Natural gas engine air-fuel ratio control method and system

Abstract

The invention relates to the technical field of air-fuel ratio control, and discloses a natural gas engine air-fuel ratio control method and system.The method comprises the steps that an air-fuel ratio measured value, an error value and an error change value are obtained through calculation based on an input signal; system dynamic feature extraction of an engine system is conducted on the input signal, and the air-fuel ratio is pre-judged; and an air-fuel ratio compensation objective function is constructed, optimization solution is carried out, and air-fuel ratio control is carried out based on the air-fuel ratio compensation coefficient. According to the method, a target function is constructed by taking the response speed of an engine and the time for achieving the stability of the air-fuel ratio as minimum air-fuel ratio compensation performance of an engine system, and an error value and an error change value of an air-fuel ratio measured value are converted based on an air-fuel ratio compensation coefficient obtained through solving; and the engine air quality and fuel quality of air-fuel ratio compensation control are obtained, so that the air-fuel ratio of the natural gas engine rapidly reaches the adjacent range of the target air-fuel ratio, and engine air-fuel ratio control is achieved.

Description

Technical Field

[0001] The present invention relates to the field of air-fuel ratio control, and in particular to an air-fuel ratio control method and system for a natural gas engine. Background Art

[0002] As air pollution becomes more and more serious, people's environmental awareness is getting higher and higher, and countries have formulated more stringent standards for automobile emissions. Based on the above background, countries are prompted to continuously carry out technological innovation and product substitution in engine control, engine fuel sources and other aspects. Natural gas is the third largest natural energy after coal and oil, and its reserves are abundant in nature. Natural gas can not only provide power performance comparable to oil, but also has much less pollution to the atmosphere.

[0003] The working principle of the natural gas engine is to pressure regulate, filter and inject the natural gas into the gas mixer after the natural gas in the gas cylinder is injected into the gas mixer. The natural gas and air are mixed in a certain proportion in the gas mixer and then enter the intake manifold for final ignition and combustion.

[0004] Controlling the air-fuel ratio of natural gas to air during the natural gas operation is a very important step in engine control. When the vehicle is in a transient load change condition such as sudden acceleration or deceleration, the transient air-fuel ratio of the engine cannot accurately reflect the required value due to the response delay of the engine controller, structural components, sensor devices, etc., resulting in fluctuations in engine torque and deterioration of emission characteristics.

[0005] The size of the air-fuel ratio is mainly handled from two aspects: the control of the injection amount of the fuel gas and the control of the air intake amount. The control algorithm for the air-fuel ratio is usually composed of classic PID control, observer-based air-fuel ratio control, adaptive control, etc. In classic PID control, the controller relies on sensor signals in the application of engine air-fuel ratio control. Due to the delay caused by the sensor, filter and signal transmission and the errors of each device, the output cannot respond quickly and accurately to the given requirements. Although the observer air-fuel ratio control algorithm can better solve the delay problem caused by the sensor and transmission, and can analyze the zero poles of the control system, the amount of calculation in its control algorithm is too large, which requires a high-speed microprocessor, and the identification of its system model also requires a fast convergence algorithm. If online parameter identification is performed, a high-speed microprocessor is also required, and the accuracy of model parameter identification will also affect the control accuracy of the control system.

[0006] In view of this, the present invention proposes a method and system for controlling the air-fuel ratio of a natural gas engine, which obtains a difference between an air-fuel ratio sample and a target air-fuel ratio, compares the air-fuel ratio difference with the previous difference to obtain a difference change rate, and finally compensates for the air-fuel ratio difference and the air-fuel ratio difference change, respectively, to obtain the air mass and fuel mass that can quickly reach a stable target air-fuel ratio, and to control the air-fuel ratio of the natural gas engine. Summary of the invention

[0007] In view of this, the present invention provides an air-fuel ratio control method for a natural gas engine. The method obtains the air mass entering the natural gas engine by calculation and collects the fuel mass to realize the measurement and processing of the engine air-fuel ratio, and then calculates the error value and the error change value of the air-fuel ratio measurement value. The air-fuel ratio prediction result, the error value and the error change value of the air-fuel ratio measurement value are used as input variables, the air-fuel ratio compensation coefficient is used as the parameter to be optimized and solved, and the objective function is constructed and solved with the maximization of the air-fuel ratio compensation performance of the engine system as the optimization target of the objective function. The error value and the error change value of the air-fuel ratio measurement value are converted based on the air-fuel ratio compensation coefficient to obtain the engine air mass and fuel mass controlled by the air-fuel ratio compensation, so that the current air-fuel ratio quickly reaches the vicinity of the target air-fuel ratio, thereby realizing the engine air-fuel ratio control.

[0008] To achieve the above object, the present invention provides a method for controlling the air-fuel ratio of a natural gas engine, comprising the following steps:

[0009] S1: obtaining an input signal of a natural gas engine, and calculating an air-fuel ratio measurement value and an error value and an error change value of the air-fuel ratio measurement value based on the input signal;

[0010] S2: extracting the system dynamic characteristics of the engine system from the input signal, predicting the air-fuel ratio based on the system dynamic characteristics, and obtaining an air-fuel ratio prediction result of whether the air-fuel ratio measurement value needs to be compensated;

[0011] S3: construct an air-fuel ratio compensation objective function, wherein the air-fuel ratio compensation objective uses the air-fuel ratio prediction result, the error value of the air-fuel ratio measurement value, and the error change value as input variables, the air-fuel ratio compensation coefficient as the parameter to be optimized, and the maximization of the air-fuel ratio compensation performance of the engine system as the optimization goal of the objective function;

[0012] S4: A swarm intelligence optimization algorithm is used to optimize and solve the air-fuel ratio compensation objective function to obtain an air-fuel ratio compensation coefficient. Based on the air-fuel ratio compensation coefficient, the error value and error change value of the air-fuel ratio measurement value are converted to obtain the engine air mass and fuel mass controlled by the air-fuel ratio compensation.

