Internal combustion engine maintenance method based on SFC optimization

Abstract

The invention relates to the technical field of internal combustion engine maintenance, and discloses an internal combustion engine maintenance method based on SFC optimization, which comprises the following steps: setting monitoring points of an internal combustion engine based on historical data, and classifying the monitoring points to generate multiple types of monitoring points; generating a plurality of types of monitoring data based on all types of obtained monitoring points; constructing an SFC optimization model based on the historical operation state data of the internal combustion engine; generating a corresponding SFC optimization instruction and a flue gas recovery instruction in combination with the multiple types of monitoring data and the SFC optimization model; wherein the step of generating the multiple types of monitoring data comprises the substeps of generating a first type of monitoring data based on the fuel supply data and the air flow data; and generating a second type of monitoring data based on the SFC value. The method can comprehensively consider multiple factors to quantitatively evaluate the operation state of the internal combustion engine, and is more comprehensive and accurate than a traditional method for evaluating the state of the internal combustion engine only depending on a single index.

Description

Technical Field

[0001] The present invention relates to the technical field of internal combustion engine maintenance, and particularly to a method for maintaining an internal combustion engine based on SFC optimization. Background Art

[0002] The basic working principles of gas turbines and internal combustion engines are the basis for understanding their performance. These devices convert chemical energy into mechanical energy by burning fuel. As an important indicator for measuring the efficiency of gas turbines, SFC represents the fuel consumption per unit power output, and its efficiency is affected by various factors such as combustion efficiency, intake conditions, and load changes. There are significant limitations in the prior art in terms of SFC optimization, including insufficient efficiency and emission control challenges under different operating conditions, resulting in poor economy and environmental friendliness.

[0003] With the increasingly strict environmental protection regulations, it is urgent for gas turbines to improve efficiency while reducing emissions to meet the market's demand for sustainable development. In addition, the intensification of market competition has prompted gas turbine manufacturers to seek solutions to improve economy and performance. In recent years, with the progress of new materials and intelligent control technologies, new possibilities have been provided for the improvement of SFC. The development of these technologies not only helps to improve the overall performance of gas turbines but also lays the foundation for achieving a more efficient and low-emission combustion process. Summary of the Invention

[0004] The objective of the present invention is to comprehensively analyze the influence of relevant factors such as the fuel supply system, intake system, and load conditions on the SFC value, and accurately adjust the operating parameters of the internal combustion engine according to the SFC value to achieve the best performance.

[0005] To achieve the above objective, the present invention provides a method for maintaining an internal combustion engine based on SFC optimization, including: Setting monitoring points of the internal combustion engine based on historical data, and classifying the monitoring points to generate multiple types of monitoring points; Generating multiple types of monitoring data based on all types of monitoring points obtained; Constructing an SFC optimization model based on the historical operating state data of the internal combustion engine; Generating corresponding SFC optimization instructions and flue gas recovery instructions by combining multiple types of monitoring data and the SFC optimization model; Among them, generating multiple types of monitoring data includes: Generating the first type of monitoring data based on fuel supply data and air flow data; Generating the second type of monitoring data based on the SFC value.

[0006] In some embodiments of the present invention, when constructing the SFC optimization model, it includes: Generating a first historical reference value C1 based on the historical data of the first type of monitoring data of the internal combustion engine; Generate a second historical reference value C2 based on the historical data of the second type of monitoring data of the internal combustion engine; Combine the first historical reference value C1 and the second historical reference value C2 to generate an SFC optimization reference value C3; C3 = C2 / C1 + k1; where k1 is the first correction deviation value; Obtain the historical operating state data of the internal combustion engine to generate an operating state set of the internal combustion engine; Obtain the corresponding optimization reference value set based on the operating state set; Determine the corresponding operating state of the internal combustion engine based on the historical data for the optimization reference value C3 in the optimization reference value set.

