Intelligent control methods, systems, equipment, and storage media for rare fungi cultivation rooms

By combining multi-dimensional coupling of environmental parameters with a dynamic growth model library, collaborative control commands are output, solving the problem of insufficient coupling analysis of environmental parameters and mycelial activity in the cultivation of rare fungi. This enables precise correction of the local microenvironment, improves yield stability and quality uniformity, and provides reliable technical support for the cultivation of rare fungi.

CN121844895BActive Publication Date: 2026-11-17KENDE ENVIRONMENTAL TECH ENG (SHANGHAI) CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202610054514.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-01-15
Publication Date
2026-11-17
Estimated Expiration
2046-01-15

AI Technical Summary

Technical Problem

In existing rare fungal cultivation and regulation technologies, there is a lack of coupled analysis between environmental parameters and mycelial activity indicators. This leads to regulatory decisions being detached from the actual biological growth, resulting in microenvironmental imbalance, difficulty in precise correction, and delayed stress response under sudden disturbances, which affects the stability of cultivation yield and quality.

Method used

By acquiring multi-dimensional coupled environmental parameters within the growing room, including temperature and humidity gradients, soil matrix conductivity, airflow vectors, and mycelial activity-microenvironment coupling parameters, and combining them with a dynamic growth model library, multi-dimensional collaborative control commands are output, including fan turning angle, supplemental lighting spectral combination, spray device droplet diameter and spraying sequence, and metabolic heat compensation coefficient of substrate nutrient solution, to achieve precise correction of the local microenvironment.

Benefits of technology

It significantly improves the yield stability and quality uniformity of rare fungi cultivation, solves the problem of uneven development caused by mycelial respiration heterogeneity, ensures the stability and controllability of the cultivation process, and provides technical support for large-scale and standardized cultivation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121844895B_ABST
    Figure CN121844895B_ABST
Patent Text Reader

Abstract

This application relates to the field of intelligent agricultural technology, and in particular to intelligent control methods, systems, equipment, and storage media for rare fungi cultivation rooms. The method includes: acquiring multi-dimensional coupled environmental parameters within the cultivation room, which integrate environmental data such as temperature and humidity gradients and substrate conductivity in different areas with mycelial activity-microenvironment coupling parameters such as ATP content of the fungal logs and mycelial density; comparing these parameters with a dynamic growth model library integrating multi-species data and historical feedback; and outputting multi-dimensional coordinated control commands based on the results, including fan vortex intensity, supplemental lighting phase difference, spraying timing, and nutrient solution compensation coefficient for different areas. This application achieves precise coupled control of environment and biological activity, effectively improving the yield stability and quality uniformity of rare fungi cultivation, reducing energy consumption per unit yield, and providing technical support for large-scale standardized cultivation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of intelligent agricultural technology, and in particular to intelligent control methods, systems, equipment and storage media for rare fungi cultivation rooms. Background Technology

[0002] Rare fungi (such as morels, truffles, and cordyceps) have become a key focus of modern agricultural cultivation due to their scarcity and high economic value. However, their sensitivity to the growth environment far exceeds that of common edible fungi. Even slight fluctuations in environmental factors such as temperature and humidity gradients, substrate nutrients, and airflow can lead to mycelial stagnation and primordium necrosis, directly impacting cultivation yields. Therefore, precise control of the cultivation environment is crucial for achieving stable mass production of rare fungi. Although existing technologies for controlling the cultivation of rare fungi have incorporated sensors and automatic control equipment, core technological bottlenecks remain: existing systems mostly adopt a "separate monitoring of environmental parameters + fixed threshold triggering control" model, failing to couple and analyze environmental parameters such as temperature, humidity, and carbon dioxide with mycelial activity indicators (such as ATP content and metabolic heat flux). This results in a break in the correlation between environmental parameters and fungal growth status, and a lack of bioactive data to support control decisions. For example, some solutions only activate fans and spray equipment based on temperature and humidity thresholds, neglecting the disturbance of the microenvironment caused by the localized metabolic heat generated by mycelial respiration. When a temperature gradient of more than 3°C forms in a localized area of ​​the cultivation room due to dense mycelial respiration, a uniform control strategy for the entire area cannot specifically balance the microenvironment, easily leading to the phenomenon of "environmental parameters meeting standards but mycelial growth being abnormal." Moreover, this isolated monitoring mode cannot predict the potential impact of changes in environmental parameters on mycelial activity. In the event of sudden temperature changes, accumulation of harmful gases, or other emergencies, adjustments can only be made passively after parameters exceed the standards, resulting in significant yield reductions in rare fungi due to stress damage. This lack of coupled "environment-activity" control has become a major obstacle restricting the level of intelligent cultivation and yield stability of rare fungi. Summary of the Invention

[0003] The purpose of this application is to provide intelligent control methods, systems, equipment, and storage media for rare fungi cultivation rooms. The aim is to solve the problems in the existing rare fungi cultivation control, such as the lack of coupled analysis between environmental parameters and mycelial activity indicators, which leads to control decisions being detached from the actual biological growth, difficulty in accurately correcting microenvironmental imbalances, and delayed stress response under sudden disturbances, ultimately affecting the stability of cultivation yield and quality.

[0004] The purpose of this application is to provide an intelligent control method for rare fungal cultivation rooms, including: The multi-dimensional coupled environmental parameters in the planting room are obtained. These parameters include temperature and humidity gradient values ​​in different areas, soil matrix conductivity, air flow vector, light spectrum distribution, and mycelial activity-microenvironment coupling parameters. These parameters are calculated by synchronously collecting the ATP content of the mycelial sticks, mycelial density, and local metabolic heat flux. The multidimensional coupled environmental parameters are compared with the fungal growth stage feature model in the dynamic growth model library. The fungal growth stage feature model includes the nonlinear coupling mapping relationship between mycelial spread rate, metabolic heat release and environmental parameters. The dynamic growth model library integrates multi-species growth data and historical regulation effect feedback. Based on the comparison results, multi-dimensional collaborative control instructions are output. These instructions include the fan turning angle and vortex intensity for different areas of the planting room, the spectral combination and phase difference of the supplementary lighting, the diameter of the mist particles and the spraying sequence of the spraying device, and the metabolic heat compensation coefficient of the substrate nutrient solution.

[0005] By adopting the above technical solution, environmental parameters (temperature and humidity gradient, substrate conductivity, etc.) in the cultivation room are deeply coupled with mycelial activity indicators (ATP content of the substrate, metabolic heat flux, etc.) into a multi-dimensional parameter system. This breaks the isolated barrier between environmental data and biological growth status in traditional regulation, enabling regulation decisions to directly anchor the actual growth needs of fungi and fundamentally avoid the problem of "parameters meeting standards but abnormal growth". At the same time, relying on a dynamic growth model library that integrates multi-species data and historical feedback, the current growth stage characteristics are accurately matched through nonlinear coupling mapping relationships, significantly improving the adaptability to different rare fungi and complex growth scenarios. Furthermore, by outputting multi-dimensional collaborative commands that include regionally oriented regulation parameters (fan vortex intensity, supplemental lighting phase difference, etc.), precise correction of local microenvironmental anomalies is achieved, effectively solving the problem of uneven development caused by mycelial respiration heterogeneity. Ultimately, this significantly improves the yield stability and quality uniformity of rare fungi cultivation, providing reliable technical support for their large-scale and standardized cultivation.

[0006] In one possible implementation of this application, when acquiring multi-dimensional coupled environmental parameters, to address the data drift problem caused by the superposition of condensate and mycelial respiration moisture from sensors within the growing room, the following operations are performed: Real-time acquisition of the operating temperature, humidity data collected by each humidity sensor, and the rate of change of carbon dioxide concentration in the corresponding area; The humidity collection value is compensated according to the preset drift correction algorithm. The drift correction algorithm includes the basic correction coefficient corresponding to the temperature change and the breathing water vapor interference correction coefficient corresponding to the carbon dioxide concentration change rate. The comprehensive compensation value is obtained by two-factor weighted calculation. The corrected environmental parameters are output as the basis for regulation. The drift type is determined by the temporal correlation between the rate of change of carbon dioxide concentration and humidity fluctuation, ensuring that the humidity data error is controlled within the preset error range.

