Energy-saving optimization system for thermal equipment based on energy consumption data analysis

Abstract

The present invention relates to the field of energy-saving optimization technology, including a thermal equipment energy-saving optimization system based on energy consumption data analysis. The system includes an entropy generation monitoring module, an abnormal data identification module, a data fusion analysis module, an energy loss positioning module, an operating parameter adjustment module, and an energy consumption optimization feedback module. In the present invention, by comprehensively monitoring the temperature and pressure data of the thermal equipment, the entropy generation amount is accurately calculated and the data cycle is deeply analyzed, the energy consumption efficiency of the thermal elements is optimized, and parameters can be adjusted immediately during the operation of the thermal equipment to reduce energy consumption. Through the fusion analysis of environmental factors and equipment load data, the heat exchange efficiency is improved. Accurate data synchronization and the extraction of key influencing factors make energy loss positioning more accurate, optimize the operating parameters of the thermal equipment, realize resource recycling and the application of low-carbon technologies, effectively improve energy efficiency and reduce environmental impact.

Description

Technical Field

[0001] The present invention relates to the technical field of energy-saving optimization, and in particular to a thermal equipment energy-saving optimization system based on energy consumption data analysis. Background Art

[0002] The field of energy-saving optimization technology encompasses methods and equipment for reducing energy consumption in various energy-consuming processes, aiming to improve energy efficiency and reduce environmental impact. It encompasses a wide range of technologies and solutions, such as building energy conservation, industrial process optimization, and transportation system management. Core areas include energy efficiency improvement, resource recycling, and the development and application of low-carbon technologies to optimize energy use, reduce dependence on natural resources, and alleviate the burden on the environment.

[0003] The thermal equipment energy-saving optimization system is a technical solution specifically designed to improve the operational efficiency of thermal equipment. It involves monitoring, analyzing, and optimizing the energy consumption of thermal equipment. Specific methods include optimizing temperature control systems, improving heat exchange efficiency, and adjusting operating parameters in real time. Through these specific operations and treatment methods, thermal equipment can effectively reduce energy consumption while maintaining operational performance.

[0004] Existing technologies lack immediate data feedback and dynamic adjustment capabilities. Traditional control systems typically rely on preset operating parameters and fail to fully utilize real-time data for optimization. This results in a failure to adapt adaptively in actual operation, impacting thermal efficiency. Furthermore, existing technologies are inadequate in accurately pinpointing energy losses, often failing to identify and address the specific issues leading to excessive energy consumption. This lack of detailed analysis of energy flows leads to overlooking important energy-saving opportunities, increasing reliance on natural resources and the environmental burden. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a thermal equipment energy-saving optimization system based on energy consumption data analysis.

[0006] In order to achieve the above objectives, the present invention adopts the following technical solutions: a thermal equipment energy-saving optimization system based on energy consumption data analysis includes:

[0007] The entropy generation monitoring module collects temperature and pressure data of thermal equipment, calculates the entropy generation of each working cycle according to operating conditions, summarizes and analyzes the trend of the data of each cycle, analyzes the energy saving effect of thermal elements, and obtains entropy monitoring results;

[0008] The abnormal data identification module uses the entropy monitoring results to calculate the self-information of the data points, evaluates the abnormal probability of each point based on statistical rarity, filters the abnormal data points, and compares them with the standard data under normal operation mode to identify abnormal patterns in the energy consumption data and generate abnormal pattern recognition results;

[0009] The data fusion analysis module collects ambient temperature, humidity and equipment load data, combines the abnormal pattern recognition results, performs data integration and synchronization through hierarchical clustering, extracts key influencing factors, and forms data fusion analysis results;

[0010] The energy loss location module locates abnormal operation links based on the data fusion analysis results, identifies energy loss points in the operating parameters of the thermal equipment, compares the entropy generation under different operating conditions, draws an energy flow diagram and identifies the key links of energy loss, and generates energy loss location results;

[0011] The operating parameter adjustment module adjusts the combustion efficiency and heat transfer area of ​​the thermal equipment based on the energy loss location results, continuously monitors the adjustment effect, optimizes and corrects the parameter adjustment in real time, and generates a detailed record of the operating parameter adjustment;

[0012] The energy consumption optimization feedback module uses the operating parameter adjustment detail records, integrates the real-time monitoring feedback data, adjusts the operation strategy of the thermal equipment, and continuously evaluates the performance of the adjusted thermal equipment to generate energy consumption optimization feedback results.

[0013] As a further solution of the present invention, the entropy monitoring results include periodic data analysis records, thermal efficiency evaluation results and energy consumption indicators; the abnormal pattern recognition results include abnormal point positioning results, abnormal type classification results and abnormal intensity evaluation results; the data fusion analysis results include key influencing factors and comprehensive data views; the energy loss positioning results include key loss areas, loss degree quantification records and influencing parameter identification results; the operating parameter adjustment detail records include parameter adjustment range, comparison results before and after adjustment and adjustment effect tracking records; the energy consumption optimization feedback results include performance improvement points, energy saving evaluation records and optimization strategy effectiveness feedback records.

