CN-121976890-A - Engine oil injection quantity determining method, device, equipment and storage medium

CN121976890ACN 121976890 ACN121976890 ACN 121976890ACN-121976890-A

Abstract

The application provides a method, a device, equipment and a storage medium for determining the fuel injection quantity of an engine, wherein the method comprises the steps of setting an angle range within a preset distance of a top dead center of each cylinder of the engine, uniformly arranging a plurality of sampling points, and collecting rail pressure of a high-pressure common rail system from each sampling point to form an original rail pressure array; extracting the initial value of the array as a working condition reference value, subtracting the initial value from each element of the array to obtain a relative pressure drop array, accumulating and summing the elements of the relative pressure drop array, synchronously recording the rotating speed and the fuel temperature of the engine, inputting the data (the initial value, the relative pressure drop array, the accumulated sum, the rotating speed and the fuel temperature) into a neural network, and calculating to obtain the actual fuel injection quantity. The method realizes the online real-time measurement of the fuel injection quantity of the engine through rail pressure sampling, data preprocessing and neural network calculation, can be compared with a target value in time and correct the deviation, effectively overcomes the defect that the fuel injection quantity deviation cannot be measured and corrected in real time in the prior art, and improves the running stability of the engine.

Inventors

SANG HAILANG
ZHOU SHENGKAI
LIN TIEJIAN
WANG HUI
YE YU
DAI ZHENCHAO

Assignees

广西玉柴机器股份有限公司

Dates

Publication Date: 20260505
Application Date: 20260129

Claims (10)

1. A method for determining an injection amount of an engine, comprising: Setting an angle range in a preset distance of a top dead center of each cylinder of the engine, and uniformly setting a plurality of sampling points in the angle range; acquiring rail pressure of a high-pressure common rail system from each sampling point to obtain an original rail pressure array; extracting a first value from the original rail pressure array as a working condition reference value; calculating a relative pressure drop array according to the original rail pressure array and the first value, wherein each element of the relative pressure drop array is obtained by subtracting the first value from the corresponding element of the original rail pressure array; Accumulating all elements of the relative pressure drop array, and calculating an accumulated sum; Synchronously recording the rotation speed of the engine and the temperature of the fuel; and calculating the actual fuel injection quantity through a neural network according to the first value, the relative pressure drop array, the accumulated sum, the engine speed and the fuel temperature.
2. The method of claim 1, wherein the setting an angular range around the top dead center of each cylinder of the engine and uniformly setting a plurality of sampling points in the angular range comprises: The angle range is preset to include a crank angle range corresponding to the oil injection operation.
3. The method of claim 1, wherein the setting an angular range around the top dead center of each cylinder of the engine and uniformly setting a plurality of sampling points in the angular range comprises: the plurality of sampling points are arranged in the angle range in an equally spaced manner.
4. The method of claim 1, wherein extracting a first value from the raw rail pressure array as a condition reference value comprises: The first value corresponds to an engine crankshaft angular position before injection begins.
5. The method of claim 1, wherein calculating a relative pressure drop array from the original rail pressure array and the first value, wherein each element of the relative pressure drop array is derived from subtracting the first value from a corresponding element of the original rail pressure array, comprises: the subtraction operation is applied point-by-point to each sampling point to generate the array of relative pressure drops.
6. The method of claim 1, wherein accumulating all elements of the array of relative pressure drops, calculating an accumulated sum, comprises: the sum is obtained by summing all elements of the array of relative pressure drops.
7. The method of claim 1, wherein calculating an actual fuel injection amount from the first value, the array of relative pressure drops, the accumulated sum, the engine speed, and the fuel temperature via a neural network comprises: the neural network includes an input layer, a hidden layer, and an output layer, wherein the input layer receives the first value, the array of relative pressure drops, the cumulative sum, the engine speed, and the fuel temperature.
8. An engine fuel injection amount determining device, characterized by comprising: the setting module is used for setting an angle range within a preset distance of a top dead center of each cylinder of the engine and uniformly setting a plurality of sampling points within the angle range; the acquisition module acquires rail pressure of the high-pressure common rail system from each sampling point to obtain an original rail pressure array; The extraction module is used for extracting a first value from the original rail pressure array to serve as a working condition reference value; The calculation module is used for calculating a relative pressure drop array according to the original rail pressure array and the first value, wherein each element of the relative pressure drop array is obtained by subtracting the first value from the corresponding element of the original rail pressure array; The summation module is used for accumulating all elements of the relative pressure drop array and calculating an accumulation sum; the recording module synchronously records the rotation speed of the engine and the temperature of the fuel; and the processing module calculates the actual fuel injection quantity through a neural network according to the first value, the relative pressure drop array, the accumulated sum, the engine speed and the fuel temperature.
9. An electronic device comprising a memory and a processor, the memory having stored therein a computer program, which when executed by the processor controls the execution of the method according to any of claims 1-7.
10. A computer readable storage medium, having stored thereon a computer program which, when executed in a computer, causes the computer to control the execution of the method of any of claims 1-7.

