Model training and oil injection rate molded line prediction method and device, equipment and medium

Abstract

The invention discloses a model training and oil injection rate molded line prediction method, device, equipment and medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: measuring a standard oil injection rate molded line of a target diesel engine oil injection system under a sample oil injection working condition; determining equation parameters included in the molded line equation, assigning the equation parameters to obtain candidate equation parameter values, and generating candidate fuel injection rate molded lines according to the candidate equation parameter values; determining an oil injection rate error value according to the candidate oil injection rate molded line and the standard oil injection rate molded line, and obtaining an equation optimization parameter value as a sample equation parameter value according to the oil injection rate error value; and performing model training according to the sample oil injection working conditions and the sample equation parameter values to generate an equation parameter prediction model. According to the method, it can be guaranteed that the oil injection rate molded line corresponding to the oil injection working condition data is generated, it is guaranteed that the oil injection rate molded line can conform to the actual oil injection condition of the diesel engine oil injection system, and the prediction precision of numerical simulation is further guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, equipment and medium for model training and prediction of injection rate profile. Background Art

[0002] Traditional diesel engines will continue to be the main power source in many fields such as transportation, agriculture, and national defense for a long time in the future due to their high thermal efficiency and reliable performance. However, diesel engines are currently facing the dual pressure of further improving thermal efficiency and reducing emissions, and need to carry out coordinated optimization of combustion chamber structure, intake system, injection parameters, and many other aspects. Numerical simulation has the advantages of reliability, convenience, and flexibility. It has become the main means of current product design and forward research and development to carry out joint optimization of all parameters of multiple systems of diesel engines.

[0003] Since the high-pressure injection process of the diesel engine fuel injection system is crucial to the spray atomization and fuel-air mixing quality, which is closely related to the injection rate and injection profile, how to accurately simulate the injection rate profile of the diesel engine fuel injection system in numerical simulation is very critical to accurately reproduce the fuel-air mixing and combustion process in the diesel engine cylinder.

[0004] At present, the injection rate profile in numerical simulation is mostly simplified to a simple shape of square wave or trapezoidal wave, that is, the injection rate profile is set to a fixed shape. However, in actual situations, the injection rate of the diesel engine injection system will change with different injection conditions. It can be seen that the currently predicted injection rate profile does not match the actual injection situation of the diesel engine injection system in the cylinder, which affects the prediction accuracy of the numerical simulation. Summary of the invention

[0005] The present invention provides a method, device, equipment and medium for model training and prediction of injection rate profile, so as to solve the problem that the prediction accuracy of numerical simulation is affected by the discrepancy between the predicted injection rate profile and the actual injection situation in the current diesel engine injection system.

[0006] According to one aspect of the present invention, a model training method is provided, comprising:

[0007] Measure the standard injection rate profile corresponding to the target diesel engine injection system under the sample injection condition;

[0008] Determine equation parameters included in the profile equation corresponding to the injection rate profile, assign values ​​to the equation parameters to obtain at least one candidate equation parameter value, and generate at least one candidate injection rate profile according to the candidate equation parameter value;

[0009] Determine at least one injection rate error value according to each of the candidate injection rate profiles and the standard injection rate profile, and optimize the candidate equation parameter values ​​according to the injection rate error value to obtain an equation optimization parameter value as a sample equation parameter value;

[0010] Model training is performed based on the sample injection conditions and the sample equation parameter values ​​to generate an equation parameter prediction model; wherein the equation parameter prediction model is used to predict actual equation parameter values ​​corresponding to actual injection conditions, and the actual equation parameter values ​​are used to generate an actual injection rate profile.

[0011] According to another aspect of the present invention, there is provided a method for predicting an injection rate profile, comprising:

[0012] Acquire the actual fuel injection condition of the target diesel engine fuel injection system, and input the actual fuel injection condition into the equation parameter prediction model to obtain the actual equation parameter value corresponding to the actual fuel injection condition; wherein the equation parameter prediction model is trained using the model training method described in any of the preceding items;

[0013] An actual profile equation is determined according to the actual equation parameter value, and an actual injection rate profile of the target diesel engine injection system is generated according to the actual profile equation.

[0014] According to another aspect of the present invention, there is provided a model training device, comprising:

[0015] The injection rate profile measurement module is used to measure the standard injection rate profile corresponding to the target diesel engine injection system under the sample injection condition;

[0016] a candidate injection rate profile generating module, configured to determine equation parameters included in a profile equation corresponding to the injection rate profile, assign values ​​to the equation parameters to obtain at least one candidate equation parameter value, and generate at least one candidate injection rate profile according to the candidate equation parameter value;

[0017] a sample equation parameter value determination module, configured to determine at least one injection rate error value according to each of the candidate injection rate profiles and the standard injection rate profile, and to optimize the candidate equation parameter values ​​according to the injection rate error value to obtain an equation optimization parameter value as a sample equation parameter value;

[0018] A model training module is used to perform model training based on the sample injection conditions and the sample equation parameter values ​​to generate an equation parameter prediction model; wherein the equation parameter prediction model is used to predict the actual equation parameter values ​​corresponding to the actual injection conditions, and the actual equation parameter values ​​are used to generate an actual injection rate profile.

[0019] According to another aspect of the present invention, there is provided a device for predicting an injection rate profile, comprising:

[0020] An equation parameter prediction module, used for obtaining the actual fuel injection condition of the target diesel engine fuel injection system, and inputting the actual fuel injection condition into the equation parameter prediction model to obtain the actual equation parameter value corresponding to the actual fuel injection condition; wherein the equation parameter prediction model is trained by the model training method as described in any of the preceding items;

[0021] The injection rate profile generation module is used to determine the actual profile equation according to the actual equation parameter value, and generate the actual injection rate profile of the target diesel engine injection system according to the actual profile equation.

[0022] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0023] at least one processor; and

[0024] a memory communicatively connected to the at least one processor; wherein,

[0025] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the model training method and / or the injection rate profile prediction method described in any one of the present invention.

[0026] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the model training method and / or injection rate profile prediction method described in any one of the present invention when executed by a processor.

[0027] The present invention measures the standard injection rate profile corresponding to the target diesel engine injection system under the sample injection condition; determines the equation parameters included in the profile equation corresponding to the injection rate profile, assigns the equation parameters to obtain at least one candidate equation parameter value, and generates at least one candidate injection rate profile according to the candidate equation parameter value; determines at least one injection rate error value according to each candidate injection rate profile and the standard injection rate profile, and optimizes the candidate equation parameter values ​​according to the injection rate error value to obtain the equation optimization parameter value as the sample equation parameter value; performs model training according to the sample injection condition and the sample equation parameter value. The equation parameter prediction model is trained to generate an equation parameter prediction model; wherein the equation parameter prediction model is used to predict the actual equation parameter values ​​corresponding to the actual injection condition, and the actual equation parameter values ​​are used to generate the actual injection rate profile. Since the equation parameter prediction model is trained based on sample injection conditions and sample equation parameter values, the equation parameter prediction model has the ability to predict the corresponding equation parameter values ​​based on different injection condition data, so that the injection rate profile corresponding to the injection condition data can be generated based on the equation parameter values, ensuring that the injection rate profile is consistent with the actual injection condition of the diesel engine injection system, further ensuring the prediction accuracy of the numerical simulation.

