System and method for testing and analyzing performance of biological alcohol-based fuel burner

Abstract

The invention discloses a biological alcohol-based fuel burner performance testing and analyzing system and method, and belongs to the field of performance testing. The system comprises a starting instruction sending module used for obtaining flame images, temperature data, pressure data and oxygen concentration data in the combustion process of a biological alcohol-based fuel combustor, and arranging the flame images, the temperature data, the pressure data and the oxygen concentration data into a time sequence data set; the combustion performance score determination module is used for determining a combustion performance score; the optimization module is used for determining abnormal problems and optimization measures; the restarting module is used for obtaining the time sequence data set again; the re-evaluation module is used for re-determining the combustion performance score of the biological alcohol-based fuel combustor; and the storage module is used for storing the time sequence data set before optimization, the abnormal problem and the optimization measure into a performance optimization record if the test is passed. According to the scheme, operation data of the combustor can be processed in real time, and the analysis efficiency is improved; performance changes and abnormities are automatically recognized, and manual intervention is not needed; the performance of the combustor can be gradually improved through repeated testing and optimizing processes.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence, and specifically relates to a bio-alcohol-based fuel burner performance testing and analysis system and method. Background Art

[0002] With the continuous growth of global energy demand and the increasing awareness of environmental protection, finding clean, efficient and renewable alternative energy has become an urgent need in today's world. Bioalcohol-based fuel, as a fuel mainly composed of alcohol substances, has received widespread attention due to its environmental protection, renewability and high calorific value. However, despite the many advantages of bioalcohol-based fuel, its combustion efficiency and the environmental protection of combustion products are still affected by the performance of the burner. As a key equipment for the application of bioalcohol-based fuel, the performance of the burner directly affects the combustion effect of the fuel and the emission of environmental pollutants. Therefore, it is particularly important to perform performance testing and analysis on bioalcohol-based fuel burners.

[0003] Nowadays, the performance test and analysis of bio-alcohol fuel burners is carried out manually, including sample collection, pretreatment, detection and data analysis. First, the fuel sample is collected from the burner; second, the sample is pretreated by filtering and separation to ensure the accuracy of the test; then, the calorific value, composition and other key indicators of the fuel are detected by professional instruments; finally, data analysis is performed based on the test results to evaluate the performance of the burner, providing a scientific basis for optimizing the design and environmental protection and emission reduction.

[0004] However, the results of manual testing are often affected by factors such as the tester's skill level, experience, and judgment criteria, which may lead to poor accuracy and consistency of the test results. In addition, manual testing requires a lot of manpower and time, especially when processing large amounts of data or conducting complex tests, and the efficiency is significantly lower. Summary of the invention

[0005] The present application belongs to the field of artificial intelligence, and specifically relates to a bio-alcohol-based fuel burner performance test and analysis system and method, which solves the problem that the results of manual testing of the performance of bio-alcohol-based fuel burners in the prior art are often affected by factors such as the tester's skill level, experience, and judgment criteria, which may lead to poor accuracy and consistency of the test results; and manual testing requires a lot of manpower and time, especially when processing large amounts of data or conducting complex tests, and the efficiency is significantly lower.

[0006] In a first aspect, an embodiment of the present application provides a bio-alcohol-based fuel burner performance test and analysis system, the system comprising: A start-up instruction sending module is used to send a start-up instruction to the bio-alcohol-based fuel burner, continuously obtain flame images, temperature data, pressure data and oxygen concentration data during the combustion process of the bio-alcohol-based fuel burner, until the bio-alcohol-based fuel burner is finished running, and organize the continuously obtained flame images, temperature data, pressure data and oxygen concentration data into a time series data set; A combustion performance score determination module, used to input the time series data set into a preset combustion performance score model to obtain a combustion performance score of the bio-alcohol-based fuel burner; an optimization module, configured to input the time series data set into a preset performance optimization model if the combustion performance score does not exceed a preset score threshold, obtain a first abnormal problem and a first optimization measure, and send the first abnormal problem and the first optimization measure to a control center; A restart module is used for, if receiving the first optimization completion instruction sent by the control center, re-sending a start instruction to the bio-alcohol-based fuel burner, re-continuously acquiring the flame image, temperature data, pressure data and oxygen concentration data during the combustion process of the bio-alcohol-based fuel burner until the bio-alcohol-based fuel burner is finished running, and re-organizing the continuously acquired flame image, temperature data, pressure data and oxygen concentration data into a time series data set; A re-evaluation module, used for re-inputting the time series data set into a preset combustion performance scoring model to obtain a combustion performance score of the bio-alcohol-based fuel burner; The storage module is used to determine that the bio-alcohol-based fuel burner passes the test if the combustion performance score exceeds a preset score threshold, and store the time series data set before optimization, the first abnormal problem, and the first optimization measure in a performance optimization record.

[0007] Furthermore, the training process of the preset performance optimization model includes: Obtaining performance optimization records, and determining historical abnormal time series data sets, historical performance abnormality problems, and historical performance optimization measures based on the performance optimization records; Labeling the performance anomaly problem label of the historical anomaly time series data set according to the historical performance anomaly problem, and labeling the performance optimization measure label of the historical anomaly time series data set according to the historical performance anomaly optimization measure; A performance optimization model is constructed, and the performance optimization model is trained according to the historical abnormal time series data set, the performance abnormality problem label, and the performance optimization measure label until the optimization model reaches a preset performance optimization model training standard.

[0008] Furthermore, the system also includes a performance optimization model retraining module, and the retraining module is used to: If the re-obtained combustion performance score still does not exceed the preset score threshold, the time series data set before optimization is sent to the control center; Receive the second abnormal problem and the second optimization measure sent by the control center, store the second abnormal problem and the second optimization measure in the performance optimization record, and retrain the preset performance optimization model according to the performance optimization record until the preset performance optimization model reaches the preset performance optimization model training standard.

[0009] Furthermore, the system further includes an environmental friendliness evaluation module, which is used to: Continuously acquiring noise data, thermal radiation data, and harmful gas concentration data during the combustion process of the bio-alcohol-based fuel burner until the bio-alcohol-based fuel burner is finished running, and collating the noise data, thermal radiation data, and harmful gas concentration data into an environmental friendliness test data set; If the environmental friendliness test data set does not meet the preset environmental evaluation standard, the environmental friendliness test data set is input into a preset environmental optimization model to obtain a third abnormal problem and a third optimization measure, and the third abnormal problem and the third optimization measure are sent to the control center; If a second optimization completion instruction is received from the control center, a start instruction is resent to the bio-alcohol-based fuel burner, and the noise data, thermal radiation data, and harmful gas concentration data of the combustion process of the bio-alcohol-based fuel burner are continuously acquired again until the bio-alcohol-based fuel burner is finished running, and the noise data, thermal radiation data, and harmful gas concentration data are reorganized into an environmental friendliness test data set; If the reorganized environmental friendliness test data set meets the preset environmental evaluation standard, the environmental friendliness test data set before optimization, the third abnormal problem and the third optimization measure are stored in the environmental optimization record.

[0010] Furthermore, the training process of the preset environment optimization model includes: Obtaining environmental optimization records, and determining historical abnormal environmental friendliness test data sets, historical environmental abnormality problems, and historical environmental optimization measures based on the environmental optimization records; Labeling the environmental anomaly problem labels of the historical abnormal environmental friendliness test data set according to the historical environmental anomaly problems, and labeling the environmental optimization measure labels of the historical abnormal environmental friendliness test data set according to the historical environmental optimization measures; An environmental optimization model is constructed, and the environmental optimization model is trained according to the historical abnormal environmental friendliness test data set, the environmental abnormality problem label, and the environmental optimization measure label until the environmental optimization model reaches a preset environmental optimization model training standard.

