TWI786711B - Intelligent microalgae cultivation system and method thereof - Google Patents

Abstract

The present invention is an intelligent microalgae breeding system and its method, comprising a microalgae breeding farm, a nutrient solution device, at least one monitoring device and a control computer system, mainly through the system installed in the control computer system The convolutional neural network (CNN) recognizes the image of at least one culture container recorded by the monitoring equipment, and recognizes the concentration of microalgae in at least one culture container, and then the control computer system according to the identified at least one culture container Changes in the concentration of microalgae are used to operate the nutrient solution equipment, so that the nutrient solution equipment can output the set nutrient solution into the culture container, so that the microalgae in the culture container have the benefit of accelerating or slowing down the growth, allowing microalgae culture Can achieve large-scale performance.

Description

Intelligent microalgae cultivation system and method thereof

The present invention relates to an intelligent microalgae cultivation system and its method, especially a kind of benefit of accelerating growth or slowing down growth, so that microalgae cultivation can achieve large-scale performance, and is suitable for microalgae cultivation industry or similar cultivation environment.

Among the greenhouse gases emitted by industry, carbon dioxide is the largest. Microalgae have high photosynthetic efficiency and rapid growth, and the carbon dioxide reduction efficiency of microalgae cultivation is more than ten times that of ordinary plants. It is worth developing to grow microalgae to reduce carbon dioxide through the use of biotechnology and engineering technology, especially to directly use industrial waste gas containing carbon dioxide to grow algae and reduce carbon dioxide.

Microalgal matter can be used in the production of various biofuels such as biodiesel, bioalcohol, hydrogen, coke, etc., and microalgae can convert carbon dioxide into carbohydrates, proteins, lipids and other cell components through photosynthesis. Therefore, algal species that can simultaneously produce useful substances such as physiologically active substances, pigments such as lutein and carotenoids, and omega-3 fatty acids such as EPA and DHA during carbon fixation are most economically beneficial. In addition, microalgae can also be used as animal or aquaculture feed, and used to treat waste water and waste gas.

However, most of the microalgae cultures with the main goal of carbon reduction adopt self-supporting growth methods, and the main control conditions required for their growth are light, temperature, carbon dioxide, and nutrients in the medium. Many of these conditions are environmental factors, so most of them use the design of the microalgae cultivation system to improve the efficiency of microalgae cultivation. At present, the large-scale artificial culture of microalgae has open ponds and (semi) There are two ways to close the reactor, and the latter is called a photobioreactor because it can provide sufficient light. In addition, the use of photobioreactors to cultivate microalgae can achieve higher algae cell density (high microalgae yield), because the carbon dioxide passed into the reactor has a longer residence time in the culture solution, and can fully carry out gas-liquid Mixing, so the efficiency of dissolving carbon dioxide in the culture medium is high, and the effect of carbon reduction is also better, but the cost and operating cost are higher. Large-scale farming is not feasible if the microalgae produced are not of high economic value.

Therefore, in view of the above deficiencies, the inventor expects to propose a smart microalgae cultivation system and its method that allow microalgae cultivation to achieve large-scale performance, so that users can easily complete the operation and installation. Design and organization to provide user convenience is the motivation for the invention that the inventor wants to develop.

The main purpose of the present invention is to provide an intelligent microalgae culture system and its method, which includes a microalgae farm, a nutrient solution device, at least one monitoring device and a control computer system, mainly through the The convolutional neural network (CNN) in the control computer system recognizes the image of at least one culture container recorded by the monitoring equipment, and recognizes the concentration of microalgae in at least one culture container, and then the control computer system according to the identified Operate the nutrient solution device by changing the concentration of microalgae in at least one culture container, so that the nutrient solution device can output the set nutrient solution into the culture container, so that the microalgae in the culture container have the benefit of accelerating growth or slowing down growth , so that microalgae cultivation can achieve large-scale performance, thereby increasing the overall practicality.