[0014] As a further solution of the present invention, the entropy generation monitoring module includes a data collection submodule, an entropy calculation submodule, and a trend analysis submodule;

[0015] The data collection submodule monitors thermal equipment through sensors, captures temperature and pressure data of thermal equipment at various operating stages, records corresponding operating conditions and environmental parameters, and obtains the original data set of the equipment;

[0016] The entropy calculation submodule analyzes the original data set of the device, calculates the entropy variable caused by the changes in temperature and pressure data in each working cycle, evaluates the energy conversion efficiency, and generates the cycle entropy generation amount;

[0017] The trend analysis submodule performs statistical analysis and data summarization on the periodic entropy generation, performs time series analysis to identify trends and patterns in the data, reveals the change pattern of thermal element performance over time, and obtains entropy monitoring results.

[0018] As a further embodiment of the present invention, the entropy variable is calculated according to the formula:

[0019]

[0020] Calculation is performed, where ΔS represents the entropy variable value, P i Represents the pressure value at the beginning of the cycle, V i Represents the internal volume of the thermal equipment piston at the beginning of the cycle, P f Represents the pressure value at the end of the cycle, V f represents the volume value at the end of the cycle, ΔQ represents the heat value absorbed or released during the cycle, T represents the average temperature during the cycle, and K is the Boltzmann constant.

[0021] As a further solution of the present invention, the abnormal data identification module includes a self-information calculation submodule, an abnormal probability assessment submodule, and a pattern comparison and identification submodule;

[0022] The self-information calculation submodule uses the entropy monitoring results to perform real-time data flow analysis, extract information from each data point, calculate the self-information of the data point, determine the statistical importance of the information, and generate an information index set;

[0023] The anomaly probability assessment submodule performs probability analysis on the data points based on the rarity of the information quantity indicator set, calculates the local outlier factor of the data points, determines high-risk anomalies using threshold judgment, and obtains a probability distribution record of the anomaly points;

[0024] The pattern comparison and recognition submodule combines the historical data of the thermal equipment, compares the high-risk abnormal points recorded in the abnormal point probability distribution, analyzes the deviation from the normal data, identifies the abnormal pattern in the energy consumption data, and obtains the abnormal pattern recognition result.

[0025] As a further embodiment of the present invention, the local outlier factor is calculated according to the formula:

[0026]

[0027] Calculation is performed, where LOF(k) represents the local outlier factor, k represents the number of neighboring points considered, which is used to determine the calculation range of the local density, lrd(o) represents the local reachability density of object o, which is an indicator of the degree to which o is closely surrounded by its neighboring points, lrd(p) is the local reachability density of k neighboring points p of o, N k(o) is the neighborhood set containing the k points closest to o.

[0028] As a further solution of the present invention, the data fusion analysis module includes a data acquisition submodule, a hierarchical clustering submodule, and an impact factor extraction submodule;

[0029] The data acquisition submodule synchronously collects ambient temperature and humidity data through the sensor array, and collects real-time load data of thermal equipment, verifies data synchronization and accuracy, and generates environmental and load data sets;

[0030] The hierarchical clustering submodule integrates the environment and load data sets with the abnormal pattern recognition results, performs hierarchical clustering processing, synchronizes the data at each layer, analyzes the consistency and relevance of the data during the processing process, and generates a clustered integrated data set;

[0031] The influencing factor extraction submodule performs data mining based on the clustering integration data set, identifies key influencing factors that directly affect equipment performance, refines key factors, and obtains data fusion analysis results.

[0032] As a further solution of the present invention, the energy loss location module includes an abnormal operation location submodule, an energy loss identification submodule, and an energy flow direction mapping submodule;

[0033] The abnormal operation location submodule performs abnormal detection and refinement to identify operation deviations based on the data fusion analysis results, analyzes the operation data of each link of the thermal equipment, locates the operation link that deviates from the standard operation parameters, and generates an abnormal operation point data set;

[0034] The energy loss identification submodule uses the abnormal operation point data set and compares it with the standard operation state to analyze the entropy generation of each operation link. Through data difference analysis, it identifies the key operating parameters of energy loss and obtains the energy loss key parameter set.

[0035] The energy flow drawing submodule uses the energy loss key parameter set to perform data visualization processing, draw an energy flow diagram, mark the energy loss position of the key link, and generate an energy loss positioning result.

[0036] As a further solution of the present invention, the operating parameter adjustment module includes an efficiency adjustment submodule, a continuous monitoring submodule, and a real-time optimization and correction submodule;

[0037] The efficiency adjustment submodule analyzes the combustion efficiency and heat transfer area of ​​the thermal equipment based on the energy loss location results, adjusts the operating parameters to optimize the thermal efficiency, and simultaneously performs data feedback loop adjustment to generate an adjusted operating parameter data set;

[0038] The continuous monitoring submodule performs real-time data monitoring and continuous tracking based on the adjusted working parameter data set, analyzes the continuity and stability of the adjusted parameters, and obtains a continuous monitoring data set;

[0039] The real-time optimization and correction submodule collects real-time data of thermal equipment based on the continuous monitoring data set, analyzes and confirms the optimization and adjustment effect, synchronously performs dynamic parameter correction on the thermal equipment, and generates detailed records of operation parameter adjustments.

