Closed container leakage detection method, device and system

Abstract

The present invention provides a closed container leakage detection method, device and system, which belongs to the field of signal processing technology, and includes: receiving a first audio signal collected by a microphone array arranged in the outer space of a closed container to determine the first angle range of the microphone array according to its audio characteristics; collecting multiple second audio signals within the first angle range; performing beamforming on the multiple second audio signals to determine the third audio signal when the signal is the strongest; judging whether the closed container has a leak according to the signal gain between the third audio signal and the reference audio signal. The closed container leakage detection method, device and system provided by the present invention can quickly realize dead-angle leakage detection of the container under test on the production line by beamforming the microphone array to adaptively scan the frequency range and intensity range, and has higher detection accuracy and lower detection cost, effectively improving production efficiency.

Description

Technical Field

[0001] The present invention relates to the field of signal processing technology, and in particular to a closed container leakage detection method, device and system. Background Art

[0002] Generally speaking, pressure-bearing containers such as water heater tanks and compressor cylinders have very high airtightness requirements and need to be tested for airtightness before they come off the production line.

[0003] The more common method for leak detection of closed containers on the production line is water testing. Compressed air is filled into the container and then immersed in water. Personnel observe the bubbles produced by the leak to determine whether there is a leak.

[0004] In addition, for the detection of tiny leaks, a more accurate detection scheme is to use the helium / hydrogen-nitrogen leak detection scheme, which mainly includes: filling the closed container to be tested with helium / hydrogen to the specified test pressure, and then using the helium mass spectrometer leak detector probe / hydrogen leak detector probe to scan at various possible leak points. The instrument will detect the change in helium / hydrogen concentration to determine whether there is a leak.

[0005] The above water detection method is difficult to detect tiny leaks, especially for leaks that only take a few seconds to form a small bubble. It is very difficult to rely on manual visual detection on the production line. The hydrogen / nitrogen leak detection method requires an additional gas source. The cost of helium is high, but hydrogen has the risk of causing hydrogen embrittlement of the material. In addition, in the actual production line, there will be false alarms of leak detection caused by leaks in the test equipment joints, etc., and the helium / hydrogen nitrogen leak detection solution cannot avoid such false alarms. Summary of the invention

[0006] The present invention provides a closed container leakage detection method, device and system, which are used to solve the defects of low detection efficiency, low accuracy and high cost in the prior art.

[0007] The present invention provides a closed container leakage detection method, comprising the following steps:

[0008] Receiving a first audio signal collected by a microphone array arranged in a space outside a sealed container, and determining a first angle range of the microphone array according to an audio feature of the first audio signal; the air pressure inside the sealed container is greater than the air pressure outside the container;

[0009] Controlling the microphone array to collect multiple second audio signals within the first angle range, wherein different second audio signals are obtained by scanning according to parameter combinations of different frequency ranges and intensity ranges;

[0010] Performing beamforming on the multiple second audio signals to determine a third audio signal with the strongest signal;

[0011] Whether there is leakage in the sealed container is determined according to the signal gain between the third audio signal and the reference audio signal.

[0012] According to the closed container leakage detection method provided by the present invention, the first angle range is divided to obtain a plurality of second angle ranges, including:

[0013] A plurality of the second angle ranges are acquired by evenly dividing the horizontal angle area and / or the pitch angle area of ​​the first angle range.

[0014] According to the closed container leakage detection method provided by the present invention, in the case where the closed container is judged to have leakage according to the signal gain between the third audio signal and the reference audio signal, the method further includes:

[0015] Fine-grained division of the first angle range to obtain a plurality of second angle ranges;

[0016] Controlling the microphone array to collect multiple fourth audio signals within each of the second angle ranges; the multiple fourth audio signals are all collected under a parameter combination of a frequency range and an intensity range of the third audio signal;

[0017] Performing secondary beamforming on all the fourth audio signals to determine a third angle range when the signal is strongest;

[0018] The target leakage area of ​​the sealed container is located according to the third angle range.

[0019] According to the closed container leakage detection method provided by the present invention, after locating the target leakage area of ​​the closed container according to the third angle range, the method further comprises:

[0020] Acquire a target image of the target leakage area;

[0021] The target image is fused with the actual image of the sealed container to obtain a leakage location image.

[0022] According to the closed container leakage detection method provided by the present invention, determining the first angle range of the microphone array according to the audio characteristics of the first audio signal includes:

[0023] Determining the first angle range according to the audio feature and prior information for leak detection of the sealed container;

[0024] The prior information includes different audio features when leakage occurs at different parts of the sealed container, historical leakage data of the sealed container, and one or more of the design parameters of the sealed container.

[0025] According to the closed container leakage detection method provided by the present invention, judging whether the closed container has a leak according to the signal gain between the third audio signal and the reference audio signal specifically includes:

[0026] When the signal gain is greater than a preset gain threshold, it is determined that there is a leak in the sealed container;

[0027] When the signal gain is not greater than the preset gain threshold, it is determined that there is no leakage in the sealed container.

