Intelligent picking and sorting system and method

Abstract

The invention discloses an intelligent picking and sorting system and method, and the system comprises an intelligent picking and sorting mechanical claw and a picking and sorting system. The picking and sorting system comprises a computer processing module, and a dielectric frequency spectrum generation electrode plate, a near-infrared light source generation device, a dielectric frequency spectrum receiving plate, an optical fiber probe, a near-infrared spectrometer, an image acquisition device and a power supply module which are electrically connected with the computer processing module respectively; the optical fiber probe is connected with the near-infrared spectrometer; the intelligent picking and sorting mechanical claw comprises a hydraulic mechanism and a clamping mechanism; the computer processing module is connected with the hydraulic mechanism, and the hydraulic mechanism controls the clamping mechanism to act after receiving control instruction information sent by the computer processing module; the dielectric frequency spectrum generation electrode plate, the near-infrared light source generation device, the dielectric frequency spectrum receiving plate and the optical fiber probe are respectively arranged on four mechanical claws of the clamping mechanism; the clamping force of objects can be adjusted in a self-adaptive mode, and the quality can be automatically sorted.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent picking and sorting devices, and more specifically to an intelligent picking and sorting system and method. Background Art

[0002] A manipulator is a new type of device developed in the process of mechanized and automated production. Although the manipulator is not as flexible as the human hand yet, it has the characteristics of being able to continuously repeat work and labor, not being fatigued, not being afraid of danger, and having a greater grasping force for heavy objects than the human hand. It has been widely used in fields such as mechanical manufacturing, metallurgy, electronics, light industry, and atomic energy.

[0003] With the combination of machine vision, image processing, and perception technology with the manipulator, the manipulator has become more and more intelligent, and the manipulator has achieved more functions, and has performed well in fields such as remote control, item sorting, and crop picking.

[0004] As a major fruit and vegetable planting country, China's annual fruit output exceeds 300 million tons, and vegetables exceed 800 million tons; not only is the output large, but the variety is also rich. There are more than 300 kinds of cultivated fruits, and each kind of fruit contains different varieties. For example, there are more than 17 varieties of common citrus fruits and more than 54 kinds of apples. The planting, picking, and sorting work among them requires a large amount of manpower, and repetitive actions for a long time are likely to cause occupational diseases and work injuries; the use of manipulators reduces labor costs, ensures the health and safety of workers, and improves work efficiency and quality at the same time.

[0005] However, there are still the following problems in using manipulators for fruit picking and object sorting at present:

[0006] 1. When using a hard-clamping manipulator for picking, due to the lack of force detection ability, a fixed clamping force is generally set. During the picking process, the clamping force cannot be dynamically adjusted according to the state of the fruit, often damaging the surface skin or internal tissue of the object, reducing the shelf life. If the clamping force is insufficient, the object will slide, and the picking cannot be successfully completed;

[0007] 2. The general method for the recognition and positioning function of an object in a conventional picking scenario relies on machine vision to achieve the segmentation and recognition of the object through deep learning. This method generally relies on a powerful graphics card as a computing power platform, with high costs, high requirements for the lighting environment, and at the same time, the device structure is relatively complex and the volume cannot be miniaturized;

[0008] 3. Picking and sorting are two separate processes. Usually, the fruits are picked first and then transported to the factory building for sorting according to the quality. There are many processes and a large amount of work;

[0009] 4. Most existing picking and sorting equipment such as robotic arms are special-purpose equipment, which can only pick or sort a specific type of fruit or vegetable. For example, a robotic arm for picking apples cannot be used to pick tomatoes, and a sorter for radishes cannot be used to sort eggs. This is mainly because the robotic arm cannot identify the material of the target object, cannot autonomously determine what the clamping object is, and the clamping force of the fixture cannot be automatically adjusted according to the situation. There will be either insufficient clamping or excessive force that may damage the target. It cannot detect different fruits and vegetables simultaneously, has poor universality, and a single usage method. Summary of the Invention

[0010] The object of the present invention is to provide an intelligent picking and sorting system and method. By applying the intelligent picking and sorting system to a robotic arm, during the processes of approaching, clamping, and picking, it can identify the material and type of an object, and can judge the quality inside the object, and is applicable to the intelligent picking and sorting work of various fruits and vegetables.

[0011] Thus, the deficiencies existing in the above-mentioned prior art are solved.