[0028] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of 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.

[0030] Figure 1 A flowchart of a model training method provided in Embodiment 1 of the present invention;

[0031] Figure 2 A flowchart of a model training method provided in Embodiment 2 of the present invention;

[0032] Figure 3 A flowchart of a method for predicting a fuel injection rate profile provided in Embodiment 3 of the present invention;

[0033] Figure 4 A schematic diagram of the structure of a model training device provided in Embodiment 4 of the present invention;

[0034] Figure 5A schematic diagram of the structure of a device for predicting a fuel injection rate profile provided in a fifth embodiment of the present invention;

[0035] Figure 6 A schematic diagram of the structure of an electronic device that can be used to implement an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0036] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0037] It should be noted that the terms "standard", "candidate", "sample", "actual", "first", "second", "third", "fourth", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0038] Embodiment 1

[0039] Figure 1 This is a flow chart of a model training method provided in the first embodiment of the present invention. This embodiment can be applied to training an equation parameter prediction model for predicting the actual equation parameter value corresponding to the actual injection condition, and the actual equation parameter value is used to generate the actual injection rate profile. The method can be executed by a model training device, which can be implemented in the form of hardware and / or software, such as a server. Figure 1 As shown, the method includes:

[0040] S101. Measure a standard injection rate profile corresponding to a target diesel engine injection system under a sample injection condition.

[0041] Among them, the target diesel engine injection system refers to a diesel engine injection system with the need for injection rate profile prediction, that is, the in-cylinder direct injection fuel injection system of the diesel engine that needs to be numerically simulated. The injection condition refers to the operating data generated by the nozzle of the diesel engine injection system under different injection conditions, such as different injection pressure values, injection duration values, etc. The sample injection condition refers to the injection condition obtained by collecting data when the target diesel engine injection system is running in the actual injection condition, and using it for model training.

[0042] The injection rate profile refers to the profile that reflects the changing relationship between the "injection rate" and "injection time" of the target diesel engine injection system. For example, if the "injection time" is used as the horizontal axis and the "injection rate" is used as the vertical axis, as the "injection time" progresses, different "injection rates" will be generated according to different injection qualities and injection pressures. It can be understood that since the sample injection condition is the actual injection condition of the target diesel engine injection system, the standard injection rate profile represents the injection rate profile generated by the target diesel engine injection system under the actual injection condition.

[0043] In one embodiment, a server used for model training (hereinafter referred to as the first server) determines an injection pressure value interval and an injection duration value interval corresponding to a target diesel engine injection system, wherein the injection pressure value interval refers to a range of injection pressure values ​​that may be adopted by the nozzle of the target diesel engine injection system during the injection process, that is, the injection pressure value interval is obtained based on the minimum injection pressure value as the lower limit and the maximum injection pressure value as the upper limit; correspondingly, the injection duration value interval refers to a range of injection duration values ​​that may be adopted by the nozzle of the target diesel engine injection system during the injection process, that is, the injection duration value interval is obtained based on the shortest injection duration value as the lower limit and the longest injection duration value as the upper limit.

[0044] The first server obtains an injection pressure value from an injection pressure value interval as a sample injection pressure value, and obtains an injection duration value from an injection duration value interval as a sample injection duration value, and further determines a sample injection condition according to the sample injection pressure value and the sample injection duration value. The first server uses a test device to measure the injection rate profiles corresponding to the target diesel engine injection system under different sample injection conditions, respectively, as standard injection rate profiles, that is, to measure the injection rate profiles corresponding to the target diesel engine injection system under different injection pressure values ​​and / or injection duration values, respectively, as standard injection rate profiles.

[0045] S102, determining equation parameters included in the profile equation corresponding to the injection rate profile, assigning values ​​to the equation parameters to obtain at least one candidate equation parameter value, and generating at least one candidate injection rate profile according to the candidate equation parameter value.

[0046] The profile equation corresponding to the injection rate profile refers to the equation expression obtained by converting the injection rate profile into an equation, and the equation parameter refers to at least one undetermined coefficient in the profile equation. It can be understood that as long as a set of determined equation parameter values ​​are given, a determined profile equation can be obtained, and further, the corresponding injection rate profile can be generated. For example, assuming that the profile equation corresponding to the injection rate profile is at 3 +bt 2 +c, then as long as a set of definite equation parameter values ​​of equation parameters a, b and c are given, a definite type line equation can be obtained.

[0047] The candidate equation parameter value refers to at least one equation parameter value obtained after different values ​​are assigned to the equation parameter. For example, after 50,000 different values ​​are assigned to the equation parameter randomly, 50,000 candidate equation parameter values ​​are obtained. Accordingly, according to different given candidate equation parameter values, different forms of profile equations can be obtained, and further profile simulation can obtain different injection rate profiles as candidate injection rate profiles.

[0048] S103, determining at least one injection rate error value according to each candidate injection rate profile and the standard injection rate profile, and optimizing among candidate equation parameter values ​​according to the injection rate error value to obtain equation optimization parameter values ​​as sample equation parameter values.

[0049] Among them, since the standard injection rate profile is directly measured by the test equipment, the specific expression of the profile equation corresponding to the standard injection rate profile is unknown, that is, the equation parameter values ​​of each equation parameter in the profile equation corresponding to the standard injection rate profile are unknown and cannot be directly used for model training.

[0050] Therefore, it is necessary to use the injection rate error value between the candidate injection rate profile of each known form and the standard injection rate profile to indirectly determine the candidate equation parameter values ​​that are close to the equation parameter values ​​of each equation parameter in the profile equation corresponding to the standard injection rate profile as sample equation parameter values ​​for model training.

[0051] In one embodiment, the first server determines the candidate injection rates corresponding to each injection moment according to each candidate injection rate profile, and determines the standard injection rate corresponding to each injection moment according to the standard injection rate profile, and then sums the differences between each candidate injection rate and the standard injection rate at the same injection moment to determine at least one injection rate error value between each candidate injection rate profile and the standard injection rate profile. Further, at least one injection rate error value is used as an optimization target, and an optimization algorithm is used to optimize the candidate equation parameter values, and then the candidate equation parameter value corresponding to the candidate injection rate profile with the smallest injection rate error value is used as the equation optimization parameter value, and the equation optimization parameter value is further used as the sample equation parameter value for model training. Among them, the optimization algorithm includes but is not limited to genetic algorithm, particle swarm optimization algorithm, gray wolf algorithm, artificial bee colony algorithm, ant colony optimization algorithm, etc.

