An intelligent coupling model-based adaptive control system for pleurotus geesterum fruiting room

Abstract

The application provides a smart coupling model-based adaptive control system for a pleurotus geesterum fruiting room, and relates to the field of intelligent agricultural environment control, which identifies the mutual influence relationship between environmental parameters by constructing a cascade interference prediction matrix, and uses a phased fine adjustment strategy and a preset compensation mechanism to offset the cascade interference effect in the adjustment process. In this way, the mutual interference and fluctuation amplitude in the environmental parameter adjustment process can be significantly reduced, the development abnormalities caused by environmental instability during the differentiation period of the mushroom body can be effectively avoided, the success rate of pleurotus geesterum fruiting body differentiation and the quality consistency can be improved, and the precise and stable control of the fruiting room environment can be realized.

Description

Technical Field

[0001] This invention relates to the field of intelligent agricultural environmental control, and more specifically, to an adaptive control system for mushroom growing rooms based on an intelligent coupling model. Background Technology

[0002] As a high-value edible fungus, oyster mushrooms have extremely stringent environmental requirements for growth, primarily including temperature, humidity, and carbon dioxide (CO2) concentration. Currently, environmental control system technology is widely used in modern agriculture for edible fungus cultivation, especially for the environmental control of fruiting houses. However, traditional environmental control models often rely on univariate regulation, independently controlling temperature, humidity, or CO2 concentration. This method ignores the complex coupling relationships between environmental factors, often leading to energy waste and poor control effects. In recent years, with the innovative development of IoT technology, sensor technology, and artificial intelligence models, research on intelligent control targeting coupling relationships has gradually become a hot topic in the field of edible fungus cultivation. Some studies have attempted to optimize the fruiting house environment using multivariate system analysis theory. For example, neural networks and fuzzy control methods are used to optimize the regulation accuracy of certain specific factors, but these methods still face many challenges and are significantly far from achieving truly efficient, adaptive, and comprehensive environmental control.

[0003] Existing technologies have the following limitations: First, regarding coupling issues, traditional control methods cannot effectively predict the coupling interference effects between environmental factors such as temperature, humidity, and CO2 concentration. For example, when adjusting temperature, there is a lack of quantitative analysis of its response characteristics to humidity sensors and its impact on the spatial distribution of CO2 concentration. This neglect of coupling mechanisms easily leads to secondary interference effects during multi-factor control, thereby interfering with the stability and accuracy of the system. Second, in terms of control strategies, traditional control methods rely more on manual experience or linear control algorithms, which can only cope with simple environmental changes and cannot formulate highly adaptive control plans based on the complex dynamic characteristics of environmental parameter changes. Especially in microenvironments such as oyster mushroom growing rooms where multi-factor coupling is severe and dynamic, existing technologies often struggle to achieve real-time, fine-grained adjustment of environmental parameters. Third, regarding control accuracy, sensor measurement offsets and environmental disturbances usually reduce the accuracy of the environmental control system. Existing technologies lack compensation mechanisms for these problems, ultimately affecting the growth efficiency and quality of oyster mushrooms. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides an adaptive control system for the mushroom growing room of *Pleurotus ostreatus* based on an intelligent coupling model. This system, to a certain extent, solves the problem of the superimposed effect of humidity sensor measurement offset caused by temperature regulation and uneven CO2 concentration distribution caused by humidity regulation during the transition from the primordia formation stage to the fruiting body development stage of *Pleurotus ostreatus*, which leads to a cascading interference effect in parameter regulation and makes it impossible to guarantee the coordinated and stable environmental parameters during the mushroom differentiation stage.

[0005] According to one aspect of the present invention, an adaptive control system for a mushroom growing room based on an intelligent coupling model is provided, comprising: The environmental parameter monitoring unit is used to collect environmental parameter data such as temperature, humidity, and CO2 concentration in the mushroom house in real time, and to establish a layered and zoned sensor monitoring network. A smart coupling model is used to calculate the degree of influence of temperature changes on the response characteristics of humidity sensors and the perturbation intensity of humidity regulation on the spatial distribution of CO2 concentration, and to generate a cascaded interference prediction matrix. The interference path analysis unit is used to determine the direction and intensity of interference propagation among various parameters during environmental regulation, distinguish between primary and secondary interference paths and establish interference propagation mechanisms; construct the mutual compensation relationship among the three factors of temperature, humidity and CO2, and determine the timing arrangement of regulation to suppress cascade effects. The compensation and control unit is used to implement phased and refined adjustment of each environmental factor according to the control sequence arrangement, and to offset the sensor measurement offset and concentration distribution disturbance by preset compensation amount, so as to form a coordinated and stable environmental control process. An adaptive optimization unit is used to dynamically adjust the calculation accuracy of the cascade interference prediction matrix according to the actual performance of the cascade interference, so as to realize adaptive and precise control of the mushroom growing room environment.

[0006] Furthermore, the intelligent coupling model includes a temperature sensitivity analysis module, a statistical correlation analysis module, and a coupling relationship calculation module; The intelligent coupling model analyzes the correlation strength between temperature changes and humidity sensor measurement deviations, as well as the influence of humidity adjustment actions on CO2 concentration distribution changes, quantifies the coupling influence coefficients between various parameters, and generates a cascaded interference prediction matrix.

[0007] Furthermore, the temperature sensitivity analysis module processes temperature change parameters and calculates the influence coefficient of temperature fluctuation on the response characteristics of the humidity sensor; The statistical correlation analysis module processes the humidity regulation intensity parameter and calculates the correlation coefficient between humidity regulation operation and CO2 concentration distribution based on historical data. The coupling relationship calculation module performs comprehensive calculations on the influence coefficient and the correlation coefficient with the current environmental state parameters to generate a cascaded interference prediction matrix that describes the intensity of mutual influence and propagation path between the parameters.

