Mung bean sprout cultivation water quality, humidity and temperature multi-parameter cooperative control method and system

Abstract

The invention relates to the technical field of mung bean sprout production control, and particularly discloses a mung bean sprout cultivation water quality, humidity and temperature multi-parameter cooperative control method and system.The method comprises the following steps that water quality, humidity and temperature characteristic parameters are collected in real time, a water quality activity coefficient, a humidity deviation index and a temperature stability factor are calculated respectively, a multi-modal cooperative matrix is constructed, and the multi-modal cooperative matrix is calculated; key features are extracted through core influence factor analysis, and a growth regulation coefficient is generated. According to the method, through data-driven objective evaluation and parameter coordinated adjustment, the problems of hysteresis and subjective dependence of traditional single-parameter control are solved, accurate dynamic management of the cultivation environment is achieved, and the method is suitable for large-scale popularization and application. Therefore, the method is suitable for industrial cultivation scenes of the mung bean sprouts.

Description

Technical Field

[0001] This invention relates to the field of mung bean sprout production control technology, and in particular to a method and system for the coordinated control of multiple parameters such as water quality, humidity and temperature in mung bean sprout cultivation. Background Technology

[0002] As an important type of edible sprout vegetable, mung bean sprouts have seen their large-scale cultivation technology gradually develop towards automation and intelligence. Currently, the environmental control of mung bean sprout cultivation mainly relies on the independent adjustment of single environmental parameters (such as temperature, humidity, or water quality). For example, temperature is maintained by a constant temperature device, air humidity is controlled by a humidifier, or the culture medium is changed regularly to ensure water quality.

[0003] During the growth of mung bean sprouts, there is a complex dynamic coupling relationship between dissolved oxygen content, pH value, and ambient temperature and humidity. However, current technologies do not fully consider the interaction of multiple parameters such as water quality, humidity, and temperature. For example, changes in water temperature directly affect the dissolved oxygen saturation concentration, while excessively low air humidity accelerates the evaporation of the culture medium, altering the solution's ion concentration and pH stability. Isolated control strategies lead to dynamic imbalances among parameters, causing slow growth or abnormal physiological metabolism in bean sprouts. Furthermore, while current technologies can acquire multi-parameter monitoring data, they lack effective multimodal analysis models. The nonlinear relationship between water activity, humidity deviation, and temperature stability is not quantitatively expressed, causing regulatory decisions to rely on empirical thresholds and failing to accurately quantify the degree of environmental deviation from the optimal state, resulting in low accuracy in assessing the mung bean sprout cultivation environment.

[0004] Therefore, there is an urgent need for a method to coordinate the control of multiple parameters such as water quality, humidity, and temperature in mung bean sprout cultivation in order to solve the above problems. Summary of the Invention

[0005] The purpose of this invention is to provide a method for the coordinated control of multiple parameters, including water quality, humidity, and temperature, in mung bean sprout cultivation, comprising the following steps:

[0006] Real-time monitoring data of the mung bean sprout cultivation environment is obtained, wherein the real-time monitoring data includes water quality characteristic parameters, humidity characteristic parameters, and temperature characteristic parameters;

[0007] The relative change rate of dissolved oxygen is obtained based on the water quality characteristic parameters, and the water quality activity coefficient is obtained based on the relative change rate of dissolved oxygen.

[0008] The evaporation rate coefficient is obtained based on the humidity characteristic parameters, and the humidity deviation index is obtained based on the evaporation rate coefficient.

[0009] The temperature gradient and fluctuation frequency are obtained based on the temperature characteristic parameters, and the temperature stability factor is obtained based on the temperature gradient and fluctuation frequency.

[0010] A multimodal synergy matrix is ​​constructed based on the temperature stability factor, humidity deviation index, and water quality activity coefficient. Core influencing factor analysis is performed on the multimodal synergy matrix to obtain a core influencing factor matrix. Growth regulation coefficients are obtained based on the core influencing factor extraction matrix.

[0011] The corresponding regulation level is obtained based on the growth regulation coefficient, and the cultivation environment of mung bean sprouts is synergistically controlled according to the regulation level.

[0012] Furthermore, the step of obtaining the relative change rate of dissolved oxygen based on the water quality characteristic parameters, and obtaining the water quality activity coefficient based on the relative change rate of dissolved oxygen, includes:

[0013] The current dissolved oxygen concentration and pH value are obtained based on the water quality characteristic parameters.

[0014] Obtain historical baseline dissolved oxygen concentration and preset neutral pH value;

[0015] The relative rate of change of dissolved oxygen is obtained based on the current dissolved oxygen concentration and the historical baseline dissolved oxygen concentration.

[0016] The pH offset is obtained based on the pH measurement value and the preset neutral pH value;

[0017] The water quality activity coefficient is obtained based on the relative change rate of dissolved oxygen and the pH shift.

[0018] Furthermore, the step of obtaining the evaporation rate coefficient based on the humidity characteristic parameter and obtaining the humidity deviation index based on the evaporation rate coefficient includes:

[0019] Relative humidity data and air velocity are obtained based on the humidity characteristic parameters;

[0020] The rate of change of evaporation surface temperature is obtained based on the humidity characteristic parameters, and the real-time evaporation rate is obtained based on the relative humidity data, air velocity, and rate of change of evaporation surface temperature.

[0021] The median of the ideal interval is obtained based on the preset optimal humidity range, and the absolute humidity deviation value is obtained based on the median of the ideal interval.

[0022] Obtain a preset average evaporation rate, and obtain an evaporation rate coefficient based on the real-time evaporation rate and the preset average evaporation rate;

[0023] The humidity deviation index is obtained based on the absolute humidity deviation value and the evaporation rate coefficient.

[0024] Furthermore, the step of obtaining the temperature gradient and fluctuation frequency based on the temperature characteristic parameters, and obtaining the temperature stability factor based on the temperature gradient and fluctuation frequency, includes:

[0025] The temperature value is obtained based on the temperature characteristic parameters, and the maximum temperature difference value is obtained based on the temperature value.

[0026] The temperature gradient is obtained based on the maximum temperature difference value;

[0027] The temperature gradient is analyzed to obtain the main fluctuation frequency;

[0028] The gradient influence coefficient is obtained based on the temperature gradient and the main fluctuation frequency.

[0029] The frequency deviation coefficient is obtained based on the main fluctuation frequency and the gradient influence coefficient, and the temperature stability factor is obtained based on the frequency deviation coefficient and the gradient influence coefficient.

[0030] Furthermore, the step of constructing a multimodal cooperative matrix based on the temperature stability factor, humidity deviation index, and water quality activity coefficient includes:

[0031] The temperature stability factor, humidity deviation index, and water quality activity coefficient are mapped to independent components in a three-dimensional vector space.

[0032] The temperature-humidity interaction coefficient is obtained based on the temperature stability factor and humidity deviation index.

[0033] The humidity-water interaction coefficient is obtained based on the humidity deviation index and the water quality activity coefficient.

[0034] The temperature-humidity interaction coefficient, the moisture-mass interaction coefficient, and the temperature stability factor are combined in columns to form an initial synergistic matrix;

[0035] The initial cooperative matrix is ​​standardized to eliminate the dimensional differences of different parameters and obtain the multimodal cooperative matrix.

[0036] Based on the multimodal collaboration matrix, obtain the covariance matrix;

[0037] The covariance matrix is ​​decomposed into eigenvalues ​​to extract the eigenvectors corresponding to the K largest eigenvalues.

[0038] The original data of the multimodal collaborative matrix is ​​projected onto the feature space formed by the feature vectors to generate a core influence factor matrix, where each column of the core influence factor matrix corresponds to a core influence factor score.

[0039] The variance contribution rate of each core influence factor is obtained based on the feature vector and the core influence factor score, and the growth regulation coefficient is obtained based on the variance contribution rate.

[0040] Furthermore, the step of obtaining the corresponding regulation level based on the growth regulation coefficient and synergistically controlling the cultivation environment of mung bean sprouts according to the regulation level includes:

[0041] The corresponding regulation level is obtained based on the growth regulation coefficient, wherein the regulation level includes a first regulation level, a second regulation level, and a third regulation level;

[0042] A first control instruction is generated based on the first control level. The first control instruction is used to control the oxygenation equipment and humidity control equipment to adjust the oxygen supply, humidification or dehumidification of mung bean sprouts.

[0043] A second control instruction is generated based on the second control level. The second control instruction is used to control the temperature controller and the oxygenation equipment to adjust the temperature and dissolved oxygen concentration of the mung bean sprouts in a coordinated manner.

[0044] A third control instruction is generated based on the third control level. The third control instruction is used to control the water circulation system to perform water exchange operation, control the humidity control equipment to perform forced adjustment, control the temperature controller to forcefully enter the constant temperature mode, and trigger the alarm device to issue an abnormal alarm.

[0045] This invention also discloses a multi-parameter coordinated control system for water quality, humidity, and temperature in mung bean sprout cultivation, comprising:

[0046] The first acquisition module is used to acquire real-time monitoring data of the mung bean sprout cultivation environment, wherein the real-time monitoring data includes water quality characteristic parameters, humidity characteristic parameters and temperature characteristic parameters;

[0047] The second acquisition module is used to acquire the relative change rate of dissolved oxygen based on the water quality characteristic parameters, and to acquire the water quality activity coefficient based on the relative change rate of dissolved oxygen.