[0028] The present invention also provides a closed container leakage detection device, comprising:

[0029] an audio receiving unit, configured to receive a first audio signal collected by a microphone array arranged in a space outside a sealed container, so as to determine a first angle range of the microphone array according to an audio feature of the first audio signal; the air pressure inside the sealed container is greater than the air pressure outside the container;

[0030] A collection control unit, used for controlling the microphone array to collect multiple second audio signals within the first angle range, wherein different second audio signals are obtained by scanning according to parameter combinations of different frequency ranges and intensity ranges;

[0031] A beamforming unit, configured to perform beamforming on the multiple second audio signals to determine a third audio signal when the signal is the strongest;

[0032] A data processing unit is used to determine whether there is leakage in the sealed container according to the signal gain between the third audio signal and the reference audio signal.

[0033] The present invention also provides a closed container leakage detection system, comprising: a pressurizing device, a signal processing module and a microphone array;

[0034] The pressurizing device is used to inject compressed gas into the sealed container before testing, so that the air pressure inside the sealed container is greater than the air pressure outside the container;

[0035] The microphone array sends the collected audio signal to the signal processing module through the communication connection with the signal processing module;

[0036] The signal processing module is used to execute any of the above-mentioned closed container leakage detection methods when running.

[0037] The closed container leakage detection system provided by the present invention also includes a soundproof box;

[0038] When conducting a closed container leakage detection, the closed container is located in the soundproof box;

[0039] The microphone array is arranged in the soundproof box.

[0040] The closed container leakage detection system provided by the present invention also includes a loading and unloading mechanism;

[0041] The loading and unloading mechanism is used to transport and fix the sealed container from the previous station to the detection station located in the soundproof box.

[0042] According to the closed container leakage detection system provided by the present invention, there are multiple microphone arrays, and the multiple microphones in each microphone array are distributed according to at least one of a linear array, a planar array, a circular array, a spherical array, a spiral array, a multi-mode array, and a compact array;

[0043] The plurality of microphone arrays are distributedly arranged in the soundproof box.

[0044] According to the closed container leakage detection system provided by the present invention, a camera is integrated in at least one of the microphone arrays.

[0045] According to the closed container leakage detection system provided by the present invention, an automatic joint is arranged between the gas outlet port of the pressurizing device and the gas inlet port of the closed container.

[0046] The present invention also provides an electronic device, 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, a closed container leakage detection method as described above is implemented.

[0047] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the closed container leakage detection method as described in any one of the above is implemented.

[0048] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the closed container leakage detection method as described above is implemented.

[0049] The closed container leakage detection method, device and system provided by the present invention can quickly realize no-dead-angle leakage detection of the container under test on the production line by beamforming the microphone array to adaptively scan the frequency range and intensity range, and has higher detection accuracy and lower detection cost, thereby effectively improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 This is one of the flow diagrams of the closed container leakage detection method provided by the present invention.

[0052] Figure 2 This is the second flow chart of the closed container leakage detection method provided by the present invention.

[0053] Figure 3 This is the third flow chart of the closed container leakage detection method provided by the present invention.

[0054] Figure 4 It is a structural schematic diagram of the closed container leakage detection device provided by the present invention.

[0055] Figure 5 It is a structural schematic diagram of the closed container leakage detection system provided by the present invention.

[0056] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] It should be noted that in the description of the present invention, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. The orientation or position relationship indicated by the terms "upper", "lower" and the like is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0059] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.

[0060] Combine the following Figure 1-Figure 5 The closed container leakage detection method, device and system provided by the present invention are described. Unless otherwise specified, the execution subject of these closed container leakage detection methods described below can be a computer, an industrial computer, a mobile terminal or a signal processing module that can perform data processing.

[0061] Figure 1 FIG. 1 is one of the flow diagrams of the closed container leakage detection method provided by the present invention, such as Figure 1 As shown, including but not limited to the following steps:

[0062] Step 101: receiving a first audio signal collected by a microphone array arranged in a space outside a sealed container, so as to determine a first angle range of the microphone array according to an audio feature of the first audio signal.

[0063] First, the present invention arranges at least one microphone array in the space outside the sealed container, wherein each microphone array is composed of a plurality of microphones, and the positions and spacings of the microphones constituting the microphone array can be optimized according to the size and shape of the sealed container to ensure that the weak audio signals leaking from the sealed container can be captured. The microphone array can be connected to the signal processor by wire or wirelessly. For example, the microphones constituting each microphone array can be specifically arranged in one of the array arrangement forms such as a linear array, a planar array, a circular array, a spherical array, a spiral array, a multi-mode array, a compact array, etc.

[0064] It should be noted that before conducting a closed container leak detection, the closed container to be tested will be pressurized by a pressurizing device so that the air pressure inside the closed container is greater than the air pressure outside the container. In this way, once the closed container leaks, the gas in the container will be quickly discharged outward through the leakage point, thereby generating an audio signal.

[0065] When conducting a leak detection on a sealed container, the microphone array will be activated to collect the initial audio signal in the space outside the sealed container, i.e., the first audio signal. When a leak occurs in the sealed container, the first audio signal may contain a variety of interfering sound components such as environmental noise and mechanical vibration in addition to the weak audio signal generated at the leak point. When there is no leak in the sealed container, the first audio signal will not contain the audio signal generated at the leak point.

[0066] Furthermore, after acquiring the first audio signal collected by the microphone array, the first angle range where the leakage sound may exist can be roughly determined by analyzing the audio features (such as frequency, intensity, etc.) of the first audio signal and combining some prior knowledge.

