Live shrimp non-water transportation environment automatic optimization method and system based on internet of things

Abstract

The application relates to the technical field of environment monitoring and control, and discloses a shrimp waterless transportation environment automatic optimization method and system based on Internet of Things. The method comprises the following steps: collecting multi-dimensional environment parameters such as temperature, humidity and oxygen concentration in a shrimp waterless transportation container through a distributed sensor network, intelligently identifying physiological states such as dormancy degree, stress level and molting cycle of shrimp bodies based on environment data, generating temperature-humidity-oxygen collaborative control instructions by using a multivariate coupling control algorithm, driving a self-adaptive actuator group to perform coordinated control such as refrigeration, spraying and oxygen supply, and dynamically compensating according to the molting cycle and transportation time through a predictive deviation correction mechanism. The application solves the technical problems that the environment control lacks intelligentization and collaboration in the existing shrimp transportation technology and cannot be predictively adjusted according to the physiological state of the shrimp body, and improves the precision of environment control in the transportation process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of environmental monitoring and control, and particularly relates to a live shrimp waterless transportation environment automatic optimization method and system based on Internet of Things. BACKGROUND

[0002] The existing live shrimp transportation technology mainly adopts water transportation, that is, live shrimps are placed in containers filled with seawater or freshwater for transportation, and the survival of shrimps is ensured through means such as maintaining water temperature, increasing oxygen, and water quality purification. The traditional water transportation method needs to be transported according to the proportion of 1:3 of the weight of shrimps to water, and auxiliary equipment such as temperature control equipment, oxygen increasing equipment, and water circulation filtration system is equipped. Some advanced transportation technologies also use single parameter monitoring methods to simply monitor the transportation environment through temperature sensors or dissolved oxygen sensors, but these monitoring systems can usually only detect a single environmental indicator and lack comprehensive analysis capabilities for the coordinated changes of multiple parameters.

[0003] The existing technology has significant deficiencies such as high transportation cost, insufficient control precision, and low intelligence. In the water transportation method, up to 75% of the fuel and logistics cost is actually used to transport the weight of water, and the cost of equipment for maintaining water temperature, oxygen supply, and water quality purification needs to be additionally borne, resulting in low overall transportation economic efficiency. The existing environmental monitoring technology uses independent single parameter control method, which cannot identify the physiological state changes of shrimps and cannot establish the coupling relationship between environmental parameters, resulting in lack of pertinence and predictability of environmental control strategy. The traditional control method mainly relies on manual experience and simple threshold control, and cannot dynamically adjust according to the molting cycle and metabolic state of shrimps, which is easy to cause control failure in the key physiological stage.

[0004] Secondly, the existing technology lacks intelligent identification technology for the physiological state of shrimps, and cannot perform differential control of environmental parameters according to the dormancy degree, stress level, and molting cycle of shrimps, resulting in mismatch between environmental regulation strategy and physiological needs of shrimps. Secondly, there is a lack of coupling control mechanism for multiple environmental parameters, and independent control of parameters such as temperature, humidity, and oxygen concentration will interfere with each other, and cannot achieve the effect of coordinated optimization of environmental regulation. Thirdly, there is a lack of predictive control ability based on transportation time and molting cycle, which cannot predict the cumulative deviation of environmental parameters and the change trend of physiological state of shrimps in advance, resulting in the lag and passivity of control strategy. Finally, there is a lack of coordination mechanism and precision compensation technology among actuators, and multiple actuators work at the same time will interfere with each other, and the cumulative error in the long-term transportation process cannot be effectively corrected, affecting the overall control precision and stability. SUMMARY

[0005] The application provides a live shrimp waterless transportation environment automatic optimization method and system based on Internet of Things, which is used to solve the technical problems of lack of intelligentization and collaboration in environment control in the existing live shrimp transportation technology, and inability to make predictive adjustment according to the physiological state of shrimp, and improve the precision of environment control in the transportation process.

[0006] In a first aspect, the application provides a live shrimp waterless transportation environment automatic optimization method based on Internet of Things, which comprises: collecting and processing the environmental parameters in the live shrimp waterless transportation container in real time through a distributed sensor network to obtain a multi-dimensional environmental parameter data set containing temperature field data, humidity distribution data and oxygen concentration data; intelligently identifying and processing the physiological state of shrimp according to the multi-dimensional environmental parameter data set to obtain shrimp physiological state evaluation data containing shrimp dormancy index, stress level grade and molting cycle prediction value; calculating and processing the environmental adjustment strategy of the shrimp physiological state evaluation data through a multivariate coupled control algorithm to obtain a collaborative control instruction set of temperature-humidity-oxygen concentration; coordinately driving the adaptive actuator group according to the collaborative control instruction set to obtain actuator response parameters containing refrigeration power adjustment amount, spraying frequency parameter and oxygen supply flow set value; and dynamically modifying the actuator response parameters through a predictive bias correction mechanism to obtain environmental control precision compensation data based on the change of shrimp molting cycle and transportation time.

[0007] In a second aspect, the application provides a live shrimp waterless transportation environment automatic optimization system based on Internet of Things, which comprises:

[0008] The collection module is used to collect and process the environmental parameters in the live shrimp waterless transportation container in real time through a distributed sensor network to obtain a multi-dimensional environmental parameter data set containing temperature field data, humidity distribution data and oxygen concentration data;

[0009] The identification module is used to intelligently identify and process the physiological state of shrimp according to the multi-dimensional environmental parameter data set to obtain shrimp physiological state evaluation data containing shrimp dormancy index, stress level grade and molting cycle prediction value;

[0010] The calculation module is used to calculate and process the environmental adjustment strategy of the shrimp physiological state evaluation data through a multivariate coupled control algorithm to obtain a collaborative control instruction set of temperature-humidity-oxygen concentration;

[0011] The driving module is used to coordinately drive the adaptive actuator group according to the collaborative control instruction set to obtain actuator response parameters containing refrigeration power adjustment amount, spraying frequency parameter and oxygen supply flow set value;

[0012] A correction module is configured to dynamically correct the actuator response parameter by a predictive bias correction mechanism to obtain environment control precision compensation data based on changes in the molting cycle and transportation time of the shrimp.

[0013] In a third aspect, an Internet-of-Things-based automatic optimization device for a live shrimp non-water transportation environment is provided, which includes a memory and at least one processor, the memory storing instructions; the at least one processor invokes the instructions in the memory to enable the Internet-of-Things-based automatic optimization device for a live shrimp non-water transportation environment to perform the above-mentioned Internet-of-Things-based automatic optimization method for a live shrimp non-water transportation environment.

[0014] In a fourth aspect, a computer-readable storage medium is provided, which stores instructions that, when executed on a computer, enable the computer to perform the above-mentioned Internet-of-Things-based automatic optimization method for a live shrimp non-water transportation environment.

