Flue gas waste heat recovery method and related equipment

Abstract

The invention provides a flue gas waste heat recovery method and related equipment, and is applied to the technical field of data processing. According to the method, to-be-evaluated heat source plant information and a training sample set are obtained, the to-be-evaluated heat source plant information is preprocessed, target flue gas information, heating plan information and target gas boiler information are generated, the target flue gas information and the target gas boiler information are processed, and a target heat source plant operation influence factor set is generated. Obtaining an initial flue gas waste heat calculation model matched with the target heat source plant operation influence factor set, processing the initial flue gas waste heat calculation model based on the training set and the verification set to generate a target flue gas waste heat calculation model, and processing the target heat source plant operation influence factor set based on the target flue gas waste heat calculation model to generate a target flue gas waste heat calculation model; and generating a flue gas recovery utilization rate of the to-be-evaluated heat source plant, processing the flue gas recovery utilization rate of the to-be-evaluated heat source plant, and generating flue gas waste heat recovery information of the to-be-evaluated heat source plant.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a flue gas waste heat recovery method and related equipment. Background Art

[0002] At present, heating in northern China still relies on high-temperature heat sources such as large boiler rooms and cogeneration for a long time, and heat is supplied to users through the heat network system. However, this method directly uses fossil fuels or high-grade heat (steam, high-temperature water 120 / 130℃, etc.) to meet low-grade heating needs (30℃), resulting in energy grade mismatch and unreasonable application, resulting in low energy utilization efficiency.

[0003] In recent years, a large number of waste incineration power plants, biomass power plants and other projects around cities have developed rapidly. The inventors found that the energy efficiency of existing power plants and heat source plants of this type is low and the economic cost is high. One of the important reasons is that there is a large amount of energy loss, mainly the low-temperature waste heat of flue gas and the waste heat of exhaust steam after power generation are directly discharged into the atmosphere, causing heat loss, so that energy cannot be efficiently utilized. As one of the main forms of energy supply, coal-fired power plants play an important role in electricity production; however, coal-fired power plants still face a series of challenges in energy transformation and environmental protection, including low energy utilization efficiency and large amounts of flue gas emissions; flue gas waste heat recovery is of great significance to improving the operating efficiency of coal-fired power plants and reducing greenhouse gas emissions.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of this application is to provide a flue gas waste heat recovery method and related equipment, which at least overcomes the problems existing in the prior art to a certain extent, calculates the flue gas waste heat recovery amount by collecting key information such as flue gas emissions, exhaust gas temperature and boiler operating parameters, generates risk management factors through a flue gas waste heat recovery risk warning table, analyzes and determines risk association values, generates flue gas waste heat recovery information, and improves flue gas waste heat recovery performance.

[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present invention.

[0007] According to one aspect of the present application, a method for recovering flue gas waste heat is provided, comprising: obtaining information of a heat source plant to be evaluated and a training sample set; preprocessing the information of the heat source plant to be evaluated to generate target flue gas information, heating plan information and target gas boiler information, wherein the target flue gas information includes exhaust information within a preset time period and exhaust temperature information matching the exhaust information; processing the target flue gas information and the target gas boiler information to generate a set of operating influencing factors of a target heat source plant; obtaining an initial flue gas waste heat calculation model that matches the set of operating influencing factors of the target heat source plant; processing the training sample set based on preset processing rules to generate a training set and a verification set; processing the initial flue gas waste heat calculation model based on the training set and the verification set to generate a target flue gas waste heat calculation model; processing the set of operating influencing factors of the target heat source plant based on the target flue gas waste heat calculation model to generate a flue gas recovery rate of the heat source plant to be evaluated; processing the flue gas recovery rate of the heat source plant to be evaluated to generate flue gas waste heat recovery information of the heat source plant to be evaluated.

[0008] In one embodiment of the present application, the information of the heat source plant to be evaluated is preprocessed to generate target flue gas information, heating plan information and target gas boiler information, including: performing data cleaning processing on the information of the heat source plant to be evaluated to generate attribute information of the heat source plant to be evaluated, wherein the attribute information of the heat source plant to be evaluated includes the total heat supply of the heat source plant to be evaluated, heating information for each time period, heating efficiency of the electric heat source plant to be evaluated, heating range of the electric heat source plant to be evaluated, and gas boiler equipment information; the total heat supply of the heat source plant to be evaluated, heating information for each time period and heating range of the electric heat source plant to be evaluated are processed to generate heating plan information, and the gas boiler equipment information is processed to generate target boiler information; the heating information for each time period is processed based on the target boiler information to generate target flue gas information.

[0009] In one embodiment of the present application, the target flue gas information and the target gas boiler information are processed to generate a set of target heat source plant operation influencing factors, including: processing the target gas boiler information to generate physical property information of the target gas boiler information; performing feature extraction processing on the physical property information of the target gas boiler information to generate a number of feature sample types; performing feature screening processing on the several feature sample types to generate real-time feature sample data; processing the target flue gas information based on the heating plan information to generate a flue gas emission difference; and generating a set of target heat source plant operation influencing factors based on a number of real-time feature sample data and the flue gas emission difference.

[0010] In one embodiment of the present application, a set of operating influencing factors of a target heat source plant is generated based on a number of real-time feature sample data and the flue gas emission difference, including: obtaining preset warning data; processing the flue gas emission difference based on the preset warning data to generate a classification standard; preprocessing a number of real-time feature sample data based on the classification standard to output a number of categories of classified data; and using the several categories of classified data as a set of operating influencing factors of a target heat source plant.

[0011] In one embodiment of the present application, a training sample set is processed based on a preset processing rule to generate a training set and a validation set, including: processing the training sample set to generate a training sample set with identification information, wherein the identification information is used to characterize that there is an abnormality in the operation influencing factors of other heat source plants; extracting features from the training sample set with identification information to generate a feature data set; obtaining any number of data features in the feature data set; generating adjacent features based on the distance between the any number of data features and other numbers of data features of the same category, wherein the adjacent features include a preset number of the any number of data features; determining a sampling ratio based on the number of each data feature in the training set; determining a sampling ratio based on the sampling ratio; sampling the adjacent features based on the sampling ratio to generate a preset number of sampling features; generating multiple data groups based on any data feature and each sampling feature, wherein each data group includes a preset number of data samples, wherein each data group includes a preset number of data samples, wherein at least one data sample includes identification information; processing multiple data groups to generate a training set and a validation set, wherein the training set and the validation set both include a number of data features.

