Intelligent integrated vegetable planting machine, control method and seed germination state recognition method

Abstract

The invention discloses an intelligent integrated vegetable growing machine which comprises a machine body shell, an environment detection module, an intelligent control module, a first execution part, a seed germination rate recognition module and a second execution part. The machine body shell comprises a base, a supporting rod, a mounting plate, a circular truncated cone type planting frame and a nutrition bin. A first notch is formed in the base and used for arranging the nutrition bin which performs drawing movement relative to the base; a circular truncated cone type planting frame is mounted on the base, and the circular truncated cone type planting frame is communicated with the nutrition bin through a recovery opening formed in the base; the base is connected with the mounting plate through a supporting rod; the intelligent control module is used for driving the first execution component to act according to received first environment information from the environment detection module, and the intelligent control module is used for driving the second execution component to act according to received second environment information from the environment detection module and germination rate information identified by the seed germination rate identification module. The illumination intensity, the temperature, the humidity and the nutrient solution level of the vegetable planting machine can be intelligently controlled.

Description

Technical Field

[0001] The invention relates to an intelligent integrated vegetable planting machine, a control method and a seed germination state identification method, and belongs to the field of agricultural technology based on artificial intelligence. Background Art

[0002] Soilless cultivation, also known as hydroponics, refers to the use of artificially prepared nutrient solution to supply the mineral nutrients required by plants without the use of soil, thereby achieving plant growth and development.

[0003] As people's requirements for quality of life increase, soilless vegetable growing machines are gradually emerging. However, the existing vegetable growing machines are not very intelligent and can only achieve timing control and remote control. In addition, the existing vegetable growing machines lack research on detecting seed germination rate and using insulation film to control temperature, and cannot meet the irrigation and temperature requirements of vegetables growing from seeds to mature plants. Therefore, it is still necessary to invent an intelligent control integrated vegetable growing machine for home planting to solve the above problems. Summary of the invention

[0004] The present invention provides an intelligent integrated vegetable growing machine and a control method, so as to at least solve the problems mentioned in the prior art that the existing vegetable growing machines have a low intelligence level and cannot identify the seed germination rate.

[0005] The technical solution of the present invention is:

[0006] According to a first aspect of the present invention, there is provided an intelligent integrated vegetable growing machine, comprising a machine body shell 1, an environmental detection module, an intelligent control module, a first execution component, a seed germination rate recognition module, and a second execution component; the machine body shell 1 comprises a base 2, a support rod 3, a mounting plate 4, a truncated cone planting frame 5, and a nutrient bin 8; the base 2 is provided with a first notch for setting the nutrient bin 8 that can be pulled relative to the base 2; the base 2 is provided with a second notch for installing the intelligent control module; a truncated cone planting frame 5 is installed on the base 2, and the truncated cone planting frame 5 and the nutrient bin 8 are connected to each other. The recovery port 9 opened on the base 2 is arranged in a connected manner; the base 2 is connected to the mounting plate 4 through a support rod 3 arranged along the axial direction of the truncated cone planting frame 5, and there is a gap between the mounting plate 4 and the truncated cone planting frame 5; the environmental detection module is used to transmit the detected first environmental information and the second environmental information to the intelligent control module, and the intelligent control module is used to drive the first execution component to act according to the received first environmental information, and the intelligent control module is used to drive the second execution component to act according to the received second environmental information and the germination rate information recognized by the seed germination rate recognition module.

[0007] Furthermore, a detachable transverse rod 24 is provided below the mounting plate 4 ; and a third notch serving as a liquid level sensor placement opening 19 is provided on a side of the base 2 close to the first notch.

[0008] Furthermore, the environmental detection module includes a temperature and humidity sensor 15, a light sensor 16, a liquid level sensor 28, a liquid crystal display screen 18, and a temperature sensor; the temperature and humidity sensor 15 is installed above the base 2 and is covered by the truncated cone planting rack 5, and is used to detect the temperature and humidity inside the truncated cone planting rack 5, and uses the internal temperature as the first environmental information, and the humidity as the second environmental information; the temperature sensor is used to detect outdoor temperature information, and uses the outdoor temperature as the first environmental information; the light sensor 16 is installed on the side of the transverse rod 24 away from the center, and is used to detect the light intensity, and uses the light intensity as the first environmental information; the liquid level sensor 28 is installed in the liquid level sensor placement port 19, and is used to detect the nutrient solution level in the nutrient bin 8; the liquid crystal display screen 18 is installed on the outside of the side support rod 3, and is used to display the detected first and second environmental information, and is used to prompt insufficient nutrient solution level.

[0009] Furthermore, the first execution component includes:

[0010] A light strip 7, wherein the light strip 7 is installed on the inner side of the support rods 3 on both sides, and the inner side of the support rods 3 is a side close to the truncated cone planting rack 5, so that the intelligent control module drives the light strip 7 to turn on / off according to the received first environmental information;

[0011] The arc track 23 is installed on the side of the mounting plate 4 close to the conical planting frame 5. A slide is provided on the arc track 23 to connect the thermal insulation film, so that the intelligent control module drives the motor module according to the received first environmental information, drives the slide to move through the motor module, and drives the thermal insulation film to be opened / closed through the movement of the slide.

[0012] Furthermore, the second execution component includes a liquid guide tube 10, a liquid dripping tube 11, a first water pump, and a second water pump; the liquid dripping tube 11 is installed inside the truncated cone planting rack 5, and is surrounded in a circular shape inside each layer of the truncated cone; the liquid guide tube 10 is installed inside the truncated cone planting rack 5, connecting the liquid dripping tubes 11 of the upper and lower layers; the liquid dripping tube 11 is provided with a small hole, and the small hole corresponds to the planting groove 6; the intelligent control module is used to drive the first water pump / the second water pump to act according to the received second environmental information and the germination rate information recognized by the seed germination rate recognition module: when The first water pump is activated to extract nutrient solution from the nutrient bin 8 through one end of the first water pump, and the other end of the first water pump is connected to the liquid guide tube 10, and the extracted nutrient solution is transmitted to the drip tube 11 through the liquid guide tube 10. After the drip tube 11 is filled with nutrient solution, the nutrient solution is squeezed out from the small holes of the drip tube 11 by pressure and drips into the planting trough 6 by drip irrigation; when the second water pump is activated, one end of the second water pump is responsible for extracting nutrient solution from the nutrient bin 8, and the other end of the second water pump is connected to the nozzle, which is installed on the top of the inside of the conical planting frame 5 to irrigate the planting trough 6 by spraying.