[0007] By adopting the above technical solution, this method addresses the complex problem of data drift caused by the superposition of condensation and mycelial respiration moisture in the sensors within the growing room. It overcomes the limitations of traditional single-factor correction relying solely on temperature. By real-time correlation between the humidity sensor's operating temperature, humidity readings, and the corresponding area's carbon dioxide concentration change rate, the water vapor interference from mycelial respiration is incorporated into the compensation calculation as a correction coefficient. This achieves a two-factor weighted correction of both the basic temperature influence and the specific interference from respiration moisture. Simultaneously, by leveraging the temporal correlation between the carbon dioxide concentration change rate and humidity fluctuations, the type of drift is accurately determined, significantly improving the accuracy of humidity data acquisition and effectively controlling errors within a preset range. This precise environmental parameter correction provides a reliable data foundation for subsequent growth model comparison and control command output, avoiding control decision deviations caused by data drift. It ensures accurate perception and response to the sensitive growth environment of rare fungi from the source, further supporting the stability and controllability of the planting process.

[0008] In one possible implementation of this application, when outputting multi-dimensional collaborative regulation commands, the following operations are performed to address the local microenvironmental imbalance caused by hyphal respiration heterogeneity during the fungal primordium formation stage: A microenvironment heterogeneity map is constructed based on multi-dimensional coupled environmental parameters to identify abnormal regions where the temperature gradient exceeds a preset threshold and mycelial activity is lower than the baseline value. By combining airflow vectors and metabolic heat flux distribution, the required directional airflow angle, circulation volume, and vortex intensity parameters for the abnormal region are calculated. The vortex intensity is positively correlated with the local metabolic heat flux. The output fan group coordinates the operation command to create a spiral upward airflow in the abnormal area. The airflow vortex effect balances the temperature, humidity and oxygen distribution, and the airflow rate is controlled within a suitable range.

[0009] By adopting the above technical solution, this approach addresses the challenge of local microenvironmental imbalance caused by mycelial respiration heterogeneity during the critical stage of primordia formation in rare fungi. It overcomes the limitations of traditional unified global regulation, which cannot precisely intervene in local anomalies. First, a microenvironmental heterogeneity map is constructed based on multi-dimensional coupled environmental parameters, enabling precise localization of abnormal areas with "excessive temperature gradients and low mycelial activity," thus solving the blind spot of traditional regulation that "only knows that global parameters are met, but not local growth anomalies." Next, directional airflow parameters are calculated by combining airflow vectors and metabolic heat flux distribution, with vortex intensity dynamically adjusted according to local metabolic heat flux. This allows the regulatory action to directly match the microenvironmental disturbances generated by mycelial respiration, avoiding secondary environmental fluctuations caused by blindly supplying air. Finally, a spiral upward airflow is formed through the coordinated operation of a fan group, utilizing the vortex effect to efficiently balance the temperature, humidity, and oxygen distribution in abnormal areas. This ensures that the airflow rate is within the suitable range for primordia development and specifically resolves the local imbalance caused by mycelial respiration heterogeneity. This precise and dynamic local regulation method significantly improves the survival rate and development uniformity of primordia formation, effectively reduces problems such as primordia necrosis and uneven development caused by microenvironmental imbalance, lays a stable foundation for the subsequent development of fruiting bodies of rare fungi, and further ensures the consistency of planting yield and quality.

[0010] In one possible implementation of this application, when constructing the growth stage characteristic model in the dynamic growth model library, to address the problem that traditional models cannot quantify the correlation between fungal stress response and environmental disturbance, the following operations are performed: The respiratory metabolism data and spore release concentration change rate of fungi under sudden changes in environmental parameters were obtained, and the stress response coefficient was obtained by fusing the respiratory metabolism data and spore release concentration change rate. The stress response coefficient is introduced as a penalty factor into the model training process to establish a correlation function between the magnitude and duration of environmental disturbances and the degree of stress damage. The output includes a modified model containing dynamic stress thresholds. This modified model can identify risk levels and output pre-regulation instructions in advance based on the magnitude and duration of sudden changes in environmental parameters and stress response coefficients.

[0011] By adopting the above technical solution, a core breakthrough has been achieved, moving from "post-event adjustment" to "pre-event warning," addressing the limitations of traditional growth models that cannot quantify the correlation between fungal stress response and environmental disturbance and can only passively respond to parameter exceedances. First, by integrating respiratory metabolic data and spore release concentration change rates during sudden changes in environmental parameters, a stress response coefficient is obtained, transforming the abstract stress state of rare fungi into a quantifiable data indicator, thus solving the pain point of traditional models where stress responses are difficult to capture accurately. Then, this coefficient is introduced into model training as a penalty factor to establish a correlation function between the amplitude and duration of environmental disturbance and the degree of stress damage, enabling the model to learn stress patterns under different disturbance scenarios rather than relying on fixed threshold judgments. Finally, the output modified model, based on dynamic stress thresholds, can proactively identify risk levels and output pre-regulation instructions in advance by combining disturbance characteristics and stress response coefficients, preventing irreversible stress damage to rare fungi caused by sudden environmental changes. This regulatory logic, which deeply integrates stress mechanisms into the growth model, significantly improves the system's robustness to sudden disturbances. It effectively reduces problems such as primordium necrosis and mycelial activity decline caused by unexpected situations such as sudden temperature rises and falls and accumulation of harmful gases. It provides dynamically adapted model support for the stable growth of rare fungi throughout their entire life cycle, further ensuring the stability of planting yield and quality.

[0012] In one possible implementation of this application, when processing light spectrum data, the following operations are performed to address the coupling problem between the dynamic spectral requirements of different fungal growth stages and mycelial activity: The collected spectral distribution data was analyzed, and the proportion of light intensity and diurnal fluctuation patterns of characteristic wavelengths associated with activity were extracted by combining the hyphal ATP time-series data. Based on the optimal spectral ratio and the phase difference of the light cycle corresponding to the current growth stage, the supplementary light requirements for each wavelength and the pulse width modulation parameters are calculated. This phase difference of the light cycle is determined based on the mycelial metabolic thermal rhythm. It outputs pulse width modulation commands for multi-channel LED lights to achieve dynamic spectral adjustment, and the timing of supplemental lighting is synchronized with the peak period of mycelial activity.

[0013] By adopting the above technical solution, the problem of coupling the dynamic spectral requirements of different rare fungi at different growth stages with mycelial activity is addressed. This solution breaks through the crude mode of "fixed spectral ratio + uniform supplemental lighting sequence" in traditional light regulation: First, by analyzing spectral distribution data and combining it with mycelial ATP timing data, characteristic wavelengths directly related to activity, their light intensity ratios, and diurnal fluctuation patterns are accurately extracted. This establishes a quantitative correlation between spectral parameters and mycelial physiological activity, solving the problem of blind spectral selection lacking biological activity data support in traditional solutions. Then, based on the optimal spectral ratio for the current growth stage, supplemental lighting parameters are calculated by combining the phase difference of the light cycle determined by the mycelial metabolic thermal rhythm. This ensures that spectral adjustment not only matches the needs of the growth stage but also precisely adapts to the intrinsic physiological rhythm of the mycelium, avoiding interference with mycelial activity caused by non-rhythmic supplemental lighting. Finally, dynamic spectral adjustment is achieved through pulse width modulation of multi-channel LED lights, and the timing of supplemental lighting is synchronized with the peak period of mycelial activity, maximizing supplemental lighting efficiency and reducing energy waste caused by ineffective lighting. This three-in-one light regulation logic of "spectrum-activity-rhythm" can accurately meet the light needs of rare fungi at different growth stages, effectively promote mycelial germination, primordium differentiation and fruiting body maturation, reduce the problem of decreased activity caused by light stress, and improve the energy consumption efficiency of supplemental lighting, providing a light environment that is adapted to the physiological characteristics of rare fungi for high-quality growth.

[0014] In one possible implementation of this application, when regulating the soil matrix environment, to address the multi-factor coupled interference problem of matrix pH, metabolic heat, and nutrient concentration, the following operations are performed: Simultaneously acquire substrate conductivity, pH value and substrate temperature data, wherein the substrate temperature reflects the mycelial metabolic heat level; The combined influence of pH and matrix temperature on conductivity measurement is separated by a preset two-factor coupling matrix algorithm. This two-factor coupling matrix includes pH interference coefficients for different temperature ranges. It outputs precise nutrient solution ratios and temperature compensation commands, keeping the substrate pH value stable within a suitable range, maintaining the conductivity within the corresponding range, and dynamically correcting the nutrient solution temperature according to the substrate temperature.