[0015] In the technical solution provided in the present application, the environment parameters in the live shrimp non-water transportation container are collected and processed in real time by a distributed sensor network, a multi-dimensional environment parameter data set of temperature field data, humidity distribution data and oxygen concentration data is established, which has a significant advantage over the single parameter monitoring of the prior art and can comprehensively grasp the spatial distribution and time variation characteristics of the environment state in the container. Based on the multi-dimensional environment parameter data set, the physiological state of the shrimp is intelligently identified and processed, and an innovative correlation model between the environment parameters and the physiological indicators of the shrimp is established. Through the shrimp physiological state evaluation data of the dormancy degree index, the stress level grade and the molting cycle prediction value, the technical problem that the prior art cannot identify the physiological state change of the shrimp is solved. The application of the multivariate coupling control algorithm enables the temperature, humidity and oxygen concentration to be controlled in coordination, overcoming the problem of mutual interference between parameters in the traditional independent control mode, and ensuring the accurate matching of the environment adjustment strategy and the physiological needs of the shrimp. The coordinated driving process of the self-adaptive actuator group avoids conflicts and resource waste between actuators through accurate control of the refrigeration power adjustment amount, the spray frequency parameter and the oxygen supply flow set value, greatly improving the efficiency and stability of the environment control.

[0016] The introduction of a predictive bias correction mechanism enables dynamic adjustments to environmental control accuracy compensation data based on changes in the shrimp molting cycle and transportation time, effectively solving the problem of decreased control accuracy caused by accumulated errors during long-term transportation. In the specific application of live shrimp waterless transportation, the integrated application of core algorithms such as wavelet transform, deep learning neural networks, fuzzy PID control, and ARIMA time series prediction enables the environmental control system to possess intelligent sensing capabilities for shrimp physiological states, multi-parameter collaborative optimization capabilities, and predictive adjustment capabilities for future states. It can perform personalized environmental regulation based on the shrimp's biological clock and metabolic characteristics, ensuring that live shrimp are always in the most suitable living environment during waterless transportation. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of an embodiment of the automatic optimization method for the waterless transportation environment of live shrimp based on the Internet of Things in this application.

[0019] Figure 2 This is a schematic diagram of an embodiment of the automatic optimization system for the waterless transportation environment of live shrimp based on the Internet of Things in this application.

[0020] Figure 3 This is a schematic block diagram of the structure of the automatic optimization device for the waterless transportation environment of live shrimp based on the Internet of Things in this embodiment of the invention. Detailed Implementation

[0021] This application provides an automatic optimization method and system for the waterless transportation environment of live shrimp based on the Internet of Things. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0022] For ease of understanding, the specific process of the embodiments of the present application is described below. Please refer to Figure 1 One embodiment of the live shrimp non-water transportation environment automatic optimization method based on the Internet of Things in the embodiments of the present application includes:

[0023] Step S101, real-time collection and processing of the environment parameters in the live shrimp non-water transportation container by a distributed sensor network, to obtain a multi-dimensional environment parameter data set containing temperature field data, humidity distribution data and oxygen concentration data;

[0024] Step S102, intelligent identification and processing of the shrimp body physiological state according to the multi-dimensional environment parameter data set, to obtain shrimp body physiological state evaluation data containing shrimp body dormancy degree index, stress level grade and molting cycle prediction value;

[0025] Step S103, environment adjustment strategy calculation and processing of the shrimp body physiological state evaluation data by a multivariate coupling control algorithm, to obtain a temperature-humidity-oxygen concentration collaborative control instruction set;

[0026] Step S104, coordinated driving processing of the self-adaptive actuator group according to the collaborative control instruction set, to obtain actuator response parameters containing refrigeration power adjustment amount, spraying frequency parameter and oxygen supply flow set value;

[0027] Step S105, dynamic correction processing of the actuator response parameters by a predictive bias correction mechanism, to obtain environment control precision compensation data based on the change of the shrimp body molting cycle and transportation time.

[0028] It can be understood that the execution subject of the present application can be a live shrimp non-water transportation environment automatic optimization system based on the Internet of Things, and can also be a terminal or a server, which is not limited here. The embodiments of the present application take the server as the execution subject for example.

[0029] Specifically, the distributed sensor network arranges sensor nodes at three levels of upper, middle and lower of the transportation container through a temperature sensor array, each node records three-dimensional space coordinate values and corresponding temperature values, to form temperature field raw data. The spatial interpolation algorithm adopts Kriging interpolation method, to calculate the temperature values of unmeasured points according to the temperature values and spatial position relationship of known points, and to construct a continuous temperature distribution field. The humidity sensor array is arranged around the wood chip packaging material to detect the environmental humidity corresponding to the moisture content of wood chips, and to record the humidity value and accurate time stamp each time. The oxygen concentration sensor is installed at the top and bottom of the container respectively to measure the oxygen volume percentage and carbon dioxide concentration value, to reflect the change of gas composition in the container. Time synchronization calibration processing calibrates all sensor data according to a unified time reference, to eliminate the time deviation between different sensors, to form a multi-dimensional environment parameter data set.

[0030] The frequency characteristics of temperature change and the period characteristics of humidity fluctuation are extracted by wavelet transform algorithm for frequency domain analysis of multi-dimensional environmental parameter dataset. Wavelet transform decomposes time domain signal into different frequency components, and the frequency characteristics of temperature change reflect the tiny temperature fluctuation caused by shrimp respiration. The respiration frequency is 2-4 times per minute in normal resting state. The metabolic activity intensity of shrimp is quantified by analyzing the standard deviation and coefficient of variation of respiration frequency, and the dormancy index of shrimp is calculated, with a value range of 0-1. A value close to 0 indicates deep dormancy. The temperature field data and oxygen concentration data are compared frame by frame by continuous frame difference analysis processing, and the pixel difference between adjacent time frames is calculated to reflect the movement state of shrimp. The stress level is divided into three levels of low, medium and high according to the movement frequency. If the movement frequency exceeds 50% of the normal value, it is determined to be in a high stress state. The deep learning neural network adopts a long short-term memory network structure, inputs the time series data of the dormancy index of shrimp and the stress level, identifies the periodic pattern of the biological clock of shrimp, and predicts the time window of molting event occurrence.

[0031] The fuzzy PID control algorithm establishes a fuzzy rule base to map the physiological state evaluation data of shrimp to temperature target value, humidity target value and oxygen concentration target value. The temperature target value is dynamically adjusted according to the dormancy index of shrimp. When the dormancy index is high, the target temperature is set to 12.5℃, and when the dormancy index is low, it is adjusted to 13.5℃. Dynamic correction calculation converts the metabolic level of shrimp into the correction amount of environmental parameters through a proportional coefficient. The temperature correction amount is equal to the product of the dormancy index and the reference correction coefficient. The weight distribution calculation establishes a parameter coupling weight matrix, and the temperature-humidity coupling coefficient describes the influence degree of temperature change on humidity demand. When the temperature decreases by 1℃, the humidity needs to be increased by 3% to maintain the gill moist. The time series prediction algorithm uses ARIMA model to analyze the autoregressive and moving average characteristics of molting cycle prediction value, and generates forward-looking environmental parameter pre-adjustment instruction. The collaborative optimization calculation performs matrix operation on the environmental control reference parameters, the parameter coupling weight matrix and the environmental parameter pre-adjustment instruction to obtain the collaborative control instruction set of temperature-humidity-oxygen concentration.

