Equipment energy efficiency optimization method and system based on factory data

Abstract

The invention discloses an equipment energy efficiency optimization method and system based on factory affair data, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring equipment operation parameters, vibration energy data and user behavior information in real time, and constructing a three-dimensional feature matrix; analyzing the vibration energy data and the user behavior information to respectively obtain a vibration energy potential value and a user behavior compliance degree; the vibration energy potential value and the user behavior compliance degree are incorporated into an energy efficiency optimization objective function, and an equipment collaboration strategy is dynamically generated; and obtaining equipment fault parameters and external environment parameters, quantifying the influence of the equipment health state and the external environment change on the energy efficiency, dynamically adjusting the energy efficiency optimization objective function, and generating an equipment collaborative optimization strategy for equipment energy efficiency optimization management. According to the invention, a whole-process closed loop from data perception to intelligent decision making is realized, and intelligence and sustainability of equipment energy efficiency management are finally realized in a complex dynamic environment.

Description

Technical Field

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a method and system for optimizing equipment energy efficiency based on factory data. Background Art

[0002] Plant management data refers to a collection of data related to the operation, maintenance, energy, environment, and safety management of factories or production facilities. It is used to ensure a stable production environment, optimize resource allocation, and improve operational efficiency. Optimizing equipment energy efficiency based on plant management data is a key path for modern industry to improve energy efficiency, reduce operating costs, and achieve green manufacturing. Its core goal is to achieve intelligent, green, and safe factory management.

[0003] Traditional methods for optimizing device energy efficiency focus solely on a single parameter, ignoring the synergistic influence of external factors. This leads to data silos and a lack of multi-dimensional correlation. Furthermore, the resulting energy efficiency optimization objective functions are often based on historical data or fixed rules, making them difficult to adapt to dynamic environmental changes. This leaves room for improvement. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for optimizing equipment energy efficiency based on plant affairs data, so as to solve the problems raised in the above background technology.

[0005] In the first aspect, the present application provides a method for optimizing equipment energy efficiency based on plant data, which adopts the following technical solutions:

[0006] Collect equipment operating parameters, vibration energy data, and user behavior information in real time, align timestamps, and construct a three-dimensional feature matrix;

[0007] Analyze vibration energy data and user behavior information to obtain vibration energy potential value and user behavior compliance respectively;

[0008] Incorporating vibration energy potential and user behavior compliance into the energy efficiency optimization objective function, dynamically generating device collaboration strategies, and obtaining the optimal device collaboration path;

[0009] Obtain equipment fault parameters and external environment parameters, quantify the impact of equipment health status and external environment changes on energy efficiency, dynamically adjust the energy efficiency optimization objective function, and generate equipment collaborative optimization strategies for equipment energy efficiency optimization management.

[0010] Preferably, the steps of analyzing the vibration energy data and the user behavior information to obtain the vibration energy potential value and the user behavior compliance are as follows:

[0011] Preprocessing the vibration energy data to obtain standard vibration energy data, wherein the standard vibration energy data includes an angular frequency w and an acceleration amplitude A;

[0012] By formula The vibration energy density E is calculated, where m is the mass of the vibration equipment;

[0013] Based on the vibration energy density E, the formula The electric energy that can be recovered per unit time is calculated, that is, the vibration energy potential value P, where: is the energy conversion efficiency, i.e., the electromagnetic conversion efficiency;

[0014] Compare the vibration energy potential value with the preset vibration energy threshold. If the vibration energy potential value exceeds the preset vibration energy threshold, the equipment will vibrate abnormally and trigger a fault alarm.

[0015] Analyze user behavior information to obtain user behavior compliance.

[0016] Preferably, the steps of analyzing user behavior information to obtain user behavior compliance are as follows:

[0017] The user behavior information includes the number of device operations F1 performed by the user per unit time, the parameter adjustment amplitude A1 for each operation, and the difference B1 between the device task priority set by the user and the priority recommended by the system;

[0018] Define the safe operation frequency threshold F max , through the formula F=1-(F1 / F max )×n1 is used to calculate the operating frequency compliance F, where n1 is the weight coefficient and is not equal to zero;

[0019] Define parameter adjustment amplitude threshold A max , by the formula A=1-(A1 / A max )×n2 is used to calculate the parameter adjustment compliance A, where n2 is the weight coefficient and is not equal to zero;

[0020] The device task priority matching degree B set by the user is calculated using the formula B=1-B1×n3, where n3 is the weight coefficient and is not equal to zero;

[0021] The user behavior compliance is calculated based on the operation frequency compliance F, parameter adjustment range compliance A, and device task priority matching B.

[0022] Preferably, the step of calculating the user behavior compliance by comprehensively considering the operation frequency compliance F, the parameter adjustment range compliance A, and the device task priority matching degree B is specifically as follows:

[0023] The user behavior compliance D is calculated by weighting the operation frequency compliance F, the parameter adjustment range compliance A, and the device task priority matching B using the formula D=F×n4+A×n5+B×n6.

