An intelligent regulation method, system and terminal for agricultural edible mushroom growth

Abstract

This invention relates to the field of edible fungi cultivation technology, specifically to an intelligent control method, system, and terminal for the growth of agricultural edible fungi. The method includes acquiring and screening historical growth environment parameters to identify multiple growth stages of agricultural edible fungi; determining benchmark reference parameters for each growth stage; monitoring real-time environmental parameters; generating control parameters and setting them as benchmark control values ​​when deviations exist between real-time environmental parameters and benchmark reference parameters; setting primary and secondary floating ranges; and executing control actions aimed at eliminating deviations based on the relationship between real-time environmental parameters and the floating ranges, performing non-risk-free control within a preset adjustable tolerance range, or performing secondary control based on fluctuation trend judgment results. This invention achieves a balance between control accuracy, stability, and safety by establishing benchmarks matched to growth stages and combining a tiered control strategy with a dynamic tolerance mechanism, thereby improving the economic efficiency of system operation.

Description

Technical Field

[0001] This invention belongs to the field of edible fungi cultivation technology, specifically relating to an intelligent control method, system, and terminal for the growth of agricultural edible fungi. Background Technology

[0002] Edible fungi are highly sensitive to environmental factors such as temperature, humidity, carbon dioxide concentration, and light. Even slight deviations from the ideal environmental parameters can directly affect the development of mycelium and the formation of fruiting bodies, leading to reduced yield and deterioration in quality. Therefore, introducing automated and intelligent environmental control systems into modern agricultural facilities is an important measure to achieve precise control of the growth environment of edible fungi.

[0003] However, the control logic of existing technologies is mostly static, that is, most of them adopt a feedback control mode based on preset thresholds. When the sensor detects that a certain parameter is out of range, the corresponding equipment is activated, ignoring the fact that edible fungi have different requirements for environmental parameters at different growth stages. This makes it impossible to provide a truly optimized growth environment, thus limiting the full realization of the growth potential of edible fungi.

[0004] Furthermore, in existing technologies, system responses exhibit lag and overshoot, which can easily lead to drastic fluctuations in environmental parameters. During the adjustment process, the simple on / off control logic often results in overcompensation, causing key indicators such as temperature and humidity to oscillate repeatedly around the target value. A continuously unstable environment can cause stress reactions in edible fungi, affecting their growth rate and final quality.

[0005] To address the aforementioned problems, this invention provides an intelligent control method, system, and terminal for the growth of agricultural edible fungi. Summary of the Invention

[0006] The purpose of this invention is to provide an intelligent regulation method, system, and terminal for the growth of agricultural edible fungi, so as to solve the technical problem in the prior art that the regulation results are deviated due to the neglect of the specific requirements of agricultural edible fungi for the growth environment, which affects the production efficiency and quality.

[0007] To achieve the above-mentioned objectives, the technical solution adopted by the present invention is as follows: A smart regulation method for the growth of agricultural edible fungi, comprising: Monitor real-time environmental parameters of agricultural edible fungi; When the real-time environmental parameters deviate from the benchmark reference parameters determined for the current growth stage of agricultural edible fungi, a verification result is generated based on the deviation. The determination of the benchmark reference parameters includes: acquiring and screening historical growth environmental parameters to form screened historical growth environmental parameters; identifying multiple growth stages of agricultural edible fungi based on the screened historical growth environmental parameters; and for each growth stage, determining the parameters in the screened historical growth environmental parameters that have a correlation degree greater than a preset correlation threshold as the benchmark reference parameters corresponding to that growth stage. A control strategy is generated based on the verification results; Implement regulatory actions in accordance with regulatory strategies.

[0008] Preferably, the step of generating a control strategy based on the verification results includes: The control parameters are generated based on the verification results and set as the baseline control values. Based on the baseline control value, a first-level floating range and a second-level floating range are set.

[0009] Preferably, the first-level floating range and the second-level floating range include a forward range and a reverse range, respectively.

[0010] Preferably, the steps for executing control actions according to the control strategy include: When real-time environmental parameters are outside the first-level and second-level floating ranges, control actions aimed at eliminating the deviation are executed.

[0011] Preferably, the step of executing control actions according to the control strategy further includes: When the real-time environmental parameters are within the first-level floating range, non-risk-free control is performed within the preset adjustable tolerance range.

