Target liquid detection method, device and equipment and storage medium

Abstract

The invention relates to the technical field of liquid detection, and discloses a target liquid detection method, device and equipment and a storage medium, target liquid is located in a container with an irregular shape, a butterfly-shaped transmitting antenna and a butterfly-shaped receiving antenna are arranged on one side of the target liquid side by side, and the butterfly-shaped receiving antenna is arranged on the other side of the target liquid. The method comprises the following steps: sending a detection signal to the target liquid through the butterfly-shaped transmitting antenna, and receiving a plurality of groups of echo signals through the butterfly-shaped receiving antennas on the two sides of the target liquid to obtain receiving signals; preprocessing the received signal, and classifying the preprocessed received signal through a pre-trained signal classification model to obtain type information of the target liquid; and determining whether the target liquid is dangerous liquid or not according to the type information. By increasing the signal utilization rate of the butterfly antenna and classifying data by using deep learning, the dangerous liquid can be quickly and accurately detected.

Description

Technical Field

[0001] The present invention relates to the technical field of liquid detection, and in particular to a target liquid detection method, device, equipment and storage medium. Background Art

[0002] Traditional methods for detecting hazardous liquids are mostly non-contact, typically measuring the relative change in low-frequency dielectric constant through the capacitance effect. However, this approach is significantly affected by container wall thickness and liquid volume, resulting in low accuracy. Therefore, a different approach is now being adopted. This approach uses a pair of planar butterfly antennas to transmit and receive electromagnetic waves. This method transmits broadband signals, then receives and analyzes the amplitude-frequency and phase-frequency responses of the reflected signals. This method measures the dielectric constant spectrum within a certain frequency range, thereby determining the physical and chemical properties of the liquid, with improved accuracy.

[0003] However, in current use, two sets of butterfly antennas are placed side by side for transmission and reception. When detecting dangerous liquids in bottles that are too small or irregularly shaped, there is a great loss in the utilization of the butterfly antenna signal strength, severe signal fading, and a great decrease in sensitivity. There is also the problem of a single identification feature, which makes it easy to generate false alarms when distinguishing liquids with similar electrical constants.

[0004] Therefore, there is an urgent need for a method that can overcome the defects of existing butterfly antennas in detecting hazardous liquids, increase the utilization rate of butterfly antenna signals, and thus achieve rapid and accurate detection of hazardous liquids. Summary of the Invention

[0005] In view of this, the present application provides a target liquid detection method, device, equipment and storage medium, which improve the efficiency of terminal equipment in using the network. The technical solution is as follows.

[0006] In a first aspect, the present invention provides a method for detecting a target liquid, wherein the target liquid is located in an irregularly shaped container, a butterfly-shaped transmitting antenna and a butterfly-shaped receiving antenna are arranged side by side on one side of the target liquid, and a butterfly-shaped receiving antenna is arranged on the other side of the target liquid, the method comprising:

[0007] The detection signal is sent to the target liquid through the butterfly-shaped transmitting antenna, and multiple groups of echo signals are received by the butterfly-shaped receiving antennas on both sides of the target liquid to obtain a received signal;

[0008] Preprocessing the received signal, and extracting features from the preprocessed received signal using a pretrained signal classification model to obtain characteristic parameters of the target liquid;

[0009] Matching the characteristic parameter with pre-stored liquid characteristics to obtain type information of the target liquid;

[0010] According to the type information, it is determined whether the target liquid is a hazardous liquid.

[0011] In an optional implementation, the preprocessing of the received signal includes: filtering, amplifying or digitizing the received signal to obtain a preprocessed received signal.

[0012] In an optional implementation, the characteristic parameter includes: reflection coefficient, phase change, frequency offset or amplitude difference; the type information includes: water, ethanol or gasoline.

[0013] In an optional embodiment, the determining whether the target liquid is a hazardous liquid based on the type information includes: when the type information is water, determining that the target liquid is a safe liquid; when the type information is ethanol or gasoline, determining that the target liquid is a hazardous liquid.

