A light source system, a sensing method and a control method

Abstract

The present invention provides a light source system, including a sensor, a host computer, a control unit, a driving device, and light sources of several bands; the light source is used to provide the light required for plant growth; the driving device is used to generate a DC driving signal to drive the light source to output light; the sensor is used to measure the growth state of the plant; the host computer is used to process the growth state of the plant measured by the sensor and determine the light parameters required to promote plant growth; the control unit is used to adjust the current generated by the driving device to drive the light source according to the light parameters provided by the host computer. The present invention also relates to a perception method and a control method; the present invention adopts a perception method to determine whether the plant is in a stress state during the growth process, and controls the light source to output light to illuminate the plant according to the growth state, so as to adjust the stress state of the plant, thereby increasing the yield of the fruit.

Description

Technical Field

[0001] The present invention belongs to the technical field of light source control, and discloses a light source system, a sensing method and a control method for promoting plant growth. Background Art

[0002] Plant stress caused by biotic or abiotic factors has an adverse effect on plant growth and can significantly reduce the fruit yield of plants. Plant stress states are expressed in plants through many types of symptoms. For example, water stress closes stomata and hinders photosynthesis, leading to changes in leaf color and temperature. Other stress symptoms include morphological changes, such as leaf curling or wilting.

[0003] For light, the energy source for photosynthesis, light can also produce two forms of stress, namely stress caused by excessive light and insufficient light. For example, when the light intensity exceeds the requirements for photosynthesis, light may cause an imbalance in the accumulation of redox-active intermediates in plants, which in turn may inhibit photosynthetic reactive oxygen species (ROS) reactions and reduce photosynthetic production potential. In addition to visible light, ultraviolet (UV) light is also an inherent component of sunlight, especially the increasing levels of highly damaging UVB radiation reaching the earth's surface. Therefore, plants are vulnerable to photodamage. In order to minimize the possibility of photodamage, plants have developed various protective mechanisms, including rapid photosynthetic rearrangements and more persistent adjustments to metabolite composition, leaf morphology, flowering time and seed production. These mechanisms lead to changes in leaf morphology and color when plants are under light stress. In addition, additional environmental stresses, such as drought, temperature stress and nutrient deficiency, generally reduce photosynthetic capacity and exacerbate the effects of excessive light stress.

[0004] Early detection and mitigation of plant stress is critical to minimizing acute and chronic losses in productivity. For example, for fruit trees, the effectiveness of any remedial measures depends on timely detection and identification of stress. However, due to individual differences in light perception, people are very subjective when estimating leaf color and pattern when plants are stressed, and they are not necessarily accurate. Therefore, a method to automatically monitor plant stress and adjust light can detect and solve this problem as early as possible, minimizing the impact of plant stress on yield.

[0005] In addition, light can regulate various properties of crops, such as flowering, fruiting, biomass accumulation, immunity and nutritional value. With the maturity of LED light source technology, LED lighting can replace natural light or serve as a supplement to natural light, thereby reducing energy consumption, water and fertilizer usage, controlling plant growth processes and increasing nutritional content. Research reports indicate that every 1% increase in light in facility agriculture means a 0.8% increase in yield.

[0006] At present, there are two main problems with the known light source technology for plant lighting. First, the control system does not have the function of monitoring the growth status of the plant. Second, the light source system does not have the function of automatically adjusting the lighting parameters according to the stress state of the plant. Due to these two problems, the light source designed and implemented using the existing technology has the disadvantages of low production efficiency and may even cause light stress in the plant. Summary of the invention

[0007] In order to overcome the shortcomings of the prior art, the present invention provides a design method, a perception method and a control method of a light source system for plant lighting, which can automatically monitor the stress state of the plant and adjust the light to alleviate the stress state of the plant, thereby increasing the yield of plant fruits.

[0008] The present invention provides a light source system, including light sources of several wavebands, a driving device, a sensor, a control unit, and a host computer;

[0009] The light source is used to provide the light required for plant growth;

[0010] The driving device is used to generate a driving signal to drive the light source to output light;

[0011] The sensor is used to measure the growth status of the plant;

[0012] The host computer is used to process the growth status of the plant measured by the sensor and determine the lighting parameters required to promote plant growth;

[0013] The control unit is used to adjust the driving device to generate a current for driving the light source according to the illumination parameters provided by the host computer.