[0067] Specifically, the first angle range can be understood as the horizontal angle area and the elevation angle area between the center of the microphone array and the audio signal source that may generate the first audio signal. The horizontal angle area and the elevation angle area refer to the azimuth angle range of the audio signal source relative to the center of the microphone array.

[0068] The horizontal angle usually refers to the angle between the audio signal source on the horizontal plane and a reference direction (such as the center line of the microphone array). The pitch angle refers to the angle between the audio signal source and the horizontal plane where the microphone array is located, that is, the up and down tilt angle of the sound source relative to the horizontal plane.

[0069] Therefore, the three-dimensional spatial position of the audio signal source that may generate the first audio signal is jointly determined by the two angle regions, the horizontal angle region and the pitch angle region, which is figuratively referred to as a first angle range in the present invention.

[0070] Step 102: Control the microphone array to collect multiple channels of second audio signals within the first angle range.

[0071] The different second audio signals are acquired by scanning according to parameter combinations of different frequency ranges and intensity ranges.

[0072] Within the determined first angle range, the microphone array can be controlled to scan according to different frequency range and dynamic range parameter combinations to collect multiple channels of second audio signals.

[0073] The purpose of this step is to capture audio signals that may be caused by leakage by changing the acquisition parameters such as frequency range and dynamic range, while providing a data basis for subsequent beamforming algorithms.

[0074] Dynamic range refers to the signal strength of an audio signal, indicating the range between the weakest and strongest sounds that an audio signal can produce. It can be specifically expressed as the ratio between the minimum audible level (usually the noise level) and the maximum undistorted level, usually in decibels (dB). Therefore, dynamic range describes the range of variation in signal strength of an audio signal.

[0075] In the collected audio signal, sound components of different intensities may contain different information. By adjusting the dynamic range, sound components of specific intensities can be highlighted or suppressed, thereby enhancing the recognition of leakage sounds, especially improving the ability to capture weak leakage sounds, so as to more accurately determine whether there is a leak in a closed container.

[0076] Assuming that the determined first angle range is an angle range of 30° to 60° and the ambient noise is approximately 40dB, then in step 102, the microphone array will be controlled to scan within the angle range of 30° to 60°, first collecting in a low frequency band (such as 20Hz-200Hz) and a high intensity range (such as 100dB), and then gradually adjusting to a high frequency band (such as 2kHz-20kHz) and a low intensity range (such as 30dB), and so on, until all possible frequency range and intensity range parameter combinations are covered.

[0077] Step 103: Perform beamforming on the multiple second audio signals to determine a third audio signal with the strongest signal.

[0078] The collected multi-channel second audio signals are subjected to a beamforming process, wherein beamforming is a signal processing technology that adjusts the signal phase and gain of each microphone in the microphone array so that the output signal of the entire microphone array is enhanced in a specific direction and suppressed in other directions.

[0079] The audio signal generated by the leakage of a sealed container usually has unique characteristics, such as a specific frequency range, timbre, and intensity, etc. These characteristics make the leakage signal stand out from many interfering noises.

[0080] When the present invention applies beamforming technology to a microphone array, it can focus on a specific angle range and enhance the signal strength within this range. If the leakage signal is located exactly within this focusing range, its strength will be significantly enhanced. During the scanning process, by recording the signal strengths under different parameter combinations and comparing these signal strengths, the strongest audio signal can be selected. Therefore, the third audio signal obtained is most likely generated by the leakage of the closed container because it is most strongly enhanced within a specific angle and frequency range.

[0081] Step 104: determine whether the sealed container has leakage according to the signal gain between the third audio signal and the reference audio signal.

[0082] Furthermore, the third audio signal may be compared with a known reference audio signal in terms of signal gain, wherein the reference audio signal may be an output signal of a microphone array collected in advance and without leakage under the same conditions.

[0083] Whether there is leakage in the sealed container is determined based on whether the gain between the third audio signal and the reference audio signal exceeds a preset gain threshold.

[0084] If the gain is greater than the preset gain threshold, it is considered that there is a leak; otherwise, it is considered that the container is well sealed and there is no leak.

[0085] The closed container leakage detection method provided by the present invention can quickly realize no-dead-angle leakage detection of the container under test on the production line by performing beamforming for scanning the microphone array in an adaptive frequency range and intensity range, and has higher detection accuracy and lower detection cost, thereby effectively improving production efficiency.

[0086] The closed container leakage detection method provided by the present invention, with the help of beamforming technology for microphone arrays, can not only detect whether container leakage occurs, but also accurately locate the exact position of the leakage source.

[0087] Figure 2 FIG. 2 is a flow chart of the closed container leakage detection method provided by the present invention. Figure 2As shown, when the present invention determines that there is a leakage in the sealed container (that is, the signal gain between the third audio signal and the reference audio signal is greater than the gain threshold), the first angle range determined during the rough positioning in step 101 is subdivided, and beamforming processing is re-performed within each finer-grained angle range obtained after the division, thereby obtaining the audio signal with the strongest signal within all fine-grained angle ranges, and then the corresponding angle range can be used as the target leakage area.

[0088] The horizontal angle area and the elevation angle area refer to the azimuth of the audio signal source relative to the microphone array. The horizontal angle usually refers to the angle between the audio signal source on the horizontal plane and a reference direction (such as the front of the microphone array or the center line of the microphone array). The elevation angle refers to the angle between the audio signal source and the horizontal plane where the microphone array is located, that is, the up and down tilt angle of the sound source relative to the horizontal plane. These two angles together determine the three-dimensional spatial position of the audio signal source.