[0012] To achieve the above object, the present invention provides the following technical solutions:

[0013] An intelligent picking and sorting system includes: an intelligent picking and sorting robotic claw and a picking and sorting system. The picking and sorting system includes: a computer processing module, a dielectric spectroscopy generating electrode plate, a near-infrared light source generating device, a dielectric spectroscopy receiving plate, an optical fiber probe, a near-infrared spectrometer, an image acquisition device, and a power supply module that are respectively electrically connected to the computer processing module; the optical fiber probe is connected to the near-infrared spectrometer, and the power supply module is used to provide working power for the intelligent picking and sorting system;

[0014] The intelligent picking and sorting robotic claw includes: a hydraulic mechanism and a clamping mechanism; the computer processing module is connected to the hydraulic mechanism. After receiving the control instruction information sent by the computer processing module, the hydraulic mechanism controls the clamping mechanism to act; the clamping mechanism includes four clamping arms and four robotic claws, and the ends of the four clamping arms are respectively connected to the four robotic claws through a gear mechanism; the hydraulic mechanism is respectively drivingly connected to the four clamping arms;

[0015] The dielectric spectroscopy generating electrode plate, the near-infrared light source generating device, the dielectric spectroscopy receiving plate, and the optical fiber probe are respectively arranged on the four robotic claws. The dielectric spectroscopy generating electrode plate and the dielectric spectroscopy receiving plate are arranged opposite to each other, and the near-infrared light source generating device and the optical fiber probe are arranged opposite to each other;

[0016] The image acquisition device is arranged at the middle position of the four robotic claws.

[0017] The image acquisition device is used to acquire the image of an object, identify and judge the position and shape of the object, perform rough positioning in a large scene, and guide the operation movement of the intelligent picking and sorting mechanical claw;

[0018] The dielectric spectrum generating electrode plate is used to generate an alternating electromotive force excitation;

[0019] The dielectric spectrum receiving plate is used to receive the response voltage signal generated by the alternating electromotive force excitation, and measure the approaching distance of the intelligent picking and sorting mechanical claw to the object, the material and deformation of the object;

[0020] The near-infrared light source generating device is used to emit near-infrared light signals;

[0021] The optical fiber probe is used to receive the near-infrared light signals emitted by the near-infrared light source generating device;

[0022] The near-infrared spectrometer is used to detect the near-infrared light transmission signal and measure the internal quality of the object;

[0023] The computer processing module is used to calculate the capacitance and complex relative permittivity between the dielectric spectrum generating electrode plate and the dielectric spectrum receiving plate during the process of clamping the object by the intelligent picking and sorting mechanical claw, and obtain the dielectric spectrum data information between the dielectric spectrum generating electrode plate and the dielectric spectrum receiving plate through data processing;

[0024] Based on the capacitance and its change, detect the approaching distance of the intelligent picking and sorting mechanical claw to the object and the shape of the object, send control instruction information through the computer processing module, and adjust the precise position of the intelligent picking and sorting mechanical claw and the position of the maximum outer diameter of the object;

[0025] Based on the dielectric spectrum data information, identify the material and deformation of the object, and determine the required clamping force according to the material and deformation of the object; and, detect internal defects and analyze nutrient components of the object according to the near-infrared light transmission signal, and realize automatic sorting in combination with the detection result of the object size.

[0026] Further, it also includes a temperature sensor; the temperature sensor is arranged on the intelligent picking and sorting mechanical claw and is connected to the computer processing module, and is used to provide temperature compensation for the detection of near-infrared light and the detection of dielectric spectrum.

[0027] Further, the four mechanical claws include a first mechanical claw, a second mechanical claw, a third mechanical claw and a fourth mechanical claw; the first mechanical claw and the third mechanical claw are arranged oppositely, and the second mechanical claw and the fourth mechanical claw are arranged oppositely;

[0028] The dielectric spectrum generating electrode plate is arranged on the first mechanical claw;

[0029] The near-infrared light source generating device is arranged on the second robotic gripper;

[0030] The dielectric spectrum receiving plate is arranged on the third robotic gripper;

[0031] The optical fiber probe is arranged on the fourth robotic gripper.

[0032] Furthermore, both the dielectric spectrum generating electrode plate and the dielectric spectrum receiving plate include a plurality of electrode contacts; each electrode contact includes a plurality of symmetric electrode matrices.

[0033] Furthermore, the light source of the near-infrared light signal is a halogen lamp.

[0034] Furthermore, the frequency range of the alternating electromotive force excitation changes cyclically and equally spaced between 1 MHz and 2500 MHz.