[0014] In an optional implementation, the signal classification model is obtained by training a preset neural network model.

[0015] In an optional embodiment, the method further includes:

[0016] Acquiring echo signal data and performing normalization processing on the echo signal data;

[0017] Constructing a training data set based on the normalized echo data signal;

[0018] The preset neural network model is trained according to the training data set to obtain the signal classification model.

[0019] The target liquid detection method provided by the present invention has the following advantages.

[0020] The target liquid detection method of the present invention is used to detect a target liquid in an irregularly shaped container, wherein a butterfly-shaped transmitting antenna and a butterfly-shaped receiving antenna are arranged side by side on one side of the target liquid, and a butterfly-shaped receiving antenna is arranged on the other side of the target liquid. The scheme of the present invention improves the receiving mode of the butterfly antenna, changing the original side-by-side placement of the butterfly antennas to providing receiving signal antennas on both sides of the target liquid, thereby increasing the utilization rate of the antenna signal, especially when detecting samples with weak echo signals, enhancing the signal strength. The target liquid detection method of the present invention transmits electromagnetic waves to the target liquid through the butterfly-shaped transmitting antenna. After passing through the liquid medium in the bottle, the butterfly-shaped receiving antenna receives the returned electromagnetic wave signal, and the received signal is changed from a single reflection receiving group to multiple parts and multi-angle reception. There is not only the original reflection receiving surface, but also a top transmission receiving surface. Multiple groups of receiving signals constitute the receiving signal. The received signal is preprocessed by filtering, amplifying, and digitizing it. Feature extraction is then performed on the preprocessed signal using a pretrained signal classification model to obtain characteristic parameters of the target liquid, such as reflection coefficient, phase change, frequency offset, and amplitude difference. The extracted characteristic parameters are then compared with a database of known liquid properties to identify the type and properties of the target liquid and determine whether it is a hazardous liquid. The hazardous liquid detection method of the present invention changes the original side-by-side placement of the butterfly antennas to placing receiving signal antennas on both sides of the target liquid. This increases the signal receiving surface, making the antenna's input impedance closer to the characteristic impedance of the feed system, thereby improving impedance matching performance, reducing reflection loss, and increasing the antenna's operating efficiency. Furthermore, the antenna can receive signals over a wider range, effectively increasing the antenna's ability to radiate power density in a specific direction, that is, increasing the antenna's gain. By increasing the receiving surface, the butterfly antenna can focus received signals at more angles, thereby increasing its gain in a specific direction. Furthermore, by improving the directivity of the butterfly antenna, it can more effectively receive echo signals from all directions passing through specially shaped bottles. This allows it to more effectively receive signals from a specific direction while reducing interference from other directions. This significantly improves the performance of non-metallic bottles with diverse shapes and makes it more convenient to use, as the target liquid can be placed in more than one direction. Furthermore, in environments with severe multipath effects, the increased receiving area allows for more effective capture of reflected signals from different paths, thereby improving the stability and reliability of signal reception. This is particularly important in communication systems operating in complex environments. Using a trained neural network model to classify echo signals, performance can be continuously improved with increasing data and increasing hardware capabilities, enhancing detection accuracy and speed, and accurately identifying the hazardous / safe category of different liquid samples. When identifying similar but different samples, deep learning can distinguish between the samples while also providing strong noise and interference immunity, ensuring the stability and reliability of detection results.

[0021] In a second aspect, the present invention provides a target liquid detection device, wherein the target liquid is located in an irregularly shaped container, a butterfly-shaped transmitting antenna and a butterfly-shaped receiving antenna are arranged side by side on one side of the target liquid, and a butterfly-shaped receiving antenna is arranged on the other side of the target liquid, and the device comprises:

[0022] a receiving signal acquisition module, configured to transmit a detection signal to the target liquid through the butterfly-shaped transmitting antenna, and receive multiple groups of echo signals through the butterfly-shaped receiving antennas on both sides of the target liquid to obtain a receiving signal;

[0023] A feature extraction module is used to preprocess the received signal and extract features from the preprocessed received signal using a pretrained signal classification model to obtain characteristic parameters of the target liquid;

[0024] A type matching module is used to match the characteristic parameters with pre-stored liquid characteristics to obtain type information of the target liquid;

[0025] The judgment module is used to determine whether the target liquid is a dangerous liquid according to the type information.