[0052] S104: Perform model training according to sample injection conditions and sample equation parameter values ​​to generate an equation parameter prediction model.

[0053] The equation parameter prediction model is used to predict the actual equation parameter values ​​corresponding to the actual injection condition, and the actual equation parameter values ​​are used to generate the actual injection rate profile.

[0054] In one embodiment, the first server uses sample injection conditions and sample equation parameter values ​​as sample data sets, and uses 70% of the sample data in the sample data sets as training sets, 15% of the sample data in the sample data sets as validation sets, and 15% of the sample data in the sample data sets as test sets, and uses the prediction error of the model to be trained for the test set as a model reliability evaluation criterion.

[0055] The training set is used to train the model to be trained. If the prediction error of the test set is less than 15%, the prediction accuracy of the model to be trained is considered to be high, and the model to be trained can be used as an equation parameter prediction model to predict the actual equation parameter values ​​corresponding to the actual injection condition. If the prediction error of the test set exceeds 15%, the corresponding area of ​​the sample injection condition with poor prediction is analyzed, and a new sample data set is added in this area to supplement the sample size.

[0056] The embodiment of the present invention measures the standard injection rate profile corresponding to the target diesel engine injection system under the sample injection condition; determines the equation parameters included in the profile equation corresponding to the injection rate profile, assigns the equation parameters to obtain at least one candidate equation parameter value, and generates at least one candidate injection rate profile according to the candidate equation parameter value; determines at least one injection rate error value according to each candidate injection rate profile and the standard injection rate profile, and optimizes the candidate equation parameter values ​​according to the injection rate error value to obtain the equation optimization parameter value as the sample equation parameter value; and performs modeling according to the sample injection condition and the sample equation parameter value. Training is performed to generate an equation parameter prediction model; wherein the equation parameter prediction model is used to predict the actual equation parameter values ​​corresponding to the actual injection condition, and the actual equation parameter values ​​are used to generate the actual injection rate profile. Since the equation parameter prediction model is trained based on sample injection conditions and sample equation parameter values, the equation parameter prediction model has the ability to predict the corresponding equation parameter values ​​based on different injection condition data, so that the injection rate profile corresponding to the injection condition data can be generated based on the equation parameter values, thereby ensuring that the injection rate profile is consistent with the actual injection condition of the diesel engine injection system, further ensuring the prediction accuracy of the numerical simulation.

[0057] Embodiment 2

[0058] Figure 2 This is a flow chart of a model training method provided in the second embodiment of the present invention. This embodiment further expands and optimizes the above embodiment and can be combined with the above optional implementation modes. Figure 2 As shown, the method includes:

[0059] S201. Determine an injection pressure value interval corresponding to a target diesel engine injection system, and obtain at least one sample injection pressure value by sampling according to the injection pressure value interval; determine an injection duration value interval corresponding to a target diesel engine injection system, and obtain at least one sample injection duration value by sampling according to the injection duration value interval.

[0060] Among them, the injection pressure value range refers to the range of injection pressure values ​​that the nozzle of the target diesel engine injection system may adopt during the injection process, that is, the injection pressure value range is obtained based on the minimum injection pressure value as the lower limit and the maximum injection pressure value as the upper limit. The injection duration value range refers to the range of injection duration values ​​that the nozzle of the target diesel engine injection system may adopt during the injection process, that is, the injection duration value range is obtained based on the shortest injection duration value as the lower limit and the longest injection duration value as the upper limit.

[0061] In one embodiment, the first server uses the Bernoulli equation to estimate the range of injection pressure values ​​during the operation of the nozzle of the target diesel engine injection system as the injection pressure value interval, and then samples in the injection pressure value interval to obtain at least one sample injection pressure value. Further, the first server estimates the range of injection duration values ​​during the operation of the nozzle of the target diesel engine injection system according to the attribute information of the nozzle of the target diesel engine injection system as the injection duration value interval, and then samples in the injection duration value interval to obtain at least one sample injection duration value.

[0062] Optionally, determining a fuel injection duration value interval corresponding to a target diesel engine fuel injection system includes:

[0063] The nozzle number information, nozzle diameter information and single-cycle injection quality information corresponding to the nozzle of the target diesel engine injection system are obtained; based on the nozzle number information, nozzle diameter information and single-cycle injection quality information, the injection duration value interval corresponding to the target diesel engine injection system is determined.

[0064] In one embodiment, the first server obtains the nozzle number information, nozzle diameter information and single-cycle injection quality information corresponding to the nozzle of the target diesel engine injection system, and further estimates the injection duration value range of the nozzle of the target diesel engine injection system during actual operation based on the nozzle number information, nozzle diameter information and single-cycle injection quality information, as the injection duration value interval.

[0065] By obtaining the nozzle number information, nozzle diameter information and single-cycle injection quality information corresponding to the nozzle of the target diesel engine injection system; determining the injection duration value range corresponding to the target diesel engine injection system according to the nozzle number information, nozzle diameter information and single-cycle injection quality information, the effect of estimating the injection duration value range is achieved, which does not rely on any other test equipment and has low cost and high efficiency.

[0066] Optionally, sampling is performed according to the injection pressure value interval to obtain at least one sample injection pressure value, including:

[0067] Sampling is performed in the injection pressure value interval according to a first data sampling interval, and at least one injection pressure value obtained by sampling is used as a sample injection pressure value.

[0068] The first data sampling interval may be set and adjusted according to actual experience.

[0069] In one embodiment, the first server takes the lower limit of the injection pressure value interval as the starting point, and samples data in the injection pressure value interval in sequence according to the first data sampling interval until the upper limit of the injection pressure value interval is reached, and obtains at least one injection pressure value as a sample injection pressure value.

[0070] By sampling in the injection pressure value range according to the first data sampling interval, and using at least one injection pressure value obtained by sampling as a sample injection pressure value, on the one hand, the effect of sample injection pressure value collection is achieved, laying a data foundation for subsequent solutions, and on the other hand, the sample injection pressure value is obtained by sampling at the first data sampling interval, which simplifies the data volume of the sample injection pressure value and avoids using all injection pressure values ​​in the injection pressure value range as sample injection pressure values, which easily causes the problem of data volume explosion.

[0071] Optionally, sampling is performed according to the injection duration value interval to obtain at least one sample injection duration value, including:

[0072] Sampling is performed in the injection duration value interval according to the second data sampling interval, and at least one injection duration value obtained by sampling is used as a sample injection duration value.

[0073] The second data sampling interval may be set and adjusted according to actual experience.

[0074] In one embodiment, the first server takes the lower limit of the injection duration value interval as the starting point, and samples data in the injection duration value interval in sequence according to the second data sampling interval until the upper limit of the injection duration value interval is reached, and obtains at least one injection duration value as a sample injection duration value.

