Intelligent dynamic cylinder deactivation algorithm for multi-cylinder diesel engine

Abstract

The invention discloses an intelligent dynamic cylinder deactivation algorithm for a multi-cylinder diesel engine, relates to the technical field of internal combustion engines, and solves the technical problem of unstable power output caused by lack of flexibility of an existing diesel engine cylinder deactivation strategy. The algorithm comprises the steps that the cylinder deactivation number is obtained, the accumulated cylinder deactivation frequency of each air cylinder is obtained, the cylinder deactivation priority is determined according to the accumulated cylinder deactivation frequency and the principle that the priority of the air cylinder with the minimum accumulated cylinder deactivation frequency is the highest, and cylinder deactivation operation is conducted according to the cylinder deactivation priority and the cylinder deactivation number. Uniform use of the air cylinders is achieved, energy conservation and emission reduction are achieved, the engine efficiency is improved, and the service life of the engine is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of internal combustion engines, and more particularly to an intelligent dynamic cylinder deactivation algorithm for a multi-cylinder diesel engine. Background Art

[0002] Cylinder deactivation technology, also known as variable displacement technology, means that when the engine is running under partial load, the fuel supply, ignition, intake and exhaust of some cylinders are cut off through relevant mechanisms, thus stopping their work and increasing the load rate of the remaining working cylinders to improve efficiency and reduce fuel consumption.

[0003] In existing cylinder deactivation technologies, although static or preset mode cylinder deactivation strategies have been adopted to optimize fuel economy and reduce emissions, these methods lack flexibility and cannot respond to subtle changes in engine operating conditions in real time. In addition, the aging degree of each cylinder is inconsistent, resulting in unstable power output. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide an intelligent dynamic cylinder deactivation algorithm for a multi-cylinder diesel engine in view of the deficiencies in the prior art, so as to solve the technical problem that the existing diesel engine cylinder deactivation strategy lacks flexibility and leads to unstable power output.

[0005] The present invention discloses an intelligent dynamic cylinder deactivation algorithm for a multi-cylinder diesel engine, the algorithm comprising: obtaining the number of deactivated cylinders, obtaining the cumulative number of cylinder deactivations for each cylinder, determining the cylinder deactivation priority based on the cumulative number of cylinder deactivations with the cylinder with the least cumulative number of cylinder deactivations having the highest priority, and performing cylinder deactivation operations based on the cylinder deactivation priority and the number of deactivated cylinders.

[0006] As a further improvement, the principle of giving the highest priority to the cylinder with the least cumulative number of cylinder stops is adopted. The cylinder with the least cumulative number of cylinder stops is determined as the highest priority, the cylinder with the most cumulative number of cylinder stops is determined as the lowest priority, and the priorities of the remaining cylinders with more cumulative number of cylinder stops decrease in sequence.

[0007] Furthermore, when the accumulated cylinder deactivation times of the two cylinders are the same, the cylinder deactivation frequencies of the two cylinders are obtained, and the cylinder deactivation frequencies of the two cylinders are compared, and the cylinder with the lowest cylinder deactivation frequency is given a high priority, and the cylinder with the highest cylinder deactivation frequency is given a low priority.

[0008] Furthermore, the method for obtaining the number of cylinder deactivation is:

[0009] The historical operating data of the engine and the real-time operating data of the engine are acquired, a working condition identification model is constructed according to the historical operating data of the engine, and the real-time operating data of the engine is analyzed according to the working condition identification model to obtain the number of cylinder deactivation.

[0010] Furthermore, the method for constructing the operating condition recognition model through the historical operation data of the engine is to set a driving cycle and a cylinder deactivation record database, obtain the cylinder deactivation number, the number of cylinder deactivation times corresponding to the cylinder deactivation number, and the cylinder deactivation frequency corresponding to the cylinder deactivation number of the historical operation data of the engine within the driving cycle, record the cylinder deactivation number, the number of cylinder deactivation times corresponding to the cylinder deactivation number, and the cylinder deactivation frequency corresponding to the cylinder deactivation number into the cylinder deactivation record database, and construct the operating condition recognition model through the cylinder deactivation record database.

[0011] Furthermore, a machine learning algorithm is used to construct the operating condition identification model.

[0012] Furthermore, the engine historical operation data includes engine speed, engine load, coolant temperature, exhaust temperature and intake pressure.