[0007] In some embodiments of the present invention, when generating the first historical reference value C1, it includes: Obtain the historical data of the first type of monitoring data of the current operating state of the internal combustion engine based on the operating state set of the internal combustion engine; Among them, obtain the historical fuel supply parameter type of the current operating state of the internal combustion engine and the corresponding parameter value to generate a fuel supply parameter matrix X; X = ; where x 1i is the i-th type of historical fuel supply parameter, x 2i is the parameter value of the i-th type of historical fuel supply parameter, and n is the total number of historical fuel supply parameter types; Generate an air flow reference value Y based on the obtained historical air blowing power P air ; Y = a1 * P air + b1; where a1 is the first fixed coefficient and b1 is the deviation value of the air flow reference value; Generate a fuel supply parameter comprehensive value XK based on the fuel supply parameter matrix X; Obtain the weight wi corresponding to the i-th fuel supply parameter based on the historical data; XK =

[0008] Generate the first historical reference value C1 based on the fuel supply parameter comprehensive value XK and the air flow reference value Y; C1 = f1 + XK + f2 * Y; where f1 is the weight of the fuel supply reference value XK and f2 is the weight of the air flow reference value Y.

[0009] In some embodiments of the present invention, when obtaining the weight wi corresponding to the i-th fuel supply parameter, it includes: Classify the operating state of an internal combustion engine based on operating metrics to generate a first type of operating state and a second type of operating state; Obtain the parameter mean value zi corresponding to the i-th fuel supply parameter in the first type of operating state; Generate the weight wi corresponding to the i-th fuel supply parameter based on the parameter mean value zi; wi = k2 / zi; Where k2 is the second correction deviation value.

[0010] In some embodiments of the present invention, when generating the second historical reference value C2, it includes: Obtain the historical operating state data set D of the internal combustion engine and the corresponding SFC value; D = {d1, d2…dj…dm}; Construct a multiple linear regression model of the SFC value by combining the historical operating state data set D and the corresponding SFC value: C2 =

[0011] Where b0 is the slope of the multiple linear regression model, si is the regression coefficient of the historical operating state data of the j-th internal combustion engine, dj is the reference value of the historical operating state data of the j-th internal combustion engine, and k3 is the intercept of the multiple linear regression model.

[0012] In some embodiments of the present invention, when determining the corresponding operating state of the internal combustion engine, it includes: Obtain the SFC optimization reference value C3 under all operating states of the internal combustion engine; Take the derivative of the SFC optimization reference value C3 under the current operating state of the internal combustion engine to generate the reference value change rate curve C v ; For the reference value change rate curve C v Perform smooth feature extraction to generate the reference value feature map Ct; Determine the corresponding operating state of the internal combustion engine based on the reference value feature map Ct.

[0013] In some embodiments of the present invention, when generating the reference value feature map Ct, it includes: Preset the smoothing interval g based on historical data; Based on the smoothing interval g, divide the reference value change rate curve C v To generate multiple sub-change rate curves; Obtain the left endpoint, right endpoint, and peak value of the current sub-change rate curve; Compare the peak value of the current sub-change rate curve with the first preset peak value; If the peak value of the current sub-change rate curve is less than the first preset peak value, connect the left endpoint and the right endpoint of the current sub-change rate curve to generate a sub-smoothing curve; If the peak value of the current sub-change rate curve is greater than the first preset peak value, connect the left endpoint and the peak point of the current sub-change rate curve and connect the peak point and the right endpoint to generate a sub-smoothing curve; Obtain all sub-smoothing curves to generate a reference value feature map Ct.

[0014] In some embodiments of the present invention, when generating the corresponding SFC optimization instruction and the flue gas recovery instruction, it includes: Input the first type of monitoring data and the second type of monitoring data at the currently obtained monitoring time node into the SFC optimization model to output the corresponding internal combustion engine operating state; Set the corresponding parameter adjustment range based on the current operating state of the internal combustion engine; Generate an SFC optimization instruction in combination with the parameter adjustment range; Predict the modified flue gas waste heat based on the SFC optimization instruction to generate a flue gas waste heat prediction value, and generate a flue gas recovery instruction based on the flue gas waste heat prediction value.

[0015] In some embodiments of the present invention, the SFC optimization instruction includes: The SFC optimization instruction is a combination of multiple types of optimization instructions; Among them, the multiple types of optimization instructions include: the first type of optimization instruction, the second type of optimization instruction, and the third type of optimization instruction; The first type of optimization instruction is a fuel supply parameter correction instruction; The second type of optimization instruction is a load distribution instruction; The third type of optimization instruction is an intake control instruction.

