Automatic load adjusting and optimizing system of biomass gas boiler

Abstract

The invention provides an automatic load regulation optimization system of a biomass gas boiler. The system comprises a fuel supply module, a boiler combustion module, an environmental protection processing module, a load prediction module and a control optimization module. The fuel supply module is used for controlling supply, gasification and conveying of biomass fuel; the boiler combustion module is used for controlling combustion, heat exchange and energy conversion of biomass gas, and generated heat energy meets production requirements. The environment-friendly treatment module is used for completing flue gas waste heat recovery and waste gas purification; the load prediction module is used for predicting the future boiler load demand in combination with the production demand; the control optimization module is used for intelligently adjusting and automatically controlling the operation condition of the biomass gas boiler; intelligent and self-adaptive adjustment of the boiler is achieved, the energy supply efficiency is improved, and the operation cost is effectively reduced.

Description

Technical Field

[0001] The invention relates to the field of boiler control systems, and in particular to an automatic load regulation and optimization system for a biomass gas boiler. Background Art

[0002] With the adjustment of global energy structure, biomass gas, as a renewable and clean energy, has been gradually applied in industrial boilers and heating fields. Compared with traditional coal-fired boilers, biomass gas boilers have the advantages of low carbon emissions, strong renewability, and good combustion stability, and have become an important choice to replace fossil fuel boilers. However, biomass gas boilers still face problems such as large load fluctuations, complex combustion control, and high difficulty in fuel supply matching during actual operation, which leads to limited boiler operation stability, reduced combustion efficiency, and possible increase in pollutant emissions. In addition, traditional boiler load regulation methods mostly rely on fixed rules or manual intervention, which makes it difficult to achieve precise control under complex working conditions, affecting the overall operation economy and environmental performance of the boiler. Therefore, how to improve the load regulation capability of biomass gas boilers and achieve efficient and intelligent combustion control has become a technical problem that needs to be solved urgently.

[0003] After consulting the related disclosed technical solutions, the technology with the publication number CN118757775A proposes a wide load regulation system for a biomass fluidized bed boiler, including a furnace, a separator, a burnout chamber and a flue connected in sequence, and a primary air mechanism and a secondary air mechanism for supplying air to the furnace and the burnout chamber; the scheme is provided with a first air distribution plate at the bottom to form a vertical airflow and a second air distribution plate at the side to form a horizontal airflow, and the particulate material forms a gas-solid phase mixed state that is approximately turbulent under the combined action of the horizontal airflow and the vertical airflow, which effectively improves the combustion efficiency and increases the high load value of the system. At the same time, because the two air distribution plates jointly divert the primary air, they play a major fluidization role The hood area of ​​the first air distribution plate is relatively reduced. The reduction in the hood area can achieve a predetermined critical fluidizing wind speed under the condition of the same air volume, so that under low-load conditions, when the fluidizing air is completely provided by the first air distribution plate, the air intake of the first air distribution plate can match the required critical fluidizing wind speed, thereby achieving low-nitrogen combustion under low-load conditions, relatively reducing the low-load value of the system, and effectively achieving the purpose of wide load regulation operation of the system, and obtaining better energy-saving and emission reduction effects; however, this scheme mainly realizes boiler load regulation by optimizing the air distribution plate structure and wind speed control, without combining intelligent prediction and adaptive control, and it is difficult to dynamically optimize combustion efficiency under complex conditions. Summary of the invention

[0004] The purpose of the present invention is to propose an automatic load regulation optimization system for a biomass gas boiler in view of the current shortcomings.

[0005] The present invention adopts the following technical solution:

[0006] An automatic load regulation and optimization system for a biomass gas boiler, the system comprising a fuel supply module, a boiler combustion module, an environmental protection treatment module, a load prediction module and a control optimization module; the fuel supply module is used to control the supply, gasification and transportation of biomass fuel; the boiler combustion module is used to control the combustion, heat exchange and energy conversion of biomass gas to generate thermal energy to meet production needs; the environmental protection treatment module is used to complete flue gas waste heat recovery and waste gas purification; the load prediction module is used to predict future boiler load requirements in combination with production needs; the control optimization module is used to intelligently adjust and automatically control the operation of the biomass gas boiler.

[0007] The fuel supply module includes a feed port, a conveying device, a gasification chamber and a gas delivery pipeline; the feed port is used to store biomass fuel; the delivery device is used to convey the biomass fuel from the feed port to the gasification chamber; the gasification chamber is used to gasify the biomass fuel through anaerobic cracking to generate biomass gas; the gas delivery pipeline is used to supply the biomass gas to the boiler body.

