Intelligent enterprise energy optimization method and system based on Internet and big data analysis

Abstract

The invention discloses an intelligent enterprise energy optimization method and system based on Internet and big data analysis, relates to the technical field of intelligent energy optimization, and aims to make energy management more accurate and efficient, reduce the risk of human decision and improve the flexibility and sustainability of energy use due to the intelligentization and automation of the system. Through accurate prediction and dynamic adjustment, the enterprise can reduce the energy cost and improve the equipment reliability, and finally the improvement of the overall operation benefit is promoted. The system provides a scientific decision basis for enterprises, so that energy management is more transparent and efficient, and the enterprises are promoted to realize higher-level sustainable development. Through early warning of energy waste and dynamic optimization of an energy scheduling strategy, an enterprise can reduce environmental influence while reducing cost, and through dynamic analysis of an energy demand and an energy efficiency level, the system can reduce energy waste, optimize energy supply and consumption and reduce energy cost of the enterprise to the greatest extent.

Description

Technical Field

[0001] This invention relates to the field of intelligent energy optimization technology, specifically to a method and system for intelligent energy optimization of enterprises based on the Internet and big data analysis. Background Technology

[0002] With the escalating global energy crisis and increasing emphasis on environmental protection, the efficient use and rational allocation of energy in the production process has become a crucial issue for enterprises. The energy management field is gradually transforming towards intelligent and data-driven approaches, particularly through the combination of big data analytics and artificial intelligence technologies, which is driving the precision and dynamic optimization of energy management.

[0003] Currently, most enterprises rely on traditional manual monitoring and experience-based judgment for energy management and optimization, lacking real-time and comprehensive data support. Under traditional energy management models, real-time energy efficiency monitoring and fault early warning of equipment are often difficult to achieve, with more emphasis on post-event analysis and response. Many enterprises lack the capability for real-time data acquisition and cannot identify potential risks of energy waste in advance through intelligent algorithms. Due to the lack of effective energy efficiency monitoring and maintenance prediction, equipment failures often cannot be predicted in advance, leading to unnecessary downtime or equipment damage, causing production delays and energy waste.

[0004] The lack of advanced data analytics and intelligent early warning mechanisms has led to numerous adverse consequences. Enterprises often face serious energy waste by failing to adjust equipment operating status or load based on real-time data, resulting in prolonged inefficient operation and excessive consumption. Equipment failures are typically sudden, and many enterprises fail to predict and preventatively maintain them. Once a failure occurs, downtime for repairs is necessary, leading to production losses and reduced productivity. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a method and system for intelligent energy optimization in enterprises based on the Internet and big data analysis, which solves the problems mentioned in the background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solution: an enterprise energy intelligent optimization system based on Internet and big data analysis, including an energy data acquisition and preprocessing module, an energy efficiency analysis and loss detection module, a fault prediction and risk assessment module, a prediction model and trend analysis module, an optimized scheduling and decision support module, and a reporting and feedback module;

[0007] The energy data acquisition and preprocessing module collects real-time data from the enterprise's energy equipment, including equipment operating status data, environmental factor data, and load data, and performs preprocessing, including data cleaning and standardization, to obtain dataset W.

[0008] The energy efficiency analysis and loss detection module performs real-time analysis of the equipment's energy efficiency based on the collected dataset W to obtain the equipment's energy efficiency value PN; and through big data technology and machine learning, it analyzes the equipment's load fluctuation QB, temperature change ΔT, and energy loss ES to obtain the equipment failure probability Pgz.

[0009] The fault prediction and risk assessment module uses AI algorithms to model the equipment operating status based on the obtained equipment energy efficiency value PN and equipment fault probability Pgz, and predicts the equipment fault risk; and calculates the equipment fault risk index Rf based on the actual power PS, load status data La and power fluctuation ΔP.

[0010] The prediction model and trend analysis module predict energy demand based on the failure risk index Rf, energy loss ES, and environmental factor data, predicting the trend and change pattern of energy consumption; and establishes a time series model to predict future energy demand XE and energy efficiency level XEP.

[0011] The optimization scheduling and decision support module performs intelligent energy scheduling based on energy demand XE, energy efficiency level XEP, and fault risk index Rf, and formulates energy supply and equipment scheduling strategies.

[0012] The reporting and feedback module is responsible for generating reports and feedback information, providing analysis reports on energy loss (ES) and equipment scheduling strategies, and feeding them back to management.

[0013] Preferably, the energy data acquisition and preprocessing module includes a data acquisition unit and a data preprocessing unit;

[0014] The data acquisition unit collects equipment operating status data through a power detector, a voltage sensor, and a current sensor; collects environmental factor data through a temperature and humidity sensor; and collects load data through a load monitoring sensor. The equipment operating status data includes equipment power P, equipment voltage V, and equipment current I; the environmental factor data includes temperature T and humidity S; and the load data includes equipment load Q.

[0015] The data preprocessing unit cleans and standardizes the collected data to obtain dataset W. Cleaning includes using mean padding and interpolation to remove incomplete, abnormal, and invalid data. Standardization includes using the z-score standardization method to eliminate the influence of data dimensions.

[0016] Preferably, the energy efficiency analysis and loss detection module includes an energy efficiency analysis and efficiency evaluation unit and an energy loss detection and fault prediction unit;

[0017] The energy efficiency analysis and efficiency evaluation unit evaluates the energy efficiency of the equipment based on the dataset W, obtains the equipment energy efficiency value PN, and judges the equipment operating status through the equipment energy efficiency value PN.

[0018] The energy efficiency value PN of the device is obtained by the following formula:

[0019]

[0020] In the formula, Q represents the equipment load, which is usually the maximum load or operating capacity provided by the manufacturer; PL represents the ideal power of the equipment, which is usually calculated from the equipment specifications and design parameters; PS represents the actual power of the equipment.

[0021] The device operating status is obtained through the following methods:

[0022] When 50% < equipment energy efficiency value PN < 100%, it indicates that the equipment is operating normally;

[0023] When the energy efficiency value PN ≤ 50%, it indicates that the equipment is operating abnormally; the efficiency decline is caused by reasons such as fault, aging, or load mismatch.