[0040] As a further solution of the present invention, the energy consumption optimization feedback module includes a data comprehensive analysis submodule, an operation strategy adjustment submodule, and a performance evaluation submodule;

[0041] The data comprehensive analysis submodule analyzes the real-time monitoring feedback data based on the detailed records of the operating parameter adjustments, extracts key indicators of equipment performance, identifies performance changes by comparing the differences between the before and after data, and generates a comprehensive analysis data set;

[0042] The operation strategy adjustment submodule uses the comprehensive analysis data set to adjust the operation strategy of the thermal equipment, confirms the adaptability of the adjustment process through dynamic simulation and strategy evaluation, and obtains the adjusted operation strategy record;

[0043] The performance evaluation submodule performs continuous performance evaluation based on the adjusted operation strategy records, uses quantitative analysis to compare the operation effects before and after the adjustment, evaluates the equipment performance and energy consumption optimization results, and generates energy consumption optimization feedback results.

[0044] Compared with the prior art, the advantages and positive effects of the present invention are:

[0045] In the present invention, by comprehensively monitoring the temperature and pressure data of thermal equipment, accurately calculating the entropy generation and conducting in-depth analysis of the data cycle, the energy consumption efficiency of thermal elements is optimized, allowing parameters to be adjusted instantly during the operation of thermal equipment to reduce energy consumption. By integrating and analyzing environmental factors and equipment load data, the heat exchange efficiency is improved. Accurate data synchronization and extraction of key influencing factors make energy loss positioning more accurate, optimize the operating parameters of thermal equipment, realize resource recycling and the application of low-carbon technologies, effectively improve energy efficiency and reduce environmental impact. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a system flow chart of the present invention;

[0047] Figure 2 It is a system module diagram of the present invention;

[0048] Figure 3 This is a flow chart of the entropy generation monitoring module of the present invention;

[0049] Figure 4This is a flow chart of the abnormal data identification module of the present invention;

[0050] Figure 5 This is a flow chart of the data fusion analysis module of the present invention;

[0051] Figure 6 This is a flow chart of the energy loss location module of the present invention;

[0052] Figure 7 This is a flow chart of the operating parameter adjustment module of the present invention;

[0053] Figure 8 This is a flow chart of the energy consumption optimization feedback module of the present invention. DETAILED DESCRIPTION

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

[0055] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0056] See also Figure 1 The thermal equipment energy-saving optimization system based on energy consumption data analysis includes:

[0057] The entropy generation monitoring module collects temperature and pressure data of thermal equipment, calculates the entropy generation of each working cycle according to operating conditions, summarizes and analyzes the trend of the data of each cycle, analyzes the energy saving effect of thermal elements, and obtains entropy monitoring results;

[0058] The abnormal data identification module uses the entropy monitoring results to calculate the self-information of data points, evaluates the abnormal probability of each point based on statistical rarity, filters abnormal data points, and compares them with standard data under normal operating mode to identify abnormal patterns in energy consumption data and generate abnormal pattern recognition results;

[0059] The data fusion analysis module collects ambient temperature, humidity, and equipment load data, combines it with abnormal pattern recognition results, integrates and synchronizes the data through hierarchical clustering, extracts key influencing factors, and forms data fusion analysis results;

[0060] The energy loss location module locates abnormal operation links based on data fusion analysis results, identifies energy loss points in the operating parameters of thermal equipment, compares the entropy generation under different operating conditions, draws energy flow diagrams, identifies key links of energy loss, and generates energy loss location results;

[0061] The operating parameter adjustment module adjusts the combustion efficiency and heat transfer area of ​​thermal equipment based on the energy loss location results, continuously monitors the adjustment effect, optimizes and corrects the parameter adjustment in real time, and generates detailed records of the operating parameter adjustments;

[0062] The energy consumption optimization feedback module uses the detailed records of operating parameter adjustments and comprehensive real-time monitoring feedback data to adjust the operation strategy of thermal equipment, and conducts continuous performance evaluation of the adjusted thermal equipment to generate energy consumption optimization feedback results.

[0063] The entropy monitoring results include periodic data analysis records, thermal efficiency assessment results and energy consumption indicators; the abnormal pattern recognition results include abnormal point positioning results, abnormal type classification results and abnormal intensity assessment results; the data fusion analysis results include key influencing factors and comprehensive data views; the energy loss positioning results include key loss areas, loss degree quantification records and influencing parameter identification results; the operating parameter adjustment detail records include parameter adjustment range, comparison results before and after adjustment and adjustment effect tracking records; the energy consumption optimization feedback results include performance improvement points, energy saving assessment records and optimization strategy effectiveness feedback records.

[0064] See also Figure 2 and Figure 3 ,The entropy generation monitoring module includes a data collection submodule, an entropy calculation submodule, and a trend analysis submodule;

[0065] The data collection submodule monitors thermal equipment through sensors, captures temperature and pressure data of thermal equipment at various operating stages, records corresponding operating conditions and environmental parameters, and obtains the original data set of the equipment;

[0066] The data collection submodule uses high-precision temperature and pressure sensors to monitor thermal equipment in real time. These sensors are located in key areas of the equipment, such as heating elements and pressure vessels, to ensure accurate and timely data. These sensors collect multiple data points per second, recording the temperature and pressure of the equipment at different operating stages. The collected data is transmitted via a secure network to a central processing system, where it is formatted and stored in a database, forming the raw data set for the equipment. This data set includes timestamps, corresponding operating conditions, environmental parameters, and more, laying the foundation for subsequent data processing and analysis. This provides a comprehensive understanding of the equipment's operating status and allows for the timely identification of potential problems and anomalies.