[0014] Further, the driving device includes a microprocessor and a constant current driver, the constant current driver outputs multiple direct currents to drive multiple spectral channels of the light source, and the microprocessor outputs multiple pulse width modulation signals to adjust multiple direct current amplitudes output by the constant current driver;

[0015] It also includes a constant voltage driver, which is used to convert AC voltage into DC voltage to power the microprocessor and the multiple constant current drivers.

[0016] Furthermore, the light source is composed of LED chips of multiple wavelength bands, including 400-470nm, 530-580nm, and 600-670nm.

[0017] Furthermore, the light source system may also include a sensor for measuring light intensity and spectrum.

[0018] A sensing method comprises the following steps:

[0019] S1, take an image of the target plant;

[0020] S2, identifying the color of plant leaves in the image;

[0021] S3. Determine the growth status of the plant based on the color of the leaves.

[0022] Furthermore, in step S1, the host computer performs image segmentation on the plant leaves in the image to identify the pixel range occupied by the plant leaf image.

[0023] Furthermore, in step S2, the grayscale values ​​of the RGB channels within the pixel range of the plant leaves in the image are respectively counted, and the grayscale value with the highest proportion in each channel is obtained as the peak value of the grayscale of the color channel.

[0024] Furthermore, in step S3, the peak values ​​of the RGB color channels within the leaf pixel range in the image are respectively obtained, and the peak values ​​of the RGB channels of the leaves are compared with the RGB color values ​​of the standard leaves to determine whether the color of the target leaves is within the range of the standard leaf colors; if so, the current illumination spectrum is kept unchanged; if not, the plant is in a stress state, and the illumination spectrum is switched to alleviate the stress state of the plant.

[0025] A light source control method comprises the following steps:

[0026] S1. According to the growth state of the plant, retrieve the illumination spectrum pre-saved in the host computer that matches the state, and set it as the illumination and spectrum that the ambient light should reach;

[0027] S2, using the sensor to measure the illumination and spectrum of the ambient light, and inputting the measurement information as a feedback signal into a feedback control module of the control unit;

[0028] S3, calculating a control signal according to the measured illuminance and spectrum and a preset irradiation spectrum, and adjusting the driving device by means of the control signal;

[0029] S4. The driving device outputs a direct current to the light source, causing the light source to emit light.

[0030] Furthermore, in step S3, the control algorithm is a model prediction control algorithm designed based on a mathematical relationship model between plant growth and light parameters.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] The present invention provides a light source system, a sensing method and a control method, which can automatically monitor the stress state of plants and adjust the irradiation parameters of LED light sources to alleviate the stress state of plant growth, thereby increasing the yield of plant fruits.

[0033] The method provided by the present invention is mainly suitable for supplementing natural light to illuminate plants, including but not limited to vegetables, fruits, flowers, medicinal herbs and the like.

[0034] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present invention in conjunction with the accompanying drawings. The specific implementation of the present invention is given in detail by the following embodiments and their accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0036] Figure 1 It is a schematic diagram of the structure of the light source system of the present invention;

[0037] Figure 2 This is a schematic diagram of the electric driving principle of the LED light source of the present invention;

[0038] Figure 3 is a flow chart of the sensing method of the present invention;

[0039] Figure 4 It is a flow chart of calculating the RGB color peak value within the leaf pixel range in the image of the present invention;

[0040] Figure 5 A schematic diagram of a photograph of a plant of the present invention;

[0041] Figure 6 A schematic diagram of segmenting a plant leaf image from an image of a photographed plant according to the present invention;

[0042] Figure 7 A schematic diagram of a grayscale value histogram of a color channel of a plant leaf image of the present invention;

[0043] Figure 8 Another schematic diagram of a histogram of grayscale values ​​of a color channel of a plant leaf image of the present invention;

[0044] Fig. 9 This is a flow chart of judging the growth status of a plant according to the present invention;

[0045] Fig.10 This is a schematic diagram of the present invention for controlling light output parameters of a light source using a model predictive control method. DETAILED DESCRIPTION

[0046] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form a new embodiment.

[0047] A light source system, such as Figure 1 As shown, it includes a sensor 101, a host computer 102, a control unit 103, a driving device 104, and a light source 105 of several bands; the light source 105 is used to provide the light required for plant growth; the driving device 104 is used to generate a DC driving signal to drive the light source 105 to output light; the sensor 101 is used to measure the growth state of the plant; the host computer 102 is used to process the growth state of the plant measured by the sensor, and determine the light parameters required to promote plant growth; the control unit 103 is used to adjust the current generated by the driving device to drive the light source according to the light parameters provided by the host computer.