[0011] Furthermore, the system further includes an environment optimization model retraining module, and the environment optimization model retraining module is used to: If the reorganized environmental friendliness test data set does not meet the preset environmental evaluation standard, the environmental friendliness test data set before the reorganization is sent to the control center; Receive the fourth abnormal problem and the fourth optimization measure sent by the control center, store the fourth abnormal problem and the fourth optimization measure in the environmental optimization record, and retrain the preset environmental optimization model according to the environmental optimization record until the preset environmental optimization model reaches the preset environmental optimization model training standard.

[0012] Furthermore, the system further comprises a fault warning module, wherein the fault warning module is used to: Continuously obtaining operating parameters of the bio-alcohol-based fuel burner during combustion, continuously inputting the operating parameters into a preset fault warning model, and continuously determining an operating score; If the operation score exceeds a preset fault score threshold, the fault cause and solution are determined by the preset fault warning model, and the fault cause and solution are transmitted to the control center.

[0013] Furthermore, the training process of the preset fault warning model includes: Obtaining operation records, and determining historical operation parameters and historical operation scores according to the operation records; Annotate the operation score tags of the historical operation parameters according to the historical operation scores, and create a first data set according to the historical operation parameters and the operation score tags; Obtaining fault records, and determining historical fault parameters, historical fault causes, and historical solutions based on the fault records; marking the fault cause labels of the historical fault parameters according to the historical fault causes, and marking the solution labels of the historical fault parameters according to the historical solutions; Creating a second data set based on the historical fault parameters, fault cause labels, and solution labels; A fault warning model is constructed, and the fault warning model is trained according to the first data and the second data set until the fault warning model reaches a preset fault warning model training standard.

[0014] Furthermore, the training process of the preset combustion performance scoring model includes: Acquire a historical time series data set and a historical combustion performance score, and label the combustion performance score label of the historical event sequence data set according to the historical combustion performance score; A combustion performance scoring model is constructed, and the combustion performance scoring model is trained according to the historical time series data set and the combustion performance scoring label until the combustion performance scoring model reaches a preset combustion performance scoring model training standard.

[0015] In a second aspect, an embodiment of the present application provides a method for testing and analyzing the performance of a bio-alcohol-based fuel burner, the method comprising: Sending a start command to the bio-alcohol-based fuel burner, continuously acquiring flame images, temperature data, pressure data, and oxygen concentration data during the combustion process of the bio-alcohol-based fuel burner until the bio-alcohol-based fuel burner is finished running, and collating the continuously acquired flame images, temperature data, pressure data, and oxygen concentration data into a time series data set; Inputting the time series data set into a preset combustion performance scoring model to obtain a combustion performance score of the bioalcohol-based fuel burner; If the combustion performance score does not exceed a preset score threshold, the time series data set is input into a preset performance optimization model to obtain a first abnormal problem and a first optimization measure, and the first abnormal problem and the first optimization measure are sent to a control center; If the first optimization completion instruction sent by the control center is received, a start instruction is resent to the bio-alcohol-based fuel burner, and the flame image, temperature data, pressure data and oxygen concentration data of the bio-alcohol-based fuel burner during the combustion process are continuously acquired again until the bio-alcohol-based fuel burner is finished running, and the continuously acquired flame image, temperature data, pressure data and oxygen concentration data are reorganized into a time series data set; Re-inputting the time series data set into a preset combustion performance scoring model to obtain a combustion performance score of the bio-alcohol-based fuel burner; If the combustion performance score exceeds a preset score threshold, it is determined that the bioalcohol-based fuel burner has passed the test, and the time series data set before optimization, the first abnormal problem, and the first optimization measure are stored in the performance optimization record.

[0016] In an embodiment of the present application, a startup instruction sending module is used to send a startup instruction to the bio-alcohol-based fuel burner, continuously obtain flame images, temperature data, pressure data and oxygen concentration data during the combustion process of the bio-alcohol-based fuel burner, until the bio-alcohol-based fuel burner is finished running, and organize the continuously obtained flame images, temperature data, pressure data and oxygen concentration data into a time series data set; a combustion performance score determination module is used to input the time series data set into a preset combustion performance score model to obtain a combustion performance score of the bio-alcohol-based fuel burner; an optimization module is used to input the time series data set into a preset performance optimization model if the combustion performance score does not exceed a preset score threshold, obtain a first abnormal problem and a first optimization measure, and send the first abnormal problem and the first optimization measure to a control center The restart module is used to send a start instruction to the bio-alcohol fuel burner again if the first optimization completion instruction sent by the control center is received, and the flame image, temperature data, pressure data and oxygen concentration data of the bio-alcohol fuel burner are continuously obtained again during the combustion process until the bio-alcohol fuel burner is completed, and the flame image, temperature data, pressure data and oxygen concentration data continuously obtained are reorganized into a time series data set; the re-evaluation module is used to input the time series data set into the preset combustion performance scoring model again to obtain the combustion performance score of the bio-alcohol fuel burner; the storage module is used to determine that the bio-alcohol fuel burner passes the test if the combustion performance score exceeds the preset scoring threshold, and the time series data set before optimization, the first abnormal problem and the first optimization measure are stored in the performance optimization record. Through the above-mentioned bio-alcohol fuel burner performance test and analysis system, the automatic analysis system can process the operation data of the burner in real time and improve the analysis efficiency. Using the preset model for data analysis, performance changes and anomalies can be automatically identified without manual intervention, reducing human errors. Through repeated testing and optimization processes, the performance of the burner can be gradually improved to ensure that it can maintain the best state under various working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a structural schematic diagram of a bio-alcohol-based fuel burner performance test and analysis system provided in Example 1 of the present application; Figure 2 It is a structural schematic diagram of a bio-alcohol-based fuel burner performance test and analysis system provided in Example 2 of the present application; Figure 3 It is a structural schematic diagram of a bio-alcohol-based fuel burner performance test and analysis system provided in Example 3 of the present application; Figure 4 It is a flow chart of the bio-alcohol-based fuel burner performance test and analysis method provided in Example 4 of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only part of the present application is shown in the accompanying drawings, but not all of the content. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0020] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0021] The bio-alcohol-based fuel burner performance test and analysis system provided in the embodiment of the present application is described in detail below through specific embodiments and application scenarios in conjunction with the accompanying drawings.

[0022] Embodiment 1: Figure 1 This is a schematic diagram of the structure of the bio-alcohol-based fuel burner performance test and analysis system provided in Example 1 of the present application. The system includes: A start-up instruction sending module 101 is used to send a start-up instruction to the bio-alcohol-based fuel burner, continuously obtain flame images, temperature data, pressure data and oxygen concentration data during the combustion process of the bio-alcohol-based fuel burner, until the bio-alcohol-based fuel burner is finished running, and organize the continuously obtained flame images, temperature data, pressure data and oxygen concentration data into a time series data set; A combustion performance score determination module 102 is used to input the time series data set into a preset combustion performance score model to obtain a combustion performance score of the bio-alcohol-based fuel burner; The optimization module 103 is used for inputting the time series data set into a preset performance optimization model if the combustion performance score does not exceed a preset score threshold, obtaining a first abnormal problem and a first optimization measure, and sending the first abnormal problem and the first optimization measure to a control center; The restart module 104 is used to resend a start instruction to the bio-alcohol-based fuel burner if the first optimization completion instruction sent by the control center is received, and to re-continuously obtain the flame image, temperature data, pressure data and oxygen concentration data during the combustion process of the bio-alcohol-based fuel burner until the bio-alcohol-based fuel burner is finished running, and to re-organize the continuously obtained flame image, temperature data, pressure data and oxygen concentration data into a time series data set; A re-evaluation module 105, for re-inputting the time series data set into a preset combustion performance scoring model to obtain a combustion performance score of the bio-alcohol-based fuel burner; The storage module 106 is used to determine that the bio-alcohol-based fuel burner has passed the test if the combustion performance score exceeds a preset score threshold, and store the time series data set before optimization, the first abnormal problem, and the first optimization measure in a performance optimization record.