[0067] The entropy calculation submodule analyzes the original data set of the equipment, calculates the entropy variables caused by the changes in temperature and pressure data in each working cycle, evaluates the energy conversion efficiency, and generates the cycle entropy generation;

[0068] Entropy variable, according to the formula:

[0069]

[0070] Calculation is performed, where ΔS represents the entropy variable value, P i Represents the pressure value at the beginning of the cycle, V i Represents the internal volume of the thermal equipment piston at the beginning of the cycle, P f Represents the pressure value at the end of the cycle, V f represents the volume value at the end of the cycle, ΔQ represents the heat value absorbed or released during the cycle, T represents the average temperature during the cycle, and K is the Boltzmann constant.

[0071] Collect thermal equipment data, P i =101.3kPa, V i =1.0m 3 , P f =105.5kPa, V f =1.02m 3 The data are all measured in the actual operating environment. The heat released in one working cycle is set to ΔQ = -500J (negative value means heat release), and the average temperature T = 298K. The Boltzmann constant K is 1.380649×10 -23 J / K is a physical constant used to express the physical quantification of entropy.

[0072] Calculate the contribution of temperature and pressure changes to the entropy change:

[0073]

[0074] Multiplying the above result with the Boltzmann constant k gives the first part of the entropy change:

[0075]

[0076] Calculate the entropy change due to the heat change:

[0077]

[0078] Calculate the total entropy variable:

[0079] ΔS=5.7297×10 -25 -1.677852≈-1.677852 J / K;

[0080] The results show that within a given operating cycle, the system's entropy increase is primarily due to heat release, reflecting the system's irreversibility and the efficiency of energy conversion. Furthermore, the data indicate that small changes in temperature and pressure have a very small contribution to entropy and can be ignored in engineering applications, allowing the focus to be on energy conversion and heat exchange processes.

[0081] The trend analysis submodule performs statistical analysis and data summarization on the periodic entropy generation, performs time series analysis to identify trends and patterns in the data, reveals the change pattern of thermal element performance over time, and obtains entropy monitoring results;

[0082] Based on statistical analysis and data summarization, the trend analysis submodule applies complex time series analysis techniques to conduct in-depth analysis of periodic entropy generation. It identifies potential trends and patterns in the data by constructing autoregressive (AR) and moving average (MA) models, as well as their combined autoregressive moving average (ARMA) model. This module first performs seasonal decomposition on the data to isolate and identify internal and external factors influencing system performance. Statistical methods are then used to verify the model's effectiveness and adjust model parameters to suit the data characteristics. Ultimately, this prediction is used to predict future performance trends, providing decision support for equipment maintenance and upgrades, and ensuring optimal long-term operation of the equipment.

[0083] See also Figure 2 and Figure 4 ,The abnormal data identification module includes the self-information calculation submodule, the ,abnormality probability assessment submodule, and the pattern comparison and ,recognition submodule;

[0084] The self-information calculation submodule uses the entropy monitoring results to perform real-time data flow analysis, extract information from each data point, calculate the self-information of the data point, determine the statistical importance of the information, and generate an information index set;

[0085] The self-information calculation submodule processes entropy monitoring results through real-time data stream analysis, performing in-depth analysis of each data point received from the sensor. First, the self-information of each data point is calculated to determine its statistical significance within the entire dataset. The calculation of self-information depends on the frequency of occurrence of the data point; less frequent data points have higher self-information. This generates a set of information metrics encompassing the self-information of each data point, providing an important quantitative basis for subsequent data analysis and decision-making, enabling effective management and optimization of data streams.

[0086] The anomaly probability assessment submodule performs probability analysis on data points based on the rarity of the information quantity indicator set, calculates the local outlier factor of the data points, uses threshold judgment to determine high-risk anomalies, and obtains the probability distribution record of the anomaly points;

[0087] The local outlier factor is calculated according to the formula:

[0088]

[0089] Calculation is performed, where LOF(k) represents the local outlier factor, k represents the number of neighboring points considered, which is used to determine the calculation range of the local density, lrd(o) represents the local reachability density of object o, which is an indicator of the degree to which o is closely surrounded by its neighboring points, lrd(p) is the local reachability density of k neighboring points p of o, N k (o) is the neighborhood set containing the k points closest to o.

[0090] k: integer, specifies the number of neighboring points to consider. Suppose k=5 is selected based on the density of the data.

[0091] N k (o): This is the set of k nearest neighbors of data point o. Suppose we find the five nearest neighbors of o in the dataset using the Euclidean distance metric.

[0092] lrd(o): local reachability density, defined as The average reachable distance is from o to N k The average reachable distance of each point in (o). The reachable distance is defined as max(core distance(p), distance(o,p)), where the core distance is the distance from point p to the farthest point in its k-neighborhood. Assume that lrd(o) = 0.1 for o.