[0012] In one embodiment of the present application, the target heat source plant operation influencing factor set is processed based on the target flue gas waste heat calculation model to generate the flue gas recovery rate of the heat source plant to be evaluated, including: processing the target heat source plant operation influencing factor set based on the target flue gas waste heat calculation model to generate flue gas emission status data corresponding to different classification data; processing the flue gas emission status data corresponding to different classification data based on preset processing rules to generate risk association values ​​of different classification data; processing the risk association values ​​of different classification data to generate flue gas waste heat recovery amount; processing the flue gas waste heat recovery amount to generate the flue gas recovery rate of the heat source plant to be evaluated; the target flue gas waste heat calculation model also includes a calculation formula for calculating the risk association values ​​of different classification data, and the calculation formula is: The target flue gas waste heat calculation model also includes a calculation formula for calculating the risk association values ​​of different classification data, and the calculation formula is:

[0013] R i =f(ΔT i, m i );

[0014] ΔT i =T e,i -T a,i ;;

[0015] Among them, R i is the risk association value of the i-th category, f is the weighting function, ΔT i is the temperature difference of the i-th type of flue gas, T e,i is the emission temperature of the i-th category flue gas, T a,i is the ideal recovery temperature threshold of the i-th category flue gas, m i is the mass flow rate of the i-th category flue gas;

[0016] The target flue gas waste heat calculation model also includes a calculation formula for calculating the flue gas recovery rate, which is:

[0017] Q recovered，i =R i ·m i ·C p ΔT i ;

[0018] Q recovered =∑i Q recovered,i =∑i R i ·m i ·C p ΔT i ;

[0019] Q recovered，i is the expected waste heat recovery amount of the i-th type of flue gas, Q recovered is the sum of all types of flue gas waste heat recovery, R i is the risk association value of the i-th category, C p is the specific heat capacity of flue gas;

[0020]

[0021] Among them, r is the flue gas recovery rate, Σi Q recovered，i is the sum of all types of flue gas waste heat recovery, ∑tQ total ,t is the sum of the total heat output of the boiler at different time periods, μ boiler , t is the boiler thermal efficiency in the corresponding period.

[0022] In one embodiment of the present application, the flue gas recovery rate of the heat source plant to be evaluated is processed to generate flue gas waste heat recovery information of the heat source plant to be evaluated, including: obtaining a preset flue gas waste heat recovery risk warning table; processing the flue gas recovery rate of the heat source plant to be evaluated based on the preset flue gas waste heat recovery risk warning table to generate a risk management factor; processing the risk management factor to generate a target warning time and a warning level matching the target warning time; processing the target warning time and the warning level matching the target warning time to generate the flue gas waste heat recovery information of the heat source plant to be evaluated.

[0023] Another aspect of the present application is a flue gas waste heat recovery device, characterized in that it includes: an acquisition module for acquiring information of a heat source plant to be evaluated and a training sample set; acquiring an initial flue gas waste heat calculation model that matches the set of operating influencing factors of the target heat source plant; a processing module for preprocessing the information of the heat source plant to be evaluated, generating target flue gas information, heating plan information and target gas boiler information, wherein the target flue gas information includes exhaust information within a preset time period and exhaust temperature information matching the exhaust information; processing the target flue gas information and the target The gas boiler information is processed to generate a set of operating influencing factors of the target heat source plant; the training sample set is processed based on the preset processing rules to generate a training set and a verification set; the initial flue gas waste heat calculation model is processed based on the training set and the verification set to generate a target flue gas waste heat calculation model; the target heat source plant operating influencing factor set is processed based on the target flue gas waste heat calculation model to generate a flue gas recovery rate of the heat source plant to be evaluated; the flue gas recovery rate of the heat source plant to be evaluated is processed to generate flue gas waste heat recovery information of the heat source plant to be evaluated.

[0024] According to another aspect of the present application, an electronic device is provided, characterized in that it comprises: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to implement the above-mentioned flue gas waste heat recovery method by executing the executable instructions.

[0025] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a second processor, the above-mentioned method for recovering waste heat of flue gas is implemented.

[0026] According to another aspect of the present application, a computer program product is provided, including a computer program, characterized in that when the computer program is executed by a third processor, the above-mentioned flue gas waste heat recovery method is implemented.

[0027] The present application provides a flue gas waste heat recovery method and related equipment, which collects key information such as flue gas emissions, exhaust gas temperature and boiler operating parameters, and establishes a training sample set to calculate the flue gas waste heat recovery amount, evaluate the thermal energy content, generate risk management factors through the flue gas waste heat recovery risk warning table, and analyze and determine the risk association value. Based on these values, the warning time and level are set to generate flue gas waste heat recovery information, including emission status, recovery potential and risk level. Finally, the recovery strategy is continuously monitored and optimized to improve energy efficiency and reduce environmental impact, ensuring that the heat source plant can effectively manage and improve the flue gas waste heat recovery performance.

[0028] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A flow chart showing a method for recovering waste heat from flue gas provided in one embodiment of the present application;

[0030] Figure 2 A schematic structural diagram of a flue gas waste heat recovery device provided in one embodiment of the present application is shown;

[0031] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application is shown;

[0032] Figure 4 A schematic diagram of a storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0033] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0034] Combine the following Figure 1 To describe the flue gas waste heat recovery method according to the exemplary embodiment of the present application. It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present application, and the implementation of the present application is not limited in this regard. On the contrary, the implementation of the present application can be applied to any applicable scenario.

[0035] In one embodiment, the present application also proposes a flue gas waste heat recovery method and related equipment. Figure 1 The following schematically shows a flow chart of a method for recovering waste heat from flue gas according to an embodiment of the present application. Figure 1 As shown, the method is applied to a server, comprising:

[0036] S101, obtaining information of the heat source plant to be evaluated and a training sample set.

[0037] In one implementation, relevant information about the heat source plant to be evaluated is collected to identify what types of data need to be collected, such as flue gas emissions, exhaust gas temperature, and operating parameters of gas boilers (including combustion efficiency, fuel type, boiler load, etc.). Determine from which sources the data can be obtained, such as field measurements, historical records, sensor data, operation logs, etc. Develop a detailed data collection plan, including the time, frequency, method, and person in charge of the collection. If feasible, conduct field measurements to obtain accurate flue gas emissions and exhaust gas temperature data. Use sensors and instruments installed in boilers and flue gas emission systems to collect real-time data, and review historical data to understand seasonal changes and long-term trends in boiler operation.

[0038] Collect data sets for model training. These data should include past flue gas emissions and corresponding recovery efficiencies. Ensure that the collected data is comprehensive and accurate, and provide a solid foundation for evaluating flue gas recovery rates and optimizing waste heat recovery systems.

[0039] Perform preliminary analysis on the collected data to identify patterns, trends and outliers in the data, evaluate the potential risks and uncertainties of the flue gas waste heat recovery system based on the collected data, and prepare the data set, including feature selection, data standardization, and division into training and test sets.

[0040] S102, preprocessing the heat source plant information to be evaluated to generate target flue gas information, heating plan information and target gas boiler information.

[0041] In one embodiment, the target smoke information includes smoke exhaust information within a preset time period and smoke exhaust temperature information matching the smoke exhaust information.

[0042] The data of the heat source plant to be evaluated is cleaned and processed to generate the attribute information of the heat source plant to be evaluated, wherein the attribute information of the heat source plant to be evaluated includes the total heat supply of the heat source plant to be evaluated, the heating information of each time period, the heating efficiency of the electric heat source plant to be evaluated, the heating range of the electric heat source plant to be evaluated, and the gas boiler equipment information. The total heat supply of the heat source plant to be evaluated, the heating information of each time period, and the heating range of the electric heat source plant to be evaluated are processed to generate the heating plan information, and the gas boiler equipment information is processed to generate the target boiler information. The target gas boiler information is mainly used to judge whether the current heating efficiency, heating time, and waiting time of the target gas boiler are in a normal state. Based on the target boiler information, the heating information of each time period is processed to generate the target flue gas information.

