Boiler combustion automatic detection control system based on big data model

Abstract

The invention relates to the technical field of boiler combustion control, in particular to a boiler combustion automatic detection control system based on a big data model. The system comprises a data acquisition module used for acquiring various parameter data in a boiler combustion process; the data processing module is used for preprocessing and fusing the collected data; the big data model module constructs a model based on the processed data, learns a combustion process rule and predicts the combustion process rule; the intelligent control module is used for generating a control instruction according to a model prediction result and performing optimization control on boiler combustion equipment; and the monitoring and alarming module is used for monitoring the combustion state and the equipment operation condition in real time, and giving an alarm and taking emergency measures when abnormity occurs. The system overcomes the limitation of traditional boiler combustion control means, realizes comprehensive and accurate monitoring, intelligent and efficient control and advanced fault prediction and treatment of the combustion process, effectively improves the combustion efficiency, reduces the energy consumption and pollutant emission, enhances the operation safety and reliability of the boiler, and is suitable for various industrial boiler application scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of boiler combustion control, and in particular to a boiler combustion automatic detection and control system based on a big data model. Background Art

[0002] In the field of industrial production and energy supply, boilers are key thermal energy conversion equipment, and their combustion efficiency, stability and safety are crucial. Traditional boiler combustion detection and control methods have obvious limitations. Monitoring relies only on limited basic sensors, which cannot fully and accurately reflect the combustion status; control relies on fixed parameters set by experience, which is difficult to adapt to factors such as fuel quality fluctuations and load changes, and the fault prediction and processing capabilities are also insufficient. Although there have been attempts to increase the number of sensors and adopt simple automatic control algorithms, they lack effective data analysis and adaptability to complex systems, and cannot meet the high requirements of modern industry for boiler operation.

[0003] In recent years, the application potential of big data technology in the industrial field has become prominent. It can mine patterns and provide decision support by analyzing massive data. In this context, applying big data models to the field of boiler combustion detection and control is expected to overcome the shortcomings of traditional methods, achieve more comprehensive, accurate and intelligent monitoring and control, improve combustion efficiency, reduce energy consumption, reduce emissions and enhance safety. Summary of the invention

[0004] A boiler combustion automatic detection and control system based on a big data model, characterized by comprising:

[0005] Data acquisition module, used to collect various parameter data during boiler combustion process;

[0006] Data processing module, which pre-processes and fuses the collected data;

[0007] Big data model module, which builds models based on processed data, learns the laws of combustion process and makes predictions;

[0008] Intelligent control module generates control instructions based on the model prediction results to optimize the control of boiler combustion equipment;

[0009] The monitoring and alarm module monitors the combustion status and equipment operation status in real time, issues an alarm and takes emergency measures when an abnormality occurs.

[0010] Preferably, the data acquisition module includes multiple types of sensors, specifically including temperature sensors, pressure sensors, gas composition sensors and flame monitoring sensors;

[0011] The temperature sensors are installed at different positions inside the furnace of the boiler to monitor the temperature distribution of the burning flame in the furnace in real time, which helps to understand the intensity of combustion and whether the heat release is uniform. At the same time, temperature sensors are also installed at key positions of the flue to monitor the exhaust temperature, so as to indirectly judge the combustion efficiency and whether there is any abnormal heat loss.

[0012] The pressure sensors are installed at the air inlet, air supply port, furnace and flue; the pressure sensor at the air inlet can monitor the initial wind pressure of the primary air, secondary air, etc., to ensure that the air sent into the furnace has a suitable pressure, and to ensure that the air can participate in the combustion process evenly and in sufficient quantity; the pressure sensor in the furnace is used to monitor the pressure changes in the furnace in real time, because the pressure in the furnace should be maintained in a relatively stable and reasonable range during normal combustion, and abnormal pressure fluctuations may mean that the combustion conditions are unstable, such as deflagration or poor ventilation; the pressure sensor at the flue can monitor the negative pressure in the flue, which can assist in judging the operating status of the entire ventilation system and whether the smoke exhaust is smooth;

[0013] The gas composition sensor is installed in the flue to detect the gas component concentrations of oxygen, carbon monoxide, carbon dioxide and nitrogen oxides. The oxygen concentration can reflect whether the air supply during the combustion process is appropriate. If the oxygen content is too high, it means that there is too much air, which will take away a lot of heat and reduce the combustion efficiency; if the oxygen content is too low, it may cause incomplete combustion of the fuel; carbon monoxide concentration is one of the key indicators to measure the completeness of combustion. Excessive carbon monoxide content indicates incomplete combustion and the combustion parameters need to be adjusted in time. Changes in carbon dioxide concentration can also reflect the combustion effect from the side, and combined with other gas component analysis, the chemical changes in the combustion process can be more accurately judged. Monitoring nitrogen oxide concentration is crucial to controlling pollutant emissions. By monitoring its concentration in real time, the combustion strategy can be adjusted in time according to its changes to reduce the amount of pollutants generated;