[0015] By adopting the above technical solution, this method addresses the challenge of coupled interference between substrate pH, metabolic heat, and nutrient concentration in the cultivation of rare fungi. It overcomes the limitations of traditional substrate control methods that rely on "single parameter monitoring and independent command output." First, it simultaneously acquires substrate conductivity (reflecting nutrient concentration), pH (acidity / alkalinity), and substrate temperature (characterizing mycelial metabolic heat), incorporating all three into a unified monitoring dimension. This solves the problem of isolated parameter acquisition and inability to capture complex interference in traditional methods. Then, through a two-factor coupling matrix algorithm containing pH interference coefficients for different temperature ranges, it accurately separates the combined influence of pH and metabolic heat on conductivity measurement, avoiding the common error of "pH fluctuations due to temperature changes leading to misjudgment of nutrient concentration," making the assessment of substrate nutrient status more accurate. Finally, the output nutrient solution ratio command accurately corrects pH and nutrient concentration, and the nutrient solution temperature dynamically adjusts with substrate temperature. This ensures that substrate pH and nutrient concentration remain stable within suitable ranges, while metabolic heat compensation prevents the inhibition of nutrient absorption by excessively high or low local temperatures. This logic of "multi-parameter synchronous monitoring - coupling interference separation - dynamic precise regulation" effectively resolves the problem of inaccurate regulation caused by the mutual interference of multiple factors in the substrate environment. It avoids phenomena such as mycelial growth stagnation and primordium differentiation difficulties caused by nutrient supply imbalance, acid and alkali stress or metabolic heat accumulation. It provides a stable and suitable substrate microenvironment for rare fungi, further ensuring their growth consistency and quality stability. At the same time, it reduces the waste of nutrient solution caused by regulation deviation and improves planting efficiency.

[0016] In one possible implementation of this application, when optimizing the control strategy, the following operations are performed to address the multi-objective balance problem of energy consumption, mycelial activity, and yield during the planting cycle: Record the equipment energy consumption data, corresponding fungal growth rate and mycelial activity data under different control schemes, and calculate the energy consumption-activity benefit ratio. An energy consumption-activity benefit function is constructed by using reinforcement learning algorithms, and the regulation data of each region is integrated by combining a multi-regional data aggregation framework. The contribution of data from different regions is evaluated by using regional data weight coefficients. Output dynamic optimization control commands to reduce energy consumption per unit output by more than a preset percentage while ensuring that the daily output rate is not lower than the corresponding ratio of the benchmark value and the mycelial activity is maintained above the threshold. The revenue function parameters are updated monthly based on the aggregation results of multiple regions.

[0017] By adopting the above technical solution, this approach addresses the challenge of achieving a coordinated balance between energy consumption, mycelial activity, and yield in the cultivation of rare fungi. It overcomes the limitations of traditional control methods that prioritize a single objective (such as solely pursuing yield or simply reducing energy consumption), which often results in neglecting other aspects. First, by recording energy consumption, growth rate, and mycelial activity data under different schemes and calculating the energy consumption-activity benefit ratio, the abstract multi-objective balance is transformed into a quantifiable evaluation indicator, solving the problem of difficult-to-define multi-objective weights in traditional schemes. Then, a reward function is constructed using reinforcement learning algorithms, combined with a multi-regional data aggregation framework and regional weight coefficients. This allows the model to fully absorb the control experience of each region and distinguish the contribution of data, avoiding the one-sidedness of strategies caused by bias in single-regional data. Finally, the output dynamic optimization command, while strictly ensuring that the daily yield is not lower than the benchmark ratio and that mycelial activity is maintained above the threshold, achieves a significant reduction in energy consumption per unit yield. Furthermore, by updating the reward function parameters monthly based on the multi-regional aggregation results, the control strategy can dynamically adapt to changes in fungal growth characteristics and environmental fluctuations. This multi-objective optimization logic of "quantitative assessment-intelligent learning-dynamic adaptation" not only ensures the stability of the yield and quality of rare fungi, but also significantly improves energy utilization efficiency, reduces unnecessary energy waste, and achieves synergistic improvement of economic and ecological benefits, providing technical support for the sustainability of large-scale cultivation of rare fungi.

[0018] The second objective of this application is to provide an intelligent control system for rare fungi cultivation rooms, which includes: Multi-dimensional coupled environmental parameter acquisition module: Acquires multi-dimensional coupled environmental parameters in the planting room. The multi-dimensional coupled environmental parameters include temperature and humidity gradient values ​​in different areas, soil matrix conductivity, air flow vector, light spectrum distribution, and mycelial activity-microenvironment coupling parameters. The mycelial activity-microenvironment coupling parameters are calculated by synchronously collecting the ATP content of the mycelial sticks, mycelial density, and local metabolic heat flux. Fungal growth stage characteristic model comparison module: compares the multi-dimensional coupled environmental parameters with the fungal growth stage characteristic models in the dynamic growth model library. The fungal growth stage characteristic models include the nonlinear coupling mapping relationship between mycelial spread rate, metabolic heat release and environmental parameters. The dynamic growth model library integrates multi-species growth data and historical regulation effect feedback. Multi-dimensional collaborative control command output module: Outputs multi-dimensional collaborative control commands based on comparison results. The multi-dimensional collaborative control commands include the fan turning angle and vortex intensity for different areas of the planting room, the spectrum combination and phase difference of the supplementary light lamp, the mist particle diameter and spraying sequence of the spray device, and the metabolic heat compensation coefficient of the substrate nutrient solution.

[0019] By adopting the above technical solution, environmental parameters (temperature and humidity gradient, substrate conductivity, etc.) in the cultivation room are deeply coupled with mycelial activity indicators (ATP content of the substrate, metabolic heat flux, etc.) into a multi-dimensional parameter system. This breaks the isolated barrier between environmental data and biological growth status in traditional regulation, enabling regulation decisions to directly anchor the actual growth needs of fungi and fundamentally avoid the problem of "parameters meeting standards but abnormal growth". At the same time, relying on a dynamic growth model library that integrates multi-species data and historical feedback, the current growth stage characteristics are accurately matched through nonlinear coupling mapping relationships, significantly improving the adaptability to different rare fungi and complex growth scenarios. Furthermore, by outputting multi-dimensional collaborative commands that include regionally oriented regulation parameters (fan vortex intensity, supplemental lighting phase difference, etc.), precise correction of local microenvironmental anomalies is achieved, effectively solving the problem of uneven development caused by mycelial respiration heterogeneity. Ultimately, this significantly improves the yield stability and quality uniformity of rare fungi cultivation, providing reliable technical support for their large-scale and standardized cultivation.

[0020] The third objective of this application is to provide intelligent control equipment for rare fungi cultivation rooms, the equipment comprising: The system includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed to provide intelligent control of the above-mentioned rare fungi cultivation room.

[0021] The fourth objective of this application is to provide a storage medium.

[0022] The fourth objective of this application is achieved through the following technical solution: A storage medium storing a computer program capable of being loaded by a processor and executing the aforementioned intelligent control method for a rare fungi cultivation room.

[0023] In summary, this application includes at least one of the following beneficial technical effects: 1. By deeply coupling environmental parameters (temperature and humidity gradients, substrate conductivity, etc.) within the cultivation room with mycelial activity indicators (ATP content of the substrate, metabolic heat flux, etc.) into a multi-dimensional parameter system, this approach breaks down the isolation barrier between environmental data and biological growth status in traditional regulation. This allows regulatory decisions to directly anchor to the actual growth needs of fungi, fundamentally avoiding the problem of "parameters meeting standards but abnormal growth." Simultaneously, relying on a dynamic growth model library integrating multi-species data and historical feedback, it accurately matches the characteristics of the current growth stage through nonlinear coupling mapping relationships, significantly improving adaptability to different rare fungi and complex growth scenarios. Furthermore, by outputting multi-dimensional collaborative commands including regionally oriented regulation parameters (fan vortex intensity, supplemental lighting phase difference, etc.), it achieves precise correction of local microenvironmental anomalies, effectively solving the problem of uneven development caused by mycelial respiration heterogeneity. Ultimately, this significantly improves the yield stability and quality uniformity of rare fungi cultivation, providing reliable technical support for their large-scale and standardized cultivation.