[0032] The power demand of each actuator is calculated by an actuator load distribution algorithm, and the semiconductor refrigerator power demand value is determined according to the difference between the target temperature and the current temperature. The multi-stage TEC refrigeration system adopts a series structure, the first stage TEC is responsible for coarse control, and the power output range is 50-150W, the second stage TEC is responsible for fine control, and the power output range is 10-50W. The compensatory adjustment process adjusts the working period of the spray actuator according to the temperature-humidity coupling coefficient, and the ultrasonic spray frequency is proportional to the temperature change. The gas flow regulation algorithm calculates the oxygen supply strategy according to the humidity-oxygen coupling coefficient, and the basic flow of the oxygen generator is set to 0.1 times the volume of the container per hour, and the CO2 adsorption device starts when the carbon dioxide concentration exceeds 1000ppm. The actuator coordination verification eliminates mutual interference through cross-coupling analysis, and automatically increases the spray frequency to compensate for humidity loss when the refrigeration actuator is working.

[0033] The actual output effect of the actuator is monitored by using a real-time feedback acquisition algorithm, and the actual temperature change value, humidity change value and oxygen concentration change value are recorded. The deviation calculation process performs difference operation on the target value of the cooperative control instruction set and the actual output data of the actuator to obtain the control deviation of each parameter. The time weighting analysis adjusts the importance weight of the deviation according to the molting cycle prediction value, and the molting period deviation sensitivity coefficient is set to 2 times of the normal period, and the non-molting period deviation tolerance coefficient is set to 0.5 times of the normal period. The cumulative error prediction algorithm analyzes the long-term influence of transportation time on environmental parameters, the temperature drift prediction value is calculated by a linear regression model, and the humidity decay prediction value is established by an exponential decay model according to the water loss characteristics of sawdust materials. The precision compensation calculation performs weighted summation on the environmental control deviation data, the molting cycle deviation weight factor and the transportation time deviation prediction data to calculate the temperature compensation increment, the humidity compensation increment and the oxygen concentration compensation increment, and forms the environmental control precision compensation data.

[0034] In specific embodiments, the process of performing step S101 can specifically include the following steps:

[0035] The temperature values at different levels in the transportation container are collected by a temperature sensor array to obtain temperature field raw data containing three-dimensional space coordinates and corresponding temperature values;

[0036] The temperature field raw data is reconstructed by a space interpolation algorithm to obtain temperature field data of continuous temperature distribution in the transportation container;

[0037] The humidity values near the sawdust packaging material are detected by a humidity sensor array to obtain humidity distribution data containing humidity values and collection time stamps;

[0038] According to the oxygen concentration sensor, the concentration measurement process is carried out on the gas components at the top and bottom of the container, and the oxygen concentration data containing the oxygen volume percentage and carbon dioxide concentration value are obtained.

[0039] The temperature field data, humidity distribution data and oxygen concentration data are processed through time synchronization calibration to obtain a multi-dimensional environmental parameter data set based on a unified timestamp.

[0040] Specifically, when the temperature sensor array collects temperature values at different levels in the transport container, high-precision temperature sensor nodes are first arranged at the upper, middle and lower layers of the transport container. Each sensor node records its three-dimensional spatial coordinate position and real-time detected temperature value. The three-dimensional spatial coordinates include X-axis horizontal position, Y-axis vertical position and Z-axis vertical height position, and the temperature value is recorded in Celsius. The sensor nodes are installed according to a grid layout to ensure that each area in the container is within the effective detection range of the sensors. The data collection frequency is set to collect data every 30 seconds to form a temperature field raw data structure containing timestamp, spatial coordinates and temperature value. Each record in the temperature field raw data contains sensor number, X coordinate value, Y coordinate value, Z coordinate value, temperature measurement value and data collection time, which constitutes the spatial temperature distribution information. When the spatial interpolation algorithm reconstructs the temperature field from the temperature field raw data, the Kriging interpolation method is used to calculate the temperature value of the unmeasured points. The Kriging interpolation algorithm first analyzes the spatial correlation between known temperature measurement points to establish a semi-variogram function model to describe the relationship between temperature value and spatial distance. The algorithm determines the strength and range of spatial autocorrelation by calculating the distance and temperature difference between any two points. In the interpolation calculation process, the temperature value of the unknown point is obtained by weighted average method, and the weight coefficient is determined according to the spatial distance and semi-variogram function value of the point and the surrounding known measurement points. The closer the measurement points, the greater the weight, and the farther the measurement points, the smaller the weight. After the reconstruction process is completed, a continuous temperature distribution field covering the entire transport container space is formed, which contains the temperature estimate value corresponding to each spatial position in the container. The temperature field data is stored in the form of a three-dimensional matrix, and each element of the matrix represents the temperature value of the corresponding spatial position.

[0041] When the humidity sensor array detects the humidity value of the area near the sawdust packaging material, the sensor is arranged close to the sawdust packaging layer to directly measure the relative humidity of the sawdust material surface. The relative humidity represents the percentage relationship between the water vapor content in the air and the saturated water vapor content at that temperature. Each humidity sensor records the accurate collection timestamp while detecting the humidity value, with a millisecond-level accuracy. The humidity value detection range covers the 70%-100% relative humidity interval, with a detection accuracy of plus or minus 2%. The humidity value detected by the sensor is directly related to the moisture content of the sawdust material. When the moisture content of the sawdust is high, the environmental humidity increases accordingly, and when the moisture content of the sawdust is low, the environmental humidity decreases accordingly. The humidity distribution data records the position number of each sensor, the detected humidity value and the collection timestamp, forming a time series humidity change record.

[0042] When the oxygen concentration sensor measures the concentration of the gas components at the top and bottom of the container, gas component analysis sensors are installed at the highest and lowest points of the container respectively. The top sensor mainly detects the replenishment of fresh oxygen, and the bottom sensor mainly detects the accumulation of carbon dioxide produced by shrimp respiration. The oxygen volume percentage represents the proportion of oxygen in the total gas volume, and the oxygen concentration in normal atmosphere is about 21%. The carbon dioxide concentration value represents the volume concentration of carbon dioxide in the container, with a unit of ppm, which means one millionth of the volume ratio. The sensor uses electrochemical detection principle to calculate the gas concentration through the current signal generated by the oxidation-reduction reaction of gas molecules and electrodes. The oxygen concentration data includes four data fields: detection position identification, oxygen volume percentage value, carbon dioxide concentration value and detection time.

[0043] The time synchronization calibration process calibrates and integrates the temperature field data, humidity distribution data and oxygen concentration data according to a unified time reference. The core of time synchronization is to eliminate the time deviation between different sensors to ensure that the data collected at the same time has the same time label. The calibration process first establishes a unified time reference, taking the system clock of the Internet of Things gateway as the reference time. The timestamps of each sensor are compared with the reference time, the time deviation value is calculated and corrected. The corrected data is arranged and merged in chronological order to form a multi-dimensional environmental parameter data set. Each record in the data set contains information in four dimensions: unified timestamp, temperature field data, humidity distribution data and oxygen concentration data.