[0023] Firstly, the application scenario of this solution can be a scenario of performance testing of a bio-alcohol-based fuel burner.

[0024] Based on the above usage scenarios, it can be understood that the executor of the present application can be the bio-alcohol-based fuel burner performance test and analysis system, and no excessive limitations are made here.

[0025] In this solution, the bio-alcohol fuel burner can be a device specially designed for efficiently burning bio-alcohol fuels (such as ethanol, methanol, etc.). It generates heat energy by mixing the fuel with air and igniting it, which is used for heating, power generation or other industrial applications.

[0026] A start instruction may be a signal or command sent to the burner instructing it to begin a working process.

[0027] Flame images can be captured in real time using a high-resolution camera or infrared camera. These images can be used to analyze flame stability, combustion efficiency and other characteristics.

[0028] Temperature data can be obtained by monitoring the temperature changes inside and around the burner in real time through temperature sensors (such as thermocouples or infrared sensors). These data help evaluate the thermal efficiency and safety of the combustion process.

[0029] Pressure data can be the gas pressure information inside the burner obtained by the pressure sensor. This can be used to monitor the operating status of the burner and ensure that it operates within a safe pressure range.

[0030] Oxygen concentration data can be obtained by monitoring the oxygen concentration during the combustion process through an oxygen sensor. This data can help analyze the combustion efficiency and whether there is unburned fuel.

[0031] A time series dataset can be a set of data organized in chronological order, recording the characteristics of a specific phenomenon (such as a combustion process) over time. For a bio-alcohol fuel burner, these datasets will include the changes in various indicators during the operation of the burner. Specifically, they can include timestamps: each data point contains a corresponding time mark, indicating the specific moment of data collection. Data items: including flame images (which can be stored using image sequences), temperature, pressure, oxygen concentration, etc.

[0032] You can use a PLC (Programmable Logic Controller) or remote control system (such as SCADA) to connect to the burner's control system and send start commands manually or automatically through a preset program or remote control interface. Then use a camera or infrared camera to take flame images at regular intervals and store them as image files. Set the acquisition frequency, such as one frame per second or per minute, to ensure a continuous stream of image data. Use a data acquisition system (such as a data recorder or sensor integration module) to collect temperature, pressure, and oxygen concentration data in real time. The data points of each sensor are stored at time intervals to form a continuous time series of temperature, pressure, and oxygen concentration. Each data acquisition point (flame image, temperature, pressure, oxygen concentration) must be associated with a corresponding timestamp to record the exact time point of data acquisition to ensure that the data can be sorted and analyzed. During the operation of the burner, the system continuously collects data. When the combustion process is over, the system automatically stops collecting data and organizes the final time series data set.

[0033] The preset combustion performance scoring model can be a model built by machine learning or statistical analysis methods to evaluate the combustion performance of the burner under specific conditions. The model can be trained based on historical data and consider multiple input features such as temperature, pressure, oxygen concentration, flame morphology, etc.

[0034] The combustion performance score can be an indicator for quantitatively evaluating the efficiency and safety of bio-alcohol-based fuel burners during the combustion process. The score reflects the comprehensive performance of the burner, such as the operating status and combustion efficiency.

[0035] Useful features can be extracted from time series data, such as: average temperature, maximum temperature, temperature fluctuation range, average pressure, maximum pressure, pressure change rate, average oxygen concentration, oxygen concentration fluctuation, and flame morphological features (such as flame area, color change, etc., if image processing capabilities are available). The extracted features will form a set of feature vectors that represent the key dynamic parameters of combustion in each time period. The sorted feature vectors are input into the preset combustion performance scoring model. The model is trained with historical time series data and performance score labels and has the ability to identify burner performance. After receiving the time series data, the model will perform multi-layer analysis on the data. Specifically, it can first perform time dependency analysis. Since the combustion process is dynamic, the model will analyze the changing trends of parameters such as temperature, pressure, and flame morphology. For example, temperature fluctuations and drastic changes in pressure may indicate an unstable combustion process. The model then assigns different importance to each feature based on the weights learned during training. For example, changes in flame morphology in a flame image may have a greater impact on the score than temperature changes. The model combines flame image data and numerical sensor data for comprehensive analysis to generate a unified combustion performance score. The model will comprehensively consider the performance of each feature and calculate the final score of the combustion performance based on the built-in scoring algorithm. The scoring range is usually a score (e.g. 0-100) representing the performance status of the burner. A high score indicates that the burner has a smooth combustion process, high efficiency, and excellent overall performance. A low score indicates that there may be problems with the operation of the burner, such as incomplete combustion, unstable flame, excessive temperature or pressure fluctuations, resulting in low efficiency or potential safety hazards.

[0036] The preset score threshold may be a benchmark score in the combustion performance score used to evaluate whether the burner is operating normally. If the combustion performance score is lower than this threshold, it means that the performance of the burner does not meet the expected standard and there may be a problem.

[0037] The preset performance optimization model can be a machine learning model or expert system for diagnosing burner operation anomalies and providing optimization measures. The model analyzes anomalies in the combustion process by inputting time series data and outputs specific optimization suggestions.

[0038] The first abnormal problem can be the most important performance problem or the reason for poor burner performance identified by the performance optimization model after the combustion performance score is lower than the threshold. Specifically, it can include incomplete combustion of fuel: if the oxygen supply is insufficient or the fuel quality is poor, it may lead to incomplete combustion and reduce efficiency. Excessive combustion temperature fluctuations: Temperature fluctuations may indicate an unstable combustion process, which is usually related to fuel supply, burner design or operating conditions. Inappropriate oxygen concentration: Too much or too little oxygen will affect combustion efficiency. Too much oxygen will increase energy consumption, and too little oxygen will lead to incomplete combustion. Abnormal flame morphology: Through image analysis, abnormal flame morphology (such as uneven combustion or local fire extinguishing) will also affect performance.

[0039] The first optimization measure can be the main improvement plan recommended by the performance optimization model for the first abnormal problem, which aims to solve the performance problem and improve the operating efficiency and safety of the burner. Specifically, it may include adjusting the fuel supply: If the combustion is incomplete, the model may recommend adjusting the fuel supply, such as increasing the fuel supply or improving the fuel quality. Adjusting the oxygen concentration: If the oxygen concentration is not appropriate, the optimization measures may include adjusting the oxygen supply to achieve optimal combustion efficiency. Stabilizing the combustion temperature: If the temperature fluctuates greatly, the model may recommend optimizing the operating conditions of the burner, or adjusting the design of the burner to reduce temperature fluctuations. Flame morphology optimization: If the flame morphology is unstable, the optimization measures may involve adjusting the nozzle design or the fuel injection method to ensure uniform flame distribution.

[0040] The control center can be a centralized monitoring and operating system for real-time management and control of the burner operation.

[0041] The time series data collected in real time (including flame images, temperature, pressure, oxygen concentration, etc.) can be input into the preset performance optimization model. The model analyzes the input data and extracts key features related to combustion performance, such as temperature change rate, oxygen concentration fluctuation amplitude, and flame morphology characteristics. By comparing historical data with current input data, the correlation between these features and combustion performance is analyzed to identify potential influencing factors. The model compares the input features with the normal operating mode learned during training to detect whether there is a significant deviation. If the feature value exceeds the preset normal range, the model will mark an abnormal problem, such as "oxygen concentration is too low" or "flame temperature is unstable." Based on the detection results, the model generates a specific description of the abnormal problem. For example, if the oxygen concentration is low, the model may output "Incomplete combustion caused by insufficient oxygen supply is identified." The first abnormal problem and the first optimization measure are then organized into a clear report or notification format for subsequent processing. The abnormal problem and optimization measures are sent to the control center through the system's communication interface.