[0024] Set the compliance threshold range [d1, d2] and compare the user behavior compliance D with the compliance threshold range;

[0025] If the user behavior compliance D is in [d1, d2], the user behavior has a minor violation, triggering a warning and a minor punishment;

[0026] If the user behavior compliance D is in [0,d1], the user behavior is seriously in violation, triggering mandatory penalties and permission restrictions.

[0027] Preferably, the vibration energy potential value and user behavior compliance are incorporated into the energy efficiency optimization objective function, and the steps of dynamically generating the device collaboration strategy are specifically as follows:

[0028] Normalize the vibration energy potential value P , get the standard value of vibration energy potential P0;

[0029] Constructing equipment energy consumption optimization objective function , where P i is the real-time energy consumption of device i, is the energy conversion efficiency, i.e., the electromagnetic conversion efficiency;

[0030] According to the user behavior compliance, the user behavior compliance penalty term D0 is calculated by the formula D0=1-D;

[0031] Extract vibration energy density E and construct a comprehensive objective function for equipment energy efficiency optimization , where w1 and w2 are weight coefficients and both are not equal to zero;

[0032] Based on the comprehensive objective function, the comprehensive objective function f is selected 总 The path with the smallest value is the global optimal path, and the device collaborative optimization path is obtained.

[0033] Preferably, the steps of obtaining equipment fault parameters and external environment parameters, quantifying the impact of equipment health status and external environment changes on energy efficiency, dynamically adjusting the energy efficiency optimization objective function, and generating equipment collaborative optimization strategies for equipment energy efficiency optimization management are specifically as follows:

[0034] Obtain equipment failure parameters, which include the number of equipment failures g and the equipment operating time t, and calculate the equipment health K using the formula K=1-g / t;

[0035] Acquiring external environmental parameters, wherein the external environmental parameters include an ambient temperature parameter T and an energy price parameter J;

[0036] Establish the mapping relationship between equipment failure parameters, external environment parameters and equipment energy efficiency to obtain the energy efficiency attenuation model ,in is the benchmark energy efficiency, k is the impact factor, v1 and v2 are weight coefficients, and both are not equal to zero;

[0037] According to the energy efficiency attenuation model, the comprehensive objective function of equipment energy efficiency optimization is dynamically adjusted to generate equipment collaborative optimization strategy for equipment energy efficiency optimization management.

[0038] Preferably, according to the energy efficiency attenuation model, the comprehensive objective function of the equipment energy efficiency optimization is dynamically adjusted to generate the equipment collaborative optimization strategy for the steps of equipment energy efficiency optimization management, specifically:

[0039] Obtain predicted temperature parameters and predicted electricity price parameters within a set future time period, input the predicted temperature parameters and predicted electricity price parameters into the energy efficiency attenuation model, and generate a predicted energy efficiency curve;

[0040] Set an energy efficiency attenuation threshold, extract the period in the predicted energy efficiency curve where the energy efficiency drops by more than the set energy efficiency attenuation threshold as a high-risk period, and trigger an early warning signal;

[0041] Based on early warning signals, identify non-critical production equipment in the equipment collaborative optimization path and shut down the operation of non-critical production equipment;

[0042] At the same time, the comprehensive objective function of equipment energy efficiency optimization is dynamically adjusted to generate equipment collaborative optimization strategies for equipment energy efficiency optimization management.

[0043] Preferably, the steps of dynamically adjusting the comprehensive objective function of equipment energy efficiency optimization and generating equipment collaborative optimization strategies for equipment energy efficiency optimization management are as follows:

[0044] Obtain the carbon emission cost parameter C, extract the ambient temperature parameter T and the energy electricity price parameter J, and define the environmental impact factor H = v3 × T + v4 × J + v5 × C, where v3, v4, and v5 are all weight coefficients, and none of them are equal to zero;

[0045] Extracting benchmark performance , vibration energy density E and user behavior compliance penalty term D0, dynamically adjust the comprehensive objective function of equipment energy efficiency optimization, and obtain the standard objective function of equipment energy efficiency optimization ;

[0046] Based on the standard objective function, the standard objective function f is selected 标The path with the largest value is the global optimal path, and the device collaborative standard path is obtained for device energy efficiency optimization management.

[0047] Secondly, the present application provides an equipment energy efficiency optimization system based on plant affairs data, which adopts the following technical solutions:

[0048] An equipment energy efficiency optimization system based on plant affairs data, comprising:

[0049] Multi-source data acquisition module collects equipment operating parameters, vibration energy data, and user behavior information in real time, aligns timestamps, and constructs a three-dimensional feature matrix;

[0050] The vibration energy and user behavior analysis module analyzes vibration energy data and user behavior information to obtain vibration energy potential value and user behavior compliance respectively;

[0051] The device collaboration strategy generation module incorporates vibration energy potential value and user behavior compliance into the energy efficiency optimization objective function, dynamically generates device collaboration strategies, and obtains the optimal device collaboration path;

[0052] The equipment collaborative optimization strategy generation module obtains equipment fault parameters and external environment parameters, quantifies the impact of equipment health status and external environment changes on energy efficiency, dynamically adjusts the energy efficiency optimization objective function, and generates equipment collaborative optimization strategies for equipment energy efficiency optimization management.