[0024] The energy loss detection and fault prediction unit uses big data analysis technology to detect the energy loss (ES) during equipment operation. Low equipment energy efficiency is usually accompanied by increased energy loss. By comparing real-time monitoring and historical data, the unit calculates the proportion of energy waste and identifies potentially energy-wasting equipment.

[0025] The energy loss ES is obtained by multiplying the difference between the actual power PS and the ideal power PL of the equipment by the running time.

[0026] Based on the equipment energy efficiency value PN, energy loss ES, load fluctuation QB and temperature change ΔT, and combined with machine learning algorithms, potential faults are predicted, and the equipment fault probability Pgz is obtained.

[0027] The load fluctuation QB is obtained by the ratio of the difference between the equipment load Q(t) at time t and the equipment load Q(t-1) at time t-1 to the time interval Δt.

[0028] The equipment failure probability Pgz is obtained using the following formula:

[0029]

[0030] In the formula, α1, α2, and α3 represent the ratio of equipment energy efficiency value PN to time interval Δt, the ratio of energy loss ES to load fluctuation QB, and the weighting parameter of temperature change ΔT, respectively, and exp represents the exponential function. Pgz represents the equipment failure probability, with a value range of [0,1], indicating the likelihood of equipment failure.

[0031] Preferably, the fault prediction and risk assessment module includes a fault prediction unit and a fault risk index calculation unit;

[0032] The fault prediction unit establishes a fault risk model using the equipment energy efficiency value PN, the equipment fault probability Pgz, the actual power PS of the equipment, the load status data La, and the power fluctuation ΔP.

[0033] The load status data La is obtained through the following formula:

[0034]

[0035] In the formula, V represents the equipment voltage, I represents the equipment current, cosφ represents the power factor, and PL represents the ideal power of the equipment;

[0036] The power fluctuation ΔP is obtained by the ratio of the difference between the device power P(t) at time t and the device power P(t-1) at time t-1 to the time interval Δt.

[0037] AI algorithms are used to predict equipment failure risk. Historical data is used to train the failure risk model to obtain parameters β1, β2, β3, β4 and β5, which are then input into the failure risk model to predict the failure risk index Rf.

[0038] The formula for the failure risk model is:

[0039]

[0040] In the formula, β1, β2, β3, β4 and β5 represent the weighting coefficients of equipment energy efficiency value PN, equipment failure probability Pgz, actual power PS, load state data La and power fluctuation ΔP, respectively.

[0041] Preferably, the fault risk index calculation unit evaluates the current operating status of the equipment based on the obtained equipment fault probability Pgz, power fluctuation ΔP, actual power PS and ideal power PL through a fault risk model, obtains the fault risk index Rf, and compares it with a preset risk threshold TRf to determine the current operating status of the equipment.

[0042] The failure risk index Rf is obtained using the following formula:

[0043]

[0044] The current operating status of the device is obtained by matching in the following way:

[0045] When the fault risk index Rf ≥ the risk threshold TRf, it indicates that the equipment is in an abnormal operating state, prompting maintenance and replacement of the equipment;

[0046] When the fault risk index Rf < the risk threshold TRf, it indicates that the equipment is operating normally, and the equipment monitoring status is saved.

[0047] Preferably, the prediction model and trend analysis module includes a data extraction unit and an energy demand prediction and energy efficiency modeling unit;

[0048] The data extraction unit normalizes the acquired fault risk index Rf, energy loss ES, and environmental factor data, including temperature T and humidity S, to form a model training set Y = {RF, ES, T, S}.

[0049] The energy demand forecasting and energy efficiency modeling unit establishes a regression model based on historical data and training set Y to predict future energy demand XE.

[0050] The energy demand XE is obtained using the following formula:

[0051]

[0052] In the formula, XE(t+1) represents the energy demand at time t+1, η represents the parameters of the regression model, Yi(t) represents the i-th data in the training set Y at time t, and θi represents the regression coefficient of the i-th data in the training set Y.

[0053] Based on the energy demand XE and the training set Y, the energy efficiency level XEP is calculated and compared with the preset energy consumption threshold Txep to determine the energy consumption status of the operating equipment.

[0054] The energy efficiency level XEP is obtained using the following formula:

[0055]

[0056] In the formula, ΔT represents the temperature change and ΔS represents the humidity change;

[0057] The energy consumption status of the operating equipment is obtained through the following methods:

[0058] When the energy efficiency level XEP is greater than or equal to the energy consumption threshold Txep, it indicates that the energy consumption status of the operating equipment is normal; under the condition of consuming the same amount of energy, more effective output is generated, and the energy efficiency is better.

[0059] When the energy efficiency level XEP is less than the energy consumption threshold Txep, it indicates that the energy consumption status of the operating equipment is abnormal. The equipment outputs less energy under the same energy consumption, resulting in energy waste and low equipment efficiency.

[0060] Preferably, the optimization scheduling and decision support module includes an energy scheduling optimization unit and an equipment scheduling strategy formulation unit;

[0061] The energy dispatch optimization unit assesses the system's current energy demand based on real-time collected energy demand XE, predicts future energy demand fluctuations, calculates the current energy usage efficiency Ns in conjunction with the energy efficiency level XEP, and proposes an energy adjustment scheme Z to ensure that production needs are met with minimal energy consumption.

[0062] The energy efficiency Ns is obtained by multiplying the energy efficiency level XEP by the power fluctuation ΔP.

[0063] The energy adjustment scheme Z is obtained through the following formula:

[0064]

[0065] In the formula, XEI represents the energy demand of the first type of energy, XEPI represents the energy efficiency level of the first type of energy, PI represents the supply capacity of the first type of energy, CI represents the unit cost of the first type of energy, λI represents the energy efficiency adjustment coefficient of the first type of energy, and N represents the total amount of energy.

[0066] By adjusting the supply of each type of energy source, we can minimize the consumption of inefficient energy sources, that is, by improving the energy efficiency level (XEP) to increase the efficiency of the use of lower energy sources, thereby ensuring the optimal allocation of resources.

[0067] Preferably, the equipment scheduling strategy formulation unit combines the fault risk index Rf and the energy efficiency level XEP to schedule and preventive maintain the equipment, and calculates and obtains the total risk index RTof of the equipment scheduling strategy;

[0068] Based on the total risk index RTof, energy efficiency level XEP, and production needs of the equipment scheduling strategy, formulate equipment operation and maintenance plans to ensure efficient and stable equipment operation.

