CN118817828A - Method and system for non-invasive liquid detection - Google Patents

Abstract

The present application provides a method and system for non-invasive fluid detection, comprising: collecting a first detection signal set through a first microphone and a second microphone, and collecting a second detection signal set through the first microphone and the second microphone; preprocessing the first detection signal set and the second detection signal set respectively to obtain a first pure detection signal set and a second pure detection signal set; performing differential processing on the first pure detection signal set and the second pure detection signal set to obtain differential amplitude signals of the liquid to be detected; and obtaining the characteristics of the differential amplitude signals, comparing the characteristics of the differential amplitude signals with a preset characteristic database, and determining the category of the liquid to be detected according to the comparison result. The liquid classification method with high accuracy is realized through simple and convenient sound wave signal acquisition equipment.

Description

Method and system for non-invasive liquid detection

Technical Field

The present application belongs to the field of machine learning, and more particularly to methods and systems for non-invasive liquid detection.

Background Art

In recent years, with the continuous development of science and technology, various research results on liquid detection have emerged in an endless stream, and liquid detection technology has been widely used in food safety, medical and health care, environmental protection and industrial production. In the field of food safety, industrial and commercial law enforcement personnel often need to conduct random inspections on beverages and foods sold on the market to detect whether the content of additives used meets national standards, crack down on illegal acts of abusing food additives, and thus establish a safe market environment. In the field of medical and health care, by testing the patient's body fluid composition, such as blood routine and urine routine tests, doctors can understand the patient's condition more comprehensively and accurately, so as to make more reasonable treatment plans. In the field of ecological and environmental protection, people need to regularly test the water quality components in rivers and lakes to determine whether the waters are polluted. In industrial production, by real-time monitoring of the composition, concentration and other parameters of the liquid during the production process, workers can adjust the operating conditions in a timely manner to ensure the consistency and quality of the products produced and prevent the production of defective products.

Currently, the commonly used liquid detection methods mainly include chemical analysis, mass spectrometry and radio frequency signal detection. The chemical analysis method requires the collection of samples in a professional laboratory for testing and analysis, and its detection cycle is long and the efficiency is low. The mass spectrometry method relies on expensive professional equipment such as mass spectrometers, and also needs to be operated in the laboratory. Moreover, both methods have the disadvantages of cumbersome detection steps and the need for professional personnel to operate, making it difficult to achieve convenient and efficient liquid detection. In addition, both methods are invasive detection, which can easily lead to waste of the tested samples. In contrast, the detection method based on radio frequency signals can achieve non-invasive detection of liquids. However, this method still requires expensive equipment, and is limited by the shielding effect of metal on electromagnetic waves, and cannot effectively detect liquids in metal containers.

Summary of the invention

The main purpose of the embodiments of the present invention is to provide a method and system for non-invasive liquid detection, and to provide a technical solution with simple required equipment and accurate classification results. A high-accuracy liquid classification method is achieved through a simple acoustic wave signal acquisition device.

In a first aspect, a method for non-invasive liquid detection is provided, the method comprising:

A first detection signal set is collected by a first microphone and a second microphone after a sound wave signal sent from a speaker at a first position passes through a container and a liquid to be detected loaded in the container, and a second detection signal set is collected by the first microphone and the second microphone after the sound wave signal sent from the speaker at a second position passes through the container and the liquid to be detected, the first position is a position where a first distance and a second distance are the same, the second position is a position where the first distance and the second distance are different, the first distance is a distance between the speaker and the first microphone, the second distance is a distance between the speaker and the second microphone, and the first microphone and the second microphone are arranged at mirror positions with the container as a mirror surface;

Preprocessing the first detection signal set and the second detection signal set respectively to obtain a first clean detection signal set and a second clean detection signal set;

Performing differential processing on the first pure detection signal set and the second pure detection signal set to obtain a differential amplitude signal of the liquid to be detected;

The characteristics of the differential amplitude signal are acquired, and the characteristics of the differential amplitude signal are compared with a preset characteristic database, and the category of the liquid to be detected is determined according to the comparison result.

In a possible implementation, the first detection signal set after the sound wave signal sent from the speaker at the first position passes through the container and the liquid to be detected loaded in the container is collected by the first microphone and the second microphone, and the second detection signal set after the sound wave signal sent from the speaker at the second position passes through the container and the liquid to be detected is collected by the first microphone and the second microphone, includes:

placing the speaker at the first position;

Start the speaker disposed at the first position, collect a first microphone signal formed after the sound wave signal passes through the liquid to be detected through the first microphone, and collect a second microphone signal formed after the sound wave signal passes through the liquid to be detected through the second microphone, the first microphone signal and the second microphone signal together forming the first detection signal set;

placing the speaker at the second position;

Start the speaker set at the second position, collect the third microphone signal formed after the sound wave signal passes through the liquid to be detected through the first microphone, and collect the fourth microphone signal formed after the sound wave signal passes through the liquid to be detected through the second microphone, the third microphone signal and the fourth microphone signal together form the second detection signal set.

