Biomass boiler combustion efficiency optimization method based on historical data

Abstract

The invention discloses a biomass boiler combustion efficiency optimization method based on historical data, and relates to the field of industrial process control and optimization, and the method comprises the steps: collecting the historical operation data of a biomass boiler; segmenting the historical operation data according to a time sequence, dividing the historical operation data into a high-efficiency operation section and a low-efficiency operation section of the boiler, and taking operation parameters of the high-efficiency operation section as optimization reference data; establishing a correlation model between boiler combustion efficiency and operation parameters, and calculating a weight coefficient of each parameter through a least square method; performing weighted calculation on the weight coefficient and the real-time operation parameter to obtain a boiler combustion efficiency score, and triggering optimization control when the efficiency score is lower than a preset threshold value; and dynamically adjusting the fuel supply rate and the oxygen content according to the optimized reference data. According to the method, the historical operation data of the biomass boiler are comprehensively collected and deeply analyzed, so that the operation state of the boiler gradually approaches to an efficient interval, the combustion efficiency is improved, and energy waste and pollution emission are reduced.

Description

Technical Field

[0001] The invention relates to the field of industrial process control and optimization, in particular to a method for optimizing the combustion efficiency of a biomass boiler based on historical data. Background Art

[0002] As the global energy shortage problem becomes increasingly serious, the development and utilization of clean and renewable energy has received widespread attention. Biomass energy, as a renewable energy source, can not only reduce dependence on fossil fuels, but also has good environmental benefits, so it has been rapidly promoted around the world. As an important equipment for utilizing biomass energy, biomass boilers have been widely used in heating, power generation, industrial production and other fields. The operation of traditional biomass boilers depends on preset parameters or manual experience adjustment, which is difficult to fully adapt to the complex fuel characteristics and variable operating conditions, which often leads to low boiler operation efficiency, energy waste and increased pollutant emissions. To this end, mining the operation rules of biomass boilers through data-driven methods and optimizing combustion efficiency has become one of the current research hotspots.

[0003] In the existing technology, researchers have tried biomass boiler optimization methods based on online monitoring and control. For example, some studies use Internet of Things technology to collect real-time boiler operation data and achieve partial optimization of the combustion process through intelligent control algorithms. However, these methods usually have the following shortcomings: First, the real-time control strategy is only based on the current operating data, lacks comprehensive mining of historical operating data, and it is difficult to establish an effective operating parameter optimization model; second, the optimization of combustion efficiency in existing methods often uses the adjustment of a single indicator (such as oxygen content or fuel supply rate), ignoring the synergy between various parameters, resulting in limited optimization effects; third, when the operating conditions of the boiler fluctuate greatly, the existing methods have a slow response speed and may be difficult to adapt to complex operating changes in real time. These shortcomings have led to the fact that there is still room for improvement in the existing technology in terms of improving fuel utilization and controlling pollutant emissions. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention proposes a method for optimizing the combustion efficiency of a biomass boiler based on historical data.

[0005] Therefore, the present invention provides a method for optimizing the combustion efficiency of a biomass boiler based on historical data, which can solve the problems mentioned in the background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for optimizing combustion efficiency of a biomass boiler based on historical data, which comprises:

[0008] Collecting historical operation data of the biomass boiler; the historical operation data includes boiler temperature, oxygen content, steam pressure and fuel supply rate;

[0009] The historical operation data is segmented according to the time series to divide the boiler into a high-efficiency operation segment and an inefficient operation segment, and the operation parameters of the high-efficiency operation segment are used as optimization benchmark data;

[0010] Based on the optimization benchmark data, a correlation model between boiler combustion efficiency and operating parameters is established, and a weight coefficient of each parameter is calculated by the least square method;

[0011] The weight coefficient and the real-time operating parameters are weightedly calculated to obtain a boiler combustion efficiency score, and when the efficiency score is lower than a preset threshold, optimization control is triggered;

[0012] The fuel supply rate and oxygen content are dynamically adjusted according to the optimized reference data.