[0008] Furthermore, the cascaded interference prediction matrix generated by the intelligent coupling model is shown in the following equation: in, To influence source parameters For target parameters In the transmission delay The following are the elements of the cascaded interference prediction matrix. To standardize the influence coefficient of temperature on humidity sensors, For the standardized current temperature offset, The correlation coefficient between humidity regulation and CO2 concentration changes is given. To standardize the current intensity of humidity control demand, A standardized cross-correlation function is used to calculate the combined effect of direct and indirect influences. To affect the transmission delay, For discrete time steps, The decay time constant is indirectly affected and >0, is the base of the natural logarithm.

[0009] Furthermore, the interference path analysis unit sorts all elements in the cascaded interference prediction matrix output by the intelligent coupling model in descending order of influence intensity, selects the top-ranked paths as the main interference propagation paths, and forms a priority sequence.

[0010] Furthermore, the compensation and control unit directly maps the influence coefficients and correlation coefficients output by the intelligent coupling model to sensor calibration parameters and CO2 supply adjustment parameters according to a fixed conversion ratio, thereby initiating compensation measures in advance to counteract sensor measurement offsets and concentration distribution disturbances before the actual occurrence of interference effects.

[0011] Furthermore, the compensation control unit maps the correlation coefficient to the supply adjustment compensation parameter as shown in the following formula: in, Adjusting compensation parameters for CO2 supply The correlation coefficient between humidity regulation and CO2 concentration distribution is given. The preset opening conversion factor is used to achieve a linear correspondence between the correlation coefficient and the CO2 supply port opening adjustment amount. A preset time conversion factor is used to realize the proportional mapping relationship between the correlation coefficient and the gas supply time extension. The hyperbolic tangent function is used to maintain the continuity of the original numerical values ​​of the correlation coefficients in the aperture compensation process. This is the error function.

[0012] According to another aspect of the present invention, an adaptive control method for a mushroom growing room based on an intelligent coupling model is provided, comprising: It receives temperature, humidity, and CO2 concentration data from the mushroom growing room, calculates the impact of temperature changes on the response characteristics of the humidity sensor and the disturbance intensity of humidity regulation on the spatial distribution of CO2 concentration through an intelligent coupling model, and generates a cascaded interference prediction matrix. Based on the cascade interference prediction matrix, the main interference propagation paths in the parameter adjustment process are identified, the mutual compensation relationship among the three factors of temperature, humidity and CO2 is constructed, and the timing arrangement for suppressing the cascade effect is determined. According to the aforementioned control sequence, each environmental factor is subject to phased and refined regulation. The sensor measurement offset and concentration distribution disturbance are offset by preset compensation amount, forming a coordinated and stable environmental control process. The system monitors the changes in environmental parameters during the mushroom differentiation period in real time, and dynamically adjusts the calculation accuracy of the cascade interference prediction matrix based on the actual performance of the cascade interference, thereby achieving adaptive and precise control of the mushroom growing room environment.

[0013] Compared with existing technologies, the adaptive control system for the fruiting room of *Pleurotus ostreatus* based on an intelligent coupling model provided by this invention identifies the mutual influence relationships between environmental parameters by constructing a cascaded interference prediction matrix, and uses a phased refined adjustment strategy and a preset compensation mechanism to counteract the cascaded interference effects during the adjustment process. This significantly reduces the mutual interference and fluctuation amplitude during the adjustment of environmental parameters, effectively avoids developmental abnormalities caused by environmental instability during the fruiting body differentiation period, thereby improving the success rate and quality consistency of *Pleurotus ostreatus* fruiting body differentiation, and achieving precise and stable control of the fruiting room environment. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings: Figure 1 This is a system block diagram of an adaptive control system for a mushroom growing room based on an intelligent coupling model, according to an embodiment of the present invention.

[0015] Figure 2 This is a block diagram of the patient puncture site data analysis module in the adaptive control system for the mushroom growing room based on an intelligent coupling model according to an embodiment of the present invention. Detailed Implementation

[0016] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0017] Figure 1 This is a system block diagram of an adaptive control system for a mushroom growing room based on an intelligent coupling model, according to an embodiment of the present invention. Figure 1 As shown, the adaptive control system for the mushroom growing room of Oyster mushroom based on the intelligent coupling model includes: The environmental parameter monitoring unit is used to collect environmental parameter data such as temperature, humidity, and CO2 concentration in the mushroom house in real time, and to establish a layered and zoned sensor monitoring network. A smart coupling model is used to calculate the degree of influence of temperature changes on the response characteristics of humidity sensors and the perturbation intensity of humidity regulation on the spatial distribution of CO2 concentration, and to generate a cascaded interference prediction matrix. The interference path analysis unit is used to determine the direction and intensity of interference propagation among various parameters during environmental regulation, distinguish between primary and secondary interference paths and establish interference propagation mechanisms; construct the mutual compensation relationship among the three factors of temperature, humidity and CO2, and determine the timing arrangement of regulation to suppress cascade effects. The compensation and control unit is used to implement phased and refined adjustment of each environmental factor according to the control sequence arrangement, and to offset the sensor measurement offset and concentration distribution disturbance by preset compensation amount, so as to form a coordinated and stable environmental control process. An adaptive optimization unit is used to dynamically adjust the calculation accuracy of the cascade interference prediction matrix according to the actual performance of the cascade interference, so as to realize adaptive and precise control of the mushroom growing room environment.

[0018] The environmental parameter monitoring unit acquires real-time environmental data streams through multiple temperature sensors, humidity sensors, and CO2 concentration sensors distributed at different locations within the mushroom growing room. The temperature sensor data includes temperature distribution information at the top, middle, and bottom of the mushroom growing room; the humidity sensor data covers humidity changes at key locations such as the surface of the mushroom bed, near the vents, and corners; and the CO2 concentration sensor data reflects the CO2 concentration gradient distribution throughout the entire mushroom growing room.

