Edible mushroom house environment intelligent control method

Abstract

The invention discloses an intelligent edible mushroom house environment control method, and belongs to the technical field of edible mushroom house environment control. According to the edible mushroom house environment intelligent control method, an acquisition module, a theoretical analysis module, a data comparison module, a generation module and an adjustment module are included, and the acquisition module, the theoretical analysis module, the data comparison module, the generation module and the adjustment module are connected. According to the intelligent control method for the environment of the edible mushroom house, the data comparison module compares the environment parameters monitored in real time with the optimal environment parameters according to the real-time environment change in the edible mushroom house, the change trend of the future environment is accurately predicted, and the environment parameters are optimized and adjusted, so that the intelligent control for the environment of the edible mushroom house is faster and more accurate; the defect of hysteresis of an existing system is overcome, the growth environment of the edible mushrooms is guaranteed, and then the yield and quality of the edible mushrooms are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of edible mushroom house environment control, and more specifically, to an edible mushroom house environment intelligent control method. Background Art

[0002] Edible mushrooms are a type of large fungi that are edible to humans. Edible mushrooms are usually grown in mushroom houses, which are special facilities for the artificial cultivation of edible mushrooms. They can provide suitable environmental conditions for the growth of edible mushrooms.

[0003] Chinese patent application number CN202410196810.2 discloses an intelligent control method for an edible mushroom house environment, which includes the following steps: obtaining production demand information input by a user; parsing and verifying the production demand information, and obtaining the current production environment information of the edible mushroom house after verification; generating an environmental control plan based on the production demand information and the current production environment information of the edible mushroom house through a preset environmental control model plan; issuing equipment control parameters to the environmental adjustment equipment in the edible mushroom house for parameter setting according to the environmental control plan, generating environmental adjustment control instructions according to the environmental adjustment process information, and sending the environmental adjustment control instructions to the environmental adjustment equipment in the edible mushroom house to control the environmental adjustment equipment to adjust the environmental parameters in the edible mushroom house.

[0004] The above technical scheme has the effect of accurately controlling the yield and growth rate of mushrooms. Although these systems can realize automatic monitoring and adjustment of environmental parameters to a certain extent, due to the unpredictable environment in the edible mushroom house, the existing system cannot accurately predict the future trend of environmental changes, resulting in a certain lag in intelligent control. This lag will affect the growth state of edible mushrooms, resulting in poor growth of edible mushrooms, and further affecting the final yield and quality of edible mushrooms. Summary of the invention

[0005] The purpose of the present invention is to provide an edible mushroom house environment intelligent control method to solve the problems raised in the above background technology:

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] An edible mushroom house environment intelligent control method, the steps are as follows:

[0008] S1: Collection module, which saves the historical growth environment data and yield of edible mushrooms, conducts in-depth analysis and mining of historical data, and obtains the overall evaluation average value of the growth environment in the same period of two years. The overall evaluation average value is the average value of the growth environment values ​​in the same period of two years. According to the data analysis results, the optimal growth environment of edible mushrooms in different growth stages is obtained, and the range of the optimal growth environment is the average value ±2;

[0009] S2: Enter the theoretical analysis module, compare the existing periodic environmental data parameters with the range of the optimal growth environment to analyze whether the current edible mushroom growth environment is abnormal. If the current environmental parameters are within the range of the optimal growth environment, it means that the current growth environment is normal. If the current environmental parameters are not within the range of the optimal growth environment, it means that the current growth environment is abnormal.

[0010] S3: Enter the data comparison module, which compares the real-time monitored environmental parameters with the optimal environmental parameters, calculates the average cycle deviation value of the edible mushroom growth environment, and determines whether the current growth environment of the edible mushrooms is abnormal;

[0011] S4: Enter the generation module, compare the optimal environment with the current environment data monitored in real time, and formulate an optimized environment plan;

[0012] S5: Enter the execution module, the generation module formulates an optimization plan, and according to the environmental parameters that need to be optimized in the plan, the execution module performs adjustments on various indicators required for the growth environment of edible mushrooms.

[0013] Preferably, the acquisition module, theoretical analysis module, data comparison module, generation module and adjustment module are connected.

