Intelligent edible mushroom planting system, control method and terminal

Abstract

The invention provides an intelligent edible mushroom planting system, a control method and a terminal, and the system comprises a sensor group module which comprises a plurality of types of sensors and is used for collecting environment parameters of each growth stage of edible mushrooms; the central control module is in communication connection with the sensor group module so as to receive the environmental parameters of the edible mushrooms in each growth stage from each sensor; the central control module is provided with a growth model obtained based on deep learning, and the growth model is used for generating optimal environment parameters of the edible mushrooms in each growth stage; and the environment control module is in communication connection with the central control module and is used for receiving the optimal environment parameters from the central control module so as to adjust the environment parameters of the edible mushrooms in each growth stage in real time. According to the application, the environmental conditions can be automatically adjusted and optimized according to the growth requirements of different types of edible mushrooms in different growth stages.

Description

Technical Field

[0001] The present application relates to the field of modern agricultural technology, and in particular to an intelligent edible fungus cultivation system, a control method and a terminal. Background Art

[0002] With the increase of global population and the rising demand for high-quality and healthy food, edible fungi, as a nutritious agricultural product with multiple health functions, are becoming more and more popular in the market. Traditional edible fungi cultivation warehouses are mostly small-scale and manual operations, with low production efficiency and imprecise environmental control, which makes it difficult to guarantee yield and quality. In addition, traditional cultivation warehouses are highly dependent on the environment and are easily affected by seasonal changes and climatic conditions.

[0003] In order to meet the growing market demand, the factory-based and large-scale cultivation warehouse model of edible fungi has gradually become a trend. Although the existing factory-based cultivation warehouse model has improved the yield and quality to a certain extent, it is difficult to accurately control the growth environment parameters of edible fungi according to the different stages of edible fungi growth, and it is also impossible to adaptively control the growth parameters required by different types of edible fungi.

[0004] Therefore, it is necessary to provide an intelligent edible fungus cultivation system, a control method and a terminal to solve the above-mentioned problems existing in the prior art. Summary of the invention

[0005] In view of the shortcomings of the prior art described above, the purpose of the present application is to provide an intelligent edible fungus cultivation system, control method and terminal, which are used to solve the technical problem that the prior art is difficult to intelligently adjust the required growth environment parameters according to the different stages of edible fungus growth.

[0006] To achieve the above-mentioned and other related purposes, the present application provides, in a first aspect, an intelligent edible fungus cultivation system, comprising: The sensor group module includes various types of sensors for collecting environmental parameters of edible fungi at various growth stages; A central control module is connected to the sensor group module for receiving environmental parameters of the edible fungi at each growth stage from each sensor; the central control module is equipped with a growth model based on deep learning, and the growth model is used to generate optimal environmental parameters of the edible fungi at each growth stage; The environmental control module is in communication with the central control module and is used to receive the optimal environmental parameters from the central control module and adjust the environmental parameters of the edible fungi at various growth stages in real time.

[0007] In some embodiments of the first aspect of the present application, a growth model construction module is also included, which is used to input the environmental parameters of each growth stage of edible fungi collected by various types of sensors into the deep learning model for training, testing and verification, so as to construct the growth model.

[0008] In some embodiments of the first aspect of the present application, the environmental control module includes: a temperature and humidity control unit for controlling the temperature and humidity parameters required for the growth of edible fungi; a light intensity control unit for controlling the light intensity parameters required for the growth of edible fungi; and a carbon dioxide concentration control unit for controlling the carbon dioxide concentration parameters required for the growth of edible fungi.

[0009] In some embodiments of the first aspect of the present application, a data management module is further included, which is connected to the sensor group module and is used to store and analyze the environmental parameters of each growth stage of the edible fungi collected by the sensor group module.

[0010] In some embodiments of the first aspect of the present application, a planting rack module is also included for providing a carrier for cultivating edible fungi. The planting rack module includes a hollow frame, a support frame and a plurality of planting trays. The support frame is arranged in the frame, and the plurality of planting trays are arranged on the support frame in sequence.

[0011] In some embodiments of the first aspect of the present application, a plurality of the planting rack modules are arranged in sequence along the height direction of the frame.

[0012] To achieve the above-mentioned purpose and other related purposes, the second aspect of the present application provides an intelligent edible fungus cultivation control method, which is applied to a central control module; the central control module is located in the above-mentioned intelligent edible fungus cultivation system; the method comprises: Receive environmental parameter data collected at each growth stage of edible fungi from each sensor in the sensor group module; Inputting the environmental parameter data into a deep learning model for training, testing and verification to obtain a growth model; The growth model is used to output the optimal environmental parameters of the edible fungus at each growth stage.

[0013] In some embodiments of the second aspect of the present application, the method also includes: increasing the environmental parameter data of each growth stage of edible fungi through the data increment method; using L1 or L2 regularization to limit the complexity of the deep learning model; during the model training process, stopping the model training when it is monitored that the performance of the validation set no longer improves.