[0019] The intelligent coupling model is an environmental parameter correlation analysis system based on a multi-layer neural network architecture. This model establishes a nonlinear mapping relationship between three environmental factors: temperature, humidity, and CO2 concentration, using deep learning algorithms. The operational logic of the intelligent coupling model is based on a predictive analysis framework of multi-parameter interactive influences. The model receives temperature, humidity, and CO2 concentration sensor data as input parameters, processes them internally through correlation calculations, and finally outputs a cascaded interference prediction matrix as the core result. When the model receives the three types of environmental sensor data, it first processes the temperature change parameter through a temperature sensitivity analysis module, calculating the influence coefficient of temperature fluctuations on the response characteristics of the humidity sensor. This influence coefficient quantifies the degree of humidity measurement deviation caused by temperature changes. If humidity control device parameters are input into the model, the humidity control intensity parameter is processed through a statistical correlation analysis module. Based on historical data, the correlation coefficient between humidity control operations and CO2 concentration distribution is calculated. This correlation coefficient reflects the magnitude of CO2 concentration changes caused by humidity control. The model integrates the two core coefficients mentioned above with the current environmental state parameters and generates a cascaded interference prediction matrix through the coupling relationship calculation module. This matrix describes the intensity of mutual influence and propagation path between the parameters. The matrix includes the cross-influence weights of the three factors of temperature, humidity and CO2 and the interference propagation time sequence, providing a quantitative prediction basis for subsequent environmental regulation decisions and ensuring accurate coordinated control in complex parameter coupling environments.

[0020] The model's calculation of the impact of temperature changes on the physical characteristics of the humidity sensor using trained weight parameters is based on a temperature sensitivity analysis mechanism. When temperature sensor data is input into the model, it first calculates the difference between the current temperature value and the standard calibration temperature, obtaining the temperature offset as the core input feature. If the temperature offset is positive, the model activates weighted paths related to temperature increases. These weight parameters are obtained through training on a large amount of historical data, recording the actual deviation patterns of the humidity sensor's output signal under different temperature change amplitudes. The hidden layer within the model performs a weighted calculation on the temperature offset and the corresponding weight parameters. The magnitude of the weight parameters reflects the sensitivity of the humidity sensor's response characteristics to temperature; a larger weight parameter indicates a more significant temperature impact. After the weighted calculation is complete, the model performs a nonlinear transformation on the calculation results using an activation function, outputting the influence coefficient of temperature changes on the physical characteristics of the humidity sensor. This influence coefficient quantifies the measurement deviation that the sensor may produce under the current temperature conditions. The influence coefficient is shown in the following formula: in, This is the coefficient representing the influence of temperature changes on the physical properties of the humidity sensor. Let $i$ be the dimensionless training weight parameters for the $i$-th hidden layer node. This is the difference between the current temperature and the standard calibration temperature. The standard calibration temperature reference value, To activate the temperature-sensitive threshold temperature, This is the dimensionless slope adjustment parameter for the Sigmoid function. This represents the total number of hidden layer nodes. The hyperbolic tangent activation function is used. It is an exponential function.

[0021] On the other hand, the process of identifying the statistical correlation between humidity control intensity and CO2 concentration change through data fitting is based on regression analysis of historical operating data. When the model receives the operating parameters of the humidity control equipment, it first extracts all humidity control operation records from the historical database. These records include the power level of the humidity control equipment, the operating duration, and the measurement changes of the CO2 concentration sensor during the corresponding period. If similar humidity control intensities exist in the historical data, the model will group these historical cases according to the control intensity. Each group contains multiple control operations and their corresponding CO2 concentration response data. The model uses the least squares method or other regression algorithms to perform curve fitting on the data in each group to find the best fit between humidity control intensity and CO2 concentration change. After the fitting process is completed, the model calculates the correlation coefficient and confidence interval of the fitted curve to quantify the statistical correlation strength between the two parameters. The closer the correlation coefficient is to one, the stronger the correlation; the narrower the confidence interval, the higher the prediction reliability. The model finally outputs a correlation coefficient that reflects the quantitative relationship between humidity control intensity and CO2 concentration change. The calculation of the correlation coefficient is shown in the following formula: in, The correlation coefficient between humidity regulation intensity and CO2 concentration change. For the first Normalized weight parameters for each historical data group and ≥0 and =1, For the first The average humidity regulation intensity in each group The overall mean of humidity regulation intensity for all groups. Let $j$ be the average value of the change in CO2 concentration in the $j$-th group. This represents the overall mean of the changes in CO2 concentration across all groups. The standard deviation of the humidity regulation intensity data and >0, The standard deviation of the CO2 concentration variation data and >0, The number of data points within each group. For confidence level The critical value of the t-distribution under the given conditions, The total number of groups for historical data. It is an exponential function.

[0022] Furthermore, the coupling relationship calculation module uses the influence coefficient of temperature on the humidity sensor and the correlation coefficient between humidity regulation and CO2 concentration change as core inputs. First, it determines the activation weights of each coefficient based on the current environmental state parameters. When the temperature changes, the module weights the temperature influence coefficient with the current temperature offset to obtain the expected real-time deviation value of the humidity sensor. Simultaneously, it multiplies the humidity correlation coefficient by the intensity of the current humidity regulation demand to obtain the expected change in CO2 concentration. If both coefficients are positive, it indicates that temperature and humidity regulation will produce a cascading effect in the same direction, and the module marks this cascading effect as an enhanced coupling path. The module uses cross-correlation analysis to superimpose the direct and indirect effects of each parameter. The direct effect reflects the immediate effect of adjusting a single parameter, while the indirect effect describes the delayed effect transmitted through other parameters. After calculating the influence intensity of all coupling paths, the module organizes the results into a matrix structure according to four dimensions: source parameters, target parameters, influence intensity, and propagation delay. Each element in the matrix represents a coupling relationship between a pair of parameters, the element value reflects the magnitude of the influence intensity, and the element position indicates the propagation path of the influence. This ultimately forms a cascaded interference prediction matrix that comprehensively describes the interaction mechanism between various environmental parameters. The matrix is ​​shown in the following equation: in, in, To influence source parameters For target parameters In the transmission delay The following are the elements of the cascaded interference prediction matrix. The effect coefficient of temperature on humidity sensor is standardized and , For the standardized current temperature offset magnitude and , The correlation coefficient between humidity regulation and CO2 concentration changes is given. To standardize the current humidity control demand intensity and , A standardized cross-correlation function is used to calculate the combined effect of direct and indirect influences. To affect the transmission delay, For discrete time steps, The decay time constant is indirectly affected and >0, The base of the natural logarithm, The same-direction coupling discriminant function is used to mark enhanced coupling paths. For the first The parameter in the first... Values ​​at each point in time. For the first The mean of each parameter, For the first The standard deviation of each parameter The total number of historical data points and , , , These are the reference standardized values ​​for the corresponding parameters.