[0075] By sampling in the injection duration value interval according to the second data sampling interval, and using at least one injection duration value obtained by sampling as a sample injection duration value, on the one hand, the effect of injection duration value collection is achieved, laying a data foundation for subsequent solutions, and on the other hand, the sample injection duration value is obtained by sampling at the second data sampling interval, which simplifies the data volume of the sample injection duration value and avoids using all injection duration values ​​in the injection duration value interval as sample injection duration values, which easily causes the problem of data volume explosion.

[0076] S202: Determine a sample fuel injection condition according to a combination result between a sample fuel injection pressure value and a sample fuel injection duration value.

[0077] In one implementation, each sample injection pressure value and each sample injection duration value are cross-combined, and at least one sample injection condition is determined according to the cross-combination result.

[0078] By determining the injection pressure value interval corresponding to the target diesel engine injection system, and sampling according to the injection pressure value interval to obtain at least one sample injection pressure value; determining the injection duration value interval corresponding to the target diesel engine injection system, and sampling according to the injection duration value interval to obtain at least one sample injection duration value; determining the sample injection condition according to the combination result between the sample injection pressure value and the sample injection duration value, thereby realizing the use of the two types of data, the sample injection pressure value and the sample injection duration value, as the sample injection condition, enriching the data dimension of the sample injection condition, and further ensuring the degree of consistency between the injection rate profile and the actual injection condition of the target diesel engine injection system.

[0079] S203, measuring a standard injection rate profile corresponding to a target diesel engine injection system under a sample injection condition.

[0080] S204, determining equation parameters included in the profile equation corresponding to the injection rate profile, assigning values ​​to the equation parameters to obtain at least one candidate equation parameter value, and generating at least one candidate injection rate profile according to the candidate equation parameter value.

[0081] Optionally, the equation parameters included in the profile equation for determining the injection rate profile include:

[0082] A1. Determine a first profile equation corresponding to a first profile interval in the injection rate profile, and determine first equation parameters included in the first profile equation.

[0083] Among them, the first profile interval represents a section of the injection rate profile, the first profile interval is the profile between the starting point and the first target point in the injection rate profile, and the first target point is the corresponding tangent point when the tangent slope of the injection rate profile is the first slope.

[0084] B1. Determine a second profile equation corresponding to a second profile interval in the injection rate profile, and determine second equation parameters included in the second profile equation.

[0085] Among them, the second profile interval represents a section of the injection rate profile, the second profile interval is the profile between the first target point and the second target point in the injection rate profile, and the second target point is the corresponding tangent point when the tangent slope of the injection rate profile is the second slope.

[0086] C1. Determine the third profile equation corresponding to the third profile interval in the injection rate profile, and determine the third equation parameters included in the third profile equation.

[0087] Among them, the third profile interval represents a section of the injection rate profile, the third profile interval is the profile between the second target point and the third target point in the injection rate profile, and the third target point is the corresponding tangent point when the tangent slope of the injection rate profile is the third slope.

[0088] D1. Determine a fourth profile equation corresponding to a fourth profile interval in the injection rate profile, and determine fourth equation parameters included in the fourth profile equation.

[0089] The fourth profile section represents a section of the injection rate profile, and the fourth profile section is a profile between the end point and the third target point in the injection rate profile.

[0090] The first slope is greater than the second slope, and the second slope is greater than the third slope. It can be understood that, since the first slope of the first target point is greater than the second slope of the second target point, it means that the first profile interval between the starting point and the first target point is steeper than the second profile interval between the first target point and the second target point; correspondingly, since the second slope of the second target point is greater than the third slope of the third target point, it means that the second profile interval between the first target point and the second target point is steeper than the third profile interval between the second target point and the third target point. The fourth profile interval between the end point and the third target point is opposite to the trend of the first profile interval, the second profile interval and the third profile interval, that is, the trend of the first profile interval, the second profile interval and the third profile interval is an increasing trend, while the fourth profile interval is a decreasing trend.

[0091] By determining the first profile equation corresponding to the first profile interval in the injection rate profile, and determining the first equation parameter included in the first profile equation; determining the second profile equation corresponding to the second profile interval in the injection rate profile, and determining the second equation parameter included in the second profile equation; determining the third profile equation corresponding to the third profile interval in the injection rate profile, and determining the third equation parameter included in the third profile equation; determining the fourth profile equation corresponding to the fourth profile interval in the injection rate profile, and determining the fourth equation parameter included in the fourth profile equation; the first slope is greater than the second slope, and the second slope is greater than the third slope, thereby achieving the effect of dividing the injection rate profile into four profile intervals, respectively determining the profile equations and equation parameters, and ensuring the accuracy and rationality of the equation parameter determination.

[0092] Optionally, the first profile equation is a cubic equation: p1(t)=a1t 3 +b1t 2 +c1;

[0093] Among them, p1(t) is the first profile equation, a1, b1 and c1 are the first equation parameters, and t is the injection time.

[0094] The second type of line equation is a quadratic equation: p2(t) = a2t 2 +b2t+c2;

[0095] Among them, p2(t) is the second profile equation, a2, b2 and c2 are the parameters of the second equation, and t is the injection time.

[0096] The equation of the third type line is a quadratic equation: p3(t) = a3t 2 +b3t+c3;

[0097] Among them, p3(t) is the third profile equation, a3, b3 and c3 are the third equation parameters, and t is the injection time.

[0098] Optionally, the injection rate at each injection time in the third profile interval is considered to be the same, that is, the third profile interval can be regarded as a straight line segment. In this case, the injection rate at the initial moment in the third profile interval is the same as the injection rate at the end moment of the second profile interval. In this case, the third profile equation is a fixed value p3: p3 = p2(t2) = a2t2 2 +b2t2+c2; where t2 is the end time of the second profile interval.

[0099] The fourth type of line equation is a cubic equation: p4(t) = a4t 3 +b4t 2 +c4t+d4;

[0100] Among them, p4(t) is the fourth profile equation, a4, b4, c4 and d4 are the parameters of the fourth equation, and t is the injection time.

[0101] Optionally, assigning equation parameters to obtain at least one candidate equation parameter value, and generating at least one candidate injection rate profile according to the candidate equation parameter value, includes:

[0102] A2. Assign values ​​to the first equation parameter, the second equation parameter, the third equation parameter and the fourth equation parameter respectively, and obtain at least one first candidate equation parameter value, at least one second candidate equation parameter value, at least one third candidate equation parameter value and at least one fourth candidate equation parameter value respectively.

[0103] Specifically, the first equation parameter is assigned a value to obtain at least one first candidate equation parameter value; the second equation parameter is assigned a value to obtain at least one second candidate equation parameter value; the third equation parameter is assigned a value to obtain at least one third candidate equation parameter value; the fourth equation parameter is assigned a value to obtain at least one fourth candidate equation parameter value.

[0104] B2. Generate at least one candidate injection rate profile line according to the first candidate equation parameter value, the second candidate equation parameter value, the third candidate equation parameter value and the fourth candidate equation parameter value.