[0069] The total risk index RTof of the equipment scheduling strategy is obtained using the following formula:

[0070]

[0071] In the formula, Rfj represents the failure risk index of the j-th device, Tj represents the operating time of the j-th device, δj represents the energy efficiency coefficient of the j-th device, and Qj represents the equipment load of the j-th device.

[0072] Preferably, the reporting and feedback module includes a report generation unit and a feedback unit;

[0073] The report generation unit collects data related to energy loss (ES), including energy efficiency level (XEP), energy cost, and equipment load (Q), and generates an energy loss (ES) analysis report, listing the energy efficiency status of the equipment and providing adjustment suggestions.

[0074] The feedback unit evaluates the current equipment scheduling strategy, analyzes the impact of the equipment scheduling strategy on energy efficiency, equipment load and failure risk, and generates an equipment scheduling strategy feedback report to provide management with suggestions and decision support on the scheduling strategy.

[0075] The enterprise energy intelligent optimization method based on Internet and big data analysis includes the following steps:

[0076] Step 1: This includes an energy data acquisition and preprocessing module that collects real-time data from the enterprise's energy equipment, including equipment operating status data, environmental factor data, and load data, and performs preprocessing, including data cleaning and standardization, to obtain dataset W.

[0077] Step 2: The energy efficiency analysis and loss detection module performs real-time analysis of the equipment's energy efficiency based on the collected dataset W to obtain the equipment's energy efficiency value PN; and through big data technology and machine learning, it analyzes the equipment's load fluctuation QB, temperature change ΔT, and energy loss ES to obtain the equipment failure probability Pgz.

[0078] Step 3: The fault prediction and risk assessment module uses AI algorithms to model the equipment operating status based on the obtained equipment energy efficiency value PN and equipment fault probability Pgz, and predicts the equipment fault risk; and calculates the equipment fault risk index Rf based on the actual power PS, load status data La and power fluctuation ΔP.

[0079] Step 4: The prediction model and trend analysis module uses the failure risk index Rf, energy loss ES, and environmental factor data to predict energy demand, forecast the trend and change pattern of energy consumption; and establishes a time series model to predict future energy demand XE and energy efficiency level XEP.

[0080] Step 5: The optimization scheduling and decision support module performs intelligent energy scheduling based on energy demand XE, energy efficiency level XEP, and fault risk index Rf, and formulates energy supply and equipment scheduling strategies.

[0081] Step Six: The Reporting and Feedback module is responsible for generating reports and feedback information, providing analysis reports on energy loss (ES) and equipment scheduling strategies, and feeding them back to management.

[0082] This invention provides a method and system for intelligent energy optimization in enterprises based on the Internet and big data analysis, which has the following beneficial effects:

[0083] (1) During system operation, the energy data acquisition and preprocessing module collects various data in real time from the enterprise's energy equipment, including equipment operating status, environmental factors, and load data, and performs preprocessing to ensure data accuracy and consistency. The energy efficiency analysis and loss detection module monitors equipment energy efficiency in real time, analyzes key parameters such as load fluctuations and temperature changes, and predicts energy loss and potential failure risks based on the dataset W. This real-time monitoring and prediction capability helps enterprises promptly identify potential problems such as energy waste and equipment failure, thereby enabling preventative maintenance and avoiding sudden downtime and equipment damage.

[0084] Through its energy efficiency analysis and loss detection modules and fault prediction and risk assessment modules, the system can identify energy efficiency degradation and waste in equipment, promptly detect inefficient equipment, and predict its failure probability using intelligent algorithms. This enables businesses to perform maintenance and adjustments before equipment failures occur, thereby reducing energy waste and mitigating the risk of energy efficiency degradation. Furthermore, based on big data technology and machine learning algorithms, the system can provide businesses with specific optimization measures to further improve energy utilization efficiency and avoid additional losses caused by improper equipment use or inadequate energy management.

[0085] (2) The Energy Loss Detection and Fault Prediction Unit calculates the energy loss ES of the equipment based on the difference between the actual power and the ideal power, and combines this with load fluctuations and temperature changes to predict faults. Through this module, the system can monitor the energy loss of equipment in real time, providing strong decision support for energy managers, helping enterprises optimize equipment operation and reduce energy waste. Combining big data analytics and machine learning algorithms, the system can predict potential faults based on the equipment's energy efficiency value PN, energy loss ES, load fluctuation QB, and temperature change ΔT, and calculate the equipment's fault probability Pgz. This means that enterprises can identify high-risk equipment in advance and perform preventative maintenance, avoiding production stoppages and economic losses caused by equipment failures.

[0086] (3) Through multi-level data collection, modeling and analysis, the intelligence and precision of the system are enhanced: The system can not only accurately capture the operating status of the equipment from multi-dimensional data such as equipment energy efficiency value PN, energy loss ES, load fluctuation QB and temperature change ΔT, but also use machine learning algorithms to optimize the risk prediction model and improve the accuracy of fault prediction.

[0087] The system dynamically predicts future energy demand (XE) and energy efficiency level (XE), and provides equipment scheduling suggestions based on the failure risk index (R), further improving energy utilization efficiency. The system's intelligent upgrade significantly reduces energy waste and equipment maintenance costs, improving enterprise productivity and economic benefits.

[0088] (4) By accurately predicting equipment failure risks and optimizing scheduling strategies, the system can effectively avoid excessive equipment operation or failure, reduce downtime, and improve production efficiency. Simultaneously, preventative maintenance strategies can reduce equipment repair costs and the risk of sudden failures. This reporting and feedback mechanism allows management to obtain key system operation data and trends in real time, helping decision-makers formulate more accurate energy scheduling and equipment management decisions. Through continuous optimization of feedback information, management can constantly adjust strategies to improve the overall operational efficiency and competitiveness of the enterprise. Attached Figure Description

[0089] Figure 1 This is a schematic diagram of the block diagram of the enterprise energy intelligent optimization system based on Internet and big data analysis of the present invention;

[0090] Figure 2 This is a schematic diagram illustrating the steps of the enterprise energy intelligent optimization method based on Internet and big data analysis of the present invention. Detailed Implementation

[0091] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0092] Example 1

[0093] This invention provides an enterprise energy intelligent optimization system based on the Internet and big data analysis. Please refer to [link / reference]. Figure 1 It includes modules for energy data acquisition and preprocessing, energy efficiency analysis and loss detection, fault prediction and risk assessment, prediction model and trend analysis, optimized scheduling and decision support, and reporting and feedback.