[0023] It should be noted that the fundamental reason for the intelligent coupling model to generate the cascading interference prediction matrix lies in the complex coupling relationships between parameters during the environmental control of the oyster mushroom growing room. Traditional single-parameter independent control methods cannot effectively handle such multi-factor interactions. During the critical transition from primordia formation to fruiting body development in oyster mushrooms, when temperature regulation is required, the temperature rise causes the humidity sensor to drift due to thermal effects. The system misjudges this as an abnormal humidity level and activates the humidity control equipment. Furthermore, airflow disturbances during humidity control disrupt the uniform distribution of CO2 concentration, which in turn affects the local temperature and humidity environment, creating a vicious cycle of parameter regulation. The intelligent coupling model, by pre-calculating the propagation path and intensity of this cascading interference, can predict the interaction results between parameters before the control action is executed, thereby formulating a coordinated control strategy to avoid or minimize cascading interference. The superior performance of this model is reflected in its ability to achieve the target state of environmental parameters that originally required multiple rounds of repeated adjustments to stabilize in a single coordinated regulation. This significantly reduces the number and amplitude of environmental fluctuations during the mushroom differentiation period, ensuring that oyster mushrooms obtain a continuously stable and suitable environment during the most sensitive development stage, thereby improving the quality of mushroom differentiation and the stability of yield.

[0024] On one hand, the interference path analysis unit identifies the main interference propagation paths by performing row-by-row and column-by-column numerical analysis on the cascaded interference prediction matrix, directly sorting all non-zero elements in the matrix from largest to smallest according to their influence intensity. After the system completes the sorting, it selects several paths with the highest influence intensity as the main interference propagation paths. The specific number of paths selected is determined based on the processing capacity of the mushroom house environmental control system and the sensitivity requirements of the oyster mushroom development stage. If a path shows that the influence intensity of temperature change on the humidity sensor is the highest in the sorting results, then this path is identified as the main interference propagation path from temperature to humidity. When the influence intensity of humidity adjustment on CO2 concentration distribution is also within the selected range, the propagation path from humidity to CO2 is also confirmed as a main path. The system maintains these paths in descending order of influence intensity, forming a priority sequence of interference propagation paths. The path with the highest influence intensity is defined as the core interference source, which needs to be focused on prevention and suppression during the control process.

[0025] It should be noted that the interference propagation path refers to the complete transmission chain in which a change in one environmental parameter affects other environmental parameters through physical or chemical mechanisms during the environmental control process in the fruiting house. Specifically, when the temperature control equipment is activated and the temperature in the fruiting house rises, heat is transferred to the sensitive element of the humidity sensor, causing a change in the internal resistance or capacitance characteristics of the sensor, which in turn causes a deviation in the humidity reading. This complete process from temperature change to humidity measurement deviation constitutes one interference propagation path. When the humidity control equipment is erroneously activated due to sensor deviation, the airflow generated during humidification or dehumidification changes the airflow pattern in the fruiting house, causing the originally uniform CO2 concentration to locally accumulate or dilute. This process from humidity control action to change in CO2 concentration distribution forms another interference propagation path. If the uneven distribution of CO2 concentration further affects the stability of the local temperature and humidity environment, a reverse interference path from CO2 concentration to temperature and humidity will be formed. Each interference propagation path contains four basic elements: the source of influence, the transmission mechanism, the target of influence, and the transmission delay. Multiple paths intertwine to form a complex cascading interference network, threatening the parameter stability of the oyster mushroom growth environment.

[0026] By setting a fixed limit on the number of paths, primary and secondary interference paths are distinguished. The top three paths after ranking by influence coefficient are defined as primary interference paths, and the remaining paths are classified as secondary paths. After the system completes the descending sorting of the influence coefficients of all interference paths, it automatically selects the first, second, and third paths in the ranking as primary interference paths. These three paths have the highest influence coefficient values, representing the most serious interference sources threatening environmental stability. If there are paths ranked fourth or higher in the ranking, the system will classify all of these paths as secondary paths, regardless of their specific influence coefficient values; as long as they are not in the top three, they are considered secondary threats. When the system performs compensation parameter conversion, it will assign a uniform high-weight conversion coefficient to the three primary interference paths, so that the influence coefficients of these three paths can be converted into significant compensation adjustments, ensuring that the three most important interference threats are fully compensated and offset. At the same time, the system will assign a uniform low-weight conversion coefficient to secondary paths, so that the influence coefficients of all secondary paths are converted into relatively mild compensation parameters. Through this fixed classification method based on sorting position, the system can clearly distinguish between key interferences that need to be dealt with and general interferences that can be moderately controlled, so as to achieve reasonable allocation of compensation resources and hierarchical management of interference threats.

[0027] Furthermore, based on the identified main interference propagation paths, a mutual compensation relationship among temperature, humidity, and CO2 is constructed. First, the influence direction and intensity characteristics of each main path are analyzed, and a reverse compensation mechanism between parameters is established. When temperature regulation causes a positive offset in the humidity sensor, the system designs a negative compensation action for the humidity regulation equipment, using humidity regulation in the opposite direction to counteract the interference of temperature changes on humidity measurement. The compensation intensity is matched and set according to the intensity coefficient of the temperature influence path. If the humidity regulation process leads to uneven CO2 concentration distribution, the system simultaneously designs measures to stabilize CO2 concentration, including adjusting the operating mode of ventilation equipment or changing the spatial distribution strategy of CO2 supply, ensuring that the CO2 concentration remains uniform during humidity regulation. When CO2 concentration regulation has a reverse impact on the temperature and humidity environment, the system establishes a joint compensation response mechanism for temperature and humidity, maintaining overall environmental stability through coordinated actions of temperature and humidity regulation equipment. The core of the compensation relationship lies in establishing a numerical correspondence between parameter regulation and compensation regulation. That is, each main regulation intensity corresponds to a specific compensation regulation amount, forming a complete three-factor mutual compensation network, ensuring that the regulation action of any single parameter can eliminate the cascading interference effect through the synchronous compensation of other parameters.