[0024] 2. Addressing the complex issue of data drift caused by the superposition of condensation and mycelial respiration moisture in sensors within the growing room, this method overcomes the limitations of traditional single-factor correction based solely on temperature. By real-time correlation between the humidity sensor's operating temperature, humidity readings, and the corresponding area's carbon dioxide concentration change rate, the water vapor interference from mycelial respiration is incorporated into the compensation calculation as a correction coefficient. This achieves a two-factor weighted correction of both the fundamental influence of temperature and the specific interference from respiration moisture. Simultaneously, by leveraging the temporal correlation between the carbon dioxide concentration change rate and humidity fluctuations, the type of drift is accurately determined, significantly improving the accuracy of humidity data acquisition and effectively controlling errors within a preset range. This precise environmental parameter correction provides a reliable data foundation for subsequent growth model comparison and control command output, avoiding control decision deviations caused by data drift. It ensures accurate perception and response to the sensitive growth environment of rare fungi from the source, further supporting the stability and controllability of the planting process. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating the intelligent control method for a rare fungi cultivation room provided in this application embodiment; Figure 2 This is a virtual structural diagram of the intelligent control system for the rare fungi cultivation room provided in this application embodiment. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0028] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0029] This application provides an intelligent control method* for rare fungi cultivation rooms, referring to... Figure 1 The main process of the method is described as follows: S1: Obtain multi-dimensional coupled environmental parameters in the planting room. The multi-dimensional coupled environmental parameters include temperature and humidity gradient values ​​in different areas, soil matrix conductivity, air flow vector, light spectrum distribution, and mycelial activity-microenvironment coupling parameters. The mycelial activity-microenvironment coupling parameters are calculated by synchronously collecting the ATP content of the mycelial sticks, mycelial density, and local metabolic heat flux. The planting room needs to be divided into monitoring areas according to a pre-set grid. Taking a standard planting room of 10m×10m as an example, it can be divided into 25 independent monitoring areas of 2m×2m. Each area is equipped with an integrated sensor group to achieve synchronous acquisition of multiple parameters. Temperature and humidity gradient values ​​are obtained through a distributed temperature and humidity sensor array. The sensor accuracy needs to reach ±0.5℃ and ±2%RH, and the distance between adjacent sensors should be controlled within 1.5m. By calculating the parameter difference between adjacent collection points, the temperature and humidity gradient data in the vertical direction (from the substrate surface to a height of 1.5m) and the horizontal direction within the area are obtained respectively. Soil matrix conductivity is measured using an insertion soil sensor. The sensor has a measurement range of 0-10mS / cm and an accuracy of ±0.05mS / cm. One sensor is placed at 5cm, 10cm, and 15cm below the substrate surface in each area. The average value of the three measuring points is taken as the final value of the matrix conductivity of the area. Airflow vectors are acquired by a three-dimensional wind speed and direction sensor, which can simultaneously record wind speed (measurement range 0-10 m / s, accuracy ±0.1 m / s) and wind direction angles in the horizontal and vertical directions. Illumination spectral distribution is detected by a spectrometer covering a wavelength range of 300-800 nm with a resolution of 1 nm, automatically recording the light intensity percentage of each characteristic wavelength every hour. The mycelial activity-microenvironment coupling parameters need to be calculated using three synchronously detected data: the ATP content of the mycelial logs is measured using the luciferin-luciferase method with an ATP detector having a detection limit of 0.01 pmol, and the average value is taken from three randomly selected mycelial logs in each region; the mycelial density is counted using a 400x microscope, and the average number of mycelia in three fields of view is taken; the local metabolic heat flux is obtained by collecting the surface temperature field of the region using an infrared thermal imager (temperature range -20-150℃, accuracy ±0.3℃) and combining it with the matrix thermal conductivity coefficient; the three data are weighted and summed according to the weight coefficients of ATP content 0.4, mycelial density 0.3, and metabolic heat flux 0.3 to obtain the final mycelial activity-microenvironment coupling parameters.

[0030] S2: Compare the multi-dimensional coupled environmental parameters with the fungal growth stage feature model in the dynamic growth model library. The fungal growth stage feature model includes the nonlinear coupling mapping relationship between mycelial spread rate, metabolic heat release and environmental parameters. The dynamic growth model library integrates multi-species growth data and historical regulation effect feedback. The dynamic growth model library needs to be pre-constructed and iteratively optimized. It should contain growth stage characteristic models for at least five common and rare fungi, including morels, black truffles, and cordyceps militaris. Each model corresponds to four key growth stages: mycelial germination, primordium formation, fruiting body development, and mature harvest. During model construction, at least three complete planting cycles of measured data must be collected for each fungus, including mycelial spread rate (tracked using image recognition technology to track changes in mycelial coverage area, calculated in mm / d) and metabolic heat release (calculated by combining regional temperature difference and substrate heat capacity, in J / h), and correlated with environmental parameters such as temperature, humidity, light, and substrate conductivity during the same period. Nonlinear regression algorithms such as BP neural networks are used to train the data, establishing a nonlinear coupling mapping relationship between mycelial spread rate, metabolic heat release, and environmental parameters. Simultaneously, the dynamic growth model library needs to integrate historical regulation effect feedback data. After each regulation, the magnitude of environmental parameter changes and the fungal growth status within 24 hours (such as mycelial spread rate and ATP content changes) are recorded. Model parameters are updated monthly based on new data to improve adaptation accuracy. During the comparison process, the multi-dimensional coupling environment parameters obtained by S1 are input into the model library. By calculating the Euclidean distance between the real-time parameters and the feature models of each stage, the current growth stage of the fungus is determined. At the same time, the parameter deviation value is judged—a deviation value ≤5% is considered a good match, and a deviation value >5% is marked as a state that needs to be regulated.

[0031] S3: Output multi-dimensional collaborative control instructions based on the comparison results. The multi-dimensional collaborative control instructions include the fan turning angle and vortex intensity for different areas of the planting room, the spectrum combination and phase difference of the supplementary light lamp, the diameter of the mist particles and the spraying sequence of the spraying device, and the metabolic heat compensation coefficient of the substrate nutrient solution.

[0032] Based on the comparison deviation results of S2, differentiated multi-dimensional collaborative control commands are generated and output for different monitoring areas of the planting room. These commands are transmitted to the corresponding execution devices via an industrial bus (such as the Modbus protocol). Fan control commands must specify the fan turning angle (adjustable from 0-360°) and vortex intensity (levels 1-5, corresponding to wind speeds of 1-5 m / s). For example, for areas with excessive temperature and humidity gradients, a command of "turning angle 30°, vortex intensity level 3" is output, enabling directional airflow through fan group collaboration. Supplemental lighting control commands include spectral combinations and phase difference parameters. Multi-channel LED supplemental lights support independent adjustment of characteristic wavelengths such as 380nm, 450nm, and 660nm. The intensity of each wavelength is controlled by pulse width modulation (duty cycle 0-100%), and the phase difference is set according to the natural light cycle (e.g., ...). (The difference between sunrise and sunrise is 2 hours). The spray control commands involve the droplet diameter (adjustable from 0.1-0.5mm) and spray timing. The droplet size is controlled by adjusting the nozzle orifice diameter, and precise spraying with intervals of 5-30 minutes and single sprays of 10-30 seconds is achieved through solenoid valve timing control. The substrate nutrient solution control commands need to include the metabolic heat compensation coefficient (0.8-1.2) and nutrient ratio. The compensation coefficient is calculated based on the difference between the measured temperature and the ideal temperature of the substrate. The nutrient solution temperature is adjusted by the nutrient solution temperature control module (accuracy ±0.5℃), and the concentration ratio of nutrients such as nitrogen, phosphorus, and potassium is controlled by the infusion pump. To ensure control accuracy, the S1-S3 process is repeated every 30 minutes, and the control commands are dynamically corrected based on newly collected parameters.

[0033] Specifically, in some possible embodiments, when acquiring multi-dimensional coupled environmental parameters, to address the data drift problem caused by the superposition of condensate and mycelial respiration moisture from sensors within the growing room, the following operations are performed: Real-time acquisition of the operating temperature, humidity data collected by each humidity sensor, and the rate of change of carbon dioxide concentration in the corresponding area; The humidity collection value is compensated according to the preset drift correction algorithm. The drift correction algorithm includes the basic correction coefficient corresponding to the temperature change and the breathing water vapor interference correction coefficient corresponding to the carbon dioxide concentration change rate. The comprehensive compensation value is obtained by two-factor weighted calculation. The corrected environmental parameters are output as the basis for regulation. The drift type is determined by the temporal correlation between the rate of change of carbon dioxide concentration and humidity fluctuation, ensuring that the humidity data error is controlled within the preset error range.

[0034] First, a synchronous acquisition module is deployed to obtain key parameters: a temperature sensor (accuracy ±0.1℃) is integrated next to the humidity sensor (accuracy ±2%RH, response time ≤5s) in each monitoring area to acquire the sensor's operating temperature in real time (sampling frequency 1 time / 10s); at the same time, a non-dispersive infrared carbon dioxide sensor (measurement range 0-5000ppm, accuracy ±50ppm) is installed on the top of the corresponding area to record the rate of change of carbon dioxide concentration (calculate the concentration difference within adjacent 1 minute, unit ppm / min), and form a time-series correlation dataset with the humidity acquisition value (1 time / 10s).

