Lentinus edodes growth intelligent regulation and control system combined with laser light source

Abstract

The invention discloses an intelligent mushroom growth regulation and control system combined with a laser light source. Belongs to the technical field of agricultural informatization and intelligentization, and particularly relates to the technical field of mushroom growth environment intelligent regulation and control. The system comprises a sensing module, a network module, a platform module and an application module, the sensing module is used for collecting lentinus edodes growth environment data, transmitting the data to the network module, receiving the data of the network module and regulating and controlling the lentinus edodes growth environment; the network module is used for data transmission between the sensing module and the platform module; the platform module is used for storing mushroom growth environment data and data input by the application module, predicting mushroom growth conditions, sending data to the application module and the network module and receiving data of the application module and the network module; and the application module is used for performing page interaction with a user, receiving and transmitting a user control instruction, sending data to the platform module, receiving the data of the platform module, and sending early warning information when the mushroom growth environment data is abnormal.

Description

Technical Field

[0001] The present invention belongs to the field of agricultural informatization and intelligent technology, and specifically relates to the field of intelligent control technology of mushroom growth environment. Background Art

[0002] Mushrooms, a common fungus found in nature, are also important crops used worldwide for both food and medicine. They have garnered widespread attention for their unique flavor, rich nutritional value, and pharmacological effects, including anti-tumor and cholesterol-lowering properties. According to a report by Expert Market Research, the global mushroom market was estimated to be worth approximately US$68.03 billion in 2023 and is projected to grow at a compound annual growth rate of 7.18% between 2024 and 2032.

[0003] Shiitake mushroom growth is extremely sensitive to environmental factors such as temperature, humidity, light, CO2 concentration, and air circulation. Even the slightest fluctuation can lead to a decrease in yield or deterioration in quality. Traditional cultivation management methods rely primarily on manual inspections and adjustments, which are labor-intensive, result in delayed data collection, slow response times, and significant human error, making standardized, scalable, and efficient management difficult to achieve.

[0004] In recent years, some farms have introduced automated equipment to monitor and control the environment, such as installing temperature and humidity sensors, timed fans, and supplementary lighting. However, the following problems still exist: The data collection method is single and lacks integrated sensing capabilities: Existing systems can often only monitor a few environmental parameters and cannot achieve dynamic perception and adjustment of more refined factors such as light intensity, light quality and spectral composition.

[0005] The control methods are extensive and the response mechanism is missing: Light regulation generally relies on LED lights with fixed time or intensity, which cannot be flexibly adjusted according to the needs of fungi at different growth stages and lacks a feedback control mechanism.

[0006] Lack of intelligent analysis and prediction capabilities: Current systems typically use static or preset thresholds for control, and fail to combine big data and AI algorithms to achieve growth trend prediction, abnormal warning, and decision optimization.

[0007] To conduct precise individual growth monitoring and regulation: Existing technologies mostly adjust based on the overall environment, which cannot identify the growth differences of strains in different regions and at different stages, and easily lead to "average" regulation, affecting overall production efficiency.

[0008] New control methods such as lasers have not yet been systematically integrated and applied: existing systems generally do not introduce laser light sources into the growth control of shiitake mushrooms. Studies have shown that red and blue lasers of specific wavelengths have a significant promoting effect on the growth of shiitake mushrooms, but there is still a lack of systematic solutions for their application scenarios, parameter settings and response mechanisms.

[0009] Therefore, there is an urgent need for an intelligent mushroom growth control system that integrates multi-parameter sensing, precise light quality control, and intelligent decision-making feedback, which can fully perceive environmental changes, accurately adjust key factors, improve the growth efficiency and quality of mushrooms, and meet the urgent needs of intelligent and standardized development of modern agriculture. Summary of the Invention

[0010] In order to solve at least one of the above technical problems, the present invention proposes an intelligent mushroom growth control system combined with a laser light source, the system comprising a perception module, a network module, a platform module and an application module; The perception module is used to collect data on the mushroom growth environment, transmit data to the network module and receive data from the network module, and perform mushroom growth environment control; The network module is used for data transmission between the sensing module and the platform module; The platform module is used to store the mushroom growth environment data and the data input by the application module, predict the mushroom growth situation, send data to the application module and the network module, and receive data from the application module and the network module; The application module is used to interact with users on pages, receive and transmit user control instructions, send data to and receive data from the platform module, and issue early warning information when the mushroom growth environment data is abnormal.