In a possible implementation, preprocessing the first detection signal set and the second detection signal set to obtain a first clean detection signal set and a second clean detection signal set respectively includes:

Performing bandpass filtering on the first microphone signal, the second microphone signal, the third microphone signal and the fourth microphone signal through a bandpass filter to obtain a first filtered signal, a second filtered signal, a third filtered signal and a fourth filtered signal;

The first filtered signal, the second filtered signal, the third filtered signal and the fourth filtered signal are subjected to Fourier transform to obtain a first frequency domain signal, a second frequency domain signal, a third frequency domain signal and a fourth frequency domain signal, wherein the first pure detection signal set includes the first frequency domain signal and the second frequency domain signal, and the second pure detection signal set includes the third frequency domain signal and the fourth frequency domain signal.

In a possible implementation, performing differential processing on the first pure detection signal set and the second pure detection signal set to obtain the differential amplitude signal of the liquid to be detected includes:

Obtaining a first difference between the first frequency domain signal and the second frequency domain signal, and obtaining a second difference between the third frequency domain signal and the fourth frequency domain signal;

The first difference is differentiated from the second difference to obtain the differential amplitude signal.

In a second aspect, a system for non-invasive liquid detection is provided, the system comprising:

A detection signal acquisition module, used to acquire a first detection signal set after the sound wave signal sent by the speaker from the first position passes through the liquid to be detected, and to acquire a second detection signal set after the sound wave signal sent by the speaker from the second position passes through the liquid to be detected;

A clean detection signal set acquisition module, used to pre-process the first detection signal set and the second detection signal set to obtain a first clean detection signal set and a second clean detection signal set;

A differential amplitude signal acquisition module, used for performing differential processing on the first pure detection signal set and the second pure detection signal set to acquire a differential amplitude signal of the liquid to be detected;

The category determination module is used to obtain the characteristics of the differential amplitude signal, and compare the characteristics of the differential amplitude signal with a preset characteristic database, and determine the category of the liquid to be detected according to the comparison result.

In a possible implementation, the detection signal acquisition module includes:

A first position setting unit, used to set the speaker at the first position which is the same as the first microphone and the second microphone;

A first and second microphone signal collection unit, used to start a speaker arranged at the first position, collect a first microphone signal formed after the sound wave signal passes through the liquid to be detected through the first microphone, and collect a second microphone signal formed after the sound wave signal passes through the liquid to be detected through the second microphone, the first microphone signal and the second microphone signal together forming the first detection signal set;

A second position setting unit, configured to set the speaker at a second position different from positions of the first microphone and the second microphone;

The third and fourth microphone signal acquisition units are used to start the speaker set at the second position, and collect the third microphone signal formed after the sound wave signal passes through the liquid to be detected through the first microphone, and collect the fourth microphone signal formed after the sound wave signal passes through the liquid to be detected through the second microphone. The third microphone signal and the fourth microphone signal together form the second detection signal set.

In a possible implementation, the clean detection signal set acquisition module includes:

a filter signal acquisition unit, configured to perform bandpass filtering on the first microphone signal, the second microphone signal, the third microphone signal and the fourth microphone signal through a bandpass filter to acquire a first filter signal, a second filter signal, a third filter signal and a fourth filter signal;

A frequency domain signal acquisition unit is used to perform Fourier transform on the first filtered signal, the second filtered signal, the third filtered signal and the fourth filtered signal to obtain a first frequency domain signal, a second frequency domain signal, a third frequency domain signal and a fourth frequency domain signal, wherein the first pure detection signal set includes the first frequency domain signal and the second frequency domain signal, and the second pure detection signal set includes the third frequency domain signal and the fourth frequency domain signal.

In a possible implementation, the differential amplitude signal acquisition module includes:

A difference acquisition unit, configured to acquire a first difference between the first frequency domain signal and the second frequency domain signal, and acquire a second difference between the third frequency domain signal and the fourth frequency domain signal;

The differential amplitude signal acquisition unit is used to differentiate the first difference from the second difference to acquire the differential amplitude signal.

In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for non-invasive liquid detection as provided in the first aspect is implemented.

In a fourth aspect, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the method for non-invasive liquid detection as provided in the first aspect is implemented.

In the present application, a technical solution is provided which requires simple equipment and has accurate classification results. A liquid classification method with high accuracy is achieved through a simple acoustic wave signal acquisition device.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in describing the embodiments of the present application are briefly introduced below.

