption management, lacks complete data analysis of the entire life cycle of the equipment, and leads to insufficient energy consumption optimization measures, thereby achieving the technical effect of improving the energy utilization efficiency of the equipment throughout its life cycle.

[0005] In view of the above problems, the present application provides an energy consumption optimization method based on data analysis, which includes: based on big data, collecting historical operation data of the entire cycle of the equipment, establishing an equipment life cycle energy consumption database, and storing historical operation data of the entire life cycle of multiple equipment; obtaining basic information of the target equipment, traversing the equipment life cycle energy consumption database based on the basic information of the target equipment for screening and matching, and determining the equipment life cycle energy consumption data set; training long-term and short-term neural networks based on the equipment life cycle energy consumption data set, constructing an equipment life cycle energy consumption model, inputting the basic information of the target equipment into the equipment life cycle energy consumption model, and obtaining life cycle energy consumption simulation data of the target equipment; performing anomaly identification on the life cycle energy consumption simulation data, and determining the key points of equipment energy consumption, which are the time points of abnormal energy consumption fluctuations in the life cycle of the target equipment; obtaining real-time operation data of the target equipment, performing simulation based on the key points of equipment energy consumption, and determining the simulation data of the key points of equipment energy consumption; optimizing the energy consumption management strategy of the target equipment based on the life cycle energy consumption simulation data and the equipment energy consumption key point simulation data.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] Based on big data, the historical operation data of the whole cycle of the equipment is collected to establish an equipment life cycle energy consumption database. The equipment life cycle energy consumption database stores the historical operation data of the whole life cycle of various equipment, which provides data support for subsequent data analysis and model construction. Obtain the basic information of the target equipment, traverse the equipment life cycle energy consumption database based on the basic information of the target equipment to screen and match, and determine the equipment life cycle energy consumption data set. This step filters out the relevant energy consumption data set from the database to ensure the pertinence and accuracy of the analysis, which helps to identify the energy consumption characteristics of the equipment at different use stages and provide a basis for optimization. Based on the equipment life cycle energy consumption data set, the long-term and short-term neural network is trained to build an equipment life cycle energy consumption model, and the basic information of the target equipment is input into the equipment life cycle energy consumption model to obtain the life cycle energy consumption simulation data of the target equipment. By inputting the basic information of the target equipment, its life cycle energy consumption simulation data is obtained to help predict energy consumption trends and possible abnormal fluctuations. The life cycle energy consumption simulation data is anomaly identified to determine the key points of equipment energy consumption. The key points of equipment energy consumption are the time points of abnormal energy consumption fluctuations in the life cycle of the target equipment, which provide a basis for the subsequent optimization of energy consumption management strategies. Acquire the real-time operation data of the target device, perform simulation based on the key energy consumption points of the device, determine the simulation data of the key energy consumption points of the device, make the simulation results closer to the real operation environment, further verify the energy consumption simulation results of the device, and obtain more accurate energy consumption simulation data. Based on the life cycle energy consumption simulation data and the key energy consumption point simulation data of the device, optimize the energy consumption management strategy of the target device and realize the energy-saving management of the target device throughout its life cycle.

[0008] To sum up, the deep mining and intelligent analysis of historical equipment data in this application has achieved more accurate and comprehensive energy consumption prediction and optimization management, thereby reducing overall energy consumption, improving the energy utilization efficiency of equipment, and promoting energy conservation, emission reduction and sustainable development of enterprises.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of a process flow of an energy consumption optimization method based on data analysis provided in an embodiment of the present application;

[0011] Figure 2 A schematic diagram of a process for determining key points of equipment energy consumption in a method for optimizing energy consumption based on data analysis provided in an embodiment of the present application;

[0012] Figure 3 A schematic diagram of a process for determining simulation data of key points of equipment energy consumption in a method for optimizing energy consumption based on data analysis provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] The embodiments of the present application provide an energy consumption optimization method based on data analysis, thereby solving the technical problem that the energy consumption analysis of equipment in the prior art is often based on current or partial operating data energy consumption management, lacks complete data analysis of the entire life cycle of the equipment, and leads to insufficient energy consumption optimization measures, thereby achieving the technical effect of improving the energy utilization efficiency of the equipment throughout its life cycle.

[0014] like Figure 1 As shown, the embodiment of the present application provides an energy consumption optimization method based on data analysis, the method comprising:

[0015] Based on big data, the historical operation data of the entire life cycle of the equipment is collected to establish an equipment life cycle energy consumption database, which stores the historical operation data of the entire life cycle of various equipment.