[0093] lrd(p): Local reachability density of p, the neighbor of o. Computed in a similar way to lrd(o).

[0094] Assume that the lrd(p) values ​​of p are 0.12, 0.15, 0.14, 0.13, and 0.11 respectively. The process of calculating LOF(k) is as follows:

[0095]

[0096] The results show that o's outlier degree is 30% higher than its neighbors, indicating that o is relatively an outlier in its local neighborhood. A value above 1 indicates that o is an outlier, while a value close to 1 indicates that o behaves similarly to its neighbors.

[0097] The pattern comparison and recognition submodule combines historical data of thermal equipment, compares high-risk abnormal points recorded in the abnormal point probability distribution, analyzes deviations from normal data, identifies abnormal patterns in energy consumption data, and obtains abnormal pattern recognition results;

[0098] The pattern comparison and identification submodule combines historical data from thermal equipment with the probability distribution of outliers to conduct a detailed comparative analysis of high-risk outliers. By comparing the deviations between outlier data points and normal data points, it can identify anomalous patterns in energy consumption data. This not only relies on statistical algorithms to identify data inconsistencies but also uses historical trend data as a benchmark to more accurately reveal unusual changes in equipment performance. The identified anomaly patterns provide critical information for equipment failure prevention and maintenance strategy development, enhancing the accuracy and efficiency of equipment management.

[0099] See also Figure 2 and Figure 5 ,The data fusion analysis module includes data acquisition submodule, hierarchical clustering submodule, and ,influencing factor extraction submodule;

[0100] The data acquisition submodule synchronously collects ambient temperature and humidity data through the sensor array, and collects real-time load data of thermal equipment, verifies data synchronization and accuracy, and generates environmental and load data sets;

[0101] The data acquisition submodule uses a sensor array to synchronously collect ambient temperature and humidity data, while also recording the real-time load status of thermal equipment. The sensor array design ensures data synchronization and accuracy, ensuring the accuracy of the collected information through real-time comparison and verification of data between different sensors. This data undergoes preliminary processing, such as filtering and outlier detection, to remove potential noise or erroneous readings. The resulting environmental and load datasets contain key information such as timestamps, temperature, humidity, and load levels, providing a comprehensive foundation for subsequent analysis.

[0102] The hierarchical clustering submodule integrates the environment and load data sets with the abnormal pattern recognition results, performs hierarchical clustering processing, synchronizes the data at each layer, analyzes the consistency and correlation of the data during the processing process, and generates a clustered integrated data set;

[0103] The hierarchical clustering submodule utilizes the environment and load datasets and the results of anomaly pattern recognition to process the data using a hierarchical clustering algorithm. Analysis begins with subtle differences and gradually expands to significant ones, ensuring consistency and relevance within the data hierarchy. During the clustering process, the submodule synchronizes data across all layers and uses statistical analysis to confirm data relevance and cluster validity. The resulting clustered, integrated dataset provides a comprehensive view of data at all levels, enabling more accurate and targeted data analysis.

[0104] The influencing factor extraction submodule performs data mining based on clustering and integration of data sets to identify key influencing factors that directly affect equipment performance, refine key factors, and obtain data fusion analysis results;

[0105] The influencing factor extraction submodule performs data mining based on clustered and integrated datasets to identify key factors directly impacting equipment performance. Through in-depth analysis and pattern recognition techniques, this submodule refines the key factors influencing equipment performance within the data. This includes variable importance scoring, decision tree analysis, and correlation testing to ensure that the identified factors significantly impact equipment performance. The resulting data fusion analysis highlights factors critical to equipment operation and maintenance, providing specific guidance for optimizing equipment performance.

[0106] See also Figure 2 and Figure 6 ,The energy loss location module includes the abnormal operation ,location submodule, the energy loss identification submodule, and the energy ,flow drawing submodule;

[0107] The abnormal operation location submodule performs anomaly detection and refinement to identify operational deviations based on data fusion analysis results. It analyzes the operating data of each link of the thermal equipment, locates the operating links that deviate from the standard operating parameters, and generates an abnormal operation point data set.

[0108] The Abnormal Operation Location submodule conducts in-depth analysis of anomaly detection based on data fusion analysis results. By gradually refining the identification process, it conducts a detailed inspection and comparison of operational data from all aspects of thermal equipment. This submodule tracks data, including time series analysis to identify mutation points in the data and clustering algorithms to group data to identify operations that do not conform to normal patterns. For each identified abnormal operation point, the submodule conducts an in-depth analysis, comparing its deviation from standard operating parameters to accurately locate the specific link that deviates from standard operation. This process relies not only on the calculation results of automated tools but also requires the professional judgment of operators to confirm the validity of the anomaly points, ensuring the high accuracy and practical value of the calibrated abnormal operation point dataset.