FIG1 is a flow chart of a non-invasive liquid detection method provided by one embodiment of the present invention;

FIG2 is a flow chart of a non-invasive liquid detection method provided by another embodiment of the present invention;

FIG3 is a schematic diagram of a speaker provided in different positions according to an embodiment of the present invention;

FIG4 is a flow chart of a non-invasive liquid detection method provided by another embodiment of the present invention;

FIG5 is a flow chart of a non-invasive liquid detection method provided by another embodiment of the present invention;

FIG6 is a structural diagram of a system for non-invasive liquid detection provided by an embodiment of the present invention;

FIG7 is a structural diagram of a non-invasive liquid detection system provided by another embodiment of the present invention;

FIG8 is a structural diagram of a non-invasive liquid detection system provided by another embodiment of the present invention;

FIG9 is a structural diagram of a non-invasive liquid detection system provided by another embodiment of the present invention;

FIG. 10 is a schematic diagram of the physical structure of an electronic device provided by the present invention.

DETAILED DESCRIPTION

The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar modules or modules with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present invention.

It will be understood by those skilled in the art that, unless expressly stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, modules and/or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, modules, components and/or groups thereof. It should be understood that when we refer to a module as being "connected" or "coupled" to another module, it may be directly connected or coupled to the other modules, or there may be intermediate modules. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and/or" used herein includes all or any modules and all combinations of one or more associated listed items.

In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation method of the present application will be further described in detail below in conjunction with the accompanying drawings.

The technical solution of the present application and how to solve the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

FIG1 is a flow chart of a non-invasive liquid detection method provided by an embodiment of the present invention, wherein the method comprises:

Step S101, collecting a first detection signal set after a sound wave signal sent from a speaker at a first position passes through a container and a liquid to be detected loaded in the container through a first microphone and collecting a second detection signal set after the sound wave signal sent from the speaker at a second position passes through the container and the liquid to be detected through the first microphone and the second microphone, wherein the first position is a position where a first distance and a second distance are the same, and the second position is a position where the first distance and the second distance are different, the first distance is a distance between the speaker and the first microphone, and the second distance is a distance between the speaker and the second microphone, and the first microphone and the second microphone are arranged at mirror positions with the container as a mirror surface;

Step S102, preprocessing the first detection signal set and the second detection signal set to obtain a first clean detection signal set and a second clean detection signal set;

Step S103, performing differential processing on the first pure detection signal set and the second pure detection signal set to obtain a differential amplitude signal of the liquid to be detected;

Step S104, acquiring the characteristics of the differential amplitude signal, and comparing the characteristics of the differential amplitude signal with a preset characteristic database, and determining the category of the liquid to be detected according to the comparison result.

In the embodiment of the present invention, a sound-generating device (such as a speaker) is set at a first position and generates a sound wave signal. After the sound wave signal passes through the loading container and the liquid to be detected in the loading container, a first detection signal set is generated. The first detection signal set is acquired by a sound-receiving device (such as a microphone) set at a corresponding position. Similarly, a sound-generating device is set at a second position and generates a sound wave signal. After the sound wave signal passes through the loading container and the liquid to be detected in the loading container, a second detection signal set is generated. The second detection signal set is acquired by a sound-receiving device set at a corresponding position.

Since the first detection signal set and the second detection signal set obtained contain many interference signals, the accuracy of the detection results is low if they are directly used for liquid detection. Therefore, it is necessary to preprocess the first detection signal set and the second detection signal set to remove the interference signals and obtain the first pure detection signal set and the second pure detection signal set.

By performing differential processing on the obtained first pure detection signal set and the second pure detection signal set, the differential amplitude signal of the liquid to be detected can be obtained.

The characteristics of the differential amplitude signal are obtained and compared with a pre-set characteristic database, which stores the characteristics corresponding to the differential amplitude signals of various liquids obtained through the above process. The characteristics of the differential amplitude signal of the liquid to be detected are input into the characteristic database to obtain the corresponding liquid category.

Wherein, the step of obtaining the characteristic of the differential amplitude signal includes:

The Transformer feature extraction module is subjected to machine learning, and the features of the differential amplitude signal are extracted by completing the machine learning Transformer feature extraction module.

In an embodiment of the present invention, a first detection signal set is collected after the sound wave signal sent by the speaker from the first position passes through the liquid to be detected, and a second detection signal set is collected after the sound wave signal sent by the speaker from the second position passes through the liquid to be detected; the first detection signal set and the second detection signal set are preprocessed respectively to obtain a first pure detection signal set and a second pure detection signal set; the first pure detection signal set and the second pure detection signal set are differentially processed to obtain a differential amplitude signal of the liquid to be detected; the feature of the differential amplitude signal is obtained, and the feature of the differential amplitude signal is compared with a preset feature database, and the category of the liquid to be detected is determined according to the comparison result. A technical solution is provided with simple required equipment and accurate classification results, and a high-accuracy liquid classification method is realized through a simple sound wave signal collection device.