[0014] The acoustic wave measurement sensor is installed in the furnace, the acoustic wave transmitting device periodically transmits acoustic wave signals, and the acoustic wave receiving device receives the acoustic wave signals passing through the furnace. By measuring the propagation time of the acoustic waves on different paths, the temperature field distribution in the furnace is calculated, and the flame combustion state in the furnace is determined according to the temperature field distribution. If the overall average temperature of the temperature field is high and within a reasonable range, it indicates that the combustion reaction is violent and the fuel releases more heat, which means that the combustion state is good. If the temperature distribution range is narrow, it means that the temperature in the furnace is relatively uniform and the combustion state is stable.

[0015] Preferably, the preprocessing and fusing of the collected data specifically includes:

[0016] Data format standardization: The system performs unified format standardization processing on the collected data and converts it into a unified data format;

[0017] Feature extraction: Extract feature information from the collected raw data, including temperature change rate, pressure fluctuation amplitude, gas component concentration change trend, flame stability and flame combustion state;

[0018] Data fusion: Use the weighted average method to fuse the data of multiple temperature sensors to obtain the temperature data in the area; use the Kalman filter method to fuse the pressure sensor data in a region, and then use the weighted average method to fuse the data of multiple pressure sensors in the region to obtain the pressure data in the region; use the fusion algorithm based on evidence theory to fuse the evidence about the combustion status provided by sensors in different regions.

[0019] Preferably, the method of fusing the data of multiple temperature sensors using a weighted average method specifically includes:

[0020] Get data from multiple temperature sensors and use the following formula to calculate the fused temperature data:

[0021]

[0022] Where T is the temperature after fusion, t i is the temperature data of the i-th sensor, w i is the weight of the i-th sensor, and n is the number of sensors.

[0023] Preferably, the method of fusing the data of multiple pressure sensors using a weighted average method specifically includes:

[0024] Get the pressure sensor data after Kalman filtering, and use the following formula to calculate the pressure data of multiple pressure sensors:

[0025]

[0026] Where P is the temperature after fusion, p i is the pressure data of the i-th sensor, w i is the weight of the i-th sensor, and n is the number of sensors.

[0027] Preferably, the method of fusing the evidence about the combustion state provided by different sensors using a fusion algorithm based on evidence theory specifically includes:

[0028] Determine the identification framework: The identification framework is a set of all possible combustion states. In a boiler, the combustion states include "normal combustion", "incomplete combustion" and "explosion", so the identification framework φ = {normal combustion, incomplete combustion, explosion};

[0029] Define the basic probability allocation function: For different types of sensors in each area, a basic probability value is assigned to each subset in the recognition framework based on its measurement data and related knowledge. The basic probability allocation function m satisfies the following conditions:

[0030] m()=0, which represents an empty set;

[0031] That is, the sum of the basic probabilities of all subsets is 1;

[0032] The DS synthesis rule is used to fuse the basic probability distribution functions of the same type of sensors in different areas. For two basic probability distribution functions m 1 and m 2 , their synthetic results The definition is as follows:

[0033] for and

[0034] Where K = ∑ B∩C＝ m 1 (B)m 2 (C) is the conflict coefficient, which indicates the degree of conflict between the two pieces of evidence;

[0035] According to the fused basic probability distribution function, the subset with the largest basic probability value is selected as the final combustion state judgment result.

[0036] Preferably, the constructing a model based on the processed data specifically includes:

[0037] Divide the data set: divide the preprocessed data into training set, validation set and test set;

[0038] Model training: Use the training set to train the selected model and adjust the model parameters to minimize the loss function;

[0039] Model evaluation: Use the validation set to evaluate the trained model and select the model with the best performance.

[0040] Preferably, the intelligent control module uses intelligent control algorithms such as model predictive control and fuzzy control to generate control instructions.

[0041] Preferably, the monitoring and alarm module displays key parameters and control results visually, and issues alarm signals in a timely manner under abnormal circumstances.