[0042] The first optimization completion instruction may be an instruction from the control center to confirm that the optimization measure has been executed and completed after receiving the first abnormal problem and the first optimization measure. The function of this instruction is to notify the system to start a new test process to verify the optimized burner performance.

[0043] The performance optimization record may be a storage structure for recording relevant data of the burner during the optimization process, including time series data before optimization, abnormal problems detected, and implemented optimization measures.

[0044] The first optimization completion instruction sent by the control center can be received through wireless communication technology, and the start command can be resent to the burner according to the instruction to start the burner and enter the test operation mode. After starting, the system continuously collects real-time data of the burner, including flame image, temperature, pressure, oxygen concentration, etc., and obtains these data at a preset frequency. The system continues to collect until the burner is finished. The collected data are arranged in chronological order to form a new time series data set. The sorted new time series data set is input into the trained combustion performance scoring model, and the model analyzes the input data and generates a score for the current burner performance. The system then compares the combustion performance score with the preset score threshold. If the score is higher than or equal to the preset score threshold, it means that the burner performance has passed the test. If the test passes, the system stores the following information in the performance optimization record: Pre-optimization time series data set: the data set before the optimization measures are implemented. First abnormal problem: description of the problem detected in the previous test. First optimization measure: details of the optimization operation used to solve the problem.

[0045] In an embodiment of the present application, a startup instruction sending module is used to send a startup instruction to the bio-alcohol-based fuel burner, continuously obtain flame images, temperature data, pressure data and oxygen concentration data during the combustion process of the bio-alcohol-based fuel burner, until the bio-alcohol-based fuel burner is finished running, and the continuously obtained flame images, temperature data, pressure data and oxygen concentration data are sorted into a time series data set; a combustion performance score determination module is used to input the time series data set into a preset combustion performance score model to obtain a combustion performance score of the bio-alcohol-based fuel burner; an optimization module is used to input the time series data set into a preset performance optimization model if the combustion performance score does not exceed a preset score threshold, obtain a first abnormal problem and a first optimization measure, and send the first abnormal problem and the first optimization measure to a control center ; Restart module, for receiving the first optimization completion instruction sent by the control center, re-sending the start instruction to the bio-alcohol fuel burner, re-continuously acquiring the flame image, temperature data, pressure data and oxygen concentration data during the combustion process of the bio-alcohol fuel burner, until the bio-alcohol fuel burner is completed, and re-organizing the continuously acquired flame image, temperature data, pressure data and oxygen concentration data into a time series data set; Re-evaluation module, for re-inputting the time series data set into a preset combustion performance scoring model to obtain the combustion performance score of the bio-alcohol fuel burner; Storage module, for determining that the bio-alcohol fuel burner passes the test if the combustion performance score exceeds the preset scoring threshold, and storing the time series data set before optimization, the first abnormal problem and the first optimization measure in the performance optimization record. Through the above-mentioned bio-alcohol fuel burner performance test and analysis system, the automatic analysis system can process the operation data of the burner in real time and improve the analysis efficiency. Using the preset model for data analysis, performance changes and anomalies can be automatically identified without manual intervention, reducing human errors. Through repeated testing and optimization processes, the performance of the burner can be gradually improved to ensure that it can maintain the best state under various working conditions.

[0046] Based on the above technical solution, the optional, preset performance optimization model training process includes: Obtaining performance optimization records, and determining historical abnormal time series data sets, historical performance abnormality problems, and historical performance optimization measures based on the performance optimization records; Labeling the performance anomaly problem label of the historical anomaly time series data set according to the historical performance anomaly problem, and labeling the performance optimization measure label of the historical anomaly time series data set according to the historical performance anomaly optimization measure; A performance optimization model is constructed, and the performance optimization model is trained according to the historical abnormal time series data set, the performance abnormality problem label, and the performance optimization measure label until the optimization model reaches a preset performance optimization model training standard.

[0047] In this solution, the historical abnormal time series data set can be a set of time series data collected in the past during the operation of the burner, which corresponds to the time period when the abnormality occurred. The data usually includes parameters such as flame image, temperature, pressure, oxygen concentration, etc.

[0048] Historical performance anomalies can be specific problems identified in the past operation of the burner, such as low combustion efficiency, excessive emissions, etc. They are usually classified and summarized based on real-time monitoring data or historical fault records.

[0049] Historical performance anomalies can be specific problems identified in the past operation of the burner, such as low combustion efficiency, excessive emissions, etc. They are usually classified and summarized based on real-time monitoring data or historical fault records.

[0050] The performance anomaly problem label may be a label used to identify the performance anomaly problem corresponding to each time series data point in the historical anomaly time series data set. The label may be a simple classification mark, such as "inefficient combustion", "high emission", etc.

[0051] The performance optimization measure labels may be labels for identifying the performance optimization measures associated with each time series data point in the historical anomaly time series data set. Similar to the performance anomaly problem labels, these labels identify specific optimization measures taken for each problem.

[0052] The preset performance optimization model training standard can be the standard that the model needs to achieve during the training process, including indicators such as accuracy, recall rate, F1-score, etc. The specific standard will be determined according to the actual application requirements.

[0053] You can collect and organize past operating data, filter out time periods related to performance anomalies, and organize these data into a time series format for subsequent analysis and modeling. Based on the collected historical data, analyze various performance issues and record these issues for use in model training. Then collect and organize the optimization measures implemented for each historical performance anomaly issue, and ensure that these measures are clearly recorded for subsequent analysis of their effects. Based on the previously identified historical performance anomalies, label each time series data point accordingly to ensure that the labels are accurate to improve the effect of model training. Label each historical anomaly time series data point with the optimization measure label related to it to ensure the completeness and accuracy of the label so that the model can identify effective measures. Select a suitable machine learning algorithm (such as decision tree, random forest, support vector machine, etc.). Use historical data sets, anomaly problem labels, and optimization measure labels for model training. During the training process, continuously monitor model performance, compare consistency with preset standards, and make adjustments.

[0054] In this solution, the optimization model can significantly improve the efficiency of the burner by identifying and resolving performance anomalies, and automated data analysis and model application enable the system to perform real-time analysis and improve efficiency.

[0055] On the basis of the above technical solution, optionally, the system further includes a performance optimization model retraining module, and the retraining module is used to: If the re-obtained combustion performance score still does not exceed the preset score threshold, the time series data set before optimization is sent to the control center; Receive the second abnormal problem and the second optimization measure sent by the control center, store the second abnormal problem and the second optimization measure in the performance optimization record, and retrain the preset performance optimization model according to the performance optimization record until the preset performance optimization model reaches the preset performance optimization model training standard.

[0056] In this solution, the second abnormal problem can be a specific problem that the model fails to accurately identify during the burner performance evaluation, which can be found through manual analysis. Specifically, it can include: Decreased combustion efficiency: It is recognized that the burner cannot maintain the expected combustion efficiency under certain conditions, which may be due to improper fuel mixing or insufficient air supply. Unstable flame morphology: The flame state fluctuates, affecting safety and performance.

[0057] The second optimization measure can be the second optimization measure proposed after manual analysis for the above second abnormal problem, and specifically, can include adjusting the fuel ratio: it is recommended to change the fuel ratio to optimize the combustion characteristics and ensure efficiency. Improve the air supply system: optimize the air supply settings to ensure that the burner obtains the best combustion conditions.

[0058] Previously acquired time series data sets, including flame images, temperature, pressure, and oxygen concentration data, can be collated and sent for analysis by the control center. Receive manually analyzed second abnormal problems and their corresponding optimization measures from the control center, which are based on an in-depth analysis of the actual operation of the burner. Add the second abnormal problem and the second optimization measure to the performance optimization record for subsequent analysis and reference. Then use the new data set to retrain the model for the second abnormal problem, select the appropriate machine learning algorithm for training, and adjust the parameters of the model to ensure that it adapts to the new data characteristics and requirements. Then verify the retrained model to ensure its accuracy and reliability, ensure that it can accurately identify future abnormal situations, and check the performance of the model on the new data to confirm whether it meets the preset performance optimization model training standards.