[0035] Furthermore, the outside of the dielectric spectrum generating electrode plate and the dielectric spectrum receiving plate is coated with conductive silicone.

[0036] The present invention also provides an intelligent picking and sorting method, including the following steps:

[0037] Initialize the intelligent picking and sorting robotic gripper;

[0038] Use the image acquisition device to acquire the image of the object and locate the position of the object;

[0039] Calculate the capacitance generated between the dielectric spectrum generating electrode plate and the dielectric spectrum receiving plate and the complex relative permittivity between the dielectric spectrum generating electrode plate and the dielectric spectrum receiving plate, use the capacitance size to identify the shape of the object, and determine the clamping position;

[0040] Perform data processing on the capacitance size and the complex relative permittivity to obtain dielectric spectrum data, use the dielectric spectrum data to obtain the material and type of the object, and determine the required clamping force of the object according to the material and type of the object;

[0041] Use the near-infrared light transmission signal to judge the internal quality of the object and automatically sort it.

[0042] Furthermore, the calculation of the capacitance generated between the first robotic gripper and the third robotic gripper is specifically:

[0043] The induced capacitance C when there is no object clamped between the first robotic gripper and the third robotic gripper b is:

[0044] C b = C 0 + C 1

[0045] where C0 = ε 0 S / D is the capacitance generated by the air medium between the electrodes, and ε 0 is the air dielectric constant, S is the area of the mechanical claw, D is the distance between the electrodes, and C 1 is the sum of the boundary capacitance and the distributed capacitance caused by the measurement leads and the measurement system;

[0046] When the first mechanical claw and the third mechanical claw are close to each other and do not touch the object, the capacitance C d is:

[0047] C d = Cs + C 2 + C 1

[0048]

[0049] C 2 = ε 0 S 1 / D;

[0050] where ε γ is the dielectric constant of the object, t is the thickness of the object, and x is the area of the object; C 2 is the inter-stage area outside the clamped object with an area of S 1 = S - x, D is the distance between the electrodes, and we get:

[0051] C S = C d - C b + C 0 - C 2

[0052] When the object is larger than the electrode plate on the mechanical claw, C 2 can be ignored;

[0053] When the first mechanical claw and the third mechanical claw touch the object, the first mechanical claw applies an alternating electromotive force, and the third mechanical claw receives the alternating electromotive force signal. The complex relative dielectric constant ε* between the first mechanical claw and the third mechanical claw is:

[0054] ε* = ε’ - jε” = ε + k / (jε 0 ω)

[0055] where ε’ is the real part of ε*, ε” is the imaginary part of ε*, ε is the relative dielectric constant, k is the conductivity, ω is the angular frequency, ω = 2Πf, and f is the frequency, and j represents the imaginary unit;

[0056] The magnitude and complex relative permittivity of the capacitor subjected to the electromotive force excitation signal are subjected to baseline correction, normalization, and smoothing denoising. Through the group analysis method, clustering analysis is performed on the magnitude and complex relative permittivity of the capacitor to determine the material and type of the object.

[0057] According to the specific embodiments provided by the present invention, the following technical effects are disclosed by the present invention:

[0058] 1. The present invention can detect the types and varieties of clamped fruits and vegetables through dielectric spectrum analysis at different frequencies;

[0059] 2. By setting an infrared detection device on the mechanical claw, the quality detection of fruits and vegetables can be completed during the clamping and picking processes, and rapid sorting can be carried out;

[0060] 3. Using dielectric spectrum to analyze the types and varieties of fruits and vegetables is applicable to most non-conductive fruits and vegetables with a relatively high moisture content, and has good universality;

[0061] 4. Using the mechanical claw to detect the capacitance between the claws, the non-contact detection of the shape of fruits and vegetables is realized. The pressure is sensed through the capacitance and changes, and the clamping force is adaptively adjusted, avoiding the damage of fruits and vegetables during the clamping process. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0063] The following further illustrates the intelligent picking and sorting system and method of the present invention with reference to the drawings;

[0064] Figure 1 is the structural diagram of the intelligent picking and sorting mechanical claw provided by the present invention;

[0065] Figure 2 is the structural schematic diagram of the dielectric spectrum generating electrode plate and the dielectric spectrum receiving plate provided by the present invention;

[0066] Figure 3 is the structural schematic diagram of each electrode contact in the dielectric spectrum generating electrode plate and the dielectric spectrum receiving plate in the intelligent picking and sorting system provided by the present invention;

[0067] Figure 4 is the overall schematic diagram of the intelligent picking and sorting method provided by the present invention;

[0068] Figure 5It is a schematic structural diagram of a capacitance circuit during the clamping process of the first robotic claw and the third robotic claw provided by the present invention.