[0053] In summary, this application includes at least one of the following beneficial technical effects:

[0054] 1. Integrate device status, vibration energy, and user behavior into a unified multi-dimensional data structure for subsequent analysis and modeling, breaking the limitations of traditional single-dimensional analysis and integrating device, environmental, and human factors to provide comprehensive data support for energy efficiency optimization. Vibration energy data identifies energy loss points during device operation and quantifies the device's energy efficiency under different operating conditions. User behavior is analyzed, and a rules engine is used to determine whether user operations comply with energy-saving regulations. Feedback is provided to users, encouraging them to adjust their operating habits to reduce energy consumption. This achieves a dual energy efficiency improvement path of "device optimization" and "user guidance," avoiding the global efficiency loss caused by independent optimization of single devices. Device health is assessed using fault parameters to predict the impact of potential faults on energy efficiency. When device health declines, device lifespan is prioritized over energy efficiency. Environmental forecasting predicts future impacts and proactively adjusts strategies, enabling the system to adapt to uncertainties such as device aging and environmental changes, avoiding unexpected factors that could cause energy efficiency optimization failures. It also balances short-term energy efficiency improvements with long-term device health, extending device lifespan and reducing maintenance costs. Achieve a closed loop of the entire process from data perception to intelligent decision-making, and ultimately achieve optimal management of equipment energy efficiency in complex and dynamic environments.

[0055] 2. Calculate the vibration energy density through a formula, convert the vibration signal into an energy index, and intuitively reflect the intensity of the equipment's vibration energy, providing a quantitative basis for energy recovery or fault diagnosis. Abnormally high-frequency or low-frequency energy peaks may correspond to specific faults. The formula is used to calculate the recoverable electrical energy per unit time, quantify the potential for the equipment's vibration energy to be converted into electrical energy, guide the deployment of the energy recovery system, and install vibration power generation devices in high-potential areas. Compare the calculated P with the preset threshold, and quickly identify abnormal vibrations through threshold comparison to avoid further damage to the equipment. Intervention measures can be taken before the fault expands, reducing maintenance costs and the risk of production interruptions. Analyze user operation records through a rule engine to quantify whether user behavior complies with energy-saving specifications, reduce energy waste caused by human operations, provide feedback through compliance scores, and encourage users to optimize their operating habits and improve overall energy efficiency.

[0056] 3. Obtain the predicted temperature parameters and electricity price parameters for a set time period in the future through meteorological forecasts and the electricity market, input the predicted temperature parameters and electricity price parameters into the energy efficiency attenuation model, and obtain the predicted energy efficiency curve for the future period. Identify the energy efficiency decline trend in advance through the predicted data to avoid energy efficiency losses caused by sudden environmental changes or electricity price fluctuations. Set energy efficiency attenuation thresholds based on historical data or business needs, identify periods of significant energy efficiency decline in advance, avoid passive responses, and reduce the impact of sudden risks on production. Distinguish between mission-critical and mission-critical production equipment, that is, core equipment and auxiliary and spare equipment of the production line, and shut down the operation of non-critical equipment during high-risk periods to ensure that critical equipment can still operate stably during high-risk periods, while reducing unnecessary energy consumption and significantly reducing operating costs. Add the constraints of high-risk energy efficiency periods to the original comprehensive objective function, generate a new objective function, and achieve global energy efficiency optimization through iterative optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic diagram of the specific steps of an embodiment of an equipment energy efficiency optimization method based on factory affairs data of the present invention.

[0058] Figure 2 This is a module connection diagram of an embodiment of an equipment energy efficiency optimization system based on factory affairs data of the present invention. DETAILED DESCRIPTION

[0059] Below is a combination of the embodiments and Figure 1-Figure 2 The present invention will be described in further detail, but the embodiments of the present invention are not limited thereto.

[0060] The present invention discloses a method for optimizing equipment energy efficiency based on plant affairs data, which specifically includes the following steps:

[0061] Step S1: real-time collection of equipment operating parameters, vibration energy data, and user behavior information, alignment of timestamps, and construction of a three-dimensional feature matrix;

[0062] Step S2: Analyze the vibration energy data and user behavior information to obtain the vibration energy potential value and user behavior compliance respectively;

[0063] Step S3: Incorporating the vibration energy potential value and user behavior compliance into the energy efficiency optimization objective function, dynamically generating a device collaboration strategy, and obtaining the optimal device collaboration path;

[0064] Step S4, obtain equipment fault parameters and external environment parameters, quantify the impact of equipment health status and external environment changes on energy efficiency, dynamically adjust the energy efficiency optimization objective function, and generate equipment collaborative optimization strategy for equipment energy efficiency optimization management.