[0048] As preferably, the driving device, such as Figure 2 As shown, it includes a microprocessor and a constant current driver; the constant current driver outputs multiple DC currents to drive multiple spectral channels of the light source, and the microprocessor outputs multiple pulse width modulation signals to adjust the multiple DC current amplitudes output by the constant current driver; it also includes a constant voltage driver, which is used to convert AC voltage into DC voltage to power the microprocessor and the multiple constant current drivers.

[0049] Preferably, the light source is composed of LED chips of multiple wavelength bands, including spectral components that plants mainly depend on for growth, such as blue light 400-470nm, green light 530-580nm, and red light 600-670nm.

[0050] Methods used to sense plant growth status, such as Figure 3 As shown, the following steps are included:

[0051] S1. Use an imaging device to capture an image of the target plant;

[0052] S2, identifying the color of plant leaves in the image;

[0053] S3. Determine the growth status of the plant based on the color of the leaves.

[0054] As a preferred method, the color of plant leaves in an image is identified by Figure 4 As shown, the following steps are included:

[0055] S21, segmenting the leaves in the image. Preferably, a convolutional neural network or a high-pass filter may be used to segment the image;

[0056] S22, identifying the pixel range occupied by the plant leaves in the image, that is, the set of row numbers and column numbers of the pixels in the leaf segmentation area;

[0057] S23. Calculate the peak values ​​of the RGB channels within the pixel range occupied by the leaves. Preferably, a histogram of the grayscale values ​​of each color channel can be drawn to count the number of pixels in each equally spaced grayscale value range. The grayscale value range with the largest number of pixels corresponds to the peak value of the leaf color in a certain channel.

[0058] In one embodiment, first capture Figure 5 The partial image 2 of a fruit tree 21 shown in FIG. 2 includes leaves of the fruit tree. A U-Net type convolutional neural network is used to Figure 5 The image is segmented and the Figure 6 The segmented image 2 of the leaf is shown in FIG. 201 , where 201 is the segmented leaf image. Continue to draw the histogram a of the green channel as shown in FIG. Figure 7 As shown, c is a bar graph of the number of pixels within a certain grayscale value range, and the shadow shown in b is the value range of the reference leaf color grayscale.

[0059] As a preferred method, the growth state of the plant is determined based on the color of the leaves, such as Fig. 9 As shown, the following steps are included:

[0060] S411, respectively obtaining the peak values ​​of the RGB color channels within the leaf pixel range in the image;

[0061] S412, comparing the peak value of the RGB channel of the leaf with the RGB color value of a standard leaf;

[0062] S413, judging whether the color of the target leaf is within the range of the standard leaf color;

[0063] S414. If yes, the plant is in a normal growth state, and the current irradiation spectrum is kept unchanged; if no, the plant is in a stress state, and the irradiation spectrum is switched to alleviate the stress state of the plant.

[0064] In one embodiment, Figure 7 As shown, the peak value c of the green channel of the photographed leaf is within the range b of the reference leaf color; therefore, the host computer determines that the photographed plant is in a normal growth state, and there is no need to trigger the controller to switch the lighting parameters of the LED light source.

[0065] In another embodiment, Figure 8 As shown, the peak value c of the green channel of the photographed leaf is not within the range d of the reference leaf color; the host computer determines that the photographed plant is in a state of excessive light stress, and then triggers the controller to lower the irradiance of the output light of the LED light source.

[0066] A light source control method, such as Fig. 9 As shown, the following steps are included:

[0067] S1. According to the growth state of the plant, retrieve the illumination spectrum pre-saved in the host computer that matches the state, and set it as the illumination and spectrum that the ambient light should reach;

[0068] S2, using a light sensor to measure the illumination and spectrum of the ambient light, and inputting the measurement information as a feedback signal into a feedback control module of the control unit;

[0069] S3, calculating a control signal according to the measured illuminance and spectrum and a preset irradiation spectrum, and adjusting the driving device by means of the control signal;

[0070] S4. The driving device outputs a direct current to the light source, causing the light source to emit light.

[0071] Preferably, in step S3, the algorithm for calculating the control signal is a model prediction control algorithm designed according to a mathematical relationship model between plant growth and light parameters.

[0072] In one embodiment, Fig.10 As shown, the model predictive control algorithm obtains the optimal light parameters and outputs them to the control unit, which then adjusts the DC current amplitude of the driving device to change the light parameters output by the light source until a preset plant growth state is reached.

