Multi-mode sensing environment control system based on greenhouse and disaster early warning method

Abstract

The invention discloses a multi-mode sensing environment control system and a disaster early warning method based on a greenhouse, and the system comprises a multi-mode sensing module which is used for collecting various environment parameters in the greenhouse, the multi-mode sensing module at least comprises a temperature sensor, a humidity sensor, an illumination sensor, a gas concentration sensor, a soil humidity sensor and image acquisition equipment; the method comprises the following steps: S1, acquiring environmental parameter data and crop growth images in a greenhouse in real time by a multi-modal sensing module; according to the invention, a multi-mode sensing technology is used, environment and crop information is comprehensively collected, and the evaluation accuracy is improved; a plurality of intelligent algorithm models are adopted for data processing, so that a basis is provided for environment control and disaster early warning; multiple modes are provided for disaster early warning, and timely information transmission is ensured; crop growth abnormity is monitored in real time through image analysis; the disaster early warning threshold value can be dynamically adjusted, and the early warning accuracy and timeliness are improved.

Description

Technical Field

[0001] This invention relates to the field of greenhouse technology, and in particular to a multimodal sensing environmental control system and disaster early warning method based on greenhouses. Background Technology

[0002] With the rapid development of modern agriculture, greenhouses, as a highly efficient agricultural production method, are widely used in the cultivation of crops such as vegetables, flowers, and fruits. Traditional greenhouse environmental control mainly relies on manual experience for adjustment, which suffers from problems such as untimely and inaccurate adjustments, making it difficult to meet the precise environmental requirements for crop growth.

[0003] In recent years, although some greenhouse environmental control systems based on single or a few sensors have emerged, these systems suffer from shortcomings such as incomplete data collection and inaccurate environmental condition assessment, failing to comprehensively and accurately reflect the environmental conditions inside the greenhouse. Furthermore, they lack effective early warning mechanisms for potential disasters, such as extreme temperatures, abnormal humidity, and pests and diseases, making crops vulnerable to their impact and leading to reduced yields or even total crop failure.

[0004] Therefore, developing a system and method that can comprehensively sense greenhouse environmental parameters, achieve intelligent environmental control, and provide timely disaster warnings is of great practical significance. Summary of the Invention

[0005] The purpose of this invention is to solve the above-mentioned technical problems by proposing a multimodal sensing environmental control system and disaster early warning method based on greenhouses.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] A multimodal sensing environment control system based on a greenhouse includes:

[0008] A multimodal sensing module is used to collect various environmental parameters inside a greenhouse. The multimodal sensing module includes at least a temperature sensor, a humidity sensor, a light sensor, a gas concentration sensor, a soil moisture sensor, and an image acquisition device.

[0009] The data processing and analysis module is communicatively connected to the multimodal sensing module. It is used to receive and process the environmental parameter data collected by the multimodal sensing module, analyze the data through a preset algorithm model, and obtain environmental status assessment results.

[0010] An environmental control module is communicatively connected to the data processing and analysis module. Based on the environmental status assessment results, it automatically adjusts the environmental equipment inside the greenhouse. The environmental equipment includes ventilation equipment, heating equipment, cooling equipment, irrigation equipment, supplemental lighting equipment, and gas conditioning equipment.

[0011] The disaster early warning module is communicatively connected to the data processing and analysis module. Based on the environmental status assessment results and the preset disaster early warning threshold, it determines whether a disaster early warning is triggered and issues an early warning message when triggered.

[0012] Preferably, in the multimodal sensing module:

[0013] The temperature sensors are arranged in a distributed manner, with multiple temperature collection points set at different heights and locations inside the greenhouse to accurately obtain the temperature distribution inside the greenhouse.

[0014] The humidity sensors are also arranged in a distributed manner, working in conjunction with the temperature sensors to acquire humidity data at different locations;

[0015] The light sensor can measure the light intensity of different wavelengths to gain a comprehensive understanding of the lighting conditions inside the greenhouse.