[0065] In practical applications, device status, vibration energy, and user behavior are integrated into a unified multidimensional data structure to facilitate subsequent analysis and modeling. This breaks the limitations of traditional single-dimensional analysis and integrates device, environmental, and human factors to provide comprehensive data support for energy efficiency optimization. Vibration energy data is used to identify energy loss points during device operation and quantify the device's energy utilization efficiency under different operating conditions. User behavior is analyzed, and a rule engine is used to determine whether user operations comply with energy-saving regulations. Feedback is provided to users, encouraging them to adjust their operating habits to reduce energy consumption, thus achieving a dual energy efficiency improvement path of "device optimization" and "user guidance." Using vibration energy potential and user behavior compliance as constraints for the objective function, an optimization algorithm is used to calculate device coordination strategies in real time, generating the optimal coordination path. This avoids the global efficiency loss caused by independent optimization of individual devices and achieves system-level energy efficiency improvement. Device health is assessed using fault parameters to predict the impact of potential faults on energy efficiency. When device health deteriorates, device lifespan can be prioritized over energy efficiency. Environmental factors can affect device efficiency, requiring dynamic modeling of their impact. Environmental predictions can be used to predict future impacts and adjust strategies in advance. This enables the system to adapt to uncertainties such as equipment aging and environmental changes, preventing energy efficiency optimization failures caused by unexpected factors. It also balances short-term energy efficiency improvements with long-term equipment health, extending equipment life and reducing maintenance costs. This creates a closed loop from data perception to intelligent decision-making, ultimately achieving optimal management of equipment energy efficiency in complex and dynamic environments.

[0066] The steps for analyzing vibration energy data and user behavior information to obtain vibration energy potential value and user behavior compliance are as follows:

[0067] Step S21, preprocessing the vibration energy data to obtain standard vibration energy data, wherein the standard vibration energy data includes an angular frequency w and an acceleration amplitude A;

[0068] Step S22, by formula The vibration energy density E is calculated, where m is the mass of the vibration equipment;

[0069] Step S23, based on the vibration energy density E, by formula The electric energy that can be recovered per unit time is calculated, that is, the vibration energy potential value P, where: is the energy conversion efficiency, i.e., the electromagnetic conversion efficiency;

[0070] Step S24: Compare the vibration energy potential value with a preset vibration energy threshold. If the vibration energy potential value exceeds the preset vibration energy threshold, the device is experiencing abnormal vibration, triggering a fault alarm.

[0071] Step S25: Analyze the user behavior information to obtain the user behavior compliance.

[0072] In practical applications, a formula is used to calculate vibration energy density E, converting vibration signals into energy indicators that intuitively reflect the intensity of the equipment's vibration energy, providing a quantitative basis for energy recovery or fault diagnosis. Abnormal high-frequency or low-frequency energy peaks may correspond to specific faults, such as increased high-frequency energy in bearing faults or concentrated low-frequency energy in unbalanced conditions. A formula is used to calculate the amount of recoverable electrical energy per unit time, quantifying the potential for converting equipment vibration energy into electrical energy. This guides the deployment of energy recovery systems and allows the installation of vibration power generation devices in high-potential areas. The calculated P is compared with a preset threshold. This threshold comparison allows for rapid identification of abnormal vibrations, preventing further equipment damage and enabling intervention before the fault escalates, reducing repair costs and the risk of production interruptions. A rules engine analyzes user operation records to quantify whether user behavior complies with energy-saving regulations, reducing energy waste caused by human intervention. Compliance scores provide feedback, encouraging users to optimize their operating habits and improve overall energy efficiency.

[0073] The steps to analyze user behavior information and obtain user behavior compliance are as follows:

[0074] Step S251 , the user behavior information includes the number of device operations F1 performed by the user in a unit of time, the parameter adjustment range A1 for each operation, and the difference B1 between the device task priority set by the user and the priority recommended by the system;

[0075] Step S252: define the safe operation frequency threshold F max , through the formula F=1-(F1 / F max )×n1 is used to calculate the operating frequency compliance F, where n1 is the weight coefficient and is not equal to zero;

[0076] Step S253: define the parameter adjustment amplitude threshold A max , by the formula A=1-(A1 / A max)×n2 is used to calculate the parameter adjustment compliance A, where n2 is the weight coefficient and is not equal to zero;

[0077] Step S254 , calculating the device task priority matching degree B set by the user using the formula B=1-B1×n3, where n3 is a weight coefficient and is not equal to zero;

[0078] In step S255 , the user behavior compliance is calculated based on the operation frequency compliance F, the parameter adjustment range compliance A, and the device task priority matching degree B.