[0012] Preferably, the step of executing control actions according to the control strategy further includes: When real-time environmental parameters are within the second-level fluctuation range, perform second-level control based on the fluctuation trend judgment result or maintain monitoring.

[0013] Preferably, the preset adjustable tolerance includes: When real-time environmental parameters are within the positive first-level fluctuation range, the positive adjustable tolerance is determined based on the assessment of the current environmental carrying capacity. When real-time environmental parameters are in the reverse first-level floating range, the reverse adjustable tolerance is determined based on the assessment of the current environmental risk change.

[0014] Preferably, the steps for obtaining the fluctuation trend judgment result include: Multiple real-time environmental parameters were collected during a preset observation period; Based on multiple real-time environmental parameters and according to preset fluctuation judgment criteria, fluctuation trend analysis is performed to distinguish between effective fluctuations and ineffective fluctuations, and fluctuation trend judgment results are generated.

[0015] This invention also discloses an intelligent control system for the growth of agricultural edible fungi, comprising: The benchmark parameter generation module is used to acquire and filter historical growth environment parameters, identify the growth stages of agricultural edible fungi, and determine benchmark reference parameters for each growth stage. The environmental status monitoring module is used to collect real-time environmental parameters corresponding to the benchmark reference parameters, and generate verification results when there is a deviation between the real-time environmental parameters and the benchmark reference parameters; The control strategy generation module is used to generate a control strategy including multiple levels of floating ranges based on the verification results. The environmental control execution module is used to select and execute control actions based on the control strategy.

[0016] The present invention also discloses an intelligent control terminal for the growth of agricultural edible fungi, comprising at least one processor and a memory connected to the processor; The memory stores a computer program, which includes instructions. When the processor executes the instructions, it can perform the aforementioned intelligent control method for the growth of agricultural edible fungi.

[0017] Beneficial effects 1. This invention identifies multiple growth stages of agricultural edible fungi by screening historical growth environment parameters and based on these parameters. For each growth stage, the invention calculates the correlation between environmental parameters and the stage to determine the benchmark reference parameters. By establishing benchmark reference parameters that match different growth stages, the control targets are precisely matched with the physiological needs of agricultural edible fungi at specific stages, thereby improving the scientific nature and accuracy of environmental control.

[0018] 2. This invention establishes a hierarchical control strategy by setting a primary and secondary floating range based on a benchmark control value. This strategy effectively filters out invalid fluctuations in the environment, avoids energy waste and system instability caused by frequent start-ups and shutdowns of control equipment, and enhances the system's operational stability and economic benefits while ensuring the timeliness of key controls.

[0019] 3. When performing non-risk-related regulation, this invention calculates the additional load or the current environmental risk change based on the verification results within the first-level floating range. Based on the additional load or the current environmental risk change, it generates a positive or negative adjustable tolerance, ensuring that the regulation action is performed within the dynamically calculated safety tolerance range. This allows for flexible setting of the regulation boundary based on the current environmental carrying capacity and the current environmental risk change, ensuring that each regulation is carried out within a safe and controllable range. This prevents damage to the growth of agricultural edible fungi due to excessive regulation, thereby improving the reliability of intelligent regulation. Attached Figure Description

[0020] Figure 1 This is a system module diagram of the present invention; Figure 2 This is a flowchart of the control method of the present invention. Detailed Implementation

[0021] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0022] Example 1 See Figure 1 This embodiment provides an intelligent regulation method for the growth of agricultural edible fungi, including the following steps: S1. Obtain historical growth environment parameters for agricultural edible fungi; Historical growth environment parameters are production data accumulated over a long period of time, specifically referring to time-series data of temperature, humidity, carbon dioxide concentration, and light intensity recorded continuously in minutes.

[0023] Based on the preset normal growth environment parameter range, the historical growth environment parameters are reviewed through data cleaning rules to identify and filter out data noise, that is, to identify and filter out outlier parameters in the historical growth environment parameters that do not belong to the normal growth environment parameter range.

[0024] Specifically, outlier parameters refer to parameters that do not reflect the actual growth needs of agricultural edible fungi, such as sudden changes in readings caused by momentary sensor malfunctions or sharp drops in carbon dioxide concentration caused by temporary activation of ventilation equipment.

[0025] Outlier parameters are identified and removed because their values ​​deviate from the statistical average by more than a preset tolerance within a short period of time. This results in the selection of historical growth environment parameters, which lays the foundation for establishing accurate benchmark reference parameters and thus more accurately reflects the actual growth conditions.