[0094] The energy data acquisition and preprocessing module collects real-time data from the enterprise's energy equipment, including equipment operating status data, environmental factor data, and load data, and performs preprocessing, including data cleaning and standardization, to obtain dataset W.

[0095] The energy efficiency analysis and loss detection module performs real-time analysis of the equipment's energy efficiency based on the collected dataset W to obtain the equipment's energy efficiency value PN; and through big data technology and machine learning, it analyzes the equipment's load fluctuation QB, temperature change ΔT, and energy loss ES to obtain the equipment failure probability Pgz.

[0096] The fault prediction and risk assessment module uses AI algorithms to model the equipment operating status based on the obtained equipment energy efficiency value PN and equipment fault probability Pgz, and predicts the equipment fault risk; and calculates the equipment fault risk index Rf based on the actual power PS, load status data La and power fluctuation ΔP.

[0097] The prediction model and trend analysis module predict energy demand based on the failure risk index Rf, energy loss ES, and environmental factor data, predicting the trend and change pattern of energy consumption; and establishes a time series model to predict future energy demand XE and energy efficiency level XEP.

[0098] The optimization scheduling and decision support module performs intelligent energy scheduling based on energy demand XE, energy efficiency level XEP, and fault risk index Rf, and formulates energy supply and equipment scheduling strategies.

[0099] The reporting and feedback module is responsible for generating reports and feedback information, providing analysis reports on energy loss (ES) and equipment scheduling strategies, and feeding them back to management.

[0100] In this embodiment, the optimized scheduling and decision support module utilizes energy demand forecasting and fault risk indices, combined with energy efficiency levels and load status data, to accurately predict and schedule an enterprise's energy demand. Through the intelligent scheduling system, enterprises can make more rational decisions regarding energy supply and equipment scheduling, ensuring that energy supply meets production needs while maximizing energy efficiency. This intelligent scheduling capability not only avoids energy oversupply or undersupply but also adjusts production plans based on equipment load and power fluctuations, reducing energy waste and equipment wear.

[0101] Through its fault prediction and risk assessment module, the system uses AI algorithms to model equipment operating status, predict equipment failure risks in advance, and provide decision support based on the failure risk index Rf. This not only avoids sudden equipment failures but also reduces downtime losses and improves equipment reliability and availability. Combined with analysis of energy consumption and environmental factors, the system can provide personalized equipment scheduling strategies to ensure equipment operates optimally, avoiding overload and inefficiency.

[0102] Example 2

[0103] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically: the energy data acquisition and preprocessing module includes a data acquisition unit and a data preprocessing unit;

[0104] The data acquisition unit collects equipment operating status data through a power detector, a voltage sensor, and a current sensor; collects environmental factor data through a temperature and humidity sensor; and collects load data through a load monitoring sensor. The equipment operating status data includes equipment power P, equipment voltage V, and equipment current I; the environmental factor data includes temperature T and humidity S; and the load data includes equipment load Q.

[0105] The data preprocessing unit cleans and standardizes the collected data to obtain dataset W. Cleaning includes using mean padding and interpolation to remove incomplete, abnormal, and invalid data. Standardization includes using the z-score standardization method to eliminate the influence of data dimensions.

[0106] The energy efficiency analysis and loss detection module includes an energy efficiency analysis and efficiency evaluation unit and an energy loss detection and fault prediction unit.

[0107] The energy efficiency analysis and efficiency evaluation unit evaluates the energy efficiency of the equipment based on the dataset W, obtains the equipment energy efficiency value PN, and judges the equipment operating status through the equipment energy efficiency value PN.

[0108] The energy efficiency value PN of the device is obtained by the following formula:

[0109]

[0110] In the formula, Q represents the equipment load; PL represents the ideal power of the equipment; and PS represents the actual power of the equipment.

[0111] The device operating status is obtained through the following methods:

[0112] When 50% < equipment energy efficiency value PN < 100%, it indicates that the equipment is operating normally;

[0113] When the energy efficiency value PN of the equipment is less than or equal to 50%, it indicates that the equipment is operating abnormally.

[0114] The energy loss detection and fault prediction unit uses big data analysis technology to detect the energy loss ES during equipment operation; the energy loss ES is obtained by multiplying the difference between the actual power PS and the ideal power PL of the equipment by the operating time.

[0115] Based on the equipment energy efficiency value PN, energy loss ES, load fluctuation QB and temperature change ΔT, and combined with machine learning algorithms, potential faults are predicted, and the equipment fault probability Pgz is obtained.

[0116] The load fluctuation QB is obtained by the ratio of the difference between the equipment load Q(t) at time t and the equipment load Q(t-1) at time t-1 to the time interval Δt.

[0117] The equipment failure probability Pgz is obtained using the following formula:

[0118]

[0119] In the formula, α1, α2 and α3 represent the ratio of equipment energy efficiency value PN to time interval Δt, the ratio of energy loss ES to load fluctuation QB and the weighting parameter of temperature change ΔT, respectively, and α1+α2+α3≤1, the specific values ​​are determined by the user, and exp represents the exponential function.

[0120] In this embodiment, the data acquisition unit accurately collects equipment operating status data, environmental factor data, and load data through a power detector, voltage sensor, current sensor, and temperature and humidity sensor. Load data collected by the load monitoring sensor reflects the equipment's workload, providing accurate input data for subsequent energy efficiency analysis. This allows the system to acquire comprehensive and high-quality data input, providing a solid data foundation for subsequent energy efficiency analysis and prediction. The data preprocessing unit cleans and standardizes the collected data to ensure high quality. Mean imputation and interpolation are used to handle missing and outlier values, avoiding erroneous analysis due to data issues. Furthermore, z-score standardization eliminates the influence of inconsistent parameter dimensions on the analysis results, ensuring more accurate and reliable results.