[0008] The boiler combustion module includes a multi-stage air distribution device, a boiler body and a burner; the multi-stage air distribution device is used to fully mix the biomass gas with air and transport it to the boiler body to optimize the combustion process; the boiler body is used to complete the combustion, heat energy release and heat exchange process of the biomass gas to achieve energy conversion; the burner is used to ignite the biomass gas.

[0009] Furthermore, the environmental protection treatment module includes an economizer, an air preheater, a blower, a bag dust collector, an induced draft fan and a chimney; the economizer is used to recover waste heat in the flue gas generated after combustion in the boiler body; the air preheater is used to absorb the waste heat of the flue gas, and use the waste heat of the flue gas to preheat the combustion-supporting air entering the boiler body, thereby improving the combustion efficiency in the boiler body; the blower is used to provide fresh air required for combustion of the boiler body; the bag dust collector is used to remove particulate matter and dust in the flue gas, thereby reducing pollutant emissions; the induced draft fan is used to guide the flue gas after dust removal to be discharged to the outside through the chimney.

[0010] Furthermore, the load prediction module includes a data acquisition unit, a calculation prediction unit and a result output unit; the data acquisition unit is used to acquire production demand data and boiler operation parameter data; the calculation prediction unit completes the prediction of the boiler load in the future through a pre-established load prediction model; the result output unit is used to output the prediction result of the calculation prediction unit to the control optimization module.

[0011] Furthermore, the control optimization module includes an operation status monitoring unit and a feedback control unit; the operation status monitoring unit is used to monitor the boiler operation parameter data in real time and provide it to the management end through a visual interface; the feedback control unit is used to dynamically adjust the boiler operation parameters based on the prediction error of the boiler load to ensure the load demand and boiler operation stability.

[0012] Furthermore, the specific process of establishing the load forecasting model is as follows:

[0013] S1: Acquire training data required for model training from a historical database, wherein the training data includes historical production demand data and boiler operation parameter data;

[0014] S2: preprocessing the training data, wherein the preprocessing operation includes standardizing the historical production demand data and the boiler operation parameter data, and generating a load volatility label corresponding to the training data to evaluate the credibility of the training data;

[0015] S3: Integrate the historical production demand data with time series, boiler operation parameter data and load volatility labels in the sliding time window to construct the training set required for load forecasting model training;

[0016] S4: Use LSTM to build a load forecasting model framework;

[0017] S5: Use the data in the training set to train the load forecasting model, where the loss function satisfies:

[0018]

[0019] Where L is the total loss value of the loss function, N is the total number of samples in the training set, t is the time step index in the training set, and ω t is the data reliability weight of the training data in the training set at time step t; is the actual boiler load data at time step t, obtained through the corresponding training data in the training set; is the boiler load data predicted by the LSTM load forecasting model at time step t; for ω t satisfy:

[0020]

[0021] Among them, γ is a tuning parameter used to adjust the influence of the load volatility label on the data reliability weight, which is set by pre-experimentation; is the load fluctuation label at time step t.

[0022] Furthermore, the calculation and prediction unit generates input features required for the load prediction model by standardizing the real-time production demand data and boiler operation parameter data, and inputs the input features into the load prediction model, thereby completing the prediction of future boiler load demand.

[0023] The beneficial effects achieved by the present invention are:

[0024] The present invention realizes efficient, stable and intelligent operation of the boiler by combining load prediction and intelligent control optimization; by predicting the future boiler load and dynamically adjusting the boiler operating parameters, such as fuel supply and air ratio, the combustion efficiency is improved and the energy consumption is reduced; when training the load prediction model used for boiler load prediction, the training data is weighted by combining the load volatility label, so that the model pays more attention to the data of stable load, thereby improving the accuracy of boiler load prediction; by integrating waste heat recovery and environmental protection treatment technology, pollutant emissions are reduced and energy utilization is further improved; the present invention realizes the intelligence and adaptive adjustment of the boiler, improves the energy supply efficiency and effectively reduces the operating cost, and meets environmental protection requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0026] Figure 1 It is a schematic diagram of the overall module of the present invention.

[0027] Figure 2 This is a schematic diagram of the structure of the biomass gas boiler of the present invention.

[0028] Figure 3 A flow chart of a load forecasting model is established in the present invention.