[0011] Furthermore, the perception module includes a ventilation device, a laser plant growth adjustment lamp, a high-precision monitoring camera, a humidifying tube, a temperature and humidity CO2 sensor, and a light sensor. The high-precision monitoring camera, temperature and humidity and CO2 sensors, and the light sensor are used to collect shiitake mushroom growth environment data, and the ventilation device, laser plant growth adjustment lamp, and humidifying tube are used to implement shiitake mushroom growth environment regulation.

[0012] Furthermore, the network module uses two communication modes, local network and mobile network, to transmit information.

[0013] Furthermore, in the platform module, the InfluxDB database is used to store the mushroom growth environment data, and the MySQL database is used to store the data input by the application module.

[0014] Furthermore, when the platform module predicts the growth of shiitake mushrooms, it uses the improved YOLOv11 model to detect the shiitake mushroom fruiting body image at time t, obtaining several shiitake mushroom fruiting body detection images at time t. The shiitake mushroom fruiting body images at time [t-1, t-2,…,tN] are processed in the same way, and the shiitake mushroom fruiting body detection images at time [t,t-1, t-2,…,tN] are obtained in sequence, forming a shiitake mushroom fruiting body detection image sequence, where N is manually set. Furthermore, the shiitake mushroom fruiting body detection image sequence is input into the improved ConvLSTM model for growth prediction, and the predicted shiitake mushroom fruiting body image after growth time t+M is output, where M is set manually.

[0015] Furthermore, when the shiitake mushroom fruiting body detection image sequence is input into the improved ConvLSTM model, the images in the sequence are first segmented one by one in the same way to form H groups of shiitake mushroom fruiting body detection image segmentation sequences at the time [t, t-1, t-2,…, tN]. The corresponding shiitake mushroom fruiting body image after the time t+M is predicted from each group of shiitake mushroom fruiting body detection image segmentation sequences at the time [t, t-1, t-2,…, tN]. Then, all the shiitake mushroom fruiting body detection image segmentation sequences at the time [t, t-1, t-2,…, tN] are spliced to obtain the shiitake mushroom fruiting body image after the time t+M. H and the segmentation method are set manually.

[0016] Furthermore, the improved YOLOv11 model is specifically as follows: the C3k2 module in the YOLOv11 baseline network structure is replaced by the C3k2_OREPA module, and the Concat module in the branch where the neck upsampling module is located in the YOLOv11 baseline network structure is replaced by the SDI module.

[0017] Furthermore, the improved ConvLSTM model is specifically as follows: the ConvLSTM model is changed to a dual-branch structure, the original ConvLSTM model is used as the first branch, the second branch is connected in parallel with the first branch, and the data is input into the two branches at the same time; in the second branch, the data passes through 6 Conv3D modules from input to output, and a Transpose layer is added after the last three Conv3D modules. The output of the first branch and the output of the third Conv3D module in the second branch are combined through the attention mechanism and input into the fourth Conv3D module in the second branch, and then pass through the fifth and sixth Conv3D modules in the second branch in sequence before being output.