[0043] Heating plan information is one of the key factors in determining the design and operation of the flue gas waste heat recovery system. The required flue gas volume is determined based on the heating plan information, and the corresponding steps for flue gas waste heat recovery are formulated. Specifically, the heat load demand of the heating area is analyzed, including the total heating area, the duration of the heating season, the daily heating time period, etc. The efficiency of the existing heating system is evaluated, including the thermal efficiency of the boiler, the transmission efficiency of the heat network, and the terminal heat dissipation efficiency.

[0044] Calculate the total heat required for the entire heating season based on heating demand and efficiency, and evaluate the flue gas volume and heat generated during the heating period based on boiler operating parameters and fuel type. Analyze the temperature, flow and composition of the flue gas to determine the heat that can be recovered through the waste heat recovery system, and formulate a practical and feasible waste heat recovery target based on heating demand and flue gas waste heat recovery potential.

[0045] Design a suitable waste heat recovery system, including heat exchangers, heat pumps, heat storage equipment, etc., to meet the needs of the heating plan. According to the changes in the heating plan and the actual operation, adjust the operating parameters of the waste heat recovery system in real time, optimize the waste heat recovery amount, and conduct risk assessments on different classified data, and formulate risk association values ​​to reflect the risks and recovery potential of different flue gas emission status data. Ensure that the flue gas waste heat recovery system matches the heating plan, improve energy efficiency, reduce heating costs, and reduce environmental impact.

[0046] S103: Process the target flue gas information and the target gas boiler information to generate a set of operating influencing factors of a target heat source plant.

[0047] In one embodiment, the target gas boiler information is processed to generate physical property information of the target gas boiler information. Specifically, the basic physical property data of the boiler is collected, including the size (length, width, height) of the boiler, fuel type, design heat load, actual heat load, boiler material, etc., and the thermal efficiency is calculated based on the input (fuel consumption) and output (heat of steam or hot water generated) of the boiler. Boiler performance tests are performed, including ignition tests, load change tests, stability tests, etc., to obtain performance data of the boiler under different working conditions. The historical operation data of the boiler is analyzed, including past thermal efficiency, fault records, maintenance records, etc., to evaluate whether the performance of the boiler has changed over time. The impact of boiler materials and sizes on thermal efficiency and durability is evaluated. For example, some materials may perform better at high temperatures, and the size of the boiler may affect its heat loss. The operating parameters of the boiler, such as combustion temperature, pressure, flow, etc., are monitored in real time to evaluate the immediate working status of the boiler. According to the maintenance records and fault history, the reliability of the boiler and possible fault points are analyzed, as well as their impact on the efficiency and life of the boiler. Statistics are collected on the total operating time and periodic working time of the boiler, including heating time and standby time (i.e. time in standby or non-operating state), to establish standards for the normal operating state of the boiler, including a reasonable range of thermal efficiency, threshold of failure rate, maintenance cycle, etc.

[0048] Based on the collected data and preset standards, it is determined whether the boiler is in normal condition. If the thermal efficiency of the boiler is lower than the normal range, or the failure rate exceeds the threshold, it may indicate that the boiler needs maintenance or overhaul. The collected data is analyzed to predict potential failures and maintenance needs to achieve predictive maintenance and reduce unexpected downtime.

[0049] Perform feature extraction on the physical property information of the target gas boiler information to generate several feature sample types, analyze the physical property information of the boiler, extract several feature sample types, these features may include the thermal load of the boiler, fuel type, combustion efficiency, etc., perform feature screening on several feature sample types to generate real-time feature sample data, screen the feature sample types, and screen out real-time feature sample data based on criteria such as importance, stability, and measurability.

[0050] Specifically, detailed physical property information of the boiler is collected, including but not limited to the size, material, design parameters, fuel type, combustion efficiency, emission level, etc. of the boiler, and key features that can represent the performance of the boiler are extracted from the collected data. These features include but are not limited to: thermal load: the heat output capacity of the boiler under different working conditions; fuel type: the type of fuel used, such as natural gas, liquefied petroleum gas, etc.; combustion efficiency: the efficiency of fuel combustion converted into thermal energy; emission parameters: the emission levels of pollutants such as CO, NOx, SOx, etc.; heat loss: the heat loss rate during boiler operation; boiler pressure and temperature range: pressure and temperature parameters during operation; equipment age and maintenance status: the service life and maintenance of the boiler.

[0051] Analyze the degree of impact of each feature on boiler performance and determine their importance. Use statistical methods or machine learning techniques, such as correlation analysis, regression analysis, etc. Evaluate the stability of features over time and select those that are stable in long-term operation. Ensure that the selected features are measurable, that is, accurate data can be obtained through existing monitoring equipment or methods. Screen according to the importance, stability, and measurability of the features, remove those with low importance, unstable, or difficult to measure, and screen the feature sample types. According to the importance, stability, and measurability, screen out real-time feature sample data.

[0052] Combine the selected features with the real-time monitoring system to ensure that the data of these features can be collected in real time, clean the real-time collected data, handle missing values, outliers and noise, ensure data quality, and perform necessary transformation and engineering processing on the selected features, such as normalization, standardization or feature construction. Use the processed data to generate real-time feature samples, which can be used for real-time monitoring and analysis of boiler performance. Ensure that the physical property information of the boiler is effectively extracted and screened, and the generated real-time feature sample data can accurately reflect the operating status of the boiler, providing support for boiler performance optimization and fault prevention.

[0053] The target flue gas information is processed based on the heating plan information to generate a flue gas emission difference. Specifically, the total heat required and the heating demand for each time period are determined based on the heating plan information. This includes the heat load demand of residential, commercial and industrial users, and the flue gas emissions of the boiler during the heating period are estimated using historical data and forecasting models. This can be predicted by the thermal efficiency and fuel consumption of the boiler.

[0054] Monitor the temperature, flow rate, chemical composition and other parameters of flue gas in real time to ensure compliance with environmental regulations. Compare the predicted flue gas emissions with the actual monitored emissions and calculate the difference. This difference reflects the accuracy of flue gas emission prediction and the effectiveness of the control strategy. According to the flue gas emission difference, adjust the heating plan and boiler operating parameters, optimize combustion efficiency, and reduce unnecessary energy waste and pollutant emissions. Record the flue gas emission difference and related adjustment measures, and generate reports regularly for environmental compliance review and continuous improvement. Ensure that its flue gas emissions are controlled within the predetermined target, while optimizing heating efficiency and environmental performance.

[0055] Generate a set of influencing factors for the operation of the target heat source plant based on several real-time feature sample data and flue gas emission differences. Use the heating plan information to determine the expected flue gas emissions, compare them with the actual emission data, and calculate the difference, which reflects the deviation between boiler operation and expectations. Combine the real-time feature sample data and flue gas emission differences, and identify the key factors affecting boiler operation through data mining techniques such as pattern recognition and cluster analysis. Construct a risk assessment model, incorporate the identified influencing factors into the model, and evaluate the impact of different factors on boiler operation efficiency and safety.

[0056] Monitor the boiler operation status in real time, dynamically adjust the boiler operation parameters according to the output of the risk assessment model, optimize combustion efficiency and reduce emissions, establish a feedback mechanism, and use the results of the operation adjustment again for the update of the characteristic sample data to form a closed-loop optimization system. Generate a detailed report to display the key influencing factors and risk assessment results of the boiler operation, provide decision support for operation managers, monitor and optimize the boiler operation in real time, improve energy efficiency, reduce environmental impact, and ensure safe operation.