[0013] As a preferred solution of the biomass boiler combustion efficiency optimization method based on historical data of the present invention, obtaining the optimization benchmark data includes:

[0014] Dividing the historical operation data according to the basic time unit T;

[0015] Calculate the thermal efficiency value η in each time unit;

[0016] The operation interval in which the thermal efficiency value is greater than a preset threshold and the duration exceeds a preset value is divided into a high-quality operation section, and the comprehensive score S of the high-quality operation section is calculated;

[0017] The operation data with the highest comprehensive score in the efficient operation section is extracted to calculate the optimization reference value X.

[0018] As a preferred solution of the biomass boiler combustion efficiency optimization method based on historical data of the present invention, the calculation of the thermal efficiency value η is shown in the following formula:

[0019]

[0020] Where D is the steam production, h2 is the superheated steam enthalpy, h1 is the feed water enthalpy, B is the fuel consumption, Q net is the low calorific value of the fuel, k1 is the furnace temperature correction coefficient, and k2 is the oxygen content correction coefficient;

[0021] The calculation formula of the furnace temperature correction coefficient k1 is:

[0022] k1=1-0.0015|T r -T s |

[0023] Among them, T r is the actual furnace temperature, T s is the standard furnace temperature;

[0024] The calculation formula of the oxygen content correction coefficient k2 is:

[0025]

[0026] Among them, O2 is the volume fraction of oxygen in the measured flue gas.

[0027] As a preferred solution of the biomass boiler combustion efficiency optimization method based on historical data of the present invention, the calculation S of the comprehensive score of the high-efficiency operation section is shown in the following formula:

[0028]

[0029] Among them, w1, w2, w3 are weight coefficients, P is the actual steam pressure, P s is the standard steam pressure;

[0030] The calculation of the optimization benchmark parameter value X is shown in the following formula:

[0031]

[0032] Among them, x i is the measured value of each parameter, S i is the comprehensive score at the corresponding moment, and n is the number of data points.

[0033] As a preferred solution of the method for optimizing the combustion efficiency of a biomass boiler based on historical data of the present invention, the association model is a polynomial association model of the thermal efficiency value η and the normalized parameter, as shown in the following formula:

[0034]

[0035] Among them, i = 1, 2, 3, 4 correspond to furnace temperature, oxygen content, steam pressure and fuel supply rate respectively, a i , b i is the unknown coefficient, c is the interaction coefficient, X norm,i is the normalization function;

[0036] The normalization function is expressed as follows:

[0037]

[0038] Among them, X i is the actual parameter value, X max and X minare the historical maximum and minimum values ​​of the parameters, α i is the parameter dynamic correction coefficient.

[0039] As a preferred solution of the biomass boiler combustion efficiency optimization method based on historical data of the present invention, the weight coefficient is calculated as shown in the following formula:

[0040]

[0041] Among them, the weight coefficient w j The calculation formula is:

[0042]

[0043] Among them, λ is the smoothing factor (value is 0.1), μ is the time attenuation coefficient (value is 0.001), t j is the interval between the data point and the current time, η j is the actual efficiency value, is the average efficiency value.

[0044] As a preferred solution of the biomass boiler combustion efficiency optimization method based on historical data of the present invention, the boiler combustion efficiency score includes:

[0045] The normalized parameters and the corresponding weight coefficients are weighted and superimposed to obtain the initial efficiency score;

[0046] The initial efficiency score is corrected for the time cumulative effect; the time cumulative effect correction is to gradually increase the score penalty through an exponential function when the parameter continues to deviate from the optimization benchmark value;

[0047] Performing parameter coupling correction on the initial efficiency score after the correction of the time cumulative effect, and obtaining the boiler combustion efficiency score;

[0048] The parameter coupling correction is to add additional score adjustments according to the consistency of the deviation directions when multiple parameters deviate from the baseline values ​​at the same time.

[0049] As a preferred solution of the biomass boiler combustion efficiency optimization method based on historical data of the present invention, wherein: the preset threshold value includes a dynamic warning threshold value and a mandatory intervention threshold value;

[0050] When the boiler combustion efficiency score is lower than the dynamic warning threshold and lasts for more than 15 minutes, an optimization suggestion is issued; when the boiler combustion efficiency score is lower than the mandatory intervention threshold or lasts lower than the dynamic warning threshold for more than 30 minutes, an optimization control process is triggered;

[0051] The calculation of the dynamic warning threshold and the mandatory intervention threshold is shown in the following formula:

[0052]

[0053] Among them, μ S (t) and σ S (t) are the moving average and standard deviation of the scores in the last 7 days, ρ is the threshold period adjustment coefficient, θ1(t) is the dynamic warning threshold, θ2(t) is the mandatory intervention threshold, and T is the characteristic period, i.e. 24 hours.