[0016] In some embodiments of the present invention, when generating the flue gas recovery instruction, it includes: Generate a flue gas prediction temperature reference value in combination with the currently obtained flue gas temperature data and the SFC optimization instruction; Compare the flue gas prediction temperature reference value and the flue gas temperature preset value to generate multiple flue gas recovery instructions.

[0017] Compared with the prior art, the beneficial effects of an internal combustion engine maintenance method based on SFC optimization provided by the embodiments of the present invention are as follows: By setting and classifying monitoring points through historical data to generate multiple types of monitoring data, the internal combustion engine can be comprehensively and accurately monitored; it helps to deeply understand the operating conditions of different aspects of the internal combustion engine and more accurately evaluate the operating state of the internal combustion engine.

[0018] By calculating the SFC optimization reference value C3, various factors can be comprehensively considered to quantitatively evaluate the operating state of the internal combustion engine; it is more comprehensive and accurate.

[0019] After inputting the monitoring data into the SFC optimization model to obtain the operating state, setting the parameter adjustment range according to the operating state and generating the SFC optimization instruction can adjust the internal combustion engine from different aspects; the synergistic effect of the instructions can effectively improve the operating efficiency of the internal combustion engine, reduce fuel consumption, increase the output power, etc.

[0020] By combining the SFC optimization instruction to predict the flue gas waste heat and generate the flue gas recovery instruction, the flue gas recovery can be carried out more effectively; the SFC optimization instruction changes the operating state of the internal combustion engine, affecting the flue gas waste heat situation, and the predicted flue gas waste heat value based on this can provide a more accurate basis for the flue gas recovery.

[0021] Comparing the flue gas predicted temperature reference value and the flue gas temperature preset value to generate various flue gas recovery instructions can flexibly adjust the flue gas recovery strategy according to the actual situation.

[0022] Classifying the operating state of the internal combustion engine, calculating the weight according to the mean value of the fuel supply parameters under different operating states, and constructing a multiple linear regression model of the SFC value, etc., enable this maintenance method to adapt to different operating states of the internal combustion engine.

[0023] Determining the operating state based on the reference value feature map Ct can avoid misjudgment caused by factors such as data fluctuations, improve the accuracy of state determination, and thus provide a more reliable basis for subsequent optimization and recovery instruction generation. Description of the Drawings

[0024] Figure 1 is a flowchart of a maintenance method for an internal combustion engine based on SFC optimization provided by an embodiment of the present invention. Detailed Embodiments

[0025] The following will further describe in detail the specific embodiments of the present invention with reference to the drawings and embodiments. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0026] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is 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 orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0027] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0028] In the description of the present invention, it should be noted that, unless otherwise clearly specified and defined, the terms "mounted", "connected", and "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0029] Embodiment 1: A method for maintaining an internal combustion engine based on SFC optimization provided by an embodiment of the present invention, as Figure 1 shown, includes: Setting monitoring points of the internal combustion engine based on historical data, and classifying the monitoring points to generate multiple types of monitoring points; Generating multiple types of monitoring data based on all types of monitoring points obtained; Constructing an SFC optimization model based on the historical operating state data of the internal combustion engine; Generating corresponding SFC optimization instructions and flue gas recovery instructions by combining multiple types of monitoring data and the SFC optimization model; Among them, generating multiple types of monitoring data includes: Generating the first type of monitoring data based on fuel supply data and air flow data; Generating the second type of monitoring data based on the SFC value.

[0030] In this embodiment, setting and classifying monitoring points based on historical data is the basis of the entire maintenance method. Targeted monitoring is carried out for different parts or different operating characteristics of the internal combustion engine. For example, the monitoring points set near key components such as the combustion chamber and piston may be classified into one category, while the monitoring points related to intake and exhaust may be classified into another category.

[0031] By classifying the monitoring points to generate different types of monitoring data, the operating state of the internal combustion engine can be reflected more meticulously. For example, the first type of monitoring data generated by the monitoring points related to fuel supply and air flow can directly reflect the preconditions of the combustion process.

[0032] It is reasonable to generate the first type of monitoring data based on fuel supply data and air flow data, because the supply ratio and flow rate of fuel and air have a crucial impact on the combustion efficiency, power output, etc. of internal combustion engines.