[0069] In the figure, 101 - dielectric spectrum receiving board; 102 - dielectric spectrum generating electrode board; 103 - optical fiber probe; 104 - infrared light source; 105 - sapphire glass; 106 - hydraulic mechanism; 107 - gear mechanism; 108 - image acquisition device; 110 - temperature sensor; 111 - computer processing module; 201 - first robotic claw; 202 - third robotic claw; 203 - second robotic claw; 204 - fourth robotic claw. Specific embodiments

[0070] The following will further describe in detail the specific embodiments of the present invention in conjunction with the accompanying drawings and embodiments. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0071] In order to better understand the purpose, structure and function of the present invention, the following will further describe the present invention in detail in conjunction with the accompanying drawings.

[0072] As Figure 1 shown, an intelligent picking and sorting system includes: an intelligent picking and sorting robotic claw and a picking and sorting system. The picking and sorting system includes: a computer processing module 111 and a dielectric spectrum generating electrode board 102, a near-infrared light source generating device 104, a dielectric spectrum receiving board 101, an optical fiber probe 103, a near-infrared spectrometer, an image acquisition device 108 and a power supply module that are respectively electrically connected to the computer processing module 111; the optical fiber probe 103 is connected to the near-infrared spectrometer, and the power supply module is used to provide a working power supply for the intelligent picking and sorting system;

[0073] The intelligent picking and sorting robotic claw includes: a hydraulic mechanism 106 and a clamping mechanism; the computer processing module 111 is connected to the hydraulic mechanism 106. After the hydraulic mechanism 106 receives the control instruction information sent by the computer processing module 111, it controls the clamping mechanism to act; the clamping mechanism includes four clamping arms and four robotic claws, and the ends of the four clamping arms are respectively connected to the four robotic claws through a gear mechanism 107; the hydraulic mechanism 106 is respectively drivingly connected to the four clamping arms;

[0074] The dielectric spectrum generating electrode board 102, the near-infrared light source generating device 104, the dielectric spectrum receiving board 101 and the optical fiber probe 103 are respectively arranged on the four robotic claws. The dielectric spectrum generating electrode board 102 and the dielectric spectrum receiving board 101 are arranged opposite to each other, and the near-infrared light source generating device 104 and the optical fiber probe 103 are arranged opposite to each other;

[0075] The image acquisition device 108 is arranged at the middle position of the four robotic claws.

[0076] The power supply driving module is respectively connected to the dielectric spectroscopy generating electrode plate 102, the dielectric spectroscopy receiving plate 101, the near-infrared spectrometer, the near-infrared light source generating device 104, the image acquisition device 108 and the hydraulic mechanism 106, and is used to provide electrical energy drive for each component;

[0077] It should be noted that: the clamping structure further includes four clamping arms, and the four clamping arms are respectively connected to the first mechanical claw 201, the second mechanical claw 203, the third mechanical claw 202 and the fourth mechanical claw 204 through a gear mechanism 107; the hydraulic mechanism 106 is respectively connected to the four clamping arms.

[0078] It should be noted that: four mechanical claws are provided, and the first mechanical claw 201 and the third mechanical claw 202 are respectively equipped with dielectric spectroscopy generating and sensing devices for identifying the types and varieties of fruits and vegetables; the second mechanical claw 203 and the fourth mechanical claw 204 are respectively equipped with near-infrared generating and detecting devices for detecting the quality of fruits and vegetables; the image acquisition device is specifically: a camera, which is used for image acquisition and positioning the basic position of fruits and vegetables. The camera is arranged at the center position of the four mechanical claws, and a sapphire glass is installed on the camera to protect the camera.