[0121] In the energy efficiency analysis and assessment unit, the system calculates the equipment's energy efficiency value (PN) using a formula and uses this value to assess the equipment's operating status in real time. Specifically, if the equipment's PN is between 50% and 100%, it indicates that the equipment is operating normally; while if the PN is ≤50%, it indicates that the equipment is operating abnormally. This real-time energy efficiency assessment mechanism helps companies quickly identify potential problems in equipment operation, make timely adjustments or maintenance, and prevent unnecessary energy waste caused by declining energy efficiency.

[0122] By predicting equipment failures, the system can predict the probability of failure based on real-time operating data and equipment status, and intelligently determine whether there are potential failure hazards in the equipment through machine learning algorithms. This proactive failure prediction helps companies take necessary corrective measures before failures occur, avoiding downtime losses caused by equipment failures and ensuring the continuity and stability of production.

[0123] Example 3

[0124] This embodiment is an explanation based on Embodiment 2. Please refer to it. Figure 1 Specifically: the fault prediction and risk assessment module includes a fault prediction unit and a fault risk index calculation unit;

[0125] The fault prediction unit establishes a fault risk model using the equipment energy efficiency value PN, the equipment fault probability Pgz, the actual power PS of the equipment, the load status data La, and the power fluctuation ΔP.

[0126] The load status data La is obtained through the following formula:

[0127]

[0128] In the formula, V represents the equipment voltage, I represents the equipment current, cosφ represents the power factor, and PL represents the ideal power of the equipment;

[0129] The power fluctuation ΔP is obtained by the ratio of the difference between the device power P(t) at time t and the device power P(t-1) at time t-1 to the time interval Δt.

[0130] AI algorithms are used to predict equipment failure risk. Historical data is used to train the failure risk model to obtain parameters β1, β2, β3, β4 and β5, which are then input into the failure risk model to predict the failure risk index Rf.

[0131] The formula for the failure risk model is:

[0132]

[0133] In the formula, β1, β2, β3, β4 and β5 represent the weighting coefficients of equipment energy efficiency value PN, equipment failure probability Pgz, actual power PS, load state data La and power fluctuation ΔP, respectively.

[0134] The fault risk index calculation unit evaluates the current operating status of the equipment based on the obtained equipment fault probability Pgz, power fluctuation ΔP, actual power PS and ideal power PL through the fault risk model, obtains the fault risk index Rf, and compares it with the preset risk threshold TRf to determine the current operating status of the equipment.

[0135] The failure risk index Rf is obtained using the following formula:

[0136]

[0137] The current operating status of the device is obtained by matching in the following way:

[0138] When the fault risk index Rf ≥ the risk threshold TRf, it indicates that the equipment is in an abnormal operating state, prompting maintenance and replacement of the equipment;

[0139] When the fault risk index Rf < the risk threshold TRf, it indicates that the equipment is operating normally, and the equipment monitoring status is saved.

[0140] The prediction model and trend analysis module includes a data extraction unit and an energy demand prediction and energy efficiency modeling unit.

[0141] The data extraction unit normalizes the acquired fault risk index Rf, energy loss ES, and environmental factor data, including temperature T and humidity S, to form a model training set Y = {RF, ES, T, S}.

[0142] The energy demand forecasting and energy efficiency modeling unit establishes a regression model based on historical data and training set Y to predict future energy demand XE.

[0143] The energy demand XE is obtained using the following formula:

[0144]

[0145] In the formula, XE(t+1) represents the energy demand at time t+1, η represents the parameters of the regression model, Yi(t) represents the i-th data in the training set Y at time t, and θi represents the regression coefficient of the i-th data in the training set Y.

[0146] Based on the energy demand XE and the training set Y, the energy efficiency level XEP is calculated and compared with the preset energy consumption threshold Txep to determine the energy consumption status of the operating equipment.

[0147] The energy efficiency level XEP is obtained using the following formula:

[0148]

[0149] In the formula, ΔT represents the temperature change and ΔS represents the humidity change;

[0150] The energy consumption status of the operating equipment is obtained through the following methods:

[0151] When the energy efficiency level XEP is greater than or equal to the energy consumption threshold Txep, it indicates that the energy consumption status of the operating equipment is normal.

[0152] When the energy efficiency level XEP < energy consumption threshold Txep, it indicates that the energy consumption status of the operating equipment is abnormal.

[0153] In this embodiment, a more comprehensive fault risk model is established by combining the equipment's energy efficiency value (PN), equipment failure probability (Pgz), actual power (PS), load status data (La), and power fluctuation (ΔP). The model utilizes AI algorithms to train on historical data, optimizing the weight settings of each parameter to achieve accurate prediction of equipment failure risk. The fault risk index (Rf) is calculated using the fault risk model and compared with a preset risk threshold (TRf) to clarify the current operating status of the equipment. When the equipment malfunctions, the system can quickly prompt for repair or replacement; when the equipment is operating normally, the system continues monitoring to avoid unnecessary maintenance operations.

[0154] By calculating the load status data La and power fluctuation Δ of the equipment using formulas, dynamic monitoring of the equipment's operating status is achieved. Real-time analysis of load status and power fluctuations helps enterprises monitor the stability of equipment operation and provides support for energy efficiency analysis and scheduling optimization, effectively reducing energy waste and equipment damage caused by load fluctuations.

[0155] This predictive method, based on historical data and training sets, can help companies plan their energy supply in advance, optimize energy dispatch strategies, avoid energy shortages or surpluses, and provide a scientific basis for assessing equipment energy consumption status.

[0156] This embodiment enhances the intelligence and precision of the system through multi-level data acquisition, modeling, and analysis: the system can not only accurately capture the operating status of equipment from multi-dimensional data such as load status, power fluctuation, and energy loss, but also use machine learning algorithms to optimize the risk prediction model and improve the accuracy of fault prediction.

[0157] The system dynamically predicts future energy demand (XE) and energy efficiency level (XE), and provides equipment scheduling suggestions based on the failure risk index (R), further improving energy utilization efficiency. The system's intelligent upgrade significantly reduces energy waste and equipment maintenance costs, improving enterprise productivity and economic benefits.