[0033] It is also of great significance to generate the second type of monitoring data based on the SFC value. SFC (Specific Fuel Consumption) is a key indicator for measuring the fuel economy of internal combustion engines, and the change in its value can reflect the overall operating efficiency of internal combustion engines. The monitoring data generated based on it can grasp the state of internal combustion engines from a macroscopic perspective.

[0034] Embodiment 2: When constructing the SFC optimization model, it includes: Generating the first historical reference value C1 based on the historical data of the first type of monitoring data of the internal combustion engine; Generating the second historical reference value C2 based on the historical data of the second type of monitoring data of the internal combustion engine; Combining the first historical reference value C1 and the second historical reference value C2 to generate the SFC optimization reference value C3; C3 = C2 / C1 + k1; where k1 is the first correction deviation value; Obtaining the historical operating state data of the internal combustion engine to generate the operating state set of the internal combustion engine; Obtaining the corresponding optimization reference value set based on the operating state set; Determining the corresponding operating state of the internal combustion engine based on the historical data for the optimization reference value C3 in the optimization reference value set.

[0035] In this embodiment, for the generation of the first historical reference value C1, by constructing the fuel supply parameter matrix X and combining the air flow reference value Y, various types of fuel supply parameters and their weights are considered, which can comprehensively reflect the historical state in terms of fuel supply. For example, different fuel injection amounts, injection times and other parameters are taken into consideration.

[0036] The second historical reference value C2 is calculated by constructing a multiple linear regression model of the SFC value, which can explore the relationship between the SFC value and the historical operating state data of the internal combustion engine, and this relationship can provide a basis for subsequent optimization.

[0037] Combining C1 and C2 to generate the SFC optimization reference value C3 (C3 = C2 / C1 + k1) can fuse the historical reference information in these two aspects of fuel supply and SFC. Among them, k1, as the correction deviation value, can adjust the model to a certain extent to adapt to different internal combustion engine characteristics or working conditions.

[0038] Generate an operating state set based on the historical operating state data of the internal combustion engine, further obtain the corresponding set of optimization reference values, and then determine the operating state of the internal combustion engine based on the historical data. This method can utilize a large amount of historical data to accurately judge the current operating state of the internal combustion engine, providing a basis for generating subsequent optimization instructions.

[0039] Embodiment 3: When generating the first historical reference value C1, it includes: Obtain the historical data of the first type of monitoring data of the current operating state of the internal combustion engine based on the operating state set of the internal combustion engine; Among them, obtain the historical fuel supply parameter types of the current operating state of the internal combustion engine and the corresponding parameter values to generate a fuel supply parameter matrix X; X = ; Among them, x 1i is the i-th type of historical fuel supply parameter, x 2i is the parameter value of the i-th type of historical fuel supply parameter, and n is the total number of historical fuel supply parameter types; Generate an air flow reference value Y based on the obtained historical air injection power P air ; Y = a1 * P air + b1; Among them, a1 is the first fixed coefficient, and b1 is the deviation value of the air flow reference value; Generate a fuel supply parameter comprehensive value XK based on the fuel supply parameter matrix X; Obtain the weight wi corresponding to the i-th fuel supply parameter based on the historical data; XK =

[0040] Generate the first historical reference value C1 based on the fuel supply parameter comprehensive value XK and the air flow reference value Y; C1 = f1 + XK + f2 * Y; Among them, f1 is the weight of the fuel supply reference value XK, and f2 is the weight of the air flow reference value Y.

[0041] In this embodiment, constructing the fuel supply parameter matrix X is to comprehensively represent the fuel supply situation of the internal combustion engine under different operating states. For example, x 1i can be the fuel injection pressure type, and x 2i is the corresponding specific injection pressure value.

[0042] a1 is the first fixed coefficient, which reflects the proportional relationship between the air injection power and the reference value of air flow; b1 is the deviation value of the reference value of air flow, which may be a correction value set considering some system errors or other factors not fully covered by the air injection power.

[0043] Air flow is crucial for the combustion process of an internal combustion engine. An accurate reference value Y of air flow helps to more comprehensively evaluate the operating state of the internal combustion engine.

[0044] When calculating the comprehensive value XK of fuel supply parameters, the weight w corresponding to the i-th fuel supply parameter is obtained based on historical data. These weights wi reflect the relative importance of different types of fuel supply parameters in the comprehensive evaluation.