[0109] The energy loss identification submodule uses the abnormal operation point data set and compares it with the standard operation state to analyze the entropy generation of each operation link. Through data difference analysis, it identifies the key operating parameters of energy loss and obtains the energy loss key parameter set;

[0110] The energy loss identification submodule identifies key operating parameters that impact energy efficiency through detailed analysis of abnormal operating point datasets. This process utilizes data analysis techniques, such as differential analysis and entropy calculation, to accurately measure energy differences between standard and actual operating conditions. This approach reveals the specific causes of energy loss at each operational stage, thereby pinpointing the key operating parameters responsible. The resulting set of key energy loss parameters details which operating parameters contribute to efficiency degradation. Adjusting these parameters directly impacts the energy efficiency performance of the equipment, providing a valuable basis for developing energy-saving measures and optimization strategies.

[0111] The energy flow drawing submodule uses the energy loss key parameter set to perform data visualization, draw an energy flow diagram, mark the energy loss location of key links, and generate energy loss location results;

[0112] The energy flow mapping submodule uses the obtained set of key energy loss parameters to perform detailed data visualization. This submodule can create an energy flow diagram, which details the energy flow path and loss locations during the operation of thermal equipment. The submodule first organizes the data set and then uses an algorithm to simulate energy flow, marking the links where energy loss is most significant. In addition, the chart uses different colors and graphic markers to distinguish the degree of energy loss, allowing equipment operators to intuitively understand the distribution and causes of energy loss, further formulating specific measures for equipment optimization and energy efficiency improvement, and updating the energy flow diagram based on newly collected data to ensure the timeliness and accuracy of the information.

[0113] See also Figure 2 and Figure 7 ,The operation parameter adjustment module includes an efficiency adjustment submodule, a continuous monitoring submodule, and a real-time optimization and correction submodule;

[0114] The efficiency adjustment submodule analyzes the combustion efficiency and heat transfer area of ​​thermal equipment based on the energy loss location results, adjusts the operating parameters to optimize thermal efficiency, and simultaneously performs data feedback loop adjustments to generate an adjusted operating parameter data set.

[0115] Based on the energy loss location results, the efficiency adjustment submodule accurately analyzes the combustion efficiency and heat transfer area of ​​thermal equipment. This submodule first identifies the key energy loss points during the combustion process through data analysis and adjusts the operating parameters of these points, such as the fuel supply rate, air input ratio, and heat exchanger configuration. During the adjustment process, the submodule continuously tests the effects of different parameter combinations, evaluating changes in thermal efficiency through simulation and experimental data. This method optimizes thermal efficiency and simultaneously implements a data feedback loop throughout the process to ensure the real-time and effectiveness of the adjustment measures. The resulting adjusted operating parameter dataset provides updated and more efficient operating parameters for equipment operation.

[0116] The continuous monitoring submodule performs real-time data monitoring and continuous tracking based on the adjusted working parameter data set, analyzes the continuity and stability of the adjusted parameters, and obtains a continuous monitoring data set;

[0117] The continuous monitoring submodule utilizes the adjusted operating parameter dataset to perform real-time data monitoring, continuously tracking the equipment's operating status. By deploying multiple monitoring points, the submodule collects key parameters such as temperature, pressure, and flow in real time. Using this real-time data, the submodule analyzes the continuity and stability of the adjusted parameters and how they impact the equipment's overall operating efficiency. Monitoring ensures that all parameters operate within set ranges, promptly identifies any deviations from normal ranges, and provides data support for further adjustments. The resulting continuous monitoring dataset provides the maintenance team with critical operational data, supporting the long-term stable operation of the equipment.

[0118] The real-time optimization and correction submodule collects real-time data of thermal equipment based on the continuous monitoring data set, analyzes and confirms the optimization and adjustment effect, performs dynamic parameter correction on the thermal equipment simultaneously, and generates detailed records of operating parameter adjustments;

[0119] The real-time optimization and correction submodule relies on a continuously monitored data set to dynamically correct the parameters of thermal equipment. The submodule collects key operating data in real time and analyzes the data to confirm the effectiveness of optimization adjustments. This includes evaluating improvements in thermal efficiency and reductions in energy consumption, as well as ensuring that all parameters are operating at optimal levels. Furthermore, the submodule simultaneously makes dynamic adjustments to thermal equipment, such as adjusting the combustion control system, optimizing heat exchange rates, and adjusting operating cycles. Comprehensive correction strategies ensure that equipment achieves optimal performance under all operating conditions. The generated detailed records of operating parameter adjustments reflect the specific content and results of each correction step, providing precise operational guidance for equipment maintenance and optimization.

[0120] See also Figure 2 and Figure 8 ,The energy consumption optimization feedback module includes a data comprehensive ,analysis submodule, an operation strategy adjustment submodule, and a ,performance evaluation submodule;

[0121] The data comprehensive analysis submodule analyzes real-time monitoring feedback data based on detailed records of operating parameter adjustments, extracts key equipment performance indicators, identifies performance changes by comparing the data before and after, and generates a comprehensive analysis data set;

[0122] The comprehensive data analysis submodule extracts data from detailed records of operational parameter adjustments and conducts in-depth analysis of real-time monitoring feedback to identify key performance indicators. The collected data is first cleaned and standardized. Statistical analysis methods, such as regression analysis and variance analysis, are then used to compare the data before and after parameter adjustments. This comparison helps identify specific performance changes, such as quantitative indicators of improved efficiency or reduced energy consumption. The resulting comprehensive analysis dataset provides a detailed overview of all aspects of equipment performance improvements, providing a scientific basis for further operational decisions and strategic adjustments.