[0014] In some embodiments of the second aspect of the present application, the environmental parameter data of each growth stage of edible fungi are increased by the data increment method, which includes any of the following methods: data enhancement based on interpretation method, noise method or sampling method to increment the environmental parameter data of each growth stage of edible fungi; synthetic data is obtained by using a generative adversarial network or a diffusion model to increment the environmental parameter data of each growth stage of edible fungi; environmental parameters in different environments are collected by installing environmental sensors in different regions and under different climatic conditions to increment the environmental parameter data of each growth stage of edible fungi.

[0015] To achieve the above-mentioned purpose and other related purposes, the third aspect of the present application provides an electronic terminal, including a memory, a processor and a computer program stored in the memory; the processor executes the computer program to implement the method.

[0016] As described above, the intelligent edible fungus cultivation system, control method and terminal of the present application have the following beneficial effects: Environmental parameters of edible fungi at different growth stages are collected through various types of sensors, and these environmental parameters are communicated to the central control module. The central control module deployed with a growth model outputs the optimal environmental parameters of edible fungi at different growth stages. The environmental control module adjusts the environmental parameters of edible fungi at different growth stages in real time according to the optimal environmental parameters. It can automatically adjust and optimize environmental conditions according to the growth requirements of different types of edible fungi at different growth stages, so as to achieve efficient and high-quality production of edible fungi. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 Shown is a schematic diagram of an intelligent edible fungus cultivation system in one embodiment of the present application.

[0018] Figure 2 Shown is a working schematic diagram of the environment and equipment monitoring module in one embodiment of the present application.

[0019] Figure 3 Shown is a schematic diagram of a data management module and a remote monitoring system in one embodiment of the present application.

[0020] Figure 4 Shown is a schematic diagram of a planting rack module in one embodiment of the present application.

[0021] Figure 5 Shown is a schematic diagram of a multi-layer planting rack module in one embodiment of the present application.

[0022] Figure 6 Shown is a schematic diagram of the process of automated logistics in one embodiment of the present application.

[0023] Figure 7Shown is a schematic diagram of the process of water and gas treatment in one embodiment of the present application.

[0024] Figure 8 Shown is a flow chart of an intelligent edible fungus cultivation control method in one embodiment of the present application.

[0025] Fig. 9 Shown is a schematic diagram of the structure of an electronic terminal in one embodiment of the present application. DETAILED DESCRIPTION

[0026] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0027] In the embodiments of the present application, words such as "first" and "second" are used to distinguish the same or similar items with substantially the same functions and effects. For example, the first XX and the second XX are only used to distinguish different XXs, and do not limit their order. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0028] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" represent examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0029] In the embodiments of the present application, "at least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc or abc, where a, b, c can be single or multiple.

[0030] Before further describing the present invention in detail, the nouns and terms involved in the embodiments of the present invention are explained. The nouns and terms involved in the embodiments of the present invention are applicable to the following interpretations: <1> L1 regularization: Regularization is achieved by adding the L1 norm of the weights (i.e., the sum of the absolute values ​​of the weight vector) to the loss function of the model. L1 regularization tends to produce a sparse weight matrix, that is, pushing some weights to zero, thereby achieving the effect of feature selection.

[0031] <2> L2 regularization: Regularization is achieved by adding the L2 norm of the weights (i.e., the sum of the squares of the weight vector) to the model's loss function. L2 regularization will make the weight values ​​smaller, which can effectively control the complexity of the model, reduce the variance of the model parameters, and thus improve the stability of the model.

[0032] To facilitate understanding of the embodiments of the present application, first Figure 1 Detailed description. Figure 1 An intelligent edible fungus cultivation system in an embodiment of the present invention is shown, comprising: The sensor group module 1 includes multiple types of sensors for collecting environmental parameters of edible fungi at various growth stages. The central control module 2 is connected in communication with the sensor group module 1 to receive environmental parameters of the edible fungi at various growth stages from various sensors. The central control module 2 is deployed with a growth model based on deep learning, and the growth model is used to generate optimal environmental parameters of the edible fungi at various growth stages. The environmental control module 3 is connected in communication with the central control module 2 to receive the optimal environmental parameters from the central control module 2, and to adjust the environmental parameters of the edible fungi at various growth stages in real time.

[0033] In the cultivation of edible fungi, different types of edible fungi have different requirements for the cultivation environment at different growth stages. The intelligent edible fungi cultivation system provided by the present application collects environmental parameters of different growth stages of various types of edible fungi through various types of sensors of the sensor group module 1; transmits the collected environmental parameters to the central control module 2 deployed with the growth model, and generates the optimal environmental parameters of the edible fungi at each growth stage through processing and analysis of the growth model; the environmental control module 3 adjusts the environmental parameters of the edible fungi at each growth stage in real time according to the received optimal environmental parameters, thereby achieving efficient production and quality assurance of edible fungi.

[0034] It should be understood that the optimal environmental parameters are one or more sets of environmental parameters corresponding to good growth conditions of edible fungi at different growth stages.

[0035] In some embodiments of the present application, the intelligent edible fungus cultivation system also includes a growth model construction module 21, which is used to input the environmental parameters of each growth stage of edible fungi collected by various types of sensors into the deep learning model for training, testing and verification, so as to construct the growth model.