[0089] Therefore, in order to accurately locate the leakage source, it is necessary to be able to measure the actual incident angle of the audio signal in three-dimensional space. The horizontal angle area reflects the direction of the signal in the horizontal plane, while the pitch angle area reflects the direction of the signal in the vertical plane. By expressing the angular range of the audio signal through these two angle areas, the possible incident direction of the audio signal in three-dimensional space can be constructed.

[0090] Figure 3 FIG. 3 is a flow chart of the closed container leakage detection method provided by the present invention. Figure 3 As shown, the present invention provides a specific detection process for a target leakage area, and in the case where it is determined that the sealed container has leakage according to the signal gain between the third audio signal and the reference audio signal, it also includes:

[0091] Step 301: fine-grainedly divide the first angle range to obtain multiple second angle ranges.

[0092] The present invention divides the first angle range after detecting leakage in the sealed container (ie, the signal gain between the third audio signal and the reference audio signal exceeds the gain threshold).

[0093] The first angle range is usually set based on the layout of the microphone array and the expected leakage source position range. Dividing into multiple second angle ranges can more precisely search for the leakage source and improve the accuracy of positioning.

[0094] As an optional embodiment, the first angle range is divided to obtain a plurality of second angle ranges, including:

[0095] A plurality of the second angle ranges are acquired by evenly dividing the horizontal angle area and / or the pitch angle area of ​​the first angle range.

[0096] Assuming that the horizontal angle region of the first angle range is 30° to 60°, and the pitch angle region is -60° to 60°, the horizontal angle region can be evenly divided to obtain n fine-grained second angle ranges; or the pitch angle region can be evenly divided to obtain m fine-grained second angle ranges; or the horizontal angle region and the pitch angle region can be evenly divided to obtain m fine-grained second angle ranges. n fine-grained second angle ranges, wherein n and m are both positive integers greater than 1.

[0097] The size of each second angle range can be adjusted according to actual conditions to balance positioning accuracy and computational complexity. If higher positioning accuracy is required, the first angle range can be divided into more and smaller second angle ranges; if faster processing speed is required, fewer and larger second angle ranges can be divided.

[0098] For example, assuming n=5, by only equally dividing the horizontal angle area, five fine-grained second angle ranges of 30° to 36°, 36° to 42°, 42° to 48°, 48° to 64° and 54° to 60° can be obtained, and the pitch angle area is -60° to 60°.

[0099] For another example, assuming m=5, then by only equally dividing the pitch angle area, we can obtain five fine-grained second angle ranges, namely, the pitch angle area is -60° to -36°, -36° to -12°, -12° to 12°, 12° to 36°, and 36° to 60°, and the horizontal angle area is -30° to 60°.

[0100] Similarly, assuming n=3 and m=5, the first angle range can be evenly divided in both the pitch angle region and the horizontal angle region to obtain 15 fine-grained second angle ranges, which are not enumerated one by one here.

[0101] Step 302: Control the microphone array to collect multiple fourth audio signals within each of the second angle ranges.

[0102] The present invention controls the microphone array to collect multiple fourth audio signals in each second angle range. These signals are collected under the parameter combination of the frequency range and intensity range of the third audio signal to ensure that the collected signals are related to the leakage source.

[0103] In order to accurately collect signals, by adjusting parameters such as the weight and phase of each microphone in the microphone array, the beam of the microphone array can be accurately directed to each second angle range and the collected signal has sufficient strength and clarity to facilitate subsequent analysis and processing.

[0104] Step 303: Perform secondary beamforming on all the fourth audio signals to determine a third angle range where the signal is the strongest.

[0105] In this step, beamforming (referred to as secondary beamforming) is performed on all fourth audio signals to further refine the location of the leakage source. Secondary beamforming can form a narrower beam by adjusting the weight and phase of the microphone array, thereby more accurately pointing to the leakage source.

[0106] After each beamforming, the signal strength within the beam pointing angle range is calculated, and the angle range with the strongest signal is recorded, i.e., the third angle range. This third angle range is usually smaller and more accurate than the previous second angle range, indicating that the leakage source may appear in this smaller range.

[0107] By comparing the signal strengths under different beamforming conditions, the location range of the leakage source can be further narrowed and the positioning accuracy can be improved.

[0108] Step 304: locate the target leakage area of ​​the sealed container according to the third angle range.

[0109] In this step, the specific position of the target leakage area can be located according to the third angle range, the layout of the microphone array and the geometric shape of the container. Specifically, the approximate position of the leakage source can be determined by converting the angle information of the third angle range into the coordinates of the surface of the sealed container.

[0110] Specifically, according to the layout of the microphone array, the geometric shape of the container and the information of the third angle range (including the horizontal angle area and the pitch angle area), the angle information of the third angle range can be converted into specific coordinate information of the surface of the closed container to be measured by using the methods of geometric transformation and coordinate conversion.

[0111] Assuming that the closed container to be tested is a cylindrical pressure vessel, after preliminary signal processing and beam forming, the third angle range is determined, for example, the horizontal angle range is 30° to 45°, and the elevation angle range is -15° to 15°.

