An online monitoring device for fruit mildew heart disease based on acoustic vibration and a method thereof

Abstract

The present application relates to fruit quality detection technical field, especially in kind based on acoustic vibration fruit mildew heart disease on-line monitoring device and method thereof, including annular synchronous sound signal acquisition unit, conveying belt and excitation unit. Fruit is placed on the free fruit cup on the conveying belt, along with the movement of the conveying belt, the excitation unit enters the sound signal acquisition area. When the excitation unit reaches the sound signal acquisition sleeve below, the lifting rod will quickly drive the acquisition sleeve to move downward, and tightly wrap the top of the fruit. Subsequently, the resonant horn is driven by the power amplifier, outputs the sinusoidal sweep signal, and excites the fruit to produce sound signals in the form of forced vibration, which is accurately detected by the microphone, and is collected and transmitted to the computer for saving by the signal acquisition module. The sound signal is input into the established fruit quality prediction model for prediction to obtain the predicted quality of the fruit. The present application can realize rapid, accurate and non-destructive detection of multiple fruits.

Description

Technical Field

[0001] This invention relates to the field of fruit quality testing technology, and in particular to an online monitoring device and method for fruit core rot based on acoustic vibration. Background Technology

[0002] my country's fruit industry has become the third largest industry after vegetables and grains, and is an important component of my country's modern agricultural development. In 2021, my country's fruit production reached 299.7 million tons, making it the world's largest fruit producer. However, its total exports were only 35.5 million tons, resulting in a trade deficit of US$9.16 billion. This is mainly because, although my country's fruit industry has resource advantages, it lags significantly behind Western countries in the development of high-end fruit industries, leading to the predicament of "low-price sales" for Chinese fruit exports. Therefore, developing rapid fruit quality testing and enabling the screening and classification of fruit quality will help improve the development of my country's fruit industry and its international competitiveness.

[0003] Non-destructive testing (NDT) technology for fruits is a testing method that obtains internal and external information about fruits without damaging their original physical and chemical properties. Compared with traditional fruit quality testing methods, it has advantages such as high efficiency and non-destructiveness. Acoustic vibration methods are characterized by simple operation, rapid analysis, low cost, and suitability for online testing, making them one of the most common methods for fruit quality testing. The excitation sources for acoustic vibration testing of fruit quality can be divided into two types: impact vibration and forced vibration. Impact vibration methods use various tools (such as impact hammers, pressurized air valves, pulsed lasers, etc.) to apply a transient force to the fruit, causing it to vibrate freely. This method is considered relatively suitable for online testing. However, impact vibration has a short duration, low impact energy, and poor signal quality, making it difficult to obtain good hardness prediction accuracy. Forced vibration methods use an excitation source (such as a vibration table, piezoelectric transducer, etc.) to excite fruit vibration by sweeping frequencies. Forced vibration methods can obtain better signal quality, but the required excitation time is longer and is generally considered unsuitable for online testing.

[0004] Furthermore, the effectiveness of acoustic vibration nondestructive testing of fruit is closely related to the selection of vibration characteristic parameters and the modeling method. In the past few decades, parameters such as resonant frequency have often been used to predict fruit quality or identify defects; however, these parameters are often affected by fruit size, weight, and shape, leading to insufficient information and inaccurate results. Therefore, to ensure the accuracy of acoustic vibration in detecting fruit quality, selecting appropriate acoustic excitation methods and acoustic feature extraction methods is crucial. Thus, developing an online acoustic vibration fruit quality detection system and a high-accuracy fruit quality prediction model is particularly important. Summary of the Invention

[0005] This invention aims to at least improve one of the technical problems existing in the prior art. To this end, this invention uses a resonant horn as the forced vibration excitation source and constructs a rapid and accurate online detection device based on acoustic vibration to achieve online monitoring of fruit core disease.