[0158] Example 4

[0159] This embodiment is an explanation based on Embodiment 3. Please refer to it. Figure 1 Specifically: the optimized scheduling and decision support module includes an energy scheduling optimization unit and an equipment scheduling strategy formulation unit;

[0160] The energy dispatch optimization unit assesses the current energy demand of the system based on the real-time collected energy demand XE, predicts future energy demand fluctuations, calculates the current energy usage efficiency Ns in conjunction with the energy efficiency level XEP, and proposes an energy adjustment scheme Z.

[0161] The energy efficiency Ns is obtained by multiplying the energy efficiency level XEP by the power fluctuation ΔP.

[0162] The energy adjustment scheme Z is obtained through the following formula:

[0163]

[0164] In the formula, XEI represents the energy demand of the first type of energy, XEPI represents the energy efficiency level of the first type of energy, PI represents the supply capacity of the first type of energy, CI represents the unit cost of the first type of energy, λI represents the energy efficiency adjustment coefficient of the first type of energy, and N represents the total amount of energy.

[0165] The equipment scheduling strategy formulation unit combines the fault risk index Rf and the energy efficiency level XEP to schedule and preventive maintain the equipment, and calculates and obtains the total risk index RTof of the equipment scheduling strategy.

[0166] The total risk index RTof of the equipment scheduling strategy is obtained using the following formula:

[0167]

[0168] In the formula, Rfj represents the failure risk index of the j-th device, Tj represents the operating time of the j-th device, δj represents the energy efficiency coefficient of the j-th device, and Qj represents the equipment load of the j-th device.

[0169] The reporting and feedback module includes a report generation unit and a feedback unit;

[0170] The report generation unit collects data related to energy loss (ES), including energy efficiency level (XEP), energy cost, and equipment load (Q), and generates an energy loss (ES) analysis report, listing the energy efficiency status of the equipment and providing adjustment suggestions.

[0171] The feedback unit evaluates the current equipment scheduling strategy, analyzes the impact of the equipment scheduling strategy on energy efficiency, equipment load and failure risk, and generates an equipment scheduling strategy feedback report to provide management with suggestions and decision support on the scheduling strategy.

[0172] In this embodiment, the energy dispatch optimization unit calculates the current energy utilization efficiency Ns based on real-time collected energy demand XE and energy efficiency level XEP, and predicts future fluctuations in energy demand. This enables the system to adjust energy supply in a timely manner in the event of energy demand fluctuations, and proposes energy adjustment schemes Z to cope with energy changes and optimize resource allocation.

[0173] By dynamically analyzing energy demand and energy efficiency levels, the system can minimize energy waste, optimize energy supply and consumption, reduce energy costs for businesses, and improve energy efficiency. Especially in situations with significant energy fluctuations, the system can respond quickly, reducing the risk of energy shortages or overconsumption and ensuring the company's continued operation.

[0174] The system's intelligence and automation make energy management more precise and efficient, reducing the risks of human decision-making while enhancing the flexibility and sustainability of energy use. Through accurate forecasting and dynamic adjustments, businesses can reduce energy costs and improve equipment reliability, ultimately driving overall operational efficiency. The system provides businesses with a scientific basis for decision-making, making energy management more transparent and efficient, thereby promoting higher levels of sustainable development. By providing early warnings of energy waste and dynamically optimizing energy dispatch strategies, businesses can reduce costs while minimizing environmental impact, enhancing brand image and market competitiveness.

[0175] Example 5

[0176] For enterprise energy intelligent optimization methods based on internet and big data analysis, please refer to [reference needed]. Figure 2 Specifically, it includes the following steps:

[0177] Step 1: This includes an energy data acquisition and preprocessing module that collects real-time data from the enterprise's energy equipment, including equipment operating status data, environmental factor data, and load data, and performs preprocessing, including data cleaning and standardization, to obtain dataset W.

[0178] Step 2: The energy efficiency analysis and loss detection module performs real-time analysis of the equipment's energy efficiency based on the collected dataset W to obtain the equipment's energy efficiency value PN; and through big data technology and machine learning, it analyzes the equipment's load fluctuation QB, temperature change ΔT, and energy loss ES to obtain the equipment failure probability Pgz.

[0179] Step 3: The fault prediction and risk assessment module uses AI algorithms to model the equipment operating status based on the obtained equipment energy efficiency value PN and equipment fault probability Pgz, and predicts the equipment fault risk; and calculates the equipment fault risk index Rf based on the actual power PS, load status data La and power fluctuation ΔP.

[0180] Step 4: The prediction model and trend analysis module uses the failure risk index Rf, energy loss ES, and environmental factor data to predict energy demand, forecast the trend and change pattern of energy consumption; and establishes a time series model to predict future energy demand XE and energy efficiency level XEP.

[0181] Step 5: The optimization scheduling and decision support module performs intelligent energy scheduling based on energy demand XE, energy efficiency level XEP, and fault risk index Rf, and formulates energy supply and equipment scheduling strategies.

[0182] Step Six: The Reporting and Feedback module is responsible for generating reports and feedback information, providing analysis reports on energy loss (ES) and equipment scheduling strategies, and feeding them back to management.

[0183] In this embodiment, steps one through six enable real-time monitoring of the enterprise's energy equipment operation status, collecting key data including equipment power, temperature, humidity, and load to ensure data real-time performance and accuracy. Data cleaning and standardization effectively removes abnormal data and noise, providing a high-quality data source for subsequent analysis. After cleaning and standardization, errors caused by data quality issues are avoided, laying a reliable foundation for subsequent energy efficiency analysis, fault prediction, and optimized scheduling. Real-time data acquisition and preprocessing help enterprises promptly identify potential problems in energy use, further improving the efficiency and accuracy of energy management.

[0184] In the energy efficiency analysis and loss detection module, the energy efficiency value (PN) of the equipment can be calculated by analyzing real-time data. Big data technology and machine learning models are used to assess load fluctuations, temperature changes, and energy losses. By predicting the equipment's failure probability (Pgz), potential failures can be predicted in advance. This module effectively utilizes big data analytics and machine learning technologies to improve the accuracy and real-time performance of energy efficiency analysis. Through the prediction of equipment energy efficiency values ​​and failure probabilities, enterprises can promptly detect energy efficiency declines and potential equipment failures, avoiding energy waste and equipment damage, and ensuring efficient equipment operation and energy conservation.