[0048] The third acquisition module is used to acquire the evaporation rate coefficient based on the humidity characteristic parameters, and to acquire the humidity deviation index based on the evaporation rate coefficient.

[0049] The fourth acquisition module is used to acquire the temperature gradient and fluctuation frequency based on the temperature characteristic parameters, and to acquire the temperature stability factor based on the temperature gradient and fluctuation frequency.

[0050] The module is used to construct a multimodal synergy matrix based on the temperature stability factor, humidity deviation index and water quality activity coefficient, perform core influence factor analysis on the multimodal synergy matrix to obtain a core influence factor matrix, and obtain the growth regulation coefficient based on the core influence factor matrix.

[0051] The judgment module is used to obtain the corresponding control level based on the growth control coefficient, and to coordinately control the cultivation environment of mung bean sprouts according to the control level.

[0052] This application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method for coordinated control of multiple parameters such as water quality, humidity, and temperature in mung bean sprout cultivation.

[0053] This application also provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the steps of the above-described method for coordinated control of multiple parameters such as water quality, humidity, and temperature in mung bean sprout cultivation.

[0054] The beneficial effects of this application are as follows: This invention addresses the shortcomings of independent control of environmental parameters and lack of collaborative analysis in traditional mung bean sprout cultivation. By integrating multiple parameters and analyzing core influencing factors, and constructing a multimodal collaborative matrix, temperature stability factors, humidity deviation index, water quality activity coefficient and their interactions are transformed into structured data. Then, growth regulation coefficients are generated using core influencing factor analysis, and these growth regulation coefficients are used as comprehensive reference indicators. This can quantitatively reflect the overall state of the multidimensional environment, solving the problem of missed judgments in traditional methods where single parameters are qualified but the overall environment is deteriorating, thus improving the accuracy of environmental assessment. Attached Figure Description

[0055] Figure 1 This is a schematic diagram of a method flow proposed in an embodiment of this application.

[0056] Figure 2 This is a schematic diagram of the system structure according to an embodiment of the present invention. Detailed Implementation

[0057] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0058] like Figure 1 As shown, this application provides a method for the coordinated control of multiple parameters such as water quality, humidity, and temperature in mung bean sprout cultivation, including the following steps:

[0059] S1, acquire real-time monitoring data of the mung bean sprout cultivation environment, wherein the real-time monitoring data includes water quality characteristic parameters, humidity characteristic parameters and temperature characteristic parameters;

[0060] S2, obtain the relative change rate of dissolved oxygen based on the water quality characteristic parameters, and obtain the water quality activity coefficient based on the relative change rate of dissolved oxygen;

[0061] S3, obtain the evaporation rate coefficient based on the humidity characteristic parameters, and obtain the humidity deviation index based on the evaporation rate coefficient;

[0062] S4, obtain the temperature gradient and fluctuation frequency based on the temperature characteristic parameters, and obtain the temperature stability factor based on the temperature gradient and fluctuation frequency;

[0063] S5. Construct a multimodal synergy matrix based on the temperature stability factor, humidity deviation index and water quality activity coefficient, and perform core influence factor analysis on the multimodal synergy matrix to obtain a core influence factor matrix, and obtain the growth regulation coefficient based on the core influence factor extraction matrix.

[0064] S6. Obtain the corresponding regulation level according to the growth regulation coefficient, and coordinately control the cultivation environment of mung bean sprouts according to the regulation level.

[0065] As described in steps S1-S6 above, this invention obtains real-time monitoring data of the mung bean sprout cultivation environment, analyzes and processes relevant parameters such as water quality, humidity, and temperature, constructs a multimodal collaborative matrix and performs core influencing factor analysis, and determines whether the cultivation environment parameters need to be adjusted based on the obtained growth regulation coefficient, thereby achieving the purpose of coordinated control of multiple parameters such as water quality, humidity, and temperature during the mung bean sprout cultivation process, creating a suitable environment for mung bean sprout growth, and ensuring the growth quality and yield of mung bean sprouts.

[0066] The growth of mung bean sprouts is highly sensitive to water quality, humidity, and temperature in the cultivation environment. Characteristic parameters in the water, such as dissolved oxygen concentration and pH value, affect the respiration and metabolism of the sprouts. Humidity influences the balance between water absorption and evaporation; unsuitable humidity can lead to dehydration or mold growth. Temperature affects enzyme activity during growth; unstable temperatures can interfere with normal physiological and biochemical reactions. Therefore, to ensure the healthy and rapid growth of mung bean sprouts, precise control of parameters such as water quality, humidity, and temperature is necessary to address growth problems caused by unsuitable environmental parameters.

[0067] Traditional methods for controlling the environment in mung bean sprout cultivation often monitor and adjust only a single parameter or use a relatively simple threshold judgment method, ignoring the mutual influence and synergistic effects between various parameters. This approach cannot comprehensively and accurately reflect the overall state of the cultivation environment, easily leading to lag or over-adjustment, and failing to meet the complex environmental requirements for mung bean sprout growth. The multi-parameter synergistic control method proposed in this invention, through in-depth analysis of water quality, humidity, and temperature characteristic parameters, constructs a multimodal synergistic matrix and conducts core influencing factor analysis. Specifically, by collecting and analyzing multiple parameters in the mung bean sprout cultivation environment (such as temperature stability factor, humidity deviation index, and water quality activity coefficient), a multimodal synergistic matrix is ​​constructed. This matrix comprehensively reflects the influence of different environmental factors and their interactions on mung bean sprout growth. However, directly processing so many variables can be very complex. Therefore, a method is needed to simplify this data and identify the most critical factor combinations for mung bean sprout growth. This is the core influencing factor proposed in this invention. By comprehensively considering various parameters and their interrelationships, the state of the cultivation environment can be more accurately assessed, achieving precise and synergistic control of the mung bean sprout cultivation environment.

[0068] By deploying various sensors, such as water quality sensors, humidity sensors, and temperature sensors, in the mung bean sprout cultivation environment, real-time data on water quality, humidity, and temperature can be collected. This data can serve as the basis for subsequent analysis and control, enabling effective evaluation and adjustment of the cultivation environment through accurate real-time data.

[0069] The relative change rate of dissolved oxygen is obtained based on the water quality characteristic parameters, and the water quality activity coefficient is obtained based on the relative change rate of dissolved oxygen. The water quality characteristic parameters include the current dissolved oxygen concentration and pH measurement value. The relative change rate of dissolved oxygen can be calculated based on the current dissolved oxygen concentration and the historical baseline dissolved oxygen concentration. The relative change rate of dissolved oxygen reflects the dynamic change of oxygen content in the water. Dissolved oxygen is crucial for the respiration of mung bean sprouts, and changes in dissolved oxygen concentration directly affect the metabolism of bean sprouts. At the same time, the pH deviation is obtained based on the pH measurement value and the preset neutral pH value. The pH value affects the activity of microorganisms in the water and the absorption of nutrients by bean sprouts. Combining the relative change rate of dissolved oxygen and the pH deviation, the water quality activity coefficient can be obtained. Introducing the water quality activity coefficient to comprehensively reflect the water quality during the cultivation of mung bean sprouts is a scientific and reasonable method. The water quality activity coefficient can be used to quantify the suitability of water quality for the growth of mung bean sprouts. For example, when the relative change rate of dissolved oxygen increases, it indicates that the oxygen content in the water increases. If the pH deviation is also within a reasonable range, the calculated water quality activity coefficient will increase accordingly, indicating that the current water quality is more conducive to the growth of mung bean sprouts.

[0070] An evaporation rate coefficient is obtained based on the humidity characteristic parameters, and a humidity deviation index is obtained based on the evaporation rate coefficient. The humidity characteristic parameters include relative humidity data, air velocity, and the rate of change of evaporation surface temperature. The real-time evaporation rate can be calculated using these parameters. The real-time evaporation rate reflects the speed at which water evaporates in the growth environment of mung bean sprouts. Too fast or too slow water evaporation will affect the water balance of mung bean sprouts, thereby affecting their growth. By introducing and obtaining the evaporation rate coefficient, and combining it with the absolute humidity deviation value, a humidity deviation index can be obtained. This index is used to measure the suitability of the current humidity environment for the growth of mung bean sprouts. For example, when the air velocity is high, the real-time evaporation rate will be faster. If the relative humidity is low at this time, the absolute humidity deviation value will be large. The calculated humidity deviation index will show that the current humidity environment is not conducive to the growth of mung bean sprouts and needs to be adjusted.

[0071] The temperature gradient and fluctuation frequency are obtained based on the temperature characteristic parameters, and the temperature stability factor is obtained based on the temperature gradient and fluctuation frequency. First, the temperature value needs to be obtained from the temperature characteristic parameters, and then the maximum temperature difference value is calculated. The temperature gradient is obtained based on the maximum temperature difference value. The temperature gradient reflects the degree of temperature change within a certain time and space range. Drastic changes and frequent fluctuations in temperature will affect the activity of enzymes during the growth of mung bean sprouts and interfere with their normal physiological and biochemical reactions. The temperature stability factor is obtained based on the temperature gradient and fluctuation frequency. The temperature stability factor is used to assess the stability of the temperature environment and provides a basis for determining whether the temperature needs to be adjusted. For example, when the temperature gradient is large and the main fluctuation frequency is high, the temperature stability factor will be low, indicating that the current temperature environment is unstable and not conducive to the growth of mung bean sprouts.