FIG2 is a flow chart of a non-invasive liquid detection method provided by another embodiment of the present invention, wherein the first microphone and the second microphone collect a first detection signal set after the sound wave signal sent by the speaker from the first position passes through the container and the liquid to be detected loaded in the container, and the first microphone and the second microphone collect a second detection signal set after the sound wave signal sent by the speaker from the second position passes through the container and the liquid to be detected, including:

Step S201, setting the speaker at the first position;

Step S202, starting the speaker disposed at the first position, collecting a first microphone signal formed after the sound wave signal passes through the liquid to be detected through the first microphone, and collecting a second microphone signal formed after the sound wave signal passes through the liquid to be detected through the second microphone, the first microphone signal and the second microphone signal together forming the first detection signal set;

Step S203, setting the speaker at the second position;

Step S204, start the speaker set at the second position, collect the third microphone signal formed after the sound wave signal passes through the liquid to be detected through the first microphone, and collect the fourth microphone signal formed after the sound wave signal passes through the liquid to be detected through the second microphone, the third microphone signal and the fourth microphone signal together form the second detection signal set.

Referring to Fig. 3, which is a schematic diagram of the speaker in the first position and the second position, when the speaker is set at the first position, the distance from the first microphone and the second microphone is the same. At this time, after the sound wave signal generated by the speaker passes through the container and the liquid to be detected, the first microphone and the second microphone receive the first microphone signal and the second microphone signal respectively. When the speaker is set at the second position, the distance from the first microphone and the second microphone is different. At this time, after the sound wave signal generated by the speaker passes through the container and the liquid to be detected, the first microphone and the second microphone receive the third microphone signal and the fourth microphone signal respectively.

FIG4 is a flowchart of a non-invasive liquid detection method according to another embodiment of the present invention, wherein the preprocessing of the first detection signal set and the second detection signal set to obtain a first pure detection signal set and a second pure detection signal set comprises:

Step S401, performing bandpass filtering on the first microphone signal, the second microphone signal, the third microphone signal and the fourth microphone signal through a bandpass filter to obtain a first filtered signal, a second filtered signal, a third filtered signal and a fourth filtered signal;

Step S402, performing Fourier transform on the first filtered signal, the second filtered signal, the third filtered signal and the fourth filtered signal to obtain a first frequency domain signal, a second frequency domain signal, a third frequency domain signal and a fourth frequency domain signal, the first pure detection signal set includes the first frequency domain signal and the second frequency domain signal, and the second pure detection signal set includes the third frequency domain signal and the fourth frequency domain signal.

In an embodiment of the present invention, a bandpass filter can perform bandpass filtering on the first filter signal, the second filter signal, the third filter signal, and the fourth filter signal to remove environmental noise during signal acquisition and accurately extract signal components within a preset frequency range. The first frequency domain signal, the second frequency domain signal, the third frequency domain signal, and the fourth frequency domain signal that have been accurately extracted are converted into corresponding frequency domain expressions through Fourier transform, so as to facilitate the subsequent steps to extract signal features through frequency domain expressions.

FIG5 is a flow chart of a non-invasive liquid detection method provided by another embodiment of the present invention, wherein the differential processing of the first pure detection signal set and the second pure detection signal set to obtain the differential amplitude signal of the liquid to be detected includes:

Step S501, obtaining a first difference between the first frequency domain signal and the second frequency domain signal, and obtaining a second difference between the third frequency domain signal and the fourth frequency domain signal;

Step S502: Differentiate the first difference from the second difference to obtain the differential amplitude signal.

In the embodiment of the present invention, the differential processing can eliminate the influence caused by the different frequency responses of the speaker and the microphone, and can eliminate the influence of different containers on the detection results.

The signal collected by the microphone can be expressed as: ,in, is the frequency domain representation of the signal received by the microphone, is the frequency domain representation of the sound wave signal sent by the speaker, is the frequency response of the loudspeaker, is the frequency response of the microphone, is the frequency response of the liquid, is the effect of the container material on the signal when the signal passes through the container, It represents the additional influence caused by the different thickness of the container walls on both sides and the position error caused by the artificial installation of speakers and microphones. It is random and different in each test.

When the loudspeaker is set at the first position, the first frequency domain signal and the second frequency domain signal received by the first microphone and the second microphone are:

By differentiating the first frequency domain signal and the second frequency domain signal, the first difference can be obtained:

When the loudspeaker is set at the second position, the third frequency domain signal and the fourth frequency domain signal received by the first microphone and the second microphone are:

By differentiating the third frequency domain signal and the fourth frequency domain signal, the second difference can be obtained:

Differentiating the first difference and the second difference again, we can get:

in, It means that when the distances between the speaker and the first microphone and the second microphone are different, the amplitude-frequency responses of the received signal are different due to the different propagation distances of the sound signal in the liquid, which characterizes the situation in which the sound signal is affected by the liquid during the propagation process.