[0079] In actual application, abstract user operations are converted into quantifiable indicators. A high number of equipment operations may lead to equipment overload or fatigue damage, such as frequent starting and stopping of motors; excessive parameter adjustment may cause equipment abnormalities, such as sudden load changes leading to increased vibration; when the difference between the user-set equipment task priority and the system-recommended priority is too large, the overall efficiency of the system may be reduced. The user behavior compliance is calculated by comprehensively considering the operation frequency compliance, parameter adjustment range compliance and equipment task priority matching, balancing the combined impact of operation frequency, parameter adjustment and task priority to avoid deviation from a single indicator. Through threshold setting and compliance calculation, overclocking operations and abnormal parameter adjustments are identified to avoid equipment overload or failure. Task priority matching analysis helps users optimize operating processes and reduce resource waste. At the same time, it combines user behavior data with system policies to achieve a dynamic balance between "user behavior compliance" and "system efficiency."

[0080] The steps to calculate user behavior compliance are as follows:

[0081] Step S2551: The operation frequency compliance F, the parameter adjustment range compliance A, and the device task priority matching B are weighted and integrated to obtain the user behavior compliance D using the formula D=F×n4+A×n5+B×n6;

[0082] Step S2552: Set the compliance threshold range [d1, d2] and compare the user behavior compliance D with the compliance threshold range;

[0083] Step S2553: If the user behavior compliance D is in [d1, d2], the user behavior is a minor violation, triggering a warning and a minor penalty;

[0084] In step S2554, if the user behavior compliance D is in [0, d1], the user behavior has serious violations, triggering mandatory penalties and permission restrictions.

[0085] In practical applications, decentralized compliance indicators are converted into a unified, comprehensive score (D), facilitating rapid assessment of the overall compliance of user behavior. Weights are assigned based on scenario requirements, such as assigning higher weights to parameter adjustments in high-risk devices. Key risk indicators are then integrated to achieve dynamic risk assessment. Compliance thresholds are set to accurately identify minor and major violations, and differentiated measures are taken based on the severity of the violation to avoid user resistance caused by "one-size-fits-all" management. This ensures that the system automatically intervenes within manageable risks to reduce human error. Warning and penalty mechanisms create positive incentives, such as restoring permissions when compliance improves, encouraging users to proactively adjust their behavior to improve compliance. Furthermore, high-risk operating permissions are restricted to reduce the probability of equipment damage, energy waste, or safety incidents.

[0086] Incorporating vibration energy potential and user behavior compliance into the energy efficiency optimization objective function and dynamically generating equipment collaboration strategies are as follows:

[0087] Step S31: normalize the vibration energy potential value P , get the standard value of vibration energy potential P0;

[0088] Step S32: Constructing the equipment energy consumption optimization objective function , where P i is the real-time energy consumption of device i, is the energy conversion efficiency, i.e., the electromagnetic conversion efficiency;

[0089] Step S33: Calculate the user behavior compliance penalty term D0 according to the formula D0=1-D based on the user behavior compliance;

[0090] Step S34: extract the vibration energy density E and construct a comprehensive objective function for equipment energy efficiency optimization , where w1 and w2 are weight coefficients and both are not equal to zero;

[0091] Step S35: Based on the comprehensive objective function, select the comprehensive objective function f 总 The path with the smallest value is the global optimal path, and the device collaborative optimization path is obtained.

[0092] In actual application, the vibration energy potential value is normalized to eliminate the influence of extreme values on the objective function. For example, when a device fails and P suddenly increases, the normalization can still maintain a reasonable weight. Constructing the equipment energy consumption optimization objective function and directly quantifying the energy consumption cost of equipment operation is the basic goal of energy efficiency optimization. Real-time energy consumption can be dynamically adjusted according to the equipment status to ensure the timeliness of the strategy. Convert user behavior compliance into penalty items to ensure that the optimization strategy not only focuses on energy efficiency, but also forces user behavior to comply with regulations. For example, when users frequently start and stop equipment, causing the vibration to intensify, D decreases and D0 increases. The system will give priority to more compliant paths. Search all possible equipment collaborative paths through the optimization algorithm and select the one that uses f 综 The smallest path is the global optimal path, which adapts to device status, user behavior and environmental changes. At the same time, it reduces redundant operations through device coordination strategies and realizes intelligent management of device energy efficiency.

[0093] Obtain equipment fault parameters and external environment parameters, quantify the impact of equipment health status and external environment changes on energy efficiency, dynamically adjust the energy efficiency optimization objective function, and generate equipment collaborative optimization strategies for equipment energy efficiency optimization management. The specific steps are:

[0094] Step S41: Obtain equipment failure parameters, which include the number of equipment failures g and the equipment operation time t, and calculate the equipment health K using the formula K=1-g / t;

[0095] Step S42, obtaining external environmental parameters, wherein the external environmental parameters include an ambient temperature parameter T and an energy price parameter J;

[0096] Step S43: Establish a mapping relationship between equipment fault parameters, external environment parameters and equipment energy efficiency to obtain an energy efficiency attenuation model. ,in is the benchmark energy efficiency, k is the impact factor, v1 and v2 are weight coefficients, and both are not equal to zero;

[0097] Step S44: dynamically adjust the comprehensive objective function of equipment energy efficiency optimization according to the energy efficiency attenuation model, and generate an equipment collaborative optimization strategy for equipment energy efficiency optimization management.