[0016] Specifically, firstly, the full-cycle historical operation data of various equipment is collected through big data technology, that is, the operation data generated at all stages of the equipment from commissioning to scrapping. The collection of this data can be carried out through sensors installed on the equipment, which monitor the operation of the equipment in real time.

[0017] Next, establish a device lifecycle energy consumption database specifically for storing this data. The device lifecycle energy consumption database is a database that stores the lifecycle historical operation data of various types of equipment. It is usually classified and stored according to the equipment model, operating environment and working conditions for subsequent energy consumption analysis and prediction. The database will classify and store data according to the different models, operating environments and working conditions of the equipment to facilitate subsequent analysis and calls. For example, the same model of equipment in different regions may perform differently in energy consumption. Therefore, storage based on different operating environments will help future personalized energy consumption management.

[0018] Before the equipment is put into operation or in the early stage of operation, no operating data will be generated or the amount of operating data will be small, making it difficult to predict the future energy consumption based on the historical data of the equipment itself. By establishing an equipment life cycle energy consumption database, the energy consumption characteristics of the equipment can be more comprehensively understood, providing data support for the formulation of more effective energy management strategies.

[0019] The basic information of the target device is obtained, and based on the basic information of the target device, the energy consumption database of the device life cycle is traversed for screening and matching to determine a data set of energy consumption of the device throughout its life cycle.

[0020] Specifically, first, the basic information of the target device needs to be obtained. The basic information of the target device refers to the relevant information of the device that needs to be energy-optimized, including the device model, operating conditions, environmental parameters, workload, etc. This information is used to find historical data of devices similar to the target device in the database. Next, access each data in the database one by one, and by comparing the historical data stored in the database with the basic information of the target device, filter out the device operation data that is most similar to the target device, that is, the device life cycle energy consumption data set. The filtered device life cycle energy consumption data set will serve as the basic data for subsequent model training and simulation. This device life cycle energy consumption data set contains the energy consumption data recorded throughout the life cycle of the device, including power consumption, operating time, environmental conditions, etc. at each stage.

[0021] Through screening and matching, we can find the historical energy consumption data of the target device that meets its operating environment and working conditions, thereby providing a reliable basic data set for building the energy consumption model of the target device.

[0022] Based on the equipment life cycle energy consumption data set, a long-term and short-term neural network is trained to construct an equipment life cycle energy consumption model, and the basic information of the target equipment is input into the equipment life cycle energy consumption model to obtain the life cycle energy consumption simulation data of the target equipment.

[0023] Specifically, the equipment life cycle energy consumption model is a model based on historical data, which is used to simulate the energy consumption of the equipment throughout its life cycle. The model can predict future energy consumption trends by analyzing historical data and real-time data. The screened equipment life cycle energy consumption data set is used as a training data set. These data sets contain historical energy consumption data of equipment similar to the target equipment under various working conditions, which is the basis for building an energy consumption prediction model. The equipment life cycle energy consumption data set is input into the long-term and short-term neural network model for training to generate the equipment life cycle energy consumption model. Next, the basic information of the target equipment is input into the trained model. Based on these inputs, the model will generate the life cycle energy consumption simulation data of the target equipment. Among them, the life cycle energy consumption simulation data is the energy consumption prediction result of the target equipment generated by inputting the basic information of the equipment and calculating it through the energy consumption model. It is usually expressed as time series data, reflecting the energy consumption changes of the target equipment during its operating cycle, and can provide accurate prediction information for energy consumption management, which helps to formulate more effective energy consumption control strategies.

[0024] Anomalies are identified on the life cycle energy consumption simulation data to determine key points of equipment energy consumption, where the key points of equipment energy consumption are time points in the life cycle of target equipment when energy consumption fluctuates abnormally.

[0025] Specifically, during the life cycle of the equipment, the energy consumption data does not change linearly and may fluctuate due to a variety of factors. The data analysis tool is used to process the equipment's life cycle energy consumption simulation data to identify points in the equipment's energy consumption data that deviate from normal changes. Then, the identified abnormal data is further analyzed to determine whether these abnormal fluctuations are persistent and whether they are related to the equipment's failure or aging trend. If the abnormal points are related to the known aging or failure characteristics of the equipment, these time points can be considered to be the equipment's energy consumption critical points. The energy consumption critical point can be the moment when the equipment starts to consume more energy, or it can be the point in time when the equipment's performance degrades under certain conditions. For example, if the normal energy consumption of the equipment is around 500kW, and at a certain point in time the energy consumption suddenly rises to 700kW, the time point when this energy consumption surge occurs is the energy consumption critical point.