[0112] For ease of description, for the point value with a horizontal angle of 37° and a pitch angle of -5° in the third angle range, this angle range can be converted into specific coordinate information on the surface of the sealed container according to the layout of the microphone array and the geometric shape of the container. For example, it is finally confirmed that the point at a height of 80 cm from the bottom of the sealed container and 30 cm away from a target point along the circumferential direction is the leakage point corresponding to the leakage source.

[0113] Similarly, the third angle range corresponds to an area on the surface of the closed container where the leakage source may exist.

[0114] As an optional embodiment, the present invention provides an implementation method for converting this angle range into specific coordinate information of the surface of a closed container based on the layout of the microphone array and the geometric shape of the container, which mainly includes but is not limited to: Step 1, taking the center of the microphone array as the origin, and determining a preset direction of the microphone array as the X-axis or Y-axis based on the layout of the microphone array and the geometric shape of the container, to establish a two-dimensional or three-dimensional reference coordinate system for the microphone array.

[0115] Step 2, using mathematical tools such as trigonometric functions, converts the angle information of the third angle range into coordinate values ​​relative to the reference coordinate system of the microphone array, which mainly involves two-dimensional or three-dimensional geometric transformations, such as rotation, translation, etc. It should be noted that since the geometric shape of the closed container to be tested may be irregular, when performing geometric transformation, it is generally considered to be equivalent to a regular cubic structure according to the shape and size of the closed container to be tested, such as: sphere, cylinder, cuboid, etc. or a combination of these regular cubes.

[0116] Step 3: Convert the coordinate values ​​corresponding to the angle information of the third angle range in the reference coordinate system and the reference coordinate system into specific coordinates on the surface of the sealed container. This step can be achieved by establishing a three-dimensional coordinate system on the surface of the sealed container and mapping the coordinate values ​​corresponding to the angle information of the third angle range in the reference coordinate system of the microphone array to the three-dimensional coordinate system, thereby obtaining the specific coordinates of the leakage source on the surface of the sealed container to be tested.

[0117] The closed container leakage detection method provided by the present invention can meet the leakage detection needs in different environments by dividing multiple second angle ranges and performing secondary beamforming, and adopting a multi-frequency and multi-dynamic range scanning method, and can search for the location of the leakage source more precisely, thereby improving the accuracy of positioning. The entire detection process is efficient and fast, and can complete the positioning of the leakage source in a short time, providing strong support for subsequent repair and treatment work.

[0118] Based on the content of the above embodiment, as an optional embodiment, after locating the target leakage area of ​​the closed container according to the third angle range, the method further includes:

[0119] Acquire a target image of the target leakage area;

[0120] The target image is fused with the actual image of the sealed container to obtain a leakage location image.

[0121] The present invention can ensure that the image of the target leakage area can be accurately and clearly captured by arranging an image acquisition device (such as a camera) in the outer space of the closed container or directly integrating the camera into the microphone array. According to the third angle range determined previously, the image acquisition device is started and the viewing angle and focal length of the camera are adjusted to ensure that the image of the target leakage area can be clearly captured.

[0122] The acquired images can be preprocessed, including denoising, contrast enhancement, edge detection, etc., to improve the quality and clarity of the target image.

[0123] Of course, in the preprocessed image, features related to the target leakage area can also be extracted from the collected image with the help of image recognition algorithm or machine learning algorithm to further locate the target image of the target leakage area where the leakage point is located.

[0124] After obtaining the target image of the target leakage area, the next step is to fuse this image with the actual image of the sealed container to generate a leakage location image, which can be achieved by the following steps:

[0125] The spatial correspondence between the target image and the actual image can be determined by extracting image feature points between the target image and the actual image, and performing image transformation and calibration based on these image feature points.

[0126] According to the spatial correspondence, the target image is superimposed on the actual image and fused to obtain the leakage localization image.

[0127] Finally, the obtained leakage locating image can be displayed to the operator through a display device so that the leakage position can be found quickly and accurately and corresponding measures can be taken.

[0128] The closed container leakage detection method provided by the present invention can generate an intuitive and easy-to-understand leakage location image by acquiring a target image of the target leakage area and fusing it with the actual image of the closed container. By combining audio signal positioning and image recognition technology, the intuitive, accurate and rapid positioning of the target leakage area of ​​the closed container is achieved, providing strong support for subsequent repair and treatment work.

[0129] Based on the content of the above embodiment, as an optional embodiment, determining the first angle range of the microphone array according to the audio feature of the first audio signal includes:

[0130] Determining the first angle range according to the audio feature and prior information for leak detection of the sealed container;

[0131] The prior information includes different audio features when leakage occurs at different parts of the sealed container, historical leakage data of the sealed container, and one or more of the design parameters of the sealed container.

[0132] Generally speaking, when dividing the first angle range, the first angle range can be made to completely cover the sealed container to be tested. However, sometimes, in order to take into account the detection efficiency, the first angle range can be appropriately narrowed based on a heuristic algorithm.

[0133] Specifically, the present invention may use a heuristic algorithm to roughly divide the first angle range of the microphone array, that is, to roughly estimate the horizontal angle area and the elevation angle area of ​​the microphone array.