[0016] The gas concentration sensor can detect the concentrations of carbon dioxide, oxygen, and ammonia.

[0017] The image acquisition device uses a high-definition camera, which is installed in a suitable location inside the greenhouse. It can collect real-time images of crop growth inside the greenhouse for subsequent crop growth status analysis.

[0018] Preferably, the algorithm model used in the data processing and analysis module includes:

[0019] Data fusion algorithms are used to fuse heterogeneous data collected by different sensors, eliminate redundancy and conflicts between data, and improve the accuracy and reliability of data.

[0020] A crop growth model is a model that establishes the relationship between crop growth and environmental parameters based on collected environmental parameters and historical crop growth data. This model can then be used to predict the growth status of crops under different environmental conditions.

[0021] Disaster prediction models are constructed based on historical disaster data and the changing patterns of environmental parameters to predict the types and severity of potential disasters in advance.

[0022] Preferably, the adjustment strategy of the environmental control module is as follows:

[0023] When the temperature is higher than the preset threshold, cooling equipment, such as fans and wet curtains, is activated to lower the temperature inside the greenhouse; when the temperature is lower than the preset threshold, heating equipment, such as radiators and underfloor heating, is activated to raise the temperature inside the greenhouse.

[0024] When the humidity is higher than the preset threshold, the ventilation equipment is activated to enhance air circulation and reduce humidity; when the humidity is lower than the preset threshold, the irrigation equipment is activated to increase air humidity.

[0025] When the light intensity is lower than the preset threshold, the supplemental lighting equipment is activated to provide sufficient light for the crops;

[0026] When the gas concentration exceeds the preset range, start the gas regulation equipment, such as a carbon dioxide generator or ventilation equipment, to adjust the gas concentration to a suitable range.

[0027] Preferably, the early warning method of the disaster early warning module includes:

[0028] Audible and visual warning: Audible and visual alarms are installed inside the greenhouse. When a disaster warning is triggered, a strong audible and visual signal is emitted to alert the management personnel.

[0029] SMS alerts are sent via SMS to pre-set mobile phone numbers of administrators by connecting to the mobile communication network.

[0030] APP-based early warning: A dedicated mobile application is developed to communicate with the system. When a disaster warning is issued, the app promptly pushes the warning information and provides disaster details and handling suggestions.

[0031] Preferably, the data processing and analysis module further includes a crop growth status monitoring function based on image analysis:

[0032] Image processing technology is used to preprocess the crop growth images acquired by the image acquisition device, including noise reduction, enhancement, and segmentation operations;

[0033] Extract feature parameters of crops from images, such as leaf color, shape, size, and texture.

[0034] The extracted feature parameters are compared and analyzed with preset normal crop growth feature parameters to determine whether the crop has diseases, pests, malnutrition, or abnormal growth. The analysis results are then fed back to the environmental control module and the disaster early warning module.

[0035] Preferably, the system also has remote monitoring and management functions:

[0036] By connecting the system to a remote monitoring terminal via Internet technology, managers can remotely access the system from anywhere with internet access via computer or mobile device to view environmental parameters, crop growth status, and equipment operation in the greenhouse in real time.

[0037] The remote monitoring terminal also has remote control functions, allowing managers to remotely adjust the operating status of environmental equipment according to actual conditions, thus realizing remote management of the greenhouse.

[0038] This invention also discloses a disaster early warning method based on a multimodal sensing environmental control system for greenhouses, comprising the following steps:

[0039] S1, the multimodal sensing module collects environmental parameter data and crop growth images in the greenhouse in real time;

[0040] S2, the data processing and analysis module, integrates and analyzes the collected data to obtain environmental status assessment results and crop growth status analysis results;

[0041] S3. Compare the environmental status assessment results with the preset disaster early warning threshold to determine whether the disaster early warning conditions are met.

[0042] S4. If the disaster warning conditions are met, the disaster warning module will issue a warning message according to the preset warning method and provide corresponding disaster handling suggestions.