Another object of the present invention is to provide an intelligent microalgae cultivation system and its method, through which the control computer system contains a machine learning (machine learning) program, when the convolutional neural network (CNN) records the monitoring equipment The image of the culture container is identified as the concentration of microalgae After the degree, each identification is integrated into the concentration of microalgae and the data is analyzed, and the microalgae cultivation model is established through the machine learning program, and the feedback control framework is formed by the microalgae cultivation model, so as to Achieve the effectiveness of building a smart microalgae cultivation system, thereby increasing the overall constructability.

In order to further understand the features, characteristics and technical content of the present invention, please refer to the following detailed description and drawings related to the present invention, but the attached drawings are only for reference and illustration, and are not intended to limit the present invention.

10:Microalgae farm

11: Scaffolding

12: Culture container

121: microalgae concentration

20: Nutrient solution equipment

30: Monitoring equipment

31: Lens

32: Image

40:Control computer system

50: Position sensor

S100: Put culture solution and microalgae

S110: Video recording of culture container

S120: Image identification of microalgae concentration

S130: Operate nutrient solution equipment

S140: output setting nutrient solution

Figure 1 is the first schematic diagram of the microalgae culture system of the present invention.

Figure 2 is the second schematic diagram of the microalgae culture system of the present invention.

Fig. 3 is a schematic flow chart of the main steps of the present invention.

Please refer to Figures 1 to 3, which are schematic diagrams of embodiments of the present invention, and the best implementation of the intelligent microalgae cultivation system and method thereof of the present invention is applicable to the microalgae cultivation industry or similar cultivation environments, and has The benefits of accelerating growth or slowing down growth allow microalgae cultivation to achieve large-scale performance.

And the intelligent microalgae culture system of the present invention is mainly provided with a microalgae farm 10, a nutrient solution device 20, at least one monitoring device 30 and a control computer system 40 (as shown in the first figure and the second figure) , the microalgae farm 10 is provided with a plurality of racks 11 and at least one culture container 12, and the culture container 12 is placed on the rack 11 (as shown in Figure 1), wherein the culture container 12 is Put culture fluid and microalgae, and this culture container 12 and this culture container The devices 12 are connected to each other, so that the culture solution and microalgae located in the culture containers 12 can flow between the culture containers 12, and the culture containers 12 are all transparent to increase the transparency of light irradiation during microalgae culture. Spend.

And the above-mentioned microalgae farm 10 is provided with a nutrient solution equipment 20 and at least one monitoring equipment 30 (as shown in the first figure and the 2nd figure), and the nutrient solution equipment 20 and the monitoring equipment 30 are respectively connected with the control system. The computer system 40 is connected, wherein the nutrient solution equipment 20 is connected with the culture container 12, so that the nutrient solution is delivered to the culture container 12 through the nutrient solution equipment 20 (as shown in Figure 2), so that the culture container 12 The microalgae inside can obtain nutrient solution, which is convenient to increase growth. In addition, the monitoring device 30 is provided with a lens 31, and through the lens 31, an image 32 of at least one culture container 12 is recorded (as shown in Figure 1), and then The image 32 of at least one culture vessel 12 is transmitted to the control computer system 40 for storage.

In addition, the above-mentioned culture container 12 is equipped with a position sensor 50, and the position sensor 50 is installed at the culture container 12 (as shown in Figure 1), and the position sensor 50 is connected to the The control computer system 40 is connected so that the control computer system 40 can know the position of the culture container 12 according to the position sensor 50 , so that the control computer system 40 can carry out subsequent operations.

Furthermore, the control computer system 40 is equipped with a convolutional neural network (Convolutional Neural Networks, CNN), which is a two-dimensional convolutional neural network (not shown). Image recognition is performed through the two-dimensional convolutional neural network, and the convolutional neural network (CNN) is mainly used to identify two-dimensional graphics with displacement, scaling and other forms of distortion invariance. This part of the function is mainly realized by the pooling layer , and the basic structure of the convolutional neural network (CNN) includes two layers, one is the feature extraction layer, and the input of each neuron is related to the regional receptive field of the previous layer connected and extract the characteristics of the culture. Once the regional feature is extracted, the positional relationship between it and other features is also determined; the second is the feature mapping layer. Each computing layer of the network is composed of multiple feature mappings. A map is a plane on which all neurons have equal weights.