[0057] In another embodiment, a target heat source plant operation influencing factor set is generated based on a number of real-time characteristic sample data and the flue gas emission difference, specifically including:

[0058] Obtain preset warning data, collect and organize preset warning data for flue gas emission monitoring, including but not limited to historical emissions, historical emission concentrations, historical operating conditions, etc. Process the flue gas emission difference based on the preset warning data, generate classification standards, monitor the current flue gas emission data in real time, and compare it with the preset warning data to calculate the difference, which reflects the deviation of the boiler operation status. According to the flue gas emission difference, combined with professional knowledge and historical experience, define different classification standards, such as excessive emissions, low efficiency, etc., for subsequent data processing.

[0059] Based on the classification standard, several real-time feature sample data are preprocessed to output several categories of classified data. The real-time data collected during boiler operation is cleaned, standardized and normalized to ensure data quality. The preprocessed real-time feature sample data is classified according to the classification standard to generate data sets of different categories.

[0060] Several types of classified data are used as the set of operating influencing factors of the target heat source plant. Each type of classified data is analyzed to extract key operating influencing factors, such as combustion efficiency, fuel type, flue gas composition, etc., to form a set of operating influencing factors of the target heat source plant. The set of operating influencing factors is used for risk assessment to determine the possible problems and risks in boiler operation. According to the assessment results and the set of influencing factors, the control strategy of the boiler is optimized and the operating parameters are adjusted to improve efficiency, reduce emissions and ensure safety. The operating status of the boiler and flue gas emissions are continuously monitored, and new data is fed back to the system to continuously optimize and adjust the classification standards and the set of operating influencing factors. It can more accurately evaluate the operating status of the boiler, promptly discover and deal with potential problems, ensure that the boiler operates in the best state, and meet environmental protection requirements.

[0061] S104, obtaining an initial flue gas waste heat calculation model that matches the target heat source plant operation influencing factor set.

[0062] In one implementation, the operating data of the target heat source plant is first collected, including flue gas emissions, flue gas temperature, gas boiler operating parameters, etc. These data will serve as the basis for establishing a calculation model, and these data will be analyzed to identify key factors affecting flue gas waste heat recovery efficiency, such as boiler load, fuel type, combustion efficiency, flue gas temperature, etc.

[0063] According to the identified influencing factors, select the appropriate calculation model, which can be based on physical principles, such as the heat balance equation, or use empirical formulas, such as statistical models based on historical data. Apply the collected data to the calculation model to determine the model parameters, such as specific heat capacity, mass flow rate, temperature difference, etc. These parameters are crucial to the accuracy of the model. The heat distribution and temperature characteristics in the flue gas can be accurately evaluated, so as to design a more efficient waste heat recovery system, improve energy utilization efficiency, and evaluate the potential impact of waste heat recovery on reducing pollutant emissions and lowering carbon footprint.

[0064] S105, processing the training sample set based on preset processing rules to generate a training set and a validation set.

[0065] In one embodiment, a training sample set is processed to generate a training sample set with identification information, wherein the identification information is used to characterize the presence of abnormalities in operating influencing factors of other heat source plants, feature extraction is performed on the training sample set with identification information to generate a feature data set, and any number of data features in the feature data set are obtained. Based on the distance between any number of data features and other numbers of data features of the same category, adjacent features are generated, wherein the adjacent features include a preset number of any number of data features.

[0066] Based on the number of data features in the training set, determine the sampling ratio; based on the sampling ratio, determine the sampling ratio; based on the sampling ratio, sample adjacent features to generate a preset number of sampling features; based on any data feature and each sampling feature, generate multiple data groups, wherein each data group includes a preset number of data samples; wherein each data group includes a preset number of data samples; wherein at least one data sample includes identification information; and processing the multiple data groups to generate a training set and a validation set, wherein the training set and the validation set each include a number of data features.

[0067] Based on the distance between any number of data features and other number of data features of the same category, adjacent features are generated, wherein the adjacent features include a preset number of any number of data features; in the field of data analysis and machine learning, generating adjacent features based on the distance between data features is a feature engineering method that aims to discover the relationship and pattern between features. Specifically, a certain number of data features are selected from the feature data set, which can reflect the use of electronic certificates, and the distance between any data feature and other data features of the same category is calculated using a distance metric (such as Euclidean distance, Manhattan distance or cosine similarity). According to the calculated distance, other data features closest to any data feature are determined, and these features are considered to be adjacent. A preset number is set, that is, the number of data features that are expected to be included in the adjacent feature set. For each data feature, the preset number of data features closest to it is selected to form an adjacent feature set, and the adjacent feature set is analyzed to identify the potential relationships and patterns between the features, which may be crucial to understanding the use of electronic certificates, and the importance of each data feature in the adjacent feature set is evaluated to determine which features are most critical to predicting the target variable. That is, which places may users go to in which time periods, and whether there is a sequence of appearance between different places, etc.

[0068] If there are too many features in the adjacent feature set, it may be necessary to apply dimensionality reduction techniques (such as principal component analysis PCA) to reduce the number of features while retaining important information. The generated adjacent feature set is used to train the machine learning model to predict or classify the use of electronic certificates, evaluate the performance of the model, such as accuracy, recall rate, and F1 score, and optimize the model as needed. It may be necessary to adjust the preset number and distance measurement method multiple times to find the optimal feature set. This method can better understand the complexity of the use of electronic certificates and improve the predictive ability of the early warning model. This is very important for the security management and risk assessment of electronic certificates. At the same time, this also helps to improve the model's ability to identify abnormal behaviors and ensure the security and reliability of the electronic certificate system.

[0069] Based on the number of data features in the training set, a sampling ratio is determined; based on the sampling ratio, a sampling ratio is determined; based on the sampling ratio, adjacent features are sampled to generate a preset number of sampling features; based on any data feature and each sampling feature, multiple data groups are generated, wherein each data group contains a preset number of data samples, wherein each data group contains a preset number of data samples, wherein at least one data sample includes identification information.

[0070] In data analysis and machine learning, the sampling ratio and sampling rate are determined based on the number of data features in the training set. By counting the number of each data feature in the training set, the distribution of different features can be understood. The sampling ratio is determined based on the number of data features and the size of the data set. The sampling ratio can help us decide how many samples to extract from each feature. According to the sampling ratio, the specific sampling ratio can be calculated. The sampling ratio is the ratio of the actual number of samples to the total number. The adjacent features are sampled using the sampling ratio to generate a preset number of sampled features. This process ensures the representativeness and diversity of the samples. Through the sampling process, a set of sampled features is generated, which will be used for subsequent data analysis and model training. Multiple data sets are constructed based on any data feature and each sampled feature. Each data set contains a preset number of data samples. Ensure that the samples in each data set are diverse and contain at least one sample with identification information, which helps the model learn the feature performance in different situations. Use these data sets for model training to evaluate the contribution of different features to the prediction target. Use the sampled feature set to train the machine learning model and evaluate the performance of the model through the validation set. According to the results of model training and validation, the sampling ratio and rate may need to be adjusted to optimize the prediction ability of the model. With this approach, large-scale data sets can be processed efficiently while maintaining data quality and model generalization capabilities, helping to identify potential security risks and abnormal behaviors.