[0026] This step can detect energy consumption anomalies in advance, avoid greater losses or equipment failures, and optimize maintenance and operation plans accordingly to ensure the energy efficiency and operational stability of the equipment.

[0027] Acquire the real-time operation data of the target device, perform simulation based on the key energy consumption points of the device, and determine the simulation data of the key energy consumption points of the device.

[0028] Specifically, the real-time operation data of the target device is the operation status data of the device at the current moment, including but not limited to energy consumption, temperature, operation time, etc. The real-time operation data of the target device is collected through various sensors arranged around the target device, such as power sensors, temperature sensors, operation time recording devices, etc., and a simulation model is constructed based on the determined key energy consumption points of the device and the corresponding real-time operation data. The real-time operation data of the target device is input into the simulation model to simulate the operation status and energy consumption performance of the target device at the key energy consumption points, and obtain the simulation data of the key energy consumption points. Among them, the simulation data of the key energy consumption points is the prediction data related to the key energy consumption points of the device obtained through simulation, which reflects the energy consumption performance of the target device at these key energy consumption points of the device, so as to more accurately evaluate the operation status of the device at the key points.

[0029] Based on the life cycle energy consumption simulation data and the equipment energy consumption key point simulation data, the target equipment energy consumption management strategy is optimized.

[0030] Specifically, by combining the life-cycle energy consumption simulation data and the key-point energy consumption simulation data of the equipment, multi-dimensional alignment and analysis are carried out to identify the energy consumption performance of the equipment at each key time point in the life cycle and find the patterns of abnormal energy consumption fluctuations. By comparing the historical energy consumption data with the simulation data, the energy consumption characteristics of the equipment at different stages can be clarified. For example, when the equipment starts to age, the energy consumption may gradually increase, or the energy consumption of the equipment may increase abnormally under specific working conditions. According to these analysis results, the energy consumption management strategy of the target equipment is adjusted and optimized. Among them, the energy consumption management strategy is a set of management methods and optimization measures aimed at reducing energy consumption and improving equipment efficiency by adjusting the operation mode, maintenance plan, etc. of the equipment. For example, when the analysis shows that the energy consumption of a certain equipment increases significantly under a specific load, the operation mode or production scheduling of the equipment can be adjusted to reduce the operation frequency of the equipment under high-energy-consuming loads and avoid unnecessary energy consumption waste. By this method, the operation efficiency of the equipment can be maximized, the energy consumption can be controlled, and the goal of energy conservation and emission reduction can be finally achieved, while reducing the equipment maintenance cost.

[0031] Furthermore, the embodiment of the present application establishes an equipment life-cycle energy consumption database, including:

[0032] Based on big data, traverse multiple data sources, collect the equipment models, equipment operating conditions, equipment operating conditions, and equipment full-life-cycle energy consumption data of multiple equipment, and obtain the equipment full-cycle historical operation data; preprocess the equipment full-cycle historical operation data and classify it according to the equipment model to obtain multiple equipment historical data sets; store the multiple equipment historical data sets in the database to obtain the equipment life-cycle energy consumption database.

[0033] Specifically, based on big data technology, traverse multiple data sources and collect the operation data of different equipment, including equipment models, operating conditions (such as environmental parameters such as temperature and humidity), operating conditions (such as load, operation mode, etc.), and full-life-cycle energy consumption data. These data sources can be the sensor systems of the equipment, the Internet of Things platform, etc. Integrate the collected data to obtain the equipment full-cycle historical operation data, which is labeled with equipment numbers for easy query of all historical data corresponding to each equipment.

[0034] The collected equipment data is preprocessed, including removing outliers and erroneous data, processing missing values ​​and data standardization. The preprocessed equipment data is classified according to the equipment model, operating conditions and working conditions. This classification can be completed through the classification algorithm in the database system or the grouping mechanism based on specific tags. For example, the data can be divided into different historical data sets according to the similarity of equipment models and operating conditions for more efficient subsequent retrieval and analysis. Through classification, multiple equipment historical data sets are obtained, each of which corresponds to an equipment model and contains the historical operating data of the equipment of this model throughout its life cycle under different operating conditions and different operating conditions. By storing the processed equipment historical data sets in the equipment life cycle energy consumption database, an energy consumption database covering the entire life cycle of the equipment can be established, providing data support for subsequent energy consumption model training, prediction and optimization.