[0044] In specific embodiments, the process of performing step S102 can specifically include the following steps:

[0045] The multi-dimensional environmental parameter data set is subjected to frequency domain feature extraction processing by wavelet transform algorithm to obtain shrimp body respiration frequency identification data containing temperature change frequency feature and humidity fluctuation period feature;

[0046] The shrimp body metabolism activity intensity is quantitatively calculated and processed according to the shrimp body breathing frequency identification data, and a shrimp body dormancy index representing the shrimp body metabolism level is obtained.

[0047] The stress level grade reflecting the change of the shrimp body movement state is obtained by performing continuous frame difference analysis processing on the shrimp body activity frequency based on the temperature field data and the oxygen concentration data.

[0048] The molting cycle prediction value of the shrimp body biological clock change rule is obtained by performing biological cycle mode identification processing on the shrimp body dormancy index and the stress level grade through a deep learning neural network.

[0049] The shrimp body physiological state evaluation data is obtained by performing comprehensive evaluation calculation processing according to the shrimp body dormancy index, the stress level grade and the molting cycle prediction value.

[0050] Specifically, when the wavelet transform algorithm performs frequency domain feature extraction processing on the multi-dimensional environmental parameter data set, first, the temperature and humidity data in the time domain are converted into frequency domain signals for analysis. The wavelet transform algorithm is a time-frequency analysis method that can obtain information in both time and frequency dimensions of the signal, and is particularly suitable for analyzing non-stationary signals. The algorithm selects Morlet wavelet as the mother wavelet function to perform multi-scale decomposition on the temperature time series data. During the decomposition process, the algorithm stretches and translates the mother wavelet function to calculate the wavelet coefficients at different time points and different frequencies. The temperature change frequency feature is obtained by analyzing the energy distribution of the wavelet coefficients, and the slight temperature fluctuation caused by shrimp respiration appears as an energy peak in a specific frequency range. The humidity fluctuation period feature is obtained by identifying the periodic change mode in the humidity data, and the regular humidity fluctuation is formed by the moisture absorption and release process of the sawdust packaging material. The shrimp body breathing frequency identification data includes three key parameters: main frequency component, frequency amplitude and fluctuation period. The main frequency component reflects the breathing rhythm of the shrimp body, the frequency amplitude reflects the breathing intensity, and the fluctuation period reflects the regularity of the breathing.

[0051] The metabolic activity intensity quantification process is based on the mathematical modeling analysis of the shrimp respiratory frequency identification data. Metabolic activity intensity is directly related to respiratory frequency in physiology. High respiratory frequency indicates active metabolism, and low respiratory frequency indicates slow metabolism. The quantification calculation first normalizes the main frequency component, converting the respiratory frequency data of different shrimps into the same numerical range. The normalization formula uses the maximum and minimum standardization method to map the frequency value to the interval of 0 to 1. Then, the respiratory intensity coefficient is calculated according to the frequency amplitude. The larger the amplitude, the deeper the respiration, and the more intense the metabolic activity. The regularity of the fluctuation period is evaluated by calculating the coefficient of variation. A small coefficient of variation indicates stable respiratory rhythm and a calm shrimp. The shrimp dormancy index is calculated by combining the main frequency, respiratory intensity coefficient, and rhythm stability. The numerical range is 0 to 1, with 0 indicating complete dormancy and 1 indicating complete wakefulness. The calculation process uses a weighted average method, and the weights of the three parameters are determined according to their influence on the dormancy state.

[0052] The continuous frame difference analysis process detects the small motion changes of shrimps based on temperature field data and oxygen concentration data. Frame difference analysis is a motion detection technique that identifies moving targets by comparing the data differences between consecutive time frames. Temperature field data forms continuous data frames at fixed time intervals, each frame containing temperature values for all spatial positions within the container. The analysis process calculates the temperature difference between corresponding positions in adjacent frames. Shrimp movement will cause local temperature distribution to change, forming a spatial pattern of temperature differences. Frame difference analysis of oxygen concentration data focuses on changes in oxygen consumption rate within the container. When shrimp activity increases, oxygen consumption accelerates, forming a time change in concentration gradient. The motion detection algorithm sets a threshold parameter. Regions with temperature differences exceeding the threshold are determined as motion regions. The number and distribution of motion regions reflect the activity frequency of shrimps. Stress level is classified according to the statistical characteristics of motion frequency. Low and evenly distributed motion frequency indicates low stress level, and high and concentrated motion frequency indicates high stress level. The classification uses clustering analysis to group data with similar motion characteristics into the same level.

[0053] The deep learning neural network performs biological cycle pattern recognition processing on the shrimp body dormancy index and stress level grade. The long short-term memory network structure is used to analyze the periodic pattern of time series data. The input layer of the neural network receives the time series data of the shrimp body dormancy index and stress level grade, and the hidden layer retains the memory of historical information through cyclic connection. The network training process uses known shrimp body molting cycle data as labels to learn the correlation between the changes in dormancy and stress level and the molting event. In the early stage of molting, the shrimp body shows a characteristic combination of reduced dormancy and increased stress level, and the network predicts the occurrence time of the molting event by recognizing this feature pattern. The biological cycle pattern recognition is based on the physiological rhythm characteristics of the shrimp body, which shows regular behavior changes in the molting cycle, including periodic fluctuations in activity intensity and rhythmic regulation of metabolic level. The molting cycle prediction value is calculated by the network output layer, representing the predicted time interval to the next molting event.

[0054] The comprehensive evaluation calculation process integrates the shrimp body dormancy index, stress level grade and molting cycle prediction value into unified shrimp physiological state evaluation data. The evaluation calculation uses a multi-dimensional fusion method to establish the weight relationship and influence mechanism between the three parameters. The dormancy index reflects the instantaneous physiological state of the shrimp body, the stress level grade reflects the sensitivity of the shrimp body to environmental changes, and the molting cycle prediction value reflects the biological rhythm state of the shrimp body. The calculation process first standardizes the three parameters to eliminate the influence of different dimensions and numerical ranges. Then, according to the special needs of live shrimp transportation without water, the importance weights of each parameter are determined. The dormancy index has the highest weight because it is directly related to the survival rate of transportation, the stress level grade has the second highest weight because it affects the health of the shrimp body, and the molting cycle prediction value has a relatively low weight but is important for long-distance transportation. The final shrimp physiological state evaluation data includes three dimensions: health score, risk level and care suggestion. The health score quantifies the overall physiological state of the shrimp body, the risk level warns potential health problems, and the care suggestion guides the adjustment of environmental control strategies.