[0185] In the fault prediction and risk assessment module, AI algorithms are used to model the equipment's operating status. Based on the equipment's energy efficiency value (PN) and failure probability (Pgz), the module predicts the equipment's failure risk and calculates the failure risk index (Rf). Using this predictive data, companies can promptly schedule maintenance and repairs, preventing downtime and production interruptions caused by equipment failures. This module makes equipment management more intelligent, avoiding the reliance on periodic inspections in traditional equipment maintenance. Instead, it relies on real-time data and predictive models for preventative maintenance. Through accurate fault prediction and risk assessment, companies can significantly reduce equipment failure rates, decrease maintenance costs, and improve equipment availability and reliability.

[0186] The reporting and feedback module provides management with detailed analysis of energy consumption and equipment scheduling strategies through automatically generated energy loss analysis reports and equipment scheduling strategy feedback reports. These reports not only help management assess current energy usage and equipment status but also provide reasonable improvement suggestions to support decision-making. The reporting and feedback module offers enterprises a transparent, real-time energy management system, helping management make informed decisions based on data. The adjustment suggestions in the reports can promote continuous optimization of energy management, further reducing energy waste and operating costs, and enhancing the enterprise's competitiveness and sustainable development capabilities.

[0187] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An enterprise energy intelligent optimization system based on the Internet and big data analysis, characterized by: It includes modules for energy data acquisition and preprocessing, energy efficiency analysis and loss detection, fault prediction and risk assessment, prediction model and trend analysis, optimized scheduling and decision support, and reporting and feedback. The energy data acquisition and preprocessing module collects real-time data from the enterprise's energy equipment, including equipment operating status data, environmental factor data, and load data, and performs preprocessing, including data cleaning and standardization, to obtain dataset W. The energy efficiency analysis and loss detection module performs real-time analysis of the equipment's energy efficiency based on the collected dataset W to obtain the equipment's energy efficiency value PN. And by using big data technology and machine learning, we can analyze the load fluctuation QB, temperature change ΔT and energy loss ES of the equipment to obtain the equipment failure probability Pgz; The fault prediction and risk assessment module uses AI algorithms to model the equipment operating status based on the obtained equipment energy efficiency value PN and equipment fault probability Pgz, and predicts the equipment fault risk; and calculates the equipment fault risk index Rf based on the actual power PS, load status data La and power fluctuation ΔP. The prediction model and trend analysis module predict energy demand based on the failure risk index Rf, energy loss ES, and environmental factor data, predicting the trend and change pattern of energy consumption; and establishes a time series model to predict future energy demand XE and energy efficiency level XEP. The optimization scheduling and decision support module performs intelligent energy scheduling based on energy demand XE, energy efficiency level XEP, and fault risk index Rf, and formulates energy supply and equipment scheduling strategies. The reporting and feedback module is responsible for generating reports and feedback information, providing analysis reports on energy loss (ES) and equipment scheduling strategies, and feeding them back to management.

2. The enterprise energy intelligent optimization system based on Internet and big data analysis according to claim 1, characterized in that: The energy data acquisition and preprocessing module includes a data acquisition unit and a data preprocessing unit; The data acquisition unit collects equipment operating status data through a power detector, a voltage sensor, and a current sensor; collects environmental factor data through a temperature and humidity sensor; and collects load data through a load monitoring sensor. The equipment operating status data includes equipment power P, equipment voltage V, and equipment current I; the environmental factor data includes temperature T and humidity S; and the load data includes equipment load Q. The data preprocessing unit cleans and standardizes the collected data to obtain dataset W. Cleaning includes removing incomplete, abnormal, and invalid data using mean padding and interpolation. Standardization includes using the z-score standardization method.

3. The enterprise energy intelligent optimization system based on Internet and big data analysis according to claim 2, characterized in that: The energy efficiency analysis and loss detection module includes an energy efficiency analysis and efficiency evaluation unit and an energy loss detection and fault prediction unit. The energy efficiency analysis and efficiency evaluation unit evaluates the energy efficiency of the equipment based on the dataset W, calculates and obtains the equipment energy efficiency value PN, and judges the equipment operating status through the equipment energy efficiency value PN. The energy efficiency value PN of the device is obtained by the following formula: In the formula, Q represents the equipment load; PL represents the ideal power of the equipment; and PS represents the actual power of the equipment. The device operating status is obtained through the following methods: When 50% < equipment energy efficiency value PN < 100%, it indicates that the equipment is operating normally; When the energy efficiency value PN of the equipment is less than or equal to 50%, it indicates that the equipment is operating abnormally. The energy loss detection and fault prediction unit uses big data analysis technology to detect the energy loss ES during equipment operation; the energy loss ES is obtained by multiplying the difference between the actual power PS and the ideal power PL of the equipment by the operating time. Based on the equipment energy efficiency value PN, energy loss ES, load fluctuation QB and temperature change ΔT, and combined with machine learning algorithms, potential faults are predicted, and the equipment fault probability Pgz is obtained. The load fluctuation QB is obtained by the ratio of the difference between the equipment load Q(t) at time t and the equipment load Q(t-1) at time t-1 to the time interval Δt. The equipment failure probability Pgz is obtained using the following formula: In the formula, α1, α2 and α3 represent the ratio of equipment energy efficiency value PN to time interval Δt, the ratio of energy loss ES to load fluctuation QB and the weighting parameter of temperature change ΔT, respectively, and exp represents the exponential function.

4. The enterprise energy intelligent optimization system based on Internet and big data analysis according to claim 2, characterized in that: The fault prediction and risk assessment module includes a fault prediction unit and a fault risk index calculation unit. The fault prediction unit establishes a fault risk model using the equipment energy efficiency value PN, the equipment fault probability Pgz, the actual power PS of the equipment, the load status data La, and the power fluctuation ΔP. The load status data La is obtained through the following formula: In the formula, V represents the equipment voltage, I represents the equipment current, cosφ represents the power factor, and PL represents the ideal power of the equipment; The power fluctuation ΔP is obtained by the ratio of the difference between the device power P(t) at time t and the device power P(t-1) at time t-1 to the time interval Δt. AI algorithms are used to predict equipment failure risk. Historical data is used to train the failure risk model to obtain parameters β1, β2, β3, β4 and β5, which are then input into the failure risk model to predict the failure risk index Rf. The formula for the failure risk model is: In the formula, β1, β2, β3, β4 and β5 represent the weighting coefficients of equipment energy efficiency value PN, equipment failure probability Pgz, actual power PS, load state data La and power fluctuation ΔP, respectively.