[0029] The meaning of the numbers in the figure are: 1-feeding port; 2-gasification chamber; 3-burner; 4-boiler body; 5-economizer; 6-air preheater; 7-blower; 8-bag dust collector; 9-induced draft fan; 10-chimney. DETAILED DESCRIPTION

[0030] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with its embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention; for those skilled in the art, other systems, methods and / or features of the present embodiment will become apparent after reviewing the following detailed description; it is intended that all such additional systems, methods, features and advantages are included in this specification; included within the scope of the present invention and protected by the appended claims; additional features of the disclosed embodiments are described in the following detailed description, and these features will be apparent from the following detailed description.

[0031] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, it is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and cannot be understood as limitations on this patent. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0032] Embodiment 1:

[0033] like Figure 1 , Figure 2 As shown, this embodiment provides an automatic load adjustment and optimization system for a biomass gas boiler, the system comprising a fuel supply module, a boiler combustion module, an environmental protection treatment module, a load prediction module and a control optimization module; the fuel supply module is used to control the supply, gasification and transportation of biomass fuel; the boiler combustion module is used to control the combustion, heat exchange and energy conversion of biomass gas to generate heat energy to meet production needs; the environmental protection treatment module is used to complete flue gas waste heat recovery and exhaust gas purification; the load prediction module is used to predict future boiler load requirements in combination with production needs; the control optimization module is used to intelligently adjust and automatically control the operation of the biomass gas boiler;

[0034] The fuel supply module includes a feed port, a conveying device, a gasification chamber and a gas delivery pipeline; the feed port is used to store biomass fuel; the delivery device is used to convey the biomass fuel from the feed port to the gasification chamber; the gasification chamber is used to gasify the biomass fuel through anaerobic cracking to generate biomass gas; the gas delivery pipeline is used to supply the biomass gas to the boiler body;

[0035] The boiler combustion module includes a multi-stage air distribution device, a boiler body and a burner; the multi-stage air distribution device is used to fully mix the biomass gas with air and transport it to the boiler body to optimize the combustion process; the boiler body is used to complete the combustion, heat energy release and heat exchange process of the biomass gas to achieve energy conversion; the burner is used to ignite the biomass gas;

[0036] The environmental protection treatment module includes an economizer, an air preheater, a blower, a bag filter, an induced draft fan and a chimney; the economizer is used to recover the waste heat in the flue gas generated after combustion in the boiler body; the air preheater is used to absorb the waste heat of the flue gas and use the waste heat of the flue gas to preheat the combustion-supporting air entering the boiler body to improve the combustion efficiency in the boiler body; the blower is used to provide fresh air required for the combustion of the boiler body; the bag filter is used to remove particulate matter and dust in the flue gas to reduce pollutant emissions; the induced draft fan is used to guide the flue gas after dust removal to be discharged to the outside through the chimney;

[0037] Furthermore, the load prediction module includes a data acquisition unit, a calculation prediction unit and a result output unit; the data acquisition unit is used to acquire production demand data and boiler operation parameter data; the calculation prediction unit completes the prediction of the boiler load in the future through a pre-established load prediction model; the result output unit is used to output the prediction result of the calculation prediction unit to the control optimization module;

[0038] Further, such as Figure 3 As shown, the specific establishment process of the load forecasting model is as follows:

[0039] S1: Acquire training data required for model training from a historical database, wherein the training data includes historical production demand data and boiler operation parameter data;

[0040] S2: preprocessing the training data, wherein the preprocessing operation includes standardizing the historical production demand data and the boiler operation parameter data, and generating a load volatility label corresponding to the training data to evaluate the credibility of the training data;

[0041] S3: Integrate the historical production demand data with time series, boiler operation parameter data and load volatility labels in the sliding time window to construct the training set required for load forecasting model training;

[0042] S4: Use LSTM to build a load forecasting model framework;

[0043] S5: Use the data in the training set to train the load forecasting model, where the loss function satisfies:

[0044]

[0045] Where L is the total loss value of the loss function, N is the total number of samples in the training set, t is the time step index in the training set, and ω t is the data reliability weight of the training data in the training set at time step t; is the actual boiler load data at time step t, obtained through the corresponding training data in the training set; is the boiler load data predicted by the LSTM load forecasting model at time step t; for ω t satisfy:

[0046]

[0047] Among them, γ is a tuning parameter used to adjust the influence of the load volatility label on the data reliability weight, which is set by pre-experimentation; is the load fluctuation label at time step t;

[0048] Furthermore, the specific generation method of the load fluctuation label is as follows:

[0049] S21: Set the sliding time window and calculate the load change rate in each time window:

[0050] X k =Q k -Q k-1 ;

[0051] Among them, X k is the boiler load change rate within a certain time window k; Q k is the boiler load data in the training data at the end of the time window; Q k-1 is the boiler load data in the training data at the beginning of the time window;