[0054] In a second aspect, an embodiment of the present invention provides a biomass boiler combustion efficiency optimization system based on historical data, which includes:

[0055] A collection module, used to collect historical operation data of the biomass boiler; the historical operation data includes boiler temperature, oxygen content, steam pressure and fuel supply rate;

[0056] A segmentation judgment module is used to segment the historical operation data according to the time series, divide the boiler into high-efficiency operation segments and low-efficiency operation segments, and use the operation parameters of the high-efficiency operation segments as optimization benchmark data;

[0057] A model building module, used to establish a correlation model between boiler combustion efficiency and operating parameters based on the optimization benchmark data, and calculate the weight coefficient of each parameter by the least square method;

[0058] The trigger adjustment module is used to perform weighted calculation on the weight coefficient and the real-time operating parameters to obtain a boiler combustion efficiency score. When the efficiency score is lower than a preset threshold, the optimization control is triggered to dynamically adjust the fuel supply rate and oxygen content according to the optimization benchmark data.

[0059] The beneficial effect of the present invention is that by comprehensively collecting and deeply analyzing the historical operating data of the biomass boiler, combined with the dynamic correction model of thermal efficiency, the high-efficiency operating segment is accurately identified and the optimized benchmark parameters are extracted, and a correlation model between combustion efficiency and operating parameters is established. The model is optimized by polynomial fitting and weighted least squares method, and comprehensively considers the time decay and the coupling effect between parameters, which greatly improves the accuracy and stability of efficiency prediction. In actual operation, the scheme realizes continuous monitoring and intelligent adjustment of boiler combustion efficiency through dynamic normalization of real-time operating data and efficiency score evaluation. When the efficiency score is lower than the threshold, the optimization control is triggered. Finally, through the dynamic adjustment of the fuel supply rate and oxygen content, the boiler operation state gradually moves closer to the high-efficiency range, thereby improving combustion efficiency and reducing energy waste and pollution emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0061] Figure 1 The figure is a flow chart of a method for optimizing the combustion efficiency of a biomass boiler based on historical data. DETAILED DESCRIPTION

[0062] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0063] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0064] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0065] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0066] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0067] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0068] Example 1

[0069] Reference Figure 1 , which is the first embodiment of the present invention, provides a method for optimizing the combustion efficiency of a biomass boiler based on historical data, comprising:

[0070] S1: Collecting historical operation data of the biomass boiler, wherein the historical operation data includes boiler temperature, oxygen content, steam pressure and fuel supply rate;

[0071] The historical operation data of the biomass boiler is collected, and the historical operation data includes the following parameters: the furnace temperature of the boiler is collected by 8 temperature measuring points arranged around the furnace using K-type thermocouples, and the temperature measuring points are evenly distributed along the circumference of the furnace and are 50 mm away from the furnace wall; the oxygen content in the boiler exhaust gas is collected at the flue outlet by a zirconia oxygen sensor, and the sampling frequency of the zirconia oxygen sensor is 2 times per second; the steam pressure is collected by a pressure sensor arranged at the superheater outlet, and the measurement range of the pressure sensor is 0-2.5MPa; the fuel supply rate is calculated by the speed sensor of the chain conveyor, and the feed amount of the chain conveyor is linearly related to the speed; the collection time span of the historical operation data is 90 consecutive days, and the sampling interval is 1 minute.