[0123] The operation strategy adjustment submodule uses the comprehensive analysis data set to adjust the operation strategy of the thermal equipment, confirms the adaptability of the adjustment process through dynamic simulation and strategy evaluation, and obtains the adjusted operation strategy record;

[0124] The Operation Strategy Adjustment submodule uses the comprehensive analysis dataset as input to adjust the operation strategy of thermal equipment. Using dynamic simulation technology, the module simulates the effects of different operation strategies and evaluates their adaptability and effectiveness in actual operation. Through iterative adjustments and simulation testing, the module fine-tunes operating parameters such as temperature settings, pressure control, and load distribution. After confirming the effectiveness of the adjustment process, it generates a record of the adjusted operation strategy, detailing the new strategy and its expected results, providing an updated and optimized operation plan for equipment operation.

[0125] The performance evaluation submodule conducts continuous performance evaluation based on the adjusted operation strategy records, uses quantitative analysis to compare the operation effects before and after the adjustment, evaluates equipment performance and energy consumption optimization results, and generates energy consumption optimization feedback results;

[0126] The performance evaluation submodule continuously evaluates equipment performance based on adjusted operational strategy records. This module uses quantitative analysis to compare operational data before and after adjustments to assess improvements in equipment performance and reductions in energy consumption. Performance evaluation involves monitoring multiple performance indicators, such as combustion efficiency, heat exchange efficiency, and overall energy consumption. Evaluation results help identify which strategy adjustments have a significant impact on performance. The generated energy optimization feedback details the specific benefits of each adjustment, providing accurate feedback for equipment management and optimization, supporting continuous performance improvement and the development of energy management strategies.

[0127] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. Thermal equipment energy-saving optimization system based on energy consumption data analysis, characterized by: The system comprises: The entropy generation monitoring module collects temperature and pressure data of thermal equipment, calculates the entropy generation of each working cycle according to operating conditions, summarizes and analyzes the trend of the data of each cycle, analyzes the energy saving effect of thermal elements, and obtains entropy monitoring results; The abnormal data identification module uses the entropy monitoring results to calculate the self-information of the data points, evaluates the abnormal probability of each point based on statistical rarity, filters the abnormal data points, and compares them with the standard data under normal operation mode to identify abnormal patterns in the energy consumption data and generate abnormal pattern recognition results; The data fusion analysis module collects ambient temperature, humidity and equipment load data, combines the abnormal pattern recognition results, performs data integration and synchronization through hierarchical clustering, extracts key influencing factors, and forms data fusion analysis results; The energy loss location module locates abnormal operation links based on the data fusion analysis results, identifies energy loss points in the operating parameters of the thermal equipment, compares the entropy generation under different operating conditions, draws an energy flow diagram and identifies the key links of energy loss, and generates energy loss location results; The operating parameter adjustment module adjusts the combustion efficiency and heat transfer area of ​​the thermal equipment based on the energy loss location results, continuously monitors the adjustment effect, optimizes and corrects the parameter adjustment in real time, and generates a detailed record of the operating parameter adjustment; The energy consumption optimization feedback module uses the operating parameter adjustment detail records, integrates the real-time monitoring feedback data, adjusts the operation strategy of the thermal equipment, and continuously evaluates the performance of the adjusted thermal equipment to generate energy consumption optimization feedback results.

2. The thermal equipment energy-saving optimization system based on energy consumption data analysis according to claim 1 is characterized in that: The entropy monitoring results include periodic data analysis records, thermal efficiency assessment results and energy consumption indicators; the abnormal pattern recognition results include abnormal point positioning results, abnormal type classification results and abnormal intensity assessment results; the data fusion analysis results include key influencing factors and comprehensive data views; the energy loss positioning results include key loss areas, loss degree quantification records and influencing parameter identification results; the operating parameter adjustment detail records include parameter adjustment range, comparison results before and after adjustment and adjustment effect tracking records; the energy consumption optimization feedback results include performance improvement points, energy saving assessment records and optimization strategy effectiveness feedback records.

3. The thermal equipment energy-saving optimization system based on energy consumption data analysis according to claim 1 is characterized in that: The entropy generation monitoring module includes a data collection submodule, an entropy calculation submodule, and a trend analysis submodule; The data collection submodule monitors thermal equipment through sensors, captures temperature and pressure data of thermal equipment at various operating stages, records corresponding operating conditions and environmental parameters, and obtains the original data set of the equipment; The entropy calculation submodule analyzes the original data set of the device, calculates the entropy variable caused by the changes in temperature and pressure data in each working cycle, evaluates the energy conversion efficiency, and generates the cycle entropy generation amount; The trend analysis submodule performs statistical analysis and data summarization on the periodic entropy generation, performs time series analysis to identify trends and patterns in the data, reveals the change pattern of thermal element performance over time, and obtains entropy monitoring results.

4. The thermal equipment energy-saving optimization system based on energy consumption data analysis according to claim 3 is characterized in that: The entropy variable is according to the formula: Calculation is performed, where ΔS represents the entropy variable value, P i Represents the pressure value at the beginning of the cycle, V i Represents the internal volume of the thermal equipment piston at the beginning of the cycle, P f Represents the pressure value at the end of the cycle, V f represents the volume value at the end of the cycle, ΔQ represents the heat value absorbed or released during the cycle, T represents the average temperature during the cycle, and K is the Boltzmann constant.