[0042] Compared with the prior art, the advantages of the present invention are:

[0043] Comprehensive and accurate monitoring: Through the multi-parameter sensor monitoring module, various key parameter information in the boiler combustion process can be obtained in real time and comprehensively, overcoming the limitations of traditional monitoring methods and providing rich data support for accurate judgment of combustion status;

[0044] Intelligent and efficient control: Based on the analysis and prediction results of the big data model, the automatic control and regulation module can adjust the boiler's combustion parameters in real time and intelligently to achieve the best air-fuel ratio, improve combustion efficiency, and reduce energy consumption and pollutant emissions;

[0045] Powerful fault prediction and processing capabilities: The big data model can analyze and predict the operating status of the boiler in real time, discover potential fault hazards in advance, and take corresponding measures to deal with them in a timely manner, effectively avoiding the occurrence and expansion of faults and enhancing the safety and reliability of boiler operation. DETAILED DESCRIPTION

[0046] Example: Paper mill biomass boiler application

[0047] Scenario description:

[0048] A paper mill mainly relies on biomass boilers to provide the steam heat energy required for the paper production process. The characteristics of biomass fuels (such as wood chips, straw, etc.) are complex and changeable. Factors such as moisture content and particle size vary greatly, resulting in unstable boiler combustion process, often resulting in incomplete combustion, low thermal efficiency, and unplanned shutdowns caused by coking problems, which not only affects the continuity of paper production, but also increases energy costs and equipment maintenance costs.

[0049] System construction:

[0050] Sensor Installation:

[0051] Inside the furnace of the biomass boiler, 18 high-temperature resistant thermocouple temperature sensors are installed in a grid layout, which can accurately monitor the combustion temperature in different areas of the furnace, making it easy to detect local high or low temperature abnormalities in a timely manner. These sensors cover the range from the center of the flame to near the furnace wall, and can fully reflect the temperature distribution of the burning flame.

[0052] A total of 8 pressure sensors are installed at the entrances of the primary and secondary air ducts and the furnace vents to accurately measure key pressure parameters such as air inlet pressure and furnace air pressure, so as to determine whether the ventilation system is operating normally and ensure that the air can participate in the combustion process evenly and sufficiently.

[0053] Five groups of gas composition sensors are installed in the flue. Each group of sensors can simultaneously detect the concentrations of multiple gases such as oxygen, carbon monoxide, carbon dioxide, sulfur dioxide and nitrogen oxides. Through real-time analysis of the flue gas composition, the degree of combustion completeness and pollutant emissions can be accurately grasped.

[0054] The acoustic wave transmitting devices and receiving devices of 9 acoustic wave temperature field measurement sensors are arranged on the furnace wall in a 3×3 grid layout; the acoustic wave transmitting device transmits a coded modulated acoustic wave signal with a frequency of 3kHz, and the acoustic wave receiving device receives the signal and measures the acoustic wave propagation time, and uses the acoustic algorithm to calculate the temperature field distribution in the furnace to provide more accurate information for combustion control.

[0055] Four flame monitoring sensors are installed near the furnace observation hole to monitor the brightness, flickering frequency, color and other characteristics of the flame from different angles to determine the stability of the flame and whether the combustion state is normal.

[0056] Data collection and transmission:

[0057] Using a high-precision timing collection mechanism, the data of each sensor is synchronously collected every 4 seconds to ensure that the different parameter data obtained are strictly corresponding in time, laying the foundation for subsequent accurate analysis.

[0058] Taking into account the on-site environment of the paper mill workshop, shielded twisted pair cables are used for wired transmission for sensors that are close to the control room and have relatively convenient wiring. For some sensors installed at higher locations and difficult to wire, industrial wireless communication modules are used for data transmission to ensure that all data can be efficiently and stably gathered to the data processing center.

[0059] Big data storage and management:

[0060] A dedicated big data storage server was built, which uses a combination of relational and non-relational databases to store massive amounts of boiler operation data. The relational database is used to store structured sensor parameters, equipment operation status and other information, which facilitates complex queries and association analysis; the non-relational database is used to store semi-structured and unstructured data such as historical fault records and real-time image data.

[0061] A comprehensive data backup strategy has been developed to perform full backup of all data on a daily basis and incremental backup every hour. At the same time, an off-site disaster recovery center has been set up to ensure the security and integrity of data and prevent data loss due to unexpected situations.

[0062] Model building and analysis:

[0063] Data preprocessing:

[0064] Arrange dedicated personnel to conduct preliminary screening of the collected data every day to eliminate obvious abnormal data points caused by temporary sensor failures, communication interference, etc.