[0026] In an optional embodiment, the device further comprises:

[0027] The training module is used to obtain echo signal data and normalize the echo signal data; construct a training data set based on the normalized echo data signal; and train a preset neural network model according to the training data set to obtain the signal classification model.

[0028] In an optional implementation, the received signal acquisition module 701 is specifically configured to:

[0029] The received signal is filtered, amplified or digitized to obtain a preprocessed received signal.

[0030] In an optional implementation, the judgment module 704 is specifically configured to: determine that the target liquid is a safe liquid when the type information is water; and determine that the target liquid is a dangerous liquid when the type information is ethanol or gasoline.

[0031] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the target liquid detection method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0032] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the target liquid detection method of the first aspect or any corresponding embodiment thereof.

[0033] In a fifth aspect, the present invention provides a computer program product comprising computer instructions for causing a computer to execute the target liquid detection method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0035] Figure 1 It is a schematic diagram of the arrangement of a butterfly antenna in a liquid detection method of an existing solution according to an exemplary embodiment.

[0036] Figure 2 It is a schematic diagram of a setting method of a butterfly antenna in a target liquid detection method according to an exemplary embodiment.

[0037] Figure 3 FIG4 is a flow chart of a method for detecting a target liquid according to an exemplary embodiment.

[0038] Figure 4 1 is a flow chart of a method for detecting a target liquid in a specific example according to an exemplary embodiment.

[0039] Figure 5 It is a schematic diagram of the training process of the signal classification model in a specific instance according to an exemplary embodiment.

[0040] Figure 6 The figure is a schematic diagram showing a classification result of a received signal according to an exemplary embodiment.

[0041] Figure 7 Schematic diagram of the structure of a target liquid detection device provided in an embodiment of the present application.

[0042] Figure 8 It is a structural diagram of a computer device provided by an optional embodiment of the present invention. DETAILED DESCRIPTION

[0043] To make the purpose, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0044] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association between A and B.

[0045] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and being indicated, configuration and being configured, etc.

[0046] In an embodiment of the present application, "predefinition" can be achieved by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, including a terminal device and a network device). This application does not limit its specific implementation method.

[0047] Fast and accurate detection of hazardous liquids is crucial in the industrial, environmental, and public safety sectors. Traditional hazardous liquid detection methods are mostly non-contact and fall into two categories. One method uses the capacitance effect to measure the relative change in dielectric constant at low frequencies. However, this approach is significantly affected by container wall thickness and liquid volume, resulting in low accuracy.

[0048] Another type of solution uses a pair of planar butterfly antennas to transmit and receive electromagnetic waves, transmit broadband signals, receive and analyze the amplitude-frequency and phase-frequency responses of the reflected signals, measure the dielectric constant spectrum within a frequency range, and thus determine the physical and chemical properties of the liquid.

[0049] The butterfly antenna is a broadband dipole antenna. It is usually composed of two symmetrical triangular metal plates. Its shape is similar to a butterfly and can cover a wide frequency range. It has a relatively simple structure and can effectively achieve broadband performance. Since the butterfly antenna is characterized by broadband coverage, it can cover multiple frequency bands. However, its radiation directionality is relatively weak, and the gain of the butterfly antenna is low, generally between 2dBi and 6dBi. Its radiation direction Figure 1 Generally presents a wider main lobe, which is suitable for communication scenarios that require a wider bandwidth and a shorter distance. Therefore, in current use, two sets of butterfly antennas are placed side by side for transmission and reception, such as Figure 1 shown.