[0014] Preferably, the theoretical analysis module includes a theoretical environment module and an analysis and processing module, the theoretical environment module includes a collection end and a processing end, the collection end is used to receive the growth environment data, growth status records and yield of edible mushrooms in the collection module, the processing end uses an intelligent control cabinet and a built-in algorithm to perform in-depth processing on the data received by the collection end, and then integrates and plans the data through the analysis and processing module to obtain the historical best growth environment of edible mushrooms.

[0015] Preferably, the data comparison module includes a real-time monitoring module, and the real-time monitoring module includes a receiving module, a processing module, an early warning module and an optimization and adjustment module, and the receiving module, the processing module, the early warning module and the optimization and adjustment module are connected to each other, and the real-time monitoring module collects real-time data of environmental parameters through a sensor network in real time, and the real-time monitoring module compares with the theoretical analysis module to calculate the average periodic deviation value of the growth environment of edible mushrooms and use it as a basic difference. The early warning module is used to receive the difference between the growth environment of the real-time monitoring module and the optimal growth environment of the theoretical environment module as a basic value, and the basic value is 2. The environmental average value of this period obtained by the real-time monitoring module is compared with the basic difference to predict the future growth environment of edible mushrooms, and optimize the future environment through the optimization and adjustment module.

[0016] Preferably, the receiving module includes a temperature sensor, a humidity sensor, a carbon dioxide sensor and a light sensor;

[0017] The temperature sensor is used to monitor the temperature of the edible mushroom house in real time, the humidity sensor is used to monitor the humidity of the edible mushroom house in real time, the carbon dioxide sensor is used to monitor the carbon dioxide concentration in the edible mushroom house in real time, and the light sensor is used to monitor the light range and light intensity inside the edible mushroom house in real time.

[0018] Preferably, the processing module includes a data cleaning end, a denoising end and a normalization end;

[0019] The data cleaning end is used to process the data set received by the receiving module;

[0020] The denoising end denoises the data received by the receiving module by smoothing, filtering, and detecting and deleting abnormal values ​​using statistical methods;

[0021] The normalization end plans and organizes the data set received by the receiving module.

[0022] Preferably, the early warning module includes a monitoring period average value and an environment adjustment module. The monitoring period average value can calculate the average value of the environmental parameters within the period, and the environment adjustment module adjusts the current environmental parameters.

[0023] Preferably, the early warning module can calculate the periodic average value of the edible mushroom house environment based on the real-time monitoring environmental data, and the calculation formula is as follows:

[0024] T_avg=(∑T_i) / n;

[0025] Wherein, T_avg represents the average value of the environmental parameter within the period; T_i represents the total value of the environmental parameter measured from the 1st to the i-th time; and n represents the number of measurements.

[0026] Preferably, the early warning module obtains the periodic average value of the edible mushroom house environment. If the periodic average value is ≤2, it means that the edible mushroom growth environment at this time is suitable for the required environmental value for a certain period in the future. If the periodic average value is >2, it means that the edible mushroom growth environment at this time is not suitable for the required environmental value for a certain period in the future.

[0027] Preferably, the optimization and adjustment module includes a convolutional neural network, and the optimization and adjustment module optimizes the environment inside the edible mushroom house through the convolutional neural network. The calculation formula for environmental optimization is as follows:

[0028] The convolution layer is used to extract data features. The formula is as follows:

[0029] Z ( l+ 1)=W ( l+ 1) *Z ( l ) +b ( l+ 1) ;

[0030] Among them, Z ( l ) is the output of layer l, W ( l+ 1) is the convolution kernel of the l+1th layer, * indicates the convolution operation, b ( l+ 1) is the bias term;

[0031] The pooling layer is used to reduce the dimension of the feature map and reduce the amount of calculation. The formula is as follows:

[0032] P ( l ) =Pooling(Z (l) );

[0033] Fully connected layer, the formula is as follows:

[0034] Y=W f ·X+b f ;

[0035] Where X is the input feature vector, W f is the weight matrix of the fully connected layer, b f is the bias term;

[0036] After the optimization is completed by the optimization and adjustment module, it is transmitted to the early warning module, and the environmental adjustment module adjusts the current environmental parameters. After the data adjustment is completed, the periodic average value of the edible mushroom house environment is obtained by monitoring the periodic average value, and then compared with the basic value for verification.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] 1) When the method for intelligently controlling the environment of a mushroom house is used, the data comparison module compares the environmental parameters monitored in real time with the optimal environmental parameters according to the real-time environmental changes in the mushroom house, accurately predicts the future environmental change trend and optimizes the adjustment, so that the intelligent control of the environment of the mushroom house is faster and more accurate, solves the lag problem of the existing system, ensures the growth environment of edible mushrooms, and thus improves the yield and quality of edible mushrooms.