[0018] Furthermore, a visualization panel is set in the application module to interact with the user. The user queries the mushroom growth environment data and views the predicted mushroom growth situation through the visualization panel, and inputs control instructions through the visualization panel; the mushroom growth environment data threshold is manually set in the application module. When one or more of the mushroom growth environment data input by the platform module exceeds the corresponding threshold, the application module issues a warning message. The system described in this invention has the beneficial effect of incorporating laser light sources into mushroom growth regulation, a technological innovation not previously employed in existing systematic mushroom cultivation technologies. This system establishes an integrated monitoring and control system, from the mushroom cultivation site to the growers, ensuring that environmental information from the mushroom cultivation site is readily transmitted to growers. This system, combined with intelligent technology, enables predictions of mushroom growth, providing crucial information for growers to more precisely control the mushroom growth environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 Schematic diagram of an intelligent mushroom growth control system combined with a laser light source in an embodiment of the present invention; Figure 2 This is a diagram of the OS-YOLO model structure in an embodiment of the present invention; Figure 3 This is a diagram showing the effect of Shiitake mushroom fruiting body detection and growth prediction in an embodiment of the present invention; Figure 4 This is a structural diagram of the improved ConvLSTM model in an embodiment of the present invention; Figure 5 is a curve showing the change of the fruiting body area of shiitake mushrooms over time in an embodiment of the present invention; Figure 6 Schematic diagram of the intelligent control device for mushroom growth in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0021] Example 1 This embodiment provides an intelligent mushroom growth control system combined with a laser light source, and its schematic diagram is shown as follows: Figure 1 As shown, the system includes a perception module, a network module, a platform module and an application module; The perception module is used to collect data on the mushroom growth environment, transmit data to the network module and receive data from the network module, and perform mushroom growth environment control; The network module is used for data transmission between the sensing module and the platform module; The platform module is used to store the mushroom growth environment data and the data input by the application module, predict the mushroom growth situation, send data to the application module and the network module, and receive data from the application module and the network module; The application module is used to interact with users on pages, receive and transmit user control instructions, send data to and receive data from the platform module, and issue early warning information when the mushroom growth environment data is abnormal.

[0022] Example 2 This embodiment further limits Example 1. The perception module is primarily responsible for real-time monitoring of environmental parameters, data collection, and environmental control, and is the core foundation of the intelligent mushroom growth control system. This module integrates multiple high-precision sensors, enabling precise measurement of key environmental factors such as temperature and humidity, light intensity, and CO2 concentration, and enables environmental control via a control terminal.

[0023] The perception module includes a ventilation device 1, a laser plant growth adjustment lamp 2, a high-precision monitoring camera 3, a humidifying tube 4, a temperature, humidity and CO2 sensor 7 and a light sensor 8. The high-precision monitoring camera 3, the temperature, humidity and CO2 sensor 7 and the light sensor 8 are used to collect shiitake mushroom growth environment data, and the ventilation device 1, the laser plant growth adjustment lamp 2 and the humidifying tube 4 are used to execute shiitake mushroom growth environment regulation.

[0024] Regarding hardware, the perception module's data acquisition module utilizes an embedded data acquisition board with multi-channel analog signal acquisition capabilities. It supports RS485, I2C, and SPI interface protocols, enabling compatible access to multiple sensor types. A 32-bit ARM Cortex-M4 processor, clocked at 180MHz, with 1MB of Flash and 256KB of SRAM, ensures real-time and accurate data acquisition. To enhance data acquisition stability, the system utilizes an independent 12-bit A / D converter, achieving sampling accuracies of 0.1°C for temperature, 0.1% for humidity, and 1ppm for CO2 concentration. The entire perception module utilizes a modular design, ensuring sensor scalability and system flexibility.

[0025] The environmental control system uses a Raspberry Pi 4B as the core control panel, responsible for intelligent control of fans, humidifiers, and lighting. The Raspberry Pi 4B is equipped with a quad-core ARM Cortex-A72 processor running at 1.5GHz, with optional 2GB, 4GB, or 8GB of LPDDR4 memory. It supports dual-band Wi-Fi (2.4GHz / 5GHz) and Gigabit Ethernet, and features a rich GPIO interface that allows for direct control of relays, enabling control of fans, humidifiers, and lighting. Detailed specifications for each component in the sensing module are shown in Table 1.

[0026] Table 1:

[0027] In terms of software, the perception module primarily consists of a data acquisition module and an environmental control module. The data acquisition module utilizes an ARM Cortex-M4 processor running FreeRTOS, enabling multi-tasking and improving real-time data acquisition. Sensors connect to the data acquisition board via RS485, I2C, and SPI interfaces, using Modbus RTU for data communication. The system accurately collects environmental factors such as air temperature and humidity, light intensity, and CO2 concentration, and enhances data accuracy through independent 12-bit A / D converters. During data acquisition, the system compensates temperature and humidity data, filters sensor signals, detects anomalies, and utilizes interpolation algorithms to optimize data continuity and stability. The collected environmental data is transmitted via a serial port to a Raspberry Pi 4B, which processes it further and uploads it to a server.