[0059] In this solution, by sending the time series data set before optimization to the control center and receiving the second abnormal problem and optimization measures analyzed by experts, the input data and analysis capabilities of the model can be continuously optimized to improve the accuracy and reliability of the model.

[0060] Based on the above technical solution, the optional, preset combustion performance scoring model training process includes: Acquire a historical time series data set and a historical combustion performance score, and label the combustion performance score label of the historical event sequence data set according to the historical combustion performance score; A combustion performance scoring model is constructed, and the combustion performance scoring model is trained according to the historical time series data set and the combustion performance scoring label until the combustion performance scoring model reaches a preset combustion performance scoring model training standard.

[0061] In this solution, the historical time series data set can refer to the burner operation related data collected within a certain time range, including key parameters such as temperature, pressure, oxygen concentration, etc. These data are arranged in chronological order and reflect the dynamic changes of the combustion process.

[0062] The historical combustion performance score may be a score calculated based on a preset standard or model according to the performance of the burner during historical operation, and is used to evaluate the performance level of the burner.

[0063] The combustion performance score tag may be a tag that associates the historical combustion performance score with the historical time series data set, and is used to identify the combustion performance performance within a specific time period.

[0064] The preset combustion performance scoring model training standard may refer to the performance indicators set during the model training process, such as accuracy, recall rate, etc. The model must meet these standards before the training is considered complete.

[0065] Time series data recorded during the burner's past operation, including various operating parameters, can be collected and stored. Use existing standards or formulas or manual annotations to determine the combustion performance score for each time period and record it. Associate the historical combustion performance score with the corresponding time series data to form a labeled data set. Select an appropriate algorithm (such as regression analysis, machine learning model, etc.) to build a scoring model. Use the historical time series data set and combustion performance score labels for training. Continuously evaluate the performance of the model until it reaches the preset training standard (such as accuracy, loss value, etc.) to ensure the effectiveness of the model.

[0066] In this solution, the analysis of historical data can more accurately evaluate the performance of the burner and help identify potential improvement points. The establishment of the model provides a basis for future data collection and analysis, supporting continuous improvement and performance optimization.

[0067] Embodiment 2: Figure 2 Schematic diagram of the structure of the bio-alcohol fuel burner performance test and analysis system provided in Example 2 of the present application. Figure 2 As shown, specifically including the following: The system further includes an environmental friendliness evaluation module 107, which is used to: Continuously acquiring noise data, thermal radiation data, and harmful gas concentration data during the combustion process of the bio-alcohol-based fuel burner until the bio-alcohol-based fuel burner is finished running, and collating the noise data, thermal radiation data, and harmful gas concentration data into an environmental friendliness test data set; If the environmental friendliness test data set does not meet the preset environmental evaluation standard, the environmental friendliness test data set is input into a preset environmental optimization model to obtain a third abnormal problem and a third optimization measure, and the third abnormal problem and the third optimization measure are sent to the control center; If a second optimization completion instruction is received from the control center, a start instruction is resent to the bio-alcohol-based fuel burner, and the noise data, thermal radiation data, and harmful gas concentration data of the combustion process of the bio-alcohol-based fuel burner are continuously acquired again until the bio-alcohol-based fuel burner is finished running, and the noise data, thermal radiation data, and harmful gas concentration data are reorganized into an environmental friendliness test data set; If the reorganized environmental friendliness test data set meets the preset environmental evaluation standard, the environmental friendliness test data set before optimization, the third abnormal problem and the third optimization measure are stored in the environmental optimization record.

[0068] In this embodiment, the noise data may be sound intensity data collected in real time by a noise sensor during the operation of the bio-alcohol-based fuel burner, usually in decibels (dB), reflecting the noise level generated when the burner is running.

[0069] Thermal radiation data can be thermal radiation data obtained during the combustion process using infrared sensors or thermal imaging equipment. It is usually expressed in units of temperature or thermal radiation intensity (such as watts per square meter) to indicate the heat dissipation of the burner and its surrounding environment.

[0070] Harmful gas concentration data can be the concentration data of harmful gases (such as CO, NOx, SOx, etc.) generated during the combustion process monitored by gas sensors, usually in milligrams per cubic meter (mg / m 3 ) or ppm (parts per million), reflecting the emission conditions of the burner.

[0071] The environmental friendliness test data set can be a comprehensive data set compiled from the above noise data, thermal radiation data and harmful gas concentration data. This data set is used to evaluate the impact of the bio-alcohol-based fuel burner on the environment during operation and help analyze its environmental friendliness.

[0072] After the burner is started, the noise, heat radiation and harmful gas concentration data can be monitored and recorded in real time. Ensure the accuracy and stability of the sensor to obtain reliable data. The collected noise data, heat radiation data and harmful gas concentration data are sorted into an environmental friendliness test data set by timestamp. Each record should contain the corresponding time stamp and the value of each indicator.

[0073] The preset environmental evaluation criteria can be indicators based on regulations, industry standards or best practices to evaluate the impact of the burner on the environment during operation. These criteria may include noise level (such as not exceeding a certain decibel value), heat radiation (such as not exceeding a specific temperature), harmful gas concentration (such as the maximum allowable value of CO, NOx, etc.), etc.

[0074] The third abnormal problem may be a specific problem identified after analyzing the environmental friendliness test data set, such as "NOx concentration is too high during combustion" or "noise level exceeds standard limit".

[0075] The third optimization measure may refer to a specific improvement plan proposed for the third abnormal problem, such as “adjusting the air supply to the burner to reduce NOx emissions” or “installing noise insulation materials around the burner”.

[0076] The sorted environmental friendliness test data set can be input into the preset environmental optimization model. The model will be ready for analysis to determine whether the data meets the preset environmental evaluation standards. Then the environmental optimization model is started, and the model will analyze the input data. Specifically, the model first extracts key features in the environmental friendliness data, such as noise level, thermal radiation, and harmful gas concentration. The model compares the extracted features with the historical abnormal environmental friendliness test data set to find potential abnormal problems. This process may involve machine learning algorithms, using historical tags (such as environmental abnormal problem tags) for identification. During the model analysis process, if it is found that some indicators in the current environmental friendliness test data set do not meet the preset environmental evaluation standards, the model will mark them as "third abnormal problems". For example, if the noise level exceeds the standard, the model will output "noise exceeds the standard" as an abnormal problem. For the identified third abnormal problem, the model will generate the corresponding third optimization measures based on the historical environmental optimization measure tags. For example, if the thermal radiation is detected to be too high, the model may recommend "reducing the combustion temperature" or "increasing the cooling system". Finally, the generated third abnormal problem and its corresponding optimization measures are sent to the control center to ensure that relevant personnel receive the information in time for further processing and improvement.

[0077] The second optimization completion instruction may be a signal from the control center indicating that the third abnormal problem and the third optimization measure for the burner have been implemented and completed. This instruction confirms that all optimization measures have been successfully applied and the burner can now be restarted and tested.

[0078] Environmental optimization records can be a database or document that stores all historical data related to burner performance and environmental impact. This includes environmental friendliness test data sets before optimization, identified abnormal problems, and corresponding optimization measures. This record is used for subsequent analysis, tracking improvement effects, and improving decision-making basis.

[0079] A start command can be sent to the bio-alcohol fuel burner to restart the burner. This is usually done through the control system interface. During the operation of the burner, the noise data, thermal radiation data and harmful gas concentration data are continuously monitored and acquired. After the burner operation ends, the acquired noise data, thermal radiation data and harmful gas concentration data are sorted and merged into a unified environmental friendliness test data set. Ensure that the data format is consistent to facilitate subsequent analysis. The sorted environmental friendliness test data set is then compared with the preset environmental evaluation criteria. If the new environmental friendliness test data set meets the preset environmental evaluation criteria, the environmental friendliness test data set before optimization, the third abnormal problem and the third optimization measure are stored together in the environmental optimization record. Specifically, this can be achieved through a database management system or a document storage solution.