The above-mentioned control computer system 40 recognizes the image 32 of at least one culture container 12 recorded by the monitoring device 30 through a convolutional neural network (CNN) (as shown in Figure 1), when the culture container 12 After the microalgae grow for a period of time, the microalgae concentration 121 (as shown in Figure 1) of the recorded culture container 12 is identified by convolutional neural network (CNN), and the microalgae concentration 121 of the culture container 12 is recorded. algae concentration 121, and when there is a difference between the microalgae concentration 121 of the culture container 12 and the set target value (as shown in Figure 2), then the control computer system 40 will Changes to operate the nutrient solution equipment 20, so that the nutrient solution equipment 20 can output the set nutrient solution into the culture container 12 (as shown in Figure 2), so that the microalgae in the culture container 12 have accelerated growth or Growth-reducing benefits. In addition, the control computer system 40 contains a machine learning (machine learning) program (not shown), when the convolutional neural network (CNN) recognizes the image 32 of the culture container 12 recorded by the monitoring device 30 into micro After the concentration of algae is 121, each identification is integrated into the concentration of microalgae 121 and the data is analyzed, and the microalgae cultivation model is established through the machine learning program, and the feedback control is formed by the microalgae cultivation model Framework to achieve the effectiveness of building a smart microalgae cultivation system, thereby increasing the overall constructability.

In addition, the intelligent microalgae culture method of the present invention is mainly used for microalgae culture, and includes a microalgae farm 10, a nutrient solution device 20, at least one monitoring device 30 and a control computer system 40 (as shown in Fig. 1 and shown in Fig. 2), the microalgae farm 10 series is equipped with At least one culture container 12, the nutrient solution equipment 20 is located in the microalgae farm 10, the monitoring device 30 is installed in the microalgae farm 10, the control computer system 40 is connected with the monitoring device 30 and the nutritional The liquid device 20 is connected, and the control computer system 40 is equipped with a convolutional neural network (CNN).

And its microalgae cultivation method, first carry out (as shown in Fig. 3) step S100 and put into nutrient solution and microalgae: in at least one culture container 12 that this microalgae farm 10 is installed, put into nutrient solution and Microalgae, for microalgae cultivation. After the above step S100 is completed, the next step S110 is performed.

In the above-mentioned step S100, the microalgae farm 10 is provided with a plurality of racks 11 and at least one culture container 12, and the culture container 12 is placed on the rack 11 (as shown in Figure 1), wherein The culture container 12 is put into the culture fluid and the microalgae, and the culture container 12 and the culture container 12 are communicated with each other, so that the culture fluid and the microalgae in the culture container 12 can flow between the culture containers 12, In addition, the culture containers 12 are all transparent to increase the transparency of light irradiation during microalgae cultivation. In addition, the culture container 12 is equipped with a position sensor 50, the position sensor 50 is installed at the culture container 12 (as shown in Figure 1), and the position sensor 50 is connected with the control The computer system 40 is connected so that the control computer system 40 can know the position of the culture container 12 according to the position sensor 50 , so that the control computer system 40 can carry out subsequent operations.

In addition, the next step S110 is to record the image of the culture container: monitor at least one culture container 12 through the monitoring equipment 30 installed in the microalgae farm 10, and record at least one culture container 12 through the lens 31 of the monitoring equipment 30. An image 32 of a culture container 12 . After the above step S110 is completed, the next step S120 is performed.