[0072] A multimodal synergy matrix is ​​constructed based on the temperature stability factor, humidity deviation index, and water quality activity coefficient. This multimodal synergy matrix comprehensively considers various parameters such as water quality, humidity, and temperature, as well as their interrelationships, and can more comprehensively reflect the overall state of the cultivation environment. Core influencing factor analysis is performed on the multimodal synergy matrix to obtain a core influencing factor matrix, and growth regulation coefficients are obtained based on the core influencing factor matrix. The growth regulation coefficients are used to quantify the suitability of the current cultivation environment for the growth of mung bean sprouts, providing a basis for subsequent control decisions.

[0073] The system determines whether the growth control coefficient exceeds a preset range, which is determined based on the optimal environmental conditions for mung bean sprout growth. The calculated growth control coefficient is compared with the preset range to determine whether the current cultivation environment is suitable for mung bean sprout growth. If the growth control coefficient exceeds the preset range, a multi-parameter coordinated adjustment command is triggered. When the growth control coefficient exceeds the preset range, it indicates that parameters such as water quality, humidity, and temperature in the current cultivation environment are unsuitable for mung bean sprout growth. At this time, the multi-parameter coordinated adjustment command is triggered, and the corresponding adjustment equipment is activated to coordinately adjust each parameter so that the cultivation environment is restored to a state suitable for mung bean sprout growth. For example, if the growth control coefficient indicates that both humidity and temperature are unsuitable, the adjustment command will simultaneously control the humidifier, ventilation equipment, and heating / cooling equipment to coordinately adjust humidity and temperature.

[0074] If the growth regulation coefficient does not exceed the preset range, the current cultivation environment parameters are kept unchanged. If the growth regulation coefficient is within the preset range, it means that the current cultivation environment can meet the growth requirements of mung bean sprouts, and no adjustment is required. The current environment parameters can be kept unchanged.

[0075] Through the above series of steps, this invention achieves coordinated control of multiple parameters such as water quality, humidity, and temperature in the mung bean sprout cultivation environment. It can adjust parameters in a timely and accurate manner according to environmental changes, providing a stable and suitable environment for mung bean sprout growth. Compared with traditional methods, it significantly improves the accuracy and effectiveness of mung bean sprout cultivation environment control, ensuring the growth quality and yield of mung bean sprouts.

[0076] In one embodiment, the step of obtaining the relative change rate of dissolved oxygen based on the water quality characteristic parameters and obtaining the water quality activity coefficient based on the relative change rate of dissolved oxygen includes:

[0077] S21, Obtain the current dissolved oxygen concentration and pH measurement value based on the water quality characteristic parameters;

[0078] S22, obtain historical baseline dissolved oxygen concentration and preset neutral pH value, wherein the preset neutral pH value is 7;

[0079] S23, calculate the relative change rate of dissolved oxygen based on the current dissolved oxygen concentration and the historical baseline dissolved oxygen concentration. The calculation method of the relative change rate of dissolved oxygen is: divide the difference between the current dissolved oxygen concentration and the historical baseline dissolved oxygen concentration by the historical baseline concentration. This calculation method normalizes the absolute concentration change into a relative proportion, which can improve the sensitivity and assessment consistency of the dissolved oxygen state of the water body.

[0080] S24, obtain the pH offset based on the pH measurement value and the preset neutral pH value, wherein the pH offset is the absolute value of the interpolation between the pH measurement value and the preset neutral pH value;

[0081] S25, calculate the water quality activity coefficient based on the relative change rate of dissolved oxygen and the pH shift, wherein the calculation method is: with the natural constant e as the base and the exponent term being negative (the sum of the absolute value of the relative change rate of dissolved oxygen and the square of the pH shift).

[0082] As described in steps S21-S25 above, this invention obtains the current dissolved oxygen concentration and pH measurement values ​​from the water quality characteristic parameters, and combines them with historical benchmark data and preset standard values ​​to construct a water quality activity coefficient evaluation system. This enables a quantitative assessment of the water environment quality for mung bean sprout cultivation, providing a precise basis for multi-parameter collaborative control, and ultimately achieving the goal of optimizing cultivation water quality and ensuring the healthy growth of bean sprouts.

[0083] Traditional water quality monitoring methods mainly use single-parameter threshold control, such as setting only a lower limit for dissolved oxygen concentration (e.g., 5 mg / L) or a pH range (6.5-7.5). This method ignores the coupling effect between parameters. That is, when the dissolved oxygen concentration drops rapidly, even if the pH value is still within the normal range, the overall water activity may have been significantly reduced. This invention introduces two dimensions, the relative change rate of dissolved oxygen and the pH shift, and constructs a nonlinear mapping relationship to capture the dynamic change characteristics of water quality parameters. For example, when the dissolved oxygen concentration drops from 8 mg / L to 6 mg / L (relative change rate -25%), and the pH value shifts from 7.0 to 6.5, traditional methods would consider the water quality to still meet the standards. However, this invention, through the calculation of the water activity coefficient, can accurately identify that the water quality is already in a suboptimal state.

[0084] It is important to note that the historical baseline dissolved oxygen concentration was obtained by analyzing the statistical characteristics of the first 30 batches of cultivation data, and the baseline value was determined to be 7.8 ± 0.5 mg / L using the 3σ principle. The preset neutral pH value was set to 7.0, which meets the optimal acid-base environment for mung bean sprout growth. The historical baseline dissolved oxygen concentration reflects the stable operating state of the cultivation system, while the preset neutral pH value is determined based on the biological characteristics of bean sprouts. Both are used as reference standards to assess the degree to which the current water quality deviates from the ideal state.

[0085] By introducing the concept of historical baseline dissolved oxygen concentration, assessment errors caused by environmental differences can be avoided. This is because the initial dissolved oxygen concentration of water sources varies in different regions. For example, the dissolved oxygen concentration of water sources in mountainous areas is about 9 mg / L, while that in plain areas is about 7.5 mg / L. Using historical baseline values ​​can eliminate the impact of such regional differences.

[0086] pH offset directly reflects the degree to which the acidity or alkalinity of the water deviates from neutral. The optimal pH range for mung bean sprout culture medium is 6.5-7.5. Exceeding this range will inhibit enzyme activity. When pH=5.5, amylase activity decreases by 30%, leading to a decrease in starch hydrolysis efficiency. By introducing pH offset, the degree of acid and alkaline stress can be quantified. When the pH offset is >0.5, the dosage of acid-base regulator can be automatically adjusted to ensure that the pH of the mung bean sprout culture medium is always within the range suitable for mung bean sprout growth.

[0087] By integrating two independent parameters, the relative change rate of dissolved oxygen and the pH shift, into a comprehensive index, the water quality activity coefficient, through a nonlinear weighting function, it can comprehensively reflect the suitability of water quality for bean sprout growth. The water quality activity coefficient ranges from (0,1), with a larger value indicating higher water quality activity. This water quality activity coefficient provides a unified quantitative standard for multi-parameter collaborative control.

[0088] This invention solves the problem that traditional threshold control cannot adapt to dynamic environments by introducing the concepts of relative change rate of dissolved oxygen and pH offset, which can significantly improve cultivation efficiency and product quality.

[0089] Water quality is a key environmental factor affecting the growth of mung bean sprouts. Dissolved oxygen, as an essential substance for the metabolism of microorganisms and respiration of plants in water, directly affects the aerobic respiration efficiency of the bean sprout roots. When the dissolved oxygen concentration is low, the growth rate of mung bean sprouts decreases significantly, and the root length and fresh weight will decrease accordingly. pH value indirectly affects the growth of bean sprouts by affecting the solubility of nutrients and the activity of microorganisms. An acidic environment (pH<5.5) will inhibit the absorption of trace elements such as iron and manganese, leading to yellowing of bean sprouts. Therefore, real-time monitoring and quantitative assessment of water quality activity are crucial for maintaining the stability of the bean sprout cultivation environment.

[0090] In one embodiment, the step of obtaining the evaporation rate coefficient based on the humidity characteristic parameter and obtaining the humidity deviation index based on the evaporation rate coefficient includes:

[0091] S31, Obtain relative humidity data and air velocity based on the humidity characteristic parameters;

[0092] S32, obtain the evaporation surface temperature change rate according to the humidity characteristic parameters, and obtain the real-time evaporation rate according to the relative humidity data, air velocity and evaporation surface temperature change rate. The real-time evaporation rate is calculated as follows: the real-time evaporation rate is equal to the air velocity multiplied by (1 minus the decimal expression of the relative humidity percentage), then multiplied by (1 plus the evaporation surface temperature change rate), and finally divided by (1 plus the decimal expression of the relative humidity percentage).

[0093] S33, obtain the median of the ideal interval based on the preset optimal humidity range, and obtain the absolute humidity deviation value based on the median of the ideal interval;

[0094] S34, obtain a preset average evaporation rate, and obtain an evaporation rate coefficient based on the real-time evaporation rate and the preset average evaporation rate;

[0095] S35, Obtain the humidity deviation index based on the absolute humidity deviation value and the evaporation rate coefficient, wherein the humidity deviation index is calculated as follows: the humidity deviation index is equal to the sum of the absolute humidity deviation value multiplied by the first weighting coefficient and the evaporation rate coefficient multiplied by the second weighting coefficient, and the sum of the first weighting coefficient and the second weighting coefficient is equal to 1.