[0036] In some specific embodiments, the multiple types of sensors include a temperature and humidity sensor 11, a light intensity sensor 12, and a carbon dioxide concentration sensor 13. The temperature and humidity sensor 11 is used to collect temperature and humidity data when the edible fungi grow. The light intensity sensor 12 is used to collect light intensity data when the edible fungi grow. The carbon dioxide concentration sensor 13 is used to collect carbon dioxide concentration data when the edible fungi grow.

[0037] In some specific embodiments, the deep learning model of the embodiment of the present application uses a back propagation neural network model. It should be understood that the back propagation neural network (BP) model is a multi-layer feedforward neural network that is trained by error back propagation. It consists of an input layer, a hidden layer (one or more) and an output layer, wherein the number of neurons in the hidden layer can be set as needed. The training process of the BP neural network includes two stages: forward propagation and back propagation. In the forward propagation stage, the input data is passed from the input layer, and after the weighted summation of each layer and the activation function processing, it is passed to the output layer to form the output. If there is an error between the output and the expected result, it is necessary to enter the back propagation stage. Back propagation is an optimization process whose purpose is to adjust the weights and bias parameters in the network to reduce the error between the output and the expected result. In this process, the error will propagate forward layer by layer from the output layer, and the weight of each layer will be adjusted according to the error. The adjustment of the weight depends on the gradient descent method, that is, the weight is adjusted in the opposite direction of the gradient of the loss function in order to achieve the minimum value of the loss function. For ease of description, the back propagation neural network model is simplified to the BP model below.

[0038] After preprocessing the temperature and humidity data, light intensity data and carbon dioxide concentration data collected by the temperature and humidity sensor 11, the light intensity sensor 12 and the carbon dioxide concentration sensor 13, the preprocessed data is input into the BP model for training, and the model parameters are optimized through multiple iterations. Use independent test sets and validation sets to test and verify the model. The test and validation here refer to the prior art and will not be repeated here. The trained growth model is deployed to the central control module 2, and the growth model is used to generate the optimal environmental parameters for each growth stage of the edible fungi. The environmental control module 3 adjusts the temperature, humidity, light, etc. in real time according to the optimal environmental parameters, thereby providing the best growth environment for the edible fungi.

[0039] Since the control of environmental parameters in current production is derived from historical experience and is not supported by a single growth model, for example, some temperatures are in a range, and the exact point is a non-standard parameter affected by various factors. The introduction of autonomous learning can process data in batches, narrow the range points and establish a large growth model. Therefore, the growth model constructed by the growth model construction module 21 of the embodiment of the present application can continuously optimize the environmental control strategy and production process based on historical data and real-time feedback data, that is, by analyzing the production data of different batches, it can summarize the best environmental control parameters and planting strategies to improve the yield and quality of edible fungi.

[0040] In some embodiments of the present application, the intelligent edible fungus cultivation system further includes a generative adversarial network module 22, which is connected to the growth model construction module 21 and is used to generate unconventional growth parameter data in the growth stage of the edible fungus, and these unconventional growth parameter data are used as part of the training set of the growth model construction module 21. The unconventional data generated in this embodiment can enable the trained growth model to better simulate the real growth process of the edible fungus.

[0041] It is worth noting that during the growth of edible fungi, relatively rare and unconventional growth parameter data will appear. Due to its rarity and unconventionality, it is difficult to collect data. These unconventional growth parameter data include but are not limited to: (1) Abnormal temperature tolerance data refers to the fact that edible fungi can still grow outside their suitable growth temperature range due to genetic variation or changes in environmental adaptability; (2) Atypical growth rate data refers to the fact that edible fungi have a growth rate far higher or lower than the normal level due to pathogen infection, excessive or insufficient nutrition, etc.; (3) Morphological variation data refers to the fact that edible fungi have abnormal morphological characteristics (such as cap shape, stipe length, etc.) due to genetic factors, environmental pressure or the influence of chemical substances; (4) Color change data refers to the fact that the color of edible fungi is significantly different from that under normal growth conditions due to lighting conditions, nutrient deficiency or certain metabolic disorders; (5) Mycelium abnormality data refers to the fact that edible fungi have uneven mycelium growth, abnormal branching or mycelium due to unsuitable environmental conditions or infection. The body structure is loose; (6) Data on fruiting body dysplasia refers to the incomplete or deformed development of the fruiting body (the visible part of the edible fungus) due to environmental stress or genetic factors; (7) Data on early or late maturity refers to the significant advancement or delay of the maturity period of edible fungi due to environmental conditions (such as temperature, humidity, etc.); (8) Data on abnormal disease resistance refers to the abnormal disease resistance of edible fungi due to genetic improvement, environmental adaptation or changes in pathogens; (9) Data on abnormal nutrient absorption refers to the abnormal absorption and utilization of nutrients by edible fungi due to changes in culture medium components or changes in the metabolic characteristics of the strain; (10) Data on abnormal metabolism refers to the abnormal metabolites (such as enzymes, pigments, flavor compounds) of edible fungi due to changes in metabolic pathways or the influence of environmental factors.

[0042] Specifically, the process of using generative adversarial networks (GANs) to generate unconventional growth parameter data in the growth stage of edible fungi includes the following: Step A: Based on experimental data, literature data or historical record data, collect and generate unconventional growth parameter data in the growth stage of edible fungi; and collect conventional growth parameter data of edible fungi under normal growth conditions; annotate the collected data to distinguish between conventional growth parameters and unconventional growth parameters; and preprocess the collected data.