[0072] S2: segmenting the historical operation data according to the time series to divide the boiler into high-efficiency operation segments and low-efficiency operation segments, and using the operation parameters of the high-efficiency operation segments as optimization benchmark data;

[0073] The historical operation data is processed in segments according to the time series: first, the data of 90 consecutive days is divided into 30 minutes as the basic time unit T, and the thermal efficiency value η is calculated in each time unit. The calculation formula of the thermal efficiency value η is:

[0074]

[0075] Where D is steam production (t / h), h2 is superheated steam enthalpy (kJ / kg), h1 is feed water enthalpy (kJ / kg), B is fuel consumption (t / h), Q net is the low calorific value of fuel (kJ / kg), k1 is the furnace temperature correction coefficient, and k2 is the oxygen content correction coefficient.

[0076] The calculation formula of the furnace temperature correction coefficient k1 is:

[0077] k1=1-0.0015|T r -T s |

[0078] Among them, T r is the actual furnace temperature (°C), T s The standard furnace temperature is 850℃.

[0079] The calculation formula of the oxygen content correction coefficient k2 is:

[0080]

[0081] Wherein, O2 is the volume fraction (%) of oxygen in the measured flue gas.

[0082] When the operating interval with the thermal efficiency value η greater than 85% and lasting for more than 120 minutes is divided into the high-efficiency operating section, the comprehensive score S of the high-efficiency operating section is calculated:

[0083]

[0084] Among them, w1, w2, w3 are weight coefficients, P is the actual steam pressure, P s The standard steam pressure is 1.8MPa.

[0085] Extract the operation data of the high-efficiency operation segment whose comprehensive score S is in the top 30% interval, and calculate the optimization benchmark parameter value X:

[0086]

[0087] Among them, x i is the measured value of each parameter, S i is the comprehensive score at the corresponding moment, and n is the number of data points; the optimized benchmark data include parameter ranges such as furnace temperature 850±20℃, oxygen content 6±0.5%, steam pressure 1.8±0.1MPa, and fuel supply rate 2.5±0.2t / h.

[0088] Optimally, there is an optimal matching range between the combustion efficiency and furnace temperature of the biomass boiler. Too high or too low will lead to a decrease in efficiency. When the temperature is too high (>870℃), it will aggravate the heat loss of the furnace wall and cause the precipitation of alkali metals in the biomass fuel and the formation of coking on the heating surface. When the temperature is too low (<830℃), it will cause incomplete combustion, increase the loss of combustibles, and easily form carbon monoxide. Therefore, the furnace temperature correction coefficient is used for calculation and correction. When the temperature deviates from the standard value of 850℃, the efficiency is reduced by 0.15% for every 1℃ deviation. Since the excess air coefficient and boiler efficiency are in a parabolic relationship and there is an optimal value, too high oxygen content will increase the heat loss of flue gas, and too low oxygen content will lead to incomplete combustion. Therefore, the oxygen content correction coefficient is designed to effectively correct the deviation of the excess air coefficient from the optimal value.

[0089] The product relationship of k1 and k2 reflects the coupling effect of temperature and oxygen content. When the two parameters are in the optimal range at the same time, the total correction coefficient is close to 1. Any deviation of any parameter from the optimal value will lead to a decrease in the efficiency calculation value. After adopting this correction coefficient, the error between the efficiency calculation value and the actual heat balance method calculation result is reduced by about 40%, effectively avoiding the one-sidedness of calculating efficiency based solely on the input-output ratio.

[0090] S3: Based on the optimization benchmark data, a correlation model between boiler combustion efficiency and operating parameters is established, and a weight coefficient of each parameter is calculated by the least square method;

[0091] First, the four operating parameters of furnace temperature, oxygen content, steam pressure and fuel supply rate are normalized. The normalization process uses interval mapping method to map parameter values ​​to the interval [0,1]. Dynamic correction items based on time period are introduced into the normalized parameters. The dynamic correction items include sinusoidal fluctuations with a period of 24 hours and exponential decay of parameter deviations, as follows:

[0092]

[0093] Among them, X i is the actual parameter value, X max and X min are the historical maximum and minimum values ​​of the parameters, α i is the parameter dynamic correction coefficient, X norm,i is the normalization function;

[0094] The calculation of the parameter dynamic correction coefficient is shown in the following formula:

[0095]

[0096] Among them, β is the fluctuation amplitude coefficient (value is 0.1), t is the current time, T is the characteristic period (24 hours), γ is the attenuation coefficient (value is 0.05), X opt To optimize the benchmark value.

