Through the use of intermittent oil sampling and testing of various key characteristics

 

The advantage of the neural network model is that, unlike traditional computer programs, it does not incorporate fixed mathematical algorithms to solve specific problems. It is intelligent programming. Under normal circumstances, when the data does not have a simple form, or the appropriate equation is a higher degree polynomial, ordinary statistical modeling may have limitations in accuracy. Artificial neural networks use learning algorithms to find the best solution. The neural network system trains itself by learning samples. When each set of data is input, the difference between the actual output of the network and the desired output is used to modify the connection weight, the modification of the connection weight or the training of the network Continue until the actual output of all samples is consistent with the desired output within a certain limit. At this time, it can be said that the neural network has been trained and is ready to accept new inputs that need to be solved.

Data flow of artificial neural network Figure 2 BP algorithm and application examples The BP neural network is used to estimate the service life of lubricating oil. The BP neural network is currently a widely used neural network. It has been theoretically proven that a 3-layer BP network can approximate any insinuation relationship with arbitrary precision. The application of BP network to estimate the service life of lubricating oil can be divided into three stages: one is to establish a learning sample stage, which is established by using intermittent oil sampling and testing various key characteristics, such as viscosity, flash point, water content, and insoluble The second is the network training stage, the training of the network model is based on each characteristic, the input value of the network is taken as the test result of each characteristic, and the output value is taken as the corresponding test result of each characteristic Sampling time, the training of the network continues until convergence; the third is the network working phase, that is, the estimated service life phase. When the trained BP network is used to solve the service life of the lubricant, the service life of the lubricant can be defined as the network The minimum value of all output values ​​(limit use time) above.

The automotive parts and parts machining, PTJ Shop offers the highest degree of OEM service with a basis of 10+ years experience serving the automotive industry. Our automotive precision shop and experts deliver confidence. We have perfected the art of producing large component volumes with complete JIT reliability, backed by the quality and long-term reliability our customers expect.

Link to this article:Through the use of intermittent oil sampling and testing of various key characteristics

Reprint Statement: If there are no special instructions, all articles on this site are original. Please indicate the source for reprinting.:Cnc Machining,Thank

Bookmark the permalink.

Comments are closed.