[0013] Furthermore, the seed germination rate recognition module includes a camera 17 and a host computer. The camera 17 is installed on the side of the mounting plate 4 close to the conical planting rack 5. The camera 17 captures the image from the conical planting rack 5 and transmits it to the host computer. The host computer uses a small target detection algorithm based on the improved YOLOv5 to monitor the germination rate.

[0014] According to a second aspect of the present invention, a control method for an intelligent integrated vegetable growing machine is provided, and the method steps are as follows:

[0015] Humidity control: take pictures through the camera 17 in the seed germination rate recognition module, and the upper computer calls the small target detection algorithm based on the improved YOLOv5 to perform target recognition based on the obtained image information, and calculates the seed germination rate based on the target recognition result; when the temperature and humidity sensor 15 detects that the current humidity is not within the preset humidity range, and recognizes that the current seed germination rate is greater than or equal to the preset ratio value, the second water pump in the second execution component is driven to operate through the intelligent control module; when the temperature and humidity sensor 15 detects that the current humidity is not within the preset humidity range, and recognizes that the current seed germination rate is less than the preset ratio value, the first water pump in the second execution component is driven to operate through the intelligent control module;

[0016] Temperature control: When the external temperature sensor detects that the outside temperature is not within the preset range of the external temperature, the insulation film in the first execution component is closed, and then the temperature inside the vegetable grower is detected according to the temperature and humidity sensor 15. If the detected temperature is lower than the preset range of the internal temperature, the motor module in the first execution component is driven by the intelligent control module to control the insulation film to increase the temperature until it reaches the preset range of the internal temperature and then stops increasing the temperature; if the temperature detected by the temperature and humidity sensor 15 is higher than the preset range of the internal temperature, the insulation film is controlled to lower the temperature until it reaches the preset range of the internal temperature and then stops decreasing the temperature; when the temperature detected by the external temperature sensor continues to be within the preset range of the external temperature and reaches the preset time, the motor is controlled to open the insulation film;

[0017] Light control: If the light sensor 16 detects and determines that the light intensity at this time is lower than the preset range of light intensity, the intelligent control module drives the light strip 7 to increase the brightness until the detected light intensity is within the preset range of light intensity, and then the adjustment of the brightness of the light strip 7 is stopped; if the light sensor 16 detects and determines that the light intensity at this time is higher than the preset range of light intensity, the intelligent control module drives the light strip 7 to decrease the brightness until the detected light intensity is within the preset range of light intensity, and then the adjustment of the brightness of the light strip 7 is stopped;

[0018] Liquid level control: If the liquid level sensor 28 detects that the nutrient solution level is lower than a preset position, a prompt message indicating that the nutrient solution level is insufficient is displayed on the LCD screen 18 .

[0019] Furthermore, the small target detection algorithm based on the improved YOLOv5 adopts a simplified yolov5s model. The simplified yolov5s model takes the standard yolov5s model as the framework, and the backbone network of the standard yolov5s model is modified as follows:

[0020] Layer 2: Reduce the number of repetitions of the C3 module in the second layer of the backbone network in the standard model from 3 to 2;

[0021] Layer 4: Reduce the number of repetitions of the C3 module in the fourth layer of the backbone network in the standard model from 6 to 3;

[0022] Layer 6: Reduce the number of repetitions of the C3 module in the sixth layer of the backbone network in the standard model from 9 to 4;

[0023] Layer 8: Reduce the C3 module in the 7th layer of the backbone network in the standard model from 3 repetitions to 2 repetitions.

[0024] According to a third aspect of the present invention, a seed germination state recognition method is provided, which adopts a small target detection algorithm based on an improved YOLOv5 to recognize the seed germination state; wherein the small target detection algorithm based on the improved YOLOv5 adopts a simplified yolov5s model, and the simplified yolov5s model is based on the standard yolov5s model as the framework, and the backbone network of the standard yolov5s model is modified as follows:

[0025] Layer 2: Reduce the number of repetitions of the C3 module in the second layer of the backbone network in the standard model from 3 to 2;

[0026] Layer 4: Reduce the number of repetitions of the C3 module in the fourth layer of the backbone network in the standard model from 6 to 3;

[0027] Layer 6: Reduce the number of repetitions of the C3 module in the sixth layer of the backbone network in the standard model from 9 to 4;

[0028] Layer 8: Reduce the C3 module in the 7th layer of the backbone network in the standard model from 3 repetitions to 2 repetitions.

[0029] The beneficial effects of the present invention are:

[0030] Compared with the existing soilless cultivation vegetable growing machine, the present invention can intelligently control the light intensity, temperature, humidity, and nutrient solution level of the vegetable growing machine, thereby reducing the cost of manual planting, helping people free their hands, and realizing autonomous planting. It can also use a camera to identify the seed germination rate and monitor the growth status of vegetables in real time, thereby improving the intelligence level of the home-type soilless cultivation vegetable growing machine and the survival rate of vegetables planted by the vegetable growing machine. At the same time, the present invention can autonomously plant vegetables when the user is out working, with almost no manual operation required, saving the user's time and energy, and realizing autonomous vegetable planting at home over a long distance. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a simplified block diagram of the intelligent vegetable growing machine according to an embodiment of the present invention;

[0032] Figure 2 This is a schematic diagram of the overall structure of the intelligent vegetable growing machine according to an embodiment of the present invention;

[0033] Figure 3 This is a schematic diagram of the structure of the truncated cone type planting rack according to an embodiment of the present invention;

[0034] Figure 4 A top view of the base structure according to an embodiment of the present invention (with a cover plate);

[0035] Figure 5 A top view of the base structure according to an embodiment of the present invention (without a cover plate);

[0036] Figure 6A bottom view of the overall structure of the intelligent vegetable growing machine according to an embodiment of the present invention;

[0037] Figure 7 It is a schematic diagram of a local structure of a mounting plate according to an embodiment of the present invention;

[0038] Figure 8 A schematic diagram of a mounting plate structure according to an embodiment of the present invention (with a cross bar);

[0039] Fig. 9 A schematic diagram of a mounting plate structure according to an embodiment of the present invention (without a cross bar);

[0040] Fig.10 is a schematic diagram of a transverse rod structure according to an embodiment of the present invention;

[0041] Fig.11 A schematic diagram of a ventilation device according to an embodiment of the present invention;

[0042] Fig.12 A schematic diagram of the internal structure of a truncated cone planting rack according to an embodiment of the present invention;

[0043] Fig.13 This is a training and testing flow chart of a small target detection algorithm based on an improved YOLOv5 according to an embodiment of the present invention;