[0043] S5 simultaneously feeds back disaster early warning information and handling suggestions to the environmental control module. The environmental control module automatically adjusts the operating status of environmental equipment according to the actual situation to mitigate the impact of disasters on crops.

[0044] Preferably, the disaster early warning threshold is adjusted dynamically.

[0045] A1. Set initial disaster warning thresholds based on the growth stages and variety characteristics of different crops;

[0046] A2, during system operation, collects a large amount of environmental parameter data and crop growth data, and analyzes crop growth and disaster occurrence patterns under different environmental conditions;

[0047] A3, based on data analysis results, uses machine learning algorithms to dynamically adjust and optimize disaster early warning thresholds, making the early warning thresholds more in line with the actual situation and improving the accuracy and timeliness of disaster early warnings.

[0048] Compared with the prior art, the beneficial effects of this invention are as follows:

[0049] 1. Multimodal sensing technology: By combining multiple sensors and image acquisition devices, it comprehensively collects environmental parameters and crop growth information inside the greenhouse, overcoming the shortcomings of incomplete data collection in traditional systems and improving the accuracy of environmental status assessment.

[0050] 2. Intelligent Algorithm Model: The data processing and analysis module employs multiple algorithm models, such as data fusion algorithms, crop growth models, and disaster prediction models, to perform in-depth analysis and processing of the collected data, providing a scientific basis for environmental control and disaster early warning.

[0051] 3. Multiple early warning methods: The disaster early warning module provides multiple early warning methods such as sound and light, SMS, and APP to ensure that managers can receive early warning information in a timely manner and take corresponding measures.

[0052] 4. Crop growth status image analysis: Utilizing image processing technology to analyze crop growth images, enabling real-time monitoring and early warning of abnormal growth conditions such as crop diseases, pests, and malnutrition, thus supporting precision crop management.

[0053] 5. Dynamic adjustment of disaster early warning thresholds: The disaster early warning thresholds are dynamically adjusted and optimized based on actual operational data and machine learning algorithms, making the early warning thresholds more in line with the actual situation and improving the accuracy and timeliness of disaster early warnings.

[0054] In summary, this invention utilizes multimodal sensing technology to comprehensively collect environmental and crop information, thereby improving the accuracy of assessments; data processing employs various intelligent algorithm models to provide a basis for environmental control and disaster early warning; disaster early warning offers multiple methods to ensure timely information transmission; real-time monitoring of crop growth anomalies is achieved through image analysis; and disaster early warning thresholds can be dynamically adjusted to improve the accuracy and timeliness of early warnings. Attached Figure Description

[0055] Figure 1 This is a block diagram of the multimodal sensing environment control system based on a greenhouse proposed in this invention;

[0056] Figure 2 This is a flowchart illustrating the steps of the disaster early warning method based on a multimodal sensing environmental control system for greenhouses proposed in this invention. Detailed Implementation

[0057] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0058] Reference Figures 1-2 A multimodal sensing environment control system based on a greenhouse includes a multimodal sensing module for collecting various environmental parameters inside the greenhouse. The multimodal sensing module includes at least a temperature sensor, a humidity sensor, a light sensor, a gas concentration sensor, a soil moisture sensor, and an image acquisition device.

[0059] The data processing and analysis module is communicatively connected to the multimodal sensing module. It is used to receive and process the environmental parameter data collected by the multimodal sensing module, analyze the data through a preset algorithm model, and obtain environmental status assessment results.

[0060] An environmental control module is communicatively connected to the data processing and analysis module. Based on the environmental status assessment results, it automatically adjusts the environmental equipment inside the greenhouse. The environmental equipment includes ventilation equipment, heating equipment, cooling equipment, irrigation equipment, supplemental lighting equipment, and gas conditioning equipment.

[0061] The disaster early warning module is communicatively connected to the data processing and analysis module. Based on the environmental status assessment results and the preset disaster early warning threshold, it determines whether a disaster early warning is triggered and issues an early warning message when triggered.

[0062] This invention further elaborates on the following: In the multimodal sensing module:

[0063] The temperature sensors are arranged in a distributed manner, with multiple temperature collection points set at different heights and locations inside the greenhouse to accurately obtain the temperature distribution inside the greenhouse.

