Internal combustion engine cooling water flow intelligent control method based on RBF neutral network
A cooling water flow and intelligent control technology, applied in the direction of coolant flow control, neural learning method, biological neural network model, etc., can solve the problems of power reduction, exhaust emission deterioration, increased fuel consumption, etc., to reduce parts wear Aggravate and reduce the degree of environmental pollution and reduce the effect of exhaust emission deterioration
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0045] This embodiment is an intelligent control method for cooling water flow of an internal combustion engine based on RBF neural network, and its control process is as follows figure 1 As shown, the method includes the following steps:
[0046] Step 1: Determine the temperature sampling frequency, and use the temperature sensor to measure the water temperature data of the internal combustion engine running for a period of time. The length of this segment of data is fixed at n, and the initial data is discarded for each update, and finally a binary data consisting of water temperature and water temperature change rate is formed. Dimensional data set; and then divided into training set and test set after normalized preprocessing. The division method is to divide the two-dimensional data set with a fixed length of n, the first n-1 columns are used as the training set, and the last 2 columns are used as the test set; the training set is processed in groups of two columns, and t...
Embodiment 2
[0079] This embodiment is a practical detection of the RBF neural network-based intelligent control method for cooling water flow of an internal combustion engine described in Embodiment 1. An internal combustion engine cooling water fluid control valve capable of implementing the intelligent control method for internal combustion engine cooling water flow described in Embodiment 1 will be provided, and its structure is as follows: image 3 As shown, the water inlet of the control valve assembly of the vehicle cooling cycle control system is connected to the water outlet of the engine, and the large cycle water outlet of the control valve assembly of the vehicle cooling cycle control system is connected to the water inlet of the water tank radiator. Install it on the car and send it to "Heilongjiang Auto Product Quality Supervision and Inspection Station" for testing.
[0080] The car model used in this embodiment: Haoluo ZZ3317N3867C1;
[0081] Engine model: WD615.96E;
[0...
Embodiment 3
[0088] This embodiment is to conduct a further actual test on the RBF neural network-based intelligent control method for the cooling water flow of the internal combustion engine described in Embodiment 1, and evaluate its effect on the water temperature control of the internal combustion engine.
[0089] The basic information of the test in this example is shown in Table 1. The test time was June 2018, the test vehicle was the same, the driver was the same, and the set target temperature range was: 60°C to 80°C.
[0090]The test results are shown in Table 2, where the average temperature rise rate refers to the average temperature rise rate from the start of the car until the water temperature rises to 70°C; The length of time the water temperature is maintained at 80°C or above.
[0091] Table 1. Basic information
[0092]
[0093] Table 2. Adopting the method of the present invention and not adopting the comparison of vehicle internal combustion engine operating paramet...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com