[0026] The preset tolerance is preferably more than three standard deviations.

[0027] S2. Based on the screened historical growth environment parameters obtained in step S1, identify multiple growth stages of agricultural edible fungi, such as mycelial spread stage, primordium formation stage, and fruiting body development stage. For each of the multiple growth stages, a statistical analysis process is performed to calculate the correlation between the output indicators of that growth stage and various environmental parameters in a screened historical growth environment parameter list. The output indicators refer to yield or quality score.

[0028] Specifically, by calculating the Pearson correlation coefficient, it was found that the yield during the fruiting body development period was correlated with humidity by 0.85 and with carbon dioxide concentration by 0.78.

[0029] Environmental parameters with a correlation degree greater than a preset correlation threshold are identified as key environmental parameters corresponding to this growth stage. The target range or change curve of key environmental parameters that remain stable or show regular changes during this stage are compiled into the benchmark reference parameters for this growth stage, ensuring that the focus of regulation is always on the most influential environmental factors.

[0030] The reference parameters are in the form of a stable numerical range or a dynamic change curve, serving as an ideal benchmark for real-time control.

[0031] S3. During the production process, sensors deployed in the production environment are used to collect real-time environmental parameters in the current production environment of agricultural edible fungi that correspond to the benchmark reference parameters. The real-time environmental parameters are compared with the baseline reference parameters corresponding to the current growth stage, and the deviation between the two is calculated. To comprehensively assess the environmental conditions, the verification results should consider not only static deviations but also the rate of change of real-time environmental parameters.

[0032] The rate of change is obtained by calculating the amount of change in the deviation between the real-time environmental parameters and the benchmark reference parameters per unit time. Therefore, the verification result is a set of structured data containing the magnitude of the deviation, its positive and negative directions, and its rate of change, providing richer information dimensions for subsequent control decisions.

[0033] S4. Based on the verification results generated in step S3, generate control parameters for adjusting the growth environment of agricultural edible fungi. Specifically, the verification results are input into the preset control calculation logic for calculation; The control calculation logic is a multivariate process that comprehensively considers the current deviation, the rate of change, and the characteristics of the target growth stage. It is used to calculate the optimal control amount that can correct the deviation without causing drastic environmental fluctuations.

[0034] Preset weighting coefficients are assigned to the deviation and the rate of change, and the weighted two are summed to obtain a comprehensive adjustment command. The control parameters output by the calculation are set as the reference control value. For example, calculations show that the humidifier's power needs to be increased by 15%.

[0035] The baseline control value represents the ideal adjustment amount used to correct for environmental deviations and forms the basis for setting subsequent fluctuation ranges.

[0036] S5. To achieve flexible control and avoid energy waste and environmental disturbance caused by frequent equipment start-ups and shutdowns, the following steps shall be taken: Based on the benchmark control value, set the first-level floating range and the second-level floating range; The above process uses the baseline control value as the center value and retrieves the offset by querying a preset correspondence table. This correspondence table stores the mapping relationship between the sensitivity level of different growth stages and the offset used to set the width of the first-level and second-level floating ranges. For example, during the sensitive primordium formation period, the offset obtained by looking up the table is smaller, thereby tightening the floating range. Based on the queried offset, set the boundary values ​​of the first-level floating range and the boundary values ​​of the second-level floating range on both sides of the center value. Based on the boundary values, positive and negative intervals are set for the first-level and second-level floating intervals respectively, resulting in positive first-level floating interval, negative first-level floating interval, positive second-level floating interval, and negative second-level floating interval.

[0037] It should be noted that: The first-level floating range and the second-level floating range both refer to the tolerance deviation range set according to the corresponding relationship table with the reference control value as the center. The former is a smaller inner tolerance deviation range, and the latter is a larger outer tolerance deviation range, with the boundary located outside the first-level floating range. The positive first-level floating range refers to the portion of the first-level floating range where the real-time environmental parameters are better than the reference parameters, while the negative first-level floating range refers to the portion of the first-level floating range where the real-time environmental parameters are worse than the reference parameters.

[0038] Correspondingly, the positive second-level floating range refers to the portion of the second-level floating range that is outside the positive first-level floating range and whose real-time environmental parameters are better than the benchmark reference parameters, while the negative second-level floating range refers to the portion of the second-level floating range that is outside the negative first-level floating range and whose real-time environmental parameters are worse than the benchmark reference parameters.