[0050] Due to their wide bandwidth, high sensitivity, and simple structure, butterfly antennas have the potential to detect liquid properties non-contact. Using butterfly antennas for hazardous liquid detection is a promising technology, offering an efficient, non-contact, and wide-bandwidth detection method. Using butterfly antennas allows for non-contact measurement, eliminating the risk of direct contact with the liquid. Furthermore, the antenna's wide bandwidth, covering multiple frequency bands, significantly improves detection sensitivity. Furthermore, detection results can be obtained quickly and efficiently, making it ideal for situations requiring rapid response, such as security checks.

[0051] While the accuracy of detection using a butterfly antenna has improved, it has limitations. For example, when detecting dangerous liquids in small, irregularly shaped bottles, the butterfly antenna's signal strength is significantly lost, resulting in severe signal fading and a significant decrease in sensitivity. Furthermore, the antenna utilizes a single feature, making it easy to generate false positives when distinguishing between liquids with similar dielectric constants.

[0052] In order to solve the defects of the existing butterfly antenna detection method for liquid, the embodiment of the present invention provides a target liquid detection method, wherein the target liquid is located in an irregularly shaped container, and the butterfly antennas are changed from being placed side by side to receiving signal antennas being set on both sides of the target liquid. Specifically, a butterfly transmitting antenna and a butterfly receiving antenna are set side by side on one side of the target liquid, and a butterfly receiving antenna is set on the other side of the target liquid. Figure 2 shown.

[0053] The process of the target liquid detection method provided by the embodiment of the present invention is as follows: Figure 3 As shown, the following steps are included.

[0054] S301 , sending a detection signal to a target liquid through a butterfly-shaped transmitting antenna, and receiving multiple groups of echo signals through the butterfly-shaped receiving antennas on both sides of the target liquid to obtain a received signal.

[0055] Specifically, in step S301, electromagnetic waves are transmitted to the target liquid through the butterfly transmitting antenna. After passing through the liquid medium in the bottle, the butterfly receiving antenna receives the returned electromagnetic wave signal. The received signal changes from a single reflection receiving group to multiple parts and multi-angle reception. There is not only the original reflection receiving surface, but also the top transmission receiving surface. Multiple groups of receiving signals constitute the received signal.

[0056] S302 , preprocessing the received signal, and extracting features from the preprocessed received signal using a pre-trained signal classification model to obtain characteristic parameters of the target liquid.

[0057] Optionally, in step S302, the pre-processing includes filtering, amplifying or digitizing the received signal. Characteristic parameters include: reflection coefficient, phase change, frequency offset or amplitude difference.

[0058] Optionally, in the above steps, the signal classification model is obtained by training a preset neural network model. The training process includes: obtaining echo signal data and normalizing the echo signal data; constructing a training data set based on the normalized echo data signal; and training the preset neural network model based on the training data set to obtain the signal classification model.

[0059] S303: Match the characteristic parameter with pre-stored liquid characteristics to obtain type information of the target liquid.

[0060] Specifically, in step S303, the type information includes: water, ethanol, and gasoline.

[0061] S304: Determine whether the target liquid is a hazardous liquid based on the type information.

[0062] Specifically, in step S304, when the type information is water, the target liquid is determined to be a safe liquid; when the type information is ethanol or gasoline, the target liquid is determined to be a dangerous liquid.