[0096] As described in steps S31-S35 above, by analyzing the humidity characteristic parameters in the mung bean sprout cultivation environment, the evaporation rate coefficient and humidity deviation index are obtained, thereby achieving a quantitative assessment and accurate description of the humidity status of the cultivation environment. This provides key data support for multi-parameter collaborative control in terms of humidity, ensuring that mung bean sprouts grow in a suitable humidity environment and avoiding problems such as dehydration and mold caused by improper humidity.

[0097] Humidity is a crucial environmental factor affecting the growth and development of mung bean sprouts. On the one hand, suitable humidity ensures that mung bean sprouts maintain a normal water balance, promoting cell turgor pressure stability and metabolism. On the other hand, excessive humidity easily breeds mold, leading to rotting and spoilage of the sprouts. Conversely, excessively low humidity causes excessive water evaporation, resulting in shriveling and slow growth. Furthermore, the humidity environment is not determined solely by relative humidity. Changes in air velocity and evaporation surface temperature also significantly affect the rate of water evaporation, thereby altering the actual effect of humidity on mung bean sprouts. Therefore, it is necessary to comprehensively consider multiple humidity-related parameters and establish a comprehensive humidity assessment system to accurately determine whether the current humidity environment is suitable for mung bean sprout growth, thus providing a basis for regulation.

[0098] Traditional methods for controlling humidity in mung bean sprout cultivation typically only monitor relative humidity. When the relative humidity (ranging from 0 to 100) deviates from a preset threshold, simple humidification or dehumidification is performed. This approach has significant shortcomings. First, it ignores the accelerating effect of airflow on moisture evaporation. Even when relative humidity is within the normal range, high airflow can cause rapid moisture loss from the surface of the bean sprouts during ventilation. Second, it does not consider the impact of changes in the evaporation surface temperature. During growth, the heat generated by the mung bean sprouts' metabolism raises the temperature of the evaporation surface, accelerating moisture evaporation. Traditional methods cannot detect this dynamic change.

[0099] It should be noted that, based on the biological characteristics of mung bean sprout growth, the preset optimal humidity range is 80%-90%, and the median of this range is calculated to be 85%. By subtracting the current relative humidity data from the median of the ideal range and taking the absolute value, the absolute humidity deviation value is obtained. The preset optimal humidity range is the ideal humidity environment for mung bean sprout growth, and the median of the ideal range serves as a reference benchmark. The absolute humidity deviation value can intuitively reflect the degree of deviation between the current relative humidity and the optimal humidity, and assess whether the humidity environment is suitable for mung bean sprout growth from a static perspective. When the current relative humidity is 75%, the absolute humidity deviation value is 10%, indicating that the current humidity is significantly lower than the optimal humidity. Based on this, the present invention can preliminarily determine whether humidification is required, providing direction for subsequent precise control.

[0100] The preset average evaporation rate refers to the evaporation rate obtained through multiple experiments under the optimal growth environment of mung bean sprouts simulated in the laboratory, such as a temperature of 25℃, relative humidity of 85%, and air velocity of 0.2m / s. It serves as a reference benchmark. The evaporation rate coefficient can eliminate the influence of environmental differences and reflect the degree of change of the current evaporation rate relative to the ideal state, thus evaluating the humidity environment from the perspective of dynamic evaporation process.

[0101] If the evaporation rate coefficient is greater than 1, it means that the water evaporates too quickly in the current environment. Even if the relative humidity is within the normal range, it may cause the mung bean sprouts to dehydrate. If the evaporation rate coefficient is less than 1, it means that the water evaporates too slowly and there may be a risk of excessive humidity. For example, when the evaporation rate coefficient is 1.3, it can be determined that it is necessary to strengthen the moisturizing measures to prevent the bean sprouts from losing water.

[0102] It should be noted that when calculating the humidity deviation index, the first and second weighting coefficients need to be determined by regression analysis based on a large amount of mung bean sprout growth experimental data.

[0103] This solution calculates the real-time evaporation rate by comprehensively analyzing relative humidity data, air velocity, and the rate of change of evaporation surface temperature. Combined with a preset optimal humidity range, it constructs an evaporation rate coefficient and a humidity deviation index. This method organically integrates multiple humidity-related parameters and comprehensively evaluates the humidity environment from two dimensions: static humidity deviation and dynamic evaporation process. It can more accurately reflect the actual impact of current humidity on mung bean sprout growth and provide more scientific and accurate humidity assessment results for multi-parameter collaborative control.

[0104] This embodiment demonstrates a certain degree of adaptability to unexpected situations during mung bean sprout cultivation. For example, when the sprout room is ventilated by opening the door, the hygrometer may show 82% (still within the suitable range of 80-90%), but the airflow rate may increase dramatically. Traditional methods would not trigger an alarm, and the actual airflow would accelerate moisture loss.

[0105] In this embodiment, when the real-time evaporation rate is detected to surge to 1.8 times the preset value (due to the large amount of water vapor being removed by ventilation), the humidity deviation value is calculated to be 15% (55% is the difference from the ideal value of 70%), and a humidity deviation index of 5.76 is generated (the formula assigns 70% weight to evaporation change and 30% weight to humidity deviation). Compared with the prior art, this embodiment can start humidification 30 minutes in advance to avoid the bean sprouts from shrinking due to latent dehydration, thus ensuring the cultivation quality of mung bean sprouts.

[0106] In one embodiment, the step of obtaining the temperature gradient and fluctuation frequency based on the temperature characteristic parameters, and obtaining the temperature stability factor based on the temperature gradient and fluctuation frequency, includes:

[0107] S41, obtain the temperature value based on the temperature characteristic parameters, and obtain the maximum temperature difference value based on the temperature value;

[0108] S42, Obtain the temperature gradient based on the maximum temperature difference value;

[0109] S43, Analyze the temperature gradient to obtain the main fluctuation frequency;

[0110] S44, Obtain the gradient influence coefficient based on the temperature gradient and the main fluctuation frequency;

[0111] S45, obtain the frequency deviation coefficient based on the main fluctuation frequency and the gradient influence coefficient, and obtain the temperature stability factor based on the frequency deviation coefficient and the gradient influence coefficient.

[0112] As described in steps S41-S45 above, by analyzing the temperature characteristic parameters in the mung bean sprout cultivation environment, the temperature gradient and fluctuation frequency are obtained, and the temperature stability factor is further obtained. This enables a quantitative assessment and accurate description of the temperature state of the cultivation environment, thereby providing key data support for multi-parameter collaborative control in the temperature dimension, ensuring that mung bean sprouts grow in a stable and suitable temperature environment, and avoiding the impact on their growth and development due to excessive temperature fluctuations or poor stability.

[0113] Temperature is one of the key environmental factors affecting the growth of mung bean sprouts. A suitable and stable temperature ensures the normal activity of enzymes within the sprouts, promoting the smooth progress of physiological processes such as metabolism, cell division, and elongation. Excessive temperature fluctuations can interfere with enzyme activity, leading to slow growth, deformed development, or even death of the sprouts. Too high a temperature will cause excessive respiration, consuming too many nutrients, while too low a temperature will inhibit enzyme activity and slow down growth. Furthermore, temperature gradients can affect the growth of different parts of the sprout; uneven temperature distribution can lead to inconsistent growth. Therefore, accurately assessing the stability and gradient of temperature is crucial for optimizing the mung bean sprout cultivation environment.

[0114] The temperature value is obtained based on the temperature characteristic parameters, and the maximum temperature difference value is obtained based on the temperature value. This can be achieved by arranging multiple high-precision temperature sensors in the mung bean sprout cultivation environment to collect temperature values ​​at different locations in real time. The maximum temperature difference value is obtained by subtracting the highest temperature value collected over a period of time (e.g., 1 hour) from the lowest temperature value. The temperature value reflects the real-time temperature of the current cultivation environment, while the maximum temperature difference value reflects the temperature change range over a certain period of time. A large maximum temperature difference value means a wide temperature fluctuation range, which will have an adverse effect on the growth of mung bean sprouts. Excessive temperature difference may lead to uneven water distribution in the bean sprout cells, affecting their normal physiological metabolism.

[0115] In a large mung bean sprout cultivation workshop, temperatures may vary in different areas. By obtaining the maximum temperature difference, areas with large temperature fluctuations can be identified in a timely manner, providing a basis for subsequent analysis of temperature gradients and the implementation of corresponding adjustment measures. If the maximum temperature difference in a certain area reaches 5°C within one hour, significantly higher than in other areas, further monitoring of temperature changes in that area is necessary.

[0116] The temperature gradient is obtained based on the maximum temperature difference. Assuming that the temperature sensors are evenly arranged in a vertical straight line in the mung bean sprout cultivation environment, the temperature gradient is calculated as follows: the temperature gradient is equal to the maximum temperature difference divided by the distance between adjacent sensors. The maximum temperature difference is the difference between the highest and lowest temperatures recorded by any two sensors within a set time period. If the sensors are not linearly distributed, the temperature data can be spatially interpolated using a spatial interpolation algorithm (such as Kriging interpolation) to obtain uniformly distributed virtual temperature data, and then the temperature gradient can be calculated.