[0013] As a further improvement method of the present invention:

[0014] Optionally, the step S1 of obtaining the input signal of the natural gas engine and the air-fuel ratio measurement value includes:

[0015] Obtain the input signal of the natural gas engine and the air-fuel ratio measurement value, where the input signal includes the cylinder signal, throttle signal, temperature signal, oxygen sensor signal, speed signal, battery voltage signal and accelerator pedal signal. The input signal of the natural gas engine at time t is x t :

[0016]

[0017] in:

[0018] represents the cylinder signal, throttle signal, temperature signal, oxygen sensor signal, speed signal, battery voltage signal and accelerator pedal signal of the natural gas engine at time t in sequence; in the embodiment of the present invention, the cylinder signal Throttle signal Temperature signal Oxygen sensor signal Speed ​​signal Battery voltage signal And the accelerator pedal signal They are the cylinder pressure value in the natural gas engine, throttle opening, intake temperature, oxygen content in the exhaust gas, engine speed, voltage value of the engine battery and pressure value of the accelerator pedal.

[0019] Optionally, the air-fuel ratio measurement value and the error value and error change value of the air-fuel ratio measurement value calculated based on the input signal include:

[0020] The measured air-fuel ratio of the natural gas engine at time t is represents the mass of air entering the engine combustion chamber at time t, represents the mass of natural gas fuel entering the engine combustion chamber at time t, based on the input signal x t Air quality The calculation formula is:

[0021]

[0022] in:

[0023] R air represents the air constant;

[0024] The air-fuel ratio measurement value The error value and error change value are:

[0025]

[0026] in:

[0027] ΔE(t) represents the air-fuel ratio measurement value The error value of

[0028] represents the measured value of the air-fuel ratio of the natural gas engine at time t-1, and the time interval between adjacent times is Δ; Indicates the preset target air-fuel ratio;

[0029] EC(t) represents the air-fuel ratio measurement value The error change value.

[0030] Optionally, extracting system dynamic features of the engine system from the input signal in step S2 includes:

[0031] The system dynamic characteristics of the engine system are extracted from the input signal, where the input signal x t The system dynamic feature extraction process is as follows:

[0032] S21: for input signal x t Perform time series filtering to obtain the input signal X after time series filtering. t :

[0033]

[0034] in:

[0035] w t (i) means that for the input signal x t+i For the input signal x t The time series weight in the time series filtering process, i∈[-c, 0], c represents the preset time series scale;

[0036] X t In the form of a vector with one row and seven columns Corresponding input signal x t The time series filtering processing results of the 7 signals;

[0037] The calculation process of the timing weight is as follows:

[0038] S211: Set input signal x t The temporal weight w t (0) is w, then the input signal x t-c , x t-c+1 , ..., x t-1 The sum of the timing weights is 1-w;

[0039] S212: Initialize and generate input signal x t-c , x t-c+1, ..., x t-1 The timing weight of the input signal x t+j The initialization time series weight is j∈[-c,-1],

[0040] S213: Set the current iteration number of the timing weight to z and the maximum iteration number to Num, then the timing weight The result of the zth iteration is

[0041] S214: Iterate the timing weight, where the timing weight The iteration formula is:

[0042]

[0043] in:

[0044] ||·||1 represents the L1 norm;

[0045] μ(x t+j ) represents the input signal x t+j The mean of all signals in ;

[0046] ∈ represents the iterative control coefficient; in the embodiment of the present invention, ∈ is set to 0.2;

[0047] And the iterative time series weights are normalized, where The normalization formula is:

[0048]

[0049] S215: Set z=z+1, return to step S214, until the maximum number of iterations Num is reached, and use the iteratively obtained timing weights to calculate the input signal x t Perform time series filtering, where the input signal x t+i The time series weight in the time series filtering process is w t (i)

[0050]

[0051] S22: Calculate the input signal X after time series filtering t The system dynamic characteristics f t :

[0052]

[0053] in:

[0054] ||·||2 represents the L2 norm;

[0055] ε represents the control coefficient;

[0056] exp(·) represents an exponential function with a natural constant as the base;

[0057] ZERO(X t ) indicates X t The normalized result is Represents X t The sth time series filtering result in The corresponding normalized processing result, s∈[1,7], max s , min s They are respectively the preset maximum value and the preset minimum value of the sth signal in the input signal.

[0058] Optionally, the prejudgment of the air-fuel ratio based on the system dynamic characteristics to obtain an air-fuel ratio prejudgment result of whether to compensate the air-fuel ratio measurement value includes:

[0059] The air-fuel ratio is predicted based on the system dynamic characteristics to obtain an air-fuel ratio prediction result of whether to compensate the air-fuel ratio measurement value. The compensation process of the air-fuel ratio measurement value is to adjust the air mass and fuel mass entering the engine combustion chamber, wherein the system dynamic characteristics f t The prediction formula is:

[0060]

[0061] in:

[0062] δ t Indicates whether the air-fuel ratio measurement value The predicted air-fuel ratio for compensation, δ t The higher the air-fuel ratio, the better The greater the fluctuation, the greater the probability of compensation;

[0063] σ t represents the system dynamic characteristics f t The standard deviation of t represents the system dynamic characteristics f t The mean value of t-1 Represents the input signal X after time series filtering at time t-1 t-1 The system dynamic characteristics f t-1 The mean of the system dynamic characteristics f t and f t-1 All are in 7-dimensional vector form;

[0064] ε1 represents the mean control coefficient, and ε2 represents the standard deviation control coefficient.

[0065] Optionally, constructing the air-fuel ratio compensation objective function in step S3 includes:

[0066] Collect N sets of training data to form a training data set data, where each set of training data includes an air-fuel ratio prediction result, an error value of an air-fuel ratio measurement value, and an error change value;

[0067] The representation of the training data set data is:

[0068] data = {G n =(ΔE n , E.C. n ,δ(n))|n∈[1,N]}

[0069] in:

[0070] G n Represents the nth group of training data in the training data set data;

[0071] ΔE n , E.C. n is the error value and error change value of the air-fuel ratio measurement value in the nth group of training data;

[0072] δ(n) represents the air-fuel ratio prediction result in the nth group of training data;

[0073] Based on the training data set data, an air-fuel ratio compensation objective function is constructed, in which the air-fuel ratio compensation objective takes the air-fuel ratio prediction result, the error value of the air-fuel ratio measurement value, and the error change value as input variables, the air-fuel ratio compensation coefficient as the parameter to be optimized, and the maximization of the air-fuel ratio compensation performance of the engine system as the optimization goal of the objective function. The air-fuel ratio compensation is to use the air-fuel ratio compensation coefficient to generate the air mass and gas mass entering the engine combustion chamber, and compensate and adjust the current air mass and gas mass. The constructed air-fuel ratio compensation objective function is in the form of:

[0074]

[0075] in:

[0076] F(·) represents the constructed air-fuel ratio compensation objective function, and θ represents the air-fuel ratio compensation coefficient to be optimized;

[0077] It represents the response time of the engine to the compensation process when the air-fuel ratio compensation coefficient θ is used to compensate the air-fuel ratio of the nth group of training data, wherein the greater the quality of the compensation adjustment, the greater the response time;

[0078] P n(θ) represents the response speed of the engine when the air-fuel ratio compensation coefficient θ is used to compensate the air-fuel ratio of the nth group of training data, wherein the greater the quality of the compensation adjustment, the greater the response speed;

[0079] Q represents a preset air-fuel ratio overshoot coefficient; in the embodiment of the present invention, air-fuel ratio overshoot refers to a phenomenon in which the air-fuel ratio temporarily exceeds its target value during the engine control process, and Q is set to 0.3;

[0080] M represents the preset stabilization time coefficient, and M is set to 0.7;

[0081] Indicates the time from the start of overshoot of the air-fuel ratio to the stabilization within the expected range after the air-fuel ratio compensation of the engine. In the embodiment of the present invention, the expected range of the air-fuel ratio is the adjacent range of the target air-fuel ratio whose difference with the target air-fuel ratio is within a preset threshold.

[0082] Optionally, in step S4, a swarm intelligence optimization algorithm is used to optimize and solve the air-fuel ratio compensation objective function to obtain an air-fuel ratio compensation coefficient, including:

[0083] The swarm intelligence optimization algorithm is used to optimize and solve the air-fuel ratio compensation objective function to obtain the air-fuel ratio compensation coefficient. The optimization solution process is as follows:

[0084] S41: Initialize and generate 2H groups of particle vectors, where each group of particle vectors includes a velocity vector and a position vector. The position vector corresponds to the air-fuel ratio compensation coefficient. The hth group of particle vectors generated by initialization is

[0085]

[0086] in:

[0087] Represents the position vector in the hth group of particle vectors generated by initialization. The dimension of the position vector is 6.

[0088] Represents the position vector The position values ​​of the 6 dimensions in the equation;

[0089] represents the velocity vector in the hth group of particle vectors generated by initialization, Represents the velocity vector The velocity values ​​of the 6 dimensions;

[0090] S42: Calculate the probability of the 2H groups of particle vectors being divided into the main group and the subgroup in turn, and divide the particle vectors into the main group or the subgroup, where the number of particle vectors in the main group is N and the number of subgroups is Knum , then the particle vector The probability of being classified into the main group is

[0091]

[0092] in:

[0093] Num h Indicates the calculation to the particle vector When , the number of particle vectors in the current main group;

[0094] Represents the position vector As the air-fuel ratio compensation coefficient in the air-fuel ratio compensation objective function, the objective function value is obtained and As particle vector The objective function value of

[0095] And divide the particle vectors that are not divided into the main group into K num The number of particle vectors in each subgroup is

[0096] S43: Set the current iteration number of the particle vector to d, the maximum iteration number to Max, and the initial value of d to 0. Then the dth iteration result of the hth group of particle vectors in the main group is In order The position vector and velocity vector in ;

[0097] The d-th iteration result of the g-th particle vector in the k-th subgroup is

[0098] S44: For the particle vectors in the main group and K num Iterate the particle vectors in each subgroup;

[0099] Particle Vector The iteration formula in the main group is:

[0100]

[0101] in:

[0102] rand(0,1) represents a random number between 0 and 1;

[0103] a1, a2 represent learning factors;

[0104] ω d represents the adaptive iteration weight of the dth iteration;

[0105] Represents the position vector of the particle vector with the smallest objective function value in the d-time iteration result of the h-th particle vector in the main group;

[0106] Represents the position vector of the particle vector with the smallest objective function value among all particle vectors obtained in the dth iteration in the subgroup;

[0107] Particle Vector The iteration formula in the kth subgroup is:

[0108]

[0109] in:

[0110] mean k represents the mean of all particle vectors in the kth subgroup, ∑ k represents the covariance matrix of all particle vectors in the kth subgroup, k∈[1, K num ];

[0111] S45: Let d=d+1, return to step S43, until the maximum number of iterations Max is reached, and calculate the particle vector with the largest objective function value in the main group, and extract the position vector in the particle vector as the air-fuel ratio compensation coefficient (β1, β2, β3, β4, β5, λ1):

[0112]

[0113] in:

[0114] Represents the position vector of the particle vector with the largest objective function value in the main group after the Max-th iteration,

[0115] Represents the position vector The position values ​​of the 6 dimensions in .

[0116] Optionally, converting the error value and the error change value of the air-fuel ratio measurement value based on the air-fuel ratio compensation coefficient to obtain the engine air mass and fuel mass controlled by the air-fuel ratio compensation includes:

[0117] The air-fuel ratio compensation coefficient is used to generate the compensation values ​​of the fuel mass and the air mass at time t, where the compensation values ​​of the fuel mass and the air mass at time t are:

[0118] Y1(t)=ΔE(t)·β2(β4+λ1β3)

[0119] Y2(t)=EC(t)·β5(β4+λ1β3)

[0120] in:

[0121] Y1(t) and Y2(t) are the compensation values ​​of fuel mass and air mass at time t respectively;

[0122] If S t If the value is greater than the preset threshold, the fuel mass and air mass entering the engine combustion chamber at time t are adjusted to as well as In the embodiment of the present invention, by adjusting the cylinder pressure value, throttle opening, intake temperature, oxygen content in exhaust gas, and engine speed in the natural gas engine, the air mass entering the engine combustion chamber reaches The adjustment formula is the calculation formula of the air quality in step S1.