[0039] S6. Based on the relationship between real-time environmental parameters and the positive first-level floating range, the negative first-level floating range, the positive second-level floating range, and the negative second-level floating range, select and execute the corresponding control action; When the real-time environmental parameters are in the positive first-level floating range, it indicates that the environmental conditions are slightly better than the baseline. Non-risk positive control is then implemented, which means fine-tuning for energy saving or efficiency improvement under favorable environmental conditions. At this time, the additional load is calculated based on the verification results. This calculation process quantifies the current environment's redundancy carrying capacity by comparing the difference between the real-time environmental parameters and the baseline reference parameters. Obtain the current environmental carrying capacity and set it as the additional load. Based on this, generate a positive adjustable tolerance and make fine adjustments for energy saving or efficiency improvement within the range of the positive adjustable tolerance, such as appropriately reducing the power of the dehumidification equipment. The positive adjustable tolerance is an operating range set based on the additional load, used to limit the magnitude of energy-saving or efficiency-enhancing adjustments when performing the non-risk positive control. When the real-time environmental parameters are in the reverse first-level floating range, it indicates that the environmental conditions are slightly worse than the baseline. Non-risk reverse control is then implemented, that is, a gradual correction with controlled amplitude is carried out to avoid system oscillation. At this point, the risk change is calculated based on the verification results. This calculation process extracts the rate of change from the verification results and sets this rate as the risk change, which is used to quantify the risk of the deterioration trend of environmental conditions. Based on this, a reverse adjustable tolerance is set to limit the magnitude of the correction action and ensure that the magnitude of the control action is limited to a range that will not cause a violent rebound. When real-time environmental parameters are outside the first-level and second-level floating ranges, it indicates that the environment has deviated significantly. Immediate and effective control should be implemented to bring the environmental parameters back to the safe range with maximum power or the fastest speed. When real-time environmental parameters are within the second-level fluctuation range, it indicates that the environmental deviation is trending upwards but has not yet reached an emergency state. At this time, the fluctuation trend of the real-time environmental parameters is judged to obtain the fluctuation trend judgment result. This judgment process includes: Set a preset observation period, such as 2 minutes, and continuously record multiple sampling points within this period to collect multiple real-time environmental parameters; Based on these time series data, fluctuation trend analysis is performed by calculating the slope of their linear regression trend line: If the analysis shows that the absolute value of the slope is less than the preset stability threshold, the fluctuation trend judgment result is a valid fluctuation, and monitoring will continue without immediate action. If the analysis shows that the absolute value of the slope is greater than the stability threshold and points in a direction that continues to deviate from the benchmark, then the fluctuation trend judgment result is an invalid fluctuation, and the corresponding positive secondary regulation or reverse secondary regulation is initiated to intervene in advance.

[0040] In summary, this embodiment distinguishes the actual impact of different environmental parameters on each stage of agricultural edible fungi, while also avoiding the risk of fluctuations caused by excessive regulation or untimely adjustments, thereby ensuring that the yield and quality of agricultural edible fungi remain within a controllable range.

[0041] Example 2 See Figure 2 This embodiment provides an intelligent control system for the growth of agricultural edible fungi, comprising: Reference parameter generation module It is configured to establish benchmark reference parameters for different growth stages, providing a scientific basis for subsequent real-time regulation.

[0042] Furthermore, historical growth environment parameters are obtained and filtered from the historical database. These historical growth environment parameters include, but are not limited to, data on temperature, humidity, carbon dioxide concentration, light intensity, changes in spawn bag weight, and fruiting quantity over multiple past growth cycles.

[0043] The purpose of the screening process is to eliminate outliers caused by equipment failure or human error, and to form a set of historical growth environment parameters that have been screened.

[0044] Based on screened historical growth environment parameters, the growth process of agricultural edible fungi is divided into stages.

[0045] In practical applications, by analyzing the characteristic patterns of parameter changes over time, such as the periodic peaks of carbon dioxide concentration and the stable plateau period of temperature, and combining them with label data such as yield and morphology, multiple growth stages can be automatically identified, such as the mycelial spread stage, primordium formation stage, fruiting body growth stage, and post-harvest recovery stage.

[0046] Preferably, this identification process can be implemented using techniques such as time series clustering and hidden Markov models.

[0047] For each of the identified growth stages, the correlation between each parameter and the output index of that stage is further analyzed among the screened historical growth environment parameters.