[0045] For example, if a certain type of fuel supply parameter (such as fuel injection time) has a greater impact on the performance of the internal combustion engine, then its corresponding weight wi will be relatively large, thus having a more significant impact on the result when calculating XK.

[0046] In this way, C1 synthesizes the information of the comprehensive value XK of fuel supply parameters and the reference value Y of air flow, and adjusts the contributions of the two in the overall reference value according to the magnitude relationship between f1 and f2. For example, if f1 is larger, it indicates that the comprehensive value XK of fuel supply parameters is relatively more important in this evaluation system; if f2 is larger, then the reference value Y of air flow is more important.

[0047] Example 4: When obtaining the weight wi corresponding to the i-th fuel supply parameter, it includes: Classify the operating state of the internal combustion engine based on operating indicators to generate the first type of operating state and the second type of operating state; Obtain the parameter mean value zi corresponding to the i-th fuel supply parameter in the first type of operating state; Generate the weight wi corresponding to the i-th fuel supply parameter based on the parameter mean value zi; wi = k2 / zi; Where k2 is the second correction deviation value.

[0048] In this embodiment, classifying the operating state of the internal combustion engine based on operating indicators to generate the first type of operating state and the second type of operating state is an effective method to simplify and classify the complex operating conditions of the internal combustion engine.

[0049] Different types of operating states may have different characteristics. For example, the first type of operating state is the operating state of the internal combustion engine under normal load and stable speed, while the second type of operating state is the state under high load and variable speed operation. This classification helps to analyze the characteristics of fuel supply parameters under different operating modes.

[0050] Obtain the parameter mean value zi corresponding to the i-th fuel supply parameter under the first type of operating state. This mean value zi can represent the typical value of the i-th fuel supply parameter under a specific operating state (the first type of operating state).

[0051] Example 5: When generating the second historical reference value C2, it includes: Obtain the historical operating state data set D of the internal combustion engine and the corresponding SFC values; D = {d1, d2…dj…dm}; Construct a multiple linear regression model of the SFC value by combining the historical operating state data set D and the corresponding SFC values: C2 =

[0052] where b0 is the slope of the multiple linear regression model, si is the regression coefficient of the historical operating state data of the j-th internal combustion engine, dj is the reference value of the historical operating state data of the j-th internal combustion engine, and k3 is the intercept of the multiple linear regression model.

[0053] Example 6: When determining the corresponding operating state of the internal combustion engine, it includes: Obtain the SFC optimization reference value C3 under all operating states of the internal combustion engine; Take the derivative of the SFC optimization reference value C3 under the current operating state of the internal combustion engine to generate the reference value change rate curve C v ; For the reference value change rate curve C v Perform smooth feature extraction to generate the reference value feature map Ct; Determine the corresponding operating state of the internal combustion engine based on the reference value feature map Ct.

[0054] Example 7: When generating the reference value feature map Ct, it includes: Preset a smoothing interval g based on historical data; Based on the smoothing interval g, divide the reference value change rate curve C v to generate multiple sub-change rate curves; Obtain the left endpoint, right endpoint, and peak value of the current sub-change rate curve; Compare the peak value of the current sub-change rate curve with the first preset peak value; If the peak value of the current sub-change rate curve is less than the first preset peak value, connect the left endpoint and the right endpoint of the current sub-change rate curve to generate a sub-smoothing curve; If the peak value of the current sub-change rate curve is greater than the first preset peak value, connect the left endpoint of the current sub-change rate curve to the peak point and connect the peak point to the right endpoint to generate a sub-smoothing curve. Obtain all sub-smoothing curves to generate a reference value feature map Ct.

[0055] In this embodiment, by taking the derivative of the SFC optimization reference value C3 to obtain the reference value change rate curve Cv, the change trend of the C3 value can be captured. For example, if the value of Cv is large and positive, it may indicate that the operating state of the internal combustion engine is changing rapidly in the direction of decreasing efficiency.

[0056] The method of generating the reference value feature map Ct through smoothing feature extraction can remove some noise interferences and better highlight the main features of Cv. For example, some small peaks caused by short-term fluctuations can be eliminated through smoothing, so as to more accurately determine the operating state of the internal combustion engine according to Ct.