[0079] Through continuous image acquisition by the camera during the coordinate change of the manipulator, the relative position between the manipulator and the fruits and vegetables is judged. This camera only needs to distinguish the difference and position between fruits and vegetables and leaves, and does not need to identify the types of fruits and vegetables. Therefore, the requirements for the pixel of the camera, the illumination environment used, the image processing speed and computing power are low; after approaching the fruits and vegetables, the shape of the fruits and vegetables is identified by the change of the inductive capacitance between the first and third mechanical claws, and by calculating the maximum inductive capacitance, the maximum outer diameter of the fruits and vegetables is obtained to adjust the clamping position; after the mechanical claws are closed and in contact with the fruits and vegetables, an alternating electromotive force excitation is applied on the first mechanical claw 201, and the response signal of the sensing device of the third mechanical claw 202 is measured. Through group analysis, the material and type of the clamped fruits and vegetables are judged, and the required clamping force is determined according to the material and type of the fruits and vegetables. During the clamping process, the piezoelectric capacitance change between the first and third mechanical claws determines the clamping force, and the clamping force is adaptively adjusted according to the obtained material and type of the fruits and vegetables, so as to stably clamp the fruits and vegetables while avoiding damaging the skin or internal tissues of the fruits and vegetables; the second mechanical claw 203 emits a near-infrared light signal, and the fourth mechanical claw 204 is provided with a near-infrared spectroscopy detection device to detect the near-infrared transmission signal, and through chemometric analysis, the quality inside the clamped fruits and vegetables is judged.

[0080] A sapphire glass 105 is installed on the camera to prevent the camera from being scratched.

[0081] The image acquisition device 108 is used to acquire the image of an object, identify and judge the position and shape of the object, perform rough positioning of a large scene, and realize the guidance of the operation movement of the intelligent picking and sorting mechanical claw;

[0082] The dielectric spectrum generating electrode plate 102 is used to generate an alternating electromotive force excitation;

[0083] The dielectric spectrum receiving plate 101 is used to receive the response voltage signal generated by the alternating electromotive force excitation, and measure the proximity distance of the intelligent picking and sorting mechanical claw to the object, the material and deformation of the object;

[0084] The near-infrared light source generating device 104 is used to emit near-infrared light signals;

[0085] The optical fiber probe is used to receive the near-infrared light signals emitted by the near-infrared light source generating device 104;

[0086] The near-infrared spectrometer is used to detect the near-infrared light transmission signal and realize the measurement of the internal quality of the object;

[0087] The computer processing module 111 is used to calculate the capacitance and complex relative permittivity between the dielectric spectrum generating electrode plate 102 and the dielectric spectrum receiving plate 101 during the process of clamping the object by the intelligent picking and sorting mechanical claw, and obtain the dielectric spectrum data information between the dielectric spectrum generating electrode plate 102 and the dielectric spectrum receiving plate 101 after data processing;

[0088] Based on the capacitance and its change, detect the proximity distance of the intelligent picking and sorting mechanical claw to the object and the shape of the object, and send control instruction information through the computer processing module 111 to adjust the precise position of the intelligent picking and sorting mechanical claw and the maximum outer diameter position of the object;

[0089] Based on the dielectric spectrum data information, identify the material and deformation of the object, and determine the required clamping force according to the material and deformation of the object; and, judge the internal defects such as rot, disease and pests inside the fruit and vegetable based on the near-infrared light transmission signal, as well as analyze the nutritional components such as sugar content, moisture content, acidity, vitamin content, etc., and realize automatic sorting in combination with the detection result of the fruit and vegetable size.

[0090] It should be noted that: the dielectric spectrum is used to identify the types of fruits and vegetables and provide the density information inside the fruits and vegetables, while the near-infrared spectrum can judge the chemical composition and nutritional status inside the fruit based on the light absorption feedback; through the identification of the types and internal density of fruits and vegetables by the dielectric spectrum, the identification ability of infrared spectroscopic chemometrics analysis is improved, and problems such as rot, water core, cavity or insect damage inside the fruits and vegetables are detected; automatically judge the internal quality of the clamped fruits and vegetables and automatically sort them during the picking process.

[0091] It also includes a temperature sensor 110; the temperature sensor 110 is arranged on the intelligent picking and sorting mechanical claw and is connected to the computer processing module 111, and is used to provide temperature compensation for the detection of near-infrared light and the detection of dielectric spectrum.

[0092] The dielectric spectrum generating electrode plate 102 is provided on the first mechanical claw 201 of the intelligent picking and sorting mechanical claw;

[0093] The near-infrared light source generating device 104 is provided on the second mechanical claw 203 of the intelligent picking and sorting mechanical claw;

[0094] The dielectric spectrum receiving plate 101 is provided on the second mechanical claw 203 of the intelligent picking and sorting mechanical claw;

[0095] The optical fiber probe 103 is provided on the fourth mechanical claw 204.