[0064] The humidity sensors are also arranged in a distributed manner, working in conjunction with the temperature sensors to acquire humidity data at different locations;

[0065] The light sensor can measure the light intensity of different wavelengths to gain a comprehensive understanding of the lighting conditions inside the greenhouse.

[0066] The gas concentration sensor can detect the concentrations of carbon dioxide, oxygen, and ammonia.

[0067] The image acquisition device uses a high-definition camera, which is installed in a suitable location inside the greenhouse. It can collect real-time images of crop growth inside the greenhouse for subsequent crop growth status analysis.

[0068] This invention further elaborates that the algorithm model used in the data processing and analysis module includes:

[0069] Data fusion algorithms are used to fuse heterogeneous data collected by different sensors, eliminate redundancy and conflicts between data, and improve the accuracy and reliability of data.

[0070] A crop growth model is a model that establishes the relationship between crop growth and environmental parameters based on collected environmental parameters and historical crop growth data. This model can then be used to predict the growth status of crops under different environmental conditions.

[0071] Disaster prediction models are constructed based on historical disaster data and the changing patterns of environmental parameters to predict the types and severity of potential disasters in advance.

[0072] The present invention further elaborates that the adjustment strategy of the environmental control module is as follows:

[0073] When the temperature is higher than the preset threshold, cooling equipment, such as fans and wet curtains, is activated to lower the temperature inside the greenhouse; when the temperature is lower than the preset threshold, heating equipment, such as radiators and underfloor heating, is activated to raise the temperature inside the greenhouse.

[0074] When the humidity is higher than the preset threshold, the ventilation equipment is activated to enhance air circulation and reduce humidity; when the humidity is lower than the preset threshold, the irrigation equipment is activated to increase air humidity.

[0075] When the light intensity is lower than the preset threshold, the supplemental lighting equipment is activated to provide sufficient light for the crops;

[0076] When the gas concentration exceeds the preset range, start the gas regulation equipment, such as a carbon dioxide generator or ventilation equipment, to adjust the gas concentration to a suitable range.

[0077] This invention further elaborates on the following: the early warning methods of the disaster early warning module include:

[0078] Audible and visual warning: Audible and visual alarms are installed inside the greenhouse. When a disaster warning is triggered, a strong audible and visual signal is emitted to alert the management personnel.

[0079] SMS alerts are sent via SMS to pre-set mobile phone numbers of administrators by connecting to the mobile communication network.

[0080] APP-based early warning: A dedicated mobile application is developed to communicate with the system. When a disaster warning is issued, the app promptly pushes the warning information and provides disaster details and handling suggestions.

[0081] The present invention further elaborates that the data processing and analysis module also includes a crop growth status monitoring function based on image analysis:

[0082] Image processing technology is used to preprocess the crop growth images acquired by the image acquisition device, including noise reduction, enhancement, and segmentation operations;

[0083] Extract feature parameters of crops from images, such as leaf color, shape, size, and texture.

[0084] The extracted feature parameters are compared and analyzed with preset normal crop growth feature parameters to determine whether the crop has diseases, pests, malnutrition, or abnormal growth. The analysis results are then fed back to the environmental control module and the disaster early warning module.

[0085] This invention further elaborates that the system also has remote monitoring and management functions:

[0086] By connecting the system to a remote monitoring terminal via Internet technology, managers can remotely access the system from anywhere with internet access via computer or mobile device to view environmental parameters, crop growth status, and equipment operation in the greenhouse in real time.

[0087] The remote monitoring terminal also has remote control functions, allowing managers to remotely adjust the operating status of environmental equipment according to actual conditions, thus realizing remote management of the greenhouse.

[0088] The system has adaptive learning and optimization capabilities:

[0089] During operation, the system continuously collects environmental parameter data, crop growth data, and equipment operation data.

[0090] By utilizing big data analytics and machine learning algorithms, we can deeply mine and analyze the collected data to identify potential patterns between environmental parameters, crop growth, and equipment operation.