[0117] A temperature gradient reflects the rate of temperature change in space; it represents the degree of temperature variation per unit distance. The existence of a temperature gradient leads to different temperature environments in different parts of the mung bean sprout, thus affecting the uniformity of its growth. If there is a large temperature gradient in the vertical direction, the roots and tops of the sprouts may grow at different rates, resulting in abnormal sprout morphology. The temperature gradient is in the vertical direction. Since the growth state of mung bean sprouts is a gradual upward expansion, the introduction of a temperature gradient mainly considers the temperature difference between the roots and tops of the sprouts, which can cause developmental abnormalities. By calculating the temperature gradient, we can understand the spatial distribution of temperature in the cultivation environment and determine whether there is a problem of uneven temperature. If the temperature gradient is large, it indicates that the temperature distribution of the cultivation environment needs to be adjusted, for example, by optimizing the layout of the ventilation system or heating / cooling equipment to make the temperature distribution more uniform and provide a more suitable growth environment for the mung bean sprouts.

[0118] The temperature gradient is analyzed to obtain the dominant fluctuation frequency. A Fourier transform is performed on the temperature gradient data over a period of time (e.g., 12 hours) to obtain the temperature gradient spectrum. In the spectrum, the frequency component with the largest energy (i.e., the largest amplitude) is identified. This frequency is the dominant fluctuation frequency of the temperature gradient, which indicates that the temperature gradient fluctuates most significantly at this frequency. The dominant fluctuation frequency reflects the periodicity of the temperature gradient fluctuation. Frequent fluctuations in the temperature gradient can interfere with the growth of mung bean sprouts. Different fluctuation frequencies may have different degrees of impact on the sprouts. For example, high-frequency fluctuations may make it difficult for the sprout cells to adapt to rapid temperature changes, affecting their normal physiological functions, while low-frequency fluctuations may cause the sprouts to be in an unsuitable temperature environment for a longer period of time.

[0119] By obtaining the main fluctuation frequency, we can understand the periodic characteristics of temperature gradient fluctuations and determine whether the current temperature fluctuations have an adverse effect on the growth of mung bean sprouts. If the main fluctuation frequency is too high or too low, it may be necessary to take corresponding measures to stabilize the temperature, such as adjusting the start-stop frequency of heating / cooling equipment or the operation mode of the ventilation system, in order to reduce the impact of temperature gradient fluctuations on the growth of bean sprouts.

[0120] The gradient influence coefficient is obtained based on the temperature gradient and the dominant fluctuation frequency. It can be obtained through experimental studies on the growth of mung bean sprouts under different temperature gradients and dominant fluctuation frequencies. By comprehensively considering the two parameters of temperature gradient and dominant fluctuation frequency, their combined impact on temperature stability is quantified. The gradient influence coefficient comprehensively reflects the degree of influence of temperature gradient and dominant fluctuation frequency on temperature stability. The larger the temperature gradient and the higher the dominant fluctuation frequency, the larger the gradient influence coefficient, indicating that the temperature environment is more unstable and the potential risk to the growth of mung bean sprouts is greater. When the temperature gradient is large and the dominant fluctuation frequency is high, the bean sprouts may grow poorly due to frequent temperature changes. By calculating the gradient influence coefficient, the stability of the temperature environment can be more comprehensively assessed. When the gradient influence coefficient exceeds a certain threshold, an early warning can be issued in time, and corresponding adjustment measures can be taken to strengthen the operation of temperature control equipment or optimize temperature regulation strategies to reduce the adverse effects of temperature gradient and fluctuation frequency on the growth of bean sprouts.

[0121] The frequency deviation coefficient is obtained based on the main fluctuation frequency and the gradient influence coefficient. The temperature stability factor is then obtained based on the frequency deviation coefficient and the gradient influence coefficient. First, the frequency deviation coefficient is calculated as follows: the frequency deviation coefficient equals the absolute value of the difference between the main fluctuation frequency and the optimal fluctuation frequency divided by the optimal fluctuation frequency. The optimal fluctuation frequency can be determined based on the growth characteristics of mung bean sprouts; typically, the optimal fluctuation frequency for mung bean sprout growth is 0.01 Hz. Finally, the temperature stability factor is calculated using the following formula:

[0122]

[0123] Among them, S T This represents the temperature stability factor, where γ is the weighting coefficient, and C... f Indicates the frequency deviation coefficient. The gradient influence coefficient is used to balance the contributions of the frequency deviation coefficient and the gradient influence coefficient to the temperature stability factor. The temperature stability factor is a dimensionless value with a range of [0,1]. The larger the value, the more stable the temperature environment. The weight coefficient γ can be determined by regression analysis of historical fault data, satisfying 0≤γ≤1. γ = 0.6 can be taken (based on the optimization results of 80 sets of operating data).

[0124] The frequency deviation coefficient reflects the degree of deviation between the current dominant fluctuation frequency and the optimal fluctuation frequency. The greater the deviation, the less favorable the temperature fluctuation frequency is for the growth of mung bean sprouts. The gradient influence coefficient reflects the degree of influence of the combined effect of temperature gradient and dominant fluctuation frequency on temperature stability. The temperature stability factor integrates these two factors and quantifies the stability of the current temperature environment. The closer its value is to 1, the more stable the temperature environment is, and the more favorable it is for the growth of mung bean sprouts. The closer its value is to 0, the more unstable the temperature environment is, and the more necessary it is to adjust the temperature.

[0125] By calculating the temperature stability factor, it is possible to accurately determine whether the current temperature environment is suitable for the growth of mung bean sprouts. When the temperature stability factor is below 0.6, the temperature regulation mechanism can be automatically triggered to adjust the operating parameters of the heating / cooling equipment or the working status of the ventilation system, so as to make the temperature environment more stable and provide good conditions for the growth of mung bean sprouts. At the same time, the temperature stability factor also provides a quantitative temperature index for multi-parameter collaborative control, which is convenient for comprehensive analysis and collaborative adjustment with other parameters such as water quality activity coefficient and humidity deviation index.

[0126] Traditional methods for controlling the temperature of mung bean sprout cultivation typically focus only on the average temperature. When the temperature exceeds the preset upper or lower limits, simple heating or cooling operations are performed. This approach has significant shortcomings: First, it ignores the impact of the frequency and gradient changes in temperature on sprout growth. Even if the average temperature is within the normal range, frequent fluctuations or large temperature gradient differences can still adversely affect sprout growth. Second, it cannot quantify temperature stability and cannot accurately determine whether the current temperature environment is suitable for mung bean sprout growth, resulting in a lack of targeted and precise control measures.

[0127] The solution proposed in this embodiment is to construct a temperature stability factor by comprehensively analyzing multiple temperature-related parameters such as temperature value, maximum temperature difference, temperature gradient, and fluctuation frequency. This method integrates multiple temperature characteristic parameters and comprehensively evaluates the stability of the temperature environment from two dimensions: temperature change gradient and fluctuation frequency. It can more accurately reflect the actual impact of the current temperature on the growth of mung bean sprouts and provide more scientific and accurate temperature assessment results for multi-parameter collaborative control.

[0128] In one embodiment, the step of constructing a multimodal cooperative matrix based on the temperature stability factor, humidity deviation index, and water quality activity coefficient includes:

[0129] S51 maps the temperature stability factor, humidity deviation index, and water quality activity coefficient into independent components of a three-dimensional vector space.

[0130] S52, obtain the temperature-humidity interaction coefficient based on the temperature stability factor and humidity deviation index;

[0131] S53, obtain the wet-water interaction coefficient based on the humidity deviation index and the water quality activity coefficient;

[0132] S54, combine the temperature-humidity interaction coefficient, the moisture-mass interaction coefficient and the temperature stability factor in columns to form an initial synergistic matrix;

[0133] S55, the initial cooperative matrix is ​​standardized to eliminate the dimensional differences of different parameters and obtain the multimodal cooperative matrix.

[0134] As described in steps S51-S55 above, this embodiment integrates temperature stability factor, humidity deviation index and water quality activity coefficient to construct a multimodal collaborative matrix, thereby achieving a comprehensive quantitative description of multiple key parameters in the mung bean sprout cultivation environment. This provides a foundation for subsequent core influencing factor analysis and growth regulation coefficient calculation, thus providing comprehensive and accurate data support for multi-parameter collaborative control, optimizing the mung bean sprout cultivation environment and promoting its healthy growth.

[0135] In the cultivation of mung bean sprouts, the three environmental factors of temperature, humidity, and water quality are not independent but interconnected and mutually influential. Changes in temperature affect the rate of water evaporation, which in turn affects the humidity environment. The quality of water also affects the absorption of water and nutrients by the sprouts, thus indirectly affecting their growth response to temperature and humidity. Therefore, a method is needed to comprehensively consider these three factors and their interactions to more fully assess the suitability of the cultivation environment for the growth of mung bean sprouts. The construction of a multimodal synergistic matrix is ​​based on this need. It quantifies the three parameters and their interrelationships, enabling us to grasp the overall state of the cultivation environment and provide a basis for precise regulation.