[0055] In specific embodiments, the process of performing step S103 can specifically include the following steps:

[0056] The shrimp physiological state evaluation data is processed through the fuzzy PID control algorithm to match the control parameters, and the environmental control reference parameters including temperature target value, humidity target value and oxygen concentration target value are obtained;

[0057] According to the shrimp body dormancy index, the environmental control reference parameters are dynamically corrected and calculated to obtain the temperature correction amount, humidity correction amount and oxygen correction amount based on the metabolic level adjustment of the shrimp body;

[0058] The weight distribution calculation and processing of the coupling relationship of the environmental parameters based on the stress level grade obtains the parameter coupling weight matrix of the temperature-humidity coupling coefficient, the temperature-oxygen coupling coefficient and the humidity-oxygen coupling coefficient;

[0059] The shelling cycle prediction value is processed by the time series prediction algorithm to generate a forward-looking control strategy, and the environmental parameter pre-adjustment instruction based on the shelling cycle stage change is obtained.

[0060] According to the environmental control benchmark parameters, the parameter coupling weight matrix and the environmental parameter pre-adjustment instruction, the collaborative optimization calculation and processing is performed to obtain the temperature-humidity-oxygen concentration collaborative control instruction set.

[0061] Specifically, when the fuzzy PID control algorithm matches the shrimp physiological state evaluation data with the control parameters, it establishes a fuzzy reasoning rule base to convert the shrimp health score, risk level and nursing suggestion into specific environmental control parameters. The fuzzy PID control algorithm combines the advantages of fuzzy logic reasoning and PID control, and can handle imprecise and uncertain input information. The fuzzy process of the algorithm converts the numerical values in the shrimp physiological state evaluation data into fuzzy language variables, and the health score is divided into four fuzzy sets: excellent, good, general and poor, and the risk level is divided into four levels: safe, attention, warning and danger. The reasoning rule base contains 125 control rules, which specify the environmental parameter set value corresponding to different physiological state combinations. The temperature target value is determined according to the shrimp's dormant state and health level, and when the health level is high and the dormant state is deep, the temperature target is set to 12.5 degrees Celsius, and when the health level is general and the dormant state is shallow, the temperature target is adjusted to 13.2 degrees Celsius. The humidity target value is set based on the shrimp's gill moisture demand and stress level, and when the stress level is low, the humidity target is 85%, and when the stress level is high, the humidity target is increased to 95%. The oxygen concentration target value is determined according to the metabolic activity intensity and breathing frequency of the shrimp, and when the metabolic activity is active, the oxygen concentration target is increased to 21%, and when the metabolic activity is slow, the oxygen concentration target is reduced to 19%. The environmental control benchmark parameters are obtained through the de-fuzzification process of fuzzy reasoning to obtain accurate numerical output.

[0062] The dynamic correction calculation process adjusts the environmental control benchmark parameters in real time based on the dormancy index of the shrimp body. The core of the correction calculation is to establish a mathematical relationship model between the dormancy index and the environmental parameter requirements. The dormancy index of the shrimp body reflects the activity level of metabolism. High dormancy indicates slow metabolism and low sensitivity to environmental changes. Low dormancy indicates active metabolism and stricter environmental requirements. The temperature correction amount calculation is based on the deviation relationship between the dormancy index and the ideal temperature. When the dormancy index is higher than the standard value, the temperature correction amount is negative, indicating that the temperature needs to be lowered. When the dormancy index is lower than the standard value, the temperature correction amount is positive, indicating that the temperature needs to be increased. The calculation of the correction amount uses a proportional adjustment method. The difference between the dormancy index and the standard value is multiplied by the temperature sensitivity coefficient to obtain the temperature correction amount. The calculation of the humidity correction amount takes into account the physiological needs of the shrimp's gills for humidity. In the dormant state, the gills are less active and the humidity demand is relatively lower. In the awake state, the gills are more active and the humidity demand is correspondingly higher. The oxygen correction amount is adjusted according to the changes in the shrimp's respiratory intensity. When the dormancy is high, the respiratory frequency decreases and the oxygen consumption decreases. The oxygen correction amount is negative. When the dormancy is low, the respiratory frequency increases and the oxygen consumption increases. The oxygen correction amount is positive.

[0063] The weight distribution calculation process analyzes the mutual influence relationship between environmental parameters based on the stress level grade and establishes a parameter coupling weight matrix to quantify the correlation strength between different parameters. The stress level grade reflects the sensitivity and adaptability of the shrimp body to environmental changes. Low stress level indicates stable shrimp body state and small mutual influence between environmental parameters. High stress level indicates unstable shrimp body state and significant mutual influence between environmental parameters. The temperature-humidity coupling coefficient describes the influence degree of temperature change on humidity demand. In the low stress state, the coupling coefficient is small, indicating that the influence of temperature change on humidity demand is limited. In the high stress state, the coupling coefficient is large, indicating that temperature change will significantly affect humidity demand. The temperature-oxygen coupling coefficient reflects the comprehensive influence of temperature on oxygen solubility and shrimp oxygen consumption. When temperature decreases, oxygen solubility increases but shrimp oxygen consumption decreases. The calculation of the coupling coefficient needs to balance these two opposite effects. The humidity-oxygen coupling coefficient embodies the influence of humidity change on oxygen transmission efficiency. Too high humidity will affect the diffusion of oxygen in the air, and too low humidity will affect the oxygen absorption efficiency of the shrimp's gills. The parameter coupling weight matrix is stored in the form of a symmetric matrix. The numerical range of the matrix elements is between 0 and 1. The larger the value, the stronger the coupling relationship.

[0064] The time series prediction algorithm generates a forward-looking control strategy for the predicted value of the molting cycle. The algorithm uses an ARIMA autoregressive integrated moving average model to analyze the time variation pattern of the molting cycle. The ARIMA model describes the variation of time series data through the combination of autoregressive terms, difference terms and moving average terms. The autoregressive term reflects the linear relationship between the current value and the historical value, the difference term eliminates the non-stationarity of the data, and the moving average term reflects the influence of random errors. The algorithm first segments the predicted value of the molting cycle by time window, dividing the molting cycle into three stages: pre-molting period, molting period and post-molting period. In the pre-molting period, the physiological activity of the shrimp gradually becomes active, and the sensitivity to the environment increases, so the environmental parameters need to be adjusted in advance to avoid stress. In the molting period, the shrimp is in the most vulnerable state and has the most stringent requirements for the environment, so the most suitable environmental conditions need to be maintained. In the post-molting period, the shrimp gradually returns to normal state and the environmental adaptation ability increases, so the environmental parameter control gradually relaxes. The prediction algorithm calculates the time interval to the next stage according to the current time point in the molting cycle, and generates the corresponding environmental parameter pre-adjustment timing. The environmental parameter pre-adjustment instruction includes three elements: adjustment start time, parameter change gradient and adjustment end time, to ensure that the environmental change is synchronized with the physiological cycle of the shrimp.