[0028] More specifically, the nature of the impact is identified by analyzing the numerical signs and trends of the elements corresponding to the main interference paths in the cascade interference prediction matrix, and the type of reverse compensation action is determined accordingly. When the system detects a positive value for the interference path element from temperature to humidity sensor, it indicates that an increase in temperature will cause an increase in humidity sensor readings. The system will identify this as a positive enhancing effect and determine that a dehumidification-type reverse compensation action is needed to counteract this positive effect. If the interference path element from humidity adjustment to CO2 concentration shows a negative value, it indicates that humidity adjustment will lead to a decrease in CO2 concentration or dilution of distribution. The system will determine this as a negative suppressive effect and determine that a CO2 concentration increase or redistribution-type reverse compensation action is needed. When the impact path of CO2 concentration adjustment on the temperature environment shows periodic fluctuation characteristics, the system will identify this fluctuating impact nature and determine that a temperature smoothing adjustment-type compensation action is needed to eliminate the fluctuation effect. The system establishes a fixed mapping relationship between each type of influence and the corresponding compensation action type, including enhancing influence corresponding to suppressive compensation, suppressive influence corresponding to enhancing compensation, and fluctuating influence corresponding to stabilizing compensation, to ensure that each major interference path can find an accurately matched reverse compensation action type, thereby effectively neutralizing the interference effect.

[0029] For example, the nature of the influence is identified by analyzing the numerical signs and trends of the elements corresponding to the main interference paths in the cascade interference prediction matrix, and the type of reverse compensation action is determined accordingly. When the temperature of the fruiting room needs to be raised from a lower temperature to a suitable differentiation temperature during the transformation period of oyster mushroom primordia to fruiting bodies, the heat radiation during the temperature rise process will cause the housing of the humidity sensor installed near the mushroom rack to expand due to heat. This will cause the resistance value of the humidity-sensitive element inside the sensor to drift, resulting in an abnormal increase in humidity. The system identifies this phenomenon of increased false readings of the humidity sensor caused by the temperature rise as a positive enhancement effect, and then determines that a reverse compensation action is needed to temporarily reduce the speed of the dehumidifying fan or delay the start of the humidifier to offset the measurement deviation of the sensor. If the system activates the humidifier to spray water mist into the mushroom house due to sensor misjudgment, the water mist will dilute the originally suitable concentration of CO2 gas around the mushroom bed during diffusion. This will cause the local CO2 concentration to drop from a level conducive to fruiting body differentiation to a level insufficient to promote mushroom development. The system identifies this phenomenon of CO2 concentration dilution caused by humidification as a negative inhibitory effect and determines that it is necessary to increase the air supply from the CO2 nozzles near the mushroom bed or adjust the exhaust fan operation mode to reduce CO2 loss as a counter-compensation action. When the airflow impact generated when the CO2 supply pipeline valve is opened intensifies the airflow in the mushroom house, carrying away heat from the surface of the mushroom bed and causing a temporary drop in local temperature that affects normal mushroom differentiation, the system identifies this phenomenon of temperature fluctuation caused by CO2 supply as a fluctuating effect and determines that it is necessary to activate the auxiliary heating device in advance or adjust the power output of the main heater as a compensation action to maintain temperature stability during the mushroom differentiation period.

[0030] It should be noted that the fundamental purpose of constructing the main disturbance propagation path is to transform the complex coupling relationships of environmental parameters into quantifiable and controllable specific disturbance chains, turning what was originally difficult-to-predict cascading effects into known risks that can be identified in advance and precisely addressed. During the critical developmental period of *Pleurotus ostreatus* primordia transformation into fruiting bodies, traditional single-parameter regulation methods often fall into a vicious cycle of "regulation-disturbance-readjustment-disturbance." Temperature regulation causes humidity sensor offset, leading to erroneous humidity compensation; humidity regulation, in turn, disrupts CO2 concentration uniformity, thus affecting temperature stability. The superposition of multiple disturbances keeps environmental parameters in a state of constant fluctuation, failing to achieve the precise and stable conditions required for fruiting body differentiation. Constructing the main disturbance propagation path can organize this seemingly random disturbance phenomenon into a clear causal chain, clearly indicating the specific mechanisms through which each parameter adjustment affects other parameters and to what extent. This allows the regulatory system to anticipate and prepare for potential chain reactions before executing any regulatory action.

[0031] On one hand, the compensation and control unit initiates a phased, refined control process according to a pre-determined control sequence. First, it identifies the response speed characteristics of each environmental factor and arranges the control initiation time in ascending order. When the system determines that CO2 concentration control requires the longest gas diffusion and mixing time, it schedules the activation of the CO2 supply equipment in the first stage of the control sequence. This is achieved by opening the CO2 supply valve and adjusting the opening of the gas inlet to establish a gaseous environment with the target concentration. Once the CO2 concentration control enters a stable diffusion period, the system initiates the second stage of humidity control. This involves gradually increasing the humidity level in the mushroom house by gradually activating the humidifier or dehumidifier. The intensity of the control is gradually increased based on the response characteristics of the humidity control equipment to avoid drastic humidity fluctuations. After the control effects of the first two factors have stabilized, the system activates the temperature control equipment in the third stage. This is achieved by gradually increasing the heater power or gently activating the cooling equipment to reach the target temperature. The temperature control employs a segmented increase and decrease method to ensure that the mushrooms can adapt to the temperature changes. Throughout the phased adjustment process, each phase of adjustment will wait until the previous phase reaches a relatively stable state before it begins to be executed. Through this staggered timing and gradual intensity adjustment method, the system can avoid the environmental impact caused by the simultaneous rapid changes of multiple environmental factors on the mushroom body, ensuring that the oyster mushroom obtains a stable and orderly environmental regulation process during the primordia to fruiting body transition period.