[0134] The present invention uses a heuristic algorithm to roughly estimate the horizontal angle area and the elevation angle area of ​​the microphone array, which is an intelligent, experience-based and / or data-driven method to preliminarily estimate the horizontal and elevation angle ranges where the leakage source may exist. Specifically, it is mainly based on historical detection results, common locations of leakage sources, audio characteristics of the first audio signal and other factors.

[0135] For example, based on historical leak detection cases or closed container design parameters, it is determined that most leak sources are located on the top or side of the closed container. The heuristic algorithm can use this information to first identify the top and side of the closed container to be tested as potential leak source areas, and then roughly divide the horizontal angle areas and pitch angle areas corresponding to these areas.

[0136] For another example, based on historical experience, an audio feature library can be constructed by collecting audio features (pitch, timbre, loudness, etc., and other time domain features, frequency domain features, etc.) of audio signal samples generated by different parts of a sealed container when leakage occurred in the past. In the actual detection process, after receiving the first audio signal, the corresponding audio features are extracted, and then the audio features are matched in the audio feature library to determine the leakage parts where leakage may exist. Finally, the first angle range where leakage may exist can be quickly divided according to the distribution positions of these leakage parts in the sealed container and the positional relationship between them and the microphone array.

[0137] The closed container leakage detection method provided by the present invention roughly divides the supervision range of the microphone array through a heuristic algorithm combined with prior information. On the one hand, it can quickly lock the potential leakage source area, reducing the time for comprehensive scanning of the entire closed container, thereby improving the efficiency of leakage detection; on the other hand, by utilizing historical detection results and common locations of leakage sources, it can more accurately estimate the areas where leakage sources may exist, so that the microphone array can more centrally collect and analyze audio signals in these areas, thereby enhancing the targeted detection.

[0138] Figure 4 Schematic diagram of the structure of the closed container leakage detection device provided by the present invention. Figure 4 As shown, mainly including but not limited to:

[0139] The audio receiving unit 41 is mainly used to receive a first audio signal collected by a microphone array arranged in the outer space of the sealed container, so as to determine a first angle range of the microphone array according to the audio characteristics of the first audio signal. The air pressure inside the sealed container is greater than the air pressure outside the container;

[0140] The acquisition control unit 42 is mainly used to control the microphone array to acquire multiple second audio signals within the first angle range. Different second audio signals are acquired by scanning according to different frequency range and intensity range parameter combinations;

[0141] The beamforming unit 43 is mainly used to perform beamforming on the multiple second audio signals to determine the third audio signal when the signal is the strongest;

[0142] The data processing unit 44 is mainly used to determine whether there is leakage in the sealed container according to the signal gain between the third audio signal and the reference audio signal.

[0143] It should be noted that the sealed container leakage detection device provided by the present invention can execute the sealed container leakage detection method described in any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0144] The closed container leakage detection device provided by the present invention can quickly realize no-dead-angle leakage detection of the container under test on the production line by beamforming the microphone array to adaptively scan the frequency range and intensity range, and has higher detection accuracy and lower detection cost, thereby effectively improving production efficiency.

[0145] Figure 5 Schematic diagram of the structure of the closed container leakage detection system provided by the present invention. Figure 5 As shown, it mainly includes but is not limited to: a pressurizing device 2, a signal processing module 3 and a microphone array 4;

[0146] The pressurizing device 2 is used to inject compressed gas into the sealed container 1 before testing, so that the air pressure inside the sealed container 1 is greater than the air pressure outside the container;

[0147] The microphone array 4 sends the collected audio signal to the signal processing module 3 through the communication connection between the microphone array 4 and the signal processing module 3;

[0148] The signal processing module 3 is used to execute the closed container leakage detection method provided by any of the above embodiments when running.

[0149] The pressurizing device 2 may be an air compressor, which may be one or a combination of a piston air compressor, a screw air compressor, a scroll air compressor, a centrifugal air compressor, a vane air compressor, a roots air compressor, a turbine air compressor, a membrane air compressor, an oil-free air compressor, a variable frequency air compressor, etc. The main function of the pressurizing device 2 is to inject gas into the sealed container 1, such as adding compressed air into the sealed container 1. Whether the air tightness of the sealed container 1 meets the requirements is confirmed by measuring whether there is compressed air leaking from the sealed container 1.

[0150] The microphone array is an array combination composed of analog condenser microphones, micro-electromechanical system microphones, etc., arranged in a certain shape, through a specific arrangement method, for example: one microphone array is arranged in front and behind respectively, one microphone array is arranged on the four sides of the sealed container 1, two microphone arrays are arranged around the sealed container 1 at an interval of 120°, or microphone arrays are arranged on the six sides of the sealed container 1, namely, front, back, left, right, top and bottom.

[0151] As an optional embodiment, refer to Figure 5 As shown, the multiple microphones in each of the microphone arrays are distributed according to at least one of a linear array, a planar array, a circular array, a spherical array, a spiral array, a multi-mode array, and a compact array.

[0152] Optionally, the closed container leakage detection system provided by the present invention further includes a soundproof box 8; when performing leakage detection on the closed container 1, the closed container 1 is located in the soundproof box 8. Correspondingly, all the microphone arrays 4 are also arranged in the soundproof box 8 and distributed around the closed container 1.

[0153] The main function of the soundproof box 8 is to isolate the noise generated by other workstation equipment on the production line to avoid interference with the weak audio signal caused by leakage.