[0098] In actual use, the health of the equipment is calculated by the number of equipment failures and the equipment operating time, and the abstract equipment status is converted into a quantifiable indicator. The higher the K value, the healthier the equipment. If the k value is too low, a maintenance reminder is triggered to avoid energy efficiency degradation or downtime due to equipment failure. Temperature affects equipment efficiency. For example, high temperature reduces motor efficiency, so load distribution needs to be adjusted dynamically. Electricity prices determine economic efficiency, such as increasing electricity consumption during low electricity price periods to reduce operating costs. Optimization strategies are dynamically adjusted through real-time data to avoid the limitations of static models. At the same time, energy efficiency, cost, and equipment health are integrated to avoid suboptimal solutions caused by a single goal. Electricity price strategies are combined to reduce operating costs. At the same time, carbon emissions are reduced through energy efficiency optimization, thus realizing intelligent and dynamic energy efficiency management.

[0099] According to the energy efficiency attenuation model, the comprehensive objective function of equipment energy efficiency optimization is dynamically adjusted to generate equipment collaborative optimization strategies for equipment energy efficiency optimization management. The specific steps are as follows:

[0100] Step S441, obtaining predicted temperature parameters and predicted electricity price parameters within a set future time period, inputting the predicted temperature parameters and predicted electricity price parameters into an energy efficiency attenuation model, and generating a predicted energy efficiency curve;

[0101] Step S442: setting an energy efficiency attenuation threshold, extracting the period in the predicted energy efficiency curve where the energy efficiency drops by more than the set energy efficiency attenuation threshold as a high-risk period, and triggering an early warning signal;

[0102] Step S443: identifying non-critical production equipment in the equipment collaborative optimization path based on the early warning signal, and shutting down the operation of the non-critical production equipment;

[0103] In step S444, the comprehensive objective function of the equipment energy efficiency optimization is dynamically adjusted to generate an equipment collaborative optimization strategy for equipment energy efficiency optimization management.

[0104] In practical applications, forecasted temperature and electricity price parameters for a set future time period are obtained through meteorological forecasts and the power market. These parameters are then input into an energy efficiency decay model to generate a forecasted energy efficiency curve for the future time period. This forecast data allows for the early identification of declining energy efficiency trends, preventing energy efficiency losses caused by sudden environmental changes or electricity price fluctuations. Energy efficiency decay thresholds are set based on historical data or business needs to identify periods of significant energy efficiency decline, such as periods of high temperatures and peak electricity prices, in advance. This avoids reactive responses and reduces the impact of sudden risks on production. A distinction is made between mission-critical and mission-critical production equipment—that is, core equipment on the production line versus auxiliary and backup equipment. Non-critical equipment is shut down during high-risk periods to ensure stable operation of critical equipment during these periods, while also reducing unnecessary energy consumption and significantly lowering operating costs. Constraints for high-risk energy efficiency periods are added to the original comprehensive objective function to generate a new objective function. Global energy efficiency optimization is achieved through iterative optimization.

[0105] At the same time, the comprehensive objective function of equipment energy efficiency optimization is dynamically adjusted to generate equipment collaborative optimization strategies for equipment energy efficiency optimization management steps, specifically:

[0106] Step S4441: Obtain the carbon emission cost parameter C, extract the ambient temperature parameter T and the energy price parameter J, and define the environmental impact factor H = v3 × T + v4 × J + v5 × C, where v3, v4, and v5 are all weight coefficients and are not equal to zero;

[0107] Step S4442: Extracting baseline performance , vibration energy density E and user behavior compliance penalty term D0, dynamically adjust the comprehensive objective function of equipment energy efficiency optimization, and obtain the standard objective function of equipment energy efficiency optimization ;

[0108] Step S4443: Based on the standard objective function, select the standard objective function f 标 The path with the largest value is the global optimal path, and the device collaborative standard path is obtained for device energy efficiency optimization management.

[0109] In actual application, temperature, electricity price and carbon emission cost are unified into a single indicator H, which is convenient for combining with energy efficiency objective function. Carbon emission cost reflects policy constraints, prompting the system to give priority to low-carbon paths. Electricity price reflects economy, balances cost and energy efficiency, and realizes carbon emission reduction and cost control through multi-objective optimization. Dynamically adjust the comprehensive objective function of equipment energy efficiency optimization to obtain the standard objective function of equipment energy efficiency optimization, and maximize f 标, comprehensively balancing energy efficiency, environmental impact, and user behavior to achieve multi-objective collaborative optimization. Through optimization algorithms, we select low-energy, low-carbon equipment combinations while preventing user violations, ensuring that the equipment collaborative strategy strikes a balance between technical, economic, and environmental considerations. This entire process, through the quantification of environmental factors, multi-objective modeling, and global optimization, achieves intelligent and sustainable equipment energy efficiency management.

