Method and system for ultrasonic dynamic liquid level measurement based on neural network

Abstract

The invention discloses a method for ultrasonic dynamic liquid level measurement based on a neural network. The method comprises the steps that a single-chip microcomputer transmits control signals to three ultrasonic sensors, a timer is started to begin timing simultaneously, and a pulse ultrasonic wave is generated simultaneously; the ultrasonic sensors convert echo signals into voltage signals and transmit the voltage signals to a front pre-amplification circuit, the voltage signals are transmitted to an ultrasonic wave receiving and detecting circuit after being amplified through the pre-amplification circuit, and envelope detection of the high-frequency input signals is achieved; a receiving and comparing circuit compares the voltage signals generated after detection conducted by an envelope detection circuit with the reference voltage set by a system, and digital signals are output according to the comparison result; after an external interrupt control interface receives an effective falling edge, the single-chip microcomputer generates interruption, the value, existing at present, of the timer is recorded, a mean value and the shaking gradient are used as input parameters needed by the neural network, the two parameters are transmitted to a neural network mathematic module which is well trained, and the output values of the neural network are obtained.

Description

technical field [0001] The invention relates to a detection field, in particular to an ultrasonic dynamic liquid level detection method and system based on a neural network. Background technique [0002] The liquid will visibly slosh during transportation, and the real-time dynamic monitoring of the liquid level has always been a technical problem, which has not been well solved so far. [0003] In the prior art, there are many methods for detecting the liquid level in the transportation process, for example: a dynamic liquid level monitoring method based on a single ultrasonic sensor. Then use the wavelet filter method to smooth the time-of-arrival curve extracted from the echo signal, combine the motion acceleration of the moving object, the ambient temperature and other parameters, use the support vector machine technology to classify and identify the motion state and mode, and get the dynamic level value. However, this method also has shortcomings. First, the ultrasoni...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the problem that the current liquid level detection accuracy is not high during the transportation process of liquid, and it

Images