[0080] In this embodiment, the continuous acquisition of noise, heat radiation and harmful gas concentration data can monitor the environmental impact of the burner in real time, which helps to identify potential environmental risks in a timely manner. By inputting the environmental friendliness test data set into the preset environmental optimization model, targeted adjustments can be made for specific abnormal problems and optimization measures to improve the environmental performance of the burner.

[0081] Based on the above technical solution, optionally, the training process of the preset environment optimization model includes: Obtaining environmental optimization records, and determining historical abnormal environmental friendliness test data sets, historical environmental abnormality problems, and historical environmental optimization measures based on the environmental optimization records; Labeling the environmental anomaly problem labels of the historical abnormal environmental friendliness test data set according to the historical environmental anomaly problems, and labeling the environmental optimization measure labels of the historical abnormal environmental friendliness test data set according to the historical environmental optimization measures; An environmental optimization model is constructed, and the environmental optimization model is trained according to the historical abnormal environmental friendliness test data set, the environmental abnormality problem label, and the environmental optimization measure label until the environmental optimization model reaches a preset environmental optimization model training standard.

[0082] In this solution, the historical abnormal environmental friendliness test data set can be a test data set collected in the past that does not meet the environmental assessment standards, including noise data, thermal radiation data, and harmful gas concentration data. This data set helps identify environmental problems that occur during the operation of the burner.

[0083] Historical environmental anomaly issues may be specific issues identified by analyzing historical abnormal environmental friendliness test data sets, such as excessive noise, excessive heat radiation, or excessive concentration of harmful gases in a specific time period.

[0084] Historical environmental optimization measures can be improvement measures implemented in response to historical environmental anomalies, such as adjusting burner operating parameters, optimizing fuel ratios, or performing equipment maintenance, etc. Records of these measures are helpful for subsequent analysis and improvement.

[0085] The environmental anomaly problem label can be a label for each record in the historical abnormal environmental friendliness test data set, indicating the specific environmental anomaly problem corresponding to the record. For example, the label may be "too high noise", "excessive heat radiation" or "excessive concentration of harmful gases".

[0086] The environmental optimization measure label may be a label annotated on each record in the historical abnormal environmental friendliness test data set, indicating the optimization measure adopted by the record. For example, the label may be "lowering the combustion temperature", "increasing the air supply", etc.

[0087] The preset environment optimization model training standards can be used to evaluate whether the environment optimization model training is successful, including the accuracy, recall rate, F1 value, etc. of the model. These standards ensure that the model can effectively identify environmental anomalies and provide corresponding optimization measures.

[0088] Historical environmental optimization records, including past test data, problems, and measures, can be extracted from a database or data storage system. Based on the historical optimization records, test data that does not meet environmental standards is screened out to form a historical abnormal environmental friendliness test data set. For each piece of historical abnormal environmental friendliness test data, its environmental abnormality problem and corresponding optimization measures are labeled to form an environmental abnormality problem label and an environmental optimization measure label. Use the labeled historical abnormal environmental friendliness test data set, environmental abnormality problem label, and environmental optimization measure label to build an environmental optimization model. Machine learning algorithms (such as decision trees, random forests, or neural networks) can be used for training. The model is continuously iterated until the preset environmental optimization model training standard is reached. This process can monitor the performance of the model through the validation set and perform hyperparameter tuning.

[0089] In this solution, by identifying and solving environmental anomalies, the optimization model can significantly reduce the noise, heat radiation and harmful gas emissions generated during the operation of the burner, thereby reducing the negative impact on the environment. By analyzing historical data and training the model, decision-making becomes more scientific and systematic, and corresponding optimization measures can be effectively formulated for specific problems.

[0090] On the basis of the above technical solution, optionally, the system further includes an environment optimization model retraining module, and the environment optimization model retraining module is used to: If the reorganized environmental friendliness test data set does not meet the preset environmental evaluation standard, the environmental friendliness test data set before the reorganization is sent to the control center; Receive the fourth abnormal problem and the fourth optimization measure sent by the control center, store the fourth abnormal problem and the fourth optimization measure in the environmental optimization record, and retrain the preset environmental optimization model according to the environmental optimization record until the preset environmental optimization model reaches the preset environmental optimization model training standard.

[0091] In this solution, the fourth abnormal problem may be that when evaluating the environmental friendliness test data set, the model fails to accurately identify the existing environmental abnormalities, which may include excessive noise, excessive heat radiation, or substandard concentration of harmful gases.

[0092] The fourth optimization measure may be an improvement measure formulated for the fourth abnormal problem, which may involve changing the settings of the burner, adjusting the fuel ratio, or improving the combustion process.

[0093] If the reorganized environmental friendliness test data set does not meet the preset environmental evaluation standard, the data set is sent to the control center. The fourth abnormal problem and the fourth optimization measure are received from the control center. These feedbacks are obtained through manual analysis and are intended to correct the deficiencies in model recognition. The fourth abnormal problem and the fourth optimization measure are stored in the environmental optimization record for subsequent analysis and model training. According to the environmental optimization record, the preset environmental optimization model is retrained. Use the stored abnormal problems and optimization measures to ensure that the model can more accurately identify environmental friendliness-related issues during the next evaluation until the model reaches the preset training standard.

[0094] In this solution, the closed-loop feedback mechanism can drive the continuous evolution of the model to cope with new challenges and changes, ensuring long-term effective operation. Through more accurate monitoring and optimization, potential safety hazards can be reduced and the safe and stable operation of the equipment can be ensured.

[0095] Embodiment three: Figure 3 Schematic diagram of the structure of the bio-alcohol fuel burner performance test and analysis system provided in Example 3 of the present application. Figure 3 As shown, specifically including the following: The system further includes a fault warning module 108, which is used to: Continuously obtaining operating parameters of the bio-alcohol-based fuel burner during combustion, continuously inputting the operating parameters into a preset fault warning model, and continuously determining an operating score; If the operation score exceeds a preset fault score threshold, the fault cause and solution are determined by the preset fault warning model, and the fault cause and solution are transmitted to the control center.

[0096] In this embodiment, the operating parameters may be key data collected in real time during the operation of the bioalcohol-based fuel burner, specifically, may include fuel flow, equipment vibration, combustion efficiency, and startup and shutdown time, etc., reflecting the performance and operating status of the burner.

[0097] The preset fault warning model can be a trained machine learning model that analyzes operating parameters and predicts potential faults. The model is trained based on historical data, including normal operating conditions and parameters when faults occur.

[0098] The operation score can be a value calculated by the model based on the current operating parameters to measure the working status of the burner. If the score is lower than a certain standard, it may indicate a risk of failure.

[0099] The preset fault score threshold can be a specific score limit. When the operation score exceeds this threshold, the system will trigger a fault warning. This threshold is usually set based on historical data analysis and expert experience to ensure that potential problems can be discovered in a timely manner.

[0100] The cause of the fault can be determined through fault warning model analysis. Possible causes include insufficient fuel flow, excessive combustion temperature, etc.

[0101] The solution can be suggestions or measures for the cause of the problem, such as adjusting the fuel flow, checking whether the burner is blocked, etc.

[0102] The operating parameters of the burner, such as temperature, pressure, fuel flow, oxygen concentration, emission concentration, etc., can be collected in real time through sensors and monitoring equipment. These parameters represent the real-time status of the burner. The acquired operating parameters are input into the preset fault warning model in a time series format. The fault warning model analyzes the input operating parameters and calculates an operation score. The score comprehensively reflects the current operating status of the burner and is evaluated in real time through historical data and trained models. The score may be calculated based on factors such as the normal range of the parameters and the degree of deviation. When the operation score exceeds the threshold, the model will use the previously trained data (historical fault parameters, fault cause labels, and solution labels) to identify possible fault causes. The model will infer the cause of the fault based on the comparison of the current operating parameters with the historical data. The determined fault causes and solutions are organized into a report and transmitted to the control center.