[0097] Secondly, a polynomial prediction model including linear terms, quadratic terms and cross terms is constructed. The linear terms in the polynomial prediction model reflect the direct impact of a single parameter on efficiency, the quadratic terms reflect the nonlinear characteristics of parameter changes, and the cross terms characterize the coupling effect between parameters. That is, a polynomial correlation model between boiler combustion efficiency η and normalized parameters is established, as shown in the following formula:

[0098]

[0099] Among them, i = 1, 2, 3, 4 correspond to furnace temperature, oxygen content, steam pressure and fuel supply rate respectively, a i , b i is the unknown coefficient, and c is the interaction coefficient.

[0100] Then, a weighted least squares objective function is constructed based on historical data. The weight coefficient in the weighted least squares objective function is determined by the data timeliness and efficiency deviation. The data timeliness is described by an exponential decay function, and the efficiency deviation is quantified by a Gaussian kernel function. The weighted least squares objective function is shown in the following formula:

[0101]

[0102] Among them, the weight coefficient w j The calculation formula is:

[0103]

[0104] Among them, λ is the smoothing factor (value is 0.1), μ is the time attenuation coefficient (value is 0.001), t j is the interval between the data point and the current time, η j is the actual efficiency value, is the average efficiency value.

[0105] Finally, the normal equations are solved by matrix decomposition method to obtain the coefficients of each model. The positive and negative signs of the coefficients represent the promoting or inhibiting effect of the parameters on efficiency, and the absolute values ​​of the coefficients reflect the degree of influence of the parameters. The normal equations are shown in the following formula:

[0106] A=(X T WX) -1 X T WY

[0107] Wherein, X is the parameter matrix, W is the weight diagonal matrix, and Y is the efficiency vector; the optimal coefficient matrix A contains the weight coefficients of each parameter item in the model.

[0108] S4: performing weighted calculation on the weight coefficient and the real-time operating parameters to obtain a boiler combustion efficiency score, and triggering optimization control when the efficiency score is lower than a preset threshold;

[0109] Firstly, the operation data of the boiler in the latest 30 minutes are collected, and the operation data include furnace temperature, oxygen content, steam pressure and fuel supply rate; the collected operation data are smoothed in units of 1 minute, and the exponential moving average method is used to eliminate the interference caused by parameter fluctuations, and the time constant of the smoothing process is 5 minutes; the smoothed operation parameters are dynamically normalized, and the parameter distribution characteristics of the previous 24 hours are referred to in the dynamic normalization process, and an adaptive interval mapping method is used.

[0110] The normalized parameters are weighted and superimposed with the corresponding weight coefficients to obtain the initial efficiency score:

[0111]

[0112] Among them, w i is the weight coefficient of each parameter, k ij is the parameter interaction weight coefficient, t is the current time point, is the normalized value of the i-th parameter at time t, The normalized value of the jth parameter at time t.

[0113] The time cumulative effect correction is introduced into the initial efficiency score. When the parameter continues to deviate from the optimized benchmark value, the score penalty is gradually increased through the exponential function. At the same time, the parameter coupling correction term is introduced. When multiple parameters deviate from the benchmark value at the same time, additional score adjustments are added according to the consistency of the deviation direction. Finally, the corrected boiler combustion efficiency score is obtained, as shown in the following formula:

[0114]

[0115]

[0116] Among them, λ is the cumulative effect coefficient (0.1), τ is the cumulative time window (30 minutes), X opt is the optimized reference value, η1 is the coupling correction coefficient (0.05), D i is the normalized deviation of parameter i, sgn() is the sign function, s is the integral variable, representing the time period from t-τ to t, X n (s) is the normalized parameter value at time s.

[0117] The preset threshold of the efficiency score is determined by an adaptive mechanism: based on the efficiency score data of the past 7 days, the mean and standard deviation of the score are calculated, and the mean minus 1.5 times the standard deviation is used as the dynamic warning threshold, and the mean minus 2 times the standard deviation is used as the mandatory intervention threshold; when the efficiency score is lower than the dynamic warning threshold and lasts for more than 15 minutes, the system issues an optimization suggestion; when the efficiency score is lower than the mandatory intervention threshold or continues to be lower than the dynamic warning threshold for more than 30 minutes, the optimization control process is triggered.