[0065] The collaborative optimization calculation process analyzes and mathematically operates the environmental control reference parameters, the parameter coupling weight matrix and the environmental parameter pre-adjustment instruction to generate the final collaborative control instruction set. The core of collaborative optimization is to balance the mutual restraint relationship between multiple environmental parameters, and to avoid the optimization of a single parameter leading to the deterioration of other parameters. The calculation process first sets the environmental control reference parameters as the initial setting values, and then calculates the mutual influence between parameters according to the parameter coupling weight matrix. When the temperature parameter is adjusted, the influence on the humidity parameter is calculated according to the temperature-humidity coupling coefficient, and the influence on the oxygen parameter is calculated according to the temperature-oxygen coupling coefficient. The calculation of the influence amount uses matrix multiplication operation, and the parameter change vector is multiplied by the coupling weight matrix to obtain the influence amount vector of each parameter. Then, the environmental parameter pre-adjustment instruction is taken as a constraint condition to ensure that the collaborative control instruction set meets the special needs of the molting cycle. The final temperature-humidity-oxygen concentration collaborative control instruction set includes the target setting value, change rate and control accuracy requirement of the three parameters, forming the environmental control strategy.

[0066] In a specific embodiment, the process of performing the time series prediction algorithm to generate a forward-looking control strategy for the predicted value of the molting cycle can specifically include the following steps:

[0067] The predicted value of the molting cycle is segmented by time window by the molting stage division algorithm to obtain molting cycle time node data including pre-molting period, molting period and post-molting period;

[0068] According to the molting cycle time node data, the environmental requirements of each molting stage are analyzed and processed differently, and the stage environmental regulation parameters of the temperature up-regulation amplitude of the pre-molting period, the humidity enhancement coefficient of the molting period and the oxygen concentration compensation amount of the post-molting period are obtained.

[0069] Based on the ARIMA time series prediction algorithm, the future state of the molting cycle time node data is predicted and processed, and the molting time sequence prediction results of the molting event occurrence time and duration are obtained.

[0070] The stage environmental regulation parameters and the molting time sequence prediction results are calculated and processed by the time matching algorithm to obtain the time trigger point of the environmental parameter pre-adjustment and the pre-adjustment timing control data of the adjustment duration.

[0071] According to the pre-adjustment timing control data, the environmental control strategy is time-sequenced and processed to obtain the environmental parameter pre-adjustment instruction containing the adjustment start time, parameter change gradient and adjustment end time.

[0072] Specifically, when the molting stage division algorithm performs time window segmentation processing on the molting cycle prediction value, first, according to the biological characteristics of the shrimp body, the complete molting cycle is divided into three key stages. The molting stage division algorithm is based on the physiological law of shrimp molting, and determines the time boundaries of each stage by analyzing the behavior changes and physiological index changes of the shrimp body in the molting process. The pre-molting period is the stage when the shrimp body prepares to molt, the shrimp body starts to absorb the calcium in the old shell, the water in the body increases, and the activity gradually decreases. This stage usually accounts for 20-30% of the entire molting cycle. The molting period is the stage when the shrimp body actually molts the old shell, the shrimp body is in the most fragile state, completely stops eating, and is extremely sensitive to environmental changes. This stage is relatively short in time but is the most critical. The post-molting period is the recovery stage when the new shell of the shrimp body gradually hardens, the shrimp body starts to move again, and gradually recovers normal physiological functions. This stage accounts for 50-60% of the molting cycle. The algorithm segments the molting cycle prediction value according to the physiological law by setting the time proportion parameter, calculates the start time point and end time point of each stage. The molting cycle time node data includes four key nodes: the pre-molting period start time, the molting period start time, the molting period end time and the post-molting period end time, forming a complete time segmentation framework. Each time node is marked with a time interval relative to the current time and a corresponding physiological state identifier, which constitutes the basic data structure of time window segmentation.

[0073] The differential analysis process analyzes the special environmental requirements of each molting stage according to the molting cycle time node data, and establishes a stage-specific environmental regulation parameter system. The core of differential analysis lies in identifying the differential demand patterns of shrimp body for temperature, humidity and oxygen concentration at different molting stages. During the premolting stage, the metabolic activity of the shrimp body gradually increases, and the body temperature regulation ability decreases, so it is necessary to increase the environmental temperature to compensate for the change in the heat demand of the shrimp body. The temperature up-regulation amplitude during the premolting stage is calculated by analyzing the metabolic rate change and heat balance demand of the shrimp body, which is generally 0.5 to 1.0 degrees Celsius higher than the normal transportation temperature. During the molting stage, the shrimp body skin is extremely soft and the risk of water loss increases significantly, so it is necessary to maintain the water balance of the shrimp body by significantly increasing the environmental humidity. The molting stage humidity enhancement coefficient represents the multiple relationship relative to the normal humidity setting value, which is usually set to 1.1 to 1.2 times to compensate for the risk of water loss during molting. During the post-molting stage, the respiratory activity of the shrimp body gradually recovers, but the new shell has not yet fully hardened, so sufficient oxygen supply is needed to support the shell calcification process. The post-molting stage oxygen concentration compensation is calculated based on the biochemical oxygen demand of the shell hardening process, which is usually increased by 2 to 3 percentage points compared to the normal oxygen concentration. The determination of stage-specific environmental regulation parameters is based on the changes in physiological demand and environmental adaptation ability of the shrimp body at each molting stage, forming a targeted environmental control strategy.

[0074] The ARIMA time series prediction algorithm predicts the future state of the molting cycle time node data, and uses the autoregressive integrated moving average model to analyze the time occurrence rule of the molting event. The ARIMA algorithm identifies the trend, periodicity and randomness components in the data by analyzing the time series characteristics of the historical molting cycle data. The autoregressive part analyzes the correlation between the current molting time and the previous molting times, the integral part eliminates the non-stationary trend in the data, and the moving average part handles the influence of random errors. The algorithm first performs stationarity test on the molting cycle time node data, and eliminates the trend changes in the data through difference operation. Then the order parameters of the model are determined, the autoregressive order reflects the influence range of the historical data, and the moving average order reflects the memory length of the random disturbance. The model parameters are determined by the maximum likelihood estimation method to minimize the prediction error variance. The molting event occurrence time is predicted by the model, which represents the expected time point of the next molting start. The duration is predicted based on the statistical rules of the historical molting process and the current shrimp body state, which reflects the time span of the entire molting process from start to end. The molting time prediction result includes three elements: prediction time point, prediction accuracy interval and confidence level, which provides a time reference for the development of environmental control strategy.