[0110] A plant affairs data-based equipment energy efficiency optimization system, by applying the plant affairs data-based equipment energy efficiency optimization method as described above, includes:

[0111] Multi-source data acquisition module collects equipment operating parameters, vibration energy data, and user behavior information in real time, aligns timestamps, and constructs a three-dimensional feature matrix;

[0112] The vibration energy and user behavior analysis module analyzes vibration energy data and user behavior information to obtain vibration energy potential value and user behavior compliance respectively;

[0113] The device collaboration strategy generation module incorporates vibration energy potential value and user behavior compliance into the energy efficiency optimization objective function, dynamically generates device collaboration strategies, and obtains the optimal device collaboration path;

[0114] The equipment collaborative optimization strategy generation module obtains equipment fault parameters and external environment parameters, quantifies the impact of equipment health status and external environment changes on energy efficiency, dynamically adjusts the energy efficiency optimization objective function, and generates equipment collaborative optimization strategies for equipment energy efficiency optimization management.

[0115] The above are all preferred embodiments of the present application, and are not intended to limit the scope of protection of the present application. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A method for optimizing equipment energy efficiency based on plant data, characterized in that: The following steps are involved: Collect equipment operating parameters, vibration energy data, and user behavior information in real time, align timestamps, and construct a three-dimensional feature matrix; Analyze vibration energy data and user behavior information to obtain vibration energy potential value and user behavior compliance respectively; Incorporating vibration energy potential and user behavior compliance into the energy efficiency optimization objective function, dynamically generating device collaboration strategies, and obtaining the optimal device collaboration path; Obtain equipment fault parameters and external environment parameters, quantify the impact of equipment health status and external environment changes on energy efficiency, dynamically adjust the energy efficiency optimization objective function, and generate equipment collaborative optimization strategies for equipment energy efficiency optimization management.

2. The equipment energy efficiency optimization method based on factory data according to claim 1 is characterized in that: The steps of analyzing the vibration energy data and user behavior information to obtain the vibration energy potential value and user behavior compliance are specifically as follows: Preprocessing the vibration energy data to obtain standard vibration energy data, wherein the standard vibration energy data includes an angular frequency w and an acceleration amplitude A; By formula The vibration energy density E is calculated, where m is the mass of the vibration equipment; Based on the vibration energy density E, the formula The electric energy that can be recovered per unit time is calculated, that is, the vibration energy potential value P, where: is the energy conversion efficiency, i.e., the electromagnetic conversion efficiency; Compare the vibration energy potential value with the preset vibration energy threshold. If the vibration energy potential value exceeds the preset vibration energy threshold, the equipment will vibrate abnormally and trigger a fault alarm. Analyze user behavior information to obtain user behavior compliance.

3. The equipment energy efficiency optimization method based on factory data according to claim 2 is characterized in that: The steps of analyzing user behavior information to obtain user behavior compliance are specifically as follows: The user behavior information includes the number of device operations F1 performed by the user per unit time, the parameter adjustment range A1 for each operation, and the difference B1 between the device task priority set by the user and the priority recommended by the system; Define the safe operation frequency threshold F max , through the formula F=1-(F1 / F max )×n1 is used to calculate the operating frequency compliance F, where n1 is the weight coefficient and is not equal to zero; Define parameter adjustment amplitude threshold A max , by the formula A=1-(A1 / A max )×n2 is used to calculate the parameter adjustment compliance A, where n2 is the weight coefficient and is not equal to zero; The device task priority matching degree B set by the user is calculated using the formula B=1-B1×n3, where n3 is the weight coefficient and is not equal to zero; The user behavior compliance is calculated based on the operation frequency compliance F, parameter adjustment range compliance A, and device task priority matching B.

4. The equipment energy efficiency optimization method based on factory data according to claim 3 is characterized in that: The steps of calculating the user behavior compliance by comprehensively considering the operation frequency compliance F, the parameter adjustment range compliance A, and the device task priority matching degree B are as follows: The user behavior compliance D is calculated by weighting the operation frequency compliance F, the parameter adjustment range compliance A, and the device task priority matching B using the formula D=F×n4+A×n5+B×n6. Set the compliance threshold range [d1, d2] and compare the user behavior compliance D with the compliance threshold range; If the user behavior compliance D is in [d1, d2], the user behavior has a minor violation, triggering a warning and a minor punishment; If the user behavior compliance D is in [0,d1], the user behavior is seriously in violation, triggering mandatory penalties and permission restrictions.

