CN-121978695-A - Ultrasonic signal processing method, device, equipment and storage medium

CN121978695ACN 121978695 ACN121978695 ACN 121978695ACN-121978695-A

Abstract

The invention discloses a method, a device, equipment and a storage medium for processing ultrasonic signals. The method comprises the steps of inputting environmental noise and random noise into a generating network to generate Pulse Width Modulation (PWM) coding parameters, generating ultrasonic signals based on the PWM coding parameters and transmitting the ultrasonic signals, collecting echo signals, inputting the echo signals and the ultrasonic signals into a recognition network to output a first recognition result, and determining a target distance based on the receiving time of the echo signals and the transmitting time of the ultrasonic signals if the recognition result is that the echo signals are the echo signals corresponding to the ultrasonic signals. Breaks through the dependence on high-performance modulation hardware, realizes the automatic generation of PWM (pulse-width modulation) coded ultrasonic signals with high uniqueness and strong anti-interference capability, and realizes the high-precision detection and matching of echo signals, thereby remarkably improving the detection precision, the robustness and the real-time processing capability of an ultrasonic radar system in a complex dynamic environment.

Inventors

HU WEI
YE CHEN
WANG CHEN
XIA QING
XU HUILI
YANG ZIYU

Assignees

上海智位机器人股份有限公司

Dates

Publication Date: 20260505
Application Date: 20260202

Claims (10)

1. A method of processing an ultrasonic signal, comprising: inputting the environmental noise and the random noise into a generating network to generate Pulse Width Modulation (PWM) coding parameters, wherein the PWM coding parameters comprise at least one of frequency, duty cycle and modulation sequence; generating an ultrasonic signal based on the PWM encoding parameter and transmitting the ultrasonic signal; Collecting echo signals, inputting the echo signals and the ultrasonic signals into an identification network, and outputting a first identification result, wherein the first identification result comprises whether the echo signals are echo signals corresponding to the ultrasonic signals and the confidence; and if the identification result is that the echo signal is the echo signal corresponding to the ultrasonic signal, determining the target distance based on the receiving time of the echo signal and the transmitting time of the ultrasonic signal.
2. The method of claim 1, wherein inputting the echo signal and the ultrasonic signal into an identification network and outputting a first identification result comprises: performing Fourier transform on the echo signals to obtain echo frequency domain signals; Filtering the echo signals to obtain filtered echo time domain signals; And inputting the echo frequency domain signal, the echo time domain signal and the ultrasonic signal into an identification network, and outputting a first identification result.
3. The method of claim 2, wherein the identification network comprises a time domain processing sub-network, a frequency domain processing sub-network, a signal comparison sub-network, and a fusion discrimination sub-network, wherein inputting the echo frequency domain signal, the echo time domain signal, and the ultrasonic signal into the identification network, outputting a first identification result comprises: performing feature extraction on the echo time domain signal based on the time domain processing sub-network to obtain echo time domain features; Extracting features of the echo frequency domain signals based on the frequency domain processing sub-network to obtain echo frequency domain features; Processing the echo time domain signal and the ultrasonic signal based on a signal comparison sub-network to obtain comparison characteristics; and carrying out fusion judgment on the echo time domain feature, the echo frequency domain feature and the comparison feature based on a fusion judgment sub-network to obtain a first recognition result.
4. The method of claim 1, wherein the identification network comprises an input layer, a hidden layer, and an output layer, wherein inputting the echo signal and the ultrasonic signal into the identification network, outputting a first identification result, comprises: combining the echo signal and the ultrasonic signal based on the input layer to obtain a combined signal, wherein the combined process is splicing process or differential process; Extracting features of the combined signal based on the hidden layer to obtain time-frequency features; And processing the time-frequency characteristic based on the input layer to obtain a first recognition result.
5. The method of claim 1, further comprising, after determining a target distance based on the time of receipt of the echo signal and the time of transmission of the ultrasonic signal: Acquiring a signal quality evaluation index, wherein the signal quality evaluation index comprises at least one of the type of the environmental noise, the amplitude of the ultrasonic signal, the intercepted times of the ultrasonic signal and the signal-to-noise ratio of the echo signal; and adjusting PWM coding parameters generated next time based on the signal quality evaluation quality and the confidence.
6. The method of claim 5, wherein adjusting the PWM encoding parameters for the next generation based on the signal quality assessment quality and the confidence comprises: If the signal-to-noise ratio of the echo signal is smaller than a first set value and the confidence coefficient is smaller than a second set value, executing at least one adjustment strategy as follows: If the type of the environmental noise is low frequency noise, the frequency is increased, or If the amplitude of the ultrasonic signal is smaller than a third set value, the duty ratio is increased, or And randomizing the modulation sequence if the intercepted times of the ultrasonic signals exceeds a set threshold value.
7. The method according to claim 1, wherein the training of the generating network and the identifying network is: acquiring a noise sample set; Inputting the noise sample set into the generating network and outputting a PWM coding parameter sample set; generating an ultrasonic wave sample set based on the PWM coding parameter sample set, and simulating an echo sample set corresponding to the ultrasonic wave sample set; combining the ultrasonic samples and the echo samples in pairs to obtain sample pairs, and adding labels to the sample pairs, wherein the sample pairs comprise positive sample pairs and negative sample pairs; inputting the sample pair into the recognition network, and outputting a second recognition result, wherein the second recognition result comprises whether the echo sample is an echo sample corresponding to the ultrasonic sample and a confidence level; And performing cooperative training on the generating network and the identification network based on the second identification result, the label and the confidence.
8. An ultrasonic signal processing apparatus, comprising: the PWM coding parameter generation module is used for inputting the environmental noise and the random noise into the generation network to generate pulse width modulation PWM coding parameters, wherein the PWM coding parameters comprise at least one of frequency, duty ratio and modulation sequence; The ultrasonic signal generation module is used for generating an ultrasonic signal based on the PWM coding parameters and transmitting the ultrasonic signal; The first recognition result determining module is used for acquiring echo signals, inputting the echo signals and the ultrasonic signals into a recognition network and outputting a first recognition result, wherein the first recognition result comprises whether the echo signals are echo signals corresponding to the ultrasonic signals and the confidence level; And the target distance determining module is used for determining the target distance based on the receiving time of the echo signal and the transmitting time of the ultrasonic signal if the identification result is that the echo signal is the echo signal corresponding to the ultrasonic signal.
9. An electronic device, the electronic device comprising: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of processing an ultrasonic signal according to any one of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores computer instructions for causing a processor to execute the method of processing an ultrasonic signal according to any one of claims 1-7.