[0118] Then, the calculation of dynamic warning threshold and mandatory intervention threshold are as follows:

[0119]

[0120]

[0121] Among them, μ S (t) and σ S (t) are the moving average and standard deviation of the scores in the last 7 days, and ρ is the threshold period adjustment coefficient (0.05).

[0122] Optimization control is triggered when the following conditions are met:

[0123]

[0124]

[0125] Among them, I[] is an indicative function, T1 is the warning judgment time window (30 minutes), and T2 is the forced intervention judgment time window (5 minutes).

[0126] S5: Dynamically adjust the fuel supply rate and oxygen content according to the optimized benchmark data, so that the boiler operating parameters gradually approach the parameter range of the high-efficiency operation section.

[0127] Furthermore, this embodiment also provides a biomass boiler combustion efficiency optimization system based on historical data, including:

[0128] A collection module, used to collect historical operation data of the biomass boiler; the historical operation data includes boiler temperature, oxygen content, steam pressure and fuel supply rate;

[0129] A segmentation judgment module is used to segment the historical operation data according to the time series, divide the boiler into high-efficiency operation segments and low-efficiency operation segments, and use the operation parameters of the high-efficiency operation segments as optimization benchmark data;

[0130] A model building module, used to establish a correlation model between boiler combustion efficiency and operating parameters based on the optimization benchmark data, and calculate the weight coefficient of each parameter by the least square method;

[0131] The trigger adjustment module is used to perform weighted calculation on the weight coefficient and the real-time operating parameters to obtain a boiler combustion efficiency score. When the efficiency score is lower than a preset threshold, the optimization control is triggered to dynamically adjust the fuel supply rate and oxygen content according to the optimization benchmark data.

[0132] This embodiment also provides a computer device, which is suitable for the case of a biomass boiler combustion efficiency optimization method based on historical data, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the biomass boiler combustion efficiency optimization method based on historical data proposed in the above embodiment.

[0133] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0134] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for optimizing the combustion efficiency of a biomass boiler based on historical data as proposed in the above embodiment is implemented.

[0135] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0136] Example 2

[0137] This is the second embodiment of the present invention, which provides a method for optimizing the combustion efficiency of a biomass boiler based on historical data. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0138] This study selected a power company's biomass power plant in Jiangxi Province as the test site. The plant mainly uses agricultural straw and forestry waste as fuel, and the rated evaporation capacity of the boiler is 20 tons / hour. The test team first conducted a comprehensive inspection of the boiler operation system and instrument calibration to ensure the accuracy and reliability of data collection.

[0139] In order to accurately capture the operating parameters of the biomass boiler, the team deployed a high-precision sensor array in the boiler system. The furnace temperature is monitored using 8 K-type thermocouples, which are evenly distributed along the circumference of the furnace. Each temperature measurement point maintains a standard distance of 50mm from the furnace wall to ensure the spatial uniformity of temperature measurement. Oxygen content monitoring is completed by a high-sensitivity zirconium oxide oxygen sensor with a sampling frequency of 2 times per second, which can capture the changes in oxygen concentration at the flue outlet in real time. The steam pressure sensor is installed at the superheater outlet, and the measurement range covers 0-2.5MPa, meeting the pressure monitoring needs under various operating conditions.

[0140] The data collection process was carried out strictly according to the preset plan. The operation data for 90 consecutive days was systematically recorded, with sampling every minute, forming a data set containing more than 120,000 data points. This data set not only records the operation parameters, but also provides a solid foundation for subsequent in-depth analysis.

[0141] In the data processing stage, the research team first preprocessed the raw data. Using 30 minutes as the basic time unit, the thermal efficiency of each time period was calculated. The thermal efficiency calculation took into account multiple key parameters such as steam production, steam enthalpy, feed water enthalpy, fuel consumption, and introduced correction factors for furnace temperature and oxygen content to make the efficiency evaluation more accurate and comprehensive.