[0123] In order to solve the above problems, the present invention provides an air-fuel ratio control system for a natural gas engine, wherein the control algorithm module in the system comprises:

[0124] The error data processing module is used to obtain the input signal of the natural gas engine, and calculate the air-fuel ratio measurement value, the error value of the air-fuel ratio measurement value, and the error change value based on the input signal;

[0125] The error change data processing module is used to extract the system dynamic characteristics of the engine system from the input signal, predict the air-fuel ratio based on the system dynamic characteristics, and obtain the air-fuel ratio prediction result of whether to compensate the air-fuel ratio measurement value;

[0126] The compensation algorithm module is used to construct an air-fuel ratio compensation objective function, use a swarm intelligence optimization algorithm to optimize and solve the air-fuel ratio compensation objective function, obtain an air-fuel ratio compensation coefficient, and compensate the air-fuel ratio based on the air-fuel ratio compensation coefficient.

[0127] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0128] A memory storing at least one instruction;

[0129] Communication interface, enabling electronic equipment to communicate; and

[0130] The processor executes the instructions stored in the memory to implement the above-mentioned natural gas engine air-fuel ratio control method.

[0131] In order to solve the above problem, the present invention further provides a computer-readable storage medium, wherein at least one instruction is stored in the computer-readable storage medium, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned natural gas engine air-fuel ratio control method.

[0132] Compared with the prior art, the present invention proposes a natural gas engine air-fuel ratio control method, which has the following advantages:

[0133] First, this scheme proposes a method for predicting the air-fuel ratio of an engine. By obtaining the input signals of the natural gas engine in various types of signals, the air mass entering the natural gas engine is calculated, and the fuel mass is collected to realize the measurement and processing of the engine air-fuel ratio, and then the error value and error change value of the air-fuel ratio measurement value are calculated. At the same time, the input signal is processed by time series filtering to remove the noise information in the input signal from the time domain level, and the change information of the system at the time series level is calculated in combination with the signal change value as the dynamic feature of the system. By extracting the variation information of the dynamic feature of the system, the air-fuel ratio prediction result of whether to compensate the air-fuel ratio measurement value is used. The larger the result, the greater the degree of change of the current input signal, and the air-fuel ratio abnormality may be quickly reached.

[0134] At the same time, this scheme proposes an air-fuel ratio compensation method, which takes the air-fuel ratio prediction result, the error value of the air-fuel ratio measurement value and the error change value as input variables, takes the air-fuel ratio compensation coefficient as the parameter to be optimized and solved, and takes the engine response speed and the time to reach air-fuel ratio stability as the air-fuel ratio compensation performance of the engine system. The greater the response speed and the shorter the time to reach stability, the greater the air-fuel ratio compensation performance. Then, the objective function is constructed with the maximization of the air-fuel ratio compensation performance of the engine system as the optimization target of the objective function, and the air-fuel ratio compensation objective function is optimized and solved by a swarm intelligence optimization algorithm. Several particles are quickly generated to form a group. Different iterative methods are adopted for different groups to generate several groups of solutions and judge them to obtain the air-fuel ratio compensation coefficient that makes the objective function optimal. The error value and the error change value of the air-fuel ratio measurement value are converted based on the air-fuel ratio compensation coefficient to obtain the engine air mass and fuel mass controlled by the air-fuel ratio compensation, so that the current air-fuel ratio quickly reaches the range near the target air-fuel ratio, thereby realizing the engine air-fuel ratio control. BRIEF DESCRIPTION OF THE DRAWINGS

[0135] Figure 1 A schematic flow chart of a method for controlling the air-fuel ratio of a natural gas engine provided by one embodiment of the present invention;

[0136] Figure 2 An overall diagram of the functional modules of a natural gas engine air-fuel ratio control system provided by one embodiment of the present invention;

[0137] Figure 3 A diagram of a functional module for injection compensation calculation for performing compensation calculation in an air-fuel ratio control system of a natural gas engine provided by an embodiment of the present invention;

[0138] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0139] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0140] The embodiment of the present application provides a method for controlling the air-fuel ratio of a natural gas engine. The execution subject of the method for controlling the air-fuel ratio of a natural gas engine includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for controlling the air-fuel ratio of a natural gas engine can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0141] Embodiment 1:

[0142] A method for controlling the air-fuel ratio of a natural gas engine comprises the following steps:

[0143] S1: Obtain an input signal of a natural gas engine, and calculate an air-fuel ratio measurement value and an error value and an error change value of the air-fuel ratio measurement value based on the input signal.

[0144] The step S1 of obtaining the input signal of the natural gas engine and the air-fuel ratio measurement value includes:

[0145] Obtain the input signal of the natural gas engine and the air-fuel ratio measurement value, where the input signal includes the cylinder signal, throttle signal, temperature signal, oxygen sensor signal, speed signal, battery voltage signal and accelerator pedal signal. The input signal of the natural gas engine at time t is x t :

[0146]

[0147] in:

[0148] represents the cylinder signal, throttle signal, temperature signal, oxygen sensor signal, speed signal, battery voltage signal and accelerator pedal signal of the natural gas engine at time t in sequence; in the embodiment of the present invention, the cylinder signal Throttle signal Temperature signal Oxygen sensor signal Speed ​​signal Battery voltage signal And the accelerator pedal signal They are the cylinder pressure value in the natural gas engine, throttle opening, intake temperature, oxygen content in the exhaust gas, engine speed, voltage value of the engine battery and pressure value of the accelerator pedal.

[0149] The air-fuel ratio measurement value, the error value of the air-fuel ratio measurement value, and the error change value calculated based on the input signal include:

[0150] The measured air-fuel ratio of the natural gas engine at time t is represents the mass of air entering the engine combustion chamber at time t, represents the mass of natural gas fuel entering the engine combustion chamber at time t, based on the input signal x t Air quality The calculation formula is:

[0151]

[0152] in:

[0153] R air represents the air constant;

[0154] The air-fuel ratio measurement value The error value and error change value are:

[0155]

[0156] in:

[0157] ΔE(t) represents the air-fuel ratio measurement value The error value of

[0158] Indicates the preset target air-fuel ratio;

[0159] represents the measured value of the air-fuel ratio of the natural gas engine at time t-1, and the time interval between adjacent times is Δ;

[0160] EC(t) represents the air-fuel ratio measurement value The error change value.

[0161] S2: extracting the system dynamic characteristics of the engine system from the input signal, predicting the air-fuel ratio based on the system dynamic characteristics, and obtaining an air-fuel ratio prediction result of whether the air-fuel ratio measurement value needs to be compensated.