[0154] All microphone arrays 4 are connected to the signal processing module 3 for communication, and send the collected audio signals to the signal processing module 3 in real time for the signal processing module 3 to analyze.

[0155] The signal processing module 3 executes the closed container leakage detection method provided by any of the above embodiments during specific operation, and sends the detection result to the data storage device 5 for archiving in real time for relevant staff to call.

[0156] Among them, the data storage device 5 can be a device with data storage media such as a server, an industrial computer or a disk. Its main purpose is to store the identity information of the inspected sealed container, the inspection entry time, the inspection results, the exit time, the leakage location and the leakage degree, so as to facilitate the subsequent rapid rework at the rework station, as well as statistical analysis and traceability of the data.

[0157] The closed container leakage detection system provided by the present invention may further include an alarm device 6 and a display device 7 .

[0158] When the signal processing module 3 detects leakage in the sealed container 1, it will send an alarm indication to the alarm device 6 to drive the alarm device 6 to generate an alarm.

[0159] At the same time, the signal processing module 3 will also send the relevant information of the located target leakage area of ​​the sealed container to the display device 7, so that the display device 7 can display the relevant information of the target leakage area to relevant personnel.

[0160] Optionally, the soundproof box 8 is a control door that can be opened and closed automatically on both sides. The door on one side is opened during automatic loading, and is closed after the sealed container 1 is automatically loaded and fixed. During the entire loading process, the door on the other side is closed. The door on the other side is opened during the unloading process after the leakage detection is completed, and is closed when the sealed container 1 is removed from the detection station and transported to the next station.

[0161] Correspondingly, the closed container leakage detection system provided by the present invention may also include an automatic loading and unloading mechanism, which may be a combination of one or more of a manipulator, a clamp, a belt conveyor, a roller loading device, a chain loading device, a hydraulic or pneumatic loading device, a magnetic loading device, etc., and its main function is to automatically transport the closed container 1 from the previous station of the production line and fix it to the detection station in the soundproof box 8. At the same time, after completing the leakage detection of the closed container 1, it is removed from the detection station and transported to the next station.

[0162] like Figure 5 As shown, the automatic loading and unloading mechanism is divided into a loading mechanism 9 and a unloading mechanism 10, which are respectively arranged at the control doors on both sides of the sound insulation box 8.

[0163] Optionally, the present invention also integrates a camera in at least one of the microphone arrays to capture a target image of the target leakage area when it is determined that there is a leakage in the closed container 1 and the target leakage area is located, and the captured target image is sent to the signal processing module 3, so that the signal processing module 3 fuses the target image with the actual image of the closed container to obtain a leakage locating image.

[0164] Finally, the signal processing module 3 may send the leakage localization image to the data storage device 5 for archiving, and simultaneously send the leakage localization image to the display device 7 for display.

[0165] Optionally, the closed container leakage detection system provided by the present invention may further include an automatic connector 11 provided between the gas outlet port of the pressurizing device 2 and the gas inlet port of the closed container 1. The automatic connector 11 may include a male plug and a female plug, and an electric magnetic device may be installed through the gas outlet port of the pressurizing device 2 and the gas inlet port of the closed container 1, respectively, so that once the distance between the gas outlet port and the gas inlet port is less than a preset distance, the automatic attraction and connection establishment may be performed according to the received connection drive.

[0166] The closed container leakage detection system provided by the present invention can meet the detection requirements of blind-angle leakage detection of the container under test on the production line by adaptively scanning the frequency range and intensity range of the microphone array through beam forming, and has higher detection accuracy and lower detection cost, thereby effectively improving production efficiency.

[0167] Figure 6 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 6As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute a closed container leakage detection method, the method comprising: receiving a first audio signal collected by a microphone array arranged in the outer space of the closed container, and determining a first angle range of the microphone array according to the audio characteristics of the first audio signal; the air pressure inside the closed container is greater than the air pressure outside the container; controlling the microphone array to collect multiple second audio signals within the first angle range, and different second audio signals are obtained by scanning according to different frequency ranges and intensity ranges; performing beamforming on the multiple second audio signals to determine a third audio signal when the signal is the strongest; judging whether the closed container has a leak according to the signal gain between the third audio signal and the reference audio signal.

[0168] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an 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, and the computer software product is stored in a storage medium, including a number of 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. Various media that can store program codes.

[0169] On the other hand, the present invention also 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 closed container leakage detection method provided by the above-mentioned embodiments, and the method includes: receiving a first audio signal collected by a microphone array arranged in the space outside the closed container, and determining a first angle range of the microphone array according to the audio characteristics of the first audio signal; the air pressure inside the closed container is greater than the air pressure outside the container; controlling the microphone array to collect multiple second audio signals within the first angle range, and different second audio signals are obtained by scanning according to parameter combinations of different frequency ranges and intensity ranges; performing beamforming on the multiple second audio signals to determine the third audio signal when the signal is the strongest; and judging whether there is a leak in the closed container based on the signal gain between the third audio signal and the reference audio signal.

[0170] On the other hand, the present invention also 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 closed container leakage detection method provided in the above-mentioned embodiments, the method comprising: receiving a first audio signal collected by a microphone array arranged in the space outside the closed container, to determine a first angle range of the microphone array according to the audio characteristics of the first audio signal; the air pressure inside the closed container is greater than the air pressure outside the container; controlling the microphone array to collect multiple second audio signals within the first angle range, different second audio signals are obtained by scanning according to parameter combinations of different frequency ranges and intensity ranges; performing beamforming on the multiple second audio signals to determine a third audio signal when the signal is the strongest; and judging whether there is a leak in the closed container according to the signal gain between the third audio signal and the reference audio signal.