[0039] 2) When the intelligent control method for the edible mushroom house environment is used, the cleaning end, the denoising end and the normalization end work together to denoise and clean the abnormal values ​​and abnormal radio waves of the data, and finally make a unified plan, thereby improving the monitoring accuracy of the real-time monitoring module on the edible mushroom house environment, making the early warning module calculate the periodic average value of the edible mushroom house environment more accurately, and thus making the optimization and adjustment module optimize the edible mushroom house environment more quickly and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is an overall system architecture diagram of an edible mushroom house environment intelligent control method of the present invention;

[0041] Figure 2 This is a data comparison module architecture diagram of an edible mushroom house environment intelligent control method of the present invention;

[0042] Figure 3 This is a real-time monitoring module architecture diagram of an edible mushroom house environment intelligent control method of the present invention;

[0043] Figure 4 This is a flow chart of the optimization and adjustment module of an edible mushroom house environment intelligent control method of the present invention. DETAILED DESCRIPTION

[0044] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0045] Example 1: Please refer to Figure 1 - Figure 4 , an edible mushroom house environment intelligent control method, the steps are as follows:

[0046] S1: The acquisition module saves the historical data on the growth environment and yield of edible mushrooms, conducts in-depth analysis and mining of the historical data, and identifies the optimal growth conditions affecting edible mushrooms. The historical data is the yield of edible mushrooms in different years. At the same cycle time and the same moment in the historical data, the acquisition module is used to obtain the overall evaluation average value of the growth environment in the same cycle of two years. The overall evaluation average value is the average value of the growth environment in the same cycle of two years. According to the data analysis results, the optimal growth environment of edible mushrooms at different growth stages is obtained. The range of the optimal growth environment is the average value ±2;

[0047] S2: Enter the theoretical analysis module. The intelligent control cabinet has fuzzy control algorithm, PID control algorithm and artificial intelligence-based algorithm. The built-in algorithm of the intelligent control cabinet is used to input the optimal growth conditions of edible mushrooms into the intelligent control cabinet. The fuzzy control algorithm, PID control algorithm and artificial intelligence-based algorithm are combined to comprehensively analyze the data results and model predictions. The artificial intelligence-based algorithm obtains the training model. The existing periodic environmental data parameters are compared with the range of the optimal growth environment to analyze whether the current edible mushroom growth environment is abnormal. If the current environmental parameters are included in the range of the optimal growth environment, it means that the current growth environment is normal. If the current environmental parameters are not included in the range of the optimal growth environment, it means that the current growth environment is abnormal.

[0048] S3: Enter the data comparison module, which compares the real-time monitored environmental parameters with the optimal environmental parameters, calculates the average cycle deviation value of the edible mushroom growth environment, and determines whether the current growth environment of the edible mushrooms is abnormal;

[0049] S4: Enter the generation module, compare the optimal environment with the current environment data monitored in real time, and formulate an optimized environment plan;

[0050] S5: Enter the execution module, the generation module formulates an optimization plan, and according to the environmental parameters that need to be optimized in the plan, the execution module performs adjustments on various indicators required for the growth environment of edible mushrooms.

[0051] The intelligent control method includes an acquisition module, a theoretical analysis module, a data comparison module, a generation module and an adjustment module. The acquisition module, the theoretical analysis module, the data comparison module, the generation module and the adjustment module are connected. According to the real-time environmental changes in the edible mushroom house, the data comparison module compares the environmental parameters monitored in real time with the optimal environmental parameters, accurately predicts the changing trend of the future environment, makes the intelligent control of the edible mushroom house environment faster and more accurate, solves the lag shortcoming of the existing system, ensures the growth environment of edible mushrooms, and thus improves the yield and quality of edible mushrooms.