[0162] In step S2, the system dynamic characteristics of the engine system are extracted from the input signal, including:

[0163] The system dynamic characteristics of the engine system are extracted from the input signal, where the input signal x t The system dynamic feature extraction process is as follows:

[0164] S21: for input signal x tPerform time series filtering to obtain the input signal X after time series filtering. t :

[0165]

[0166] in:

[0167] w t (i) means that for the input signal x t+i For the input signal x t The time series weight in the time series filtering process, i∈[-c, 0], c represents the preset time series scale;

[0168] X t In the form of a vector with one row and seven columns Corresponding input signal x t The time series filtering processing results of the 7 signals;

[0169] The calculation process of the timing weight is as follows:

[0170] S211: Set input signal x t The temporal weight w t (0) is w, then the input signal x t-c , x t-c+1 , ..., x t-1 The sum of the timing weights is 1-w;

[0171] S212: Initialize and generate input signal x t-c , x t-c+1 , ..., x t-1 The timing weight of the input signal x t+j The initialization time series weight is j∈[-c,-1],

[0172] S213: Set the current iteration number of the timing weight to z and the maximum iteration number to Num, then the timing weight The result of the zth iteration is

[0173] S214: Iterate the timing weight, where the timing weight The iteration formula is:

[0174]

[0175] in:

[0176] ||·||1 represents the L1 norm;

[0177] μ(x t+j ) represents the input signal x t+jThe mean of all signals in ;

[0178] ∈ represents the iterative control coefficient; in the embodiment of the present invention, ∈ is set to 0.2;

[0179] And the iterative time series weights are normalized, where The normalization formula is:

[0180]

[0181] S215: Set z=z+1, return to step S214, until the maximum number of iterations Num is reached, and use the iteratively obtained timing weights to calculate the input signal x t Perform time series filtering, where the input signal x t+i The time series weight in the time series filtering process is w t (i)

[0182]

[0183] S22: Calculate the input signal X after time series filtering t The system dynamic characteristics f t :

[0184]

[0185] in:

[0186] ||·||2 represents the L2 norm;

[0187] ε represents the control coefficient;

[0188] exp(·) represents an exponential function with a natural constant as the base;

[0189] ZERO(X t ) indicates X t The normalized result is Represents X t The sth time series filtering result in The corresponding normalized processing result, s∈[1,7], max s , min s They are respectively the preset maximum value and the preset minimum value of the sth signal in the input signal.

[0190] The air-fuel ratio is predicted based on the system dynamic characteristics to obtain an air-fuel ratio prediction result of whether to compensate the air-fuel ratio measurement value, including:

[0191] The air-fuel ratio is predicted based on the system dynamic characteristics to obtain an air-fuel ratio prediction result of whether to compensate the air-fuel ratio measurement value. The compensation process of the air-fuel ratio measurement value is to adjust the air mass and fuel mass entering the engine combustion chamber, wherein the system dynamic characteristics f t The prediction formula is:

[0192]

[0193] in:

[0194] δ t Indicates whether the air-fuel ratio measurement value The predicted air-fuel ratio for compensation, δ t The higher the air-fuel ratio, the better The greater the fluctuation, the greater the probability of compensation;

[0195] σ t represents the system dynamic characteristics f t The standard deviation of t represents the system dynamic characteristics f t The mean value of t-1 Represents the input signal X after time series filtering at time t-1 t-1 The system dynamic characteristics f t-1 The mean of the system dynamic characteristics f t and f t-1 All are in 7-dimensional vector form;

[0196] ε1 represents the mean control coefficient, and ε2 represents the standard deviation control coefficient.

[0197] S3: Construct air-fuel ratio compensation objective function.

[0198] The air-fuel ratio compensation objective function is constructed in step S3, including:

[0199] Collect N sets of training data to form a training data set data, where each set of training data includes an air-fuel ratio prediction result, an error value of an air-fuel ratio measurement value, and an error change value;

[0200] The representation of the training data set data is:

[0201] data = {G n =(ΔE n , E.C. n ,δ(n))|n∈[1,N]}

[0202] in:

[0203] G n Represents the nth group of training data in the training data set data;

[0204] ΔE n , E.C. n is the error value and error change value of the air-fuel ratio measurement value in the nth group of training data;

[0205] δ(n) represents the air-fuel ratio prediction result in the nth group of training data;

[0206] Based on the training data set data, an air-fuel ratio compensation objective function is constructed, in which the air-fuel ratio compensation objective takes the air-fuel ratio prediction result, the error value of the air-fuel ratio measurement value, and the error change value as input variables, the air-fuel ratio compensation coefficient as the parameter to be optimized, and the maximization of the air-fuel ratio compensation performance of the engine system as the optimization goal of the objective function. The air-fuel ratio compensation is to use the air-fuel ratio compensation coefficient to generate the air mass and gas mass entering the engine combustion chamber, and compensate and adjust the current air mass and gas mass. The constructed air-fuel ratio compensation objective function is in the form of:

[0207]

[0208] in:

[0209] F(·) represents the constructed air-fuel ratio compensation objective function, and θ represents the air-fuel ratio compensation coefficient to be optimized;

[0210] It represents the response time of the engine to the compensation process when the air-fuel ratio compensation coefficient θ is used to compensate the air-fuel ratio of the nth group of training data, wherein the greater the quality of the compensation adjustment, the greater the response time;

[0211] Pn(θ) represents the response speed of the engine when the air-fuel ratio compensation coefficient θ is used to compensate the air-fuel ratio of the nth group of training data, wherein the greater the quality of the compensation adjustment, the greater the response speed;

[0212] Q represents a preset air-fuel ratio overshoot coefficient; in the embodiment of the present invention, air-fuel ratio overshoot refers to a phenomenon in which the air-fuel ratio temporarily exceeds its target value during the engine control process, and Q is set to 0.3;

[0213] M represents the preset stabilization time coefficient, and M is set to 0.7;

[0214] It indicates the time from when the air-fuel ratio starts to overshoot to when it stabilizes within the expected range after the air-fuel ratio compensation is performed on the engine.

[0215] S4: A swarm intelligence optimization algorithm is used to optimize and solve the air-fuel ratio compensation objective function to obtain an air-fuel ratio compensation coefficient. Based on the air-fuel ratio compensation coefficient, the error value and error change value of the air-fuel ratio measurement value are converted to obtain the engine air mass and fuel mass controlled by the air-fuel ratio compensation.