[0105] In one embodiment, at least one first candidate profile interval is generated according to the first candidate equation parameter value, at least one second candidate profile interval is generated according to the second candidate equation parameter value, at least one third candidate profile interval is generated according to the third candidate equation parameter value, at least one fourth candidate profile interval is generated according to the fourth candidate equation parameter value, and at least one candidate injection rate profile is generated according to the first candidate profile interval, the second candidate profile interval, the third candidate profile interval and the fourth candidate profile interval.

[0106] By assigning values ​​to the first equation parameter, the second equation parameter, the third equation parameter and the fourth equation parameter respectively, at least one first candidate equation parameter value, at least one second candidate equation parameter value, at least one third candidate equation parameter value and at least one fourth candidate equation parameter value are obtained respectively; at least one candidate injection rate profile line is generated according to the first candidate equation parameter value, the second candidate equation parameter value, the third candidate equation parameter value and the fourth candidate equation parameter value. Since the candidate equation parameter values ​​are calculated for the four profile intervals of the entire candidate injection rate profile line respectively, the difficulty of calculating the candidate equation parameter values ​​is reduced, and the accuracy and rationality of the generation of the candidate injection rate profile line are further guaranteed.

[0107] S205. Determine at least one injection rate error value according to each candidate injection rate profile and the standard injection rate profile, and optimize the candidate equation parameter values ​​according to the injection rate error value to obtain the equation optimization parameter value as the sample equation parameter value.

[0108] Optionally, determining at least one injection rate error value according to each candidate injection rate profile and the standard injection rate profile includes:

[0109] A3. Determine a first injection rate error value according to the first candidate profile interval and the first standard profile interval.

[0110] The first candidate profile section is the first profile section corresponding to any candidate injection rate profile, and the first standard profile section is the first profile section corresponding to the standard injection rate profile.

[0111] In one embodiment, the first server determines the candidate injection rates corresponding to each injection moment in the first candidate profile interval, and determines the standard injection rate corresponding to each injection moment in the first standard profile interval, and then sums the differences between each candidate injection rate and the standard injection rate at the same injection moment to determine at least one first injection rate error value between the first candidate profile interval and the first standard profile interval.

[0112] B3. Determine a second injection rate error value based on the second candidate profile interval and the second standard profile interval.

[0113] The second candidate profile section is the second profile section corresponding to any candidate injection rate profile, and the second standard profile section is the second profile section corresponding to the standard injection rate profile.

[0114] In one embodiment, the first server determines the candidate injection rates corresponding to each injection moment in the second candidate profile interval, and determines the standard injection rate corresponding to each injection moment in the second standard profile interval, and then sums the differences between each candidate injection rate and the standard injection rate at the same injection moment to determine at least one second injection rate error value between the second candidate profile interval and the second standard profile interval.

[0115] C3. Determine a third injection rate error value according to the third candidate profile section and the third standard profile section.

[0116] The third candidate profile section is the third profile section corresponding to any candidate injection rate profile, and the third standard profile section is the third profile section corresponding to the standard injection rate profile.

[0117] In one embodiment, the first server determines the candidate injection rates corresponding to each injection moment in the third candidate profile line interval, and determines the standard injection rate corresponding to each injection moment in the third standard profile line interval, and then sums the differences between each candidate injection rate and the standard injection rate in the same injection moment to determine at least one third injection rate error value between the third candidate profile line interval and the third standard profile line interval.

[0118] D3. Determine a fourth injection rate error value according to a fourth candidate profile interval and a fourth standard profile interval.

[0119] The fourth candidate profile section is a fourth profile section corresponding to any candidate injection rate profile, and the fourth standard profile section is a fourth profile section corresponding to the standard injection rate profile.

[0120] In one embodiment, the first server determines the candidate injection rates corresponding to each injection moment in the fourth candidate line interval, and determines the standard injection rate corresponding to each injection moment in the fourth standard line interval, and then sums the differences between each candidate injection rate and the standard injection rate in the same injection moment to determine at least one fourth injection rate error value between the fourth candidate line interval and the fourth standard line interval.

[0121] Optionally, optimizing among candidate equation parameter values ​​according to the injection rate error value includes:

[0122] The first injection rate error value, the second injection rate error value, the third injection rate error value and the fourth injection rate error value are all taken as optimization targets, and an optimization algorithm is used to optimize among candidate equation parameter values.

[0123] In one embodiment, the first server takes at least one first injection rate error value, at least one second injection rate error value, at least one third injection rate error value and at least one fourth injection rate error value as optimization targets, and uses an optimization algorithm to optimize among candidate equation parameter values, and then takes the candidate equation parameter values ​​corresponding to the candidate injection rate profile with the smallest first injection rate error value, second injection rate error value, third injection rate error value and fourth injection rate error value as equation optimization parameter values, and further uses the equation optimization parameter values ​​as sample equation parameter values ​​for model training.

[0124] By determining the first injection rate error value according to the first candidate line interval and the first standard line interval; determining the second injection rate error value according to the second candidate line interval and the second standard line interval; determining the third injection rate error value according to the third candidate line interval and the third standard line interval; determining the fourth injection rate error value according to the fourth candidate line interval and the fourth standard line interval, the first injection rate error value, the second injection rate error value, the third injection rate error value and the fourth injection rate error value are all used as optimization targets, and an optimization algorithm is used to perform optimization among the candidate equation parameter values. Since the first injection rate error value, the second injection rate error value, the third injection rate error value and the fourth injection rate error value are all used as optimization targets, compared with only taking the total injection rate error value as the optimization target, the accuracy of the equation optimization parameter values ​​finally determined is guaranteed, and the effect of model training is further guaranteed.

[0125] S206: Perform model training according to sample injection conditions and sample equation parameter values ​​to generate an equation parameter prediction model.

[0126] Embodiment 3

[0127] Figure 3 This is a flowchart of a method for predicting a fuel injection rate profile provided in the third embodiment of the present invention. This embodiment is applicable to the case where a trained equation parameter prediction model is used to predict a fuel injection rate profile. The method can be executed by a fuel injection rate profile prediction device, which can be implemented in the form of hardware and / or software, such as by a server. Figure 3 As shown, the method includes:

[0128] S301, obtaining the actual fuel injection condition of the target diesel engine fuel injection system, and inputting the actual fuel injection condition into the equation parameter prediction model to obtain the actual equation parameter value corresponding to the actual fuel injection condition.

[0129] The actual fuel injection condition refers to the fuel injection condition data generated by the fuel injector of the target diesel engine fuel injection system in actual operation, including the actual fuel injection pressure value and / or the actual fuel injection duration value. The equation parameter prediction model is trained using the model training method as in any of the previous items.

[0130] In one embodiment, a server for predicting the injection rate profile (hereinafter referred to as the second server) obtains the actual injection condition of the target diesel engine injection system, and inputs the actual injection condition into a deployed equation parameter prediction model, uses the equation parameter prediction model to predict the actual injection condition, and outputs the actual equation parameter value corresponding to the actual injection condition.