[0073] To further illustrate the model predictive control algorithm, in one embodiment, a mathematical model between the growth state of the plant and the light parameters is first established as follows:

[0074] z=f(l,e) (1)

[0075] Among them, l and e are respectively the light parameter and other necessary environmental parameters; z represents the growth state of the plant. Preferably, z can be a real number between 0 and 1, where 0 represents that the plant has died and 1 represents that the plant is growing very vigorously; the smaller the decimal value in the middle, the stronger the stress state of the plant.

[0076] Based on model (1), a control algorithm can be designed using the model predictive control method commonly used in control theory, as follows:

[0077]

[0078] st0≤L m ≤1 (3)

[0079] 0≤Z m ≤1 (4)

[0080] Among them, Tm , Z m , L m 、E m They represent the expected value of the plant growth state within m future time sampling points starting from the current moment, the expression of the growth state derived from formula (1), the value of the illumination parameter, and the value of other necessary environmental parameters respectively; function Z m (L m , E m ) is directly derived from formula (1); operator That is, the weighted bi-norm; formulas (3) and (4) are the constraints for optimizing formula (2). After calculating formula (2-4) to obtain the optimal light parameter sequence Lm within the future m time sampling points, the light parameter corresponding to the current moment is taken as the optimal parameter at the current moment.

[0081] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in any form. Any ordinary technician in the industry can smoothly implement the present invention as shown in the drawings and above. However, any equivalent changes, modifications and evolutions made by technicians familiar with the profession without departing from the scope of the technical solution of the present invention using the technical content disclosed above are all equivalent embodiments of the present invention. At the same time, any equivalent changes, modifications and evolutions made to the above embodiments based on the essential technology of the present invention are still within the protection scope of the technical solution of the present invention.

Claims

1. A light source system, characterized in that: It includes light sources of several bands, driving devices, sensors, control units, and host computers; The light source is used to provide the light required for plant growth; The driving device is used to generate a driving signal to drive the light source to output light; The sensor is used to measure the growth status of the plant; The host computer is used to process the growth status of the plant measured by the sensor and determine the lighting parameters required to promote plant growth; The control unit is used to adjust the driving device to generate a current to drive the light source according to the illumination parameters provided by the host computer; The driving device comprises a microprocessor and a constant current driver, wherein the constant current driver outputs a plurality of direct currents to drive a plurality of spectral channels of the light source, and the microprocessor outputs a plurality of pulse width modulation signals to adjust a plurality of direct current amplitudes output by the constant current driver; The driving device further comprises a constant voltage driver, which is used to convert an AC voltage into a DC voltage to supply power to the microprocessor and the plurality of constant current drivers; The light source system also includes a sensor for measuring light intensity and spectrum; The light source is composed of LED chips of multiple wavelength bands, including 400-470nm, 530-580nm, and 600-670nm.

2. A perception method, characterized in that: The light source system as claimed in claim 1 is configured to perform the following steps: S1, take an image of the target plant; S2, identifying the color of plant leaves in the image; S3. Determine the growth status of the plant based on the color of the leaves; Wherein, in step S1, the host computer performs image segmentation on the plant leaves in the image to identify the pixel range occupied by the plant leaf image; In step S2, the grayscale values ​​of the RGB channels within the pixel range of the plant leaves in the image are respectively counted, and the grayscale value with the highest proportion in each channel is obtained as the peak value of the grayscale of the color channel; Among them, in step S3, the peak values ​​of the RGB color channels within the leaf pixel range in the image are respectively obtained, and the peak values ​​of the RGB channels of the leaves are compared with the RGB color values ​​of the standard leaves to determine whether the color of the target leaves is within the range of the standard leaf colors; if so, the current illumination spectrum is kept unchanged; if not, the plant is in a stress state, and the illumination spectrum is switched to alleviate the stress state of the plant.

3. A light source control method, characterized in that: The light source system as claimed in claim 1 is configured to perform the following steps: S1. According to the growth state of the plant, retrieve the illumination spectrum pre-saved in the host computer that matches the state, and set it as the illumination and spectrum that the ambient light should reach; S2, using the sensor to measure the illumination and spectrum of the ambient light, and inputting the measurement information as a feedback signal into a feedback control module of the control unit; S3, calculating a control signal according to the measured illuminance and spectrum and a preset irradiation spectrum, and adjusting the driving device by means of the control signal; S4, the driving device outputs a direct current to the light source, causing the light source to emit light; Wherein, in step S3, the algorithm for calculating the control signal is a model prediction control algorithm designed based on a mathematical relationship model between plant growth and light parameters.

Images