[0216] In the step S4, a swarm intelligence optimization algorithm is used to optimize and solve the air-fuel ratio compensation objective function to obtain an air-fuel ratio compensation coefficient, including:

[0217] The swarm intelligence optimization algorithm is used to optimize and solve the air-fuel ratio compensation objective function to obtain the air-fuel ratio compensation coefficient. The optimization solution process is as follows:

[0218] S41: Initialize and generate 2H groups of particle vectors, where each group of particle vectors includes a velocity vector and a position vector. The position vector corresponds to the air-fuel ratio compensation coefficient. The hth group of particle vectors generated by initialization is

[0219]

[0220] in:

[0221] Represents the position vector in the hth group of particle vectors generated by initialization. The dimension of the position vector is 6.

[0222] Represents the position vector The position values ​​of the 6 dimensions in the equation;

[0223] represents the velocity vector in the hth group of particle vectors generated by initialization, Represents the velocity vector The velocity values ​​of the 6 dimensions;

[0224] S42: Calculate the probability of the 2H groups of particle vectors being divided into the main group and the subgroup in turn, and divide the particle vectors into the main group or the subgroup, where the number of particle vectors in the main group is N and the number of subgroups is K num , then the particle vector The probability of being classified into the main group is

[0225]

[0226] in:

[0227] Num h Indicates the calculation to the particle vector When , the number of particle vectors in the current main group;

[0228] Represents the position vector As the air-fuel ratio compensation coefficient in the air-fuel ratio compensation objective function, the objective function value is obtained and As particle vector The objective function value of

[0229] And divide the particle vectors that are not divided into the main group into K num The number of particle vectors in each subgroup is

[0230] S43: Set the current iteration number of the particle vector to d, the maximum iteration number to Max, and the initial value of d to 0. Then the dth iteration result of the hth group of particle vectors in the main group is In order The position vector and velocity vector in ;

[0231] The d-th iteration result of the g-th particle vector in the k-th subgroup is

[0232] S44: For the particle vectors in the main group and K num Iterate the particle vectors in each subgroup;

[0233] Particle Vector The iteration formula in the main group is:

[0234]

[0235] in:

[0236] rand(0,1) represents a random number between 0 and 1;

[0237] a1, a2 represent learning factors;

[0238] ω d represents the adaptive iteration weight of the dth iteration;

[0239] Represents the position vector of the particle vector with the smallest objective function value in the d-time iteration result of the h-th particle vector in the main group;

[0240] Represents the position vector of the particle vector with the smallest objective function value among all particle vectors obtained in the dth iteration in the subgroup;

[0241] Particle Vector The iteration formula in the kth subgroup is:

[0242]

[0243] in:

[0244] mean k represents the mean of all particle vectors in the kth subgroup, ∑ k represents the covariance matrix of all particle vectors in the kth subgroup, k∈[1, K num ];

[0245] S45: Let d=d+1, return to step S43, until the maximum number of iterations Max is reached, and calculate the particle vector with the largest objective function value in the main group, and extract the position vector in the particle vector as the air-fuel ratio compensation coefficient (β1, β2, p3, β4, β5, λ1):

[0246]

[0247] in:

[0248] Represents the position vector of the particle vector with the largest objective function value in the main group after the Max-th iteration, Represents the position vector The position values ​​of the 6 dimensions in .

[0249] The error value and the error change value of the air-fuel ratio measurement value are converted based on the air-fuel ratio compensation coefficient to obtain the engine air mass and fuel mass controlled by the air-fuel ratio compensation, including:

[0250] The air-fuel ratio compensation coefficient is used to generate the compensation values ​​of the fuel mass and the air mass at time t, where the compensation values ​​of the fuel mass and the air mass at time t are:

[0251] Y1(t)=ΔE(t)·β2(β4+λ1β3)

[0252] Y2(t)=EC(t)·β5(β4+λ1β3)

[0253] in:

[0254] Y1(t) and Y2(t) are the compensation values ​​of fuel mass and air mass at time t respectively;

[0255] If S t If the value is greater than the preset threshold, the fuel mass and air mass entering the engine combustion chamber at time t are adjusted to as well as In the embodiment of the present invention, by adjusting the cylinder pressure value, throttle opening, intake temperature, oxygen content in exhaust gas, and engine speed in the natural gas engine, the air mass entering the engine combustion chamber reaches The adjustment formula is the calculation formula of the air quality in step S1.

[0256] Embodiment 2:

[0257] like Figure 2The figure shows an overall functional module diagram of a natural gas engine air-fuel ratio control system provided by an embodiment of the present invention. The natural gas engine air-fuel ratio control system includes an injection module and a cylinder body. The input signals include a cylinder signal 1, a throttle signal 2, a temperature signal 3, an oxygen sensor signal 4, a speed signal 5, a battery voltage signal 6, an accelerator pedal signal 7, a vehicle control module 8, an injection and ignition control module 9, a crankshaft signal 10, a camshaft signal 11, an ignition signal 12, an injection module 13, and a cylinder body.

[0258] like Figure 3 As shown, it is a functional module diagram of injection compensation calculation for compensation calculation in a natural gas engine air-fuel ratio control system provided by an embodiment of the present invention, including module normalization 122, normalization 223, error data processing 24, PID125, multiplier 26, PID 27, error change data processing 28, PID2 29, multiplier 30, compensation coefficient λ131, control coefficient β432, absolute value calculation 33, compensation algorithm 34, multiplier 35, control coefficient β336, control coefficient β237, control coefficient β538, which can realize the natural gas engine air-fuel ratio control method in Example 1.