[0131] S302: determining an actual profile equation according to actual equation parameter values, and generating an actual injection rate profile of a target diesel engine injection system according to the actual profile equation.

[0132] In one embodiment, the second server constructs an actual profile equation according to the actual equation parameter values, and generates an actual injection rate profile of the target diesel engine injection system according to the actual profile equation using a preset drawing tool.

[0133] Since the equation parameter prediction model trained by the model training method as described above can predict the corresponding equation parameter values ​​according to different injection condition data, the embodiment of the present invention obtains the actual injection condition of the target diesel engine injection system and inputs the actual injection condition into the equation parameter prediction model to obtain the actual equation parameter value corresponding to the actual injection condition, determines the actual profile equation according to the actual equation parameter value, and generates the actual injection rate profile of the target diesel engine injection system according to the actual profile equation, so that the actual injection rate profile corresponding to the actual injection condition can be generated according to the actual equation parameter value, thereby ensuring that the actual injection rate profile can be consistent with the actual injection condition of the diesel engine injection system, and further ensuring the prediction accuracy of the numerical simulation.

[0134] Embodiment 4

[0135] Figure 4 This is a schematic diagram of the structure of a model training device provided in Embodiment 4 of the present invention. Figure 4 As shown, the device comprises:

[0136] The injection rate profile measurement module 41 is used to measure the standard injection rate profile corresponding to the target diesel engine injection system under the sample injection condition;

[0137] a candidate injection rate profile generating module 42, configured to determine equation parameters included in a profile equation corresponding to the injection rate profile, assign values ​​to the equation parameters to obtain at least one candidate equation parameter value, and generate at least one candidate injection rate profile according to the candidate equation parameter value;

[0138] a sample equation parameter value determination module 43, for determining at least one injection rate error value according to each of the candidate injection rate profiles and the standard injection rate profile, and performing optimization among the candidate equation parameter values ​​according to the injection rate error value to obtain an equation optimization parameter value as a sample equation parameter value;

[0139] The model training module 44 is used to perform model training according to the sample injection conditions and the sample equation parameter values ​​to generate an equation parameter prediction model; wherein the equation parameter prediction model is used to predict the actual equation parameter values ​​corresponding to the actual injection conditions, and the actual equation parameter values ​​are used to generate an actual injection rate profile.

[0140] Optionally, the device further includes a sample injection condition determination module, which is specifically used to:

[0141] Determining an injection pressure value interval corresponding to the target diesel engine injection system, and sampling according to the injection pressure value interval to obtain at least one sample injection pressure value;

[0142] Determining an injection duration value interval corresponding to the target diesel engine injection system, and sampling according to the injection duration value interval to obtain at least one sample injection duration value;

[0143] The sample injection condition is determined according to a combination result between the sample injection pressure value and the sample injection duration value.

[0144] Optionally, the sample injection condition determination module is further used to:

[0145] Obtaining information on the number of spray holes, spray hole diameter, and single-cycle fuel injection quality corresponding to the nozzle of the target diesel engine fuel injection system;

[0146] The injection duration value interval corresponding to the target diesel engine injection system is determined according to the spray hole number information, the spray hole diameter information and the single-cycle injection quality information.

[0147] Optionally, the sample injection condition determination module is further used to:

[0148] Sampling in the injection pressure value interval according to a first data sampling interval, and using at least one injection pressure value obtained by sampling as the sample injection pressure value;

[0149] The sample injection operating condition determination module is further specifically used for:

[0150] Sampling is performed in the injection duration value interval according to a second data sampling interval, and at least one injection duration value obtained by sampling is used as the sample injection duration value.

[0151] Optionally, the candidate injection rate profile generation module 42 is specifically used to:

[0152] Determine a first profile equation corresponding to a first profile interval in the injection rate profile, and determine a first equation parameter included in the first profile equation; wherein the first profile interval is a profile between a starting point and a first target point in the injection rate profile, and the first target point is a tangent point corresponding to when a tangent slope of the injection rate profile is a first slope;

[0153] Determine a second profile equation corresponding to a second profile interval in the injection rate profile, and determine a second equation parameter included in the second profile equation; wherein the second profile interval is a profile between the first target point and the second target point in the injection rate profile, and the second target point is a tangent point corresponding to when the tangent slope of the injection rate profile is a second slope;

[0154] Determine a third profile equation corresponding to a third profile interval in the injection rate profile, and determine a third equation parameter included in the third profile equation; wherein the third profile interval is a profile between the second target point and the third target point in the injection rate profile, and the third target point is a tangent point corresponding to when the tangent slope of the injection rate profile is the third slope;

[0155] Determine a fourth profile equation corresponding to a fourth profile interval in the injection rate profile, and determine fourth equation parameters included in the fourth profile equation; wherein the fourth profile interval is a profile between a termination point in the injection rate profile and the third target point;

[0156] The first slope is greater than the second slope, and the second slope is greater than the third slope.

[0157] Optionally, the first profile equation is: p1(t)=a1t 3 +b1t 2 +c1;

[0158] Wherein, p1(t) is the first profile equation, a1, b1 and c1 are the first equation parameters, and t is the injection time;

[0159] The second profile equation is: p2(t)=a2t 2 +b2t+c2;

[0160] Wherein, p2(t) is the second profile equation, a2, b2 and c2 are the parameters of the second equation, and t is the injection time;

[0161] The third profile equation is: p3(t)=a3t 2 +b3t+c3;

[0162] Wherein, p3(t) is the third profile equation, a3, b3 and c3 are the third equation parameters, and t is the injection time;

[0163] The fourth type line equation is: p4(t) = a4t 3 +b4t 2 +c4t+d4;

[0164] Among them, p4(t) is the fourth profile equation, a4, b4, c4 and d4 are the parameters of the fourth equation, and t is the injection time.

[0165] Optionally, the candidate injection rate profile generation module 42 is specifically used to:

[0166] Assigning values ​​to the first equation parameter, the second equation parameter, the third equation parameter and the fourth equation parameter respectively, and obtaining at least one first candidate equation parameter value, at least one second candidate equation parameter value, at least one third candidate equation parameter value and at least one fourth candidate equation parameter value respectively;

[0167] At least one candidate injection rate profile is generated according to the first candidate equation parameter value, the second candidate equation parameter value, the third candidate equation parameter value and the fourth candidate equation parameter value.