[0096] As Figure 2 and Figure 3 shown, both the dielectric spectrum generating electrode plate 102 and the dielectric spectrum receiving plate 101 include a plurality of electrode contacts 401; each electrode contact 401 includes a plurality of symmetric electrode matrices 301.

[0097] It should be noted that: the outside is coated with conductive silicone to protect the electrodes and the clamped object, and at the same time increase the friction; inside the electrode contacts of the dielectric spectrum generating electrode plate, the symmetric electrode matrices generate an alternating electromotive force in a differential manner to eliminate external environmental electromagnetic interference.

[0098] The light source of the near-infrared light signal is a halogen lamp.

[0099] The frequency range of the alternating electromotive force changes cyclically and equally spaced between 1 MHz and 2500 MHz.

[0100] The outside of the dielectric spectrum generating electrode plate 102 and the dielectric spectrum receiving plate 101 is coated with conductive silicone 302.

[0101] As Figure 4 shown, the present invention also provides an intelligent picking and sorting method, including the following steps:

[0102] Initialize the intelligent picking and sorting mechanical claw;

[0103] Use the image acquisition device 108 to acquire the image of the object and locate the position of the object;

[0104] Calculate the capacitance generated between the dielectric spectrum generating electrode plate 102 and the dielectric spectrum receiving plate 101 and the complex relative permittivity between the dielectric spectrum generating electrode plate 102 and the dielectric spectrum receiving plate 101, and use the capacitance to identify the shape of the object and determine the clamping position;

[0105] Data processing is performed on the capacitance value and complex relative permittivity to obtain dielectric spectrum data. The material and type of an object are determined using the dielectric spectrum data, and the clamping force required for the object is determined based on the material and type of the fruit or vegetable.

[0106] Using the near-infrared light transmission signal, based on the judgment of the material and type of the clamped object from the dielectric spectrum, the algorithm for enhancing the infrared spectrum signal is used to further judge the internal quality of the object and perform automatic sorting.

[0107] Among them, the principle of using infrared spectrum to judge the internal quality of fruits and vegetables is that specific molecules in the substance have the property of absorbing near-infrared light of specific wavelengths. By measuring the absorption of infrared light of specific wavelengths, the composition and content of this substance can be analyzed.

[0108] Calculate the capacitance value generated between the dielectric spectrum generating electrode plate 102 and the dielectric spectrum receiving plate 101, specifically:

[0109] As Figure 5 shown, the induced capacitance C when there is no object clamped between the first robotic gripper 201 and the third robotic gripper 202 b is:

[0110] C b = C 0 + C 1

[0111] Among them, C 0 = ε 0 S / D is the capacitance generated by the air medium between the electrodes, ε 0 is the air dielectric constant, S is the area of the robotic gripper, D is the distance between the electrodes, and C 1 is the sum of the fringe capacitance and the distributed capacitance caused by the measurement leads and the measurement system;

[0112] The capacitance C when the first robotic gripper 201 and the third robotic gripper 202 are close to but not in contact with an object d is:

[0113] C d = Cs + C 2 + C 1

[0114]

[0115] C 2 = ε 0 S 1 / D;

[0116] Among them, ε γ is the dielectric constant of the object, t is the thickness of the object, x is the area of the object; C 2 is the inter-stage area outside the clamped object with an area of S1 = S - x, where D is the distance between the electrodes, and we get:

[0117] C S = C d - C b + C 0 - C 2

[0118] When the object is larger than the electrode plate on the mechanical claw, C 2 can be ignored. By changing the travel distance of the mechanical claw, the change in the object's shape can be obtained, and the position of the maximum outer diameter of the object can be acquired for clamping.

[0119] It should be noted that: among them, the dielectric property is related to the material composition, and the change in the material composition will be reflected in the dielectric property. The dielectric spectrum is the change of the dielectric constant in the electromagnetic field with different frequencies. This method contains more information than the dielectric constant method at a single frequency. Therefore, the dielectric spectrum technology is a commonly used method for measuring non-conductive substances and semi-solid materials with a relatively high moisture content, and different varieties and types can be identified according to the dielectric spectrum.