[0052] The theoretical analysis module includes a theoretical environment module and an analysis and processing module. The theoretical environment module includes a collection end and a processing end. The collection end is used to receive the growth environment data, growth status records and output of edible mushrooms in the collection module. The processing end uses an intelligent control cabinet and a built-in algorithm to perform in-depth processing on the data received by the collection end, and then integrates and plans the data through the analysis and processing module to obtain the historical best growth environment for edible mushrooms.

[0053] The data comparison module includes a real-time monitoring module, which includes a receiving module, a processing module, an early warning module and an optimization and adjustment module. The receiving module, the processing module, the early warning module and the optimization and adjustment module are connected. The real-time monitoring module collects real-time data of environmental parameters through a sensor network. The real-time monitoring module is compared with the theoretical analysis module to calculate the average periodic deviation value of the edible mushroom growth environment and use it as a basic difference. The early warning module is used to receive the difference between the growth environment of the real-time monitoring module and the optimal growth environment of the theoretical environment module as a basic value, and the basic value is 2. The environmental average value of this period obtained by the real-time monitoring module is compared with the basic difference to predict the future growth environment of edible mushrooms, and optimize the future environment through the optimization and adjustment module.

[0054] The receiving module includes a temperature sensor, a humidity sensor, a carbon dioxide sensor and a light sensor;

[0055] The temperature sensor is used to monitor the temperature of the edible mushroom house in real time, the humidity sensor is used to monitor the humidity of the edible mushroom house in real time, the carbon dioxide sensor is used to monitor the carbon dioxide concentration in the edible mushroom house in real time, and the light sensor is used to monitor the light range and light intensity inside the edible mushroom house in real time.

[0056] The early warning module includes a monitoring cycle average value and an environmental adjustment module. The monitoring cycle average value can calculate the average value of environmental parameters within the cycle, and the environmental adjustment module adjusts the current environmental parameters.

[0057] The early warning module can calculate the periodic average value of the mushroom house environment based on real-time monitoring environmental data. The calculation formula is as follows:

[0058] T_avg=(∑T_i) / n;

[0059] Wherein, T_avg represents the average value of the environmental parameter within the period; T_i represents the total value of the environmental parameter measured from the 1st to the i-th time; and n represents the number of measurements.

[0060] The early warning module obtains the periodic average value of the edible mushroom room environment. If the periodic average value is ≤2, it means that the edible mushroom growth environment at this time is suitable for the required environmental value for a certain period in the future. If the periodic average value is >2, it means that the edible mushroom growth environment at this time is not suitable for the required environmental value for a certain period in the future.

[0061] The optimization and adjustment module includes a convolutional neural network. The optimization and adjustment module optimizes the environment inside the edible mushroom house through the convolutional neural network. The calculation formula for environmental optimization is as follows:

[0062] The convolution layer is used to extract data features. The formula is as follows:

[0063] Z ( l+1) =W ( l+ 1) *Z ( l ) +b ( l+ 1) ;

[0064] Among them, Z ( l ) is the output of layer l, W ( l+ 1) is the convolution kernel of the l+1th layer, * indicates the convolution operation, b ( l+ 1) is the bias term;

[0065] The pooling layer is used to reduce the dimension of the feature map and reduce the amount of calculation. The formula is as follows:

[0066] P ( l ) =Pooling(Z (l) );

[0067] Fully connected layer, the formula is as follows:

[0068] Y=W f ·X+b f ;

[0069] Where X is the input feature vector, W f is the weight matrix of the fully connected layer, b f is the bias term;

[0070] After the optimization is completed by the optimization and adjustment module, it is transmitted to the early warning module. The environmental adjustment module adjusts the current environmental parameters. After the data adjustment is completed, the periodic average value of the edible mushroom house environment is obtained by monitoring the periodic average value, and then compared with the basic value for verification.