[0043] It should be understood that there are many ways to preprocess data, such as data cleaning (removing noise and outliers), data standardization to make it suitable for input into the generative adversarial network, and dividing the data into training sets, validation sets, and test sets.

[0044] Step B: inputting the preprocessed data into a generative adversarial network model for training; the generative adversarial network model includes a generator and a discriminator, the generator is used to generate unconventional growth parameter data, and the discriminator is used to distinguish between real data and generated data.

[0045] Specifically, the discriminator is trained using the training set data so that it can identify real data. The generator is trained using the training set data so that the data it generates can deceive the discriminator. The generator and the discriminator are trained alternately until the data generated by the generator is real enough and the discriminator cannot effectively distinguish them. In addition, model training also includes the process of model optimization, which includes: adjusting model parameters and structures, such as learning rate, batch size, etc., to improve the quality of generated data; using validation set data to evaluate model performance and ensure that the generated data is similar to the distribution of real data.

[0046] Step C: Use the trained generative adversarial network to generate unconventional growth parameter data as part of the training set for the growth model.

[0047] Specifically, the quality and authenticity of the generated data are verified using the test set data to ensure that the generated data is statistically similar to the real unconventional growth parameter data. In addition, based on the feedback from the application results, the generative adversarial network model is further adjusted and optimized; and new unconventional growth parameter data is continuously collected and the training set is updated to improve the generalization ability of the model.

[0048] In some embodiments of the present application, the environmental control module 3 includes: a temperature and humidity control unit 31, a light intensity control unit 32 and a carbon dioxide concentration control unit 33, which can automatically adjust and optimize environmental conditions according to the growth requirements of different edible fungi. The temperature and humidity control unit 31 is used to control the temperature and humidity parameters required for the growth of edible fungi. The light intensity control unit 32 is used to control the light intensity parameters required for the growth of edible fungi. The carbon dioxide concentration control unit 33 is used to control the carbon dioxide concentration parameters required for the growth of edible fungi. The environmental control module 3 can add or replace specific functional modules as needed, such as UV light disinfection, CO2 compensation system, etc., to meet special planting needs.

[0049] It should be noted that the environment control module 3 also includes other environment parameter control units required by edible fungi, which will not be described one by one here.

[0050] In some specific embodiments, Figure 2As shown in the figure, the intelligent edible fungus cultivation system is also equipped with an environment and equipment monitoring module. Environmental monitoring includes temperature and humidity monitoring, water leakage monitoring, water level monitoring, noise monitoring, sulfur hexafluoride (SF6) gas monitoring, harmful gas monitoring, switch cabinet temperature monitoring, and wireless cable temperature monitoring. By monitoring these data, if an abnormality is detected, the environmental control module 3 controls the working status of lighting, air conditioning, dehumidifier, drainage pump, fresh air fan, fan, heater, and mouse repellent to keep the growth environment of edible fungi in a suitable state in real time and ensure safety. Equipment status monitoring includes transformer overtemperature monitoring, switch cabinet contact temperature measurement, switch cabinet local monitoring, low-voltage feeder monitoring, and battery monitoring. By monitoring the status of the equipment, the operating status of the equipment can be monitored in real time to ensure the safe operation of the equipment. In addition, security and fire monitoring are also configured, including perimeter shooting, smoke detection, intrusion alarm, open fire detection, sound and light alarm, fire monitoring, smart access control, and video monitoring to ensure the safety of the system. At the same time, AI intelligent inspection is also configured to ensure the safety of the environment for the growth of edible fungi.

[0051] In some embodiments of the present application, the intelligent edible fungus cultivation system further includes a data management module 4. The data management module 4 is connected to the sensor group module 1, and is used to store and analyze the environmental parameters of each growth stage of the edible fungus collected by the sensor group module 1. The data management module 4 records, analyzes and optimizes various data in the cultivation process through data collection and analysis, and provides data support for the adjustment of the cultivation strategy.

[0052] In some embodiments of the present application, the intelligent edible fungus cultivation system further includes a communication module 6. The communication module 6 connects the intelligent edible fungus cultivation system and the external management system, that is, the communication module 6 communicates with the cloud server, and the cloud server communicates with the client, supports remote monitoring and operation, and realizes intelligent management of the entire process.

[0053] In some specific embodiments, Figure 3As shown, the data management module 4 and the monitoring system are used for real-time data processing and monitoring. The data of each sensor and control device are uploaded to the cloud in real time through the communication module. The manager can check the operating status in the planting warehouse at any time through the remote monitoring system, and perform remote operations and adjustments as needed. Specifically, the real-time data collected by each sensor is pre-processed, and then transmitted to the time window module after pre-processing, which is used to process time-related data. After processing, it is transmitted to the rule executor through the scene routing, executes the rules defined by the rule engine, outputs event processing, and forwards it to the external management system through an external forwarder or triggers certain tasks or events through the timing contact module; at the same time, the monitoring system is used to monitor the data, and if it is abnormal, the alarm module is triggered. In addition, other modules are also provided, which will not be repeated here. Through the above design, a large amount of real-time data can be processed, complex event processing logic can be supported, and it can be integrated with third-party services. Through real-time monitoring and rule configuration, it can respond quickly to various events, record and process the environmental parameters of edible fungi, and continuously optimize planting strategies.