[0057] Presetting the smoothing interval g based on historical data is the first step in generating the reference value feature map Ct. The smoothing interval g determines the scale for dividing the reference value change rate curve Cv.

[0058] For example, if the value of g is large, the number of sub-change rate curves divided will be relatively small, and the data range covered by each sub-curve will be large; conversely, if the value of g is small, the number of sub-change rate curves will be large, and the data range covered by each sub-curve will be small.

[0059] Divide the reference value change rate curve Cv according to the smoothing interval g to generate multiple sub-change rate curves. This division method decomposes the Cv curve according to certain rules, facilitating subsequent analysis of the local features of the curve.

[0060] Each sub-change rate curve represents the change situation of Cv within a certain local interval, which helps to capture the change characteristics of the curve more carefully.

[0061] Obtaining the left endpoint, right endpoint, and peak value of the current sub-change rate curve is an important step in analyzing the characteristics of the sub-curve. The left endpoint and right endpoint determine the starting and ending positions of the sub-curve, while the peak value reflects the maximum value point in the sub-curve.

[0062] These key feature points can represent the basic morphological features of the sub-curve. For example, the size and position of the peak value can reflect the maximum change situation of the reference value change rate within this local interval.

[0063] Compare the peak value of the current sub-change rate curve with the first preset peak value, and take different processing methods according to the comparison result.

[0064] If the peak value is less than the first preset peak value, it indicates that the change of the sub-curve is relatively gentle. At this time, connect the left endpoint and the right endpoint to generate a sub-smoothing curve. This method actually simplifies the sub-curve and removes the possible small fluctuations.

[0065] If the peak value is greater than the first preset peak value, it indicates that the sub-curve has obvious fluctuations. Connect the left endpoint and the peak point and connect the peak point and the right endpoint to generate a sub-smoothing curve. In this way, while retaining the main fluctuation characteristics, the curve is also smoothed to a certain extent.

[0066] Finally, obtain all the sub-smoothing curves to generate the reference value feature map Ct. Ct is composed of each processed sub-smoothing curve, and it can comprehensively reflect the overall characteristics of the reference value change rate curve Cv after smoothing and feature extraction.

[0067] Through Ct, the change characteristics of the reference value related to the operation state of the internal combustion engine can be analyzed more intuitively, providing an important basis for accurately determining the operation state of the internal combustion engine subsequently.

[0068] Embodiment 8: When generating the corresponding SFC optimization instruction and flue gas recovery instruction, it includes: Input the first type of monitoring data and the second type of monitoring data at the currently monitored time node into the SFC optimization model to output the corresponding operation state of the internal combustion engine; Set the corresponding parameter adjustment range based on the current operation state of the internal combustion engine; Generate an SFC optimization instruction in combination with the parameter adjustment range; Predict the modified flue gas waste heat based on the SFC optimization instruction to generate a flue gas waste heat prediction value, and generate a flue gas recovery instruction based on the flue gas waste heat prediction value.

[0069] Embodiment 9: The SFC optimization instruction includes: The SFC optimization instruction is a combination of multiple types of optimization instructions; Among them, the multiple types of optimization instructions include: the first type of optimization instruction, the second type of optimization instruction, and the third type of optimization instruction; The first type of optimization instruction is a fuel supply parameter correction instruction; The second type of optimization instruction is a load distribution instruction; The third type of optimization instruction is an intake control instruction.

[0070] In this embodiment, an SFC optimization instruction is generated in combination with the parameter adjustment range. The SFC optimization instruction includes multiple types, such as a fuel supply parameter correction instruction, a load distribution instruction, and an intake control instruction, etc.

[0071] According to the set parameter adjustment range, for the fuel supply parameter correction instruction, parameters such as fuel injection volume and injection time may be adjusted within the range; the load distribution instruction may redistribute the load of the internal combustion engine according to the range; the intake control instruction may adjust the intake volume, intake time, etc. The combined effect of these instructions aims to optimize the operation of the internal combustion engine and improve efficiency or performance.

[0072] Embodiment 10: When generating the flue gas recovery instruction, it includes: Combining the obtained current flue gas temperature data and the SFC optimization instruction to generate a flue gas predicted temperature reference value; Comparing the flue gas predicted temperature reference value and the preset flue gas temperature value to generate various flue gas recovery instructions.