[0052] S22: Normalize the load change rate in each time window as the load volatility label corresponding to the training data in the time window:

[0053] Furthermore, some functional implementation codes of the load forecasting model are as follows:

[0054]

[0055]

[0056]

[0057]

[0058] Furthermore, the calculation prediction unit generates input features required by the load prediction model by normalizing the real-time production demand data and boiler operation parameter data, and inputs the input features into the load prediction model, thereby completing the prediction of future boiler load demand;

[0059] Specifically, the production demand data refers to the production demand information provided by the management personnel according to the production plan; the boiler operation parameter data includes but is not limited to the fuel supply, the current actual load, the boiler gas consumption rate, the boiler heat exchange efficiency and the exhaust gas temperature, etc.;

[0060] This solution combines the historical production demand data and boiler operation parameter data through the LSTM load forecasting model to accurately learn the time series change trend of the boiler load. During the training process of the load forecasting model, the training data is weighted in combination with the load volatility label, so that the model pays more attention to the data of stable load, which can reduce the interference of load fluctuations and possible abnormal data on the prediction results, thereby further improving the accuracy of boiler load forecasting, reducing manual intervention, and improving the system's automatic adjustment capabilities.

[0061] Embodiment 2:

[0062] This embodiment should be understood to include at least all the features of any of the above embodiments, and further improve upon them;

[0063] This embodiment provides an automatic load regulation and optimization system for a biomass gas boiler, the system comprising a fuel supply module, a boiler combustion module, an environmental protection treatment module, a load prediction module and a control optimization module; the fuel supply module is used to control the supply, gasification and transportation of biomass fuel; the boiler combustion module is used to control the combustion, heat exchange and energy conversion of biomass gas to generate heat energy to meet production needs; the environmental protection treatment module is used to complete flue gas waste heat recovery and waste gas purification; the load prediction module is used to predict future boiler load requirements in combination with production needs; the control optimization module is used to intelligently adjust and automatically control the operation of the biomass gas boiler;

[0064] Furthermore, the control optimization module includes an operation status monitoring unit and a feedback control unit; the operation status monitoring unit is used to monitor the boiler operation parameter data in real time and provide it to the management end through a visual interface; the feedback control unit is used to dynamically adjust the boiler operation parameters based on the prediction error of the boiler load to ensure the load demand and boiler operation stability;

[0065] Furthermore, the feedback control unit adjusts the boiler operating parameters in the following manner:

[0066] For certain boiler operating parameters that affect boiler load changes:

[0067]

[0068] Among them, Δμ l is the parameter adjustment of the boiler operating parameters at the current time step l, e l is the boiler load prediction error at time step l, that is, the difference between the actual boiler load at time step l and the boiler load predicted by the load prediction module; K p is the proportional adjustment coefficient, K i is the integral adjustment coefficient, K d is the differential adjustment coefficient, the K p , K i and K d Set by pre-experiment respectively; K r is the inertia adjustment coefficient, Δμ l-1 is the adjustment amount of the boiler operating parameters at the previous time step l-1 of the current time step;

[0069] For K r satisfy:

[0070]

[0071] Among them, Δμ max is the preset normalized adjustment coefficient for the operating parameters of this type of boiler, α and β are amplitude adjustment coefficients, which are used to adjust the influence of the parameter adjustment amount at the previous moment on the parameter adjustment amount at the current moment, and are set by pre-experimentation;

[0072] This solution dynamically adjusts boiler operating parameters, such as fuel supply and air flow, by combining the boiler load prediction error, so as to reduce load fluctuations and ensure stable operation of the boiler; by adopting PID control combined with the inertia adaptive adjustment of the boiler operating parameter adjustment amount at the previous moment, when the adjustment range of the boiler operating parameters at the current moment is small, a higher inertia is maintained, that is, the larger the inertia adjustment coefficient is at this time, the more frequent adjustments can be prevented; when the adjustment range of the boiler operating parameters at the current moment is large, the inertia is reduced to avoid excessive adjustment, thereby improving the accuracy of boiler operating parameter adjustment; at the same time, combined with the forward-looking prediction capability of the load prediction model, the boiler operation adjustment is made more intelligent and predictive, the lag response is reduced, and the overall stability of the boiler operation and the combustion efficiency are improved.

[0073] The contents disclosed above are only preferred feasible embodiments of the present invention, and do not limit the protection scope of the present invention. Therefore, all equivalent technical changes made using the contents of the present invention specification and drawings are included in the protection scope of the present invention. In addition, the elements therein can be updated as technology develops.