[0044] Fig.14 The yolov5s architecture described in the embodiment of the present invention;

[0045] Fig.15 This is a diagram of the MobileNetV3 network structure described in an embodiment of the present invention;

[0046] Fig.16 This is a structural diagram of the C3 module according to an embodiment of the present invention;

[0047] Fig.17 This is a practical application test diagram of Simplify_yolov5s described in an embodiment of the present invention;

[0048] The numbers in the figure are: 1 body shell; 2 base; 3 support rod; 4 mounting plate; 5 conical planting rack; 6 planting trough; 7 light strip; 8 nutrient bin; 9 recovery port; 10 liquid guide tube; 11 drip tube; 12 fixing screw; 13 root system port; 14 ventilation device; 15 temperature and humidity sensor; 16 light sensor; 17 camera; 18 LCD screen; 19 liquid level sensor placement port; 20 planting rack buckle; 21 central control bin; 22 wheels; 23 circular track; 24 transverse rod; 25 fixing plate; 26 nutrient bin cover; 27 central control bin cover; 28 liquid level sensor. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other arbitrarily without conflict.

[0050] refer to Figure 1-17 As shown, according to the first aspect of an embodiment of the present invention, there is provided an intelligent integrated vegetable growing machine, including a body shell 1, an environment detection module, an intelligent control module, a first execution component, a seed germination rate recognition module, and a second execution component; the body shell 1 includes a base 2, a support rod 3, a mounting plate 4, a truncated cone planting frame 5, and a nutrient bin 8; the base 2 is provided with a first notch for setting the nutrient bin 8 for pulling movement relative to the base 2; the base 2 is provided with a second notch as a central control bin 21 for installing the intelligent control module, and a truncated cone planting frame 5 is installed on the base 2, and the truncated cone planting frame 5 The nutrient bin 8 is communicated with the recovery port 9 opened on the base 2; the base 2 is connected to the mounting plate 4 via a support rod 3 arranged along the axial direction of the truncated cone planting rack 5, and there is a gap between the mounting plate 4 and the truncated cone planting rack 5; the environment detection module is used to transmit the detected first environment information and the second environment information to the intelligent control module, the intelligent control module is used to drive the first execution component to act according to the received first environment information, and the intelligent control module is used to drive the second execution component to act according to the received second environment information and the germination rate information recognized by the seed germination rate recognition module.

[0051] Furthermore, a detachable transverse rod 24 is provided below the mounting plate 4; a third notch serving as a liquid level sensor placement port 19 is provided on one side of the base 2 close to the first notch;

[0052] The environment detection module includes a temperature and humidity sensor 15, a light sensor 16, a liquid level sensor 28, a liquid crystal display screen 18, and a temperature sensor; the temperature and humidity sensor 15 is installed above the base 2 and is covered by the truncated cone planting rack 5, and is used to detect the temperature and humidity inside the truncated cone planting rack 5, and the internal temperature is used as the first environmental information, and the humidity is used as the second environmental information; the temperature sensor is used to detect the outdoor temperature information, and the outdoor temperature is used as the first environmental information; it should be noted that the temperature sensor can use the temperature acquisition function of the temperature and humidity sensor, or can also be separately configured with a sensor with only the temperature acquisition function. In the example of the present invention, a sensor of the same model as the temperature and humidity sensor 15 is used;

[0053] The light sensor 16 is installed on the side of the transverse rod 24 away from the center, and is used to detect the light intensity, that is, the light intensity received by the planted vegetables, and uses the light intensity as the first environmental information;

[0054] The liquid level sensor 28 is installed in the liquid level sensor placement port 19 and is used to detect the liquid level of the nutrient solution in the nutrient bin 8;

[0055] The LCD screen 18 is installed on the outside of one side support rod 3, and is used to display the detected first and second environmental information, to indicate the insufficient nutrient solution level, and to indicate whether the first and second environmental information are within a suitable range.

[0056] Further, the mounting plate 4 is connected to the transverse rod 24 through a fixing plate 25. The fixing plate 25 is divided into a concave surface and a convex surface. The concave surface of the fixing plate 25 is a circular concave column arranged in the middle of the mounting plate 4. A groove is arranged inside the circular concave column. The convex surface of the fixing plate 25 is a circular annular convex column arranged in the middle of the transverse rod 24. A clamping groove is arranged at both ends of the circular annular convex column. With reference to the mortise and tenon fixing structure, the annular protrusion next to the clamping groove in the circular annular convex column on the convex surface of the fixing plate 25 is inserted into the groove in the circular concave column on the concave surface of the fixing plate 25. The concave surface and the convex surface of the fixing plate 25 are combined by rotation to connect the mounting plate 4 to the transverse rod 24. A light sensor 16 is installed on the outermost end side of the transverse rod 24, and the light sensor 16 is used to detect the light intensity of the intelligent vegetable growing machine.

[0057] Exemplarily, the base is cylindrical, and the first notch, the second notch, and the third notch are all fan-shaped groove areas of the base 2; the nutrient bin cover 26 and the central control bin cover 27 are parts cut out of the base 2, which can be taken out separately, and the nutrient bin cover 26 and the central control bin cover 27 are respectively fixed to the base 2 with fixing screws 12, and the nutrient bin cover 26 is used to cover the nutrient bin 8 and the liquid level sensor placement port 19, and the central control bin cover 27 is used to cover the central control bin 21, and the nutrient bin cover 26 and the central control bin cover 27 separate the nutrient bin 8, the liquid level sensor placement port 19, and the central control bin 21 from the conical planting rack 5; the recovery port 9 is arranged in the middle of the base 2 and is located above the nutrient bin 8. It is a smaller fan-shaped groove, which can allow excess nutrient solution in the conical planting rack 5 to flow into the nutrient bin 8 through the recovery port 9. Furthermore, the first slot and the second slot are arranged adjacent to each other, and the first slot and the third slot are arranged opposite to each other; the partition between the adjacently arranged first slot and the second slot is a thin plate, so that the liquid level sensor 28 installed in the liquid level sensor placement port 19 can detect the liquid level of the nutrient solution in the nutrient bin 8.

[0058] Furthermore, wheels 22 are installed at the bottom of the base 2, and each two wheels 22 are separated by a quarter of a sector, with a total of four wheels 22. The installation of the wheels 22 is conducive to the movement of the vegetable growing machine device.

[0059] Furthermore, the installation plate 4 is 50 cm away from the truncated cone planting frame 5 to facilitate the installation of the light sensor 16, the camera 17, the circular track 23, etc.