[0136] The temperature stability factor, humidity deviation index, and water quality activity coefficient are mapped to independent components in a three-dimensional vector space, wherein the temperature stability factor S T Humidity deviation index ΔR and water quality activity coefficient K w These represent environmental characteristics of temperature, humidity, and water quality, respectively, and are considered as three independent components in a three-dimensional vector space, i.e., vectors. In this way, each parameter has a clear position and direction in the vector space, which facilitates the analysis of their relationships. Mapping the three parameters to a three-dimensional vector space is to describe them within a unified mathematical framework. In this space, the magnitude and direction of each component reflect the characteristics of the corresponding parameter and its degree of influence on the growth environment of mung bean sprouts. The larger the temperature stability factor, the more stable the temperature environment, which is more favorable for the growth of mung bean sprouts, and the larger the corresponding component in the vector space. The larger the humidity deviation index, the more the humidity environment deviates from the suitable state, which is more unfavorable for the growth of mung bean sprouts, and its corresponding component will also change accordingly. In this way, the comprehensive situation of the three parameters under different environmental conditions can be intuitively compared and analyzed.

[0137] By mapping parameters to vector components, vector operations and spatial analysis can be used to study the relationships between them. The magnitude of the vectors can be calculated to measure the stability of the overall environment, or the angle between the vectors can be calculated to analyze the correlation between different parameters. This method provides richer analytical tools for multi-parameter collaborative control and helps to understand the influence mechanism of environmental factors on the growth of mung bean sprouts more deeply.

[0138] The temperature-humidity interaction coefficient is obtained based on the temperature stability factor and humidity deviation index. Then, the humidity-water quality interaction coefficient is calculated using a nonlinear coupling method based on the humidity deviation index and water quality activity coefficient. Since the interaction between temperature and humidity affects the growth environment of mung bean sprouts, the changes in temperature and humidity are often not isolated. Their synergistic effect may have a more complex impact on the growth of bean sprouts. In a high temperature and high humidity environment, bean sprouts are more susceptible to mold attack, while in a low temperature and low humidity environment, the growth rate of bean sprouts will be inhibited. The temperature-humidity interaction coefficient is used to quantify this synergistic effect. The larger its value, the more significant the impact of the interaction between temperature and humidity on the growth environment of bean sprouts.

[0139] By introducing the temperature-humidity interaction coefficient, its role is to assess how the two key environmental factors of temperature and humidity work together to affect the growth environment of mung bean sprouts, and to guide environmental regulation measures accordingly. By quantifying this synergistic effect, it is possible to more accurately determine whether the current environmental conditions are suitable for the growth of mung bean sprouts, and what regulatory measures need to be taken to optimize the growth environment. The temperature-humidity interaction coefficient takes into account the complex relationship between temperature and humidity, rather than simply assessing each factor individually.

[0140] In the cultivation of mung bean sprouts, the interaction between humidity and water quality affects the growth environment of the sprouts. The quality of water affects the efficiency of water absorption and utilization by the sprouts, while the humidity environment affects the evaporation of water on the surface of the sprouts and the growth of microorganisms. Therefore, there is a close relationship between humidity and water quality. The humidity-water quality interaction coefficient can be used to quantify this relationship. The larger the value, the more important the interaction between humidity and water quality is to the growth environment of the sprouts.

[0141] By calculating the moisture-water interaction coefficient, we can better understand the combined effects of humidity and water quality on mung bean sprout growth. In actual control, a large moisture-water interaction coefficient indicates that we need to pay attention to the regulation of both humidity and water quality, and consider their mutual influence. If the water quality is poor, we need to adjust the humidity environment appropriately to reduce the negative impact of water quality problems on bean sprout growth. Conversely, if the humidity environment is unsuitable, we need to improve the water quality to improve the growth quality of bean sprouts. This helps to achieve synergistic control of humidity and water quality, providing a better growth environment for mung bean sprouts. The purpose of setting the moisture-water interaction coefficient is to better understand how humidity and water quality work together to affect the growth environment of mung bean sprouts, and to guide corresponding control measures. There is a close relationship between humidity and water quality. By quantifying this relationship, we can more accurately determine whether the current environmental conditions are suitable for mung bean sprout growth and decide what regulatory measures need to be taken to optimize the growth environment.

[0142] The temperature-humidity interaction coefficient, the humidity-mass interaction coefficient, and the temperature stability factor are combined column-wise to form an initial synergy matrix, and the temperature-humidity interaction coefficient C is... T Moisture-mass interaction coefficient C H and temperature stability factor S T Arranged column-wise, they form an initial 3×1 cooperative matrix M0, i.e.

[0143] The initial synergy matrix is ​​a mathematical representation that integrates the three factors of temperature, humidity, and water quality and their interactions. By combining these three elements column-wise, a single matrix can simultaneously reflect the individual effects of the three factors and their interactions, providing a unified framework for subsequent analysis and processing. The initial synergy matrix provides a foundation for further data analysis and processing. We can perform various mathematical operations on the matrix, such as matrix multiplication and transpose, to study the relationships between different factors and their comprehensive impact on mung bean sprout growth. At the same time, the initial synergy matrix can also be used as input data for subsequent algorithms such as core influencing factor analysis to extract more valuable information and provide a decision-making basis for multi-parameter synergy control.

[0144] The initial coordination matrix is ​​standardized to eliminate the dimensional differences of different parameters, thus obtaining the multimodal coordination matrix. This is because the temperature and humidity interaction coefficient C... T Moisture-mass interaction coefficient C H and temperature stability factor S T

[0145] Since they have different dimensions and ranges of values, in order to eliminate these differences and facilitate subsequent analysis and comparison, the initial synergy matrix needs to be standardized. The calculation formula is as follows:

[0146]

[0147] Where M is the standardized multimodal collaboration matrix, μ represents the mean vector of the initial collaboration matrix M0, and σ represents the standard deviation vector of the initial collaboration matrix M0. The specific calculation process is as follows:

[0148]

[0149] Where n is the number of samples, and These are the temperature-humidity interaction coefficient, moisture-mass interaction coefficient, and temperature stability factor for the i-th sample, respectively.

[0150] The purpose of standardization is to transform parameters with different dimensions and value ranges into dimensionless data with the same scale, making them comparable in subsequent analyses. After standardization, each element in the multimodal synergy matrix represents the degree of deviation of the parameter from its mean, thereby eliminating the influence of dimensional differences on the analysis results. Therefore, it can more accurately reflect the relative relationships and comprehensive effects between different parameters. In subsequent operations such as core influencing factor analysis, the standardized matrix can better extract the main features of the data and avoid analytical errors caused by dimensional differences. At the same time, the standardized matrix is ​​also easier to compare and integrate with other data, providing more reliable data support for multi-parameter synergy control.

[0151] The solution proposed in this embodiment is to construct a multimodal synergy matrix, using temperature stability factor, humidity deviation index, and water quality activity coefficient as elements of the matrix, and considering their interactions (reflected by temperature-humidity interaction coefficient and humidity-quality interaction coefficient). This method can comprehensively and accurately reflect the overall state of multiple parameters in the cultivation environment and the complex relationships between them. By analyzing the multimodal synergy matrix, the suitability of the environment for mung bean sprout growth can be assessed more accurately, thereby providing a scientific basis for multi-parameter synergistic control and improving the accuracy and effectiveness of regulation.

[0152] In one embodiment, the step of performing core influence factor analysis on the multimodal synergy matrix to obtain a core influence factor matrix, and obtaining the growth regulation coefficient based on the core influence factor matrix, includes:

[0153] S56, Obtain the covariance matrix based on the multimodal cooperative matrix;

[0154] S57, Perform eigenvalue decomposition on the covariance matrix and extract the eigenvectors corresponding to the first K largest eigenvalues;

[0155] S58, Project the original data of the multimodal collaborative matrix onto the feature space formed by the feature vectors to generate a core influence factor matrix, wherein each column of the core influence factor matrix corresponds to a core influence factor score.

[0156] S59. Obtain the variance contribution rate of each core influence factor based on the feature vector and the core influence factor score, and obtain the growth regulation coefficient based on the variance contribution rate.

[0157] As described in steps S56-S59 above, core influence factor analysis enables objective evaluation of data-driven processes. Utilizing the covariance matrix and eigenvalue decomposition, the weights of core influence factors are determined based on the inherent variability of the data, avoiding human interference. The temperature-humidity interaction coefficient C constructed earlier... T Moisture-mass interaction coefficient C H As matrix elements, they can be mapped to specific core impact factors in core impact factor analysis, explicitly expressing the nonlinear effects between parameters. By selecting the top K core impact factors (e.g., K=2), more than 80% of the key information can be retained, and the multidimensional problem can be simplified into a comprehensive evaluation in a two-dimensional space, which can improve decision-making efficiency.

[0158] Based on the multimodal collaboration matrix, obtain the covariance matrix. Let the multimodal collaboration matrix be the standardized matrix M∈R. n×m Where n is the number of samples, and m = 3 is the parameter dimension, i.e., the temperature-humidity interaction coefficient C. T Moisture-mass interaction coefficient C Hand temperature stability factor S T There are three key environmental factors, each representing a dimension, therefore m = 3. The formula for calculating the covariance matrix Σ is:

[0159]

[0160] Where, Σ i，j Σ represents the covariance between the i-th parameter and the j-th parameter. In this embodiment, Σ 1，2 The temperature and humidity interaction coefficient C represents T Interaction coefficient C with wet mass H covariance, Σ 1，3 The temperature and humidity interaction coefficient C represents T and temperature stability factor S T covariance, Σ 2，3 The wet-mass interaction coefficient C H and temperature stability factor S T The covariance of M, calculated using this formula, reflects the linear correlation between the two. The elements in M ​​are derived from the standardization process described above, specifically by mapping a three-dimensional vector, calculating the interaction coefficients, and standardizing the matrix. T The transpose of the initial cooperative matrix M is represented by M. T The operation of M can calculate an m×m covariance matrix Σ. i，j This reflects the linear correlation between the two, and this operation allows for the quantification of the relationship between different parameters.