[0071] The feature data set is divided into a training set and a validation set, usually randomly allocated in a certain ratio (such as 80% training set, 20% validation set). The initial document recognition model is trained using the training set, and the model parameters are iteratively optimized. The model performance is evaluated on the validation set, and the model structure or parameters are adjusted to improve accuracy and generalization ability. Based on the performance on the validation set, the model is further optimized using techniques such as cross-validation and hyperparameter tuning. After the training and validation process is completed, an optimized target document recognition model is obtained, which can be used for actual document recognition tasks. A comprehensive evaluation of the target document recognition model is performed, including indicators such as accuracy, recall, and F1 score.

[0072] S106: Process the initial flue gas waste heat calculation model based on the training set and the validation set to generate a target flue gas waste heat calculation model.

[0073] In one implementation, the model is tested using a validation data set to evaluate the model's prediction accuracy. Based on the test results, the model is adjusted and optimized as necessary, and the verified and adjusted initial flue gas waste heat calculation model is applied to the target heat source plant to predict the flue gas waste heat recovery amount and evaluate the recovery efficiency. Based on the model's prediction results, a risk assessment is performed to provide decision support for the operation and management of the heat source plant, such as adjusting boiler operating parameters to optimize waste heat recovery efficiency.

[0074] During the actual operation, the flue gas emissions and boiler operating status are continuously monitored, new data is collected, and the calculation model is regularly updated to ensure the accuracy and applicability of the model. This ensures that the flue gas waste heat recovery system of the heat source plant operates efficiently, and at the same time provides a scientific basis for the energy conservation, emission reduction and sustainable development of the heat source plant.

[0075] S107, processing the target heat source plant operation influencing factor set based on the target flue gas waste heat calculation model to generate a flue gas recovery rate of the heat source plant to be evaluated.

[0076] In one embodiment, the target heat source plant operation influencing factor set is processed based on the target flue gas waste heat calculation model to generate flue gas emission status data corresponding to different classification data, and the flue gas emission status data corresponding to different classification data is processed based on preset processing rules to generate risk association values ​​of different classification data. The risk association value can be used as a weighting factor for the waste heat recovery amount to reflect the actual recoverability of different types of flue gas. The real-time operation data of the target flue gas and gas boiler are collected, including exhaust temperature, flue gas flow, fuel consumption, etc., as well as environmental parameters such as outdoor temperature. The collected data is used to evaluate the thermal efficiency of the boiler and the thermal energy content of the flue gas emissions through the flue gas waste heat calculation model to generate a set of operation influencing factors.

[0077] According to the preset processing rules, the real-time data is divided into different categories, such as high-efficiency operation, medium-efficiency operation and low-efficiency operation, etc. For each classification, the risk association value is calculated, which can be determined based on the deviation of the flue gas emission status data from the preset efficiency standard or historical data. According to the high or low risk association value, a risk level is assigned to each classified data, such as low risk, medium risk and high risk. The calculated flue gas emission status data, risk association value, risk level and flue gas recovery rate are integrated into a report to provide decision support for the heat source plant, continuously monitor flue gas emissions and boiler operation status, adjust risk management strategies and waste heat recovery plans according to real-time data, and optimize system performance.

[0078] Heat source plants can monitor and optimize flue gas waste heat recovery efficiency in real time, reduce operational risks, and improve energy efficiency. In actual operation, it may also be necessary to consider the economic benefits and environmental impact of flue gas waste heat recovery to ensure the economic feasibility and environmental friendliness of waste heat recovery projects. At the same time, data analysis of flue gas emission monitoring systems is also crucial, which can help companies better understand their emissions, ensure compliance, optimize production processes, improve efficiency, and reduce environmental impact.

[0079] The risk association values ​​of different classified data are processed to generate the flue gas waste heat recovery amount. According to the waste heat calculation model and the set of operating influencing factors, the corresponding flue gas emission status data is calculated for each type of classified data. According to the preset processing rules, these data are converted into risk association values. By comprehensively processing the risk association values ​​of all categories, the total flue gas waste heat recovery amount is estimated. The flue gas waste heat recovery amount is processed to generate the flue gas recovery rate of the heat source plant to be evaluated.

[0080] Specifically, the risk association value of each classification is calculated based on the flue gas emission status data and the set of operating influencing factors. These values ​​may be based on the deviation of parameters such as flue gas temperature, flow rate, chemical composition, etc. from the preset standard or historical optimal performance. The flue gas waste heat calculation model is used in combination with the risk association value to evaluate the waste heat recovery potential of each classification, which usually involves a quantitative analysis of the energy content of the flue gas. For each classification, the amount of flue gas waste heat recovery is calculated based on its risk association value, which is completed through appropriate thermodynamic formulas, such as using a heat balance equation.

[0081] If the risk-related values ​​of different categories have different weights, the waste heat recovery amount is weighted according to these weights to reflect the actual recoverability of different categories. The weighted waste heat recovery amounts of all categories are summarized to obtain the total waste heat recovery amount of the entire heat source plant, and the total heat output of the boiler during the assessment period is determined, which includes the total heat generated by burning fuel. The calculated flue gas waste heat recovery amount and recovery rate are integrated and analyzed in depth to identify opportunities for improvement and potential risks. A detailed report is generated to show the calculation results of the flue gas waste heat recovery amount and recovery rate, as well as the impact on the operating efficiency of the heat source plant. This information is used to provide decision support for the operation and management of the heat source plant, such as adjusting boiler operating parameters, optimizing the waste heat recovery system, or upgrading equipment. Based on the results of the recovery rate, a continuous improvement plan is formulated to improve energy efficiency, reduce energy costs, and reduce environmental impacts. The efficiency of flue gas waste heat recovery can be systematically evaluated, energy utilization can be optimized, and data support can be provided for achieving higher energy efficiency and environmental goals.

[0082] The target flue gas waste heat calculation model also includes a calculation formula for calculating the risk association value of different classification data, and the calculation formula is:

[0083] R i =f(ΔT i , m i );

[0084] ΔT i =T e,i -T a,i ;;

[0085] Among them, R i is the risk association value of the i-th category, f is a weighting function, including the weighting of temperature difference and mass flow rate to reflect the potential and risk of waste heat recovery, ΔT i is the temperature difference of the i-th category flue gas, that is, the difference between the actual temperature of the flue gas and the lowest temperature when it is recycled, representing the available temperature difference in the flue gas, T e,i is the emission temperature of the i-th category flue gas, T a,i is the ideal recovery temperature threshold of the i-th category flue gas, that is, when the flue gas temperature is lower than this value, it has recovery value, m i is the mass flow rate of the i-th category of flue gas, that is, the mass of flue gas flowing through a certain cross section per unit time;

[0086] The target flue gas waste heat calculation model also includes a calculation formula for calculating the flue gas recovery rate, which is:

[0087] Q recovered，i =R i ·m i ·C p ΔT i ;

[0088] Q recovered =∑i Q recovered,i =Σi R i ·m i ·C p ΔT i ;

[0089] Q recovered，i is the expected waste heat recovery amount of the i-th type of flue gas, Q recovered is the sum of all types of flue gas waste heat recovery, R i is the risk association value of the i-th category, which serves as the weighting factor for waste heat recovery of flue gas of this category, reflecting the actual recoverability of different types of flue gas, C p The specific heat capacity of flue gas, which indicates the amount of heat that a unit mass of flue gas can absorb or release when the temperature changes, is usually related to the temperature and composition of the flue gas;

[0090]

[0091] Among them, r is the flue gas recovery rate, ∑i Q recovered，i is the sum of all types of flue gas waste heat recovery, ∑tQ total ,t is the sum of the total heat output of the boiler at different time periods, μ boiler , t is the boiler thermal efficiency in the corresponding period.