[0075] The time matching algorithm calculates the control timing of the periodic environmental regulation parameters and the molting timing prediction results to determine the optimal execution time window of the environmental parameter regulation. The core of the time matching algorithm is to coordinate the time synchronization of the environmental regulation action and the physiological changes of the shrimp, to ensure that the change of the environmental conditions can timely respond to the physiological demand changes of the shrimp. The algorithm first analyzes the effective time requirements of each periodic environmental regulation parameter. The temperature regulation in the pre-molting period needs to be completed before the shrimp's metabolism accelerates, the humidity regulation in the molting period needs to reach the target value before the shrimp starts to molt, and the oxygen concentration compensation in the post-molting period needs to be kept sufficient supply when the new shell starts to harden. Then, the regulation advance time is calculated according to the response characteristics of the environmental regulation equipment. The temperature regulation needs to be started in advance for a long time because it involves the thermal inertia of the refrigeration equipment. The humidity regulation needs to be started in advance for a short time because the spray equipment responds quickly. The oxygen concentration regulation needs to be started in advance for an intermediate time because gas diffusion needs some time. The time trigger point of the advance regulation of the environmental parameters is calculated by subtracting the corresponding advance time from the time when the molting event occurs. The regulation duration is determined according to the physiological demand duration of each stage and the environmental stability requirement, which needs to meet the physiological demand and avoid energy waste caused by excessive regulation. The pre-regulation timing control data includes the trigger time, execution duration and target completion time of each environmental parameter, forming a complete time control scheme.

[0076] The timing arrangement process accurately schedules and adjusts the parameters of the environmental control strategy according to the pre-regulation timing control data. The goal of timing arrangement is to reasonably arrange the regulation actions of multiple environmental parameters in time sequence to avoid conflicts and interference between different regulation actions. The arrangement process first sorts the regulation tasks in time sequence, analyzes the time overlap and resource competition between tasks. The determination of the regulation start time needs to consider the priority of device startup and the importance of regulation effect. The priority of life safety related regulation tasks is the highest, the priority of comfort related regulation tasks is the second, and the priority of energy saving related regulation tasks is the lowest. The parameter change gradient is calculated based on the difference between the target parameter value and the current parameter value and the available regulation time. Too fast change gradient will cause stress impact on the shrimp, and too slow change gradient will miss the best regulation opportunity. Gradient calculation uses linear or exponential change curve, and selects appropriate change mode according to parameter characteristics and physiological adaptability. The setting of the regulation end time needs to ensure that the environmental parameters reach the target value at the key moment of molting and remain stable, and reserve enough preparation time for subsequent regulation tasks. The environmental parameter pre-regulation instruction is organized in time sequence, each time point corresponds to a specific parameter setting value and control action, forming a directly executable control program.

[0077] In a specific embodiment, the process of performing step S104 can specifically include the following steps:

[0078] The cooperative control instruction set is subjected to power demand calculation processing by an actuator load distribution algorithm to obtain actuator driving demand data of a semiconductor refrigerator power demand value, an ultrasonic humidifier working intensity and an oxygen generator output flow rate;

[0079] The multi-stage TEC refrigeration system is subjected to hierarchical power control processing according to the actuator driving demand data to obtain refrigeration power adjustment amounts of a first-stage TEC coarse adjustment power output and a second-stage TEC fine adjustment power output; the working cycle of the spray actuator is subjected to compensatory adjustment processing based on a temperature-humidity coupling coefficient to obtain spray frequency parameters of an ultrasonic spray frequency, a micro-spray interval time and a spray particle size control parameter; the humidity-oxygen coupling coefficient is subjected to oxygen supply strategy calculation processing by a gas flow rate adjustment algorithm to obtain oxygen supply flow rate set values of an oxygen generator basic flow rate, a CO2 adsorption device starting threshold and a gas circulating fan rotating speed;

[0080] The actuator coordination verification processing is performed according to the refrigeration power adjustment amounts, the spray frequency parameters and the oxygen supply flow rate set values to obtain actuator response parameters for eliminating mutual interference among the actuators.

[0081] Specifically, when the actuator load distribution algorithm performs power demand calculation processing on the cooperative control instruction set, firstly, the power characteristics and load demand relationships of the actuators are analyzed. The core of the load distribution algorithm is to convert the environmental control target into the working parameters of the specific actuators, and to calculate the driving demand of each actuator by establishing the mathematical mapping relationship between the control target and the power demand. The calculation of the semiconductor refrigerator power demand value is based on the difference between the target temperature and the current temperature, the container heat capacity and the heat loss coefficient. The greater the temperature difference, the higher the required refrigeration power, the larger the container volume, the higher the required refrigeration power, and the higher the environmental temperature, the greater the heat loss to be overcome. The algorithm converts the temperature control demand into the refrigeration power demand through a thermodynamic calculation model, and the calculation process considers the refrigeration efficiency, the heat transfer coefficient and the environmental factors. The determination of the ultrasonic humidifier working intensity is based on the difference between the target humidity and the current humidity, the container space volume and the air flow velocity. The humidity difference determines the amount of water vapor to be increased, the container volume determines the humidification coverage range, and the air flow affects the humidity distribution uniformity. The working intensity is calculated by a humidification efficiency model to convert the humidity control target into the electric power and working time parameters of the humidifier. The calculation of the oxygen generator output flow rate is based on the target oxygen concentration, the existing oxygen content in the container, the shrimp oxygen consumption rate and the gas exchange efficiency. The algorithm calculates the oxygen supplement amount required to reach the target concentration through the gas balance equation. The actuator driving demand data includes the power set value, the working duration and the response priority of each actuator, forming the basic parameters of the actuator control.

[0082] The hierarchical power control process performs accurate power distribution and adjustment strategy for the multi-stage TEC refrigeration system. The multi-stage TEC refrigeration system adopts a series structure, the first stage TEC is responsible for large-scale temperature adjustment, and the second stage TEC is responsible for fine temperature control. The cooperative work of the two-stage system realizes high precision and fast response of temperature control. The calculation of the first stage TEC coarse adjustment power output is based on the main part of the temperature difference. When the target temperature and the current temperature difference is large, the first stage TEC bears the main refrigeration load, and the power output is linearly related to the temperature difference, but the maximum power limit is set to avoid overload. The control strategy of the coarse adjustment stage adopts a fast response mode, which adjusts the temperature to the target value within a short time. The calculation of the second stage TEC fine adjustment power output is based on the accuracy requirement of temperature control. When the temperature is close to the target value, the second stage TEC performs fine adjustment control, and the power output is proportional to the square of the temperature deviation, which reflects the precision control characteristic. The control strategy of the fine adjustment stage adopts a stability priority mode, which maintains the accuracy and stability of the temperature through small amplitude power adjustment. The distribution of refrigeration power adjustment considers the efficiency characteristics and thermal response time of the two-stage TEC. The first stage TEC power change has a fast but limited effect on temperature, and the second stage TEC power change has a slow but high precision effect on temperature. The hierarchical control realizes the unity of speed and accuracy of temperature control by coordinating the working state of the two-stage TEC.