[0103] In this embodiment, by quickly identifying and handling faults, the risk of major safety accidents can be reduced, and it can be ensured that the state of the burner during operation is continuously monitored, so that problems can be discovered and responded to in a timely manner.

[0104] On the basis of the above technical solution, optionally, the training process of the preset fault warning model includes: Obtaining operation records, and determining historical operation parameters and historical operation scores according to the operation records; Annotate the operation score tags of the historical operation parameters according to the historical operation scores, and create a first data set according to the historical operation parameters and the operation score tags; Obtaining fault records, and determining historical fault parameters, historical fault causes, and historical solutions based on the fault records; marking the fault cause labels of the historical fault parameters according to the historical fault causes, and marking the solution labels of the historical fault parameters according to the historical solutions; Creating a second data set based on the historical fault parameters, fault cause labels, and solution labels; A fault warning model is constructed, and the fault warning model is trained according to the first data and the second data set until the fault warning model reaches a preset fault warning model training standard.

[0105] In this solution, the operation record may refer to various types of operation data collected during the operation of the bioalcohol-based fuel burner.

[0106] The historical operating parameters may be parameter data extracted from operating records collected in the past, reflecting the operating status of the burner at different time points.

[0107] The historical operation score can be a score calculated based on the operating parameters to evaluate the effectiveness and safety of the burner operation.

[0108] The operation score label can be a label for the historical operation parameters to indicate the operation score corresponding to each set of parameters, for example, good, medium, poor, etc.

[0109] The first data set may be a data set consisting of historical operating parameters and their corresponding operating score labels, which is used for fault warning model training.

[0110] The fault record may contain detailed information of fault events occurring during the operation of the burner, including the time when the fault occurred, relevant parameters and the type of fault.

[0111] Historical fault parameters can be operating parameters extracted from fault records to help analyze the system status when the fault occurs.

[0112] The historical fault cause can be the fault cause indicated in the fault record, which helps to understand the root cause of the fault.

[0113] Historical solutions can be repair measures taken for historical failures to prevent similar failures from happening again.

[0114] The fault cause label can be used to annotate the fault cause of historical fault parameters and provide reference data for model learning.

[0115] The solution label can be used to mark the solution of the historical fault parameters and provide a corresponding solution for the model.

[0116] The second data set may include a data set of historical fault parameters, fault cause labels, and solution labels for use in fault warning model training.

[0117] The preset fault warning model training standard may refer to the performance standard that the model needs to achieve during the training process, such as accuracy, recall rate, etc., which is usually determined through methods such as cross-validation.

[0118] Operation records and fault records can be continuously collected to ensure the timeliness and integrity of the data. Historical operation parameters and operation scores are extracted from the operation records, and operation score labels are generated through annotation to form the first data set. Historical fault parameters are extracted from the fault records, and the causes and solutions of the faults are annotated to form the second data set. Select appropriate machine learning algorithms (such as decision trees, random forests, neural networks, etc.) to build a fault warning model. Input the first and second data sets into the model and train until the model reaches the preset training standard. Use the test set to verify the model, evaluate its performance on new data, and ensure that it has good generalization ability.

[0119] In this solution, through the analysis of historical data, the model can identify potential failure modes, provide early warning, and reduce unexpected downtime.

[0120] Embodiment 4: Figure 4 Schematic diagram of the process of the bio-alcohol fuel burner performance test and analysis method provided in Example 4 of the present application. Figure 4 As shown, the specific steps include: S401, sending a start command to the bio-alcohol-based fuel burner, continuously acquiring flame images, temperature data, pressure data, and oxygen concentration data during the combustion process of the bio-alcohol-based fuel burner until the bio-alcohol-based fuel burner is finished running, and organizing the continuously acquired flame images, temperature data, pressure data, and oxygen concentration data into a time series data set.

[0121] S402, inputting the time series data set into a preset combustion performance scoring model to obtain a combustion performance score of the bioalcohol-based fuel burner.

[0122] S403: If the combustion performance score does not exceed a preset score threshold, the time series data set is input into a preset performance optimization model to obtain a first abnormal problem and a first optimization measure, and the first abnormal problem and the first optimization measure are sent to a control center.

[0123] S404: If the first optimization completion instruction sent by the control center is received, a start instruction is resent to the bio-alcohol-based fuel burner, and the flame image, temperature data, pressure data and oxygen concentration data of the bio-alcohol-based fuel burner during the combustion process are continuously acquired again until the bio-alcohol-based fuel burner is finished running, and the continuously acquired flame image, temperature data, pressure data and oxygen concentration data are reorganized into a time series data set.

[0124] S405, re-inputting the time series data set into a preset combustion performance scoring model to obtain a combustion performance score of the bio-alcohol-based fuel burner.

[0125] S406: If the combustion performance score exceeds a preset score threshold, it is determined that the bioalcohol-based fuel burner has passed the test, and the time series data set before optimization, the first abnormal problem, and the first optimization measure are stored in a performance optimization record.

[0126] In this embodiment, a start instruction is sent to the bio-alcohol-based fuel burner, and the flame image, temperature data, pressure data and oxygen concentration data of the bio-alcohol-based fuel burner during the combustion process are continuously obtained until the bio-alcohol-based fuel burner is finished running, and the continuously obtained flame image, temperature data, pressure data and oxygen concentration data are sorted into a time series data set; the time series data set is input into a preset combustion performance scoring model to obtain a combustion performance score of the bio-alcohol-based fuel burner; if the combustion performance score does not exceed a preset scoring threshold, the time series data set is input into a preset performance optimization model to obtain a first abnormal problem and a first optimization measure, and the first abnormal problem and the first optimization measure are sent to the control center; if the control center is received The first optimization completion instruction sent by the control center, the start instruction is resent to the bio-alcohol fuel burner, the flame image, temperature data, pressure data and oxygen concentration data of the bio-alcohol fuel burner in the combustion process are continuously obtained again, until the bio-alcohol fuel burner is completed, and the flame image, temperature data, pressure data and oxygen concentration data continuously obtained are reorganized into a time series data set; the time series data set is re-input into the preset combustion performance scoring model to obtain the combustion performance score of the bio-alcohol fuel burner; if the combustion performance score exceeds the preset scoring threshold, it is determined that the bio-alcohol fuel burner passes the test, and the time series data set before optimization, the first abnormal problem and the first optimization measure are stored in the performance optimization record. Through the above-mentioned bio-alcohol fuel burner performance test analysis method, the automatic analysis system can process the operation data of the burner in real time and improve the analysis efficiency. Using the preset model for data analysis, performance changes and anomalies can be automatically identified without manual intervention, reducing human errors. Through repeated testing and optimization processes, the performance of the burner can be gradually improved to ensure that it can maintain the best state under various working conditions.

[0127] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also 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 element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0128] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0129] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0130] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A bio-alcohol fuel burner performance test and analysis system, characterized in that: The system comprises: A start-up instruction sending module is used to send a start-up instruction to the bio-alcohol-based fuel burner, continuously obtain flame images, temperature data, pressure data and oxygen concentration data during the combustion process of the bio-alcohol-based fuel burner, until the bio-alcohol-based fuel burner is finished running, and organize the continuously obtained flame images, temperature data, pressure data and oxygen concentration data into a time series data set; A combustion performance score determination module, used to input the time series data set into a preset combustion performance score model to obtain a combustion performance score of the bio-alcohol-based fuel burner; an optimization module, configured to input the time series data set into a preset performance optimization model if the combustion performance score does not exceed a preset score threshold, obtain a first abnormal problem and a first optimization measure, and send the first abnormal problem and the first optimization measure to a control center; A restart module is used for, if receiving the first optimization completion instruction sent by the control center, re-sending a start instruction to the bio-alcohol-based fuel burner, re-continuously acquiring the flame image, temperature data, pressure data and oxygen concentration data during the combustion process of the bio-alcohol-based fuel burner until the bio-alcohol-based fuel burner is finished running, and re-organizing the continuously acquired flame image, temperature data, pressure data and oxygen concentration data into a time series data set; A re-evaluation module, used for re-inputting the time series data set into a preset combustion performance scoring model to obtain a combustion performance score of the bio-alcohol-based fuel burner; The storage module is used to determine that the bio-alcohol-based fuel burner passes the test if the combustion performance score exceeds a preset score threshold, and store the time series data set before optimization, the first abnormal problem, and the first optimization measure in a performance optimization record.