FIG6 is a structural diagram of a non-invasive liquid detection system provided by an embodiment of the present invention, wherein the system comprises:

The detection signal acquisition module 601 is used to collect a first detection signal set after the sound wave signal sent from the speaker at a first position passes through a container and a liquid to be detected loaded in the container through a first microphone and a second microphone, and to collect a second detection signal set after the sound wave signal sent from the speaker at a second position passes through the container and the liquid to be detected through the first microphone and the second microphone, wherein the first position is a position where a first distance and a second distance are the same, and the second position is a position where the first distance and the second distance are different, the first distance is a distance between the speaker and the first microphone, and the second distance is a distance between the speaker and the second microphone, and the first microphone and the second microphone are arranged at a mirror position with the container as a mirror surface;

A clean detection signal set acquisition module 602, configured to pre-process the first detection signal set and the second detection signal set to acquire a first clean detection signal set and a second clean detection signal set;

A differential amplitude signal acquisition module 603 is used to perform differential processing on the first pure detection signal set and the second pure detection signal set to acquire a differential amplitude signal of the liquid to be detected;

The category determination module 604 is used to obtain the characteristics of the differential amplitude signal, and compare the characteristics of the differential amplitude signal with a preset characteristic database, and determine the category of the liquid to be detected according to the comparison result.

In the embodiment of the present invention, a sound-generating device (such as a speaker) is set at a first position and generates a sound wave signal. After the sound wave signal passes through the loading container and the liquid to be detected in the loading container, a first detection signal set is generated. The first detection signal set is acquired by a sound-receiving device (such as a microphone) set at a corresponding position. Similarly, a sound-generating device is set at a second position and generates a sound wave signal. After the sound wave signal passes through the loading container and the liquid to be detected in the loading container, a second detection signal set is generated. The second detection signal set is acquired by a sound-receiving device set at a corresponding position.

Since the first detection signal set and the second detection signal set obtained contain many interference signals, the accuracy of the detection results is low if they are directly used for liquid detection. Therefore, it is necessary to preprocess the first detection signal set and the second detection signal set to remove the interference signals and obtain the first pure detection signal set and the second pure detection signal set.

By performing differential processing on the obtained first pure detection signal set and the second pure detection signal set, the differential amplitude signal of the liquid to be detected can be obtained.

The characteristics of the differential amplitude signal are obtained and compared with a pre-set characteristic database, which stores the characteristics corresponding to the differential amplitude signals of various liquids obtained through the above process. The characteristics of the differential amplitude signal of the liquid to be detected are input into the characteristic database to obtain the corresponding liquid category.

Wherein, the step of obtaining the characteristic of the differential amplitude signal includes:

The Transformer feature extraction module is subjected to machine learning, and the features of the differential amplitude signal are extracted by completing the machine learning Transformer feature extraction module.

In an embodiment of the present invention, a first detection signal set after a sound wave signal sent from a speaker at a first position passes through a container and a liquid to be detected loaded in the container is collected by a first microphone and a second microphone, and a second detection signal set after the sound wave signal sent from the speaker at a second position passes through the container and the liquid to be detected is collected by the first microphone and the second microphone, the first position is a position where the first distance and the second distance are the same, the second position is a position where the first distance and the second distance are different, the first distance is the distance between the speaker and the first microphone, the second distance is the distance between the speaker and the second microphone, and the first microphone and the second microphone are set at a mirror position with the container as a mirror surface; the first pure detection signal set and the second pure detection signal set are differentially processed to obtain a differential amplitude signal of the liquid to be detected; the feature of the differential amplitude signal is obtained, and the feature of the differential amplitude signal is compared with a preset feature database, and the category of the liquid to be detected is determined according to the comparison result. A technical solution with simple required equipment and accurate classification results is provided, and a high-accuracy liquid classification method is realized through a simple sound wave signal collection device.

FIG. 7 is a structural diagram of a non-invasive liquid detection system provided by another embodiment of the present invention. The detection signal acquisition module 601 includes:

A first position setting unit 701, configured to set the speaker at the first position;

The first and second microphone signal collection unit 702 is used to start the speaker set at the first position, collect the first microphone signal formed after the sound wave signal passes through the liquid to be detected through the first microphone, and collect the second microphone signal formed after the sound wave signal passes through the liquid to be detected through the second microphone, and the first microphone signal and the second microphone signal together form the first detection signal set;

A second position setting unit 703, configured to set the speaker at the second position;

The third and fourth microphone signal acquisition unit 704 is used to start the speaker set at the second position, and to collect the third microphone signal formed after the sound wave signal passes through the liquid to be detected through the first microphone, and to collect the fourth microphone signal formed after the sound wave signal passes through the liquid to be detected through the second microphone. The third microphone signal and the fourth microphone signal together form the second detection signal set.