5. The equipment energy efficiency optimization method based on factory data according to claim 1 is characterized in that: The steps of incorporating the vibration energy potential value and user behavior compliance into the energy efficiency optimization objective function and dynamically generating the device collaboration strategy are specifically as follows: Normalize the vibration energy potential value P , get the standard value of vibration energy potential P0; Constructing equipment energy consumption optimization objective function , where P i is the real-time energy consumption of device i, is the energy conversion efficiency, i.e., the electromagnetic conversion efficiency; According to the user behavior compliance, the user behavior compliance penalty term D0 is calculated by the formula D0=1-D; Extract vibration energy density E and construct a comprehensive objective function for equipment energy efficiency optimization , where w1 and w2 are weight coefficients and both are not equal to zero; Based on the comprehensive objective function, the comprehensive objective function f is selected 总 The path with the smallest value is the global optimal path, and the device collaborative optimization path is obtained.

6. The equipment energy efficiency optimization method based on factory data according to claim 1 is characterized in that: The steps of obtaining equipment fault parameters and external environment parameters, quantifying the impact of equipment health status and external environment changes on energy efficiency, dynamically adjusting the energy efficiency optimization objective function, and generating equipment collaborative optimization strategies for equipment energy efficiency optimization management are specifically as follows: Obtain equipment failure parameters, which include the number of equipment failures g and the equipment operating time t, and calculate the equipment health K using the formula K=1-g / t; Acquiring external environmental parameters, wherein the external environmental parameters include an ambient temperature parameter T and an energy price parameter J; Establish the mapping relationship between equipment failure parameters, external environment parameters and equipment energy efficiency to obtain the energy efficiency attenuation model ,in is the benchmark energy efficiency, k is the impact factor, v1 and v2 are weight coefficients, and both are not equal to zero; According to the energy efficiency attenuation model, the comprehensive objective function of equipment energy efficiency optimization is dynamically adjusted to generate equipment collaborative optimization strategy for equipment energy efficiency optimization management.

7. The equipment energy efficiency optimization method based on factory data according to claim 6 is characterized in that: The steps of dynamically adjusting the comprehensive objective function of equipment energy efficiency optimization based on the energy efficiency attenuation model and generating an equipment collaborative optimization strategy for equipment energy efficiency optimization management are specifically as follows: Obtain predicted temperature parameters and predicted electricity price parameters within a set future time period, input the predicted temperature parameters and predicted electricity price parameters into the energy efficiency attenuation model, and generate a predicted energy efficiency curve; Set an energy efficiency attenuation threshold, extract the period in the predicted energy efficiency curve where the energy efficiency drops by more than the set energy efficiency attenuation threshold as a high-risk period, and trigger an early warning signal; Based on early warning signals, identify non-critical production equipment in the equipment collaborative optimization path and shut down the operation of non-critical production equipment; At the same time, the comprehensive objective function of equipment energy efficiency optimization is dynamically adjusted to generate equipment collaborative optimization strategies for equipment energy efficiency optimization management.

8. The equipment energy efficiency optimization method based on factory data according to claim 7 is characterized in that: The steps of dynamically adjusting the comprehensive objective function of equipment energy efficiency optimization and generating equipment collaborative optimization strategies for equipment energy efficiency optimization management are specifically as follows: Obtain the carbon emission cost parameter C, extract the ambient temperature parameter T and the energy electricity price parameter J, and define the environmental impact factor H = v3 × T + v4 × J + v5 × C, where v3, v4, and v5 are all weight coefficients, and none of them are equal to zero; Extracting benchmark performance , vibration energy density E and user behavior compliance penalty term D0, dynamically adjust the comprehensive objective function of equipment energy efficiency optimization, and obtain the standard objective function of equipment energy efficiency optimization ; Based on the standard objective function, the standard objective function f is selected 标 The path with the largest value is the global optimal path, and the device collaborative standard path is obtained for device energy efficiency optimization management.

9. An equipment energy efficiency optimization system based on factory data, characterized in that: Applying the equipment energy efficiency optimization method based on plant affairs data as described in any one of claims 1 to 8, comprising: Multi-source data acquisition module collects equipment operating parameters, vibration energy data, and user behavior information in real time, aligns timestamps, and constructs a three-dimensional feature matrix; The vibration energy and user behavior analysis module analyzes vibration energy data and user behavior information to obtain vibration energy potential value and user behavior compliance respectively; The device collaboration strategy generation module incorporates vibration energy potential value and user behavior compliance into the energy efficiency optimization objective function, dynamically generates device collaboration strategies, and obtains the optimal device collaboration path; The equipment collaborative optimization strategy generation module obtains equipment fault parameters and external environment parameters, quantifies the impact of equipment health status and external environment changes on energy efficiency, dynamically adjusts the energy efficiency optimization objective function, and generates equipment collaborative optimization strategies for equipment energy efficiency optimization management.

Images