[0071] The use steps of the present invention are as follows: when the intelligent control method for the environment of an edible mushroom house is used, the acquisition module identifies the key factors and optimal growth conditions that affect the growth of edible mushrooms, enters the theoretical analysis module, determines the optimal growth environment range of the edible mushrooms, enters the data comparison module, determines whether there is an abnormality between the optimal environmental parameters of the edible mushrooms and the current environmental parameters monitored by the real-time monitoring module, enters the generation module, formulates an optimized environmental plan, enters the adjustment module, and the adjustment module adjusts various indicators required for the growth environment of the edible mushrooms. According to the real-time environmental changes in the edible mushroom house, the data comparison module compares the environmental parameters monitored in real time with the optimal environmental parameters, accurately predicts the changing trend of the future environment, and makes the intelligent control of the edible mushroom house environment faster and more accurate, solves the shortcoming of the hysteresis of the existing system, ensures the growth environment of the edible mushrooms, and thus improves the yield and quality of the edible mushrooms.

[0072] Example 2: Please refer to Figure 1 - Figure 4 , the difference between the embodiment 1 and the embodiment 1 is that the processing module includes a data cleaning end, a denoising end and a normalization end;

[0073] The data cleaning end is used to process the data set received by the receiving module to correct and delete inaccurate, incomplete, inconsistent or duplicate data records;

[0074] The denoising end denoises the data received by the receiving module by smoothing, filtering, and using statistical methods to detect and delete outliers;

[0075] The normalization end plans and organizes the data set received by the receiving module, eliminates the dimensional influence between different features in the data set, and makes the model easier to learn and predict. Through the coordinated work of the cleaning end, denoising end and normalization end, the outliers and abnormal radio waves of the data are denoised and cleaned. Finally, unified planning is performed, which improves the monitoring accuracy of the real-time monitoring module on the edible mushroom house environment, makes the early warning module calculate the periodic average value of the edible mushroom house environment more accurately, and thus makes the optimization and adjustment module optimize the edible mushroom house environment more quickly and accurately.

[0076] The use steps of the present invention are as follows: when the intelligent control method for the edible mushroom house environment is used, the processing module processes the temperature, humidity, carbon dioxide and light data information transmitted by the receiving module. During the processing, the cleaning end, the denoising end and the normalization end work in coordination to denoise and clean the abnormal values ​​and abnormal radio waves of the data. Finally, unified planning is performed, thereby improving the monitoring accuracy of the real-time monitoring module on the edible mushroom house environment, making the early warning module more accurate in calculating the periodic average value of the edible mushroom house environment, and further making the optimization and adjustment module more rapid and accurate in optimizing the edible mushroom house environment.

[0077] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An edible mushroom house environment intelligent control method, characterized in that: The method for intelligently controlling the environment of an edible mushroom house comprises the following steps: S1: Collection module, which saves the historical growth environment data and yield of edible mushrooms, conducts in-depth analysis and mining of historical data, and obtains the overall evaluation average value of the growth environment in the same period of two years. The overall evaluation average value is the average value of the growth environment values ​​in the same period of two years. According to the data analysis results, the optimal growth environment of edible mushrooms in different growth stages is obtained, and the range of the optimal growth environment is the average value ±2; S2: Enter the theoretical analysis module, compare the existing periodic environmental data parameters with the range of the optimal growth environment to analyze whether the current edible mushroom growth environment is abnormal. If the current environmental parameters are within the range of the optimal growth environment, it means that the current growth environment is normal. If the current environmental parameters are not within the range of the optimal growth environment, it means that the current growth environment is abnormal. S3: Enter the data comparison module, which compares the real-time monitored environmental parameters with the optimal environmental parameters, calculates the average cycle deviation value of the edible mushroom growth environment, and determines whether the current growth environment of the edible mushrooms is abnormal; S4: Enter the generation module, compare the optimal environment with the current environment data monitored in real time, and formulate an optimized environment plan; S5: Enter the execution module, the generation module formulates an optimization plan, and according to the environmental parameters that need to be optimized in the plan, the execution module performs adjustments on various indicators required for the growth environment of edible mushrooms.

2. The method for intelligently controlling the environment of a mushroom house according to claim 1, characterized in that: The acquisition module, theoretical analysis module, data comparison module, generation module and adjustment module are connected to each other.

3. The method for intelligently controlling the environment of a mushroom house according to claim 2, characterized in that: The theoretical analysis module includes a theoretical environment module and an analysis and processing module. The theoretical environment module includes a collection end and a processing end. The collection end is used to receive the growth environment data, growth status records and output of edible mushrooms in the collection module. The processing end uses an intelligent control cabinet and a built-in algorithm to perform in-depth processing on the data received by the collection end, and then integrates and plans the data through the analysis and processing module to obtain the historical best growth environment of edible mushrooms.