Claims

1. An automatic load regulation optimization system for a biomass gas boiler, characterized in that: The system includes a fuel supply module, a boiler combustion module, an environmental protection treatment module, a load prediction module and a control optimization module; the fuel supply module is used to control the supply, gasification and transportation of biomass fuel; the boiler combustion module is used to control the combustion, heat exchange and energy conversion of biomass gas to generate heat energy to meet production needs; the environmental protection treatment module is used to complete flue gas waste heat recovery and waste gas purification; the load prediction module is used to predict future boiler load requirements in combination with production needs; the control optimization module is used to intelligently adjust and automatically control the operation of the biomass gas boiler; The fuel supply module includes a feed port, a conveying device, a gasification chamber and a gas delivery pipeline; the feed port is used to store biomass fuel; the delivery device is used to convey the biomass fuel from the feed port to the gasification chamber; the gasification chamber is used to gasify the biomass fuel through anaerobic cracking to generate biomass gas; the gas delivery pipeline is used to supply the biomass gas to the boiler body; The boiler combustion module includes a multi-stage air distribution device, a boiler body and a burner; the multi-stage air distribution device is used to fully mix the biomass gas with air and transport it to the boiler body to optimize the combustion process; The boiler body is used to complete the combustion, heat energy release and heat exchange process of the biomass gas to achieve energy conversion; the burner is used to ignite the biomass gas.

2. The automatic load adjustment and optimization system for a biomass gas boiler according to claim 1 is characterized in that: The environmental protection treatment module includes an economizer, an air preheater, a blower, a bag dust collector, an induced draft fan and a chimney; the economizer is used to recover the waste heat in the flue gas generated after combustion in the boiler body; the air preheater is used to absorb the waste heat of the flue gas and use the waste heat of the flue gas to preheat the combustion-supporting air entering the boiler body, thereby improving the combustion efficiency in the boiler body; the blower is used to provide fresh air required for the combustion of the boiler body; the bag dust collector is used to remove particulate matter and dust in the flue gas and reduce pollutant emissions; the induced draft fan is used to guide the flue gas after dust removal to be discharged to the outside through the chimney.

3. The automatic load regulation optimization system for a biomass gas boiler according to claim 2 is characterized in that: The load prediction module includes a data acquisition unit, a calculation prediction unit and a result output unit; the data acquisition unit is used to acquire production demand data and boiler operation parameter data; the calculation prediction unit completes the prediction of the boiler load in the future through a pre-established load prediction model; the result output unit is used to output the prediction result of the calculation prediction unit to the control optimization module.

4. The automatic load regulation and optimization system for a biomass gas boiler according to claim 3 is characterized in that: The control optimization module includes an operation status monitoring unit and a feedback control unit; the operation status monitoring unit is used to monitor the boiler operation parameter data in real time and provide it to the management end through a visual interface; The feedback control unit is used to dynamically adjust boiler operating parameters based on the prediction error of boiler load to ensure load demand and boiler operation stability.

5. The automatic load adjustment and optimization system for a biomass gas boiler according to claim 4 is characterized in that: The specific establishment process of the load forecasting model is as follows: S1: Acquire training data required for model training from a historical database, wherein the training data includes historical production demand data and boiler operation parameter data; S2: preprocessing the training data, wherein the preprocessing operation includes standardizing the historical production demand data and the boiler operation parameter data, and generating a load volatility label corresponding to the training data to evaluate the credibility of the training data; S3: Integrate the historical production demand data with time series, boiler operation parameter data and load volatility labels in the sliding time window to construct the training set required for load forecasting model training; S4: Use LSTM to build a load forecasting model framework; S5: Use the data in the training set to train the load forecasting model, where the loss function satisfies: Where L is the total loss value of the loss function, N is the total number of samples in the training set, t is the time step index in the training set, and ω t is the data reliability weight of the training data in the training set at time step t; is the actual boiler load data at time step t, obtained through the corresponding training data in the training set; is the boiler load data predicted by the LSTM load forecasting model at time step t; for ω t satisfy: Among them, γ is a tuning parameter used to adjust the influence of the load volatility label on the data reliability weight, which is set by pre-experimentation; is the load fluctuation label at time step t.

6. The automatic load adjustment and optimization system for a biomass gas boiler according to claim 5 is characterized in that: The calculation prediction unit generates input features required by the load prediction model by standardizing the real-time production demand data and boiler operation parameter data, and inputs the input features into the load prediction model, thereby completing the prediction of future boiler load demand.

Images