[0063] In summary, the target liquid detection method provided by the embodiment of the present invention is used to detect the target liquid in an irregularly shaped container, wherein a butterfly-shaped transmitting antenna and a butterfly-shaped receiving antenna are arranged side by side on one side of the target liquid, and a butterfly-shaped receiving antenna is arranged on the other side of the target liquid. The scheme of the present invention improves the receiving mode of the butterfly antenna, and changes the butterfly antenna from the original side-by-side placement to a receiving signal antenna arranged on both sides of the target liquid, thereby increasing the utilization rate of the antenna signal, especially when detecting samples with weak echo signals, enhancing the signal strength. The target liquid detection method of the present invention transmits electromagnetic waves to the target liquid through the butterfly-shaped transmitting antenna. After passing through the liquid medium in the bottle, the butterfly-shaped receiving antenna receives the returned electromagnetic wave signal, and the received signal is changed from a single reflection receiving group to multiple parts and multi-angle reception. There is not only the original reflection receiving surface, but also a top transmission receiving surface. Multiple groups of receiving signals constitute the receiving signal. The received signal is preprocessed by filtering, amplifying, and digitizing it. Feature extraction is then performed on the preprocessed signal using a pretrained signal classification model to obtain characteristic parameters of the target liquid, such as reflection coefficient, phase change, frequency offset, and amplitude difference. The extracted characteristic parameters are then compared with a database of known liquid properties to identify the type and properties of the target liquid and determine whether it is a hazardous liquid. The hazardous liquid detection method of the present invention changes the original side-by-side placement of the butterfly antennas to placing receiving signal antennas on both sides of the target liquid. This increases the signal receiving surface, making the antenna's input impedance closer to the characteristic impedance of the feed system, thereby improving impedance matching performance, reducing reflection loss, and increasing the antenna's operating efficiency. Furthermore, the antenna can receive signals over a wider range, effectively increasing the antenna's ability to radiate power density in a specific direction, that is, increasing the antenna's gain. By increasing the receiving surface, the butterfly antenna can focus received signals at more angles, thereby increasing its gain in a specific direction. Furthermore, by improving the directivity of the butterfly antenna, it can more effectively receive echo signals from all directions passing through specially shaped bottles. This allows it to more effectively receive signals from a specific direction while reducing interference from other directions. This significantly improves the performance of non-metallic bottles with diverse shapes and makes it more convenient to use, as the target liquid can be placed in more than one direction. Furthermore, in environments with severe multipath effects, the increased receiving area allows for more effective capture of reflected signals from different paths, thereby improving the stability and reliability of signal reception. This is particularly important in communication systems operating in complex environments. Using a trained neural network model to classify echo signals, performance can be continuously improved with increasing data and increasing hardware capabilities, enhancing detection accuracy and speed, and accurately identifying the hazardous / safe category of different liquid samples. When identifying similar but different samples, deep learning can distinguish between the samples while also providing strong noise and interference immunity, ensuring the stability and reliability of detection results.

[0064] The following example illustrates the training process of the signal classification model in the above target liquid detection method. The butterfly antenna setting reference Figure 2 , the target liquid detection process based on the deep learning model of neural network is as follows Figure 4 As shown, it is the same as the above embodiment and will not be repeated here.

[0065] The signal classification model is designed to classify sample signals into two categories: safe and dangerous according to the detection requirements, which serve as the output layer node of the model. During the training phase of the signal classification model, a large amount of training data is required to train the model. In this model, 1500 sets of data are used as learning data, and a relatively small amount of 500 sets of echo signals are used as test data to evaluate the classification ability of the model. The training process is as follows: Figure 5 As shown. After sufficient training, the deep learning model based on the neural network can accurately classify the echo signal according to the characteristics. In order to improve the detection accuracy through the prediction of this model, the present invention also considers the interference problem in the environment. Through shielding measures and filtering technology, the influence of environmental electromagnetic interference on the detection results is reduced. The actual construction and implementation process is as follows Figure 5 As shown. When using a deep learning model for data classification, the accuracy of sample differentiation and prediction can be optimized by adjusting the model parameters (such as the number of nodes in the hidden layer). According to the data learning effect and training time of the training echo signal, in practical applications, the optimal configuration is found by adjusting the model parameters. At the same time, as the number of hidden layer nodes increases, the classification error rate of the deep learning model usually decreases significantly, thereby improving the accuracy of echo signal classification. The trained model is used to detect 100 conventional samples for effect verification, of which half are safety / dangerous samples each. The accuracy of this model's judgment can reach 95%, and the training effect is significant. The received signal is classified by the trained model, and the following is obtained: Figure 6 The waveform shown in the figure, Figure 6 The graph shows the time (s)-algorithm data input (V), which is the waveform after processing for algorithm learning. It mainly includes three categories: water, ethanol, and gasoline. It can be seen that water as a safe sample and the other two types of dangerous goods have obvious distinctions in terms of phase, number of waveform peaks and valleys, and numerical values.