[0035] Furthermore, the embodiment of the present application determines a data set of energy consumption for the entire life cycle of the equipment, including:

[0036] Obtain basic information of the target device, wherein the basic information of the target device includes device model, operating conditions and operating conditions; extract the device model, traverse the device life cycle energy consumption database to match the device model, and determine a first device data set; extract the operating conditions, filter the first device data set based on preset condition fluctuation constraints, and determine a second device data set; extract the operating conditions, traverse the second device data set to match the operating conditions, and determine a third device data set; calculate the similarity between the basic information of the target device and the third device data set, filter the device data whose similarity is greater than or equal to the similarity threshold, and obtain a similar device data set; extract the historical energy consumption data of the equipment in the similar device data set as the equipment full life cycle energy consumption data set.

[0037] Specifically, detailed information about the target device is collected, including the device model, operating conditions, and operating conditions. This information is the basis for subsequent data screening and matching, and can usually be obtained through the device's factory data and real-time monitoring system. Next, based on the model of the target device, a preliminary match is performed in the device life cycle energy consumption database to screen out device data with the same model as the target device, forming the first device data set.

[0038] The operating conditions of the target device, such as ambient temperature, humidity, operating area, etc., are further extracted and filtered in the first device data set according to the preset condition fluctuation constraints. The filtered data forms the second device data set to ensure that the data of the matching device and the target device operate under similar environmental conditions. Among them, the preset fluctuation constraint is a customized operating environment condition fluctuation range, such as allowing the temperature to fluctuate within ±5°C.

[0039] Then, according to the operating conditions of the equipment, such as load conditions, working modes, etc., the data in the second equipment data set is further screened to ensure that these equipment are operated under similar working conditions, thereby generating a third equipment data set.

[0040] The device information in the third device data set is similar to the basic information of the target device, and the similarity between the two is determined using algorithms such as cosine similarity or Euclidean distance. If the similarity is greater than or equal to the set similarity threshold, these data are filtered out to form a similar device data set. The similarity threshold is the minimum requirement for measuring the similarity between two data sets. The historical energy consumption data of the device is extracted from the similar device data set to construct a full life cycle energy consumption data set for the target device.

[0041] By gradually matching equipment models, operating conditions and working conditions, and screening through similarity calculation, we ensure that the extracted equipment energy consumption data set is highly relevant to the target equipment, providing accurate and reliable historical data for subsequent energy consumption modeling and optimization.

[0042] Furthermore, the embodiment of the present application constructs an energy consumption model for the entire life cycle of the equipment, including:

[0043] The energy consumption data set of the equipment throughout its life cycle is standardized and normalized to generate a preprocessed energy consumption data set; the preprocessed energy consumption data set is processed for time characteristics to obtain a time series data set; the time series data set is divided into a training set and a test set according to a predetermined ratio, the long-term and short-term neural network is trained by the training set, the performance of the long-term and short-term neural network is tested by the test set, and the energy consumption model of the equipment throughout its life cycle is obtained.

[0044] Specifically, first, the energy consumption data set of the equipment's entire life cycle is standardized and normalized, and data with different characteristics (such as power, time, etc.) are converted to the same scale to reduce the model's sensitivity to the data dimension and improve the training effect.

[0045] Next, the preprocessed energy consumption dataset is processed for time features to ensure that the model can capture the time series characteristics of the data. The data is organized in chronological order and sliding windows are constructed to maintain the time dependency of the data. For example, for the energy consumption data of an industrial equipment, it can be aggregated and split by hour, day or month to generate the corresponding time series dataset. The processed time series dataset is divided into a training set and a test set according to a certain ratio, such as 80% training set and 20% test set. The training set is used to train the neural network, while the test set is used to evaluate the generalization ability of the model to ensure that the model performs well on unseen data.

[0046] Use the training set to train the long-term short-term neural network. The long-term short-term neural network can remember and forget important information in the time series through its special gating mechanism, and is suitable for processing data with a long time span. The training of the long-term short-term neural network can be implemented through deep learning frameworks such as TensorFlow or PyTorch. The training process includes forward propagation, back propagation, and gradient update.