[0120] After the first mechanical claw 201 and the third mechanical claw 202 come into contact with the object, the first mechanical claw 201 applies an alternating electromotive force, and the third mechanical claw 202 receives the alternating electromotive force signal. The complex relative dielectric constant ε* between the first mechanical claw 201 and the third mechanical claw 202 is:

[0121] ε* = ε’ - jε” = ε + k / (jε 0 w)

[0122] where ε’ is the real part of ε*, ε” is the imaginary part of ε*, ε is the relative dielectric constant, k is the conductivity, w is the angular frequency, w = 2Πf, and f is the frequency. represents the imaginary unit;

[0123] Among them, the change in the material composition will be reflected in the dielectric spectrum. There are differences in the charge storage capabilities of fruits and vegetables with different materials and types. The dielectric spectrum curve generated by the alternating electromotive force can reflect this difference. After the response spectrum data of the electromotive force excitation signal is subjected to baseline correction, normalization, and smoothing and denoising, the group analysis method is used to perform cluster analysis on the response spectrum data to judge the materials and types of fruits and vegetables.

[0124] The foregoing description of the disclosed embodiments enables those skilled in the art to practice or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent picking and sorting system, characterized in that: include: An intelligent picking and sorting mechanical claw and a picking and sorting system, the picking and sorting system comprising: a computer processing module (111) and a dielectric spectrum generating electrode plate (102) electrically connected to the computer processing module (111), a near-infrared light source generating device (104), a dielectric spectrum receiving board (101), an optical fiber probe (103), a near-infrared spectrometer, an image acquisition device (108) and a power supply module; the optical fiber probe (103) is connected to the near-infrared spectrometer, and the power supply module is used to provide working power for the intelligent picking and sorting system; The intelligent picking and sorting mechanical claw comprises: a hydraulic mechanism (106) and a clamping mechanism; the computer processing module (111) is connected to the hydraulic mechanism (106), and after the hydraulic mechanism (106) receives the control instruction information sent by the computer processing module (111), it controls the action of the clamping mechanism; the clamping mechanism comprises four clamping arms and four mechanical claws, and the ends of the four clamping arms are respectively connected to the four mechanical claws through a gear mechanism (107); the hydraulic mechanism (106) is respectively connected to the four clamping arms in a driving manner; The dielectric spectrum generating electrode plate (102), the near-infrared light source generating device (104), the dielectric spectrum receiving plate (101) and the optical fiber probe (103) are respectively arranged on four mechanical claws, the dielectric spectrum generating electrode plate (102) and the dielectric spectrum receiving plate (101) are arranged opposite to each other, and the near-infrared light source generating device (104) and the optical fiber probe (103) are arranged opposite to each other; The image acquisition device (108) is arranged in the middle of the four mechanical claws.

2. The intelligent picking and sorting system according to claim 1 is characterized in that: The image acquisition device (108) is used to acquire images of objects, identify and judge the position and shape of the objects, perform rough positioning of large scenes, and guide the operation movement of the intelligent picking and sorting mechanical claws; The dielectric spectrum generating electrode plate (102) is used to generate alternating electromotive force excitation; The dielectric spectrum receiving board (101) is used to receive the response voltage signal generated by the alternating electromotive force excitation, so as to realize the measurement of the approach distance of the intelligent picking and sorting mechanical claw to the object, the material and deformation of the object; The near-infrared light source generating device (104) is used to emit a near-infrared light signal; The optical fiber probe is used to receive the near-infrared light signal emitted by the near-infrared light source generating device (104); The near-infrared spectrometer is used to detect near-infrared light transmission signals to measure the internal quality of an object; The computer processing module (111) is used to calculate the capacitance and the complex relative dielectric constant between the dielectric spectrum generating electrode plate (102) and the dielectric spectrum receiving plate (101) during the process of clamping the object using the intelligent picking and sorting mechanical claw, and obtain dielectric spectrum data information between the dielectric spectrum generating electrode plate (102) and the dielectric spectrum receiving plate (101) through data processing; Based on the size and change of the capacitance, the proximity distance of the intelligent picking and sorting mechanical claw to the object and the shape of the object are detected, and control instruction information is sent through the computer processing module (111) to adjust the precise position of the intelligent picking and sorting mechanical claw and the maximum outer diameter position of the object; Identify the material and deformation of the object based on the dielectric spectrum data information, and determine the required clamping force according to the material and deformation of the object; In addition, internal defect detection and nutritional composition analysis of objects are performed based on near-infrared light transmission signals, and automatic sorting is achieved in combination with object size detection results.

3. The intelligent picking and sorting system according to claim 1 is characterized in that: It also includes a temperature sensor (110); the temperature sensor (110) is arranged on the intelligent picking and sorting mechanical claw and is connected to the computer processing module (111) to provide temperature compensation for the detection of near-infrared light and the detection of dielectric spectrum.