[0142] Through careful analysis of 90 days of data, multiple high-efficiency operation segments were identified. The common feature of these segments is that the thermal efficiency continues to exceed 85% and the maintenance time is not less than 120 minutes. These high-efficiency operation segments were comprehensively scored, and finally the operation data with the top 30% of the comprehensive scores were extracted as the optimization benchmark. The following records were obtained:

[0143] Table 1 Biomass boiler operation efficiency test data

[0144]

[0145] Through in-depth analysis of the test data, it can be concluded that the operating efficiency of the biomass boiler is affected by the complex coupling of multiple parameters, and there is an optimal operating parameter range. It can be clearly observed from the table data that when the furnace temperature is 840-862℃, the oxygen content is 5.8-6.3%, the steam pressure is 1.75-1.85MPa, and the fuel supply rate is 2.3-2.7t / h, the boiler thermal efficiency remains at a high level of 85.7%-88.1%.

[0146] Compared with the traditional single parameter control method, the multi-parameter dynamic optimization strategy proposed in this invention significantly improves the operating efficiency of the biomass boiler. By introducing the temperature correction coefficient and the oxygen content correction coefficient, not only can the single parameter be accurately adjusted, but more importantly, the coupling effect between parameters can be captured. For example, when the furnace temperature deviates slightly from the standard value of 850°C, each deviation of 1°C will result in a 0.15% decrease in efficiency; at the same time, fluctuations in oxygen content will also cause nonlinear changes in thermal efficiency.

[0147] The innovation of this study is to build a polynomial prediction model containing linear terms, quadratic terms and cross terms, which not only reflects the direct impact of a single parameter on efficiency, but also reflects the complex interactions between parameters. By determining the model coefficients by weighted least squares method, researchers can quantify the specific contribution of each parameter to boiler efficiency.

[0148] Compared with the traditional method of adjusting based on experience, the adaptive optimization control mechanism of the present invention is more advanced. It can dynamically adjust the warning threshold and intervention threshold according to the operation data of the last 7 days, realizing real-time and accurate monitoring of the boiler operation status. When the efficiency score is lower than the dynamic warning threshold for 15 minutes in a row, the system will actively issue optimization suggestions; if it is continuously lower than the mandatory intervention threshold or is in a suboptimal state for a long time, the parameter adjustment process will be directly triggered.

[0149] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing the combustion efficiency of a biomass boiler based on historical data, characterized in that: include: Collecting historical operation data of the biomass boiler; the historical operation data includes boiler temperature, oxygen content, steam pressure and fuel supply rate; The historical operation data is segmented according to the time series to divide the boiler into a high-efficiency operation segment and an inefficient operation segment, and the operation parameters of the high-efficiency operation segment are used as optimization benchmark data; Based on the optimization benchmark data, a correlation model between boiler combustion efficiency and operating parameters is established, and a weight coefficient of each parameter is calculated by the least square method; The weight coefficient and the real-time operating parameters are weightedly calculated to obtain a boiler combustion efficiency score, and when the efficiency score is lower than a preset threshold, optimization control is triggered; The fuel supply rate and oxygen content are dynamically adjusted according to the optimized reference data.

2. The method for optimizing the combustion efficiency of a biomass boiler based on historical data according to claim 1, characterized in that: Obtaining the optimized benchmark data includes: Dividing the historical operation data according to the basic time unit T; Calculate the thermal efficiency value η in each time unit; The operation interval in which the thermal efficiency value is greater than a preset threshold and the duration exceeds a preset value is divided into a high-quality operation section, and the comprehensive score S of the high-quality operation section is calculated; The operation data with the highest comprehensive score in the efficient operation section is extracted to calculate the optimization reference value X.

3. The method for optimizing the combustion efficiency of a biomass boiler based on historical data according to claim 2, characterized in that: The calculation of the thermal efficiency value η is shown in the following formula: Where D is the steam production, h2 is the superheated steam enthalpy, h1 is the feed water enthalpy, B is the fuel consumption, Q net is the low calorific value of the fuel, k1 is the furnace temperature correction coefficient, and k2 is the oxygen content correction coefficient; The calculation formula of the furnace temperature correction coefficient k1 is: k1=1-0.0015|T r -T s | Among them, T r is the actual furnace temperature, T s is the standard furnace temperature; The calculation formula of the oxygen content correction coefficient k2 is: Among them, O2 is the volume fraction of oxygen in the measured flue gas.