[0054] In some embodiments of the present application, Figure 4 As shown, the intelligent edible fungus planting system also includes a planting rack module 5, which is used to provide an edible fungus cultivation carrier. The planting rack module 5 is arranged in the planting warehouse. Exemplarily, the planting rack module 5 can be designed to be mobile, so that the planting rack module 5 has both mobility and modularity, which is convenient for adaptive adjustment according to production needs. The planting rack module 5 includes a hollow frame 51, a support frame 52 and a plurality of planting trays 53. The support frame 52 is arranged in the frame 51, and the plurality of planting trays 53 are arranged on the support frame 52 in sequence. The planting trays 53 are used to cultivate edible fungi, and the specific number of the planting trays 53 can be specifically designed according to actual conditions.

[0055] In some embodiments of the present application, Figure 5 As shown, the plurality of planting rack modules 5 are sequentially arranged along the height direction of the frame 51. By stacking the multi-layer planting rack modules 5 in the vertical direction, the vertical space can be efficiently utilized to achieve high-density planting. For example, six layers of planting rack modules 5 are stacked in the height direction of the frame 51. It should be noted that the height direction of the frame 51 is Figure 5 Above and below heights shown.

[0056] In some embodiments of the present application, the intelligent edible fungus cultivation system also includes an automated logistics module. For example, an automated guided vehicle (AGV), conveyor belt and other logistics systems are installed inside the cultivation warehouse, which are responsible for the transportation, sorting and unloading of the cultivation trays. The transportation route and time of the trays can be dynamically adjusted according to the production plan and actual conditions, and the waiting time and unnecessary movement of the cultivation trays can be minimized by optimizing the logistics scheduling, which greatly improves the production efficiency and reduces the manual operation. For example, the process of automated logistics and warehousing is as follows: Figure 6 As shown in the figure, the information management system is the core of the whole process, including the logistics management information system, warehouse management system, warehouse control system and sorting system. Among them, the order and production information of the enterprise resource planning system or production management system are sent to the logistics management information system; the logistics management information system is responsible for decomposing and integrating logistics information, and then sending it to the warehouse management system, and can also feedback logistics information; the warehouse management system transmits the in-and-out information to the warehouse control system, and transmits the sorting information to the sorting system. The warehouse control system transmits the in-and-out information and the sorting system transmits the sorting information to the electrical control system, thereby controlling the warehouse equipment, handling and transportation equipment, and sorting and picking equipment in the logistics equipment to perform cargo storage, handling and sorting tasks for various materials, and realize the transportation of various materials to the production line or in-and-out of the warehouse. Thus, the logistics and warehousing processes with automation and informatization are realized.

[0057] In some embodiments of the present application, the intelligent edible mushroom cultivation system also includes a resource recovery module. The resource recovery module integrates a water resource circulation system and a waste treatment system, and can realize the recycling of water resources and the resource treatment of waste mushroom residues, thereby reducing environmental impact. For example, the process of water and gas resource treatment is as follows: Figure 7 As shown, the gases generated during the production process, such as NH3, are collected by an air suction hood, and transported to a primary spray tower through an air intake pipe, where water is used to spray the waste gas to settle the water-soluble components; the remaining gas is transported to a secondary spray tower through an air intake pipe, where water is sprayed on the waste gas to settle the water-soluble components; the remaining gas is then transported to a demister through an air intake pipe, where a demister is used to remove the mist; finally, the remaining gas is discharged through a chimney, and the gas treatment process is completed. The water generated in each process can be treated by a water circulation system, and the reflux pipe is used to transport the water. The water containing NH3 enters the soaking pool for secondary use, thereby ensuring that there is no external discharge of the water part. An independent pipe network is used to treat rainwater and enter the municipal rainwater pipe network.

[0058] In some embodiments of the present application, the intelligent edible fungus cultivation system also includes an energy management module. The energy management module is responsible for monitoring and optimizing the energy consumption in the cultivation warehouse, and is equipped with renewable energy devices such as solar energy to improve energy utilization efficiency and reduce production costs. For example, solar photovoltaics are laid on the roof of the cultivation warehouse and energy storage facilities are configured to store excess energy during off-peak hours for use during peak hours.

[0059] The intelligent edible fungus cultivation system provided by the present application adopts a modular design, and can flexibly adjust the configuration of each functional module according to the growth requirements of different edible fungus varieties at different growth stages. It has strong adaptability and is easy to maintain and upgrade. The following will provide specific examples of the configuration of each functional module for the adaptability of different types of edible fungi.

[0060] Example 1: Intelligent edible mushroom cultivation system for Agaricus bisporus.