[0032] Furthermore, based on the analysis results of the main interference propagation paths, the impact of various adjustment actions on sensor measurements and concentration distribution is pre-calculated, and a corresponding compensation database is established to offset interference effects in real time. When the temperature control equipment is activated and the mushroom house temperature rises, the system immediately retrieves the preset compensation value for the impact of temperature changes on the humidity sensor from the compensation database. This compensation value is automatically subtracted from the humidity control algorithm to correct the sensor's false reading increment, ensuring that the humidity control equipment receives a calibrated, true humidity signal. If the humidity control equipment activates dehumidification or humidification operations due to the compensated signal, the system will simultaneously activate the preset compensation mechanism for CO2 concentration distribution, selecting corresponding CO2 concentration protection measures from the compensation database based on the humidity control intensity and the airflow influence range. When the system detects that water vapor generated during humidification will dilute the local CO2 concentration, it will pre-increase the air supply intensity of the CO2 supply port in that area to compensate for the impending concentration drop. If the operation of the dehumidification fan will change the airflow distribution in the mushroom house and affect CO2 uniformity, the system will adjust the local operation mode of the exhaust equipment or temporarily close some CO2 supply ports to maintain the stability of the concentration distribution. The entire compensation process adopts a predictive compensation approach, which means that compensation measures are initiated before the actual occurrence of the interference effect. By setting a lead time, it is ensured that the compensation effect can offset the interference effect synchronously, and ultimately, all environmental parameters are kept in a coordinated and stable state within the target range during the adjustment process.

[0033] Specifically, the influence coefficients and correlation coefficients output by the intelligent coupling model are directly converted into specific correction parameters in a preset compensation database through a mapping transformation mechanism, establishing a correspondence between coefficient values ​​and compensation intensity. When the system obtains the influence coefficient of temperature regulation on the humidity sensor, it converts the value of this coefficient into the compensation range of the humidity sensor correction parameters. The larger the influence coefficient, the larger the corresponding sensor correction compensation amount. The system determines whether the compensation direction is additive or subtractive correction based on the sign of the coefficient. If the correlation coefficient shows a strong correlation between humidity regulation and CO2 concentration distribution, the system converts the strength level of the correlation coefficient into compensation parameters for CO2 supply adjustment. Strong correlation corresponds to a large-scale CO2 supply compensation adjustment, while weak correlation corresponds to a slight supply fine-tuning. When the system processes multiple interrelated influence coefficients, it performs a weighted transformation based on the weight of each coefficient's position in the cascaded interference chain. The influence coefficient of the main interference path receives a higher transformation weight, resulting in a larger compensation parameter, while the coefficient of the secondary path receives a lower weight, resulting in a smaller compensation adjustment. During the conversion process, the system maintains the relative magnitude of the coefficients in the compensation parameters, ensuring that the proportional relationship between each correction parameter in the compensation database remains consistent with the strength comparison of the original influence coefficients. This ultimately forms a complete compensation parameter system that can accurately correspond to various interference intensities and types, providing accurate numerical basis for interference cancellation in actual control processes.

[0034] The system directly converts the strength level of the correlation coefficient into compensation parameters for CO2 supply adjustment by establishing a linear correspondence between the correlation coefficient value and the CO2 supply adjustment range. The specific value of the correlation coefficient is directly mapped to the adjustment amount of the CO2 supply port opening and the extension of the supply time according to a fixed conversion ratio. After obtaining the correlation coefficient between humidity regulation and CO2 concentration distribution, the system multiplies this value by a preset opening conversion factor to obtain the compensation parameter for the CO2 supply port opening adjustment. A larger correlation coefficient results in a larger opening adjustment, and a smaller correlation coefficient results in a smaller adjustment. If the correlation coefficient is positive, the system sets the conversion result as a positive compensation parameter to increase the CO2 supply port opening; if the correlation coefficient is negative, the system sets the conversion result as a negative compensation parameter to decrease the supply port opening. Simultaneously, the system multiplies the same correlation coefficient by another preset time conversion factor to obtain the compensation parameter for extending the CO2 supply time, ensuring that the adjustment amount of the supply duration is proportional to the magnitude of the correlation coefficient. During the conversion process, the system maintains the continuity of the original correlation coefficient values ​​in the compensation parameters, ensuring that each specific correlation coefficient value corresponds to a uniquely determined CO2 supply adjustment compensation parameter. This achieves a precise one-to-one conversion from theoretical analysis results to actual control parameters, providing an accurate basis for compensation adjustment to maintain stable CO2 concentration. The adjustment compensation parameter is shown in the following formula: in, in, The result is a comprehensive conversion of CO2 supply adjustment and compensation parameters, including the opening adjustment amount and the gas supply time extension amount. The correlation coefficient between humidity regulation and CO2 concentration distribution was used as a direct input variable. The preset opening conversion factor is used to achieve a linear correspondence between the correlation coefficient and the CO2 supply port opening adjustment amount. A preset time conversion factor is used to realize the proportional mapping relationship between the correlation coefficient and the gas supply time extension. The hyperbolic tangent function is used to maintain the continuity of the original numerical values ​​of the correlation coefficients in the aperture compensation process. The error function is used to ensure the continuity of the time compensation parameters and the accuracy of the one-to-one conversion. The base of the natural logarithm, Pi is the mathematical constant of a circle.