Specifically, when the speaker is set at the first position, the distance from the first microphone and the second microphone is the same. At this time, after the sound wave signal generated by the speaker passes through the container and the liquid to be detected, the first microphone and the second microphone receive the first microphone signal and the second microphone signal respectively. When the speaker is set at the second position, the distance from the first microphone and the second microphone is different. At this time, after the sound wave signal generated by the speaker passes through the container and the liquid to be detected, the first microphone and the second microphone receive the third microphone signal and the fourth microphone signal respectively.

FIG8 is a structural diagram of a non-invasive liquid detection system provided by another embodiment of the present invention. The pure detection signal set acquisition module 602 includes:

A filtered signal acquisition unit 801 is used to perform bandpass filtering on the first microphone signal, the second microphone signal, the third microphone signal and the fourth microphone signal through a bandpass filter to obtain a first filtered signal, a second filtered signal, a third filtered signal and a fourth filtered signal;

The frequency domain signal acquisition unit 802 is used to perform Fourier transform on the first filtered signal, the second filtered signal, the third filtered signal and the fourth filtered signal to obtain a first frequency domain signal, a second frequency domain signal, a third frequency domain signal and a fourth frequency domain signal, the first pure detection signal set includes the first frequency domain signal and the second frequency domain signal, and the second pure detection signal set includes the third frequency domain signal and the fourth frequency domain signal.

In an embodiment of the present invention, a bandpass filter can perform bandpass filtering on the first filter signal, the second filter signal, the third filter signal, and the fourth filter signal to remove environmental noise during signal acquisition and accurately extract signal components within a preset frequency range. The first frequency domain signal, the second frequency domain signal, the third frequency domain signal, and the fourth frequency domain signal that have been accurately extracted are converted into corresponding frequency domain expressions through Fourier transform, so as to facilitate the subsequent steps to extract signal features through frequency domain expressions.

FIG9 is a structural diagram of a non-invasive liquid detection system provided by another embodiment of the present invention. The differential amplitude signal acquisition module 603 includes:

A difference acquisition unit 901 is used to acquire a first difference between the first frequency domain signal and the second frequency domain signal, and to acquire a second difference between the third frequency domain signal and the fourth frequency domain signal;

The differential amplitude signal acquisition unit 902 is used to differentiate the first difference and the second difference to acquire the differential amplitude signal.

In the embodiment of the present invention, the differential processing can eliminate the influence caused by the different frequency responses of the speaker and the microphone, and can eliminate the influence of different containers on the detection results.

The signal collected by the microphone can be expressed as: ,in, is the frequency domain representation of the signal received by the microphone, is the frequency domain representation of the sound wave signal sent by the speaker, is the frequency response of the loudspeaker, is the frequency response of the microphone, is the frequency response of the liquid, is the effect of the container material on the signal when the signal passes through the container, It represents the additional influence caused by the different thickness of the container walls on both sides and the position error caused by the artificial installation of speakers and microphones. It is random and different in each test.

When the loudspeaker is set at the first position, the first frequency domain signal and the second frequency domain signal received by the first microphone and the second microphone are:

By differentiating the first frequency domain signal and the second frequency domain signal, the first difference can be obtained:

When the loudspeaker is set at the second position, the third frequency domain signal and the fourth frequency domain signal received by the first microphone and the second microphone are:

By differentiating the third frequency domain signal and the fourth frequency domain signal, the second difference can be obtained:

Differentiating the first difference and the second difference again, we can get:

in, It means that when the distances between the speaker and the first microphone and the second microphone are different, the amplitude-frequency responses of the received signal are different due to the different propagation distances of the sound signal in the liquid, which characterizes the situation in which the sound signal is affected by the liquid during the propagation process.

Figure 10 illustrates a schematic diagram of the physical structure of an electronic device. As shown in Figure 10, the electronic device may include: a processor (processor) 1001, a communication interface (Communications Interface) 1002, a memory (memory) 1003 and a communication bus 1004, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The processor can call the logic instructions in the memory to execute the method of non-invasive liquid detection, which includes: collecting a first detection signal set after the sound wave signal sent by the speaker from a first position passes through the container and the liquid to be detected loaded in the container through the first microphone and the second microphone, and collecting a second detection signal set after the sound wave signal sent by the speaker from a second position passes through the container and the liquid to be detected through the first microphone and the second microphone, the first position is a position where the first distance and the second distance are the same, the second position is a position where the first distance and the second distance are different, the first distance is the distance between the speaker and the first microphone, the second distance is the distance between the speaker and the second microphone, and the first microphone and the second microphone are set at a mirror position with the container as a mirror surface; pre-processing the first detection signal set and the second detection signal set respectively to obtain a first pure detection signal set and a second pure detection signal set; performing differential processing on the first pure detection signal set and the second pure detection signal set to obtain a differential amplitude signal of the liquid to be detected; obtaining a feature of the differential amplitude signal, and comparing the feature of the differential amplitude signal with a preset feature database, and determining the category of the liquid to be detected according to the comparison result.