[0006] According to a first aspect of the present invention, an online monitoring device for fruit core rot based on acoustic vibration includes a conveyor belt, wherein the device further includes: A circular synchronous sound signal acquisition unit is disposed above the conveyor belt. The circular synchronous sound signal acquisition unit includes a sound signal acquisition sleeve, a microphone, a circular conveyor device, and a lifting rod. The circular conveyor device is disposed above the conveyor belt. A lifting rod is installed on the moving slide rail of the circular conveyor device. A sound signal acquisition sleeve is fixedly installed at the driving end of the lifting rod away from the circular conveyor device. The sound signal acquisition sleeve has a sleeve cup. A microphone is fixedly installed at the end of the sound signal acquisition sleeve connected to the driving end of the lifting rod. A free-form fruit cup is placed on the conveyor belt and moves with the conveyor belt. The free-form fruit cup has a cavity, and a resonant horn is installed in the cavity. The resonant horn is connected to an external power amplifier. An excitation unit is installed on the free-form fruit cup located above the resonant horn. A data acquisition module, which is electrically connected to the microphone; The data processing unit is electrically connected to the data acquisition module and to the power amplifier. In one possible implementation of the first aspect, the sound signal acquisition sleeve, driven by a ring-shaped conveyor, moves synchronously with the integrated free-form fruit cup excitation unit, ensuring that the acoustic vibration detection of the fruit is completed in a very short time. After the detection is completed, the sound acquisition sleeve is quickly reset by the lifting rod, preparing for the next detection.

[0007] According to a second aspect of the present invention, a method for online monitoring of fruit core rot based on acoustic vibration is provided, wherein the method employs the aforementioned online monitoring device for fruit core rot based on acoustic vibration for detection, and includes the following steps: Step S100: Establish an online monitoring scenario for fruit core rot based on acoustic vibration. The scenario includes an online monitoring device for fruit core rot based on acoustic vibration. Turn on the online monitoring device for fruit quality. Step S200: Based on the sinusoidal sweep frequency signal output by the resonant horn, the fruit under test is excited to generate a sound signal by forced vibration, and the sound signal is acquired and saved; Step S300: After acquiring the sound signal, the fruit to be tested is cut in half along the equator and the cross-sectional image is captured by a camera. Then, OpenCV is used to process the cross-sectional image of the fruit to be tested to calculate the degree of lesion in the core rot area of ​​the fruit to be tested. In step S400, the saved sound signal is processed in the data processing unit, and the sound signal is converted into audio frequency domain data through a fast Fourier transform. The audio frequency domain data is used as input to the fruit quality prediction model, and then the fruit quality prediction model outputs the predicted quality of the fruit.

[0008] In one possible implementation of the second aspect, in step S200, the sinusoidal sweep frequency signal output by the resonant horn specifically means that the resonant horn, driven by the power amplifier, outputs a sinusoidal sweep frequency signal of 100 Hz to 1500 Hz within 0.5 seconds, and excites the fruit under test to generate a sound signal by forced vibration. The sound signal is detected by the microphone in the sound signal acquisition sleeve, and is acquired in real time by the signal acquisition module and transmitted to the data processing unit for storage.

[0009] In one possible implementation of the second aspect, step S300, processing the cross-sectional image of the fruit to be tested using OpenCV specifically includes: firstly, detecting the outline of the cross-section of the fruit to be tested using edge detection, calculating the number of pixels S1 of the fruit to be tested, then performing grayscale processing on the image, using threshold segmentation, dilation and erosion to obtain the complete lesion area and calculating the number of pixels S2, and finally using the ratio of pixels S2 / S1 to represent the degree of apple lesion. Figure 2 Apples with different degrees of mold were displayed. Based on previous research and the sample conditions of this experiment, the apples were divided into healthy fruit, mildly diseased fruit (>0% and ≤7%), moderately diseased fruit (>7% and ≤15%), and severely diseased fruit (>15%).

[0010] In one possible implementation of the second aspect, in step S300, a fast Fourier transform is performed on the original sound signal. When performing the fast Fourier transform, it is necessary to select an appropriate number of analysis points according to the sampling frequency and sampling time to convert the sound signal from a time-domain signal into a sound image.

[0011] In one possible implementation of the second aspect, the fruit to be tested includes apples and yellow peaches.

[0012] In one possible implementation of the second aspect, the fruit quality prediction model outputs predicted quality of the fruit to be tested, including fruit firmness, edible period, shelf life, and internal diseases.