[0013] Beneficial Effects

[0014] The advantages of the present invention are:

[0015] The present invention obtains the number of cylinder deactivations and the cumulative number of cylinder deactivations of each cylinder, determines the cylinder deactivation priority based on the cumulative number of cylinder deactivations with the cylinder with the least cumulative number of cylinder deactivations having the highest priority, performs cylinder deactivation operations based on the cylinder deactivation priority and the number of cylinder deactivations, thereby achieving uniform use of cylinders, achieving energy conservation and emission reduction, improving engine efficiency and extending the service life of the engine. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart for determining cylinder deactivation priority in the dynamic cylinder deactivation algorithm of the present invention;

[0017] Figure 2 The present invention is a flow chart for determining the number of cylinder deactivation in the dynamic cylinder deactivation algorithm. DETAILED DESCRIPTION

[0018] The present invention will be further described below in conjunction with the embodiments, but it does not constitute any limitation to the present invention. Any limited number of modifications made by anyone within the scope of the claims of the present invention are still within the scope of the claims of the present invention.

[0019] See also Figure 1-2 The present invention provides an intelligent dynamic cylinder deactivation algorithm for a multi-cylinder diesel engine. The algorithm includes obtaining historical engine operation data and real-time engine operation data, building a working condition recognition model through the historical engine operation data, analyzing the real-time engine operation data through the working condition recognition model and obtaining an optimal cylinder deactivation strategy.

[0020] The operating condition recognition model is constructed based on the historical engine operating data, which includes engine speed, engine load, coolant temperature, exhaust temperature and intake pressure.

[0021] Collect engine operation data through the data collection and preprocessing module: The data collection and preprocessing module contains various sensors installed on the diesel engine, which are used to collect engine operation data in real time. The engine operation data includes speed, load, coolant temperature, exhaust temperature, and intake pressure. The data preprocessing steps include data cleaning, data denoising, and data normalization to ensure data quality and provide a reliable data foundation for subsequent machine learning model training.

[0022] In each driving cycle, the cylinder deactivation number and the cylinder deactivation number corresponding to the cylinder deactivation number are recorded in real time. The recorded data contains a time stamp for traceability and analysis.

[0023] Data storage: The recorded data is stored in a dedicated cylinder deactivation record database to ensure data integrity and security. The cylinder deactivation database supports efficient data query and update operations to quickly obtain and analyze cylinder deactivation history data.

[0024] The method for constructing a working condition recognition model for the historical operation data of the engine is to set up a driving cycle and a cylinder stop record database, obtain the cylinder stop number, the number of cylinder stops corresponding to the cylinder stop number, and the cylinder stop frequency corresponding to the cylinder stop number of the historical operation data of the engine within the driving cycle, record the cylinder stop number, the number of cylinder stops corresponding to the cylinder stop number, and the cylinder stop frequency corresponding to the cylinder stop number in the cylinder stop record database, and construct the working condition recognition model through the cylinder stop record database.

[0025] The optimal cylinder deactivation strategy is: setting cylinder deactivation priority, obtaining operating conditions and power requirements from the engine's real-time operating data, and the operating condition identification model determines the number of cylinders that need to be deactivated and the cylinder deactivation order based on cylinder deactivation priority, operating conditions and power requirements.

[0026] The principle is that the cylinder with the least cumulative cylinder deactivation times has the highest priority, and the cylinder with the most cumulative cylinder deactivation times has the lowest priority. The priorities of the remaining cylinders decrease in sequence with increasing cumulative cylinder deactivation times.

[0027] The method for setting the cylinder deactivation priority is as follows: obtaining the number of cylinder deactivations, obtaining the cumulative number of cylinder deactivations for each cylinder, and determining the cylinder deactivation priority according to the cumulative number of cylinder deactivations with the cylinder having the least cumulative number of cylinder deactivations having the highest priority. When there are two cylinders with the same cumulative number of cylinder deactivations, obtaining the cylinder deactivation frequencies of the two cylinders, comparing the cylinder deactivation frequencies of the two cylinders, the cylinder with the lowest cylinder deactivation frequency has a high priority, and the cylinder with the highest cylinder deactivation frequency has a low priority.

[0028] Build the operating condition recognition model through the machine learning model construction and application module: This module uses machine learning algorithms to build the operating condition recognition model. The model is trained using the engine's historical operating data so that the model can accurately identify the engine's real-time operating data.