[0168] Optionally, the sample equation parameter value determination module 43 is specifically used to:

[0169] Determine a first injection rate error value according to a first candidate profile interval and a first standard profile interval; wherein the first candidate profile interval is the first profile interval corresponding to any of the candidate injection rate profiles, and the first standard profile interval is the first profile interval corresponding to the standard injection rate profile;

[0170] Determine a second injection rate error value according to a second candidate profile interval and a second standard profile interval; wherein the second candidate profile interval is the second profile interval corresponding to any of the candidate injection rate profiles, and the second standard profile interval is the second profile interval corresponding to the standard injection rate profile;

[0171] Determine a third injection rate error value according to a third candidate profile interval and a third standard profile interval; wherein the third candidate profile interval is the third profile interval corresponding to any of the candidate injection rate profiles, and the third standard profile interval is the third profile interval corresponding to the standard injection rate profile;

[0172] Determine a fourth injection rate error value according to a fourth candidate profile interval and a fourth standard profile interval; wherein the fourth candidate profile interval is the fourth profile interval corresponding to any of the candidate injection rate profiles, and the fourth standard profile interval is the fourth profile interval corresponding to the standard injection rate profile;

[0173] The sample equation parameter value determination module 43 is specifically used for:

[0174] The first injection rate error value, the second injection rate error value, the third injection rate error value and the fourth injection rate error value are all taken as optimization targets, and an optimization algorithm is used to optimize among the candidate equation parameter values.

[0175] The model training device provided in the embodiment of the present invention can execute the model training method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0176] Embodiment 5

[0177] Figure 5 This is a schematic diagram of the structure of a prediction device for an injection rate profile provided in Embodiment 5 of the present invention. Figure 5 As shown, the device comprises:

[0178] The equation parameter prediction module 51 is used to obtain the actual fuel injection condition of the target diesel engine fuel injection system, and input the actual fuel injection condition into the equation parameter prediction model to obtain the actual equation parameter value corresponding to the actual fuel injection condition; wherein the equation parameter prediction model is trained using the model training method described in any of the previous items;

[0179] The injection rate profile generating module 52 is used to determine the actual profile equation according to the actual equation parameter value, and to generate the actual injection rate profile of the target diesel engine injection system according to the actual profile equation.

[0180] The device for predicting the injection rate profile provided in the embodiment of the present invention can execute the method for predicting the injection rate profile provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0181] Embodiment 6

[0182] Figure 6A schematic diagram of the structure of an electronic device 60 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0183] like Figure 6 As shown, the electronic device 60 includes at least one processor 61, and a memory connected to the at least one processor 61, such as a read-only memory (ROM) 62, a random access memory (RAM) 63, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 61 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 62 or the computer program loaded from the storage unit 68 to the random access memory (RAM) 63. In the RAM 63, various programs and data required for the operation of the electronic device 60 can also be stored. The processor 61, the ROM 62, and the RAM 63 are connected to each other via a bus 64. An input / output (I / O) interface 65 is also connected to the bus 64.

[0184] A number of components in the electronic device 60 are connected to the I / O interface 65, including: an input unit 66, such as a keyboard, a mouse, etc.; an output unit 67, such as various types of displays, speakers, etc.; a storage unit 68, such as a disk, an optical disk, etc.; and a communication unit 69, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 69 allows the electronic device 60 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0185] The processor 61 may be a variety of general and / or dedicated processing components with processing and computing capabilities. Some examples of the processor 61 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 61 executes the various methods and processes described above, such as a model training method and / or a method for predicting an injection rate profile.

[0186] In some embodiments, the model training method and / or the method for predicting the injection rate profile may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 68. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 60 via the ROM 62 and / or the communication unit 69. When the computer program is loaded into the RAM 63 and executed by the processor 61, one or more steps of the model training method and / or the method for predicting the injection rate profile described above may be performed. Alternatively, in other embodiments, the processor 61 may be configured to execute the model training method and / or the method for predicting the injection rate profile by any other appropriate means (e.g., by means of firmware).

[0187] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0188] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0189] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0190] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0191] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0192] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0193] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0194] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A model training method, characterized in that: include: Measure the standard injection rate profile corresponding to the target diesel engine injection system under the sample injection condition; Determine equation parameters included in the profile equation corresponding to the injection rate profile, assign values ​​to the equation parameters to obtain at least one candidate equation parameter value, and generate at least one candidate injection rate profile according to the candidate equation parameter value; Determine at least one injection rate error value according to each of the candidate injection rate profiles and the standard injection rate profile, and optimize the candidate equation parameter values ​​according to the injection rate error value to obtain an equation optimization parameter value as a sample equation parameter value; Model training is performed based on the sample injection conditions and the sample equation parameter values ​​to generate an equation parameter prediction model; wherein the equation parameter prediction model is used to predict actual equation parameter values ​​corresponding to actual injection conditions, and the actual equation parameter values ​​are used to generate an actual injection rate profile.

2. The method according to claim 1, wherein the measuring target diesel engine fuel injection system is preceded by a standard fuel injection rate profile corresponding to a sample fuel injection condition, further comprising: Determining an injection pressure value interval corresponding to the target diesel engine injection system, and sampling according to the injection pressure value interval to obtain at least one sample injection pressure value; Determining an injection duration value interval corresponding to the target diesel engine injection system, and sampling according to the injection duration value interval to obtain at least one sample injection duration value; The sample injection condition is determined according to a combination result between the sample injection pressure value and the sample injection duration value.

3. The method according to claim 2, characterized in that The step of determining a fuel injection duration value interval corresponding to the target diesel engine fuel injection system includes: Obtaining information on the number of spray holes, spray hole diameter, and single-cycle fuel injection quality corresponding to the nozzle of the target diesel engine fuel injection system; The injection duration value interval corresponding to the target diesel engine injection system is determined according to the spray hole number information, the spray hole diameter information and the single-cycle injection quality information.

4. The method according to claim 2, characterized in that: The step of sampling according to the injection pressure value interval to obtain at least one sample injection pressure value includes: Sampling in the injection pressure value interval according to a first data sampling interval, and using at least one injection pressure value obtained by sampling as the sample injection pressure value; The step of sampling according to the injection duration value interval to obtain at least one sample injection duration value includes: Sampling is performed in the injection duration value interval according to a second data sampling interval, and at least one injection duration value obtained by sampling is used as the sample injection duration value.

5. The method according to claim 1, characterized in that The equation parameters of the profile equation corresponding to the injection rate profile include: Determine a first profile equation corresponding to a first profile interval in the injection rate profile, and determine a first equation parameter included in the first profile equation; wherein the first profile interval is a profile between a starting point and a first target point in the injection rate profile, and the first target point is a tangent point corresponding to when a tangent slope of the injection rate profile is a first slope; Determine a second profile equation corresponding to a second profile interval in the injection rate profile, and determine a second equation parameter included in the second profile equation; wherein the second profile interval is a profile between the first target point and the second target point in the injection rate profile, and the second target point is a tangent point corresponding to when the tangent slope of the injection rate profile is a second slope; Determine a third profile equation corresponding to a third profile interval in the injection rate profile, and determine a third equation parameter included in the third profile equation; wherein the third profile interval is a profile between the second target point and the third target point in the injection rate profile, and the third target point is a tangent point corresponding to when the tangent slope of the injection rate profile is the third slope; Determine a fourth profile equation corresponding to a fourth profile interval in the injection rate profile, and determine fourth equation parameters included in the fourth profile equation; wherein the fourth profile interval is a profile between a termination point in the injection rate profile and the third target point; The first slope is greater than the second slope, and the second slope is greater than the third slope.