[0092] S108, processing the flue gas recovery rate of the heat source plant to be evaluated to generate flue gas waste heat recovery information of the heat source plant to be evaluated.

[0093] In one implementation, a preset flue gas waste heat recovery risk warning table is obtained, and the flue gas recovery utilization rate of the heat source plant is processed based on this table to generate a risk management factor, and then generate a target warning time and warning level, and finally generate flue gas waste heat recovery information, specifically: obtain a preset flue gas waste heat recovery risk warning table, which usually includes risk levels and related parameters under different flue gas emission conditions. A preset flue gas waste heat recovery risk warning table usually includes risk levels and related parameters under different flue gas emission conditions, and these parameters may involve the temperature, flow rate, chemical composition, etc. of the flue gas. The purpose of this warning table is to evaluate the operating risks of the flue gas waste heat recovery system and take corresponding measures to ensure the safety and efficiency of the system.

[0094] The early warning table will classify risks into different levels, such as low risk, medium risk and high risk, based on different parameters of flue gas emissions, such as temperature and flow rate. Thresholds for various parameters will be set in the table. When the actual measured values ​​reach or exceed these thresholds, the system will automatically increase the warning level. The early warning system needs to monitor various parameters of flue gas emissions in real time and compare them with the standards in the early warning table. Once a potential risk is detected, the system will immediately issue an early warning and take corresponding feedback measures. Early warning signals may include different levels of alarms, such as sound and light alarms, automatic notifications to operation managers, etc., to ensure timely response.

[0095] The early warning table will also include management measures for different risk levels, such as reducing boiler load, adjusting combustion parameters or conducting equipment inspections. The risk early warning table needs to be evaluated and updated regularly to adapt to new operating conditions and technical requirements. The parameter thresholds and risk levels in the early warning table should comply with local environmental protection regulations and industrial standards to ensure the compliance of the flue gas waste heat recovery system. Through such an early warning table, the heat source plant can promptly discover and deal with risks that may arise in the flue gas waste heat recovery process, ensuring the stable operation of the system and the safety of the environment.

[0096] Based on the preset flue gas waste heat recovery risk warning table, the flue gas recovery rate of the heat source plant to be evaluated is processed to generate risk management factors. The flue gas waste heat calculation model is used in combination with the operating data of the heat source plant to evaluate the current flue gas recovery rate, including parameters such as the total heat output of the boiler, flue gas emissions, and exhaust temperature. According to the risk warning table and the evaluation results of the flue gas recovery rate, risk management factors are generated for the flue gas recovery system of the heat source plant. These factors include the stability of flue gas emissions, system reliability, environmental impact, and economy. Risk management factors are key variables for evaluating and controlling potential risks of flue gas waste heat recovery systems. They may include but are not limited to the following aspects: Flue gas emissions and temperature are direct factors affecting waste heat recovery efficiency. The more emissions and the higher the temperature, the greater the potential for waste heat recovery; the thermal efficiency of the boiler directly affects the quality and quantity of waste heat. Improved thermal efficiency can increase the recoverability of waste heat; lower exhaust temperature can help improve waste heat recovery efficiency, but too low exhaust temperature may increase recovery costs; the reliability and maintenance status of waste heat recovery system equipment determine the stability and long-term operating efficiency of the system; including external environmental temperature, humidity, etc., these factors may affect the recovery and utilization efficiency of flue gas waste heat; involving safety risks in the operation process, such as risks caused by improper equipment operation or violation of operating procedures; risks caused by improper technology selection or untimely technology updates; involving economic factors such as project investment return rate, cost-benefit analysis, etc.; relevant environmental laws and regulations and policy changes may have an impact on waste heat recovery projects; energy market price fluctuations may affect the economic benefits of waste heat recovery projects. By identifying, evaluating and controlling these risk management factors, the potential risks in flue gas waste heat recovery projects can be effectively managed and reduced to ensure the smooth progress and long-term stable operation of the project.

[0097] The risk management factors are processed to generate target warning moments and warning levels that match the target warning moments. Based on the risk management factors, the target warning moments are determined, that is, when the flue gas waste heat recovery system needs to be adjusted or maintained. At the same time, the corresponding warning levels are generated according to the severity of the risk. The determination of the warning level is usually based on the evaluation results of the risk management factors, which reflect the potential risks and uncertainties of the flue gas waste heat recovery system. Specifically, a comprehensive evaluation is conducted on the risk management factors of the flue gas waste heat recovery system, including boiler efficiency, fuel characteristics, combustion efficiency, environmental conditions, etc., and the risk management factors are converted into quantifiable risk values, such as determining the size and possibility of the risk through probability distribution, risk matrix and other methods.

[0098] Risks are divided into different levels according to their size and possibility. Common levels include low risk (green), medium risk (yellow), high risk (orange) and extremely high risk (red). Warning thresholds are set for each risk level. When the risk value reaches or exceeds a specific threshold, a warning of the corresponding level is triggered. By real-time monitoring of the system operation status, the warning level is dynamically adjusted to ensure the timeliness and accuracy of the warning.

[0099] According to the warning level, corresponding warning information is issued, including warning level, warning time, possible impact and recommended response measures. According to different levels of risks, corresponding emergency plans are formulated to ensure rapid and effective response when risks occur, strengthen risk communication with relevant personnel, improve their risk awareness and response capabilities, and improve risk management skills through training. According to the warning results and actual events, the setting of risk management factors and warning levels is continuously optimized to achieve continuous improvement of risk management. In this way, potential risks in the flue gas waste heat recovery process can be effectively monitored and warned, operational risks can be reduced, and the stability and reliability of the system can be improved.

[0100] The target warning time and the warning level that matches the target warning time are processed to generate the flue gas waste heat recovery information of the heat source plant to be evaluated. This information will guide the heat source plant to take corresponding measures to optimize the flue gas waste heat recovery efficiency and reduce potential risks. The flue gas waste heat recovery information of the heat source plant to be evaluated should include the following key aspects: Flue gas emission status: including flue gas composition, temperature, flow rate and other parameters, which are the basis for evaluating the potential of flue gas waste heat recovery; Efficiency of waste heat recovery system: involves how much heat energy in the flue gas can be recovered by the system and converted into usable heat energy. Environmental impact: Evaluate the potential impact of the waste heat recovery system on reducing pollutant emissions and lowering carbon footprint, in compliance with environmental regulations; Technology and equipment status: Including the technical parameters, operating status and maintenance of the waste heat recovery equipment to ensure that the equipment can operate stably and efficiently; Economic analysis: Evaluate the investment cost, operating cost and income of the waste heat recovery project to determine the economic benefits of the project; Risk assessment: Based on risk management factors, evaluate the possible risks in the waste heat recovery process, such as equipment failure, changes in market demand, etc., and formulate corresponding risk control measures; Operation optimization suggestions: Based on the flue gas emission status and waste heat recovery efficiency, put forward suggestions for optimizing boiler operation and waste heat recovery system to improve overall energy efficiency and economy. This information will provide a comprehensive flue gas waste heat recovery assessment for the heat source plant, helping it to optimize energy utilization, reduce operating costs, and ensure environmental compliance.