[0091] Based on the analysis results, the algorithm model parameters of the data processing and analysis module, the adjustment strategy of the environmental control module, and the warning threshold of the disaster early warning module are automatically adjusted, so that the system can better adapt to the operating requirements of different crops and different environmental conditions, and realize the system's self-optimization and intelligent control.

[0092] This invention also discloses a disaster early warning method based on a multimodal sensing environmental control system for greenhouses, comprising the following steps:

[0093] S1, the multimodal sensing module collects environmental parameter data and crop growth images in the greenhouse in real time;

[0094] S2, the data processing and analysis module, integrates and analyzes the collected data to obtain environmental status assessment results and crop growth status analysis results;

[0095] S3. Compare the environmental status assessment results with the preset disaster early warning threshold to determine whether the disaster early warning conditions are met.

[0096] S4. If the disaster warning conditions are met, the disaster warning module will issue a warning message according to the preset warning method and provide corresponding disaster handling suggestions.

[0097] S5 simultaneously feeds back disaster early warning information and handling suggestions to the environmental control module. The environmental control module automatically adjusts the operating status of environmental equipment according to the actual situation to mitigate the impact of disasters on crops.

[0098] This invention further elaborates on the following: the disaster early warning threshold adopts a dynamic adjustment method.

[0099] A1. Set initial disaster warning thresholds based on the growth stages and variety characteristics of different crops;

[0100] A2, during system operation, collects a large amount of environmental parameter data and crop growth data, and analyzes crop growth and disaster occurrence patterns under different environmental conditions;

[0101] A3, based on data analysis results, uses machine learning algorithms to dynamically adjust and optimize disaster early warning thresholds, making the early warning thresholds more in line with the actual situation and improving the accuracy and timeliness of disaster early warnings.

[0102] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A multi-modal sensing environment control system based on a greenhouse, characterized in that, The application relates to a greenhouse environment monitoring and control system. The system comprises: a multi-modal perception module for collecting various environmental parameters in a greenhouse, which comprises at least a temperature sensor, a humidity sensor, an illumination sensor, a gas concentration sensor, a soil humidity sensor, and an image acquisition device; a data processing and analysis module in communication with the multi-modal perception module, for receiving and processing the environmental parameter data collected by the multi-modal perception module, analyzing the data through a preset algorithm model, and obtaining an environmental state evaluation result; an environmental control module in communication with the data processing and analysis module, for automatically adjusting environmental equipment in the greenhouse according to the environmental state evaluation result, wherein the environmental equipment comprises ventilation equipment, heating equipment, cooling equipment, irrigation equipment, light supplementing equipment, and gas adjusting equipment; 2. The greenhouse based multi-modal sensing environment control system as claimed in claim 1, wherein, a disaster warning module in communication with the data processing and analysis module, for judging whether to trigger a disaster warning based on the environmental state evaluation result and a preset disaster warning threshold, and issuing a warning information when the disaster warning is triggered. In the multi-modal perception module: the temperature sensor is distributedly arranged at different heights and positions in the greenhouse to accurately obtain the temperature distribution in the greenhouse; the humidity sensor is also distributedly arranged to cooperate with the temperature sensor to obtain humidity data at different positions; the illumination sensor can measure illumination intensity of different wave bands to comprehensively understand the illumination condition in the greenhouse; the gas concentration sensor can detect carbon dioxide, oxygen, and ammonia gas concentrations; 3. The greenhouse based multi-modal sensing environment control system as claimed in claim 1, wherein, the image acquisition device adopts a high-definition camera installed at a suitable position in the greenhouse to collect real-time crop growth images in the greenhouse for subsequent crop growth state analysis. The algorithm model used by the data processing and analysis module comprises: a data fusion algorithm for fusing and processing heterogeneous data collected by different sensors, eliminating redundancy and conflicts between data, and improving the accuracy and reliability of the data; a crop growth model for establishing a relationship model between crop growth and environmental parameters based on collected environmental parameters and crop growth historical data, and predicting the growth state of crops under different environmental conditions through the model; 4. The greenhouse based multi-modal sensing environment control system as claimed in claim 1, wherein, a disaster prediction model for constructing a disaster prediction model according to historical disaster data and environmental parameter change rules, and predicting the type and degree of possible disasters in advance. The adjustment strategy of the environmental control module is: when the temperature is higher than a preset threshold, starting cooling equipment such as a fan and a wet curtain to reduce the temperature in the greenhouse; when the temperature is lower than the preset threshold, starting heating equipment such as a heater and floor heating to increase the temperature in the greenhouse; when the humidity is higher than a preset threshold, starting ventilation equipment to strengthen air circulation and reduce the humidity; when the humidity is lower than the preset threshold, starting irrigation equipment to increase the air humidity; when the illumination intensity is lower than a preset threshold, starting light supplementing equipment to provide sufficient illumination for crops; 5. The greenhouse-based multi-modal sensing environment control system of claim 1, wherein, when the gas concentration exceeds a preset range, starting gas adjusting equipment such as a carbon dioxide generator and ventilation equipment to adjust the gas concentration to a suitable range. The warning mode of the disaster warning module comprises: Sound and light warning, install sound and light alarm in the greenhouse, when the disaster warning is triggered, send strong sound and light signal to remind the manager; SMS warning, connect with mobile communication network, send warning information to the manager's mobile phone number in the form of SMS; APP warning, develop a special mobile application, communicate with the system, when there is a disaster warning, push the warning information to the APP in time, and provide disaster details and processing suggestions.