[0047] After the model training is completed, the performance of the long-term and short-term neural network is evaluated using the test set. Common evaluation indicators include mean square error (MSE) and mean absolute error (MAE). These indicators are used to detect the prediction effect of the model to ensure that it can accurately predict the future energy consumption changes of the equipment.

[0048] Once the model is trained and tested, it can be used as a full life cycle energy consumption model for the equipment to predict future energy consumption trends. This model can be regularly updated or retrained in a production environment to adapt to new data inputs and ensure its prediction accuracy under different working conditions.

[0049] Further, such as Figure 2 As shown, the embodiment of the present application determines the key points of device energy consumption, including:

[0050] Curve fitting is performed according to the life cycle energy consumption simulation data to generate an energy consumption simulation curve; the energy consumption simulation curve is segmented according to the equipment life cycle to obtain multiple-stage energy consumption simulation curves; the equipment standard operation energy consumption data is obtained for curve fitting to generate multiple-stage standard energy consumption curves; the multiple-stage energy consumption simulation curves and the multiple-stage standard energy consumption curves are aligned to identify energy consumption fluctuation anomalies and determine the key points of the equipment energy consumption.

[0051] Specifically, the life cycle energy consumption simulation data is processed by the curve fitting method to generate a simulation curve that reflects the energy consumption trend of the equipment throughout its life cycle, namely the energy consumption simulation curve. This curve can intuitively show how the energy consumption of the equipment changes over time. The energy consumption simulation curve is divided into multiple stages according to the life cycle of the equipment, such as the initial operation stage, stable operation stage, aging stage, etc. Each stage represents the energy consumption characteristics of the equipment in a certain period. The energy consumption change characteristics of the equipment are different at different stages. After segmentation, multiple stage energy consumption simulation curves are obtained to facilitate subsequent analysis.

[0052] Obtain the equipment standard operating energy consumption data, which refers to the energy consumption data of the equipment under standard working conditions (i.e. normal operating conditions), as an energy consumption benchmark for comparison and analysis with actual energy consumption. Standard energy consumption data usually comes from the equipment manufacturer or industry benchmark. Curve fitting is also performed on the equipment standard operating energy consumption data to generate standard energy consumption curves for multiple stages.

[0053] The energy consumption simulation curves at different stages are aligned with the standard energy consumption curves, and the deviation between the actual energy consumption and the standard energy consumption is found by comparing their differences at each stage. This process can use DTW (dynamic time warping) or simple interpolation to synchronize the two curves.

[0054] On the aligned curve, identify the significant deviation points between actual energy consumption and standard energy consumption. These points usually represent abnormal fluctuations in equipment energy consumption. By setting an abnormal threshold, identify those fluctuation points that exceed the standard energy consumption. These points usually indicate potential failures or efficiency declines in the equipment. Identify these fluctuation points as key points of equipment energy consumption in the equipment life cycle. These key energy consumption points can help identify abnormal conditions of equipment at different life cycle stages and serve as reference points for equipment status monitoring and maintenance decisions, thereby optimizing equipment operation strategies and maintenance plans and improving the overall energy efficiency performance of the equipment.

[0055] Further, such as Figure 3 As shown, the embodiment of the present application determines the simulation data of key points of energy consumption of the equipment, including:

[0056] Deploy a sensor array to collect real-time operation data of the target device and obtain a real-time operation data set; extract the real-time operation data of the key points of the device energy consumption from the real-time operation data set and obtain a key point real-time operation data set; obtain the physical characteristic data and operating environment data of the target device, and build a simulation model based on the physical characteristic data and operating environment data and the basic information of the target device; simulate the device operation according to the key point real-time operation data set and the simulation model to obtain simulation data of the key points of the device energy consumption.

[0057] Specifically, the sensor array is a system composed of multiple sensors, which is used to monitor various operating parameters of the equipment, such as temperature, pressure, power, etc. First, sensors are installed at different locations of the target equipment to deploy the sensor array. The sensor array can obtain the operating data of the target equipment in real time, summarize these real-time operating data, and obtain the real-time operating data set of the target equipment. The real-time operating data set reflects the actual operating status of the equipment in a certain period of time, such as power consumption, rotation speed, temperature, etc.

[0058] Extract the operation data related to the key points of equipment energy consumption from the collected real-time operation data set. For example, if a certain equipment has a peak energy consumption fluctuation in the third year of operation, the data at that time point can be analyzed in detail. Collect the physical characteristics of the target equipment, such as mechanical structure, material properties, etc., as well as the operating environment, such as external temperature and humidity. These data are the basis for subsequent simulation analysis. This information can be obtained from the technical manual provided by the equipment manufacturer or through on-site measurements.