5. The enterprise energy intelligent optimization system based on Internet and big data analysis according to claim 4, characterized in that: The fault risk index calculation unit evaluates the current operating status of the equipment based on the obtained equipment fault probability Pgz, power fluctuation ΔP, actual power PS and ideal power PL through the fault risk model, obtains the fault risk index Rf, and compares it with the preset risk threshold TRf to determine the current operating status of the equipment. The failure risk index Rf is obtained using the following formula: The current operating status of the device is obtained by matching in the following way: When the fault risk index Rf ≥ the risk threshold TRf, it indicates that the equipment is in an abnormal operating state, prompting maintenance and replacement of the equipment; When the fault risk index Rf < the risk threshold TRf, it indicates that the equipment is operating normally, and the equipment monitoring status is saved.

6. The enterprise energy intelligent optimization system based on Internet and big data analysis according to claim 1, characterized in that: The prediction model and trend analysis module includes a data extraction unit and an energy demand prediction and energy efficiency modeling unit. The data extraction unit normalizes the acquired fault risk index Rf, energy loss ES, and environmental factor data, including temperature T and humidity S, to form a model training set Y = {RF, ES, T, S}. The energy demand forecasting and energy efficiency modeling unit establishes a regression model based on historical data and training set Y to predict future energy demand XE. The energy demand XE is obtained using the following formula: In the formula, XE(t+1) represents the energy demand at time t+1, η represents the parameters of the regression model, Yi(t) represents the i-th data in the training set Y at time t, and θi represents the regression coefficient of the i-th data in the training set Y. Based on the energy demand XE and the training set Y, the energy efficiency level XEP is calculated and compared with the preset energy consumption threshold Txep to determine the energy consumption status of the operating equipment. The energy efficiency level XEP is obtained using the following formula: In the formula, ΔT represents the temperature change and ΔS represents the humidity change; The energy consumption status of the operating equipment is obtained through the following methods: When the energy efficiency level XEP is greater than or equal to the energy consumption threshold Txep, it indicates that the energy consumption status of the operating equipment is normal. When the energy efficiency level XEP < energy consumption threshold Txep, it indicates that the energy consumption status of the operating equipment is abnormal.

7. The enterprise energy intelligent optimization system based on Internet and big data analysis according to claim 6, characterized in that: The optimized scheduling and decision support module includes an energy scheduling optimization unit and an equipment scheduling strategy formulation unit; The energy dispatch optimization unit assesses the current energy demand of the system based on the real-time collected energy demand XE, predicts future energy demand fluctuations, calculates the current energy usage efficiency Ns in conjunction with the energy efficiency level XEP, and proposes an energy adjustment scheme Z. The energy efficiency Ns is obtained by multiplying the energy efficiency level XEP by the power fluctuation ΔP. The energy adjustment scheme Z is obtained through the following formula: In the formula, XEI represents the energy demand of the first type of energy, XEPI represents the energy efficiency level of the first type of energy, PI represents the supply capacity of the first type of energy, CI represents the unit cost of the first type of energy, λI represents the energy efficiency adjustment coefficient of the first type of energy, and N represents the total amount of energy.

8. The enterprise energy intelligent optimization system based on Internet and big data analysis according to claim 7, characterized in that: The equipment scheduling strategy formulation unit combines the fault risk index Rf and the energy efficiency level XEP to schedule and preventive maintain the equipment, and calculates and obtains the total risk index RTof of the equipment scheduling strategy. The total risk index RTof of the equipment scheduling strategy is obtained using the following formula: In the formula, Rfj represents the failure risk index of the j-th device, Tj represents the operating time of the j-th device, δj represents the energy efficiency coefficient of the j-th device, and Qj represents the equipment load of the j-th device.

9. The enterprise energy intelligent optimization system based on Internet and big data analysis according to claim 3, characterized in that: The reporting and feedback module includes a report generation unit and a feedback unit; The report generation unit collects data related to energy loss (ES), including energy efficiency level (XEP), energy cost, and equipment load (Q), and generates an energy loss (ES) analysis report, listing the energy efficiency status of the equipment and providing adjustment suggestions. The feedback unit evaluates the current equipment scheduling strategy, analyzes the impact of the equipment scheduling strategy on energy efficiency, equipment load and failure risk, and generates an equipment scheduling strategy feedback report to provide management with suggestions and decision support on the scheduling strategy.

10. A method for intelligent energy optimization of enterprises based on Internet and big data analysis, applied to the intelligent energy optimization system for enterprises based on Internet and big data analysis as described in any one of claims 1 to 9, characterized in that: Includes the following steps: Step 1: This includes an energy data acquisition and preprocessing module that collects real-time data from the enterprise's energy equipment, including equipment operating status data, environmental factor data, and load data, and performs preprocessing, including data cleaning and standardization, to obtain dataset W. Step 2: The energy efficiency analysis and loss detection module performs real-time analysis of the equipment's energy efficiency based on the collected dataset W to obtain the equipment's energy efficiency value PN; And by using big data technology and machine learning, we can analyze the load fluctuation QB, temperature change ΔT and energy loss ES of the equipment to obtain the equipment failure probability Pgz; Step 3: The fault prediction and risk assessment module uses AI algorithms to model the equipment operating status based on the obtained equipment energy efficiency value PN and equipment fault probability Pgz, and predicts the equipment fault risk; and calculates the equipment fault risk index Rf based on the actual power PS, load status data La and power fluctuation ΔP. Step 4: The prediction model and trend analysis module uses the failure risk index Rf, energy loss ES, and environmental factor data to predict energy demand, forecast the trend and change pattern of energy consumption; and establishes a time series model to predict future energy demand XE and energy efficiency level XEP. Step 5: The optimization scheduling and decision support module performs intelligent energy scheduling based on energy demand XE, energy efficiency level XEP, and fault risk index Rf, and formulates energy supply and equipment scheduling strategies. Step Six: The Reporting and Feedback module is responsible for generating reports and feedback information, providing analysis reports on energy loss (ES) and equipment scheduling strategies, and feeding them back to management.

Images