[0060] Furthermore, planting frame buckles 20 are provided on both sides of the bottom of the truncated cone planting frame 5, which are used to fit the truncated cone planting frame 5 with the base 2 to fix the truncated cone planting frame 5. Planting grooves 6 are provided at intervals on each step tread of the truncated cone planting frame 5, and many root openings 13 are provided on the planting grooves 6, so that the roots of the vegetable plants can pass through the root openings 13 to reach the inside of the truncated cone planting frame 5 and receive watering inside the truncated cone planting frame 5. A ventilation device 14 is provided in the middle layer of the truncated cone planting frame 5, which can connect the inside and outside of the truncated cone planting frame 5, so that the internal and external air of the truncated cone planting frame 5 circulates to ensure the renewal of the air inside the truncated cone planting frame 5 and provide a certain amount of oxygen for the roots of the vegetable plants.

[0061] Furthermore, the first execution component includes:

[0062] Light strips 7, the light strips 7 are installed on the inner sides of the support rods 3 on both sides, the inner side of the support rods 3 is a side close to the truncated cone planting rack 5, so that the intelligent control module drives the light strips 7 to turn on / off according to the received first environmental information, and supplements the light intensity in the turned-on state to achieve the light intensity required by the vegetables;

[0063] The arc track 23 is installed on the side of the mounting plate 4 close to the conical planting frame 5. A slide is provided on the arc track 23 to connect the thermal insulation film, so that the intelligent control module drives the motor module according to the received first environmental information, drives the slide to move through the motor module, and drives the thermal insulation film to be opened / closed through the movement of the slide.

[0064] For example, Figure 1As shown, the base 2 is connected to the mounting plate 4 through two support rods 3 arranged along the axial direction of the truncated cone planting frame 5, one end of the support rod 3 is connected to the mounting plate 4 through a fastening screw, and the other end of the support rod 3 is connected to the base 2 through a screw; two arc tracks 23 are installed on the mounting plate 4 close to the side of the truncated cone planting frame 5, one arc track 23 is located on one side of the two support rods, and the other arc track 23 is located on the other side of the two support rods, so that the two circular tracks 23 are installed on the edge of the inner side of the mounting plate 4 in a ring manner; a rotating shaft is installed at one end of the two arc tracks 23, and a pressure sensor is installed at the other end of the two arc tracks 23, that is, there are two rotating shafts and two Pressure sensor; after plugging in the power supply, the intelligent control module drives the motor module to operate, the motor module rotates the shaft, a thin wire is wound around the shaft and arranged along the track, the slide is installed on the thin wire, the thin wire is released by the forward rotation of the shaft, so that the slide on the thin wire follows the thin wire, and a thermal insulation film is installed on the slide, thereby driving the thermal insulation film to move on the track, so as to achieve the effect of closing the thermal insulation film; the two pressure sensors installed at the connection between the mounting plate 4 and the support rod 3 are respectively used to detect the pressure of the slide on the tracks on both sides to determine whether the slide has reached the pressure sensor placement. If it reaches the pressure sensor placement, the pressure sensor receives a pressure signal and commands the motor module to stop driving the shaft to rotate. Similarly, if the motor module drives the shaft to reverse, it drives the thermal insulation film to open, so as to achieve the effect of controlling the thermal insulation film to close and open.

[0065] The intelligent control module drives the motor module according to the received first environmental information, specifically: when the external temperature sensor detects that the external temperature is not within the set range, the insulation film is closed, and then the temperature in the vegetable grower is detected according to the temperature and humidity sensor 15. If the detected temperature is lower than the appropriate temperature range, the motor module is driven to control the insulation film to increase the temperature, and the temperature will not be increased if it reaches the appropriate range; if the temperature is higher than the appropriate temperature range, the insulation film is controlled to lower the temperature, and the temperature will not be lowered if it reaches the appropriate range. When the temperature detected by the external temperature sensor is continuously within the set range and reaches a preset time, the motor is controlled to open the insulation film.

[0066] The intelligent control module drives the light strip 7 to turn on / off according to the received first environmental information. Specifically, if the light sensor 16 detects and determines that the light intensity at this time is lower (higher) than the appropriate range of light intensity, the light strip 7 is automatically controlled to increase (lower) the brightness until the detected light intensity reaches the appropriate range, and then the adjustment of the brightness of the light strip 7 is stopped.

[0067] Furthermore, the seed germination rate recognition module includes a camera 17 and a host computer. The camera 17 is installed on the side of the mounting plate 4 close to the truncated cone planting rack 5. The camera 17 captures the image from the truncated cone planting rack 5 and transmits it to the host computer. The host computer uses a small target detection algorithm based on the improved YOLOv5 to monitor the germination rate. The camera 17 is installed at the center of the transverse rod 24, and the planting status of the seeds or seedlings in the planting groove 6 is observed through the camera 17.

[0068] Furthermore, the second execution component includes a liquid guide tube 10, a liquid dripping tube 11, a first water pump, and a second water pump; the liquid dripping tube 11 is installed inside the truncated cone planting rack 5, and is surrounded in a circular shape inside each layer of the truncated cone; the liquid guide tube 10 is installed inside the truncated cone planting rack 5, connecting the liquid dripping tubes 11 of the upper and lower layers; the liquid dripping tube 11 is provided with a small hole, and the small hole corresponds to the planting groove 6; the intelligent control module is used to drive the first water pump / the second water pump to operate according to the received second environmental information and the germination rate information recognized by the seed germination rate recognition module: when the first water pump is operated, the first water pump is used to pump water from the nutrient bin through one end of the first water pump 8, the other end of the first water pump is connected to the liquid guide tube 10, and the extracted nutrient solution is transmitted to the drip tube 11 through the liquid guide tube 10. After the drip tube 11 is filled with nutrient solution, the nutrient solution is squeezed out from the small hole of the drip tube 11 by pressure, and dripped into the planting trough 6 by drip irrigation. A water-absorbing sponge is placed in the planting trough 6 to absorb the dripping nutrient solution and maintain a certain humidity; when the second water pump is activated, one end of the second water pump is responsible for extracting nutrient solution from the nutrient bin 8, and the other end of the second water pump is connected to the nozzle, which is installed on the top of the inside of the conical planting rack 5 to irrigate the roots of the seedlings in the planting trough 6 by spraying.