[0035] Secondly, compensation calculations are performed using a pre-set drift correction algorithm: the basic correction coefficient is determined based on the influence of temperature on the humidity sensor. By experimentally collecting humidity measurement deviations at different temperatures within the 0-40℃ range, a temperature correction function is fitted (e.g., f(T)=k1×T²+k2×T+k3, where k1, k2, and k3 are fitting parameters, and T is the sensor's operating temperature); the respiratory water vapor interference correction coefficient is correlated with the rate of change of carbon dioxide concentration. Since the amount of water vapor released by mycelial respiration is positively correlated with carbon dioxide emissions, a correction coefficient function is obtained through historical data calibration (e.g., g(ΔCO2)=m×ΔCO2+n, where m and n are calibration parameters, and ΔCO2 is the rate of change of carbon dioxide concentration); in the two-factor weighted calculation, the weight of the basic temperature correction coefficient is set to 0.6, and the weight of the respiratory water vapor interference correction coefficient is set to 0.4. The comprehensive compensation value = (basic correction coefficient × 0.6 + respiratory water vapor interference correction coefficient × 0.4) + original humidity collection value.

[0036] Finally, the drift type is determined by time-series correlation and the correction results are output: if the rate of change of carbon dioxide concentration is significantly positively correlated with humidity fluctuation (correlation coefficient ≥ 0.7), it is determined to be drift dominated by mycelial respiration water vapor, and the weight of the respiration water vapor interference correction coefficient is strengthened to 0.5; if the correlation is ≤ 0.3, it is determined to be drift dominated by condensate water, and the weight of the temperature basis correction coefficient is strengthened to 0.7; the corrected data must meet the preset range of error ≤ ±1.5%RH. Through comparison and verification with a high-precision dew point meter (accuracy ±0.2℃ dew point temperature), it is ensured that the proportion of data with excessive correction error per hour is ≤ 3%. Finally, the corrected humidity parameters are incorporated into the multi-dimensional coupled environmental parameter system as the basis for subsequent control decisions.

[0037] Specifically, in some possible embodiments, when outputting multi-dimensional collaborative regulation instructions, the following operations are performed to address the local microenvironmental imbalance caused by hyphal respiration heterogeneity during the fungal primordium formation stage: A microenvironment heterogeneity map is constructed based on multi-dimensional coupled environmental parameters to identify abnormal regions where the temperature gradient exceeds a preset threshold and mycelial activity is lower than the baseline value. By combining airflow vectors and metabolic heat flux distribution, the required directional airflow angle, circulation volume, and vortex intensity parameters for the abnormal region are calculated. The vortex intensity is positively correlated with the local metabolic heat flux. The output fan group coordinates the operation command to create a spiral upward airflow in the abnormal area. The airflow vortex effect balances the temperature, humidity and oxygen distribution, and the airflow rate is controlled within a suitable range.

[0038] First, a microenvironmental heterogeneity map is constructed and abnormal regions are identified. Based on the multi-dimensional coupled environmental parameters obtained from S1, a gridded data interpolation algorithm (such as Kriging interpolation) is used to transform discrete data collection points into a continuously distributed two-dimensional map. The map includes temperature gradient distribution (unit: °C / m), mycelial activity distribution (expressed as a percentage of the baseline value), and metabolic heat flux distribution (unit: W / m²). Preset thresholds are set according to the characteristics of the target fungi. For example, the temperature gradient threshold during the primordium formation period of morel fungi is 2 °C / m, and the baseline value for mycelial activity is an ATP content of 20 pmol / g (based on the average activity during the primordium period of this fungus). When a region simultaneously meets the criteria of "temperature gradient > 2 °C / m" and "mycelial activity < 80% of the baseline value", it is marked as an abnormal region, and its boundary is located visually through the map (accuracy ±0.5m).

[0039] Secondly, the airflow control parameters required for the abnormal area are calculated: the aerodynamic simulation module is called, and the airflow vector (real-time wind speed and direction) and metabolic heat flux distribution data of the abnormal area are input. The directional airflow angle is calculated through fluid dynamics simulation—the fan delivery angle is determined by taking the center of the area as the origin and combining the surrounding airflow direction (deviation ≤ 5°) to ensure that the airflow can penetrate the core of the abnormal area; the circulation volume is calculated based on the area volume (length × width × height) and air replacement requirements. For example, an abnormal area of ​​1m³ needs to replace the air 8-10 times per hour; the vortex intensity adopts a 5-level system (levels 1-5), which is positively correlated with the local metabolic heat flux. The calculation formula is "vortex intensity level = (local metabolic heat flux / baseline metabolic heat flux) × 5" (the baseline metabolic heat flux is the average heat flux during the primordial period of the fungus, such as 15W / m²). That is, the higher the heat flux, the higher the vortex intensity level (not exceeding level 5) to enhance the heat diffusion effect.

[0040] Finally, output the coordinated operation instruction for the fan group: the fan group is arranged in a delta-shaped layout in the planting room (one steerable axial flow fan is configured per 10 m², with a wind speed adjustment range of 0.5-3 m / s and a steering angle of 0-360°). According to the calculated directional airflow angle, circulation volume and vortex intensity, coordinated instructions are output to 3-4 fans in the corresponding area — for example, for an abnormal area of 2m×2m, the north fan is controlled to steer to 30° and the east fan to steer to 120°, so as to form a spiraling upward airflow (clockwise rotation direction, ascending rate 0.3 m / s) through the wind speed difference (for example, the wind speed of the north fan is 1.2 m / s, and the wind speed of the east fan is 0.9 m / s); at the same time, the airflow rate is strictly controlled within the appropriate range of 0.8-1.2 m / s (to avoid damage to primordia caused by high-speed airflow), and the fan frequency is dynamically corrected through real-time wind speed sensor feedback (sampling frequency of 1 time / 5s), so as to ensure that the vortex effect can balance the temperature and humidity (deviation ≤1℃, ≤3%RH) and oxygen distribution (carbon dioxide concentration difference ≤200ppm) in the area. The regulation effect is verified by an infrared thermal imager and an oxygen sensor every 15 minutes until the parameters of the abnormal area return to the normal range.

[0041] Specifically, in some possible embodiments, when constructing the growth stage feature model in the dynamic growth model library, the following operations are performed to solve the problem that traditional models cannot quantify the correlation between fungal stress response and environmental disturbance: Obtain the respiratory metabolism data and the change rate of spore release concentration of fungi when environmental parameters change abruptly, and fuse the respiratory metabolism data and the change rate of spore release concentration to obtain a stress response coefficient; Introduce the stress response coefficient as a penalty factor into the model training process, and establish a correlation function between the amplitude and duration of environmental disturbance and the degree of stress damage; Output a modified model containing a dynamic stress threshold, which can identify the risk level and output pre-regulation instructions in advance according to the abrupt change amplitude and duration of environmental parameters and the stress response coefficient.

[0042] The stress response coefficient was obtained by selecting the primordium formation period of the target fungus (such as morel) as the key monitoring stage. An environmental parameter abrupt change simulation module was set up in the cultivation room, which could artificially trigger disturbances such as sudden temperature changes (±5℃ / 30min), sudden humidity changes (±15%RH / 30min), or sudden increases in carbon dioxide concentration (+1000ppm / 30min). Two core data points were collected simultaneously: ① Respiratory metabolic data: using a portable respiration rate meter (measurement range 0-500mL / h・kg, accuracy ±2%), the oxygen consumption and carbon dioxide release of the mushroom logs were recorded in real time, and the respiratory entropy (CO2 release / O2 consumption) was calculated as a respiratory metabolic indicator; ② Spore release concentration change rate: using an air sampler (flow rate 20L / min) combined with microscopic counting, the spore concentration was recorded every 10 minutes, and the concentration change rate (unit: spores / m³・min) between adjacent time periods was calculated. The two data points were weighted and fused according to the weight of "respiratory entropy 0.6 + spore release concentration change rate 0.4" to obtain the stress response coefficient (the value ranges from 0 to 1, and the larger the value, the stronger the stress response).