[0013] The online monitoring device for fruit core rot based on acoustic vibration according to embodiments of the present invention has the following advantages compared with the prior art: (1) This invention uses a resonant horn as the excitation source for the forced excitation method. The fruit to be tested is placed directly in the free-form fruit cup and comes into contact with the vibrating plate of the resonant horn at the bottom of the free-form fruit cup. At this time, the vibration energy of the resonant horn is directly transmitted to the fruit in a solid-solid coupling manner. The fruit directly serves as the vibration medium for sound wave generation, allowing the fruit to emit sound waves directly, resulting in a significant advantage in transmission efficiency. In addition, when the horn excites the fruit, the vibration energy can be more concentrated on the fruit itself, with less divergent vibration energy and a better excitation effect. By outputting a frequency sweep signal of a certain energy level (up to 30 KHz to 18 KHz), fruits with different peel thicknesses can be excited, making it suitable for the detection of various fruits.

[0014] (2) The ring synchronous sound signal acquisition unit designed in this invention makes it possible to apply the forced vibration mode to the online detection of fruit quality. While obtaining high-quality signals, it realizes rapid and continuous detection of multiple fruits, which greatly improves detection efficiency and accuracy.

[0015] (3) This invention uses the entire acoustic frequency domain data as input to the fruit quality prediction model. Compared with the method of using resonance parameters as input to the fruit quality prediction model, this method has higher detection accuracy and feasibility, and the model has higher prediction accuracy.

[0016] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the overall structure of an online monitoring device for fruit core rot based on acoustic vibration according to an embodiment of the present invention; Figure 2 This is a schematic diagram of an online monitoring method for fruit core rot based on acoustic vibration according to an embodiment of the present invention; Figure 3 This is an example diagram illustrating the degree of core rot in an apple, based on the present invention. Figure 4 This is a flowchart for calculating the degree of core rot according to the present invention, using apples as an example; Figure 5 This is a confusion matrix for identifying moldy core disease results according to an embodiment of the present invention, using apples as an example.

[0019] Figure label: 1. Circular synchronous sound signal acquisition unit; 2. Integrated free-form fruit cup excitation unit; 3. Sound signal acquisition sleeve; 4. Lifting rod; 5. Circular conveyor device; 6. Free-form fruit cup; 7. Fruit; 8. Conveyor belt; 9. Resonant speaker; 10. Microphone; 11. Data acquisition module; 12. Power amplifier; 13. Data processing unit. Detailed Implementation

[0020] The embodiments of the present invention are described in detail below. The embodiments described with reference to the accompanying drawings are exemplary. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0021] It should be noted that when a component is said to be "fixed to" another component, it can be directly attached to the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0023] The terms "first," "second," "third," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects and not to describe a particular order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, it may include a series of steps or units, or optionally, steps or units not listed, or other steps or units inherent to these processes, methods, products, or devices.

[0024] The accompanying drawings show only the portions relevant to this application, not all of them. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as sequential processes, many of these operations may be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations may be rearranged. The process may be terminated when its operation is completed, but may also have additional steps not included in the drawings. The process may correspond to a method, function, procedure, subroutine, subprogram, etc.

[0025] The terms “component,” “module,” “system,” “unit,” etc., used in this specification are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a unit can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, a thread of execution, a program, and / or distributed between two or more computers. Furthermore, these units can be executed from various computer-readable media on which various data structures are stored. Units can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from a second unit interacting with another unit between a local system, a distributed system, and / or a network; for example, the Internet interacting with other systems via signals).