Description

Engine oil injection quantity determining method, device, equipment and storage medium Technical Field The application belongs to the field of oil injection control, and particularly relates to an engine oil injection quantity determining method, an engine oil injection quantity determining device, engine oil injection quantity determining equipment and a storage medium. Background Control of the engine fuel injection amount is used to manage the cyclical fuel injection amount by controlling the power-up time of the fuel injector by an Engine Controller (ECU) to achieve basic fuel injection control of the engine. Conventionally, the ECU controls the amount of fuel injected per cylinder per cycle by adjusting the power-up time of the fuel injector according to a preset fuel injection amount. The method precisely controls the opening time of the fuel injector through the electronic signal, thereby realizing the target setting of the fuel injection quantity under ideal conditions and achieving the effects of fuel economy and emission control. However, in the process of the power-on time control mode in the prior art, due to factors such as aging of an engine, production consistency deviation and the like, deviation exists between an actual fuel injection quantity and an ECU preset value, and a real-time measurement means is lacking on the engine, measurement can only be carried out by relying on an off-line fuel injector test bed, so that the fuel injection quantity deviation cannot be detected and corrected in time, and the running stability and performance of the engine are affected. Disclosure of Invention The application aims to overcome the defects in the prior art and provide a method, a device, equipment and a storage medium for determining the fuel injection quantity of an engine. The application provides a method for determining the fuel injection quantity of an engine, which comprises the following steps: Setting an angle range in a preset distance of a top dead center of each cylinder of the engine, and uniformly setting a plurality of sampling points in the angle range; acquiring rail pressure of a high-pressure common rail system from each sampling point to obtain an original rail pressure array; extracting a first value from the original rail pressure array as a working condition reference value; calculating a relative pressure drop array according to the original rail pressure array and the first value, wherein each element of the relative pressure drop array is obtained by subtracting the first value from the corresponding element of the original rail pressure array; Accumulating all elements of the relative pressure drop array, and calculating an accumulated sum; Synchronously recording the rotation speed of the engine and the temperature of the fuel; and calculating the actual fuel injection quantity through a neural network according to the first value, the relative pressure drop array, the accumulated sum, the engine speed and the fuel temperature. Optionally, the setting an angle range near the top dead center of each cylinder of the engine, and uniformly setting a plurality of sampling points in the angle range includes: The angle range is preset to include a crank angle range corresponding to the oil injection operation. Optionally, the setting an angle range near the top dead center of each cylinder of the engine, and uniformly setting a plurality of sampling points in the angle range includes: the plurality of sampling points are arranged in the angle range in an equally spaced manner. Optionally, extracting a first value from the original rail pressure array as a working condition reference value includes: The first value corresponds to an engine crankshaft angular position before injection begins. Optionally, calculating a relative pressure drop array from the original rail pressure array and the first value, wherein each element of the relative pressure drop array is obtained by subtracting the first value from a corresponding element of the original rail pressure array, comprising: the subtraction operation is applied point-by-point to each sampling point to generate the array of relative pressure drops. Optionally, accumulating all elements of the relative pressure drop array, and calculating an accumulated sum, including: the sum is obtained by summing all elements of the array of relative pressure drops. Optionally, calculating an actual fuel injection amount through a neural network according to the first value, the relative pressure drop array, the accumulated sum, the engine speed and the fuel temperature includes: the neural network includes an input layer, a hidden layer, and an output layer, wherein the input layer receives the first value, the array of relative pressure drops, the cumulative sum, the engine speed, and the fuel temperature. The application also provides an engine fuel injection quantity determining device, which comprises: the setting module is used for se