[0035] It should be noted that the fundamental purpose of converting the correlation coefficient into CO2 supply adjustment compensation parameters is to transform the interference of humidity regulation on CO2 concentration distribution identified by the intelligent coupling model into executable preventive compensation measures, enabling the system to initiate corresponding CO2 supply protection actions before humidity regulation causes interference. During the critical developmental period of *Pleurotus ostreatus* primordia transformation into fruiting bodies, the operation of humidity regulation equipment will disrupt the uniform distribution of CO2 concentration in the mushroom house through physical mechanisms such as airflow disturbance and water vapor dilution. The correlation coefficient conversion mechanism can quantify this degree of disruption into specific CO2 supply compensation requirements, ensuring that the CO2 concentration remains stable throughout the humidity regulation process. When the system detects that temperature regulation causes humidity sensor offset and humidity compensation regulation needs to be initiated, the converted CO2 supply adjustment parameters will simultaneously guide the CO2 supply equipment to preventively increase or decrease the supply, offsetting the potential interference of humidity regulation on CO2 distribution. This avoids the lag problem of needing secondary regulation after humidity regulation is completed, which is common in traditional control methods.

[0036] On one hand, once the mushroom plants enter the differentiation stage, the adaptive optimization unit initiates a high-frequency data acquisition mode. All sensors synchronously read environmental parameters at preset time intervals, transmitting the collected temperature, humidity, and CO2 concentration data to the central control system for processing and analysis in real time. If the system detects any parameter exceeding its normal fluctuation range, it immediately increases the monitoring frequency of that parameter and related parameters, using encrypted sampling to capture the detailed process and trend characteristics of the changes. When multiple sensors simultaneously display abnormal parameter changes, the system initiates a cascaded interference identification program, comparing the time series and change patterns of the data from each sensor to determine whether there is a mutual influence relationship between the parameters. The system continuously compares the real-time collected parameter change data with the expected adjustment effect, identifying the difference between the actual environmental response and theoretical predictions, paying particular attention to whether the actual change trajectory of each parameter after the adjustment action conforms to the calculation results of the prediction matrix.

[0037] The correction direction and magnitude are determined by comparing the deviation between the actual intensity of cascaded interference obtained from real-time monitoring and the calculation results of the prediction matrix, establishing a closed-loop feedback mechanism for deviation analysis and matrix update. When the system detects that the actual degree of humidity sensor offset caused by temperature regulation exceeds the expected intensity calculated by the prediction matrix, it calculates the ratio of the actual offset to the predicted offset and converts this difference information into the correction increment of the corresponding matrix element. If the actual disturbance effect of a humidity regulation on the CO2 concentration distribution is significantly weaker than the prediction result, the system will reduce the influence coefficient of the humidity-CO2 correlation position in the prediction matrix according to the ratio of the actual disturbance intensity to the predicted intensity, so that the corrected coefficient can more accurately reflect the true degree of interference. When the system accumulates enough deviation data, it will start a batch correction program to uniformly adjust all elements in the prediction matrix with systematic deviations. The correction magnitude is determined according to the persistence and consistency of the deviation; persistent deviations receive larger correction magnitudes, while occasional deviations receive smaller adjustment amounts. After the correction is completed, the system will recalculate the compensation parameters and control strategies using the updated prediction matrix. The effectiveness of the correction will be evaluated by verifying the actual control effect. If the prediction accuracy is improved after the correction, the correction result will be retained. If the accuracy is not improved, the system will roll back to the matrix state before the correction and try other correction schemes. Through this continuous monitoring-analysis-correction-verification cycle, the system achieves continuous optimization of the prediction matrix accuracy and adaptive improvement of the environmental control strategy, ensuring that the environmental control of the mushroom growing room always maintains the highest accuracy and stability.

[0038] In summary, the adaptive control system for the fruiting house of *Pleurotus ostreatus* based on the intelligent coupling model, as described in this invention, is explained. It identifies the mutual influence relationships between environmental parameters by constructing a cascaded interference prediction matrix and employs a phased, refined adjustment strategy and a preset compensation mechanism to counteract the cascaded interference effects during the adjustment process. This significantly reduces the mutual interference and fluctuation amplitude during environmental parameter adjustment, effectively avoiding developmental abnormalities caused by environmental instability during the fruiting body differentiation period. Consequently, it improves the success rate and quality consistency of *Pleurotus ostreatus* fruiting body differentiation, achieving precise and stable control of the fruiting house environment.

[0039] Here, those skilled in the art will understand that the specific operations of each step in the above-described adaptive control method for the mushroom growing room based on the intelligent coupling model have been referenced above. Figure 1 and Figure 2 The adaptive control system for mushroom growing rooms based on the intelligent coupling model has been described in detail, and therefore, its repeated description will be omitted.

[0040] According to another aspect of the present invention, an adaptive control method for a mushroom growing room based on an intelligent coupling model is provided, comprising: It receives temperature, humidity, and CO2 concentration data from the mushroom growing room, calculates the impact of temperature changes on the response characteristics of the humidity sensor and the disturbance intensity of humidity regulation on the spatial distribution of CO2 concentration through an intelligent coupling model, and generates a cascaded interference prediction matrix. Based on the cascade interference prediction matrix, the main interference propagation paths in the parameter adjustment process are identified, the mutual compensation relationship among the three factors of temperature, humidity and CO2 is constructed, and the timing arrangement for suppressing the cascade effect is determined. According to the aforementioned control sequence, each environmental factor is subject to phased and refined regulation. The sensor measurement offset and concentration distribution disturbance are offset by preset compensation amount, forming a coordinated and stable environmental control process. The system monitors the changes in environmental parameters during the mushroom differentiation period in real time, and dynamically adjusts the calculation accuracy of the cascade interference prediction matrix based on the actual performance of the cascade interference, thereby achieving adaptive and precise control of the mushroom growing room environment.

[0041] In summary, the adaptive control method for the fruiting room of *Pleurotus ostreatus* based on the intelligent coupling model, as described in this invention, is elucidated. It identifies the mutual influence relationships between environmental parameters by constructing a cascaded interference prediction matrix and employs a phased, refined adjustment strategy and a preset compensation mechanism to counteract the cascaded interference effects during the adjustment process. This significantly reduces the mutual interference and fluctuation amplitude during environmental parameter adjustment, effectively avoiding developmental abnormalities caused by environmental instability during the fruiting body differentiation period. Consequently, it improves the success rate and quality consistency of *Pleurotus ostreatus* fruiting body differentiation, achieving precise and stable control of the fruiting room environment.