[0026] like Figure 1 As shown, this embodiment provides an online monitoring device for fruit core rot based on acoustic vibration, including a conveyor belt 8, which further includes: A circular synchronous sound signal acquisition unit 1 is disposed above the conveyor belt 8. The circular synchronous sound signal acquisition unit 1 includes a sound signal acquisition sleeve 3, a microphone 10, a circular conveyor device 5, and a lifting rod 4. The circular conveyor device 5 is disposed above the conveyor belt 8. The circular conveyor device 7 can be configured with a circular track and a moving block driven by a motor, which can make the moving block move in a controlled manner along the circular track (not shown in the figure). The lifting rod 4 is installed on the moving slide rail of the circular conveyor device 5. The sound signal acquisition sleeve 3 is fixedly installed at the driving end of the lifting rod 4 away from the circular conveyor device 5. The sound signal acquisition sleeve 3 has a sleeve cup. The microphone 10 is fixedly installed at the end of the sound signal acquisition sleeve 3 connected to the driving end of the lifting rod 4. A free-form fruit cup 6 is placed on the conveyor belt 8 and moves with the conveyor belt 8. The free-form fruit cup 6 has a cavity, and a resonant horn 9 is installed in the cavity. The resonant horn 9 is connected to an external power amplifier 12. An excitation unit 2 is installed on the free-form fruit cup 6 located above the resonant horn 9. Data acquisition module 11, which is electrically connected to microphone 10; The data processing unit 13 is electrically connected to the data acquisition module 11 and the power amplifier 12. In the specific implementation process, when detecting fruit 7, simply place fruit 7 on the free-form fruit cup 6 on the conveyor belt 8. As the conveyor belt 8 moves, the integrated free-form fruit cup excitation unit 2 will automatically enter the sound signal acquisition area. When the integrated free-form fruit cup excitation unit 2 reaches below the sound signal acquisition sleeve 3, the lifting rod 4 will quickly drive the sound signal acquisition sleeve 3 downward to tightly fit the top of fruit 7. Subsequently, the resonant speaker 9, driven by the power amplifier 12, outputs a 100-1500Hz sinusoidal sweep frequency signal within 0.5 seconds, and excites fruit 7 to generate sound signals through forced vibration. These signals contain the physical characteristics of the fruit. These sound signals are accurately detected by the microphone 10 in the sound signal acquisition sleeve 3, and are collected in real time by the signal acquisition module 11 and transmitted to the data processing unit 13 for storage. Throughout the testing process, the sound acquisition sleeve 3, driven by the annular conveyor 5, moves synchronously with the integrated free-form fruit cup vibration unit 2, ensuring that the acoustic vibration test of the fruit is completed in a very short time. After the test is completed, the sound acquisition sleeve 3 quickly resets under the action of the lifting rod 4, preparing for the next test. The saved sound signal is processed in the data processing unit 13, where it is converted into audio frequency domain data using a Fast Fourier Transform. This audio frequency domain data is then used as input to the fruit quality prediction model, which subsequently outputs the predicted fruit quality.

[0027] The system and method for online detection of fruit quality using acoustic vibration provided by this invention are universal for the quality detection of different fruits. Taking Fuji apples as an example, this invention is used to describe the implementation process of detecting apple core rot. The quality of other fruits can be referred to this embodiment.

[0028] like Figure 2 As shown, this embodiment also provides an online monitoring method for fruit core rot based on acoustic vibration, wherein the method uses the above-mentioned online monitoring device for fruit core rot based on acoustic vibration for detection, and includes the following steps: Step S100: Establish an online monitoring scenario for fruit core rot based on acoustic vibration. The scenario includes an online monitoring device for fruit core rot based on acoustic vibration. Turn on the online monitoring device for fruit quality. Step S200: Based on the sinusoidal sweep frequency signal output by the resonant speaker, the fruit under test is excited to generate a sound signal by forced vibration. The sound signal is acquired and saved. Specifically, the sinusoidal sweep frequency signal output by the resonant speaker is that the resonant speaker outputs a sinusoidal sweep frequency signal of 100 Hz to 1500 Hz within 0.5 seconds under the drive of the power amplifier, and the fruit under test is excited to generate a sound signal by forced vibration. The sound signal is detected by the microphone in the sound signal acquisition sleeve, and is acquired in real time by the signal acquisition module and transmitted to the data processing unit for storage. Step S300: After acquiring the sound signal, the fruit to be tested is cut in half along the equator, and a cross-sectional image is captured with a camera. Then, OpenCV is used to process the cross-sectional image of the fruit to be tested to calculate the degree of lesions in the core rot area of ​​the fruit. The processing procedure of the cross-sectional image of the fruit to be tested using OpenCV is as follows: Figure 4 As shown, firstly, edge detection is used to detect the outline of the cross-section of the fruit to be tested, and the number of pixels S1 of the fruit to be tested is calculated. Then, grayscale processing is performed on the image, and threshold segmentation, dilation and erosion are used to obtain the complete lesion area and the number of pixels S2 is calculated. Finally, the ratio of pixels S2 / S1 is used to represent the degree of apple lesion. Figure 3 Apples with different degrees of mold were displayed. Based on previous research and the sample conditions of this experiment, the apples were divided into healthy fruit, mildly diseased fruit (>0% and ≤7%), moderately diseased fruit (>7% and ≤15%), and severely diseased fruit (>15%). In step S400, the saved sound signal is processed in the data processing unit, and the sound signal is converted into audio frequency domain data through a fast Fourier transform. The audio frequency domain data is used as input to the fruit quality prediction model, and then the fruit quality prediction model outputs the predicted quality of the fruit.