[0069] Specifically, the camera 17 can be installed in the left groove of the transverse rod 24 below the mounting plate 4 to monitor the growth status of vegetables and the germination rate of seeds in the planting groove 6 in real time; the planting groove 6 is arranged on each layer of the truncated cone planting frame 5, and is staggered and distributed according to the size of each layer of the truncated cone, and vegetable seeds or seedlings can be placed in the planting groove 6 for planting; the root openings 13 are densely arranged on each planting groove 6 to ensure that the vegetable roots pass through the root openings 6 to reach the inside of the truncated cone planting frame 5 to absorb the sprayed nutrient solution. When the temperature and humidity sensor 15 detects that the current humidity is not within the appropriate range and the camera 17 recognizes that the current seed germination rate is greater than 90%, the second water pump is used to extract the nutrient solution in the nutrient bin 8. One end of the water pump is responsible for extracting the nutrient solution from the nutrient bin 8, and the other end is connected to the nozzle, which is installed on the top of the conical planting rack 5 to spray the roots of the seedlings in the planting trough 6; when the temperature and humidity sensor 15 detects that the current humidity is not within the appropriate range and the camera 17 recognizes that the current seed germination rate is less than 90%, the first water pump is activated to extract the nutrient solution in the nutrient bin 8 to achieve drip irrigation of the seeds.

[0070] According to a second aspect of an embodiment of the present invention, a control method for an intelligent integrated vegetable growing machine is provided, and the method steps are as follows:

[0071] Humidity control: take pictures through the camera 17 in the seed germination rate recognition module, and the upper computer calls the small target detection algorithm based on the improved YOLOv5 to perform target recognition based on the obtained image information, and calculates the seed germination rate based on the target recognition result; when the temperature and humidity sensor 15 detects that the current humidity is not within the preset humidity range, and recognizes that the current seed germination rate is greater than or equal to the preset ratio value, the second water pump in the second execution component is driven to operate through the intelligent control module; when the temperature and humidity sensor 15 detects that the current humidity is not within the preset humidity range, and recognizes that the current seed germination rate is less than the preset ratio value, the first water pump in the second execution component is driven to operate through the intelligent control module;

[0072] Temperature control: When the external temperature sensor detects that the outside temperature is not within the preset range of the external temperature, the insulation film in the first execution component is closed, and then the temperature inside the vegetable grower is detected according to the temperature and humidity sensor 15. If the detected temperature is lower than the preset range of the internal temperature, the motor module in the first execution component is driven by the intelligent control module to control the insulation film to increase the temperature until it reaches the preset range of the internal temperature and then stops increasing the temperature; if the temperature detected by the temperature and humidity sensor 15 is higher than the preset range of the internal temperature, the insulation film is controlled to lower the temperature until it reaches the preset range of the internal temperature and then stops decreasing the temperature; when the temperature detected by the external temperature sensor continues to be within the preset range of the external temperature and reaches the preset time, the motor is controlled to open the insulation film;

[0073] Light control: If the light sensor 16 detects and determines that the light intensity at this time is lower than the preset range of light intensity, the intelligent control module drives the light strip 7 to increase the brightness until the detected light intensity is within the preset range of light intensity, and then the adjustment of the brightness of the light strip 7 is stopped; if the light sensor 16 detects and determines that the light intensity at this time is higher than the preset range of light intensity, the intelligent control module drives the light strip 7 to decrease the brightness until the detected light intensity is within the preset range of light intensity, and then the adjustment of the brightness of the light strip 7 is stopped;

[0074] Liquid level control: If the liquid level sensor 28 detects that the nutrient solution level is lower than a preset position, a prompt message indicating that the nutrient solution level is insufficient is displayed on the LCD screen 18 .

[0075] Exemplarily, the use instructions of the intelligent integrated vegetable growing machine provided by the present invention are as follows:

[0076] The specific hardware description is as follows: The first water pump and the second water pump of the present invention are purchased USB watering pumps, the motor of this water pump is an enlarged 365 motor; the motor module that drives the thermal insulation film to move is an L298N motor driver board module; the pressure sensor is a KEYES resistive film pressure sensor module; the liquid level sensor 28 is an XKC-Y25-PNP / V non-contact liquid level sensor; the light sensor is a TCRT5000 infrared reflection sensor; the temperature and humidity sensor is a DHT11 temperature and humidity sensor module; the central control development chip used in the intelligent control module is an ESP-32-WROOM development board, a total of three; the camera is an esp32_CAM remote monitoring camera. The steps for use are as follows:

[0077] S1. The user uses the four wheels 22 at the bottom of the vegetable growing machine to place the vegetable growing machine at a suitable location at home;

[0078] S2, the user sows vegetable seeds or places vegetable seedlings into the planting groove 6 of each layer of the truncated cone planting rack 5;

[0079] S3, the user needs to pour the nutrient solution into the nutrient bin 8 so that the nutrient solution level reaches two-thirds of the nutrient bin 8;

[0080] S4. The user turns on the home WIFI, and after powering the ESP32 chip in the central control compartment 21, it can connect to the WiFi autonomously;

[0081] S5. Connect the power supply to the ESP32 chip in the central control compartment 21, so that the light strip 7, the temperature and humidity sensor 15, the light sensor 16, the camera 17, the LCD screen 18, the liquid level sensor 28, and the temperature sensor on the device can be powered;

[0082] S6, the camera 17 monitors the plants planted in the planting groove 6 and determines the seed germination rate. When the temperature and humidity sensor 15 detects that the current humidity is not within the preset humidity range and identifies that the current seed germination rate is greater than or equal to 90%, it can be determined that the planted plants or most of the seeds have germinated, and the watering mode is set to spray mode, that is, the second water pump is activated; on the contrary, if it is identified that the current seed germination rate is less than 90%, it is determined that the user is planting seeds and the germination rate is low at this time, and the watering mode is set to drip irrigation mode, that is, the first water pump is activated;

[0083] S7, when the temperature and humidity sensor 15, the light sensor 16, the liquid level sensor 28, and the temperature sensor are powered, they start to detect the temperature, humidity, nutrient solution level, external temperature, and light intensity near the device in the vegetable growing machine;

[0084] S8, transmit the detected data to the ESP32 chip, which analyzes the detected data and determines whether the data is within the appropriate range:

[0085] If the external temperature sensor detects that the outside temperature is not within the preset range of the external temperature, the thermal insulation film in the first execution component is closed (that is, the thermal insulation film surrounds the vegetable growing machine device), and then the temperature inside the vegetable growing machine is detected according to the temperature and humidity sensor 15. If the detected temperature is lower than the preset range of the internal temperature, the motor module in the first execution component is driven by the intelligent control module to control the thermal insulation film to increase the temperature until it reaches the preset range of the internal temperature and then stops increasing the temperature; if the temperature detected by the temperature and humidity sensor 15 is higher than the preset range of the internal temperature, the thermal insulation film is controlled to lower the temperature until it reaches the preset range of the internal temperature and then stops decreasing the temperature; when the temperature detected by the external temperature sensor continues to be within the preset range of the external temperature and reaches more than 10 seconds, the motor is controlled to open the thermal insulation film;