[0065] The data cleaning algorithm is used to deeply clean the remaining data to remove duplicate and redundant data records. At the same time, for the parts with missing values, appropriate interpolation algorithms are used to complete them according to the time series characteristics of the data and the surrounding normal data conditions.

[0066] In view of the differences in data range and magnitude collected by different sensors, normalization processing is performed to map all data to the interval [0,1], so that each parameter data has equal weight and comparability in subsequent analysis and model training.

[0067] Feature Engineering:

[0068] From the massive amount of preprocessed data, key characteristic information such as the standard deviation of temperature, the rate of change of pressure, the ratio of the concentration of each gas component, the temperature field characteristics and the fluctuation amplitude of flame brightness are extracted.

[0069] The characteristic information is correlated and analyzed through data analysis algorithms to find the correlation between temperature, pressure, gas component concentration, flame stability and flame combustion state, and a variety of data fusion algorithms are used to comprehensively process multi-parameter data.

[0070] Model training:

[0071] According to the characteristics of biomass boiler combustion process with certain time series characteristics and multi-factor nonlinear coupling, a hybrid model architecture combining long short-term memory network based on deep learning and convolutional neural network (CNN) was selected. The convolution layer of CNN is used to automatically extract local feature patterns in the data, and then the long-term dependency relationship of the features on the time series is modeled through the LSTM layer.

[0072] The data processed by feature engineering is divided into training set, validation set and test set in the ratio of 7:2:1. During the training process, the adaptive learning rate adjustment algorithm is used, combined with the early stopping method to prevent overfitting. After multiple rounds of iterative training, the weight parameters of the model are continuously adjusted to minimize the loss function of the model on the validation set, ensuring that the model has good generalization ability.

[0073] Automatic control and regulation:

[0074] Real-time monitoring and analysis:

[0075] The system receives data from various sensors in real time and inputs it into the trained hybrid model. The model quickly outputs the current combustion status assessment results, including the specific value of the combustion efficiency, whether there is a coking risk, and the predicted values ​​of the emission levels of various pollutants. At the same time, it determines whether the current combustion status belongs to normal combustion, slightly incomplete combustion, coking tendency or other abnormal status categories.

[0076] For example, based on real-time input data such as temperature and gas composition, the model determines that a certain area in the current furnace may be experiencing local low temperatures and incomplete combustion due to the accumulation of biomass fuel, and predicts that if it is not adjusted in time, there will be a risk of coking in the future.

[0077] Control strategy generation and execution:

[0078] Based on the analysis results of the model, the automatic control and regulation module quickly generates corresponding control instructions. In view of the above-mentioned situation of incomplete combustion and coking tendency, the air volume of primary and secondary air is automatically fine-tuned to increase the disturbance of air so that the fuel and air can be more fully mixed; at the same time, the feed rate of biomass fuel is appropriately reduced to avoid excessive accumulation of fuel and optimize the combustion process.

[0079] If the model predicts that sulfur dioxide emissions are about to exceed the standard, the system will automatically adjust parameters such as combustion temperature and excess air coefficient to minimize the generation of pollutants while ensuring combustion efficiency, so that the emission level remains within the compliance range. In addition, when a possible serious fault is detected, the system immediately triggers the emergency shutdown procedure and sends detailed fault alarm information to the operator to ensure the safety of the boiler.

[0080] Implementation effect:

[0081] By applying this combustion automatic detection and control system based on the big data model to the biomass boiler of the paper mill, after a period of operation observation, the boiler's combustion efficiency has increased by an average of about 12%, the number of unplanned shutdowns due to coking problems has been reduced by 40%, and the emissions of major pollutants such as sulfur dioxide and nitrogen oxides have been reduced by about 18%, effectively ensuring the stable and efficient production of papermaking, while reducing energy consumption and environmental pressure, bringing significant economic and environmental benefits to the enterprise.

[0082] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0083] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A boiler combustion automatic detection and control system based on a big data model, characterized in that: include: Data acquisition module, used to collect various parameter data during boiler combustion process; Data processing module, which pre-processes and fuses the collected data; Big data model module, which builds models based on processed data, learns the laws of combustion process and makes predictions; Intelligent control module generates control instructions based on the model prediction results to optimize the control of boiler combustion equipment; The monitoring and alarm module monitors the combustion status and equipment operation status in real time, issues an alarm and takes emergency measures when an abnormality occurs.