[0029] It should be noted that the fruits to be tested include apples and yellow peaches, but are not entirely limited to these. The predicted quality of the fruits to be tested output by the fruit quality prediction model includes fruit firmness, edible period, shelf life, and internal diseases.

[0030] It should be noted that in step S300, a fast Fourier transform is performed on the original sound signal. When performing the fast Fourier transform, it is necessary to select an appropriate number of analysis points according to the sampling frequency and sampling time to convert the sound signal from a time-domain signal into a sound image.

[0031] This embodiment uses the sound spectrum to train the MLP-Transformer model. The batch size for training the MLP-Transformer model is set to 16, and the training epochs are 200 for each set. The results on the training and prediction sets are shown in Table 1. As can be seen from the table, the MLP-Transformer performs well on the training set, with an accuracy of 100.00% based on the sound spectrum model. Furthermore, the MLP-Transformer model has a good prediction accuracy of 98.62% on the prediction set. This indicates that the MLP-Transformer performs excellently on the apple core rot detection task. Table 2 shows the performance of the sound spectrum-based MLP-Transformer on the prediction set. The results show that the weighted_P, weighted_R, and weighted_F1 of the MLP-Transformer model are 98.64%, 98.62%, and 98.62%, respectively. This indicates that the MLP-Transformer model has good generalization ability for the apple core rot detection task. Furthermore, the R-values ​​in the table for normal samples and severely affected core rot samples reached 100%, indicating that the model completely identified both normal and severely affected core rot samples. The R-values ​​for mild and moderate core rot were 97.56% and 97.14%, respectively. Figure 5 It can be seen that only one sample with mild core rot was misclassified as a sample with moderate core rot, and one sample with moderate core rot was misclassified as a sample with severe core rot. This indicates that the MLP-Transformer model has good recognition ability for both mild and moderate core rot samples.

[0032] Table 1. Training and prediction results of the MLP-Transformer model based on sound spectrum. Table 2 Performance evaluation of the MLP-Transformer model based on sound spectrum on the prediction set. The online monitoring device for fruit core rot based on acoustic vibration according to embodiments of the present invention has the following advantages compared with the prior art: (1) This invention uses a resonant horn as the excitation source for the forced excitation method. The fruit to be tested is placed directly in the free-form fruit cup and comes into contact with the vibrating plate of the resonant horn at the bottom of the free-form fruit cup. At this time, the vibration energy of the resonant horn is directly transmitted to the fruit in a solid-solid coupling manner. The fruit directly serves as the vibration medium for sound wave generation, allowing the fruit to emit sound waves directly, resulting in a significant advantage in transmission efficiency. In addition, when the horn excites the fruit, the vibration energy can be more concentrated on the fruit itself, with less divergent vibration energy and a better excitation effect. By outputting a frequency sweep signal of a certain energy level (up to 30 KHz to 18 KHz), fruits with different peel thicknesses can be excited, making it suitable for the detection of various fruits.

[0033] (2) The ring synchronous sound signal acquisition unit designed in this invention makes it possible to apply the forced vibration mode to the online detection of fruit quality. While obtaining high-quality signals, it realizes rapid and continuous detection of multiple fruits, which greatly improves detection efficiency and accuracy.

[0034] (3) This invention uses the entire acoustic frequency domain data as input to the fruit quality prediction model. Compared with the method of using resonance parameters as input to the fruit quality prediction model, this method has higher detection accuracy and feasibility, and the model has higher prediction accuracy.

[0035] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention.

[0036] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example.