In the above-mentioned step S110, the microalgae farm 10 is provided with a nutrient solution device 20 and at least one monitoring device 30 (as shown in Fig. 1 and Fig. 2), and the nutrient solution device 20 and the monitoring device 30 are Connect with the control computer system 40 respectively, wherein the nutrient solution equipment 20 is connected with the culture container 12, so that the nutrient solution can be delivered to the culture container 12 through the nutrient solution equipment 20 (as shown in Figure 2), Allow the microalgae in the culture container 12 to obtain nutrient solution, so as to increase the growth. In addition, the monitoring device 30 is provided with a lens 31, and through the lens 31, an image 32 of at least one culture container 12 is recorded (as shown in FIG. 1 . shown), and then transmit the image 32 of at least one culture container 12 to the control computer system 40 for storage.

In addition, in the next step S120 image recognition of microalgae concentration: the control computer system 40 recognizes the image 32 of at least one culture container 12 captured by the monitoring device 30 through a convolutional neural network (CNN), and recognizes The microalgae concentration 121 of at least one culture container 12 . After the above step S120 is completed, the next step S130 is performed.

In the above-mentioned step S120, the control computer system 40 is equipped with a convolutional neural network (Convolutional Neural Networks, CNN), and the convolutional neural network (CNN) is a two-dimensional convolutional neural network (not shown). ), to perform image recognition through the two-dimensional convolutional neural network, and the convolutional neural network (CNN) is mainly used to identify two-dimensional graphics that are invariant to displacement, scaling and other forms of distortion. This part of the function is mainly performed by the pool The basic structure of the convolutional neural network (CNN) includes two layers, one is the feature extraction layer, the input of each neuron is connected to the regional receptive field of the previous layer, and the regional receptive field is extracted. feature. Once the regional feature is extracted, the positional relationship between it and other features is also determined; the second is the feature mapping layer. Each computing layer of the network is composed of multiple feature mappings. The reflection is a plane on which all Neurons have equal weights. The control computer system 40 recognizes the image 32 of at least one culture container 12 recorded by the monitoring device 30 through a convolutional neural network (CNN) (as shown in Figure 1), when the culture container 12 After the microalgae grow for a period of time, the Convolutional Neural Network (CNN) is used to identify the microalgae concentration 121 of the culture container 12 recorded (as shown in Figure 1), and record the microalgae concentration of the culture container 12 121.

In addition, the next step S130 is to operate the nutrient solution equipment: the control computer system 40 operates the nutrient solution equipment 20 according to the change of the identified microalgae concentration 121 of at least one culture container 12 . After the above step S130 is completed, the next step S140 is performed.

In addition, the next step S140 is to output the set nutrient solution: to enable the nutrient solution device 20 to output the set nutrient solution into the culture container 12 .

And above-mentioned step S130 and step S140 when the microalgae concentration 121 of this culture container 12 and setting target value appear difference (as shown in Fig. 2), then by this control computer system 40 according to the identified The variation of microalgae concentration 121 is operated this nutrient solution equipment 20, allows this nutrient solution equipment 20 to output the nutrient solution of setting in this culture container 12 (as shown in Fig. 2), makes the microalgae in this culture container 12 Has growth-accelerating or growth-reducing benefits.

In addition, the control computer system 40 contains a machine learning (machine learning) program (not shown), when the convolutional neural network (CNN) recognizes the image 32 of the culture container 12 recorded by the monitoring device 30 into micro After the concentration of algae is 121, each identification is integrated into the concentration of microalgae 121 and the data is analyzed, and the microalgae cultivation model is established through the machine learning program, and the feedback control is formed by the microalgae cultivation model System structure to achieve the effectiveness of building a smart microalgae cultivation system, thereby increasing the overall constructability.

From the above detailed description, those who are familiar with this art can understand that the present invention can indeed achieve the aforementioned purpose, and have actually met the provisions of the Patent Law, so they should file an application for a patent for invention.

But the above-mentioned ones are only preferred embodiments of the present invention, and should not limit the scope of the present invention; therefore, all simple equivalent changes and modifications made according to the patent scope of the present invention and the contents of the description of the invention , should still fall within the scope covered by the patent of the present invention.