[0086] If the light sensor 16 detects and determines that the light intensity at this time is lower than the preset range of light intensity, the intelligent control module drives the light strip 7 to increase the brightness until the detected light intensity is within the preset range of light intensity, and then the adjustment of the brightness of the light strip 7 is stopped; if the light sensor 16 detects and determines that the light intensity at this time is higher than the preset range of light intensity, the intelligent control module drives the light strip 7 to decrease the brightness until the detected light intensity is within the preset range of light intensity, and then the adjustment of the brightness of the light strip 7 is stopped;

[0087] If the liquid level sensor 28 detects that the liquid level of the nutrient solution is less than one quarter of the container, a prompt message “Insufficient nutrient solution, please replenish nutrient solution in time” will be displayed on the LCD screen 18 .

[0088] By applying the above technical solution, it can be known that the current temperature, humidity, light intensity, and nutrient solution level values ​​can be observed through the LCD screen 18. For the nutrient solution level, when the liquid level value detected by the sensor is less than one-fourth of the container, the LCD screen 18 will display a prompt of "Insufficient nutrient solution, please replenish the nutrient solution in time". For temperature, humidity, and light intensity, if the values ​​detected by the temperature and humidity sensor 15 and the light sensor 16 are lower than the appropriate range, "Too low, being adjusted..." will be displayed after the corresponding detection value; if the values ​​detected by the temperature and humidity sensor 15 and the light sensor 16 are higher than the appropriate range, "Too high, being adjusted..." will be displayed after the corresponding detection value; if the values ​​detected by the temperature and humidity sensor 15 and the light sensor 16 are within the appropriate range, "Normal" will be displayed after the corresponding detection value.

[0089] According to a third aspect of the present invention, a seed germination state recognition method is provided, which adopts a small target detection algorithm based on an improved YOLOv5 to recognize the seed germination state; wherein the small target detection algorithm based on the improved YOLOv5 adopts a simplified yolov5s model, and the simplified yolov5s model is based on the standard yolov5s model as the framework, and the backbone network of the standard yolov5s model is modified as follows:

[0090] Layer 2: Reduce the number of repetitions of the C3 module in the second layer of the backbone network in the standard model from 3 to 2;

[0091] Layer 4: Reduce the number of repetitions of the C3 module in the fourth layer of the backbone network in the standard model from 6 to 3;

[0092] Layer 6: Reduce the number of repetitions of the C3 module in the sixth layer of the backbone network in the standard model from 9 to 4;

[0093] Layer 8: Reduce the C3 module in the 7th layer of the backbone network in the standard model from 3 repetitions to 2 repetitions.

[0094] The small target detection algorithm based on the improved YOLOv5 needs to be trained before calling. The specific training process is further given as follows:

[0095] Step 1. Download the public dataset of seed seedlings from the Kaggle platform, and use the labeling software LabelImg to annotate the dataset in YOLO format. The seedling images in the dataset are labeled as "alive" and the ungerminated holes are labeled as "dormant".

[0096] Step 2. Each image marked in Step 1 corresponds to a txt file with the same name as the image. Each line in the txt file represents a marked instance. There are 5 columns in total, which represent the label category, the ratio of the horizontal coordinate of the center of the marked box to the width of the image, the ratio of the vertical coordinate of the center of the marked box to the height of the image, the ratio of the width of the marked box to the width of the image, and the ratio of the height of the marked box to the height of the image. Finally, 800 training sets and 300 test sets are obtained.

[0097] Step 3: Use Mosaic-9 data enhancement on the collected vegetable seedling dataset, that is, randomly crop, randomly arrange, and randomly scale 9 pictures, and then combine them into one picture, while reasonably introducing some random noise. In the dataset, the picture format and background are too simple, and the target occupies too large a proportion of the picture space. The pictures captured by the camera on the vegetable growing machine are mostly top-down views, and the detection targets are small. Mosaic-9 data enhancement can splice multiple pictures into one picture to increase data diversity.

[0098] Furthermore, the specific steps of Mosaic-9 data enhancement in Step 3 are as follows:

[0099] 1) Assume that the model input size parameter is s, and generate a gray image with a size of 3s*3s;

[0100] 2) Randomly select a point from the rectangle defined by point A (s / 2, s / 2) and point B (5s / 2, 5s / 2) as the stitching center C = (x c ,y c );

[0101] x c =s / 2+(5s / 2-s / 2)·rand()

[0102] y c =s / 2+(5s / 2-s / 2)·rand()

[0103] 3) Randomly select 9 pictures and take part of them to piece together this picture. The 9 colors represent 9 sample pictures, and the excess parts will be discarded;

[0104] 4) After transforming the images, the final output is the data set enhanced by Mosaic-9. Finally, 800 enhanced training sets and 300 enhanced test sets are obtained.

[0105] Step 4: In order to improve the detection speed while maintaining high recognition accuracy, the model is streamlined and optimized. This optimization aims to reduce the computational complexity and inference time while ensuring the model's feature extraction capabilities to achieve the best balance between detection accuracy and speed. The specific optimization plan is as follows:

[0106] Solution 1: MobileNet_yolov5s:

[0107] Replace the original YOLOv5 backbone network with MobileNetV3. This module is a lightweight neural network architecture that can achieve higher feature extraction capabilities with lower computational effort. Replacing the YOLOv5 backbone network with MobileNetV3 can effectively reduce the computational complexity of the model and shorten the inference time.

[0108] The complex convolutional layers and C3 modules of the original YOLOv5 backbone network are replaced by the MobileNetV3 module to form a lightweight architecture. This not only speeds up the model's calculations, but also reduces memory usage and resource consumption, making the model more suitable for the embedded camera devices of this project and significantly improving the inference speed.

[0109] The backbone network is modified as follows:

[0110] The first layer is MobileNetV3 with parameters [24,1]. As the initial feature extraction layer of the network, it is responsible for capturing the basic feature information in the image. '24' indicates the number of output channels, '1' indicates the use of 1 convolution operation, the output feature map size is 80×80, and the stride is 3 / 8 to capture the more detailed information in the image.