6. The greenhouse-based multi-modal sensing environment control system of claim 1, wherein, The data processing and analysis module also includes crop growth state monitoring function based on image analysis: Use image processing technology to preprocess the crop growth image collected by the image acquisition device, including denoising, enhancement, segmentation operation; Extract the feature parameters of the crop in the image, such as leaf color, shape, size and texture Compare the extracted feature parameters with the preset normal crop growth feature parameters, judge whether the crop has disease and pest, and analyze the abnormal growth of nutrient deficiency, and feed back the analysis result to the environment control module and disaster warning module.

7. The greenhouse-based multi-modal sensing environment control system of claim 1, wherein, The system also has remote monitoring and management function: Through internet technology, connect the system with remote monitoring terminal, the manager can access the system remotely through computer and mobile device anywhere with network, real-time view the environmental parameters, crop growth state and equipment running status in the greenhouse; Remote monitoring terminal also has remote control function, the manager can remotely adjust the running status of environmental equipment according to the actual situation, realize remote management of greenhouse.

8. A disaster warning method of a multi-modal sensing environment control system based on the greenhouse of any one of claims 1-7, characterized in that, Including the following steps: S1, multi-modal perception module real-time collects environmental parameter data and crop growth image in greenhouse; S2, data processing and analysis module processes and analyzes the collected data, gets environmental state evaluation result and crop growth state analysis result; S3, compare the environmental state evaluation result with the preset disaster warning threshold, judge whether it meets the disaster warning condition; S4, if it meets the disaster warning condition, the disaster warning module sends warning information according to the preset warning mode, and provides corresponding disaster handling suggestion; S5, at the same time, feed back the disaster warning information and handling suggestion to the environmental control module, the environmental control module automatically adjusts the running status of environmental equipment according to the actual situation, to reduce the influence of disaster on crops.

9. The greenhouse-based multi-modal sensing environment control system disaster warning method of claim 8, wherein, The disaster warning threshold adopts dynamic adjustment method: A1, set the initial disaster warning threshold according to the growth stage and variety characteristics of different crops; A2, in the process of system running, collect a large amount of environmental parameter data and crop growth data, analyze the growth of crops and disaster occurrence law under different environmental conditions; A3, based on the data analysis result, use machine learning algorithm to dynamically adjust and optimize the disaster warning threshold, make the warning threshold more consistent with the actual situation, improve the accuracy and timeliness of disaster warning.

Images