Claims

1. An adaptive control system for a mushroom growing room based on an intelligent coupling model, characterized in that, include: The environmental parameter monitoring unit is used to collect environmental parameter data such as temperature, humidity, and CO2 concentration in the mushroom house in real time, and to establish a layered and zoned sensor monitoring network. A smart coupling model is used to calculate the degree of influence of temperature changes on the response characteristics of humidity sensors and the perturbation intensity of humidity regulation on the spatial distribution of CO2 concentration, and to generate a cascaded interference prediction matrix. The interference path analysis unit is used to determine the direction and intensity of interference propagation among various parameters during environmental regulation, distinguish between primary and secondary interference paths and establish interference propagation mechanisms; construct the mutual compensation relationship among the three factors of temperature, humidity and CO2, and determine the timing arrangement of regulation to suppress cascade effects. The compensation and control unit is used to implement phased and refined adjustment of each environmental factor according to the control sequence arrangement, and to offset the sensor measurement offset and concentration distribution disturbance by preset compensation amount, so as to form a coordinated and stable environmental control process. An adaptive optimization unit is used to dynamically adjust the calculation accuracy of the cascade interference prediction matrix according to the actual performance of the cascade interference, so as to realize adaptive and precise control of the mushroom growing room environment.

2. The adaptive control system for the mushroom growing room of *Pleurotus ostreatus* based on an intelligent coupling model according to claim 1, characterized in that, The intelligent coupling model includes a temperature sensitivity analysis module, a statistical correlation analysis module, and a coupling relationship calculation module; The intelligent coupling model analyzes the correlation strength between temperature changes and humidity sensor measurement deviations, as well as the influence of humidity adjustment actions on CO2 concentration distribution changes, quantifies the coupling influence coefficients between various parameters, and generates a cascaded interference prediction matrix.

3. The adaptive control system for the mushroom growing room of *Pleurotus ostreatus* based on an intelligent coupling model according to claim 2, characterized in that, The temperature sensitivity analysis module processes temperature change parameters and calculates the influence coefficient of temperature fluctuation on the response characteristics of the humidity sensor. The statistical correlation analysis module processes the humidity regulation intensity parameter and calculates the correlation coefficient between humidity regulation operation and CO2 concentration distribution based on historical data. The coupling relationship calculation module performs comprehensive calculations on the influence coefficient and the correlation coefficient with the current environmental state parameters to generate a cascaded interference prediction matrix that describes the intensity of mutual influence and propagation path between the parameters.

4. The adaptive control system for the mushroom growing room of *Pleurotus ostreatus* based on an intelligent coupling model according to claim 3, characterized in that, The cascaded interference prediction matrix generated by the intelligent coupling model is shown in the following equation: in, To influence source parameters For target parameters In the transmission delay The following are the elements of the cascaded interference prediction matrix. To standardize the influence coefficient of temperature on humidity sensors, For the standardized current temperature offset, The correlation coefficient between humidity regulation and CO2 concentration changes is given. To standardize the current intensity of humidity control demand, A standardized cross-correlation function is used to calculate the combined effect of direct and indirect influences. To affect the transmission delay, For discrete time steps, The decay time constant is indirectly affected and >0, is the base of the natural logarithm.

5. The adaptive control system for the mushroom growing room of *Pleurotus ostreatus* based on an intelligent coupling model according to claim 4, characterized in that, The interference path analysis unit sorts all elements in the cascaded interference prediction matrix output by the intelligent coupling model in descending order of influence intensity, selects the top-ranked paths as the main interference propagation paths, and forms a priority sequence.

6. The adaptive control system for the mushroom growing room of *Pleurotus ostreatus* based on an intelligent coupling model according to claim 5, characterized in that, The compensation and control unit directly maps the influence coefficients and correlation coefficients output by the intelligent coupling model to sensor calibration parameters and CO2 supply adjustment parameters according to a fixed conversion ratio, and initiates compensation measures in advance to counteract sensor measurement offsets and concentration distribution disturbances before the actual occurrence of interference effects.

7. The adaptive control system for the mushroom growing room of *Pleurotus ostreatus* based on an intelligent coupling model according to claim 6, characterized in that, The compensation control unit maps the correlation coefficient to the supply adjustment compensation parameter as shown in the following formula: in, Adjusting compensation parameters for CO2 supply The correlation coefficient between humidity regulation and CO2 concentration distribution is given. The preset opening conversion factor is used to achieve a linear correspondence between the correlation coefficient and the CO2 supply port opening adjustment amount. A preset time conversion factor is used to realize the proportional mapping relationship between the correlation coefficient and the gas supply time extension. The hyperbolic tangent function is used to maintain the continuity of the original numerical values ​​of the correlation coefficients in the aperture compensation process. This is the error function.

8. An adaptive control method for the fruiting room of *Pleurotus ostreatus* based on an intelligent coupling model, characterized in that, include: It receives temperature, humidity, and CO2 concentration data from the mushroom growing room, calculates the impact of temperature changes on the response characteristics of the humidity sensor and the disturbance intensity of humidity regulation on the spatial distribution of CO2 concentration through an intelligent coupling model, and generates a cascaded interference prediction matrix. Based on the cascade interference prediction matrix, the main interference propagation paths in the parameter adjustment process are identified, the mutual compensation relationship among the three factors of temperature, humidity and CO2 is constructed, and the timing arrangement for suppressing the cascade effect is determined. According to the aforementioned control sequence, each environmental factor is subject to phased and refined regulation. The sensor measurement offset and concentration distribution disturbance are offset by preset compensation amount, forming a coordinated and stable environmental control process. The system monitors the changes in environmental parameters during the mushroom differentiation period in real time, and dynamically adjusts the calculation accuracy of the cascade interference prediction matrix based on the actual performance of the cascade interference, thereby achieving adaptive and precise control of the mushroom growing room environment.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the adaptive control system for the mushroom growing room based on the intelligent coupling model as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the adaptive control system for the mushroom growing room based on the intelligent coupling model as described in any one of claims 1 to 7.

Images