[0061] Agaricus bisporus is one of the edible mushroom varieties with the largest market demand. In order to meet its large-scale production needs, a multi-layer planting rack module is used. The environmental control module can accurately adjust parameters such as temperature, humidity, light, and CO2 concentration to meet the needs of different growth stages of Agaricus bisporus. The central control module monitors various environmental data in real time through the data management module, and dynamically adjusts the planting environment according to the growth curve of Agaricus bisporus. The automated logistics module is responsible for automatically transporting the picked Agaricus bisporus pallets to the warehouse for preliminary processing and packaging. For example, the environmental parameters of each growth stage of Agaricus bisporus are as follows: (1) Mycelium growth stage: the temperature is controlled at 22-24°C; the humidity of the substrate is maintained at about 65%, and the relative humidity of the air is maintained at about 65%; no light is required at this stage and it can be carried out under dark conditions; the carbon dioxide concentration has little effect on mycelium growth and can be maintained at normal atmospheric levels; (2) Primordial formation stage: the temperature is maintained at 15-18°C; the air humidity is controlled at about 90%; the light intensity is controlled at 500-1000 lux; the carbon dioxide concentration is controlled at 0.1%-0.5%; (3) Fruiting body growth stage: the temperature is controlled at 15-16°C; the relative humidity of the air should be maintained at 90%-95% to maintain the moisture of the fruiting body; the light intensity is 2000-3000 lux to promote the formation of the cap and the synthesis of pigments; the CO2 concentration should be controlled at 0.1%-0.3% to ensure the normal development of the fruiting body.

[0062] Example 2: Intelligent edible fungus cultivation system for Ganoderma lucidum.

[0063] As a precious medicinal fungus, Ganoderma lucidum has more stringent production requirements. The system uses a closed high-rise planting rack module and a highly accurate environmental control module, which can finely control the temperature, humidity, light intensity, CO2 concentration, etc. in the planting environment, and is equipped with a spectrometer to detect the growth status and active ingredient content of Ganoderma lucidum. The automated logistics module ensures that the planting, picking and transportation processes of Ganoderma lucidum are fully automated to avoid contamination and damage caused by human factors. For example, the environmental parameters of Ganoderma lucidum at each stage are as follows: (1) Mycelium growth stage: temperature is controlled between 24℃ and 28℃; relative air humidity should be maintained at 70% to 80%; CO2 concentration is controlled at 0.03% to 0.05%; (2) Fruiting body stage: temperature is controlled between 20℃ and 25℃; relative air humidity needs to be increased to 85% to 95%; light intensity is between 500 and 1000 lux; CO2 concentration is appropriately increased, but usually not more than 0.1%.

[0064] Example 3: Intelligent edible mushroom cultivation system for Agaricus blazei.

[0065] Agaricus blazei is an edible fungus with high economic value, and its production has strict environmental requirements. The system uses a special air filtration system and humidity control unit to ensure the purity of the planting environment and precise control of humidity. The planting rack module in the planting warehouse can adjust the position and height of the tray according to the growth cycle of Agaricus blazei, ensuring that each layer of Agaricus blazei can obtain the best growth conditions. After picking, the logistics system will automatically transport the tray to the primary processing area to reduce manual contact and maintain the quality of Agaricus blazei. For example, the environmental parameters of each stage of Agaricus blazei are as follows: (1) Mycelium growth stage: the temperature is controlled at 22°C to 25°C; the humidity of the culture medium should be maintained at about 65%, and the relative humidity of the air should be maintained at 70%-80%; no light is required at this stage and it can be carried out under dark conditions; the CO2 concentration should be controlled at 0.03% to 0.05%; (2) Fruiting body stage: the temperature is controlled at 18°C ​​to 22°C; the relative humidity of the air needs to be increased to 85% to 95%; the light intensity ranges from 500 to 1000 lux; the CO2 concentration should be maintained at 0.05% to 0.1%, and ventilation should be increased.

[0066] Example 4: Intelligent edible fungus cultivation system for shiitake mushrooms.

[0067] The cultivation of shiitake mushrooms requires specific temperature, humidity and light conditions. The system adopts a multi-layer planting rack module design, which can achieve high-density planting in a limited space. The environmental control module automatically adjusts the planting environment by real-time monitoring of temperature, humidity and light intensity to ensure the optimal growth state of shiitake mushrooms. The data management module records and analyzes the production data of each batch to help managers optimize production plans and increase yields. For example, the environmental parameters of shiitake mushrooms at each stage are as follows: (1) Mycelium growth stage: temperature is controlled at 22℃ to 25℃; relative air humidity is maintained at 70% to 80%; no light is required at this stage and it can be carried out under dark conditions; CO2 concentration should be controlled at 0.03% to 0.05%; (2) Fruiting body stage: temperature is controlled at 12℃ to 18℃; relative air humidity should be maintained at 85% to 95%; light intensity is controlled at 2000 to 3000 lux; CO2 concentration should be maintained at 0.05% to 0.1%, and ventilation should be strengthened.

[0068] The present application also provides an intelligent edible fungus cultivation control method, the method flow chart is as follows Figure 8 As shown, the method is applied to a central control module; the central control module is located in the intelligent edible fungus cultivation system as described above; the method comprises: Step S81: receiving environmental parameter data collected at each growth stage of edible fungi from each sensor in the sensor group module; Step S82: inputting the environmental parameter data into a deep learning model for training, testing and verification to obtain a growth model; Step S83: Use the growth model to output the optimal environmental parameters of the edible fungus at each growth stage.