In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

On the other hand, an embodiment of the present invention further provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the non-invasive liquid detection method provided by the above-mentioned method embodiments, the method comprising: collecting a first detection signal set after a sound wave signal sent from a speaker at a first position passes through a container and a liquid to be detected loaded in the container through a first microphone and a second microphone, and collecting a second detection signal set after the sound wave signal sent from the speaker at a second position passes through the container and the liquid to be detected through the first microphone and the second microphone, the first position being a position where the first distance and the second distance are the same, The second position is a position where the first distance and the second distance are different, the first distance is the distance between the speaker and the first microphone, the second distance is the distance between the speaker and the second microphone, and the first microphone and the second microphone are arranged at mirror positions with the container as a mirror surface; the first detection signal set and the second detection signal set are preprocessed respectively to obtain a first pure detection signal set and a second pure detection signal set; the first pure detection signal set and the second pure detection signal set are differentially processed to obtain a differential amplitude signal of the liquid to be detected; the characteristics of the differential amplitude signal are obtained, and the characteristics of the differential amplitude signal are compared with a preset feature database, and the category of the liquid to be detected is determined according to the comparison result.

On the other hand, an embodiment of the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the method for non-invasive liquid detection provided in the above-mentioned embodiments, the method comprising: collecting, by a first microphone and a second microphone, a first detection signal set of a sound wave signal sent from a speaker from a first position after passing through a container and a liquid to be detected loaded in the container, and collecting, by the first microphone and the second microphone, a second detection signal set of a sound wave signal sent from the speaker from a second position after passing through the container and the liquid to be detected, the first position being a position where a first distance and a second distance are the same, and the second position being a position where the first distance and the second distance are not the first detection signal set and the second detection signal set are respectively pre-processed to obtain a first pure detection signal set and a second pure detection signal set; the first pure detection signal set and the second pure detection signal set are differentially processed to obtain a differential amplitude signal of the liquid to be detected; the characteristics of the differential amplitude signal are obtained, and the characteristics of the differential amplitude signal are compared with a preset characteristic database, and the category of the liquid to be detected is determined according to the comparison result.

It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

The above is only a partial implementation of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims (10)

1. A method of non-invasive fluid detection, the method comprising:

The method comprises the steps that a first microphone and a second microphone collect a first detection signal set after sound wave signals sent by a loudspeaker from a first position pass through a container and liquid to be detected loaded on the container, the first microphone and the second microphone collect a second detection signal set after the sound wave signals sent by the loudspeaker from a second position pass through the container and the liquid to be detected, the first position is the same as the first position in a first distance and the second distance, the second position is different in a first distance and the second distance, the first distance is the distance between the loudspeaker and the first microphone, the second distance is the distance between the loudspeaker and the second microphone, and the first microphone and the second microphone are arranged at mirror positions taking the container as a mirror surface;

Preprocessing the first detection signal set and the second detection signal set respectively to obtain a first pure detection signal set and a second pure detection signal set;

performing differential processing on the first pure detection signal set and the second pure detection signal set to obtain differential amplitude signals of the liquid to be detected;

And obtaining the characteristics of the differential amplitude signals, comparing the characteristics of the differential amplitude signals with a preset characteristic database, and determining the category of the liquid to be detected according to the comparison result.

2. The method of claim 1, wherein the capturing, by the first and second microphones, the acoustic signal transmitted from the first location by the speaker through the container and the first set of detection signals after the liquid to be detected loaded by the container, and the capturing, by the first and second microphones, the acoustic signal transmitted from the second location by the speaker through the container and the second set of detection signals after the liquid to be detected, comprises:

disposing the speaker in the first position;

Starting a loudspeaker arranged at the first position, acquiring a first microphone signal formed after the sound wave signal passes through the liquid to be detected through the first microphone, acquiring a second microphone signal formed after the sound wave signal passes through the liquid to be detected through the second microphone, and forming the first detection signal set together by the first microphone signal and the second microphone signal;

disposing the speaker in the second position;

The loudspeaker arranged at the second position is started, the first microphone is used for collecting a third microphone signal formed after the sound wave signal passes through the liquid to be detected, the second microphone is used for collecting a fourth microphone signal formed after the sound wave signal passes through the liquid to be detected, and the third microphone signal and the fourth microphone signal jointly form the second detection signal set.