[0073] In this embodiment, after inputting the monitoring data into the SFC optimization model to output the operating state of the internal combustion engine, it is reasonable to set the parameter adjustment range based on the operating state and generate the SFC optimization instruction. For example, if the operating state of the internal combustion engine shows low combustion efficiency, for the fuel supply parameter correction instruction (the first type of optimization instruction), the fuel injection volume or injection time may be adjusted; for the load distribution instruction (the second type of optimization instruction), the load may be redistributed to improve the overall efficiency; for the intake control instruction (the third type of optimization instruction), the intake volume or intake time may be adjusted, etc.

[0074] When predicting the corrected flue gas waste heat to generate a flue gas waste heat prediction value based on the SFC optimization instruction, the relationship between the adjustment of the operating state of the internal combustion engine by the SFC optimization instruction and the flue gas waste heat can be utilized. For example, when the fuel supply parameter correction instruction adjusts the fuel injection volume, it may affect the combustion efficiency, thereby changing the temperature and waste heat situation of the flue gas.

[0075] By combining the current flue gas temperature data and the SFC optimization instruction to generate a flue gas predicted temperature reference value and comparing it with the preset flue gas temperature value to generate various flue gas recovery instructions, the flue gas recovery strategy can be flexibly adjusted according to the actual flue gas temperature situation. For example, if the flue gas predicted temperature reference value is higher than the preset value, an instruction to increase the operating power of the flue gas recovery equipment may be generated; if it is lower than the preset value, the operating power may be reduced or some auxiliary adjustments may be made to improve the recovery efficiency of the flue gas waste heat.

[0076] Finally, it should be noted that: Obviously, those skilled in the art can make various changes and deformations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and deformations.

[0077] The above is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. An internal combustion engine maintenance method based on SFC optimization, characterized in that, Including: Setting monitoring points of an internal combustion engine based on historical data, and classifying the monitoring points to generate multiple types of monitoring points; Generating multiple types of monitoring data based on all types of monitoring points obtained; Constructing an SFC optimization model based on the historical operating state data of the internal combustion engine; Generating corresponding SFC optimization instructions and flue gas recovery instructions by combining multiple types of monitoring data and the SFC optimization model; Among them, generating multiple types of monitoring data includes: Generating the first type of monitoring data based on fuel supply data and air flow data; Generating the second type of monitoring data based on the SFC value.

2. The internal combustion engine maintenance method optimized based on SFC according to claim 1, characterized in that, When constructing the SFC optimization model, it includes: Generating a first historical reference value C1 based on the historical data of the first type of monitoring data of the internal combustion engine; Generating a second historical reference value C2 based on the historical data of the second type of monitoring data of the internal combustion engine; Combining the first historical reference value C1 and the second historical reference value C2 to generate an SFC optimization reference value C3; C3 = C2 / C1 + k1; Among them, k1 is the first correction deviation value; Obtaining the historical operating state data of the internal combustion engine to generate an operating state set of the internal combustion engine; Obtaining a corresponding optimization reference value set based on the operating state set; Determining the corresponding operating state of the internal combustion engine for the optimization reference value C3 in the optimization reference value set based on historical data.

3. The internal combustion engine maintenance method optimized based on SFC according to claim 2, wherein, When generating the first historical reference value C1, it includes: Obtaining the historical data of the first type of monitoring data of the current operating state of the internal combustion engine based on the operating state set of the internal combustion engine; Among them, obtaining the historical fuel supply parameter type and the corresponding parameter value of the current operating state of the internal combustion engine to generate a fuel supply parameter matrix X; X= ； where x 1i is the i-th type of historical fuel supply parameter type, and x 2i is the parameter value of the i-th type of historical fuel supply parameter type, and n is the total number of historical fuel supply parameter types; Based on the obtained historical air blowing power P air Generate an air flow reference value Y; Y = a1 * P air + b1; Among them, a1 is the first fixed coefficient, and b1 is the deviation value of the air flow reference value; Generating a fuel supply parameter comprehensive value XK based on the fuel supply parameter matrix X; Obtaining the weight wi corresponding to the i-th fuel supply parameter based on historical data; XK= Generating the first historical reference value C1 based on the fuel supply parameter comprehensive value XK and the air flow reference value Y; C1 = f1 + XK + f2 * Y; Among them, f1 is the weight of the fuel supply reference value XK, and f2 is the weight of the air flow reference value Y.