[0161] The covariance matrix described above characterizes the cooperative variation law among parameters. For example, if Σ 1，2 (temperature and humidity interaction coefficient C) T Interaction coefficient C with wet mass H A positive covariance indicates that when the temperature-humidity interaction is strong, the humidity-water quality interaction also tends to be enhanced, reflecting that water quality is more prone to deterioration under high temperature and high humidity environments.

[0162] The technique involves eigenvalue decomposition of the covariance matrix to extract the eigenvectors corresponding to the K largest eigenvalues. This is achieved by performing eigenvalue decomposition on Σ: Σ = QΛQ T ;

[0163] Where Λ=diag(λ1,λ2,λ3) is the eigenvalue matrix (λ1≥λ2≥λ3);

[0164] Q = [q1, q2, q3] is the eigenvector matrix. The eigenvectors [q1, ..., q3] corresponding to the K largest eigenvalues ​​are selected. k Typically, K is set to 1 or 2 to ensure that the cumulative variance contribution rate is ≥80%.

[0165] The eigenvalue λ iThe value of q1 represents the variance of the original data that the i-th core influence factor can explain, reflecting the importance of this core influence factor. The element values ​​of the eigenvector qi represent the contribution of the original parameters to this core influence factor. For example, if q1 = [0.6, 0.6, 0.3], it indicates that the temperature-humidity interaction coefficient and the humidity-matter interaction coefficient contribute significantly to the first core influence factor, and this core influence factor can be named the "temperature-humidity-matter synergistic effect factor".

[0166] The original data is projected onto the feature space formed by the feature vectors to generate the core influence factor matrix, wherein the core influence factor matrix PC = M × Q. k (Q k The matrix PC consists of the first K eigenvectors. Each column of PC corresponds to a core influence factor score (e.g., PC1, PC2). The projection process transforms the linear combination of the original parameters into core influence factors, achieving data dimensionality reduction. For example, the first core influence factor score PC1 can represent the "intensity of the synergistic effect of temperature and humidity-wet matter", and the second core influence factor score PC2 can represent the "independent influence of temperature stability". The dimensionality-reduced data can be visualized through a two-dimensional scatter plot (e.g., PC1 on the horizontal axis and PC2 on the vertical axis), intuitively distinguishing the environmental stress types of different samples (e.g., if a sample has a high PC1 and a low PC2, it indicates that the main problem is an excessively strong interaction between temperature and humidity-wet matter).

[0167] The variance contribution rate is obtained based on the eigenvector and the core influence factor score. The growth regulation coefficient is then calculated, and the variance contribution rate of the i-th core influence factor is determined. The formula for calculating the growth regulation coefficient is:

[0168]

[0169] Among them, G R This represents the growth regulation coefficient.

[0170] The variance contribution rate is used as a weight to ensure that core influencing factors that have a significant impact on data variation are included in G. R The proportion is higher in the middle; for example, if the first core impact factor explains 70% of the variance, its score is in the G range. R The first core impact factor has a weight of 0.7, while the second core impact factor explains 27% of the variance and has a weight of 0.27.

[0171] Example: If ∝1 = 0.7, PC1 = 1.5, ∝1 = 0.27, PC2 = 0.8, then:

[0172] G R =0.7×|1.5|+0.27×|0.8|=1.05+0.216=1.266, and the preset threshold is [0,1], then the adjustment command is triggered.

[0173] This embodiment avoids the subjectivity of manually setting weights, with growth regulation coefficients entirely data-driven, enhancing the reliability of the assessment. Through core influencing factor extraction, it can simultaneously identify anomalies in single parameters (such as excessively low temperature stability factors) and parameter interactions (such as excessively high temperature-humidity interaction coefficients), making regulation more targeted. In mung bean sprout cultivation, certain combinations of environmental conditions may reflect their impact on growth more effectively than considering a single factor. For example, the interaction between temperature and humidity (temperature-humidity interaction coefficient) or the relationship between humidity and water quality (humidity-water quality interaction coefficient). Core influencing factor extraction identifies the key combinations that best explain differences in mung bean sprout growth, helping to understand which environmental conditions require special attention and adjustment. This method relies entirely on actual monitoring data, avoiding the subjectivity problems caused by manually setting weights. Through learning from a large amount of historical data, core influencing factor extraction can automatically determine which factors are most critical for mung bean sprout growth and provide corresponding regulation suggestions. This approach improves the objectivity and accuracy of decision-making, contributing to increased yield and quality of mung bean sprouts.

[0174] In one embodiment, the step of obtaining the corresponding regulation level based on the growth regulation coefficient and synergistically controlling the cultivation environment of mung bean sprouts according to the regulation level includes:

[0175] S61, obtain the corresponding regulation level according to the growth regulation coefficient, wherein the regulation level includes a first regulation level, a second regulation level and a third regulation level. It should be noted that in this embodiment, the specific regulation level threshold can be set according to historical data and experimental results. For example, the range of the first regulation level can be set to within 0.5, the range of the second regulation level can be 0.5-0.8, and if it exceeds 0.8, it enters the third regulation level. These thresholds should be optimized and adjusted according to actual production needs and the biological characteristics of mung bean sprouts.

[0176] S62, generate a first control command based on the first control level. When the growth control coefficient is at the first control level, it is determined to be a slight deviation state. The first control command is used to control the oxygenation equipment and humidity control equipment to adjust the oxygen supply, humidification or dehumidification of mung bean sprouts. When the growth control coefficient is at this level, it indicates that the current environmental parameters are only slightly deviated from the optimal state. At this time, the main focus is on water activity and humidity deviation, because these factors have a greater impact on the initial growth of mung bean sprouts.

[0177] S63, a second control instruction is generated according to the second control level. When the growth control coefficient is at the second control level, it is determined to be a moderate deviation state. The second control instruction is used to control the temperature controller and the oxygenation equipment to adjust the temperature and dissolved oxygen concentration of mung bean sprouts in a coordinated manner. At this level, not only are there problems with water quality and humidity, but temperature stability also begins to fluctuate. It is necessary to adjust the temperature and dissolved oxygen concentration at the same time to restore suitable growth conditions.

[0178] S64, a third control command is generated based on the third control level. When the growth control coefficient is at the third control level, it is determined to be a severely deviated state. The third control command is used to control the water circulation system to perform water exchange, control the humidity control equipment to perform forced adjustment, and control the temperature controller to forcefully enter the constant temperature mode. At the same time, the alarm device is triggered to issue an abnormal alarm. When this level is reached, it indicates that the current environment has seriously deviated from the optimal state, and all key parameters need to be adjusted urgently. At this time, more aggressive measures such as water exchange, forced adjustment of humidity and temperature are taken, and an alarm is issued.

[0179] The aforementioned hierarchical control strategy can generate corresponding control instructions based on the specific circumstances of different levels, ensuring that each adjustment is an optimization targeting the most pressing issues. This achieves refined control of multiple key parameters in the mung bean sprout cultivation environment, which not only improves production efficiency but also promotes the effective utilization of resources.

[0180] like Figure 2 As shown, this invention also discloses a multi-parameter coordinated control system for water quality, humidity, and temperature in mung bean sprout cultivation, comprising:

[0181] The first acquisition module is used to acquire real-time monitoring data of the mung bean sprout cultivation environment, wherein the real-time monitoring data includes water quality characteristic parameters, humidity characteristic parameters and temperature characteristic parameters;

[0182] The second acquisition module is used to acquire the relative change rate of dissolved oxygen based on the water quality characteristic parameters, and to acquire the water quality activity coefficient based on the relative change rate of dissolved oxygen.

[0183] The third acquisition module is used to acquire the evaporation rate coefficient based on the humidity characteristic parameters, and to acquire the humidity deviation index based on the evaporation rate coefficient.

[0184] The fourth acquisition module is used to acquire the temperature gradient and fluctuation frequency based on the temperature characteristic parameters, and to acquire the temperature stability factor based on the temperature gradient and fluctuation frequency.

[0185] The module is used to construct a multimodal synergy matrix based on the temperature stability factor, humidity deviation index and water quality activity coefficient, perform core influence factor analysis on the multimodal synergy matrix to obtain a core influence factor matrix, and obtain the growth regulation coefficient based on the core influence factor matrix.

[0186] The judgment module is used to obtain the corresponding control level based on the growth control coefficient, and to coordinately control the cultivation environment of mung bean sprouts according to the control level.

[0187] In one embodiment, the fourth acquisition module includes:

[0188] The first acquisition unit is used to acquire a temperature value based on the temperature characteristic parameters and to acquire a maximum temperature difference value based on the temperature value.