[0048] When the correlation between a certain parameter and the output indicator exceeds a preset correlation threshold, the parameter is identified as a key environmental parameter corresponding to that growth stage. The target value range or variation curve of the key environmental parameter under that growth stage is then identified as a benchmark reference parameter corresponding to that growth stage. This forms a dynamic benchmark parameter library covering all growth stages.

[0049] Environmental Status Monitoring Module It is configured to sense the current state of the growth environment in real time and compare it with the benchmark reference parameters.

[0050] The sensor network continuously collects real-time environmental parameters corresponding to the baseline reference parameters. Simultaneously, the baseline reference parameters matching the current growth stage of the agricultural edible fungi are obtained from the baseline parameter generation module.

[0051] The collected real-time environmental parameters are compared with the corresponding benchmark reference parameters in real time. When the real-time environmental parameters deviate from the benchmark reference parameters, i.e., the real-time temperature is higher or lower than the benchmark temperature range, a verification result is generated. The verification result is a set of structured data containing the magnitude of the deviation, its positive or negative direction, and its rate of change, and is then passed to the control strategy generation module.

[0052] Regulation strategy generation module It is configured to formulate refined control strategies based on the verification results generated by the environmental status monitoring module.

[0053] After receiving the verification result, based on the deviation information contained in the verification result, a control parameter for correcting the deviation is generated, and the control parameter is set as the benchmark control value.

[0054] For example, if the real-time temperature is 2 degrees Celsius higher than the reference temperature, the reference control value may be set to the fan speed or cooling power corresponding to a 2-degree Celsius temperature drop.

[0055] Based on the baseline control value, multiple levels of floating ranges are set to avoid frequent and unnecessary rigid start-stop control. Specifically, a first-level floating range and a first- and second-level floating range are set around the baseline control value.

[0056] The first-level fluctuation range represents a tolerable, slight deviation range, while the second-level fluctuation range represents an observation range that requires vigilance but does not require immediate strong intervention.

[0057] Both the first-level floating range and the second-level floating range include a positive range and a negative range, respectively, to deal with the two situations of parameters being too high and too low.

[0058] This complete scheme, which includes multiple levels of floating ranges, constitutes the regulatory strategy for this round of regulation.

[0059] Environmental control execution module It is configured to be responsible for translating abstract control strategies into specific control actions.

[0060] Furthermore, it receives control strategies from the control strategy generation module and, in conjunction with real-time environmental parameters provided by the environmental status monitoring module, selects and executes corresponding control actions. Its execution logic follows a hierarchical response mechanism: When the real-time environmental parameters are outside the first-level floating range and the second-level floating range, it indicates that the deviation has exceeded the tolerance and observation range, which is a situation that must be dealt with immediately. At this time, immediate and effective control should be performed, such as turning on the ventilation equipment or heating equipment to the maximum power, so as to bring the environmental parameters back to the vicinity of the reference parameters as quickly as possible. When real-time environmental parameters are within the first-level fluctuation range, it indicates a small deviation, and the system enters a flexible control mode, at which point non-risk-related controls are executed within the preset adjustable tolerance range. Specifically: If real-time environmental parameters are within the positive first-level fluctuation range, such as slightly high carbon dioxide concentration, then based on the positive adjustable tolerance determined by the assessment of the current environmental carrying capacity, delayed ventilation or small-scale ventilation should be implemented to save energy; among which the current environmental carrying capacity is such as the current mycelium's tolerance to carbon dioxide. If the real-time environmental parameters are within the first-level reverse fluctuation range, such as slightly low humidity, the module will determine the reverse adjustable tolerance based on the assessment of risk changes, such as the risk that low humidity may cause the caps to crack, and perform appropriate humidification to prevent quality degradation. When real-time environmental parameters are within the second-level fluctuation range, it indicates that the deviation is at a critical state, which may be a precursor to the true trend or a temporary sensor noise. To avoid misjudgment, a fluctuation trend judgment is performed. That is: Multiple real-time environmental parameters are collected during the preset observation period. Based on these parameters, fluctuation trend analysis is performed according to the preset fluctuation judgment criteria, and fluctuation trend judgment results are generated.

[0061] If the fluctuation is determined to be ineffective, the corresponding secondary control measures will be implemented, namely preventive mitigation measures; if the fluctuation is determined to be effective, no action will be taken, and monitoring will be maintained.