[0111] The second layer is MobileNetV3 with parameters [48,2]. The number of channels in the second layer is increased to '48', and 2 convolution operations are performed to extract higher-level features. The output feature map size is 20×20, and the stride is 4 / 16. Compared with the first layer, the feature map size of this layer is significantly reduced, but it has stronger abstraction ability and can capture more important object information in the image.

[0112] The third layer is MobileNetV3 with parameters [576,3]. The number of channels in the third layer is increased to '576', and 3 convolution operations are performed to further enhance deep feature extraction. The output feature map size is kept at 20×20 with a stride of 5 / 32. This layer is responsible for integrating high-level features of the image so that subsequent layers can effectively recognize complex objects and background information.

[0113] Solution 2: Simplify_yolov5s:

[0114] In the original structure of YOLOv5, the C3 module is used for deep feature extraction and achieves efficient feature learning through multiple repetitions, thereby enhancing the recognition ability of the model. However, this repeated layer design also leads to high computational costs and affects the inference speed of the model.

[0115] In this solution, the number of repetitions of the C3 module is reduced to reduce the amount of calculation, and the parameter settings of the convolutional layer are adjusted to further simplify the network. This can not only retain the core feature extraction capabilities of the YOLOv5 model, but also reduce the complexity of the model, thereby finding a more reasonable balance between detection speed and accuracy. The detailed simplification is as follows:

[0116] Layer 2: The original network uses the C3 module and repeats it 3 times. The simplified version reduces the number of repetitions to 2 to reduce the amount of computation.

[0117] Layer 4: The C3 module is repeated 6 times in the original network, and the simplified version reduces it to 3 times, also to reduce computational costs.

[0118] Layer 6: The C3 module is repeated 9 times in the original network, and the simplified version reduces it to 4 times, significantly reducing the computational overhead.

[0119] Layer 8: The C3 module of the original network is repeated 3 times, and the simplified version is further reduced to 2 times.

[0120] After the adjustment, the model significantly simplified its structure while retaining its core feature extraction capabilities to achieve a good balance between accuracy and detection speed.

[0121] Step 5: Send the enhanced training set to different networks for iterative training, repeat the cycle 100 times, obtain the optimal training model, and use the test set to test the training model;

[0122] Step 6. To verify the effectiveness of the algorithm of the present invention, the improved algorithms MobileNet_yolov5s and Simplify_yolov5s of the present invention were tested on the same test set as the original yolov5s. The results of the comparison of various performance indicators are shown in Table 1. As can be seen from the analysis of Table 1, yolov5s, as a standard model, performs well in recall and precision, and also has the lowest border loss and confidence loss, but the processing speed is slow. MobileNet_yolov5s significantly improves the processing speed by adopting the MobileNetV3 structure, and the FPS is more than three times that of yolov5s, but the accuracy is reduced. Simplify_yolov5s has achieved a good balance between accuracy and speed, which is close to the accuracy of yolov5s and has a high FPS. It is suitable for the vegetable germination rate monitoring of this project that takes into account both accuracy and real-time performance. Therefore, this model is selected as the final detection model.

[0123] Table 1 Comparison of model parameters

[0124] Model cycle FPS Recall Accuracy Border loss Confidence loss yolov5s 100 20.034 0.92654 0.94243 0.022031 0.0096117 MobileNet_yolov5s 100 69.262 0.90558 0.90063 0.024510 0.0100680 Simplify_yolov5s 100 68.897 0.90873 0.94224 0.022664 0.0094546

[0125] Step 7. Verify the model and detect germinated and ungerminated targets under different lighting, backgrounds and angles; Fig.17 It can be seen that both the sprouted (0) and unsprouted (1) categories are effectively detected in the image, all sprouted and unsprouted targets are framed, and the labels of different categories are correctly distinguished. The ratio of the number of sprouts to the total number of targets is taken as the germination rate, and the total target is "sprouted targets + unsprouted targets". During the training process, the various loss functions and performance indicators of the model are continuously optimized, and the performance on the test set also shows that the model has good generalization ability and robustness. It shows that the model has good detection performance in various detection tasks and meets the actual requirements of this project for target detection.

[0126] The specific implementation modes of the present invention are described in detail above in conjunction with the accompanying drawings, but the present invention is not limited to the above implementation modes, and various changes can be made within the knowledge scope of ordinary technicians in this field without departing from the purpose of the present invention.

Claims

1. An intelligent integrated vegetable growing machine, characterized in that: The invention comprises a machine body shell (1), an environment detection module, an intelligent control module, a first execution component, a seed germination rate recognition module, and a second execution component; the machine body shell (1) comprises a base (2), a support rod (3), a mounting plate (4), a truncated cone type planting frame (5), and a nutrient bin (8); the base (2) is provided with a first notch for arranging a nutrient bin (8) that can be pulled relative to the base (2); the base (2) is provided with a second notch for installing the intelligent control module; the truncated cone type planting frame (5) is installed on the base (2), and the truncated cone type planting frame (5) and the nutrient bin (8) are connected via the base The recovery port (9) opened on (2) is arranged in a connected manner; the base (2) is connected to the mounting plate (4) through a support rod (3) arranged along the axial direction of the truncated cone planting frame (5), and there is a gap between the mounting plate (4) and the truncated cone planting frame (5); the environmental detection module is used to transmit the detected first environmental information and the second environmental information to the intelligent control module, the intelligent control module is used to drive the first execution component to act according to the received first environmental information, and the intelligent control module is used to drive the second execution component to act according to the received second environmental information and the germination rate information recognized by the seed germination rate recognition module.

2. The intelligent integrated vegetable growing machine according to claim 1, characterized in that: A detachable transverse rod (24) is provided below the mounting plate (4); and a third notch serving as a liquid level sensor placement opening (19) is provided on a side of the base (2) close to the first notch.

3. The intelligent integrated vegetable growing machine according to claim 2, characterized in that: The environment detection module comprises a temperature and humidity sensor (15), a light sensor (16), a liquid level sensor (28), a liquid crystal display screen (18), and a temperature sensor; the temperature and humidity sensor (15) is installed above the base (2) and is covered by the truncated cone planting frame (5), and is used to detect the temperature and humidity inside the truncated cone planting frame (5), and uses the internal temperature as the first environment information and the humidity as the second environment information; the temperature sensor is used to detect outdoor temperature information, and uses the outdoor temperature as the first environment information; The light sensor (16) is installed on a side of the transverse rod (24) away from the center and is used to detect light intensity and use the light intensity as the first environmental information; The liquid level sensor (28) is installed in the liquid level sensor placement port 19 and is used to detect the liquid level of the nutrient solution in the nutrient bin (8); The liquid crystal display screen (18) is installed on the outside of one side support rod (3) and is used to display the detected first and second environmental information and to indicate the insufficient liquid level of the nutrient solution.