Description

Ultrasonic signal processing method, device, equipment and storage medium Technical Field The embodiment of the invention relates to the technical field of signal processing, in particular to a method, a device, equipment, a storage medium and a program product for processing an ultrasonic signal. Background Along with the rapid development of the fields of intelligent robots, automatic driving, industrial automation and the like, the ultrasonic radar becomes an important means for space perception and target detection due to low cost, low power consumption and strong environmental adaptability. The traditional ultrasonic radar system generally adopts hardware schemes such as frequency Modulation (Frequency Modulation, FM), phase Modulation (PM) and the like, and improves the anti-interference capability and the ranging accuracy of signals through a specific coding mode. However, such schemes often rely on dedicated high performance hardware (e.g., high precision DDS chips, complex analog front ends), resulting in higher overall system costs and difficulty in popularizing on large-scale low cost terminals or embedded platforms. In addition, the existing signal generation modes such as PWM coding are mostly static designs, and when facing to complex and changeable practical application scenes, the existing signal generation modes are limited in anti-interference capability and signal uniqueness, and the problems of false alarm, missing detection and the like are easy to occur. Disclosure of Invention The embodiment of the invention provides a processing method, a device, equipment and a storage medium for ultrasonic signals, which can improve the detection precision, robustness and real-time processing capability of an ultrasonic radar system in a complex dynamic environment. In a first aspect, an embodiment of the present invention provides a method for processing an ultrasonic signal, including: inputting the environmental noise and the random noise into a generating network to generate Pulse Width Modulation (PWM) coding parameters, wherein the PWM coding parameters comprise at least one of frequency, duty cycle and modulation sequence; generating an ultrasonic signal based on the PWM encoding parameter and transmitting the ultrasonic signal; Collecting echo signals, inputting the echo signals and the ultrasonic signals into an identification network, and outputting a first identification result, wherein the first identification result comprises whether the echo signals are echo signals corresponding to the ultrasonic signals and the confidence; and if the identification result is that the echo signal is the echo signal corresponding to the ultrasonic signal, determining the target distance based on the receiving time of the echo signal and the transmitting time of the ultrasonic signal. In a second aspect, an embodiment of the present invention further provides an apparatus for processing an ultrasonic signal, including: the PWM coding parameter generation module is used for inputting the environmental noise and the random noise into the generation network to generate pulse width modulation PWM coding parameters, wherein the PWM coding parameters comprise at least one of frequency, duty ratio and modulation sequence; The ultrasonic signal generation module is used for generating an ultrasonic signal based on the PWM coding parameters and transmitting the ultrasonic signal; The first recognition result determining module is used for acquiring echo signals, inputting the echo signals and the ultrasonic signals into a recognition network and outputting a first recognition result, wherein the first recognition result comprises whether the echo signals are echo signals corresponding to the ultrasonic signals and the confidence level; And the target distance determining module is used for determining the target distance based on the receiving time of the echo signal and the transmitting time of the ultrasonic signal if the identification result is that the echo signal is the echo signal corresponding to the ultrasonic signal. In a third aspect, an embodiment of the present invention further provides an electronic device, including: at least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method for processing an ultrasonic signal according to the embodiment of the present invention. In a fourth aspect, an embodiment of the present invention further provides a computer readable storage medium, where the computer readable storage medium stores computer instructions, where the computer instructions are configured to cause a processor to execute the method for processing an ultrasonic signal according to the embodiment of the present invention. In a fifth aspect, an embodiment of the present invention further provides a computer program produc