[0069] It should be noted that the intelligent edible fungus cultivation control method of this embodiment can realize the functions of the above-mentioned intelligent edible fungus cultivation system, which will not be described in detail here.

[0070] In some embodiments of the present application, the method also includes: increasing the environmental parameter data of each growth stage of edible fungi through the data increment method; using L1 or L2 regularization to limit the complexity of the deep learning model; during the model training process, stopping the model training when it is monitored that the performance of the validation set is no longer improved.

[0071] Since the growth process of crops and industrial application fields are different, the growth data of edible fungi is highly complex and variable, and there is a problem of insufficient data. Therefore, when the machine learning model is applied to the field of edible fungi growth, the model learns the noise and details in the data on the training data, but fails to capture the general rules of the data, and the model will be overfitted and underfitted. Therefore, in order to overcome the phenomenon of model overfitting and underfitting, this embodiment uses the data increment method to increase the amount of data for model training to reduce the model's sensitivity to noise in the training data; uses L1 or L2 regularization (see the above explanation of terms) to limit the complexity of the model to prevent the model from overfitting on the training data, thereby improving the generalization ability of the model; and uses an early stopping strategy to stop training in time when the model is no longer improved, to prevent overfitting.

[0072] In some embodiments of the present application, the environmental parameter data of each growth stage of edible fungi are increased by the data increment method, which includes any of the following methods: data enhancement based on interpretation method, noise method or sampling method to increase the environmental parameter data of each growth stage of edible fungi; synthetic data is obtained by using a generative adversarial network or a diffusion model to increase the environmental parameter data of each growth stage of edible fungi; environmental parameters in different environments are collected by installing environmental sensors in different regions and under different climatic conditions to increase the environmental parameter data of each growth stage of edible fungi.

[0073] It should be understood that the interpretation method refers to generating interpretations of original data as enhanced data, such as replacing synonyms with environmental parameter data during the growth of edible fungi to generate new data points; the noise method refers to adding noise to original data while ensuring the effectiveness of the results to improve the robustness of the model. For example, some random noise can be added to the environmental parameter data for the growth of edible fungi to simulate the impact of environmental changes; the sampling method refers to using sampling data as enhanced data based on the distribution of original data. For example, in the growth of edible fungi, new growth cycle data are generated through statistical methods based on existing growth cycle data.

[0074] It should also be understood that the generative adversarial network (GAN) consists of a generator and a discriminator. The generator is responsible for generating data, and the discriminator is responsible for distinguishing between the generated data and the real data. During the training process, the generator and the discriminator compete with each other. The generator tries to generate more and more realistic data, while the discriminator tries to distinguish between true and false data more accurately. In this way, synthetic data with a distribution similar to that of real data can be generated for the environmental parameter data of the incremental edible fungus growth stage; the diffusion model generates data by gradually adding noise to the data and then learning how to reverse this process. It can be used to generate synthetic edible fungus growth environmental parameter data.

[0075] Fig. 9is a schematic block diagram of an electronic terminal provided in an embodiment of the present application. Fig. 9 As shown, the electronic terminal 900 includes: at least one processor 901, a memory 902, at least one network interface 903 and a user interface 905. The various components in the electronic terminal 900 are coupled together through a bus system 904. It can be understood that the bus system 904 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 904 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 904 is not used in the following description. Fig. 9 In the specification, various buses are labeled as bus systems.

[0076] The user interface 905 may include a display, a keyboard, a mouse, a trackball, a click gun, keys, buttons, a touch pad or a touch screen.

[0077] It is understood that the memory 902 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM). The memory described in the embodiments of the present invention is intended to include but is not limited to these and any other suitable categories of memory.

[0078] The memory 902 in the embodiment of the present invention is used to store various categories of data to support the operation of the electronic terminal 900. Examples of these data include: any executable program for operating on the electronic terminal 900, such as an operating system 9021 and an application 9022; the operating system 9021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application 9022 can include various applications, such as a media player (Media Player), a browser (Browser), etc., for implementing various application services. The XX method provided by the embodiment of the present invention can be included in the application 9022.

[0079] The method disclosed in the above embodiment of the present invention can be applied to the processor 901, or implemented by the processor 901. The processor 901 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 901 or the instruction in the form of software. The above processor 901 may be a general processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 901 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiment of the present invention. The general processor 901 may be a microprocessor or any conventional processor, etc. In combination with the steps of the accessory optimization method provided in the embodiment of the present invention, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0080] In an exemplary embodiment, the electronic terminal 900 may be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD) to execute the aforementioned method.