4. The intelligent integrated vegetable growing machine according to claim 1, characterized in that: The first execution component comprises: A light strip (7), wherein the light strip (7) is installed on the inner side of the support rods (3) on both sides, and the inner side of the support rods (3) is a side close to the truncated cone planting frame (5), so that the intelligent control module can drive the light strip (7) to turn on / off according to the received first environmental information; An arc track (23) is installed on the side of the mounting plate (4) close to the conical planting frame (5). A slide is provided on the arc track (23) to connect the thermal insulation film, so that the intelligent control module drives the motor module according to the received first environmental information, drives the slide to move through the motor module, and drives the thermal insulation film to be opened / closed through the movement of the slide.

5. The intelligent integrated vegetable growing machine according to claim 1, characterized in that: The second execution component comprises a liquid guide tube (10), a liquid drip tube (11), a first water pump, and a second water pump; the liquid drip tube (11) is installed inside the truncated cone planting frame (5) and surrounds the inside of each layer of the truncated cone in a circular shape; the liquid guide tube (10) is installed inside the truncated cone planting frame (5) and connects the liquid drip tubes (11) of the upper and lower layers; the liquid drip tube (11) is provided with a small hole, and the small hole corresponds to the planting groove (6); the intelligent control module is used to drive the first water pump / the second water pump to operate according to the received second environmental information and the germination rate information recognized by the seed germination rate recognition module: when the first water pump The pump is activated, and nutrient solution is extracted from the nutrient bin (8) through one end of the first water pump, and the other end of the first water pump is connected to the liquid guide tube (10), and the extracted nutrient solution is transmitted to the drip tube (11) through the liquid guide tube (10). After the drip tube (11) is filled with nutrient solution, the nutrient solution is squeezed out from the small hole of the drip tube (11) by pressure, and dripped into the planting trough (6) by drip irrigation; when the second water pump is activated, one end of the second water pump is responsible for extracting nutrient solution from the nutrient bin (8), and the other end of the second water pump is connected to the nozzle, which is installed on the top of the inside of the truncated cone planting frame (5) to irrigate the planting trough (6) by spraying.

6. The intelligent integrated vegetable growing machine according to claim 1, characterized in that: The seed germination rate recognition module comprises a camera (17) and a host computer. The camera (17) is mounted on the side of the mounting plate (4) close to the truncated cone planting rack (5). The camera (17) captures an image from the truncated cone planting rack (5) and transmits it to the host computer. The host computer uses a small target detection algorithm based on an improved YOLOv5 to monitor the germination rate.

7. A control method for an intelligent integrated vegetable growing machine, characterized in that: The method steps are as follows: Humidity control: taking pictures through the camera (17) in the seed germination rate recognition module, the upper computer calls the small target detection algorithm based on the improved YOLOv5 to perform target recognition based on the obtained image information, and calculates the seed germination rate based on the target recognition result; when the temperature and humidity sensor (15) detects that the current humidity is not within the preset humidity range, and recognizes that the current seed germination rate is greater than or equal to the preset ratio value, the second water pump in the second execution component is driven to operate through the intelligent control module; When the temperature and humidity sensor (15) detects that the current humidity is not within the preset humidity range and identifies that the current seed germination rate is less than a preset ratio value, the first water pump in the second execution component is driven to operate through the intelligent control module; Temperature control: when the external temperature sensor detects that the outside temperature is not within the preset range of the external temperature, the insulation film in the first execution component is closed, and then the temperature in the vegetable growing machine is detected according to the temperature and humidity sensor (15). If the detected temperature is lower than the preset range of the internal temperature, the motor module in the first execution component is driven by the intelligent control module to control the insulation film to increase the temperature until the temperature rises to within the preset range of the internal temperature and then stops rising; if the temperature detected by the temperature and humidity sensor (15) is higher than the preset range of the internal temperature, the insulation film is controlled to lower the temperature until the temperature falls within the preset range of the internal temperature and then stops lowering the temperature; when the temperature detected by the external temperature sensor continues to be within the preset range of the external temperature and reaches a preset time, the motor is controlled to open the insulation film; Light control: if the light sensor (16) detects and determines that the light intensity at this time is lower than the preset light intensity range, the intelligent control module drives the light strip (7) to increase the brightness until the detected light intensity is within the preset light intensity range, and then the adjustment of the brightness of the light strip (7) is stopped; if the light sensor (16) detects and determines that the light intensity at this time is higher than the preset light intensity range, the intelligent control module drives the light strip (7) to decrease the brightness until the detected light intensity is within the preset light intensity range, and then the adjustment of the brightness of the light strip (7) is stopped; Liquid level control: If the liquid level sensor (28) detects that the nutrient solution liquid level is lower than a preset position, a prompt message indicating that the nutrient solution liquid level is insufficient is displayed on the liquid crystal display (18).

8. The control method of the intelligent integrated vegetable growing machine according to claim 7, characterized in that: The small target detection algorithm based on the improved YOLOv5 adopts a simplified yolov5s model. The simplified yolov5s model takes the standard yolov5s model as the framework, and the backbone network of the standard yolov5s model is modified as follows: Layer 2: Reduce the number of repetitions of the C3 module in the second layer of the backbone network in the standard model from 3 to 2; Layer 4: Reduce the number of repetitions of the C3 module in the fourth layer of the backbone network in the standard model from 6 to 3; Layer 6: Reduce the number of repetitions of the C3 module in the sixth layer of the backbone network in the standard model from 9 to 4; Layer 8: Reduce the C3 module in the 7th layer of the backbone network in the standard model from 3 repetitions to 2 repetitions.

9. A method for identifying the germination status of seeds, characterized in that: The germination state of seeds is identified by using a small target detection algorithm based on the improved YOLOv5; wherein, the small target detection algorithm based on the improved YOLOv5 adopts a simplified yolov5s model, which is based on the standard yolov5s model. The backbone network of the standard yolov5s model is modified as follows: Layer 2: Reduce the number of repetitions of the C3 module in the second layer of the backbone network in the standard model from 3 to 2; Layer 4: Reduce the number of repetitions of the C3 module in the fourth layer of the backbone network in the standard model from 6 to 3; Layer 6: Reduce the number of repetitions of the C3 module in the sixth layer of the backbone network in the standard model from 9 to 4; Layer 8: Reduce the C3 module in the 7th layer of the backbone network in the standard model from 3 repetitions to 2 repetitions.

Images