[0062] This embodiment adjusts the control targets according to the actual growth stage of agricultural edible fungi, and achieves refined and intelligent management of the environment through multi-level floating ranges and trend judgment, thereby improving the automation level, product quality and resource utilization efficiency of agricultural edible fungi production.

[0063] Example 3 An intelligent control terminal for the growth of agricultural edible fungi includes at least one processor and a memory connected to the processor. The memory stores a computer program, which includes instructions. When the processor executes the instructions, it can perform the aforementioned intelligent control method for the growth of agricultural edible fungi.

[0064] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. An intelligent regulation method for the growth of agricultural edible fungi, characterized in that, include: Monitor real-time environmental parameters of agricultural edible fungi; When real-time environmental parameters deviate from the baseline reference parameters determined for the current growth stage of agricultural edible fungi, a verification result is generated based on the deviation. The determination of the benchmark reference parameters includes: acquiring and screening historical growth environment parameters to form screened historical growth environment parameters; identifying multiple growth stages of agricultural edible fungi based on the screened historical growth environment parameters; and for each of the multiple growth stages, determining the parameters in the screened historical growth environment parameters that have a correlation degree greater than a preset correlation threshold as the benchmark reference parameters corresponding to that growth stage. A control strategy is generated based on the verification results; Implement regulatory actions in accordance with regulatory strategies.

2. The intelligent regulation method for the growth of agricultural edible mushrooms according to claim 1, characterized in that, The steps for generating a control strategy based on the verification results include: The control parameters are generated based on the verification results and set as the baseline control values. Based on the baseline control value, a first-level floating range and a second-level floating range are set.

3. The intelligent regulation method for the growth of agricultural edible fungi according to claim 2, characterized in that, The first-level floating range and the second-level floating range include the positive range and the negative range, respectively.

4. The intelligent regulation method for agricultural edible mushroom growth according to claim 3, characterized in that, The steps for implementing regulatory actions based on the regulatory strategy include: When real-time environmental parameters are outside the first-level and second-level floating ranges, control actions aimed at eliminating the deviation are executed.

5. The intelligent regulation method for the growth of agricultural edible fungi according to claim 4, characterized in that, The steps for implementing regulatory actions based on the regulatory strategy also include: When the real-time environmental parameters are within the first-level floating range, non-risk-free control is performed within the preset adjustable tolerance range.

6. The intelligent control method for the growth of agricultural edible fungi according to claim 5, characterized in that, The steps for implementing regulatory actions based on the regulatory strategy also include: When real-time environmental parameters are within the second-level fluctuation range, perform second-level control based on the fluctuation trend judgment result or maintain monitoring.

7. The intelligent control method for the growth of agricultural edible fungi according to claim 5, characterized in that, Preset adjustable tolerances include: When real-time environmental parameters are within the positive first-level fluctuation range, the positive adjustable tolerance is determined based on the assessment of the current environmental carrying capacity. When real-time environmental parameters are in the reverse first-level floating range, the reverse adjustable tolerance is determined based on the assessment of the current environmental risk change.

8. The intelligent regulation method for the growth of agricultural edible fungi according to claim 6, characterized in that, The steps to obtain the fluctuation trend judgment result include: Multiple real-time environmental parameters were collected during a preset observation period; Based on multiple real-time environmental parameters and according to preset fluctuation judgment criteria, fluctuation trend analysis is performed to distinguish between effective fluctuations and ineffective fluctuations, and fluctuation trend judgment results are generated.

9. An intelligent control system for the growth of agricultural edible fungi, characterized in that, include: The benchmark parameter generation module is used to acquire and filter historical growth environment parameters, identify the growth stages of agricultural edible fungi, and determine benchmark reference parameters for each growth stage. The environmental status monitoring module is used to collect real-time environmental parameters corresponding to the benchmark reference parameters, and generate verification results when there is a deviation between the real-time environmental parameters and the benchmark reference parameters; The control strategy generation module is used to generate a control strategy including multiple levels of floating ranges based on the verification results. The environmental control execution module is used to select and execute control actions based on the control strategy.

10. An intelligent control terminal for the growth of agricultural edible fungi, characterized in that, Includes at least one processor and memory connected to the processor; The memory stores a computer program, which includes instructions. When the processor executes the instructions, it is able to perform the intelligent control method for the growth of agricultural edible fungi as described in any one of claims 1 to 6.

Images