[0037] Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The reference to "embodiment" herein means that a specific feature, structure, or characteristic described in connection with an embodiment can be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily indicate the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0038] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A method for online monitoring of fruit core rot based on acoustic vibration, characterized in that, The detection was performed using an online monitoring device for fruit core rot based on acoustic vibration. The device includes a conveyor belt (8) and further includes: A ring-shaped synchronous sound signal acquisition unit (1) is set above the conveyor belt (8). The ring-shaped synchronous sound signal acquisition unit (1) includes a sound signal acquisition sleeve (3), a microphone (10), a ring-shaped conveyor device (5), and a lifting rod (4). The ring-shaped conveyor device (5) is set above the conveyor belt (8). A lifting rod (4) is installed on the moving slide rail of the ring-shaped conveyor device (5). A sound signal acquisition sleeve (3) is fixedly installed at the driving end of the lifting rod (4) away from the ring-shaped conveyor device (5). The sound signal acquisition sleeve (3) has a cup. A microphone (10) is fixedly installed at the end of the sound signal acquisition sleeve (3) connected to the driving end of the lifting rod (4). Under the drive of the ring-shaped conveyor device (5), the sound signal acquisition sleeve (3) moves synchronously with the integrated free-type fruit cup excitation unit (2). After the detection is completed, the sound signal acquisition sleeve (3) is quickly reset under the drive of the lifting rod (4). Free-form fruit cup (6), the free-form fruit cup (6) is placed on the conveyor belt (8) and moves with the conveyor belt (8). The free-form fruit cup (6) has a cavity. A resonant horn (9) is installed in the cavity. The resonant horn (9) is connected to an external power amplifier (12). An excitation unit (2) is installed on the free-form fruit cup (6) above the resonant horn (9). A data acquisition module (11) is electrically connected to the microphone (10); The data processing unit (13) is electrically connected to the data acquisition module (11) and the power amplifier (12). The method includes the following steps: Step S100: Establish an online monitoring scenario for fruit core rot based on acoustic vibration. The scenario includes an online monitoring device for fruit core rot based on acoustic vibration. Turn on the online monitoring device for fruit core rot based on acoustic vibration. Step S200: Based on the sinusoidal sweep frequency signal output by the resonant horn, the fruit under test is excited to generate a sound signal by forced vibration, and the sound signal is acquired and saved; Step S300: After acquiring the sound signal, the fruit to be tested is cut in half along the equator and the cross-sectional image is captured by a camera. Then, OpenCV is used to process the cross-sectional image of the fruit to be tested to calculate the degree of lesion in the core rot area of ​​the fruit to be tested. In step S400, the saved sound signal is processed in the data processing unit. The sound signal is converted into audio frequency domain data through fast Fourier transform. The audio frequency domain data is used as the input of the fruit quality prediction model, and then the fruit quality prediction model outputs the predicted quality of the fruit.

2. The online monitoring method for fruit core rot based on acoustic vibration according to claim 1, characterized in that, In step S200, the sinusoidal sweep frequency signal output by the resonant speaker specifically means that the resonant speaker, driven by the power amplifier, outputs a sinusoidal sweep frequency signal of 100 Hz to 1500 Hz within 0.5 seconds, and excites the fruit under test to generate a sound signal by forced vibration. The sound signal is detected by the microphone in the sound signal acquisition sleeve, and is acquired in real time by the signal acquisition module and transmitted to the data processing unit for storage.

3. The online monitoring method for fruit core rot based on acoustic vibration according to claim 1, characterized in that, In step S300, the processing of the cross-sectional image of the fruit to be tested using OpenCV specifically includes: firstly, edge detection is used to detect the outline of the cross-section of the fruit to be tested, and the number of pixels S1 of the fruit to be tested is calculated; then, grayscale processing is performed on the image, and threshold segmentation, dilation and erosion are used to obtain the complete lesion area and the number of pixels S2 is calculated; finally, the degree of apple lesion is represented by the ratio of pixels S2 / S1.

4. The online monitoring method for fruit core rot based on acoustic vibration according to claim 3, characterized in that, In step S300, a fast Fourier transform is performed on the original sound signal. When performing the fast Fourier transform, it is necessary to select an appropriate number of analysis points according to the sampling frequency and sampling time to convert the sound signal from a time-domain signal into a sound image.

5. The online monitoring method for fruit core rot based on acoustic vibration according to claim 1, characterized in that, The fruits to be tested include apples and yellow peaches.

6. The online monitoring method for fruit core rot based on acoustic vibration according to claim 1, characterized in that, The fruit quality prediction model outputs predicted quality of the fruit to be tested, including fruit firmness, edible period, shelf life, and internal diseases.

Images