[0028] The environmental control module uses a Raspberry Pi 4B as the core control device, running Raspberry Pi OS and using Python to program the control program, enabling intelligent control of fans, humidifiers, and lights. The Raspberry Pi uses GPIO interfaces to control relays, turning devices on and off. Combined with server-side control commands, it dynamically adjusts fan speed, humidifier operating status, and light intensity. The system also supports remote control. Users can send control commands via the web or mobile device, and the data is transmitted to the Raspberry Pi via the network layer for execution. Furthermore, to enhance system flexibility, an external wireless signal transmitter is connected to the Raspberry Pi, allowing a small local remote control to manually adjust device status, addressing emergency control needs in special circumstances.

[0029] Example 2 This embodiment further limits Example 1. The network module uses both local and mobile networks for information transmission. As a key link in data transmission, the network layer is responsible for reliably transmitting data collected by the perception layer to the platform layer, ensuring the real-time and stability of the system. The system supports both WiFi and 4G communication methods to meet the needs of different application scenarios.

[0030] WiFi transmission utilizes a 2.4GHz IEEE 802.11 b / g / n wireless module with a maximum transmission rate of 150Mbps, making it suitable for laboratory environments or production bases with fixed network access. The WiFi module is equipped with an external high-gain antenna to improve signal coverage and interference resistance. For remote applications or those with complex network conditions, the system utilizes 4G communication and is equipped with an industrial-grade 4G Data Transfer Unit (DTU). This supports China Mobile, China Unicom, and China Telecom networks, offering a downlink rate of 150Mbps and an uplink rate of 50Mbps, ensuring stable and efficient data upload to cloud servers.

[0031] Both WiFi and 4G communication methods are available to accommodate diverse application scenarios. In laboratories or production facilities with fixed network access, the WiFi module provides a stable local network connection, supporting IEEE 802.11 b / g / n protocols with data rates up to 150Mbps and equipped with a high-gain antenna to enhance signal coverage. In remote or complex network environments, the system utilizes an industrial-grade 4G DTU for data transmission, supporting full Netcom networks and employing TLS 1.2 encryption to ensure secure and stable data transmission.

[0032] The network module uses the MQTT protocol for data communication, utilizing a publish / subscribe model to improve transmission efficiency and avoid the redundant data traffic of point-to-point communication. The system also features a built-in resumable transmission mechanism, which caches data during network anomalies and automatically retransmits it when the connection is restored, preventing data loss. Furthermore, to ensure the real-time performance of control commands, the network layer supports low-latency data transmission optimization, enabling users' remote control operations to be quickly fed back to the perception layer for execution.

[0033] Example 3 This embodiment further limits Example 1. In terms of hardware deployment, the platform module is primarily responsible for data storage, analysis, and issuing control instructions, while the application module provides a user interface for remote monitoring and control. To ensure efficient system operation, the platform and application modules are deployed on a single high-performance server. See Table 2 for detailed configuration.

[0034] Table 2:

[0035] Example 4 This embodiment is a further limitation of embodiment 1. The platform module is responsible for data storage, analysis and execution of equipment control strategies, and adopts a distributed architecture to improve data processing capabilities. Environmental parameter data is stored in the InfluxDB time series database, which supports efficient data query and analysis, while user information and control strategies are stored in the MySQL relational database. The server-side develops a data analysis module based on Python, combined with data processing libraries such as Pandas, NumPy and SciPy to achieve statistical analysis, trend prediction and anomaly detection of environmental parameters. The system has a built-in deep learning model, and the OS-YOLO model proposed based on the YOLO model performs the task of detecting and segmenting mushroom fruiting bodies in surveillance videos. The OS-YOLO model structure is shown in Figure 2As shown in the figure, the C3k2 module in the YOLOv11 baseline network structure is first replaced with the C3k2_OREPA module. By introducing the reparameterized convolutional module OREPA, the cost and complexity of deep learning model training are reduced, improving inference speed and FPS. Secondly, the Concat module in the branch containing the neck upsampling module in the YOLOv11 baseline network structure is replaced with the SDI module. By integrating the hierarchical feature maps generated by the encoder, the semantic information and detail information in the image are enhanced, improving detection accuracy. Figure 3 The left image shows the current segmentation and prediction results for a Shiitake mushroom fruiting body. The right image shows the predicted segmentation results after a certain period of time. Prediction is achieved using an improved dual-branch ConvLSTM model, which models the growth state of Shiitake mushroom fruiting bodies and enhances the predictive capabilities of time series data. Figure 4 In the improved dual-branch ConvLSTM model structure diagram, the traditional ConvLSTM model is changed to a dual-branch convolution structure. By adding a branch formed by stacking three layers of Conv3D, the model's ability to capture spatial details between sequence images is enhanced. The attention mechanism (Attention) and transposed convolution (Transpose) are integrated. The input is the image segmented after the detection and segmentation of the shiitake mushroom fruiting body. The output result is the corresponding predicted image of the shiitake mushroom fruiting body after a period of time (12 hours in this example). The prediction results of the shiitake mushroom fruiting body of each output segmented image are spliced to obtain the prediction result of the shiitake mushroom stick.

[0036] The growth curve of Shiitake mushrooms generated by OS-YOLO model detection of Shiitake mushroom fruiting body images is as follows: Figure 5 As shown in the figure, the dotted line represents the prediction results of the shiitake mushroom fruiting body area obtained by the improved dual-branch ConvLSTM model in different sheds.

[0037] To improve data interaction efficiency, the platform module uses the Django framework to provide a RESTful API, supporting web and mobile access, and leveraging WebSocket technology to push environmental data in real time. Users can remotely monitor and control key parameters such as temperature, humidity, and light intensity. Upon receiving commands, the system immediately sends feedback to the network module, which then executes them through the perception module.

[0038] Example 4 This embodiment further limits Example 1. The application module software provides a user interface that supports remote environmental monitoring, data analysis, and device control. The web client, developed using React and Node.js, displays historical trends, real-time data, and device status in real time. The mobile application, developed using the Flutter framework and compatible with Android and iOS devices, enables users to monitor the environment and adjust device parameters anytime, anywhere.

[0039] The system features multi-role permission management, including administrators, regular users, and guests. Different users have access to corresponding data and functions based on their permissions, ensuring data security. Furthermore, the application module incorporates an intelligent alarm mechanism. By manually setting thresholds for shiitake mushroom growth environment data within the application module, the application module issues an alert when one or more of the shiitake mushroom growth environment data input by the platform module exceeds the corresponding threshold. Combining WebSocket with mobile device push notifications, the application module sends alerts to users when environmental parameters are abnormal, addressing diverse production needs.

[0040] Example 5 This embodiment is a further limitation of embodiment 1. Based on the perception module, this embodiment further designs corresponding hardware equipment and builds a set of intelligent mushroom growth control devices, such as Figure 6 As shown, the device includes a ventilation device 1, a laser plant growth adjustment lamp 2, a high-precision monitoring camera 3, a humidification tube 4, a sensor panel 5, a humidification device 6, a temperature, humidity, and CO2 sensor 7, a light sensor 8, and a mushroom cultivation platform 9. The overall dimensions of the device are 1 meter long, 0.7 meters wide, and 1 meter high. The exterior is covered with a light-shielding material to ensure the consistency and controllability of the internal light environment, providing stable lighting conditions for mushroom growth. Inside the device, a mushroom stick cultivation platform is set 0.15 meters above the ground to facilitate mushroom cultivation and management while optimizing space utilization. Combined with an intelligent control system, the device achieves precise control of the mushroom growth environment, providing scientific and intelligent hardware support for efficient mushroom cultivation.

Claims

1. An intelligent mushroom growth control system combined with a laser light source, characterized in that: The system includes a perception module, a network module, a platform module and an application module; The perception module is used to collect data on the mushroom growth environment, transmit data to the network module and receive data from the network module, and perform mushroom growth environment control; The network module is used for data transmission between the sensing module and the platform module; The platform module is used to store the mushroom growth environment data and the data input by the application module, predict the mushroom growth situation, send data to the application module and the network module, and receive data from the application module and the network module; The application module is used to interact with users on pages, receive and transmit user control instructions, send data to and receive data from the platform module, and issue early warning information when the mushroom growth environment data is abnormal.