4. The method for optimizing the combustion efficiency of a biomass boiler based on historical data according to claim 3, characterized in that: The calculation formula S of the comprehensive score of the efficient operation section is as follows: Among them, w1, w2, w3 are weight coefficients, P is the actual steam pressure, P s is the standard steam pressure; The calculation of the optimization benchmark parameter value X is shown in the following formula: Among them, x i is the measured value of each parameter, S i is the comprehensive score at the corresponding moment, and n is the number of data points.

5. The method for optimizing the combustion efficiency of a biomass boiler based on historical data according to claim 4, characterized in that: The correlation model is a polynomial correlation model of the thermal efficiency value η and the normalized parameter, as shown in the following formula: Among them, i = 1, 2, 3, 4 correspond to furnace temperature, oxygen content, steam pressure and fuel supply rate respectively, a i 、b i is the unknown coefficient, c is the interaction coefficient, X norm,i is the normalization function; The normalization function is expressed as follows: Among them, X i is the actual parameter value, X max and X min are the historical maximum and minimum values ​​of the parameters, α i is the parameter dynamic correction coefficient.

6. The method for optimizing the combustion efficiency of a biomass boiler based on historical data according to claim 5, characterized in that: The weight coefficient is calculated as follows: Among them, the weight coefficient w j The calculation formula is: Among them, λ is the smoothing factor (value is 0.1), μ is the time attenuation coefficient (value is 0.001), t j is the interval between the data point and the current time, η j is the actual efficiency value, is the average efficiency value.

7. The method for optimizing the combustion efficiency of a biomass boiler based on historical data according to claim 6, characterized in that: The boiler combustion efficiency score includes: The normalized parameters and the corresponding weight coefficients are weighted and superimposed to obtain the initial efficiency score; The initial efficiency score is corrected for the time cumulative effect; the time cumulative effect correction is to gradually increase the score penalty through an exponential function when the parameter continues to deviate from the optimization benchmark value; Performing parameter coupling correction on the initial efficiency score after the correction of the time cumulative effect, and obtaining the boiler combustion efficiency score; The parameter coupling correction is to add additional score adjustments according to the consistency of the deviation directions when multiple parameters deviate from the baseline values ​​at the same time.

8. The method for optimizing the combustion efficiency of a biomass boiler based on historical data according to claim 7, characterized in that: The preset thresholds include a dynamic warning threshold and a mandatory intervention threshold; When the boiler combustion efficiency score is lower than the dynamic warning threshold and lasts for more than 15 minutes, an optimization suggestion is issued; when the boiler combustion efficiency score is lower than the mandatory intervention threshold or lasts lower than the dynamic warning threshold for more than 30 minutes, an optimization control process is triggered; The calculation of the dynamic warning threshold and the mandatory intervention threshold is shown in the following formula: Among them, μ S (t) and σ S (t) are the moving average and standard deviation of the scores in the last 7 days, ρ is the threshold period adjustment coefficient, θ1(t) is the dynamic warning threshold, θ2(t) is the mandatory intervention threshold, and T is the characteristic period, i.e. 24 hours.

9. A biomass boiler combustion efficiency optimization system based on historical data, based on the biomass boiler combustion efficiency optimization method based on historical data according to any one of claims 1 to 8, characterized in that: include: A collection module, used to collect historical operation data of the biomass boiler; the historical operation data includes boiler temperature, oxygen content, steam pressure and fuel supply rate; A segmentation judgment module is used to segment the historical operation data according to the time series, divide the boiler into high-efficiency operation segments and low-efficiency operation segments, and use the operation parameters of the high-efficiency operation segments as optimization benchmark data; A model building module, used to establish a correlation model between boiler combustion efficiency and operating parameters based on the optimization benchmark data, and calculate the weight coefficient of each parameter by the least square method; The trigger adjustment module is used to perform weighted calculation on the weight coefficient and the real-time operating parameters to obtain a boiler combustion efficiency score. When the efficiency score is lower than a preset threshold, the optimization control is triggered to dynamically adjust the fuel supply rate and oxygen content according to the optimization benchmark data.

Images