10:Microalgae farm

11: Scaffolding

12: Culture container

121: microalgae concentration

30: Monitoring equipment

31: Lens

32: Image

40:Control computer system

Claims (8)

An intelligent microalgae culture system includes: a microalgae farm, the microalgae farm is equipped with at least one culture container, the culture container is filled with culture fluid and microalgae, the microalgae farm At least one culture container is equipped with at least one position sensor, the position sensor is installed at the culture container; a nutrient solution equipment, the nutrient solution equipment is set in the microalgae farm, the nutrient solution The device is connected to the at least one culture container; at least one monitoring device is installed in the microalgae farm, and the monitoring device records the image of at least one culture container through a lens; and a control computer system, The control computer system is respectively connected with the monitoring equipment and the nutrient solution equipment, and the control computer system is equipped with a convolutional neural network (CNN), so as to control the monitoring equipment through the convolutional neural network (CNN). Recognizing the recorded image of at least one culture container, and identifying the concentration of microalgae in at least one culture container, and then the control computer system operates the nutrient solution equipment according to the changes in the concentration of microalgae in the identified at least one culture container, Allow the nutrient solution device to output the set nutrient solution into the culture container. The intelligent microalgae cultivation system as described in item 1 of the scope of the patent application, wherein the convolutional neural network (CNN) is further a two-dimensional convolutional neural network for imaging through the two-dimensional convolutional neural network identify. The intelligent microalgae cultivation system described in item 1 of the scope of the patent application, wherein the position sensor is further connected with the control computer system. The intelligent microalgae cultivation system as described in item 1 of the scope of patent application, wherein the control computer system further contains a machine learning (machine learning) program, and the convolutional neural network Road (CNN) recognizes the image of at least one culture container captured by the monitoring equipment as the concentration of microalgae and conducts data analysis to establish a microalgae cultivation model. An intelligent microalgae cultivation method is mainly used for microalgae cultivation, which includes a microalgae farm, a nutrient solution device, at least one monitoring device and a control computer system. The microalgae farm is equipped with at least one The culture container, the nutrient solution equipment is installed in the microalgae farm, the monitoring equipment is installed in the microalgae farm, the control computer system is respectively connected with the monitoring equipment and the nutrient solution equipment, the control computer system It is equipped with a convolutional neural network (CNN), and the main steps of the cultivation method include: putting culture solution and microalgae: putting culture solution and For microalgae cultivation, at least one culture container of the microalgae farm is equipped with at least one position sensor, and the position sensor is installed at the culture container; the image of the culture container is recorded: At least one culture container is monitored through the monitoring equipment installed in the microalgae farm, and the image of at least one culture container is recorded through the lens of the monitoring equipment; the image identifies the concentration of microalgae: the control computer system is through the volume The integrated neural network (CNN) recognizes the image of at least one culture container captured by the monitoring equipment, and recognizes the concentration of microalgae in at least one culture container; operates the nutrient solution equipment: the control computer system is based on the identified at least one culture container Operate the nutrient solution equipment based on changes in the concentration of microalgae; and output a set nutrient solution: allowing the nutrient solution equipment to output a set nutrient solution into the culture container. The intelligent microalgae cultivation method described in item 5 of the scope of the patent application, wherein the convolutional neural network The CNN (CNN) is further a two-dimensional convolutional neural network for image recognition through the two-dimensional convolutional neural network. The intelligent microalgae cultivation method described in item 5 of the scope of the patent application, wherein the position sensor is further connected with the control computer system. The intelligent microalgae breeding method described in item 5 of the scope of the patent application, wherein the control computer system further includes a machine learning (machine learning) program, and the convolutional neural network (CNN) is recorded by the monitoring equipment The image of at least one culture container is identified as microalgae concentration for data analysis, so as to establish a microalgae cultivation model.

Images