4. The internal combustion engine maintenance method optimized based on SFC according to claim 3, characterized in that When obtaining the weight wi corresponding to the i-th fuel supply parameter, it includes: Classifying the operating state of the internal combustion engine based on operating indicators to generate a first type of operating state and a second type of operating state; Obtaining the parameter mean value zi corresponding to the i-th fuel supply parameter in the first type of operating state; Generating the weight wi corresponding to the i-th fuel supply parameter based on the parameter mean value zi; wi = k2 / zi; Among them, k2 is the second correction deviation value.

5. The internal combustion engine maintenance method optimized based on SFC according to claim 4, characterized in that, When generating the second historical reference value C2, it includes: Obtaining the historical operating state data set D of the internal combustion engine and the corresponding SFC value; D = {d1, d2…dj…dm}; Combining the historical operating state data set D and the corresponding SFC value to construct a multiple linear regression model of the SFC value: C2= Among them, b0 is the slope of the multiple linear regression model, si is the regression coefficient of the historical operating state data of the j-th internal combustion engine, dj is the reference value of the historical operating state data of the j-th internal combustion engine, and k3 is the intercept of the multiple linear regression model.

6. The internal combustion engine maintenance method optimized based on SFC according to claim 5, characterized in that When determining the corresponding operating state of the internal combustion engine, it includes: Obtaining the SFC optimization reference value C3 under all operating states of the internal combustion engine; Derive the derivative of the SFC optimization reference value C3 under the current operating state of the internal combustion engine to generate the reference value change rate curve C under the current operating state of the internal combustion engine v ; For the reference value change rate curve C v perform smooth feature extraction to generate a reference value feature map Ct; Determining the corresponding operating state of the internal combustion engine based on the reference value feature map Ct.

7. The internal combustion engine maintenance method optimized based on SFC according to claim 6, characterized in that, When generating the reference value feature map Ct, it includes: Presetting a smoothing interval g based on historical data; Based on the smooth interval g, divide the reference value change rate curve C v to generate multiple sub-change rate curves; Obtaining the left endpoint, right endpoint, and peak value of the current sub-change rate curve; Comparing the peak value of the current sub-change rate curve with a first preset peak value; If the peak value of the current sub-change rate curve is less than the first preset peak value, connecting the left endpoint and the right endpoint of the current sub-change rate curve to generate a sub-smoothing curve; If the peak value of the current sub-change rate curve is greater than the first preset peak value, connecting the left endpoint and the peak point of the current sub-change rate curve and connecting the peak point and the right endpoint to generate a sub-smoothing curve; Obtaining all sub-smoothing curves to generate the reference value feature map Ct.

8. The method for maintaining an internal combustion engine optimized based on SFC according to claim 7, characterized in that, When generating the corresponding SFC optimization instruction and flue gas recovery instruction, it includes: Inputting the first type of monitoring data and the second type of monitoring data at the currently monitored time node into the SFC optimization model to output the corresponding operating state of the internal combustion engine; Setting a corresponding parameter adjustment range based on the current operating state of the internal combustion engine; Generating an SFC optimization instruction in combination with the parameter adjustment range; Predicting the corrected flue gas waste heat based on the SFC optimization instruction to generate a flue gas waste heat prediction value, and generating a flue gas recovery instruction based on the flue gas waste heat prediction value.

9. The method for maintaining an internal combustion engine optimized based on SFC according to claim 8, characterized in that, The SFC optimization instruction includes: The SFC optimization instruction is a combination of multiple types of optimization instructions; Among them, the multiple types of optimization instructions include: the first type of optimization instruction, the second type of optimization instruction, and the third type of optimization instruction; The first type of optimization instruction is a fuel supply parameter correction instruction; The second type of optimization instruction is a load distribution instruction; The third type of optimization instruction is an intake control instruction.

10. The method for maintaining an internal combustion engine optimized based on SFC according to claim 9, characterized in that, When generating the flue gas recovery instruction, it includes: Generating a flue gas prediction temperature reference value in combination with the currently obtained flue gas temperature data and the SFC optimization instruction; Comparing the flue gas prediction temperature reference value and the flue gas temperature preset value to generate multiple flue gas recovery instructions.

Images