[0059] Based on the physical characteristics of the equipment, the operating environment, and the basic information of the target equipment, a simulation model of the equipment is constructed. The simulation model is used to predict the performance of the equipment at key energy consumption points, providing a basis for subsequent energy consumption simulation analysis. It can be constructed using simulation tools such as MATLAB / Simulink or Ansys. The extracted key point real-time operation data set is input into the simulation model to simulate the operating status of the equipment at key energy consumption points and generate simulation data of key energy consumption points of the equipment.

[0060] Furthermore, the embodiment of the present application optimizes the energy consumption management strategy of the target device, including:

[0061] The life cycle energy consumption simulation data and the equipment energy consumption key point simulation data are aligned in multiple dimensions to determine the target equipment energy consumption data curve; peak detection is performed based on the target equipment energy consumption data curve to determine the energy consumption peak, and load optimization is performed based on the energy consumption peak to determine the target equipment energy consumption optimization strategy; the energy consumption change rate is calculated based on the target equipment energy consumption data curve to evaluate the equipment aging trend, identify the equipment aging critical point, and predict the equipment failure point, and a target equipment life cycle maintenance schedule is formulated based on the equipment aging critical point and the equipment failure point.

[0062] Specifically, the life cycle energy consumption simulation data and the key point energy consumption simulation data of the equipment are matched in terms of time axis, operating conditions, load status, etc. to generate a comprehensive target equipment energy consumption data curve. This target equipment energy consumption data curve represents the energy consumption of the equipment in different time periods.

[0063] Use peak detection algorithms, such as local maximum detection, to analyze the energy consumption data curve of the target device, identify the highest point of energy consumption during the operation of the device, and determine the energy consumption peak. Based on the identified energy consumption peak, load optimization is performed, including: real-time monitoring of the current load of the device, obtaining indicators such as CPU usage, memory usage, and power consumption. According to the load of the device, apply load balancing algorithms, such as weighted polling, hash distribution, or minimum load priority distribution, to distribute the load to multiple devices. When the load of a device exceeds the preset threshold, use a migration strategy to assign tasks to other devices with lower loads to avoid a device being overloaded. Finally, an energy consumption optimization strategy for the target device is generated. This strategy is used to adjust the operating parameters of the device, such as load distribution, working hours, or operating mode, to reduce energy consumption peaks and improve energy efficiency.

[0064] Analyze the energy consumption data curve of the target equipment, and obtain the rate of change of energy consumption by calculating the rate of change between data points, where the rate of change of energy consumption indicates the rate of change of energy consumption of the equipment in different time periods. According to the calculated rate of change of energy consumption, identify the critical point of equipment aging, that is, the time point when aging is significantly accelerated, and use this information to predict possible equipment failure points. Based on the prediction results of the critical point of equipment aging and the point of failure, formulate a life cycle maintenance plan for the target equipment. This plan will indicate when to perform maintenance and overhaul to prevent failures and extend the service life of the equipment. By calculating the rate of change of energy consumption, the aging trend of the equipment can be discovered in time, and the point of failure can be predicted, thus avoiding high energy consumption and downtime losses caused by potential equipment failures, effectively extending the service life of the equipment, and reducing maintenance costs and improving the reliability of the overall system.

[0065] Furthermore, the embodiment of the present application predicts the equipment failure point, including:

[0066] Define a fault indicator, wherein the fault indicator has a fault indicator threshold label; calculate the fault indicator of the key point of the equipment energy consumption according to the target equipment energy consumption data curve, and obtain multiple key point fault indicator sets, wherein each equipment energy consumption key point corresponds to a key point fault indicator set; determine whether the multiple key point fault indicator sets are greater than the fault indicator threshold label, and if so, define the equipment energy consumption key point as an equipment fault point.

[0067] Specifically, fault indicators are metrics used to evaluate whether a device is faulty, such as abnormal energy consumption, vibration, temperature, and other indicators. These indicators help detect whether the device is operating normally. The fault indicator threshold label is the set fault indicator threshold used to determine whether the device is faulty. When the fault indicator exceeds this threshold, the device is considered to be faulty.