4. The intelligent picking and sorting system according to claim 1 is characterized in that: The four mechanical claws include a first mechanical claw (201), a second mechanical claw (203), a third mechanical claw (202) and a fourth mechanical claw (204); the first mechanical claw (201) and the third mechanical claw (202) are arranged opposite to each other, and the second mechanical claw (203) and the fourth mechanical claw (204) are arranged opposite to each other; The dielectric spectrum generating electrode plate (102) is arranged on the first mechanical claw (201); The near-infrared light source generating device (104) is arranged on the second mechanical claw (203); The dielectric spectrum receiving plate (101) is arranged on the third mechanical claw (202); The optical fiber probe (103) is arranged on the fourth mechanical claw (204).

5. The intelligent picking and sorting system according to claim 1 is characterized in that: The dielectric spectrum generating electrode plate (102) and the dielectric spectrum receiving plate (101) both include a plurality of electrode contacts (401); each electrode contact (401) includes a plurality of symmetrical electrode matrices (301).

6. The intelligent picking and sorting system according to claim 2 is characterized in that: The light source of the near-infrared light signal is a halogen lamp.

7. The intelligent picking and sorting system according to claim 2 is characterized in that: The frequency range of the alternating electromotive force excitation varies cyclically and at equal intervals between 1 MHz and 2500 MHz.

8. The intelligent picking and sorting system according to claim 1, characterized in that: The exterior of the dielectric spectrum generating electrode plate (102) and the dielectric spectrum receiving plate (101) are coated with conductive silicone (302).

9. An intelligent picking and sorting method, applied to the intelligent picking and sorting system according to any one of claims 1 to 8, characterized in that: The following steps are involved: Initialize the intelligent picking and sorting mechanical claws; Using an image acquisition device (108) to acquire an image of the object and locate the position of the object; Calculating the capacitance generated between the dielectric spectrum generating electrode plate (102) and the dielectric spectrum receiving plate (101) and the complex relative dielectric constant between the dielectric spectrum generating electrode plate (102) and the dielectric spectrum receiving plate (101), using the capacitance to identify the shape of the object and determine the clamping position; Data processing is performed on the capacitance and the complex relative dielectric constant to obtain dielectric spectrum data, and the material and type of the object are obtained using the dielectric spectrum data, and the clamping force required for the object is determined according to the material and type of the object; Near-infrared light transmission signals are used to judge the internal quality of objects and automatically sort them.

10. The intelligent picking and sorting method according to claim 9, characterized in that: The capacitance generated between the dielectric spectrum generating electrode plate (102) and the dielectric spectrum receiving plate (101) is calculated as follows: The inductive capacitance C between the first mechanical claw (201) and the third mechanical claw (202) when there is no object clamped b for: C b =C0+C1 Where C0=ε0S / D is the capacitance generated by the air medium between the electrodes, ε0 is the air dielectric constant, S is the area of ​​the mechanical claw, D is the distance between the electrodes, and C1 is the sum of the boundary capacitance and the distributed capacitance caused by the measurement lead and the measurement system; The capacitance C between the first mechanical claw (201) and the third mechanical claw (202) when they are close to but not in contact with an object d for: C d =Cs+C2+C1 C2=ε0S1 / D; Among them, ε γ is the dielectric constant of the object, t is the thickness of the object, x is the area of ​​the object; C2 is the area between the clamped objects, S1 = Sx, D is the distance between the electrodes, and we get: C S =C d -C b +C0-C2 When the object is larger than the plate on the gripper, C2 can be ignored; When the first mechanical claw (201) and the third mechanical claw (202) contact an object, the first mechanical claw (201) applies an alternating electromotive force, and the third mechanical claw (202) receives an alternating electromotive force signal. The complex relative dielectric constant ε* between the first mechanical claw (201) and the third mechanical claw (202) is: ε*=ε'-jε”=ε+k / (jε0w) Where ε' is the real part of ε*, ε" is the imaginary part of ε*, ε is the relative permittivity, k is the conductivity, w is the angular frequency, w = 2Πf, f is the frequency, represents an imaginary unit; The size of the capacitor and the complex relative dielectric constant of the electromotive force excitation signal are baseline corrected, normalized, smoothed and denoised. Through the group analysis method, the size of the capacitor and the complex relative dielectric constant are clustered and analyzed to determine the material and type of the object.

Images