[0259] The natural gas engine air-fuel ratio control system of the present invention can be installed in an electronic device. According to the algorithm function implemented, the compensation algorithm part in the natural gas engine air-fuel ratio control system mainly includes an error data processing module 24, an error change data processing module 28 and a compensation algorithm module 34. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0260] The error data processing module 24 is used to obtain the input signal of the natural gas engine, and calculate the air-fuel ratio measurement value, the error value of the air-fuel ratio measurement value, and the error change value based on the input signal;

[0261] The error change data processing module 28 is used to extract the system dynamic characteristics of the engine system from the input signal, prejudge the air-fuel ratio based on the system dynamic characteristics, and obtain the air-fuel ratio prejudgment result of whether to compensate the air-fuel ratio measurement value;

[0262] The compensation algorithm module 34 is used to construct an air-fuel ratio compensation objective function, optimize and solve the air-fuel ratio compensation objective function using a swarm intelligence optimization algorithm, obtain an air-fuel ratio compensation coefficient, and compensate the air-fuel ratio based on the air-fuel ratio compensation coefficient;

[0263] In detail, each module in the natural gas engine air-fuel ratio control system in the embodiment of the present invention is used in the same manner as above. Figure 1The technical means are the same as the natural gas engine air-fuel ratio control method described in, and can produce the same technical effects, so they will not be repeated here.

[0264] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0265] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0266] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0267] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A natural gas engine air-fuel ratio control method, characterized in that: The method comprises: S1: obtaining an input signal of a natural gas engine, and calculating an air-fuel ratio measurement value and an error value and an error change value of the air-fuel ratio measurement value based on the input signal; S2: extracting the system dynamic characteristics of the engine system from the input signal, predicting the air-fuel ratio based on the system dynamic characteristics, and obtaining an air-fuel ratio prediction result of whether the air-fuel ratio measurement value needs to be compensated; S3: constructing an air-fuel ratio compensation objective function; S4: A swarm intelligence optimization algorithm is used to optimize and solve the air-fuel ratio compensation objective function to obtain an air-fuel ratio compensation coefficient. Based on the air-fuel ratio compensation coefficient, the error value and error change value of the air-fuel ratio measurement value are converted to obtain the engine air mass and fuel mass controlled by the air-fuel ratio compensation.

2. A natural gas engine air-fuel ratio control method as claimed in claim 1, characterized in that: The step S1 of obtaining the input signal of the natural gas engine and the air-fuel ratio measurement value includes: Obtain the input signal of the natural gas engine and the air-fuel ratio measurement value, where the input signal includes the cylinder signal, throttle signal, temperature signal, oxygen sensor signal, speed signal, battery voltage signal and accelerator pedal signal. The input signal of the natural gas engine at time t is x t : in: It represents the cylinder signal, throttle signal, temperature signal, oxygen sensor signal, speed signal, battery voltage signal and accelerator pedal signal of the natural gas engine at time t in sequence.

3. A natural gas engine air-fuel ratio control method as claimed in claim 2, characterized in that: The air-fuel ratio measurement value, the error value of the air-fuel ratio measurement value, and the error change value calculated based on the input signal include: The measured air-fuel ratio of the natural gas engine at time t is represents the mass of air entering the engine combustion chamber at time t, represents the mass of natural gas fuel entering the engine combustion chamber at time t, based on the input signal x t Air quality The calculation formula is: in: R air represents the air constant; The air-fuel ratio measurement value The error value and error change value are: in: ΔE(t) represents the air-fuel ratio measurement value The error value of represents the measured value of the air-fuel ratio of the natural gas engine at time t-1, and the time interval between adjacent times is Δ; Indicates the preset target air-fuel ratio; EC(t) represents the air-fuel ratio measurement value The error change value.

4. A natural gas engine air-fuel ratio control method as claimed in claim 1, characterized in that: The S2 step includes: The system dynamic characteristics of the engine system are extracted from the input signal, where the input signal x t The system dynamic feature extraction process is as follows: S21: for input signal x t Perform time series filtering to obtain the input signal X after time series filtering. t : in: w t (i) means that for the input signal x t+i For the input signal x t The time series weight in the time series filtering process, i∈[-c,0], c represents the preset time series scale; X t In the form of a vector with one row and seven columns Corresponding input signal x t The time series filtering processing results of the 7 signals; The calculation process of the timing weight is as follows: S211: Set input signal x t The temporal weight w t (0) is w, then the input signal x t-c ,x t-c+1 ,...,x t-1 The sum of the timing weights is 1-w; S212: Initialize and generate input signal x t-c ,x t-c+1 ,...,x t-1 The timing weight of the input signal x t+j The initialization time series weight is S213: Set the current iteration number of the timing weight to z and the maximum iteration number to Num, then the timing weight The result of the zth iteration is S214: Iterate the timing weight, where the timing weight The iteration formula is: in: ||·||1 represents the L1 norm; μ(x t+j ) represents the input signal x t+j The mean of all signals in ; ∈ represents the iterative control coefficient; And the iterative time series weights are normalized, where The normalization formula is: S215: Set z=z+1, return to step S214, until the maximum number of iterations Num is reached, and use the iteratively obtained timing weights to calculate the input signal x t Perform time series filtering, where the input signal x t+i The time series weight in the time series filtering process is w t (o): S22: Calculate the input signal X after time series filtering t The system dynamic characteristics f t : in: ||·||2 represents the L2 norm; ε represents the control coefficient; exp(·) represents an exponential function with a natural constant as the base; ZERO(X t ) indicates X t The normalized result is Represents X t The sth time series filtering result in The corresponding normalized processing result, s∈[1,7], max s ,min s They are respectively the preset maximum value and the preset minimum value of the sth signal in the input signal.

5. A natural gas engine air-fuel ratio control method as claimed in claim 4, characterized in that: The air-fuel ratio is predicted based on the system dynamic characteristics to obtain an air-fuel ratio prediction result of whether to compensate the air-fuel ratio measurement value, including: The air-fuel ratio is predicted based on the system dynamic characteristics to obtain an air-fuel ratio prediction result of whether to compensate the air-fuel ratio measurement value. The compensation process of the air-fuel ratio measurement value is to adjust the air mass and fuel mass entering the engine combustion chamber, wherein the system dynamic characteristics f t The prediction formula is: in: δ t Indicates whether the air-fuel ratio measurement is required Predicted results of air-fuel ratio for compensation; σ t represents the system dynamic characteristics f t The standard deviation of t represents the system dynamic characteristics f t The mean value of t-1 Represents the input signal X after time series filtering at time t-1 t-1 The system dynamic characteristics f t-1 The mean of the system dynamic characteristics f t and f t-1 All are in 7-dimensional vector form; ε1 represents the mean control coefficient, and ε2 represents the standard deviation control coefficient.