[0068] First, determine the indicators used to detect equipment failures. For example, you can define "abnormal fluctuations in energy consumption" as a fault indicator. Set the corresponding threshold label, such as marking it as abnormal if the energy consumption exceeds 10% of the normal level. According to the energy consumption data curve of the target device, analyze the energy consumption data of the key points of the equipment's energy consumption, and obtain the fault indicators of each key point of the equipment's energy consumption by calculating the average value, variance, etc. For each key point of the equipment's energy consumption, generate a corresponding set of fault indicators. These indicator sets contain the calculation results of each key point of the equipment's energy consumption, such as "energy consumption exceeding the standard range", "fluctuation frequency", etc. Compare the fault indicators of each key point of the equipment's energy consumption with the set threshold label. If the fault indicator value of a key point of the equipment's energy consumption exceeds the threshold label, the key point of the equipment's energy consumption is judged to be a device failure point.

[0069] Through the above steps, the fault point of the equipment can be accurately located, and the possible fault problems that may occur during the operation of the equipment can be identified in time, which helps to prevent equipment failure, reduce downtime and maintenance costs, and improve the reliability and stability of the equipment.

[0070] In summary, the energy consumption optimization method based on data analysis provided in the embodiments of the present application has the following technical effects:

[0071] Based on big data, the historical operation data of the whole cycle of the equipment is collected to establish an equipment life cycle energy consumption database. The equipment life cycle energy consumption database stores the historical operation data of the whole life cycle of various equipment, which provides data support for subsequent data analysis and model construction. Obtain the basic information of the target equipment, traverse the equipment life cycle energy consumption database based on the basic information of the target equipment to screen and match, and determine the equipment life cycle energy consumption data set. This step filters out the relevant energy consumption data set from the database to ensure the pertinence and accuracy of the analysis, which helps to identify the energy consumption characteristics of the equipment at different use stages and provide a basis for optimization. Based on the equipment life cycle energy consumption data set, the long-term and short-term neural network is trained to build an equipment life cycle energy consumption model, and the basic information of the target equipment is input into the equipment life cycle energy consumption model to obtain the life cycle energy consumption simulation data of the target equipment. By inputting the basic information of the target equipment, its life cycle energy consumption simulation data is obtained to help predict energy consumption trends and possible abnormal fluctuations. The life cycle energy consumption simulation data is anomaly identified to determine the key points of equipment energy consumption. The key points of equipment energy consumption are the time points of abnormal energy consumption fluctuations in the life cycle of the target equipment, which provide a basis for the subsequent optimization of energy consumption management strategies. Acquire the real-time operation data of the target device, perform simulation based on the key energy consumption points of the device, determine the simulation data of the key energy consumption points of the device, make the simulation results closer to the real operation environment, further verify the energy consumption simulation results of the device, and obtain more accurate energy consumption simulation data. Based on the life cycle energy consumption simulation data and the key energy consumption point simulation data of the device, optimize the energy consumption management strategy of the target device and realize the energy-saving management of the target device throughout its life cycle.

[0072] Overall, the in-depth mining and intelligent analysis of historical equipment data in the embodiments of the present application achieves more accurate and comprehensive energy consumption prediction and optimization management, thereby reducing overall energy consumption, improving the energy utilization efficiency of equipment, and promoting energy conservation, emission reduction and sustainable development of enterprises.

[0073] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An energy consumption optimization method based on data analysis, characterized in that: include: Based on big data, historical operation data of the entire equipment cycle is collected to establish an equipment life cycle energy consumption database, which stores historical operation data of various equipment throughout their life cycles; Obtaining basic information of the target device, traversing the device life cycle energy consumption database for screening and matching based on the basic information of the target device, and determining a data set of energy consumption for the entire life cycle of the device; Based on the equipment life cycle energy consumption data set, a long-term and short-term neural network is trained to construct an equipment life cycle energy consumption model, and the basic information of the target equipment is input into the equipment life cycle energy consumption model to obtain the life cycle energy consumption simulation data of the target equipment; Performing abnormal identification on the life cycle energy consumption simulation data to determine the key point of equipment energy consumption, wherein the key point of equipment energy consumption is the time point of abnormal fluctuation of energy consumption in the life cycle of the target equipment; Acquire the real-time operation data of the target device, perform simulation based on the key points of energy consumption of the device, and determine the simulation data of the key points of energy consumption of the device; Based on the life cycle energy consumption simulation data and the equipment energy consumption key point simulation data, the target equipment energy consumption management strategy is optimized.