2. The intelligent mushroom growth control system combined with a laser light source according to claim 1 is characterized in that: The sensing module comprises a ventilation device (1), a laser plant growth regulating lamp (2), a high-precision monitoring camera (3), a humidifying tube (4), a temperature, humidity and CO2 sensor (7), and a light sensor (8). The high-precision monitoring camera (3), the temperature, humidity and CO2 sensor (7), and the light sensor (8) are used to collect shiitake mushroom growth environment data, and the ventilation device (1), the laser plant growth regulating lamp (2), and the humidifying tube (4) are used to perform shiitake mushroom growth environment regulation.

3. The intelligent mushroom growth control system combined with a laser light source according to claim 2 is characterized in that: The network module uses two communication modes, local network and mobile network, to transmit information.

4. The intelligent mushroom growth control system combined with a laser light source according to claim 3 is characterized in that: In the platform module, the InfluxDB database is used to store the mushroom growth environment data, and the MySQL database is used to store the data input by the application module.

5. The intelligent mushroom growth control system combined with a laser light source according to claim 4 is characterized in that: When the platform module predicts the growth of shiitake mushrooms, it uses the improved YOLOv11 model to detect the shiitake mushroom fruiting body image at time t, obtaining several shiitake mushroom fruiting body detection images at time t. The shiitake mushroom fruiting body images at time [t-1, t-2,…,tN] are processed in the same way, and the shiitake mushroom fruiting body detection images at time [t,t-1, t-2,…,tN] are obtained in sequence, forming a shiitake mushroom fruiting body detection image sequence, where N is manually set. The shiitake mushroom fruiting body detection image sequence is input into the improved ConvLSTM model for growth prediction, and the predicted shiitake mushroom fruiting body image after growth time t+M is output, where M is set manually.

6. The intelligent mushroom growth control system combined with a laser light source according to claim 5 is characterized in that: When the shiitake mushroom fruiting body detection image sequence is input into the improved ConvLSTM model, the images in the sequence are first segmented one by one in the same way to form H groups of shiitake mushroom fruiting body detection image segmentation sequences at time [t, t-1, t-2, …, tN]. The corresponding shiitake mushroom fruiting body image after time t+M is predicted from each group of shiitake mushroom fruiting body detection image segmentation sequences at time [t, t-1, t-2, …, tN]. Then, all the shiitake mushroom fruiting body detection image segmentation sequences at time [t, t-1, t-2, …, tN] are spliced together to obtain the shiitake mushroom fruiting body image after time t+M. H and the segmentation method are set manually.

7. The intelligent mushroom growth control system combined with a laser light source according to claim 6, characterized in that: The improved YOLOv11 model specifically replaces the C3k2 module in the YOLOv11 baseline network structure with the C3k2_OREPA module, and replaces the Concat module in the branch where the neck upsampling module in the YOLOv11 baseline network structure is located with the SDI module.

8. The intelligent mushroom growth control system combined with a laser light source according to claim 7 is characterized in that: The improved ConvLSTM model specifically comprises: changing the ConvLSTM model to a dual-branch structure, using the original ConvLSTM model as the first branch, the second branch being connected in parallel with the first branch, and inputting data into the two branches simultaneously; In the second branch, data passes through 6 Conv3D modules from input to output, and Transpose layers are added after the last three Conv3D modules. The output of the first branch and the output of the third Conv3D module in the second branch are combined through the attention mechanism and input into the fourth Conv3D module in the second branch. Then, they pass through the fifth and sixth Conv3D modules in the second branch and are output.

9. The intelligent mushroom growth control system combined with a laser light source according to claim 8, characterized in that: A visualization panel is set up in the application module to interact with the user. The user queries the mushroom growth environment data and views the predicted mushroom growth situation through the visualization panel, and inputs control instructions through the visualization panel; the mushroom growth environment data threshold is manually set in the application module. When one or more of the mushroom growth environment data input by the platform module exceeds the corresponding threshold, the application module issues an early warning message.

Images