5. The thermal equipment energy-saving optimization system based on energy consumption data analysis according to claim 1 is characterized in that: The abnormal data identification module includes a self-information calculation submodule, an abnormal probability assessment submodule, and a pattern comparison and identification submodule; The self-information calculation submodule uses the entropy monitoring results to perform real-time data flow analysis, extract information from each data point, calculate the self-information of the data point, determine the statistical importance of the information, and generate an information index set; The anomaly probability assessment submodule performs probability analysis on the data points based on the rarity of the information quantity indicator set, calculates the local outlier factor of the data points, determines high-risk anomalies using threshold judgment, and obtains a probability distribution record of the anomaly points; The pattern comparison and recognition submodule combines the historical data of the thermal equipment, compares the high-risk abnormal points recorded in the abnormal point probability distribution, analyzes the deviation from the normal data, identifies the abnormal pattern in the energy consumption data, and obtains the abnormal pattern recognition result.

6. The thermal equipment energy-saving optimization system based on energy consumption data analysis according to claim 5 is characterized in that: The local outlier factor is according to the formula: Calculation is performed, where LOF(k) represents the local outlier factor, k represents the number of neighboring points considered, lrd(o) represents the local reachability density of object o, lrd(p) is the local reachability density of k neighboring points p of o, N k (o) is the neighborhood set containing the k points closest to o.

7. The thermal equipment energy-saving optimization system based on energy consumption data analysis according to claim 1 is characterized in that: The data fusion analysis module includes a data acquisition submodule, a hierarchical clustering submodule, and an impact factor extraction submodule; The data acquisition submodule synchronously collects ambient temperature and humidity data through the sensor array, and collects real-time load data of thermal equipment, verifies data synchronization and accuracy, and generates environmental and load data sets; The hierarchical clustering submodule integrates the environment and load data sets with the abnormal pattern recognition results, performs hierarchical clustering processing, synchronizes the data at each layer, analyzes the consistency and relevance of the data during the processing process, and generates a clustered integrated data set; The influencing factor extraction submodule performs data mining based on the clustering integration data set, identifies key influencing factors that directly affect equipment performance, refines key factors, and obtains data fusion analysis results.

8. The thermal equipment energy-saving optimization system based on energy consumption data analysis according to claim 1 is characterized in that: The energy loss positioning module includes an abnormal operation positioning submodule, an energy loss identification submodule, and an energy flow direction drawing submodule; The abnormal operation location submodule performs abnormal detection and refinement to identify operation deviations based on the data fusion analysis results, analyzes the operation data of each link of the thermal equipment, locates the operation link that deviates from the standard operation parameters, and generates an abnormal operation point data set; The energy loss identification submodule uses the abnormal operation point data set and compares it with the standard operation state to analyze the entropy generation of each operation link. Through data difference analysis, it identifies the key operating parameters of energy loss and obtains the energy loss key parameter set. The energy flow drawing submodule uses the energy loss key parameter set to perform data visualization processing, draw an energy flow diagram, mark the energy loss position of the key link, and generate an energy loss positioning result.

9. The thermal equipment energy-saving optimization system based on energy consumption data analysis according to claim 1 is characterized in that: The operating parameter adjustment module includes an efficiency adjustment submodule, a continuous monitoring submodule, and a real-time optimization correction submodule; The efficiency adjustment submodule analyzes the combustion efficiency and heat transfer area of ​​the thermal equipment based on the energy loss location results, adjusts the operating parameters to optimize the thermal efficiency, and simultaneously performs data feedback loop adjustment to generate an adjusted operating parameter data set; The continuous monitoring submodule performs real-time data monitoring and continuous tracking based on the adjusted working parameter data set, analyzes the continuity and stability of the adjusted parameters, and obtains a continuous monitoring data set; The real-time optimization and correction submodule collects real-time data of thermal equipment based on the continuous monitoring data set, analyzes and confirms the optimization and adjustment effect, synchronously performs dynamic parameter correction on the thermal equipment, and generates detailed records of operation parameter adjustments.

10. The thermal equipment energy-saving optimization system based on energy consumption data analysis according to claim 1 is characterized in that: The energy consumption optimization feedback module includes a data comprehensive analysis submodule, an operation strategy adjustment submodule, and a performance evaluation submodule; The data comprehensive analysis submodule analyzes the real-time monitoring feedback data based on the detailed records of the operating parameter adjustments, extracts key indicators of equipment performance, identifies performance changes by comparing the differences between the before and after data, and generates a comprehensive analysis data set; The operation strategy adjustment submodule uses the comprehensive analysis data set to adjust the operation strategy of the thermal equipment, confirms the adaptability of the adjustment process through dynamic simulation and strategy evaluation, and obtains the adjusted operation strategy record; The performance evaluation submodule performs continuous performance evaluation based on the adjusted operation strategy records, uses quantitative analysis to compare the operation effects before and after the adjustment, evaluates the equipment performance and energy consumption optimization results, and generates energy consumption optimization feedback results.

Images