[0081] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0082] To sum up, the existing factory planting mode mostly adopts a single-layer structure, the density of the planting warehouse is limited, and the space utilization rate is low; and the environmental control system is not intelligent enough, and it is difficult to accurately adjust the temperature, humidity, light, and CO2 concentration parameters according to the different stages of edible fungus growth; at the same time, most of the existing management systems rely on manual operation, and the level of automation is low, making it difficult to achieve refined management. Therefore, the present invention provides an intelligent edible fungus planting system, control method and terminal. When working, the production plan is set by the central control module, and key factors such as the planting cycle and environmental parameters are determined as the optimal growth parameter output of the edible fungi. The environmental control module automatically adjusts the environmental conditions such as temperature, humidity, light, and CO2 concentration according to the set growth stage to meet the growth needs of the edible fungi; at the same time, during the planting process, the planting rack module stacks and moves the planting trays in a preset arrangement to maximize the use of space; the automated logistics module is responsible for the transportation, Positioning and management to ensure the efficient operation of the entire production process; the resource recovery module is responsible for processing the wastewater and fungus residue generated during the production process, recycling water resources and treating waste; and in the whole process, the communication module uploads the collected environmental data and production data to the data management module for storage and analysis, and the management personnel can monitor the production status and adjust the production parameters in real time through the remote terminal; the energy management module optimizes energy distribution according to the actual power consumption to ensure the stable operation of the system, that is, this application adopts a multi-layer architecture and modular design, combined with advanced environmental control technology and automated management system, with the characteristics of automated environmental control, intelligent production process, and efficient resource utilization. It can plant various edible fungi with high density and high efficiency under large-scale production conditions, and can monitor and adjust internal environmental parameters in real time, optimize production processes, reduce energy consumption, and improve resource utilization, thereby realizing large-scale, standardized, and high-quality production of edible fungi. Therefore, this application effectively overcomes the various shortcomings in the prior art and has a high industrial utilization value.

[0083] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. An intelligent edible fungus cultivation system, characterized in that: include: The sensor group module includes various types of sensors for collecting environmental parameters of edible fungi at various growth stages; The growth model building module is used to input the environmental parameters of edible fungi at various growth stages collected by various types of sensors into the deep learning model for training, testing and verification, so as to build a growth model; increase the environmental parameter data of edible fungi at various growth stages by the data increment method; use L1 or L2 regularization to limit the complexity of the deep learning model; during the model training process, stop the model training when the performance of the verification set is no longer improved; A generative adversarial network module is connected to the growth model building module and is used to generate unconventional growth parameter data in the growth stage of edible fungi; the unconventional growth parameter data in the growth stage of edible fungi include: abnormal temperature tolerance data, atypical growth rate data, morphological variation data, color change data, mycelium abnormality data, fruiting body underdevelopment data, early or late maturity data, disease resistance abnormality data, nutrient absorption abnormality data, and metabolic abnormality data; A central control module is connected to the sensor group module for receiving environmental parameters of the edible fungi at each growth stage from each sensor; the central control module is equipped with a growth model based on deep learning, and the growth model is used to generate optimal environmental parameters of the edible fungi at each growth stage; The environmental control module is in communication with the central control module and is used to receive the optimal environmental parameters from the central control module and adjust the environmental parameters of the edible fungi at various growth stages in real time.

2. The intelligent edible fungus cultivation system according to claim 1 is characterized in that: The environmental control module comprises: A temperature and humidity control unit, used to control the temperature and humidity parameters required for the growth of edible fungi; A light intensity control unit, used to control the light intensity parameters required for the growth of edible fungi; The carbon dioxide concentration control unit is used to control the carbon dioxide concentration parameters required for the growth of edible fungi.

3. The intelligent edible fungus cultivation system according to claim 1 is characterized in that: It also includes a data management module, which is connected to the sensor group module and is used to store and analyze the environmental parameters of each growth stage of the edible fungi collected by the sensor group module.

4. The intelligent edible fungus cultivation system according to claim 1, characterized in that: It also includes a planting frame module for providing a carrier for cultivating edible fungi. The planting frame module includes a hollow frame, a support frame and a plurality of planting trays. The support frame is arranged in the frame, and the plurality of planting trays are arranged on the support frame in sequence.

5. The intelligent edible fungus cultivation system according to claim 4 is characterized in that: The plurality of planting rack modules are arranged in sequence along the height direction of the frame.

6. An intelligent edible fungus cultivation control method, characterized in that: Applied to a central control module; the central control module is located in the intelligent edible fungus cultivation system according to claim 1; the method comprises: Receive environmental parameter data collected at each growth stage of edible fungi from each sensor in the sensor group module; The environmental parameter data is input into the deep learning model for training, testing and verification to obtain a growth model; the environmental parameter data of each growth stage of edible fungi is increased by a data increment method; L1 or L2 regularization is used to limit the complexity of the deep learning model; during the model training process, when the performance of the verification set is monitored to no longer improve, the model training is stopped; The growth model is used to output the optimal environmental parameters of the edible fungus at each growth stage.

7. The intelligent edible fungus cultivation control method according to claim 6 is characterized in that: The method of increasing the environmental parameter data of each growth stage of edible fungi by the data increment method includes any of the following methods: Data enhancement is performed based on interpretation methods, noise methods or sampling methods to increase the environmental parameter data of each growth stage of edible fungi; Generate synthetic data using generative adversarial networks or diffusion models to increase environmental parameter data at each growth stage of edible fungi; Environmental sensors are installed in different regions and under different climatic conditions to collect environmental parameters in different environments, so as to increase the environmental parameter data of edible fungi at each growth stage.

8. An electronic terminal comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the method of claim 6.

Images