4. The method for intelligently controlling the environment of a mushroom house according to claim 3, characterized in that: The data comparison module includes a real-time monitoring module, which includes a receiving module, a processing module, an early warning module and an optimization and adjustment module. The receiving module, the processing module, the early warning module and the optimization and adjustment module are connected to each other. The real-time monitoring module collects real-time data of environmental parameters through a sensor network. The real-time monitoring module compares with the theoretical analysis module to calculate the average period deviation value of the edible mushroom growth environment and uses it as a basic difference. The early warning module is used to receive the difference between the growth environment of the real-time monitoring module and the optimal growth environment of the theoretical environment module as a basic value, and the basic value is 2. The environmental average value of this period obtained by the real-time monitoring module is compared with the basic difference to predict the future edible mushroom growth environment, and optimize the future environment through the optimization and adjustment module.

5. The method for intelligently controlling the environment of a mushroom house according to claim 4, characterized in that: The receiving module includes a temperature sensor, a humidity sensor, a carbon dioxide sensor and a light sensor; The temperature sensor is used to monitor the temperature of the edible mushroom house in real time, the humidity sensor is used to monitor the humidity of the edible mushroom house in real time, the carbon dioxide sensor is used to monitor the carbon dioxide concentration in the edible mushroom house in real time, and the light sensor is used to monitor the light range and light intensity inside the edible mushroom house in real time.

6. The method for intelligently controlling the environment of a mushroom house according to claim 4, characterized in that: The processing module includes a data cleaning end, a denoising end and a normalization end; The data cleaning end is used to process the data set received by the receiving module; The denoising end denoises the data received by the receiving module by smoothing, filtering, and detecting and deleting abnormal values ​​using statistical methods; The normalization end plans and organizes the data set received by the receiving module.

7. The method for intelligently controlling the environment of a mushroom house according to claim 4, characterized in that: The early warning module includes a monitoring period average value and an environment adjustment module. The monitoring period average value can calculate the average value of the environmental parameters within the period, and the environment adjustment module adjusts the current environmental parameters.

8. The method for intelligently controlling the environment of a mushroom house according to claim 7, characterized in that: The early warning module can calculate the periodic average value of the edible mushroom house environment based on the real-time monitoring environmental data. The calculation formula is as follows: T_avg=(∑T_i) / n; Wherein, T_avg represents the average value of the environmental parameter within the period; T_i represents the total value of the environmental parameter measured from the 1st to the i-th time; and n represents the number of measurements.

9. The method for intelligently controlling the environment of a mushroom house according to claim 8, characterized in that: The early warning module obtains the periodic average value of the edible mushroom house environment. If the periodic average value is ≤2, it means that the edible mushroom growth environment at this time is suitable for the required environmental value for a certain period in the future. If the periodic average value is >2, it means that the edible mushroom growth environment at this time is not suitable for the required environmental value for a certain period in the future.

10. The method for intelligently controlling the environment of a mushroom house according to claim 1, characterized in that: The optimization and adjustment module includes a convolutional neural network. The optimization and adjustment module optimizes the environment inside the edible mushroom house through the convolutional neural network. The calculation formula for environmental optimization is as follows: The convolution layer is used to extract data features. The formula is as follows: Z ( l+ 1) =W ( l+ 1) *Z ( l ) +b ( l+ 1) ; Among them, Z ( l ) is the output of layer l, W ( l+ 1) is the convolution kernel of the l+1th layer, * indicates the convolution operation, b ( l+ 1) is the bias term; The pooling layer is used to reduce the dimension of the feature map and reduce the amount of calculation. The formula is as follows: P ( l ) =Pooling(Z (l) ); Fully connected layer, the formula is as follows: Y=W f ·X+b f ; Where X is the input feature vector, W f is the weight matrix of the fully connected layer, b f is the bias term; After the optimization is completed by the optimization and adjustment module, it is transmitted to the early warning module, and the environmental adjustment module adjusts the current environmental parameters. After the data adjustment is completed, the periodic average value of the edible mushroom house environment is obtained by monitoring the periodic average value, and then compared with the basic value for verification.

Images