[0043] Secondly, a correlation function was constructed and a penalty factor was introduced: data from at least 50 historical stress events (covering different types, amplitudes, and durations of disturbances) were collected. The amplitude of environmental disturbances (e.g., temperature change ΔT, humidity change ΔH), duration t (in minutes), and corresponding stress damage level (expressed as the rate of decrease in mycelial activity after 24 hours) were recorded for each event. A random forest algorithm was used to train the model, and the stress response coefficient was embedded as a penalty factor into the loss function (loss value = basic prediction loss × (1 + stress response coefficient)). This strengthened the model's learning weight for high-stress scenarios, ultimately establishing a correlation function of "environmental disturbance amplitude × duration → stress damage level".

[0044] Finally, a modified model is output and pre-regulation is implemented: the modified model includes a dynamic stress threshold, which is dynamically adjusted according to the fungal growth stage (e.g., the temperature change threshold during the primordia stage is set to ±3℃ / 30min, and relaxed to ±4℃ / 30min during the fruiting body stage). During model operation, the magnitude and duration of sudden changes in environmental parameters and the stress response coefficient are input in real time, and the stress damage risk level is calculated through a correlation function (divided into low, medium, and high levels, corresponding to damage rates <5%, 5%-15%, and >15%). When identified as medium risk, pre-regulation instructions are output 30 minutes in advance (e.g., activating the buffer heating / cooling module, adjusting the fan speed); for high risk, enhanced regulation is implemented 60 minutes in advance (e.g., activating the backup temperature control system, increasing the humidity compensation frequency).

[0045] Specifically, in some possible embodiments, when processing light spectrum data, the following operations are performed to address the coupling issue between the dynamic spectral requirements of different fungal growth stages and mycelial activity: The collected spectral distribution data was analyzed, and the proportion of light intensity and diurnal fluctuation patterns of characteristic wavelengths associated with activity were extracted by combining the hyphal ATP time-series data. Based on the optimal spectral ratio and the phase difference of the light cycle corresponding to the current growth stage, the supplementary light requirements for each wavelength and the pulse width modulation parameters are calculated. This phase difference of the light cycle is determined based on the mycelial metabolic thermal rhythm. It outputs pulse width modulation commands for multi-channel LED lights to achieve dynamic spectral adjustment, and the timing of supplemental lighting is synchronized with the peak period of mycelial activity.

[0046] The process involved analyzing spectral data and extracting characteristic wavelength parameters: A high-resolution spectrometer (detection range 300-800nm, resolution 1nm, sampling frequency 1 time / 30min) was used to collect real-time spectral distribution data within the cultivation room. Simultaneously, an ATP detector (detection limit 0.01pmol) was used to record the temporal changes in mycelial ATP content (detected every 2 hours, continuously monitored for 72 hours to form a time-series curve). Pearson correlation coefficient analysis was used to calculate the correlation between light intensity at each wavelength and the ATP time-series data (|r|≥0.6 was considered a strong correlation). Characteristic wavelengths (e.g., 450nm blue light and 660nm red light during the morel primordia stage) were extracted, and the light intensity percentages of these wavelengths (e.g., 450nm 25%-30%, 660nm 40%-45%) and diurnal fluctuation patterns (e.g., 660nm light intensity peaks between 10:00-14:00 under natural light) were statistically analyzed.

[0047] Secondly, the supplemental lighting and modulation parameters are calculated: The optimal spectral ratio is preset according to the growth stage of the target fungus (e.g., during mycelial germination, 35% blue light and 25% red light are required; during primordium formation, the ratio is adjusted to 25% blue light and 45% red light). Combined with real-time spectral distribution data, the supplemental lighting requirements for each characteristic wavelength are calculated through the difference (e.g., if the current 450nm light intensity accounts for 20%, supplemental lighting needs to be increased to 25%, then the supplemental lighting increment is 5%). The phase difference of the illumination cycle is determined based on the mycelial metabolic thermal rhythm: Substrate temperature changes are recorded using an infrared thermal imager (sampling frequency 1 time / hour), and a diurnal metabolic thermal rhythm curve is fitted (e.g., the peak occurs between 14:00 and 16:00). The phase difference of the supplemental lighting cycle is set to be 1 hour earlier (i.e., supplemental lighting is enhanced starting at 13:00) to match the metabolically active period. The pulse width modulation parameters are calculated based on the supplementary lighting requirements. The duty cycle (0-100%) of the multi-channel LED lamp is positively correlated with the supplementary lighting increment (e.g., a 5% supplementary lighting increment corresponds to a 20% duty cycle), ensuring a light intensity adjustment accuracy of ±5%.

[0048] Finally, dynamic modulation commands are output and supplemental lighting timing is synchronized: Multi-channel LEDs are configured with independent channels based on characteristic wavelengths (e.g., 380nm, 450nm, 660nm, 730nm). Commands are output based on calculated pulse width modulation parameters (e.g., 20% duty cycle for the 450nm channel, 30% duty cycle for the 660nm channel), enabling real-time dynamic adjustment of the spectrum via a dimming controller. Supplemental lighting timing is strictly synchronized with the peak period of mycelial activity: The peak activity period (e.g., 9:00-11:00 AM) is determined based on ATP timing data. During this period, the supplemental lighting intensity is automatically increased (duty cycle increased by 10%-15%), and reduced to the baseline intensity during non-peak periods. Hourly data feedback from the spectrometer and ATP detector is used to correct modulation parameters, ensuring that the characteristic wavelength light intensity ratio deviation is ≤3%, and the synchronization error between supplemental lighting timing and peak activity is ≤15 minutes, ultimately achieving precise coupling between spectral regulation and mycelial physiological activity.

[0049] Specifically, in some possible embodiments, when regulating the soil matrix environment, the following operations are performed to address the multi-factor coupling interference problem of matrix pH, metabolic heat, and nutrient concentration: Simultaneously acquire substrate conductivity, pH value and substrate temperature data, wherein the substrate temperature reflects the mycelial metabolic heat level; The combined influence of pH and matrix temperature on conductivity measurement is separated by a preset two-factor coupling matrix algorithm. This two-factor coupling matrix includes pH interference coefficients for different temperature ranges. It outputs precise nutrient solution ratios and temperature compensation commands, keeping the substrate pH value stable within a suitable range, maintaining the conductivity within the corresponding range, and dynamically correcting the nutrient solution temperature according to the substrate temperature.

[0050] The process involves synchronously collecting core substrate parameters: Three-in-one sensors (integrating conductivity, pH, and temperature detection functions) are deployed at 5cm, 10cm, and 15cm below the surface of each substrate monitoring area (e.g., a 2m×2m grid) in the growing room. The conductivity measurement range is 0-10mS / cm (accuracy ±0.05mS / cm), the pH measurement range is 4.0-8.0 (accuracy ±0.02pH), and the temperature measurement range is 5-40℃ (accuracy ±0.1℃). The sampling frequency is set to once every 10 minutes to acquire substrate conductivity (reflecting nutrient concentration), pH (acidity / alkalinity), and substrate temperature (indirectly characterizing mycelial metabolic heat level) in real time. These data are then aggregated via a data bus to form a three-dimensional parameter matrix (space × time × parameter).

[0051] Secondly, the combined effects are separated by a two-factor coupling matrix algorithm: the preset two-factor coupling matrix is ​​constructed according to temperature range (5-10℃, 10-15℃, ..., 35-40℃, each 5℃ is a range) and pH range (4.0-4.5, 4.5-5.0, ..., 7.5-8.0, each 0.5pH is a range). The matrix elements are the pH interference coefficients of the corresponding ranges (calibrated by previous experiments, such as 0.92 in the 10-15℃ range and pH 5.0-5.5, representing the degree of influence of pH on conductivity measurement under this condition). During algorithm execution, the target interval in the matrix is ​​first located based on the real-time matrix temperature and pH value, and the corresponding pH interference coefficient is extracted. Then, the total interference is calculated using the formula "composite influence value = (matrix temperature - reference temperature) × temperature coefficient + (measured pH - reference pH) × pH interference coefficient" (reference temperature is set to 20℃, reference pH is set to 6.0, and temperature coefficient is 0.03mS / cm・℃). Finally, the measured conductivity is subtracted from the composite influence value to obtain the conductivity value corresponding to the true nutrient concentration after removing coupling interference.