[0066] In summary, the target liquid detection method provided in this embodiment improves the original butterfly antenna detection method in the antenna part and the classification algorithm part. At the antenna level, the butterfly antenna is changed from the original side-by-side placement to adding receiving signal antennas on both sides of the test sample, which increases the utilization rate of the antenna signal, especially when detecting samples with weak echo signals, and enhances the signal strength. The improvement to the butterfly antenna increases the receiving surface. Increasing the receiving surface can make the input impedance of the antenna closer to the characteristic impedance of the feeding system, thereby improving the impedance matching performance, reducing reflection loss, and improving the working efficiency of the antenna. Secondly, the antenna can receive signals in a wider range, which can effectively improve the antenna's ability to radiate power density in a specific direction, that is, increase the antenna's gain. By increasing the receiving surface, the butterfly antenna can concentrate on receiving signals at more angles, thereby increasing its gain in a specific direction. This is particularly important when receiving weak signals. Furthermore, the directivity of the butterfly antenna can be improved, enabling it to more effectively receive echo signals from various directions passing through specially shaped bottles. This allows it to more effectively receive signals from a specific direction while reducing interference from other directions. This is a significant improvement for non-metallic bottles with a wide variety of shapes, and also makes it more convenient to use, as test samples can be placed in more than one direction. Furthermore, in environments with severe multipath effects, increasing the receiving signal surface can more effectively capture reflected signals from different paths, thereby improving the stability and reliability of signal reception. This is particularly important in communication systems operating in complex environments.

[0067] At the classification algorithm level, neural network-based echo signal classification algorithms offer high accuracy. Furthermore, they can classify samples using multiple features, such as amplitude, frequency, and phase. This significantly enhances the reliability of distinguishing liquids with similar dielectric constants compared to traditional contact and semi-contact methods that rely solely on a single feature. Deep learning-based echo signal classification algorithms have significantly improved accuracy. Through continuous model training and optimization, deep learning algorithms can continuously improve performance with increasing data and advancing hardware capabilities, enhancing detection accuracy and speed, and accurately identifying the hazardous / safe classification of different liquid samples. When identifying similar but distinct samples, deep learning can distinguish these differences and exhibit strong noise and interference immunity. Once trained, the model operates under a wide range of environmental requirements, enabling it to effectively distinguish different liquid types even in the presence of ambient noise or interfering signals, ensuring stable and reliable detection results. In scenarios requiring detection of liquids in varying states (such as varying temperature and humidity), deep learning models, trained on large amounts of data, can adapt to these complex environmental conditions while maintaining detection accuracy. This makes deep learning more widely used in liquid detection and can meet a variety of practical application needs.

[0068] In the embodiments of the present application, a target liquid detection device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments. The details already described will not be repeated here. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0069] The present invention provides a target liquid detection device. Figure 7 : This is a schematic structural diagram of a target liquid detection device provided by an embodiment of the present application. The target liquid is located in an irregularly shaped container. A butterfly-shaped transmitting antenna and a butterfly-shaped receiving antenna are arranged side by side on one side of the target liquid, and a butterfly-shaped receiving antenna is arranged on the other side of the target liquid. The device includes:

[0070] A received signal acquisition module 701 is configured to transmit a detection signal to the target liquid through the butterfly-shaped transmitting antenna, and receive multiple groups of echo signals through the butterfly-shaped receiving antennas on both sides of the target liquid to obtain a received signal;

[0071] A feature extraction module 702 is used to preprocess the received signal and extract features from the preprocessed received signal using a pretrained signal classification model to obtain characteristic parameters of the target liquid;

[0072] A type matching module 703 is used to match the characteristic parameters with pre-stored liquid characteristics to obtain type information of the target liquid;

[0073] The judgment module 704 is configured to determine whether the target liquid is a hazardous liquid according to the type information.