2. According to the big data model-based boiler combustion automatic detection and control system of claim 1, it is characterized in that: The data acquisition module includes various types of sensors, specifically including temperature sensors, pressure sensors, gas composition sensors and acoustic wave sensors; The temperature sensors are installed at different positions inside the furnace of the boiler to monitor the temperature distribution of the burning flame in the furnace in real time; at the same time, temperature sensors are installed at key positions of the flue to monitor the exhaust gas temperature; The pressure sensors are installed at the air inlet, air outlet, furnace and flue; the pressure sensor at the air inlet is used to monitor the initial air pressure of the primary air, secondary air, etc.; the pressure sensor in the furnace is used to monitor the pressure change in the furnace in real time; the pressure sensor at the flue is used to monitor the negative pressure in the flue; The gas component sensor is installed in the flue to detect the gas component concentrations of oxygen, carbon monoxide, carbon dioxide and nitrogen oxides; The acoustic wave sensor is installed in the furnace, the acoustic wave transmitting device periodically transmits acoustic wave signals, the acoustic wave receiving device receives the acoustic wave signals passing through the furnace, and the temperature field distribution in the furnace is calculated by measuring the propagation time of the acoustic wave on different paths, and the flame combustion state in the furnace is determined according to the temperature field distribution.

3. The boiler combustion automatic detection and control system based on the big data model according to claim 1 is characterized in that: The preprocessing and fusing of the collected data specifically includes: Data format standardization: standardize the collected data and convert it into a unified data format; Feature extraction: Extract feature information from the standardized data, including temperature data, pressure data and flame combustion status; Data fusion: Use the weighted average method to fuse the data of multiple temperature sensors in the same area to obtain the temperature data in the area; use the Kalman filter method to fuse the pressure sensor data in a region, and then use the weighted average method to fuse the data of multiple pressure sensors in the region to obtain the pressure data in the region; use the fusion algorithm based on evidence theory to fuse the evidence about the combustion status provided by sensors in different regions.

4. The boiler combustion automatic detection and control system based on the big data model according to claim 3 is characterized in that: The method of fusing the data of multiple temperature sensors using the weighted average method specifically includes: Get data from multiple temperature sensors and use the following formula to calculate the fused temperature data: Where T is the temperature after fusion, t i is the temperature data of the i-th sensor, w i is the weight of the i-th sensor, and n is the number of sensors.

5. The boiler combustion automatic detection and control system based on the big data model according to claim 3 is characterized in that: The method of fusing the data of multiple pressure sensors using a weighted average method specifically includes: Get the pressure sensor data after Kalman filtering, and use the following formula to calculate the pressure data of multiple pressure sensors: Where P is the temperature after fusion, p i is the pressure data of the i-th sensor, w i is the weight of the i-th sensor, and n is the number of sensors.

6. The boiler combustion automatic detection and control system based on big data model according to claim 3 is characterized in that: The method of using a fusion algorithm based on evidence theory to fuse the evidence about the combustion state provided by different sensors specifically includes: I. Determine the identification framework: The identification framework is a collection of all possible combustion states. In a boiler, the combustion states include "normal combustion", "incomplete combustion" and "explosion". II. Define the basic probability allocation function: For different types of sensors in each area, a basic probability value is assigned to each subset in the recognition framework based on its measurement data and related knowledge. The basic probability allocation function m satisfies the following conditions: in represents the empty set; That is, the sum of the basic probabilities of all subsets is 1; III. Use the DS synthesis rule to fuse the basic probability distribution functions of the same type of sensors in different regions. For two basic probability distribution functions m1 and m2, their synthesis results The definition is as follows: for and in is the conflict coefficient, which indicates the degree of conflict between the two pieces of evidence; IV. According to the fused basic probability distribution function, the subset with the largest basic probability value is selected as the final combustion state judgment result.

7. The boiler combustion automatic detection and control system based on big data model according to claim 1 is characterized in that: The constructing of the model based on the processed data specifically includes: Divide the data set: divide the preprocessed data into training set, validation set and test set; Model training: Use the training set to train the selected model and adjust the model parameters to minimize the loss function; Model evaluation: Use the validation set to evaluate the trained model and select the model with the best performance.

8. The boiler combustion automatic detection and control system based on big data model according to claim 7 is characterized in that: The loss function includes a cross entropy loss function and a mean square error loss function.

9. According to the boiler combustion automatic detection and control system based on big data model described in claim 1, the intelligent control module adopts model predictive control and fuzzy control intelligent control algorithm to generate control instructions.

10. According to the boiler combustion automatic detection and control system based on the big data model described in claim 1, the monitoring and alarm module visualizes the key parameters and control results, and promptly issues an alarm signal under abnormal circumstances.

Images