[0052] Finally, precise control commands are output: based on the substrate requirements of the target fungi (e.g., morel mushrooms thrive at pH 5.5-6.5 with an electrical conductivity of 1.5-2.5 mS / cm), the nutrient solution adjustment amount is calculated. If the pH is too high (e.g., 6.8), a citric acid solution ratio command is output (0.1% concentration, 500 mL sprayed per square meter of substrate); if the electrical conductivity is too low (e.g., 1.2 mS / cm), a nitrogen, phosphorus, and potassium mixed nutrient solution ratio command is output (N:P:K=3:1:2, 0.8% concentration, 800 mL drip-irrigated per square meter). Simultaneously, the nutrient solution temperature is dynamically corrected based on the substrate temperature: the nutrient solution temperature is adjusted to within the range of "substrate temperature ±1℃" using the nutrient solution temperature control module (accuracy ±0.3℃) (e.g., when the substrate temperature is 22℃, the nutrient solution temperature is controlled at 21-23℃) to avoid excessive temperature differences stimulating the mycelium. The control effect is verified by sensor feedback every 30 minutes to ensure that pH fluctuation is ≤ ±0.2 and conductivity fluctuation is ≤ ±0.1 mS / cm, ultimately achieving synergistic stability of multiple factors in the matrix environment.

[0053] Specifically, in some possible embodiments, when optimizing the control strategy, the following operations are performed to address the multi-objective balance problem of energy consumption, mycelial activity, and yield during the planting cycle: Record the equipment energy consumption data, corresponding fungal growth rate and mycelial activity data under different control schemes, and calculate the energy consumption-activity benefit ratio. An energy consumption-activity benefit function is constructed by using reinforcement learning algorithms, and the regulation data of each region is integrated by combining a multi-regional data aggregation framework. The contribution of data from different regions is evaluated by using regional data weight coefficients. Output dynamic optimization control commands to reduce energy consumption per unit output by more than a preset percentage while ensuring that the daily output rate is not lower than the corresponding ratio of the benchmark value and the mycelial activity is maintained above the threshold. The revenue function parameters are updated monthly based on the aggregation results of multiple regions.

[0054] The system establishes a multi-dimensional data recording and benefit ratio calculation system: A smart energy consumption monitoring module is deployed in the growing room. Through smart meters (accuracy ±0.5%) and power sensors of fans / supplementary lighting / pumps (sampling frequency 1 time / minute), hourly energy consumption data (unit: kWh) corresponding to different control schemes (such as fan speed combinations, supplementary lighting duration, nutrient solution supply, etc.) is recorded in real time. Simultaneously, an image recognition system (resolution 1920×1080, sampling frequency 1 time / 24 hours) calculates the fungal growth rate (unit: g / m²・d), and an ATP detector (detection limit 0.01 pmol) measures mycelial activity (unit: pmol / g). Based on the recorded data, the energy consumption-activity benefit ratio is calculated using the formula: "Benefit Ratio = (Growth Rate × Mycelial Activity) / Energy Consumption." The growth rate and mycelial activity are standardized from 0 to 1 (eliminating dimensional influences) to control the benefit ratio value within the range of 0-100, facilitating horizontal comparison.

[0055] Secondly, a reinforcement learning model and multi-region data aggregation framework are constructed: a deep Q-network (DQN) is used as the core of the reinforcement learning algorithm. The current environmental parameters (temperature, humidity, substrate state, etc.) + energy consumption / activity / yield data of each region are used as the state input, and the combination of control parameters such as fan speed, supplemental lighting duty cycle, and nutrient solution flow rate are used as the action output. The reward function is "maximizing the profit ratio" (reward value = current profit ratio - historical average profit ratio). During multi-region data aggregation, weight coefficients are set for each region (range 0-1, summing to 1). The weights are based on historical data: regions with high yield stability (coefficient of variation < 10%) and good energy efficiency (energy consumption per unit yield lower than the average) are given high weights (e.g., 0.15), while regions with large fluctuations are given low weights (e.g., 0.05). By weighted summation, the data from each region is integrated to avoid interference from outliers in a single region on the model.

[0056] Finally, dynamic optimization instructions are output and parameter iterations are implemented: Core constraints are set—daily yield should not be lower than 90% of the baseline value (the baseline value is the historical average daily yield of the fungus, such as 0.8 kg / m²·d for morels), and mycelial activity should be maintained above the threshold (e.g., 15 pmol / g). The reinforcement learning model outputs optimization control instructions hourly (e.g., reducing the average fan speed from 2000 r / min to 1800 r / min, adjusting the supplementary lighting duty cycle from 60% to 55%), which are executed and the effects are recorded by the industrial controller. Monthly updates of the reward function parameters (e.g., adjusting the weight ratio of energy consumption and activity in the reward function) are based on multi-region aggregated full-cycle data (energy consumption, activity, yield) to ensure the model adapts to changes in fungal growth characteristics. Experimental verification shows that this strategy can reduce energy consumption per unit yield by more than 15% while keeping daily yield fluctuations within ±5%, achieving synergistic optimization of energy consumption and growth efficiency, provided the constraints are met.

[0057] Another embodiment of this application provides an intelligent control system for a rare fungus cultivation room, wherein, see reference Figure 2 An intelligent control system for a rare fungus cultivation room includes: Multi-dimensional coupled environmental parameter acquisition module 100: Acquires multi-dimensional coupled environmental parameters in the planting room. The multi-dimensional coupled environmental parameters include temperature and humidity gradient values ​​in different areas, soil matrix electrical conductivity, air flow vector, light spectrum distribution, and mycelial activity-microenvironment coupling parameters. The mycelial activity-microenvironment coupling parameters are calculated by synchronously collecting the ATP content of the mycelial sticks, mycelial density, and local metabolic heat flux. Fungal growth stage characteristic model comparison module 200: compares the multi-dimensional coupled environmental parameters with the fungal growth stage characteristic models in the dynamic growth model library. The fungal growth stage characteristic models include the nonlinear coupling mapping relationship between mycelial spread rate, metabolic heat release and environmental parameters. The dynamic growth model library integrates multi-species growth data and historical regulation effect feedback. Multi-dimensional collaborative control command output module 300: Outputs multi-dimensional collaborative control commands based on comparison results. The multi-dimensional collaborative control commands include the fan turning angle and vortex intensity for different areas of the planting room, the spectrum combination and phase difference of the supplementary light lamp, the diameter of the mist particles and the spraying sequence of the spraying device, and the metabolic heat compensation coefficient of the substrate nutrient solution.

[0058] The intelligent control system for the rare fungi cultivation room provided in this embodiment can realize the steps of the aforementioned embodiment due to the functions of each module and the logical connection between them. Therefore, it can achieve the same technical effect as the aforementioned embodiment. For the principle analysis, please refer to the relevant description of the steps of the intelligent control method for the rare fungi cultivation room, which will not be repeated here.

[0059] This application embodiment also provides an intelligent control device for a rare fungi cultivation room, including a memory and a processor. The memory stores a computer program that can be loaded by the processor and executed by the above-described intelligent control method for a rare fungi cultivation room.

[0060] This application embodiment also provides a storage medium, wherein a computer program is stored that can be loaded by a processor and executed to perform the above-described intelligent control method for the cultivation room of rare fungi.

[0061] The storage medium provided in this embodiment can achieve the same technical effect as the aforementioned embodiments because the computer program therein, after being loaded and run on the processor, will implement the various steps of the aforementioned embodiments. For the principle analysis, please refer to the relevant description of the aforementioned method steps, which will not be repeated here.

[0062] The storage medium includes, for example, various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0063] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0064] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0065] Furthermore, features defined by the terms "first" and "second" may explicitly or implicitly include at least one of those features. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., and unless otherwise explicitly specified, is used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features.