[0029] The MPC algorithm module is used to analyze the real-time operating data of the engine: Based on the identification of the real-time operating conditions of the engine in the real-time operating data of the engine, the MPC algorithm module predicts and obtains the engine operating trend including load changes and speed fluctuations in the future. According to the predicted engine operating trend, the MPC algorithm analyzes and obtains the optimal cylinder deactivation strategy, that is, determines the number of cylinders that should be deactivated in the current and future period of time to minimize fuel consumption and emissions while ensuring stable engine operation. The MPC algorithm also considers the dynamic response characteristics and constraints of the engine (including NVH restrictions and emission restrictions) to ensure the feasibility and effectiveness of the cylinder deactivation strategy. The MPC algorithm is also called the model predictive control algorithm.

[0030] Cylinder stop record and maintenance module: This module is used to store the cylinder stop record database, which is used to store detailed information of each cylinder stop operation, including the cylinder stop number, the cylinder stop time corresponding to the cylinder stop number, and the cylinder stop number corresponding to the cylinder stop number.

[0031] Cylinder usage balance strategy module: Based on the cylinder deactivation record database, the cylinder usage balance algorithm module analyzes the cylinder deactivation history of each cylinder and obtains the cylinder deactivation frequency and cumulative cylinder deactivation times of each cylinder. When determining a new cylinder deactivation strategy, the cylinder usage balance algorithm module will give priority to cylinders with fewer cylinder deactivation times to achieve uniform use among cylinders.

[0032] The above is only a preferred embodiment of the present invention. It should be pointed out that for those skilled in the art, several modifications and improvements can be made without departing from the structure of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent.

Claims

1. An intelligent dynamic cylinder deactivation algorithm for a multi-cylinder diesel engine, characterized in that: The algorithm includes obtaining the number of cylinder deactivations, obtaining the cumulative number of cylinder deactivations for each cylinder, determining the cylinder deactivation priority based on the cumulative number of cylinder deactivations with the cylinder with the least cumulative number of cylinder deactivations having the highest priority, and performing cylinder deactivation operations based on the cylinder deactivation priority and the number of cylinder deactivations.

2. The intelligent dynamic cylinder deactivation algorithm for a multi-cylinder diesel engine according to claim 1, characterized in that: The principle of giving the highest priority to the cylinder with the least cumulative number of cylinder stops is that the cylinder with the least cumulative number of cylinder stops has the highest priority, the cylinder with the most cumulative number of cylinder stops has the lowest priority, and the priorities of the remaining cylinders with more cumulative number of cylinder stops decrease in sequence.

3. The intelligent dynamic cylinder deactivation algorithm for a multi-cylinder diesel engine according to claim 1, characterized in that: When the accumulated cylinder deactivation times of the two cylinders are the same, the cylinder deactivation frequencies of the two cylinders are obtained, and the cylinder deactivation frequencies of the two cylinders are compared, and the cylinder with the lowest cylinder deactivation frequency is given a high priority, and the cylinder with the highest cylinder deactivation frequency is given a low priority.

4. The intelligent dynamic cylinder deactivation algorithm for a multi-cylinder diesel engine according to claim 1, characterized in that: The method for obtaining the cylinder shutdown quantity is: The historical operating data of the engine and the real-time operating data of the engine are acquired, a working condition identification model is constructed according to the historical operating data of the engine, and the real-time operating data of the engine is analyzed according to the working condition identification model to obtain the number of cylinder deactivation.

5. The intelligent dynamic cylinder deactivation algorithm for a multi-cylinder diesel engine according to claim 4, characterized in that: The method for constructing the operating condition recognition model through the historical operation data of the engine is as follows: setting a driving cycle and a cylinder deactivation record database, obtaining the cylinder deactivation number, the number of cylinder deactivation times corresponding to the cylinder deactivation number, and the cylinder deactivation frequency corresponding to the cylinder deactivation number of the historical operation data of the engine in the driving cycle, recording the cylinder deactivation number, the number of cylinder deactivation times corresponding to the cylinder deactivation number, and the cylinder deactivation frequency corresponding to the cylinder deactivation number in the cylinder deactivation record database, and constructing the operating condition recognition model through the cylinder deactivation record database.

6. The intelligent dynamic cylinder deactivation algorithm for a multi-cylinder diesel engine according to claim 5, characterized in that: A machine learning algorithm is used to construct the operating condition identification model.

7. The intelligent dynamic cylinder deactivation algorithm for a multi-cylinder diesel engine according to claim 4, characterized in that: The historical engine operation data includes engine speed, engine load, coolant temperature, exhaust temperature and intake pressure.

Images