[0101] In this application, the server obtains the information of the heat source plant to be evaluated and the training sample set; performs data cleaning processing on the information of the heat source plant to be evaluated to generate the attribute information of the heat source plant to be evaluated, wherein the attribute information of the heat source plant to be evaluated includes the total heat supply of the heat source plant to be evaluated, the heating information of each time period, the heating efficiency of the electric heat source plant to be evaluated, the heating range of the electric heat source plant to be evaluated, and the gas boiler equipment information; the total heat supply of the heat source plant to be evaluated, the heating information of each time period, and the heating range of the electric heat source plant to be evaluated are processed to generate the heating plan information, and the gas boiler equipment information is processed to generate the target boiler information ; Based on the target boiler information, the heating information of each time period is processed to generate the target flue gas information, wherein the target flue gas information includes the exhaust information within a preset time period and the exhaust temperature information matching the exhaust information; the target gas boiler information is processed to generate the physical property information of the target gas boiler information; the physical property information of the target gas boiler information is subjected to feature extraction processing to generate several feature sample types; the feature screening processing is performed on several feature sample types to generate real-time feature sample data; the target flue gas information is processed based on the heating plan information to generate the flue gas emission difference.

[0102] Obtain preset warning data, process flue gas emission differences based on the preset warning data, generate classification standards, preprocess several real-time feature sample data based on the classification standards, output several types of classified data, and use the several types of classified data as a set of operating influencing factors of the target heat source plant. Obtain an initial flue gas waste heat calculation model that matches the set of operating influencing factors of the target heat source plant, process the training sample set, generate a training sample set with identification information, wherein the identification information is used to characterize the existence of abnormalities in the operating influencing factors of other heat source plants, perform feature extraction on the training sample set with identification information, generate a feature data set, obtain any number of data features in the feature data set, generate adjacent features based on the distance between any number of data features and other numbers of data features of the same category, wherein the adjacent features include a preset number of any number of data features, and determine based on the number of each data feature in the training set. Sampling ratio, based on the sampling ratio, determine the sampling ratio, sample adjacent features based on the sampling ratio, generate a preset number of sampling features, generate multiple data groups based on any data feature and each sampling feature, wherein each data group contains a preset number of data samples, wherein each data group contains a preset number of data samples, wherein at least one data sample includes identification information, process the multiple data groups to generate a training set and a validation set, wherein the training set and the validation set both include a number of data features, process the initial flue gas waste heat calculation model based on the training set and the validation set, and generate a target flue gas waste heat calculation model.

[0103] Based on the target flue gas waste heat calculation model, the target heat source plant operation influencing factor set is processed to generate flue gas emission status data corresponding to different classification data; based on the preset processing rules, the flue gas emission status data corresponding to different classification data are processed to generate risk association values ​​of different classification data; the risk association values ​​of different classification data are processed to generate the flue gas waste heat recovery amount; the flue gas waste heat recovery amount is processed to generate the flue gas recovery rate of the heat source plant to be evaluated; the preset flue gas waste heat recovery risk warning table is obtained; the flue gas recovery rate of the heat source plant to be evaluated is processed based on the preset flue gas waste heat recovery risk warning table to generate risk management factors; the risk management factors are processed to generate a target warning time and a warning level matching the target warning time; the target warning time and the warning level matching the target warning time are processed to generate the flue gas waste heat recovery information of the heat source plant to be evaluated. Collect key information such as flue gas emissions, exhaust gas temperature and boiler operating parameters, establish a training sample set, calculate the flue gas waste heat recovery amount, evaluate the thermal energy content, generate risk management factors through the flue gas waste heat recovery risk warning table, and analyze and determine the risk association value. Set the warning time and level based on these values, and generate flue gas waste heat recovery information, including emission status, recovery potential and risk level. Finally, continuously monitor and optimize the recovery strategy to improve energy efficiency and reduce environmental impact, ensuring that the heat source plant can effectively manage and improve the flue gas waste heat recovery performance.

[0104] In one embodiment, if Figure 2 As shown, the present application also provides a flue gas waste heat recovery device, comprising:

[0105] The acquisition module 201 is used to acquire information of the heat source plant to be evaluated and a training sample set; and to acquire an initial flue gas waste heat calculation model that matches the set of operating influencing factors of the target heat source plant;

[0106] The processing module 202 is used to pre-process the information of the heat source plant to be evaluated, generate target flue gas information, heating plan information and target gas boiler information, wherein the target flue gas information includes exhaust information within a preset time period and exhaust temperature information matching the exhaust information; process the target flue gas information and the target gas boiler information to generate a set of operating influencing factors of the target heat source plant; process the training sample set based on preset processing rules to generate a training set and a verification set; process the initial flue gas waste heat calculation model based on the training set and the verification set to generate a target flue gas waste heat calculation model; process the set of operating influencing factors of the target heat source plant based on the target flue gas waste heat calculation model to generate a flue gas recovery rate of the heat source plant to be evaluated; process the flue gas recovery rate of the heat source plant to be evaluated to generate flue gas waste heat recovery information of the heat source plant to be evaluated.

[0107] The present application embodiment provides an electronic device, such as Figure 3 As shown, the electronic device 3 includes a first processor 300, a memory 301, a bus 302 and a communication interface 303. The first processor 300, the communication interface 303 and the memory 301 are connected via the bus 302; the memory 301 stores a computer program that can be run on the first processor 300, and when the first processor 300 runs the computer program, the flue gas waste heat recovery method provided in any of the aforementioned embodiments of the present application is executed.

[0108] The memory 301 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 303 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0109] The bus 302 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 301 is used to store programs, and the first processor 300 executes the program after receiving an execution instruction. The flue gas waste heat recovery method disclosed in any implementation of the embodiment of the present application may be applied to the first processor 300, or implemented by the first processor 300.

[0110] The first processor 300 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the first processor 300. The above-mentioned first processor 300 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor to be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 301, and the first processor 300 reads the information in the memory 301 and completes the steps of the above method in combination with its hardware.

[0111] The electronic device provided in the above-mentioned embodiment of the present application and the flue gas waste heat recovery method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0112] The present application embodiment provides a computer-readable storage medium, such as Figure 4 As shown, the computer-readable storage medium 401 stores a computer program, and when the computer program is read and executed by the second processor 402, the aforementioned flue gas waste heat recovery method is implemented.

[0113] The technical solution of the embodiment of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling an electronic device (which may be an air conditioner, a refrigeration device, a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0114] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the flue gas waste heat recovery method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0115] An embodiment of the present application provides a computer program product, including a computer program, wherein the computer program is executed by a third processor to implement the method described above.

[0116] The computer program product provided in the above-mentioned embodiments of the present application and the flue gas waste heat recovery method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0117] It should be noted that, in this application, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or still includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0118] Each embodiment in the present application is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiment of the method for recovering waste heat of flue gas, the electronic device, the electronic device, and the readable storage medium for evaluating waste heat of flue gas, since they are basically similar to the embodiment of the method for recovering waste heat of flue gas, the description is relatively simple, and the relevant parts can be referred to the partial description of the embodiment of the method for recovering waste heat of flue gas.

[0119] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application shall be subject to the scope defined by the claims.