6. A natural gas engine air-fuel ratio control method as claimed in claim 1, characterized in that: The air-fuel ratio compensation objective function is constructed in step S3, including: Collect N sets of training data to form a training data set data, where each set of training data includes an air-fuel ratio prediction result, an error value of an air-fuel ratio measurement value, and an error change value; The representation of the training data set data is: data={G n =(ΔE n ,EC n ,δ(n))|n∈[1,N]} in: G n Represents the nth group of training data in the training data set data; ΔE n ,EC n is the error value and error change value of the air-fuel ratio measurement value in the nth group of training data; δ(n) represents the air-fuel ratio prediction result in the nth group of training data; Based on the training data set data, an air-fuel ratio compensation objective function is constructed. The air-fuel ratio compensation is to use the air-fuel ratio compensation coefficient to generate the air mass and gas mass entering the engine combustion chamber, and to compensate and adjust the current air mass and gas mass. The constructed air-fuel ratio compensation objective function is in the form of: in: F(·) represents the constructed air-fuel ratio compensation objective function, and θ represents the air-fuel ratio compensation coefficient to be optimized; It represents the response time of the engine to the compensation process when the air-fuel ratio compensation coefficient θ is used to compensate the air-fuel ratio of the nth group of training data; P n (θ) represents the response speed of the engine when the air-fuel ratio compensation coefficient θ is used to compensate the air-fuel ratio of the nth set of training data; Q represents the preset air-fuel ratio overshoot coefficient; M represents the preset stabilization time coefficient, and M is set to 0.7; It indicates the time from the beginning of overshoot of the air-fuel ratio to the stabilization within the expected range after air-fuel ratio compensation is performed on the engine. The expected range of the air-fuel ratio is the adjacent range of the target air-fuel ratio whose difference with the target air-fuel ratio is within a preset threshold.

7. A natural gas engine air-fuel ratio control method as claimed in claim 6, characterized in that: The S4 step includes: The swarm intelligence optimization algorithm is used to optimize and solve the air-fuel ratio compensation objective function to obtain the air-fuel ratio compensation coefficient. The optimization solution process is as follows: S41: Initialize and generate 2H groups of particle vectors, where each group of particle vectors includes a velocity vector and a position vector. The position vector corresponds to the air-fuel ratio compensation coefficient. The hth group of particle vectors generated by initialization is in: Represents the position vector in the hth group of particle vectors generated by initialization. The dimension of the position vector is 6. Represents the position vector The position values ​​of the 6 dimensions in the equation; represents the velocity vector in the hth group of particle vectors generated by initialization, Represents the velocity vector The velocity values ​​of the 6 dimensions; S42: Calculate the probability of the 2H groups of particle vectors being divided into the main group and the subgroup in turn, and divide the particle vectors into the main group or the subgroup, where the number of particle vectors in the main group is N and the number of subgroups is K num , then the particle vector The probability of being classified into the main group is in: Num h Indicates the calculation to the particle vector When , the number of particle vectors in the current main group; Represents the position vector As the air-fuel ratio compensation coefficient in the air-fuel ratio compensation objective function, the objective function value is obtained and As particle vector The objective function value of And divide the particle vectors that are not divided into the main group into K num The number of particle vectors in each subgroup is S43: Set the current iteration number of the particle vector to d, the maximum iteration number to Max, and the initial value of d to 0. Then the dth iteration result of the hth group of particle vectors in the main group is In order The position vector and velocity vector in ; The d-th iteration result of the g-th particle vector in the k-th subgroup is S44: For the particle vectors in the main group and K num Iterate the particle vectors in each subgroup; Particle Vector The iteration formula in the main group is: in: rand(0,1) represents a random number between 0 and 1; a1, a2 represent learning factors; ω d represents the adaptive iteration weight of the dth iteration; Represents the position vector of the particle vector with the smallest objective function value in the d-time iteration result of the h-th particle vector in the main group; Represents the position vector of the particle vector with the smallest objective function value among all particle vectors obtained in the dth iteration in the subgroup; Particle Vector The iteration formula in the kth subgroup is: in: mean k represents the mean of all particle vectors in the kth subgroup, ∑ k represents the covariance matrix of all particle vectors in the kth subgroup, k∈[1,K num ]; S45: Set d=d+1, return to step S43, until the maximum number of iterations Max is reached, and calculate the particle vector with the largest objective function value in the main group, and extract the position vector in the particle vector as the air-fuel ratio compensation coefficient in: Represents the position vector of the particle vector with the largest objective function value in the main group after the Max-th iteration, Represents the position vector The position values ​​of the 6 dimensions in .

8. A natural gas engine air-fuel ratio control method as claimed in claim 7, characterized in that: The error value and the error change value of the air-fuel ratio measurement value are converted based on the air-fuel ratio compensation coefficient to obtain the engine air mass and fuel mass controlled by the air-fuel ratio compensation, including: The air-fuel ratio compensation coefficient is used to generate the compensation values ​​of the fuel mass and the air mass at time t, where the compensation values ​​of the fuel mass and the air mass at time t are: Y1(t)=ΔE(t)·β2(β4+λ1β3) Y2(t)=EC(t)·β5(β4+λ1β3) in: Y1(t) and Y2(t) are the compensation values ​​of fuel mass and air mass at time t respectively; If S t If the value is greater than the preset threshold, the fuel mass and air mass entering the engine combustion chamber at time t are adjusted to as well as The air-fuel ratio at time t is compensated and controlled.

9. A natural gas engine air-fuel ratio control system, characterized in that: The control algorithm module in the system includes: The error data processing module is used to obtain the input signal of the natural gas engine, and calculate the air-fuel ratio measurement value, the error value of the air-fuel ratio measurement value, and the error change value based on the input signal; The error change data processing module is used to extract the system dynamic characteristics of the engine system from the input signal, predict the air-fuel ratio based on the system dynamic characteristics, and obtain the air-fuel ratio prediction result of whether to compensate the air-fuel ratio measurement value; The compensation algorithm module is used to construct an air-fuel ratio compensation objective function, use a swarm intelligence optimization algorithm to optimize and solve the air-fuel ratio compensation objective function, obtain an air-fuel ratio compensation coefficient, and compensate the air-fuel ratio based on the air-fuel ratio compensation coefficient; To realize an air-fuel ratio control method for a natural gas engine as described in any one of claims 1-8.

Images