6. The method according to claim 5, characterized in that The first type line equation is: p1(t)=a1t 3 +b1t 2 +c1 Wherein, p1(t) is the first profile equation, a1, b1 and c1 are the first equation parameters, and t is the injection time; The second type line equation is: <h2 style=";text-align:left;direction:ltr">p2(t) = a2t<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> +b2t+c2 Wherein, p2(t) is the second profile equation, a2, b2 and c2 are the parameters of the second equation, and t is the injection time; The third type line equation is: <h2 style=";text-align:left;direction:ltr">p3(t) = a3t<h2 style=";text-align:left;direction:ltr"> 2 <h2 style=";text-align:left;direction:ltr"> +b3t+c3 Wherein, p3(t) is the third profile equation, a3, b3 and c3 are the third equation parameters, and t is the injection time; The fourth type line equation is: p4(t)=a4t 3 +b4t 2 +c4t+d4 Among them, p4(t) is the fourth profile equation, a4, b4, c4 and d4 are the parameters of the fourth equation, and t is the injection time.

7. The method according to claim 5, characterized in that The step of assigning values ​​to the equation parameters to obtain at least one candidate equation parameter value, and generating at least one candidate injection rate profile line according to the candidate equation parameter value, comprises: Assigning values ​​to the first equation parameter, the second equation parameter, the third equation parameter and the fourth equation parameter respectively, and obtaining at least one first candidate equation parameter value, at least one second candidate equation parameter value, at least one third candidate equation parameter value and at least one fourth candidate equation parameter value respectively; At least one candidate injection rate profile is generated according to the first candidate equation parameter value, the second candidate equation parameter value, the third candidate equation parameter value and the fourth candidate equation parameter value.

8. The method according to claim 5, characterized in that The determining at least one injection rate error value according to each of the candidate injection rate profiles and the standard injection rate profile comprises: Determine a first injection rate error value according to a first candidate profile interval and a first standard profile interval; wherein the first candidate profile interval is the first profile interval corresponding to any of the candidate injection rate profiles, and the first standard profile interval is the first profile interval corresponding to the standard injection rate profile; Determine a second injection rate error value according to a second candidate profile interval and a second standard profile interval; wherein the second candidate profile interval is the second profile interval corresponding to any of the candidate injection rate profiles, and the second standard profile interval is the second profile interval corresponding to the standard injection rate profile; Determine a third injection rate error value according to a third candidate profile interval and a third standard profile interval; wherein the third candidate profile interval is the third profile interval corresponding to any of the candidate injection rate profiles, and the third standard profile interval is the third profile interval corresponding to the standard injection rate profile; Determine a fourth injection rate error value according to a fourth candidate profile interval and a fourth standard profile interval; wherein the fourth candidate profile interval is the fourth profile interval corresponding to any of the candidate injection rate profiles, and the fourth standard profile interval is the fourth profile interval corresponding to the standard injection rate profile; The optimizing among the candidate equation parameter values ​​according to the injection rate error value comprises: The first injection rate error value, the second injection rate error value, the third injection rate error value and the fourth injection rate error value are all taken as optimization targets, and an optimization algorithm is used to optimize among the candidate equation parameter values.

9. A method for predicting an injection rate profile, characterized in that: include: Acquire the actual fuel injection condition of the target diesel engine fuel injection system, and input the actual fuel injection condition into the equation parameter prediction model to obtain the actual equation parameter value corresponding to the actual fuel injection condition; wherein the equation parameter prediction model is trained by the model training method according to any one of claims 1 to 8; An actual profile equation is determined according to the actual equation parameter value, and an actual injection rate profile of the target diesel engine injection system is generated according to the actual profile equation.

10. A model training device, characterized in that: include: The injection rate profile measurement module is used to measure the standard injection rate profile corresponding to the target diesel engine injection system under the sample injection condition; a candidate injection rate profile generating module, configured to determine equation parameters included in a profile equation corresponding to the injection rate profile, assign values ​​to the equation parameters to obtain at least one candidate equation parameter value, and generate at least one candidate injection rate profile according to the candidate equation parameter value; a sample equation parameter value determination module, configured to determine at least one injection rate error value according to each of the candidate injection rate profiles and the standard injection rate profile, and to optimize the candidate equation parameter values ​​according to the injection rate error value to obtain an equation optimization parameter value as a sample equation parameter value; A model training module is used to perform model training based on the sample injection conditions and the sample equation parameter values ​​to generate an equation parameter prediction model; wherein the equation parameter prediction model is used to predict the actual equation parameter values ​​corresponding to the actual injection conditions, and the actual equation parameter values ​​are used to generate an actual injection rate profile.

11. The device according to claim 10, further comprising a sample injection condition determination module, specifically configured to: Determining an injection pressure value interval corresponding to the target diesel engine injection system, and sampling according to the injection pressure value interval to obtain at least one sample injection pressure value; Determining an injection duration value interval corresponding to the target diesel engine injection system, and sampling according to the injection duration value interval to obtain at least one sample injection duration value; The sample injection condition is determined according to a combination result between the sample injection pressure value and the sample injection duration value.

12. The device according to claim 11, characterized in that The sample injection operating condition determination module is further specifically used for: Obtaining information on the number of spray holes, spray hole diameter, and single-cycle fuel injection quality corresponding to the nozzle of the target diesel engine fuel injection system; The injection duration value interval corresponding to the target diesel engine injection system is determined according to the spray hole number information, the spray hole diameter information and the single-cycle injection quality information.

13. The device according to claim 11, characterized in that The sample injection operating condition determination module is further specifically used for: Sampling in the injection pressure value interval according to a first data sampling interval, and using at least one injection pressure value obtained by sampling as the sample injection pressure value; The sample injection operating condition determination module is further specifically used for: Sampling is performed in the injection duration value interval according to a second data sampling interval, and at least one injection duration value obtained by sampling is used as the sample injection duration value.

14. A device for predicting a fuel injection rate profile, characterized in that: include: An equation parameter prediction module, used for obtaining the actual injection condition of the target diesel engine injection system, and inputting the actual injection condition into the equation parameter prediction model to obtain the actual equation parameter value corresponding to the actual injection condition; wherein the equation parameter prediction model is trained by the model training method according to any one of claims 1 to 8; The injection rate profile generation module is used to determine the actual profile equation according to the actual equation parameter value, and generate the actual injection rate profile of the target diesel engine injection system according to the actual profile equation.

15. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the model training method described in any one of claims 1 to 8, and / or implement the method for predicting the injection rate profile described in claim 9.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to execute the model training method described in any one of claims 1 to 8, and / or to implement the method for predicting the injection rate profile described in claim 9.

Images