2. The bio-alcohol-based fuel burner performance test and analysis system according to claim 1, characterized in that: The training process of the preset performance optimization model includes: Obtaining performance optimization records, and determining historical abnormal time series data sets, historical performance abnormality problems, and historical performance optimization measures based on the performance optimization records; Labeling the performance anomaly problem label of the historical anomaly time series data set according to the historical performance anomaly problem, and labeling the performance optimization measure label of the historical anomaly time series data set according to the historical performance anomaly optimization measure; A performance optimization model is constructed, and the performance optimization model is trained according to the historical abnormal time series data set, the performance abnormality problem label, and the performance optimization measure label until the optimization model reaches a preset performance optimization model training standard.

3. The bio-alcohol-based fuel burner performance test and analysis system according to claim 2, characterized in that: The system also includes a performance optimization model retraining module, wherein the retraining module is used to: If the re-obtained combustion performance score still does not exceed the preset score threshold, the time series data set before optimization is sent to the control center; Receive the second abnormal problem and the second optimization measure sent by the control center, store the second abnormal problem and the second optimization measure in the performance optimization record, and retrain the preset performance optimization model according to the performance optimization record until the preset performance optimization model reaches the preset performance optimization model training standard.

4. The bio-alcohol-based fuel burner performance test and analysis system according to claim 1, characterized in that: The system further includes an environmental friendliness evaluation module, which is used to: Continuously acquiring noise data, thermal radiation data, and harmful gas concentration data during the combustion process of the bio-alcohol-based fuel burner until the bio-alcohol-based fuel burner is finished running, and collating the noise data, thermal radiation data, and harmful gas concentration data into an environmental friendliness test data set; If the environmental friendliness test data set does not meet the preset environmental evaluation standard, the environmental friendliness test data set is input into a preset environmental optimization model to obtain a third abnormal problem and a third optimization measure, and the third abnormal problem and the third optimization measure are sent to the control center; If a second optimization completion instruction is received from the control center, a start instruction is resent to the bio-alcohol-based fuel burner, and the noise data, thermal radiation data, and harmful gas concentration data of the combustion process of the bio-alcohol-based fuel burner are continuously acquired again until the bio-alcohol-based fuel burner is finished running, and the noise data, thermal radiation data, and harmful gas concentration data are reorganized into an environmental friendliness test data set; If the reorganized environmental friendliness test data set meets the preset environmental evaluation standard, the environmental friendliness test data set before optimization, the third abnormal problem and the third optimization measure are stored in the environmental optimization record.

5. The bio-alcohol-based fuel burner performance test and analysis system according to claim 4, characterized in that: The training process of the preset environment optimization model includes: Obtaining environmental optimization records, and determining historical abnormal environmental friendliness test data sets, historical environmental abnormality problems, and historical environmental optimization measures based on the environmental optimization records; Labeling the environmental anomaly problem labels of the historical abnormal environmental friendliness test data set according to the historical environmental anomaly problems, and labeling the environmental optimization measure labels of the historical abnormal environmental friendliness test data set according to the historical environmental optimization measures; An environmental optimization model is constructed, and the environmental optimization model is trained according to the historical abnormal environmental friendliness test data set, the environmental abnormality problem label, and the environmental optimization measure label until the environmental optimization model reaches a preset environmental optimization model training standard.

6. The bio-alcohol-based fuel burner performance test and analysis system according to claim 5, characterized in that: The system further includes an environment optimization model retraining module, wherein the environment optimization model retraining module is used to: If the reorganized environmental friendliness test data set does not meet the preset environmental evaluation standard, the environmental friendliness test data set before the reorganization is sent to the control center; Receive the fourth abnormal problem and the fourth optimization measure sent by the control center, store the fourth abnormal problem and the fourth optimization measure in the environmental optimization record, and retrain the preset environmental optimization model according to the environmental optimization record until the preset environmental optimization model reaches the preset environmental optimization model training standard.

7. The bio-alcohol-based fuel burner performance test and analysis system according to claim 1, characterized in that: The system further comprises a fault warning module, which is used to: Continuously obtaining operating parameters of the bio-alcohol-based fuel burner during combustion, continuously inputting the operating parameters into a preset fault warning model, and continuously determining an operating score; If the operation score exceeds a preset fault score threshold, the fault cause and solution are determined by the preset fault warning model, and the fault cause and solution are transmitted to the control center.

8. The bio-alcohol-based fuel burner performance test and analysis system according to claim 7, characterized in that: The training process of the preset fault warning model includes: Obtaining operation records, and determining historical operation parameters and historical operation scores according to the operation records; Annotate the operation score tags of the historical operation parameters according to the historical operation scores, and create a first data set according to the historical operation parameters and the operation score tags; Obtaining fault records, and determining historical fault parameters, historical fault causes, and historical solutions based on the fault records; marking the fault cause labels of the historical fault parameters according to the historical fault causes, and marking the solution labels of the historical fault parameters according to the historical solutions; Creating a second data set based on the historical fault parameters, fault cause labels, and solution labels; A fault warning model is constructed, and the fault warning model is trained according to the first data and the second data set until the fault warning model reaches a preset fault warning model training standard.

9. The bio-alcohol-based fuel burner performance test and analysis system according to claim 1, characterized in that: The training process of the preset combustion performance scoring model includes: Acquire a historical time series data set and a historical combustion performance score, and label the combustion performance score label of the historical event sequence data set according to the historical combustion performance score; A combustion performance scoring model is constructed, and the combustion performance scoring model is trained according to the historical time series data set and the combustion performance scoring label until the combustion performance scoring model reaches a preset combustion performance scoring model training standard.

10. A bio-alcohol fuel burner performance test and analysis method, characterized in that: The method comprises: Sending a start command to the bio-alcohol-based fuel burner, continuously acquiring flame images, temperature data, pressure data, and oxygen concentration data during the combustion process of the bio-alcohol-based fuel burner until the bio-alcohol-based fuel burner is finished running, and collating the continuously acquired flame images, temperature data, pressure data, and oxygen concentration data into a time series data set; Inputting the time series data set into a preset combustion performance scoring model to obtain a combustion performance score of the bioalcohol-based fuel burner; If the combustion performance score does not exceed a preset score threshold, the time series data set is input into a preset performance optimization model to obtain a first abnormal problem and a first optimization measure, and the first abnormal problem and the first optimization measure are sent to a control center; If the first optimization completion instruction sent by the control center is received, a start instruction is resent to the bio-alcohol-based fuel burner, and the flame image, temperature data, pressure data and oxygen concentration data of the bio-alcohol-based fuel burner during the combustion process are continuously acquired again until the bio-alcohol-based fuel burner is finished running, and the continuously acquired flame image, temperature data, pressure data and oxygen concentration data are reorganized into a time series data set; Re-inputting the time series data set into a preset combustion performance scoring model to obtain a combustion performance score of the bio-alcohol-based fuel burner; If the combustion performance score exceeds a preset score threshold, it is determined that the bioalcohol-based fuel burner has passed the test, and the time series data set before optimization, the first abnormal problem, and the first optimization measure are stored in the performance optimization record.

Images