3. The method of claim 2, wherein preprocessing the first and second sets of detection signals to obtain a first and second set of clean detection signals, respectively, comprises:

performing band-pass filtering on the first microphone signal, the second microphone signal, the third microphone signal and the fourth microphone signal through a band-pass filter to obtain a first filtering signal, a second filtering signal, a third filtering signal and a fourth filtering signal;

And performing Fourier transform on the first filtering signal, the second filtering signal, the third filtering signal and the fourth filtering signal to obtain a first frequency domain signal, a second frequency domain signal, a third frequency domain signal and a fourth frequency domain signal, wherein the first pure detection signal set comprises the first frequency domain signal and the second frequency domain signal, and the second pure detection signal set comprises the third frequency domain signal and the fourth frequency domain signal.

4. The method of claim 3, wherein the performing differential processing on the first set of pure detection signals and the second set of pure detection signals to obtain the differential amplitude signal of the liquid to be detected comprises:

Acquiring a first difference between the first frequency domain signal and the second frequency domain signal, and acquiring a second difference between the third frequency domain signal and the fourth frequency domain signal;

And differentiating the first difference with the second difference to obtain the differential amplitude signal.

5. A system for non-invasive fluid detection, the system comprising:

The detection signal acquisition module is used for acquiring a first detection signal set after an acoustic wave signal sent by a loudspeaker from a first position passes through a container and liquid to be detected loaded on the container through a first microphone and a second microphone, acquiring a second detection signal set after the acoustic wave signal sent by the loudspeaker from a second position passes through the container and the liquid to be detected through the first microphone and the second microphone, wherein the first position is the same position of a first distance and a second distance, the second position is a position with different first distance and second distance, the first distance is a distance between the loudspeaker and the first microphone, the second distance is a distance between the loudspeaker and the second microphone, and the first microphone and the second microphone are arranged at mirror positions taking the container as mirror surfaces;

The pure detection signal set acquisition module is used for respectively preprocessing the first detection signal set and the second detection signal set to acquire a first pure detection signal set and a second pure detection signal set;

The differential amplitude signal acquisition module is used for carrying out differential processing on the first pure detection signal set and the second pure detection signal set to acquire differential amplitude signals of the liquid to be detected;

The category determining module is used for acquiring the characteristics of the differential amplitude signals, comparing the characteristics of the differential amplitude signals with a preset characteristic database and determining the category of the liquid to be detected according to the comparison result.

6. The system of claim 5, wherein the detection signal acquisition module comprises:

a first position setting unit configured to set the speaker at the first position;

The first microphone signal acquisition unit is used for starting a loudspeaker arranged at the first position, acquiring a first microphone signal formed after the sound wave signal passes through the liquid to be detected through the first microphone, acquiring a second microphone signal formed after the sound wave signal passes through the liquid to be detected through the second microphone, and forming the first detection signal set together by the first microphone signal and the second microphone signal;

A second position setting unit configured to set the speaker at the second position;

The third microphone signal acquisition unit is used for starting a loudspeaker arranged at the second position, acquiring a third microphone signal formed after the sound wave signal passes through the liquid to be detected through the first microphone, acquiring a fourth microphone signal formed after the sound wave signal passes through the liquid to be detected through the second microphone, and forming a second detection signal set together by the third microphone signal and the fourth microphone signal.

7. The system of claim 6, wherein the clean detection signal set acquisition module comprises:

A filtered signal obtaining unit, configured to perform band-pass filtering on the first microphone signal, the second microphone signal, the third microphone signal, and the fourth microphone signal through a band-pass filter, to obtain a first filtered signal, a second filtered signal, a third filtered signal, and a fourth filtered signal;

The frequency domain signal acquisition unit is configured to perform fourier transform on the first filtered signal, the second filtered signal, the third filtered signal, and the fourth filtered signal, and acquire a first frequency domain signal, a second frequency domain signal, a third frequency domain signal, and a fourth frequency domain signal, where the first pure detection signal set includes the first frequency domain signal and the second frequency domain signal, and the second pure detection signal set includes the third frequency domain signal and the fourth frequency domain signal.

8. The system of claim 7, wherein the differential amplitude signal acquisition module comprises:

A difference obtaining unit, configured to obtain a first difference between the first frequency domain signal and the second frequency domain signal, and obtain a second difference between the third frequency domain signal and the fourth frequency domain signal;

And the differential amplitude signal acquisition unit is used for differentiating the first differential and the second differential to acquire the differential amplitude signal.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of non-invasive liquid detection according to any of claims 1-4 when the computer program is executed.

10. A non-transitory computer readable storage medium, having stored thereon a computer program, which when executed by a processor, implements the method of non-invasive liquid detection according to any of claims 1-4.