2. The energy consumption optimization method based on data analysis according to claim 1, characterized in that: Establish an equipment life cycle energy consumption database, including: Based on big data, we traverse multiple data sources to collect equipment models, equipment operating conditions, equipment operating conditions, and equipment life cycle energy consumption data for multiple equipment, and obtain the equipment's full-cycle historical operation data; Preprocessing the historical operation data of the equipment throughout its entire cycle and classifying the data according to equipment models to obtain multiple equipment historical data sets; The multiple equipment historical data sets are stored in a database to obtain the equipment life cycle energy consumption database.

3. The energy consumption optimization method based on data analysis according to claim 1, characterized in that: Determine the energy consumption data set for the entire life cycle of the equipment, including: Obtaining basic information of the target device, wherein the basic information of the target device includes device model, operating conditions and operating status; Extract the device model, traverse the device life cycle energy consumption database to match the device model, and determine a first device data set; Extracting the operating condition, screening the first device data set based on a preset condition fluctuation constraint, and determining a second device data set; Extracting the operating condition, traversing the second device data set to perform operating condition matching, and determining a third device data set; Calculating the similarity between the target device basic information and the third device data set, screening device data with a similarity greater than or equal to a similarity threshold, and obtaining a similar device data set; The historical energy consumption data of the equipment is extracted from similar equipment data sets as the equipment full life cycle energy consumption data set.

4. The energy consumption optimization method based on data analysis according to claim 1, characterized in that: Build an energy consumption model for the entire life cycle of the equipment, including: Standardizing and normalizing the energy consumption data set of the equipment throughout its life cycle to generate a preprocessed energy consumption data set; Performing time feature processing on the preprocessed energy consumption data set to obtain a time series data set; The time series data set is divided into a training set and a test set according to a predetermined ratio, the long-term and short-term neural network is trained by the training set, and the performance of the long-term and short-term neural network is tested by the test set to obtain the energy consumption model of the equipment throughout its life cycle.

5. The method for optimizing energy consumption based on data analysis according to claim 1, characterized in that: Determine the key points of equipment energy consumption, including: Performing curve fitting according to the life cycle energy consumption simulation data to generate an energy consumption simulation curve; The energy consumption simulation curve is segmented according to the equipment life cycle to obtain multiple stage energy consumption simulation curves; Obtain the equipment's standard operating energy consumption data for curve fitting and generate standard energy consumption curves for multiple stages; The energy consumption simulation curves of the multiple stages are aligned with the standard energy consumption curves of the multiple stages, abnormal energy consumption fluctuations are identified, and key energy consumption points of the equipment are determined.

6. The method for optimizing energy consumption based on data analysis according to claim 1, characterized in that: Determine the simulation data of key points of equipment energy consumption, including: Deploy sensor arrays to collect real-time operation data of target devices and obtain real-time operation data sets; Extracting the real-time operation data of the key points of energy consumption of the equipment from the real-time operation data set to obtain the key point real-time operation data set; Acquire physical property data and operating environment data of the target device, and build a simulation model based on the physical property data, operating environment data and basic information of the target device; The equipment operation simulation is performed according to the key point real-time operation data set and the simulation model to obtain the key point simulation data of the equipment energy consumption.

7. The method for optimizing energy consumption based on data analysis according to claim 1, characterized in that: Optimize the energy consumption management strategy of target devices, including: Perform multi-dimensional alignment on the life cycle energy consumption simulation data and the equipment energy consumption key point simulation data to determine a target equipment energy consumption data curve; Perform peak detection according to the energy consumption data curve of the target device to determine the energy consumption peak, perform load optimization based on the energy consumption peak, and determine the energy consumption optimization strategy of the target device; The energy consumption change rate is calculated according to the target equipment energy consumption data curve, the equipment aging trend is evaluated, the equipment aging critical point is identified, and the equipment failure point is predicted. Based on the equipment aging critical point and the equipment failure point, a target equipment life cycle maintenance plan is formulated.

8. The method for optimizing energy consumption based on data analysis according to claim 7, characterized in that: Predict equipment failure points, including: defining a fault indicator, wherein the fault indicator has a fault indicator threshold label; According to the target device energy consumption data curve, the fault index of the key point of the device energy consumption is calculated to obtain a plurality of key point fault index sets, wherein each key point of the device energy consumption corresponds to a key point fault index set; It is determined whether the plurality of key point fault indicator sets are greater than the fault indicator threshold label, and if so, the equipment energy consumption key point is determined as the equipment fault point.

Images