Claims

1. A method for recovering waste heat from flue gas, characterized in that: include: Obtain the information of the heat source plant to be evaluated and the training sample set; Preprocessing the heat source plant information to be evaluated to generate target flue gas information, heating plan information and target gas boiler information, wherein the target flue gas information includes exhaust gas information within a preset time period and exhaust gas temperature information matching the exhaust gas information; Processing the target flue gas information and the target gas boiler information to generate a set of operating influencing factors of a target heat source plant; Acquire an initial flue gas waste heat calculation model that matches the target heat source plant operation influencing factor set; Process the training sample set based on preset processing rules to generate a training set and a validation set; Processing the initial flue gas waste heat calculation model based on the training set and the validation set to generate a target flue gas waste heat calculation model; Processing the target heat source plant operation influencing factor set based on the target flue gas waste heat calculation model to generate a flue gas recovery rate of the heat source plant to be evaluated; The flue gas recovery rate of the heat source plant to be evaluated is processed to generate flue gas waste heat recovery information of the heat source plant to be evaluated.

2. The method according to claim 1, characterized in that The heat source plant information to be evaluated is preprocessed to generate target flue gas information, heating plan information and target gas boiler information, including: Performing data cleaning processing on the information of the heat source plant to be evaluated to generate attribute information of the heat source plant to be evaluated, wherein the attribute information of the heat source plant to be evaluated includes the total heat supply of the heat source plant to be evaluated, heat supply information for each time period, the heat supply efficiency of the electric heat source plant to be evaluated, the heat supply range of the electric heat source plant to be evaluated, and gas boiler equipment information; The total heat supply of the heat source plant to be evaluated, the heat supply information for each time period, and the heat supply range of the electric heat source plant to be evaluated are processed to generate heating plan information. Processing the gas boiler equipment information to generate target boiler information; The heating information of each time period is processed based on the target boiler information to generate target flue gas information.

3. The method according to claim 2, characterized in that The target flue gas information and the target gas boiler information are processed to generate a set of target heat source plant operation influencing factors, including: Processing the target gas boiler information to generate physical property information of the target gas boiler information; Performing feature extraction processing on the physical attribute information of the target gas boiler information to generate a number of feature sample types; Performing feature screening processing on the several feature sample types to generate real-time feature sample data; Processing the target flue gas information based on the heating plan information to generate a flue gas emission difference; A set of operating influencing factors of a target heat source plant is generated based on a number of real-time characteristic sample data and the flue gas emission difference.

4. The method according to claim 3, characterized in that A set of operating influencing factors of a target heat source plant is generated based on a number of real-time characteristic sample data and the flue gas emission difference, including: Obtain preset warning data; Processing the flue gas emission difference based on the preset warning data to generate a classification standard; Preprocessing a number of real-time feature sample data based on the classification standard, and outputting a number of classification data; Several types of classified data are used as a set of influencing factors for the operation of the target heat source plant.

5. The method according to claim 1, characterized in that The training sample set is processed based on the preset processing rules to generate the training set and the validation set, including: Processing the training sample set to generate a training sample set with identification information, wherein the identification information is used to characterize that there are abnormalities in the operation influencing factors of other heat source plants; Extracting features from the training sample set with identification information to generate a feature data set; Obtaining any number of data features in the feature data set; Generate adjacent features based on the distance between the any number of data features and other numbers of data features of the same category, wherein the adjacent features include a preset number of the any number of data features; Determining a sampling ratio based on the number of each data feature in the training set; Based on the sampling ratio, determining a sampling ratio; Sampling the adjacent features based on the sampling ratio to generate a preset number of sampling features; Based on any data feature and each sampling feature, generating a plurality of data groups, wherein each data group comprises a preset number of data samples, wherein each data group comprises a preset number of data samples, wherein at least one data sample comprises identification information; The plurality of data sets are processed to generate a training set and a validation set, wherein the training set and the validation set both include a number of data features.

6. The method according to claim 4, characterized in that The target heat source plant operation influencing factor set is processed based on the target flue gas waste heat calculation model to generate the flue gas recovery rate of the heat source plant to be evaluated, including: Processing the target heat source plant operation influencing factor set based on the target flue gas waste heat calculation model to generate flue gas emission status data corresponding to different classification data; Processing the flue gas emission status data corresponding to different classification data based on preset processing rules to generate risk association values ​​for different classification data; Process the risk association values ​​of different classification data to generate the flue gas waste heat recovery amount; Processing the flue gas waste heat recovery amount to generate a flue gas recovery rate of the heat source plant to be evaluated; The target flue gas waste heat calculation model also includes a calculation formula for calculating the risk association value of different classification data, and the calculation formula is: R i =f(ΔT i ,m i ); ΔT i =T e,i -T a,i ;; Among them, R i is the risk association value of the i-th category, f is the weighting function, ΔT i is the temperature difference of the i-th type of flue gas, T e,i is the emission temperature of the i-th category flue gas, T a,i is the ideal recovery temperature threshold of the i-th category flue gas, m i is the mass flow rate of the i-th category flue gas; The target flue gas waste heat calculation model also includes a calculation formula for calculating the flue gas recovery rate, which is: Q recovered，i =R i ·m i ·C p ·ΔT i ; Q recovered =∑i Q recovered,i =ΣiR i ·m i ·C p ·ΔT i ; Q recovered，i is the expected waste heat recovery amount of the i-th type of flue gas, Q recovered is the sum of all types of flue gas waste heat recovery, R i is the risk association value of the i-th category, C p is the specific heat capacity of flue gas; Among them, r is the flue gas recovery rate, Σi Q recovered，i is the sum of all types of flue gas waste heat recovery, ∑tQ total ,t is the sum of the total heat output of the boiler at different time periods, μ boiler , t is the boiler thermal efficiency in the corresponding period.

7. The method according to claim 6, characterized in that The flue gas recovery rate of the heat source plant to be evaluated is processed to generate flue gas waste heat recovery information of the heat source plant to be evaluated, including: Obtain the preset flue gas waste heat recovery risk warning table; Based on the preset flue gas waste heat recovery risk warning table, the flue gas recovery rate of the heat source plant to be evaluated is processed to generate a risk management factor; Processing the risk management factors to generate a target warning time and a warning level matching the target warning time; The target warning time and the warning level matching the target warning time are processed to generate flue gas waste heat recovery information of the heat source plant to be evaluated.

8. A flue gas waste heat recovery device, characterized in that: The device comprises: An acquisition module is used to acquire information of the heat source plant to be evaluated and a training sample set; and to acquire an initial flue gas waste heat calculation model that matches the set of operating influencing factors of the target heat source plant; A processing module is used to preprocess the information of the heat source plant to be evaluated, generate target flue gas information, heating plan information and target gas boiler information, wherein the target flue gas information includes exhaust information within a preset time period and exhaust temperature information matching the exhaust information; process the target flue gas information and the target gas boiler information to generate a set of operating influencing factors of the target heat source plant; process the training sample set based on preset processing rules to generate a training set and a verification set; process the initial flue gas waste heat calculation model based on the training set and the verification set to generate a target flue gas waste heat calculation model; process the set of operating influencing factors of the target heat source plant based on the target flue gas waste heat calculation model to generate a flue gas recovery rate of the heat source plant to be evaluated; process the flue gas recovery rate of the heat source plant to be evaluated to generate flue gas waste heat recovery information of the heat source plant to be evaluated.

9. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; Wherein, the first processor is configured to execute the flue gas waste heat recovery method according to any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the method for recovering waste heat from flue gas as claimed in any one of claims 1 to 7 is implemented.

Images