[0066] Therefore, any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0067] The embodiments described in this specific implementation are preferred embodiments of this application and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. An intelligent control method for a rare mushroom cultivation house, characterized in that, include: Multi-dimensional coupled environmental parameters within the growing room are acquired. These parameters include temperature and humidity gradients in different areas, soil matrix conductivity, airflow vectors, light spectrum distribution, and mycelial activity-microenvironment coupling parameters. These parameters are calculated using synchronously collected data on ATP content of the mycelial logs, mycelial density, and local metabolic heat flux. To address data drift caused by the superposition of condensate and mycelial respiration moisture from sensors within the growing room, the following steps are performed: Real-time acquisition of the operating temperature, humidity readings, and corresponding carbon dioxide concentration change rates of each humidity sensor; compensation calculation of the humidity readings based on a preset drift correction algorithm, which includes a basic correction coefficient for temperature changes and a respiration moisture interference correction coefficient for carbon dioxide concentration change rates. A comprehensive compensation value is obtained through a two-factor weighted calculation; the corrected environmental parameters are output as a control basis. The drift type is determined by the temporal correlation between carbon dioxide concentration change rates and humidity fluctuations, ensuring that humidity data errors are controlled within a preset error range. The multi-dimensional coupled environmental parameters are compared with the fungal growth stage feature models in the dynamic growth model library. These models include a nonlinear coupling mapping relationship between mycelial spread rate, metabolic heat release, and environmental parameters. The dynamic growth model library integrates multi-species growth data and historical regulatory effect feedback. When constructing the growth stage feature models in the dynamic growth model library, to address the problem that traditional models cannot quantify the correlation between fungal stress response and environmental disturbance, the following steps are performed: Respiratory metabolic data and spore release concentration change rate of fungi during sudden changes in environmental parameters are obtained; the respiratory metabolic data and spore release concentration change rate are fused to obtain a stress response coefficient; the stress response coefficient is introduced as a penalty factor into the model training process to establish a correlation function between the amplitude and duration of environmental disturbance and the degree of stress damage; a corrected model containing a dynamic stress threshold is output. This corrected model can identify the risk level and output pre-regulation instructions in advance based on the amplitude and duration of sudden changes in environmental parameters and the stress response coefficient. Based on the comparison results, multi-dimensional collaborative control commands are output. These commands include fan turning angles and vortex intensity for different areas of the growing room, supplementary lighting spectral combinations and phase differences, spray device droplet diameters and spraying sequences, and the metabolic heat compensation coefficient of the substrate nutrient solution. When outputting multi-dimensional collaborative control commands, the following operations are performed to address the local microenvironmental imbalance caused by mycelial respiration heterogeneity during the fungal primordia formation stage: a microenvironmental heterogeneity map is constructed based on multi-dimensional coupled environmental parameters to identify abnormal areas where the temperature gradient exceeds a preset threshold and mycelial activity is lower than a baseline value; the required directional airflow angle, circulation volume, and vortex intensity parameters for the abnormal areas are calculated by combining airflow vectors and metabolic heat flux distribution, where the vortex intensity is positively correlated with local metabolic heat flux; and a collaborative operation command for the fan group is output to create a spiral upward airflow in the abnormal areas, balancing temperature, humidity, and oxygen distribution through the airflow vortex effect, and controlling the airflow rate within a suitable range.

2. The intelligent regulation method of the rare fungus cultivation room according to claim 1, characterized in that, When processing light spectrum data, to address the coupling issue between the dynamic spectral requirements of different fungal growth stages and mycelial activity, the following operations are performed: The collected spectral distribution data was analyzed, and the light intensity ratio and diurnal fluctuation pattern of characteristic wavelengths associated with activity were extracted by combining the hyphal ATP time series data. Based on the optimal spectral ratio and the phase difference of the light cycle corresponding to the current growth stage, the supplementary light requirements for each wavelength and the pulse width modulation parameters are calculated. This phase difference of the light cycle is determined based on the mycelial metabolic thermal rhythm. It outputs pulse width modulation commands for multi-channel LED lights to achieve dynamic spectral adjustment, and the timing of supplemental lighting is synchronized with the peak period of mycelial activity. 3.The method of claim 1, wherein the method further comprises: determining a temperature of the rare fungus; and controlling the temperature of the rare fungus based on the determined temperature. When regulating the soil matrix environment, to address the multi-factor coupled interference problem of matrix pH, metabolic heat, and nutrient concentration, the following operations are performed: Simultaneously acquire substrate conductivity, pH value and substrate temperature data, wherein the substrate temperature reflects the mycelial metabolic heat level; The combined influence of pH and matrix temperature on conductivity measurement is separated by a preset two-factor coupling matrix algorithm. This two-factor coupling matrix includes pH interference coefficients for different temperature ranges. It outputs precise nutrient solution ratios and temperature compensation commands, keeping the substrate pH value stable within a suitable range, maintaining the conductivity within the corresponding range, and dynamically correcting the nutrient solution temperature according to the substrate temperature. 4.The method of claim 1, wherein the method further comprises: determining a temperature of the rare fungus; and controlling the temperature of the rare fungus based on the determined temperature. When optimizing the control strategy, to address the multi-objective balance between energy consumption, mycelial activity, and yield during the planting cycle, the following operations should be performed: Record the equipment energy consumption data, corresponding fungal growth rate and mycelial activity data under different control schemes, and calculate the energy consumption-activity benefit ratio. An energy consumption-activity benefit function is constructed by using reinforcement learning algorithms, and the regional regulation data are integrated by combining a multi-regional data aggregation framework. The contribution of data from different regions is evaluated by using regional data weight coefficients. Output dynamic optimization control commands to reduce energy consumption per unit output by more than a preset percentage while ensuring that the daily output rate is not lower than the corresponding ratio of the benchmark value and the mycelial activity is maintained above the threshold. The revenue function parameters are updated monthly based on the aggregation results of multiple regions.

5. An intelligent control system for a rare mushroom cultivation house, characterized in that, include: Multi-dimensional Coupled Environmental Parameter Acquisition Module: Acquires multi-dimensional coupled environmental parameters within the growing room, including temperature and humidity gradient values ​​in different areas, soil matrix conductivity, airflow vector, light spectrum distribution, and mycelial activity-microenvironment coupling parameters. These parameters are calculated using synchronously collected data on mycelial ATP content, mycelial density, and local metabolic heat flux. When acquiring these parameters, to address data drift caused by the superposition of condensate and mycelial respiration moisture from sensors within the growing room, the following operations are performed: Real-time acquisition of the operating temperature, humidity readings, and corresponding carbon dioxide concentration change rates of each humidity sensor; Compensation calculation of the humidity readings based on a preset drift correction algorithm, which includes a basic correction coefficient corresponding to temperature changes and a respiration moisture interference correction coefficient corresponding to the carbon dioxide concentration change rate, with a comprehensive compensation value obtained through dual-factor weighted calculation; Outputting the corrected environmental parameters as a control basis, where the drift type is determined by the temporal correlation between the carbon dioxide concentration change rate and humidity fluctuations, ensuring that humidity data errors are controlled within a preset error range. The fungal growth stage characteristic model comparison module compares the multi-dimensional coupled environmental parameters with the fungal growth stage characteristic models in the dynamic growth model library. These models include a nonlinear coupling mapping relationship between mycelial spread rate, metabolic heat release, and environmental parameters. The dynamic growth model library integrates multi-species growth data and historical regulatory effect feedback. When constructing the growth stage characteristic models in the dynamic growth model library, to address the problem that traditional models cannot quantify the correlation between fungal stress response and environmental disturbance, the following operations are performed: Respiratory metabolic data and spore release concentration change rate of fungi during sudden changes in environmental parameters are obtained; the respiratory metabolic data and spore release concentration change rate are fused to obtain a stress response coefficient; the stress response coefficient is introduced as a penalty factor into the model training process to establish a correlation function between the amplitude and duration of environmental disturbance and the degree of stress damage; a corrected model containing a dynamic stress threshold is output. This corrected model can identify the risk level and output pre-regulation instructions in advance based on the amplitude and duration of sudden changes in environmental parameters and the stress response coefficient. Multi-dimensional collaborative control command output module: Based on the comparison results, it outputs multi-dimensional collaborative control commands, which include the fan turning angle and vortex intensity, supplementary lighting spectral combination and phase difference, spray device droplet diameter and spraying sequence, and the metabolic heat compensation coefficient of the substrate nutrient solution for different areas of the growing room. When outputting multi-dimensional collaborative control commands, it performs the following operations to address the local microenvironment imbalance caused by mycelial respiration heterogeneity during the fungal primordia formation stage: Based on multi-dimensional coupled environmental parameters, it constructs a microenvironment heterogeneity map to identify abnormal areas where the temperature gradient exceeds a preset threshold and mycelial activity is lower than the baseline value; Combining airflow vectors and metabolic heat flux distribution, it calculates the required directional airflow angle, circulation volume, and vortex intensity parameters for the abnormal areas, where the vortex intensity is positively correlated with the local metabolic heat flux; It outputs a collaborative operation command for the fan group to form a spiral upward airflow in the abnormal areas, balancing temperature, humidity, and oxygen distribution through the airflow vortex effect, and controlling the airflow rate within a suitable range.

6. An intelligent control device for a rare fungal cultivation room, characterized in that, include: The memory and processor, wherein the memory stores a computer program that can be loaded by the processor and executed as described in any one of claims 1-4 for the intelligent control method of the rare fungi cultivation room.

7. A storage medium, characterized in that, The computer program is stored and can be loaded by a processor and executed as described in any one of claims 1-4 for the intelligent control method of the rare fungi cultivation room.

Citation Information

Patent Citations

  • Intelligent temperature and humidity regulation and control fungus cultivation method for edible fungus sticks

    CN120359963A

  • Energy-saving refrigeration method based on fungus planting room and related equipment

    CN121230349A