[0074] In an optional embodiment, the device further comprises:

[0075] The training module 705 is used to obtain echo signal data and normalize the echo signal data; construct a training data set based on the normalized echo data signal; and train the preset neural network model according to the training data set to obtain the signal classification model.

[0076] In an optional implementation, the received signal acquisition module 701 is specifically configured to:

[0077] The received signal is filtered, amplified or digitized to obtain a preprocessed received signal.

[0078] In an optional implementation, the judgment module 704 is specifically configured to: determine that the target liquid is a safe liquid when the type information is water; and determine that the target liquid is a dangerous liquid when the type information is ethanol or gasoline.

[0079] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0080] The target liquid detection device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0081] The embodiment of the present invention also provides a computer device having the above Figure 7 The target liquid detection device shown.

[0082] See also Figure 8 , Figure 8 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 8 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information in the graphical user interface on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8 A processor 10 is taken as an example.

[0083] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0084] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0085] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0086] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0087] The computer device further includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 8 The bus connection is taken as an example.

[0088] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0089] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0090] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A target liquid detection method, characterized in that: The target liquid is located in an irregularly shaped container, a butterfly-shaped transmitting antenna and a butterfly-shaped receiving antenna are arranged side by side on one side of the target liquid, and a butterfly-shaped receiving antenna is arranged on the other side of the target liquid. The method comprises: Sending a detection signal to the target liquid through the butterfly-shaped transmitting antenna, and receiving multiple groups of echo signals through the butterfly-shaped receiving antennas on both sides of the target liquid to obtain a receiving signal; Preprocessing the received signal, and extracting features of the preprocessed received signal through a pretrained signal classification model to obtain characteristic parameters of the target liquid; Matching the characteristic parameters with pre-stored liquid characteristics to obtain type information of the target liquid; According to the type information, it is determined whether the target liquid is a hazardous liquid.

2. The method according to claim 1, characterized in that The preprocessing of the received signal comprises: The received signal is filtered, amplified or digitized to obtain a preprocessed received signal.

3. The method according to claim 2, characterized in that The characteristic parameters include: reflection coefficient, phase change, frequency offset or amplitude difference; the type information includes: water, ethanol or gasoline.

4. The method according to claim 2, characterized in that: The step of determining whether the target liquid is a hazardous liquid according to the type information includes: When the type information is water, determining that the target liquid is a safe liquid; When the type information is ethanol or gasoline, it is determined that the target liquid is a hazardous liquid.

5. The method according to any one of claims 1 to 4, characterized in that: The signal classification model is obtained by training a preset neural network model.

6. The method according to claim 5, characterized in that The method further comprises: Acquiring echo signal data, and performing normalization processing on the echo signal data; Constructing a training data set based on the normalized echo data signal; The preset neural network model is trained according to the training data set to obtain the signal classification model.

7. A target liquid detection device, characterized in that: The target liquid is located in an irregularly shaped container, a butterfly-shaped transmitting antenna and a butterfly-shaped receiving antenna are arranged side by side on one side of the target liquid, and a butterfly-shaped receiving antenna is arranged on the other side of the target liquid. The device comprises: A receiving signal acquisition module, used for sending a detection signal to the target liquid through the butterfly-shaped transmitting antenna, and receiving multiple groups of echo signals through the butterfly-shaped receiving antennas on both sides of the target liquid to obtain a receiving signal; A feature extraction module is used to preprocess the received signal and extract features from the preprocessed received signal through a pretrained signal classification model to obtain characteristic parameters of the target liquid; A type matching module, used to match the characteristic parameters with pre-stored liquid characteristics to obtain type information of the target liquid; The judgment module is used to determine whether the target liquid is a dangerous liquid according to the type information.

8. The target liquid detection device according to claim 7, characterized in that: The device also includes: The training module is used to obtain echo signal data and normalize the echo signal data; construct a training data set based on the normalized echo data signal; and train a preset neural network model according to the training data set to obtain the signal classification model.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the target liquid detection method according to any one of claims 1 to 6 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the target liquid detection method according to any one of claims 1 to 6.

Images