[0171] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0172] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0173] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A closed container leakage detection method, characterized in that: include: Receiving a first audio signal collected by a microphone array arranged in a space outside a sealed container, and determining a first angle range of the microphone array according to an audio feature of the first audio signal; the air pressure inside the sealed container is greater than the air pressure outside the container; Controlling the microphone array to collect multiple second audio signals within the first angle range, wherein different second audio signals are obtained by scanning according to parameter combinations of different frequency ranges and intensity ranges; Performing beamforming on the multiple second audio signals to determine a third audio signal with the strongest signal; Whether there is leakage in the sealed container is determined according to the signal gain between the third audio signal and the reference audio signal.

2. The closed container leakage detection method according to claim 1, characterized in that: In the case where it is determined that the sealed container has leakage according to the signal gain between the third audio signal and the reference audio signal, the method further includes: Dividing the first angle range to obtain a plurality of second angle ranges; Controlling the microphone array to collect multiple fourth audio signals within each of the second angle ranges; the multiple fourth audio signals are all collected under a parameter combination of a frequency range and an intensity range of the third audio signal; Performing secondary beamforming on all the fourth audio signals to determine a third angle range when the signal is strongest; The target leakage area of ​​the sealed container is located according to the third angle range.

3. The closed container leakage detection method according to claim 2, characterized in that: The first angle range is divided to obtain a plurality of second angle ranges, including: A plurality of the second angle ranges are acquired by evenly dividing the horizontal angle area and / or the pitch angle area of ​​the first angle range.

4. The closed container leakage detection method according to any one of claims 2 to 3, characterized in that: After locating the target leakage area of ​​the closed container according to the third angle range, the method further includes: Acquire a target image of the target leakage area; The target image is fused with the actual image of the sealed container to obtain a leakage location image.

5. The closed container leakage detection method according to claim 1, characterized in that: The determining a first angle range of the microphone array according to the audio feature of the first audio signal comprises: Determining the first angle range according to the audio feature and prior information for leak detection of the sealed container; The prior information includes different audio features when leakage occurs at different parts of the sealed container, historical leakage data of the sealed container, and one or more of the design parameters of the sealed container.

6. The closed container leakage detection method according to claim 1, characterized in that: The step of judging whether the sealed container has a leak according to the signal gain between the third audio signal and the reference audio signal specifically includes: When the signal gain is greater than a preset gain threshold, it is determined that there is a leak in the sealed container; When the signal gain is not greater than the preset gain threshold, it is determined that there is no leakage in the sealed container.

7. A closed container leakage detection device, characterized in that: include: an audio receiving unit, configured to receive a first audio signal collected by a microphone array arranged in a space outside a sealed container, so as to determine a first angle range of the microphone array according to an audio feature of the first audio signal; the air pressure inside the sealed container is greater than the air pressure outside the container; A collection control unit, used for controlling the microphone array to collect multiple second audio signals within the first angle range, wherein different second audio signals are obtained by scanning according to parameter combinations of different frequency ranges and intensity ranges; A beamforming unit, configured to perform beamforming on the multiple second audio signals to determine a third audio signal when the signal is the strongest; A data processing unit is used to determine whether there is leakage in the sealed container according to the signal gain between the third audio signal and the reference audio signal.

8. A closed container leakage detection system, characterized in that: include: A pressurizing device, a signal processing module, and a microphone array; The pressurizing device is used to inject compressed gas into the sealed container before testing, so that the air pressure inside the sealed container is greater than the air pressure outside the container; The microphone array sends the collected audio signal to the signal processing module through the communication connection with the signal processing module; The signal processing module is used to execute the closed container leakage detection method described in any one of claims 1-6 when running.

9. The closed container leakage detection system according to claim 8, characterized in that: Also included is a soundproof box; When conducting a closed container leakage detection, the closed container is located in the soundproof box; The microphone array is arranged in the soundproof box.

10. The closed container leakage detection system according to claim 9, characterized in that: It also includes loading and unloading mechanisms; The loading and unloading mechanism is used to transport and fix the sealed container from the previous station to the detection station located in the soundproof box.

11. The closed container leakage detection system according to any one of claims 9 to 10, characterized in that: The microphone array is multiple; The plurality of microphones in each of the microphone arrays are distributed in at least one of a linear array, a planar array, a circular array, a spherical array, a spiral array, a multi-mode array, and a compact array; The plurality of microphone arrays are distributedly arranged in the soundproof box.

12. The closed container leakage detection system according to claim 11, characterized in that: A camera is integrated into at least one of the microphone arrays.

13. The closed container leakage detection system according to any one of claims 8 to 10, characterized in that: An automatic joint is mounted on the air outlet port of the pressurizing device and the air inlet port of the sealed container.

14. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the closed container leakage detection method according to any one of claims 1 to 6 is implemented.

15. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the closed container leakage detection method according to any one of claims 1 to 6 is implemented.

16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the closed container leakage detection method according to any one of claims 1 to 6 is implemented.

Images