[0189] The second acquisition unit is used to acquire the temperature gradient based on the maximum temperature difference value;

[0190] An analysis unit is used to analyze the temperature gradient and obtain the main fluctuation frequency;

[0191] The third acquisition unit is used to acquire the gradient influence coefficient based on the temperature gradient and the main fluctuation frequency.

[0192] The fourth acquisition unit is used to acquire a frequency deviation coefficient based on the main fluctuation frequency and the gradient influence coefficient, and to acquire a temperature stability factor based on the frequency deviation coefficient and the gradient influence coefficient.

[0193] This application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method for coordinated control of multiple parameters such as water quality, humidity, and temperature in mung bean sprout cultivation.

[0194] This application also provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the steps of the above-described method for coordinated control of multiple parameters such as water quality, humidity, and temperature in mung bean sprout cultivation.

[0195] The above description is merely a preferred embodiment of the present invention and does not limit the scope of this application. Any equivalent results or equivalent process transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the scope of protection of this application.

Claims

1. A method for the coordinated control of multiple parameters, including water quality, humidity, and temperature, in mung bean sprout cultivation, characterized in that, Includes the following steps: Real-time monitoring data of the mung bean sprout cultivation environment is obtained, wherein the real-time monitoring data includes water quality characteristic parameters, humidity characteristic parameters, and temperature characteristic parameters; The relative change rate of dissolved oxygen is obtained based on the water quality characteristic parameters, and the water quality activity coefficient is obtained based on the relative change rate of dissolved oxygen. The evaporation rate coefficient is obtained based on the humidity characteristic parameters, and the humidity deviation index is obtained based on the evaporation rate coefficient. The temperature gradient and fluctuation frequency are obtained based on the temperature characteristic parameters, and the temperature stability factor is obtained based on the temperature gradient and fluctuation frequency. A multimodal synergy matrix is ​​constructed based on the temperature stability factor, humidity deviation index, and water quality activity coefficient. Core influencing factor analysis is performed on the multimodal synergy matrix to obtain a core influencing factor matrix. Growth regulation coefficients are obtained based on the core influencing factor extraction matrix. The corresponding regulation level is obtained based on the growth regulation coefficient, and the cultivation environment of mung bean sprouts is synergistically controlled according to the regulation level.

2. The method for coordinated control of multiple parameters such as water quality, humidity, and temperature in mung bean sprout cultivation according to claim 1, characterized in that, The steps of obtaining the relative change rate of dissolved oxygen based on the water quality characteristic parameters and obtaining the water quality activity coefficient based on the relative change rate of dissolved oxygen include: The current dissolved oxygen concentration and pH value are obtained based on the water quality characteristic parameters. Obtain historical baseline dissolved oxygen concentration and preset neutral pH value; The relative rate of change of dissolved oxygen is obtained based on the current dissolved oxygen concentration and the historical baseline dissolved oxygen concentration. The pH offset is obtained based on the pH measurement value and the preset neutral pH value; The water quality activity coefficient is obtained based on the relative change rate of dissolved oxygen and the pH shift.

3. The method for synergistic control of multiple parameters such as water quality, humidity, and temperature in mung bean sprout cultivation according to claim 1, characterized in that, The steps of obtaining the evaporation rate coefficient based on the humidity characteristic parameters and obtaining the humidity deviation index based on the evaporation rate coefficient include: Based on the humidity characteristic parameters, relative humidity data, air velocity, and evaporation surface temperature change rate are obtained. The real-time evaporation rate is obtained based on the relative humidity data, air velocity, and the rate of change of evaporation surface temperature. The median of the ideal interval is obtained based on the preset optimal humidity range, and the absolute humidity deviation value is obtained based on the median of the ideal interval. Obtain a preset average evaporation rate, and obtain an evaporation rate coefficient based on the real-time evaporation rate and the preset average evaporation rate; The humidity deviation index is obtained based on the absolute humidity deviation value and the evaporation rate coefficient.

4. The method for coordinated control of multiple parameters such as water quality, humidity, and temperature in mung bean sprout cultivation according to claim 1, characterized in that, The step of obtaining the temperature gradient and fluctuation frequency based on the temperature characteristic parameters, and obtaining the temperature stability factor based on the temperature gradient and fluctuation frequency, includes: The temperature value is obtained based on the temperature characteristic parameters, and the maximum temperature difference value is obtained based on the temperature value. The temperature gradient is obtained based on the maximum temperature difference value; The temperature gradient is analyzed to obtain the main fluctuation frequency; The gradient influence coefficient is obtained based on the temperature gradient and the main fluctuation frequency. The frequency deviation coefficient is obtained based on the main fluctuation frequency and the gradient influence coefficient, and the temperature stability factor is obtained based on the frequency deviation coefficient and the gradient influence coefficient.

5. The method for coordinated control of multiple parameters such as water quality, humidity, and temperature in mung bean sprout cultivation according to claim 1, characterized in that, The steps of constructing a multimodal synergy matrix based on the temperature stability factor, humidity deviation index, and water quality activity coefficient, performing core influence factor analysis on the multimodal synergy matrix to obtain a core influence factor matrix, and obtaining the growth regulation coefficient based on the core influence factor matrix include: The temperature stability factor, humidity deviation index, and water quality activity coefficient are mapped to independent components in a three-dimensional vector space. The temperature-humidity interaction coefficient is obtained based on the temperature stability factor and humidity deviation index. The humidity-water interaction coefficient is obtained based on the humidity deviation index and the water quality activity coefficient. The temperature-humidity interaction coefficient, the moisture-mass interaction coefficient, and the temperature stability factor are combined in columns to form an initial synergistic matrix; The initial cooperative matrix is ​​standardized to eliminate the dimensional differences of different parameters and obtain the multimodal cooperative matrix. Based on the multimodal collaboration matrix, obtain the covariance matrix; The covariance matrix is ​​decomposed into eigenvalues ​​to extract the eigenvectors corresponding to the K largest eigenvalues. The original data of the multimodal collaborative matrix is ​​projected onto the feature space formed by the feature vectors to generate a core influence factor matrix, where each column of the core influence factor matrix corresponds to a core influence factor score. The variance contribution rate of each core influence factor is obtained based on the feature vector and the core influence factor score, and the growth regulation coefficient is obtained based on the variance contribution rate.

6. The method for coordinated control of multiple parameters such as water quality, humidity, and temperature in mung bean sprout cultivation according to claim 1, characterized in that, The step of obtaining the corresponding regulation level based on the growth regulation coefficient and synergistically controlling the cultivation environment of mung bean sprouts according to the regulation level includes: The corresponding regulation level is obtained based on the growth regulation coefficient, wherein the regulation level includes a first regulation level, a second regulation level, and a third regulation level; A first control instruction is generated based on the first control level. The first control instruction is used to control the oxygenation equipment and humidity control equipment to adjust the oxygen supply, humidification or dehumidification of mung bean sprouts. A second control instruction is generated based on the second control level. The second control instruction is used to control the temperature controller and the oxygenation equipment to adjust the temperature and dissolved oxygen concentration of the mung bean sprouts in a coordinated manner. A third control instruction is generated based on the third control level. The third control instruction is used to control the water circulation system to perform water exchange operation, control the humidity control equipment to perform forced adjustment, control the temperature controller to forcefully enter the constant temperature mode, and trigger the alarm device to issue an abnormal alarm.

7. A multi-parameter coordinated control system for water quality, humidity, and temperature in mung bean sprout cultivation, characterized in that, include: The first acquisition module is used to acquire real-time monitoring data of the mung bean sprout cultivation environment, wherein the real-time monitoring data includes water quality characteristic parameters, humidity characteristic parameters and temperature characteristic parameters; The second acquisition module is used to acquire the relative change rate of dissolved oxygen based on the water quality characteristic parameters, and to acquire the water quality activity coefficient based on the relative change rate of dissolved oxygen. The third acquisition module is used to acquire the evaporation rate coefficient based on the humidity characteristic parameters, and to acquire the humidity deviation index based on the evaporation rate coefficient. The fourth acquisition module is used to acquire the temperature gradient and fluctuation frequency based on the temperature characteristic parameters, and to acquire the temperature stability factor based on the temperature gradient and fluctuation frequency. The module is used to construct a multimodal synergy matrix based on the temperature stability factor, humidity deviation index and water quality activity coefficient, perform core influence factor analysis on the multimodal synergy matrix to obtain a core influence factor matrix, and obtain the growth regulation coefficient based on the core influence factor matrix. The judgment module is used to obtain the corresponding control level based on the growth control coefficient, and to coordinately control the cultivation environment of mung bean sprouts according to the control level.

8. The multi-parameter coordinated control system for water quality, humidity, and temperature in mung bean sprout cultivation according to claim 7, characterized in that, The fourth acquisition module includes: The first acquisition unit is used to acquire a temperature value based on the temperature characteristic parameters and to acquire a maximum temperature difference value based on the temperature value. The second acquisition unit is used to acquire the temperature gradient based on the maximum temperature difference value; An analysis unit is used to analyze the temperature gradient and obtain the main fluctuation frequency; The third acquisition unit is used to acquire the gradient influence coefficient based on the temperature gradient and the main fluctuation frequency. The fourth acquisition unit is used to acquire a frequency deviation coefficient based on the main fluctuation frequency and the gradient influence coefficient, and to acquire a temperature stability factor based on the frequency deviation coefficient and the gradient influence coefficient.

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 method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images