[0083] The compensatory adjustment process dynamically adjusts the working period of the spray executor based on the temperature-humidity coupling coefficient. The temperature-humidity coupling coefficient quantifies the degree of influence of temperature change on humidity demand. When the refrigeration system works to reduce the temperature, the saturation humidity in the air will also decrease accordingly, and the humidity loss needs to be compensated by increasing the spray frequency. The calculation of the ultrasonic spray frequency is based on the product of the coupling coefficient and the temperature change. For every unit decrease in temperature, the spray frequency increases by a value proportional to the coupling coefficient. The adjustment of the spray frequency adopts a dynamic compensation mechanism, which monitors the temperature change in real time and adjusts the working parameters of the spray executor accordingly. The determination of the micro-spray interval time is based on the uniformity requirement of humidity distribution and the spray diffusion time. Too short interval time will cause local humidity to be too high, and too long interval time will cause uneven humidity distribution. The setting of the spray particle size control parameter is based on the balance between humidity transmission efficiency and evaporation speed. When the particle size is small, the evaporation is fast but the transmission distance is short, and when the particle size is large, the transmission distance is long but the evaporation is slow. The spray frequency parameters are determined by an optimization algorithm to find the best combination of parameters, minimizing energy consumption and water consumption while meeting humidity control requirements. The goal of compensatory adjustment is to offset the adverse effects of temperature control on the humidity environment and maintain the balance of temperature and humidity.

[0084] The gas flow regulation algorithm calculates and processes the oxygen supply strategy based on the humidity-oxygen coupling coefficient, and analyzes the influence law of humidity change on oxygen transmission and distribution. The humidity-oxygen coupling coefficient reflects the influence of air humidity on the diffusion efficiency of oxygen. When the humidity is too high, the diffusion speed of oxygen in the air decreases, and when the humidity is too low, the oxygen absorption efficiency of the shrimp gill decreases. The calculation of the basic flow of the oxygen generator is based on the oxygen consumption of the shrimp body, the volume of the container and the target oxygen concentration. The basic flow ensures the stable supply of the target oxygen concentration under standard humidity conditions. The flow regulation dynamically compensates for the change in humidity, increases the oxygen generator flow when the humidity is higher than the standard value to compensate for the decrease in diffusion efficiency, and reduces the oxygen generator flow when the humidity is lower than the standard value to avoid high oxygen concentration. The setting of the CO2 adsorption device starting threshold is based on the carbon dioxide accumulation speed generated by the shrimp body respiration and the gas exchange efficiency in the container. If the threshold is too low, it will cause frequent starting and increase energy consumption. If the threshold is too high, it will cause the carbon dioxide concentration to exceed the standard and affect the health of the shrimp body. The regulation of the gas circulation fan speed is based on the balance between oxygen distribution uniformity and energy efficiency. If the speed is too high, it will increase energy consumption and noise. If the speed is too low, it will cause uneven oxygen distribution. The oxygen supply flow set value is calculated by considering oxygen demand, humidity influence and energy consumption constraints, forming a complete gas environment control strategy.

[0085] The actuator coordination verification process analyzes and resolves the mutual influence and conflicts of the refrigeration power regulation amount, the spraying frequency parameter and the oxygen supply flow set value. The goal of coordination verification is to identify and eliminate the mutual interference and negative effects caused by the work of different actuators. When the refrigeration actuator works, it will lower the environmental temperature, causing the air humidity to decrease relatively. The verification algorithm detects this influence and adjusts the spraying actuator parameters for compensation. When the spraying actuator works, it will increase the air humidity, affecting the oxygen diffusion efficiency. The verification algorithm adjusts the oxygen generator flow and the fan speed to maintain uniform oxygen distribution. The oxygen generator and the fan will generate a small amount of heat when they work, affecting the temperature control accuracy. The verification algorithm includes this heat in the refrigeration power calculation for compensation. The methods of interference elimination include parameter compensation, timing adjustment and power limitation. Parameter compensation offsets the mutual influence by adjusting the actuator set value, timing adjustment avoids simultaneous interference by staggering the work, and power limitation reduces the mutual influence by controlling the work intensity of the actuator. The actuator response parameters after coordination verification include the corrected power set value, the optimized work timing and the interference elimination control strategy, ensuring that the actuators work cooperatively to achieve the best environmental control effect.

[0086] In specific embodiments, the process of performing step S105 can specifically include the following steps:

[0087] The actuator response parameters are monitored by the real-time feedback collection algorithm to obtain the actual output data of the actuators, including the actual temperature change value, the actual humidity change value and the actual oxygen concentration change value.

[0088] According to the deviation calculation processing of the cooperative control instruction set and the actual output data of the actuator, the environmental control deviation data of the temperature control deviation amount, the humidity control deviation amount and the oxygen concentration control deviation amount are obtained;

[0089] Based on the time weighting analysis processing of the environmental control deviation data on the basis of the predicted value of the shelling period, the shelling period deviation weight factor of the shelling period deviation sensitivity coefficient and the non-shelling period deviation tolerance coefficient is obtained;

[0090] The long-term deviation trend calculation processing of the transport time change is carried out through the cumulative error prediction algorithm, and the transport time deviation prediction data of the temperature drift prediction value, the humidity attenuation prediction value and the oxygen consumption cumulative value are obtained;

[0091] According to the precision compensation calculation processing of the environmental control deviation data, the shelling period deviation weight factor and the transport time deviation prediction data, the environmental control precision compensation data containing the temperature compensation increment, the humidity compensation increment and the oxygen concentration compensation increment are obtained.

[0092] Specifically, when the real-time feedback collection algorithm monitors the execution effect of the actuator response parameters, the actual environmental changes after the work of each actuator are continuously monitored through the distributed sensor network. The core of the real-time feedback collection algorithm is to establish a causal relationship tracking mechanism between the actuator action and the environmental change, and to determine the corresponding relationship between the environmental parameter change and the specific actuator action through time stamp correlation analysis. The algorithm first records the accurate time point when each actuator starts working and the working parameter setting value, and then continuously monitors the change trend and change amplitude of the corresponding environmental parameters. The actual temperature change value is calculated by comparing the temperature measurement data before and after the actuator starts, and the algorithm analyzes the data change of the temperature sensor array to identify the temperature drop pattern and spatial distribution characteristics caused by the work of the refrigeration actuator. The actual humidity change value is calculated by monitoring the humidity sensor data change near the wood chip packaging material, and the algorithm focuses on the humidity rise speed and saturation degree after the work of the spray actuator. The actual oxygen concentration change value is calculated by analyzing the concentration difference change of the oxygen sensors at the top and bottom of the container, and the algorithm tracks the increasing trend and distribution uniformity of the oxygen concentration after the work of the oxygen generator. The actual output data of the actuator includes the actual change amount, the change rate and the stabilization time of the environmental parameters corresponding to each actuator, reflecting the real working effect of the actuator and the environmental response characteristics.

[0093] The deviation calculation process compares the target values of the cooperative control instruction set with the actual output data of the actuators, quantifies the difference between the control effect and the expected target. The mathematical processing of deviation calculation uses difference analysis method, by subtracting the actual value from the target value to get the absolute value and relative proportion of deviation. The calculation of temperature control deviation is based on the difference between the temperature target set value in the cooperative control instruction set and the actual temperature change value, positive deviation indicates that the actual temperature is higher than the target temperature, negative deviation indicates that the actual temperature is lower than the target temperature. The humidity control deviation is calculated by comparing the humidity target value with the actual humidity change value, the deviation analysis considers the time delay characteristics and spatial distribution unevenness of humidity change. The oxygen concentration control deviation is based on the comparison of oxygen concentration target value and actual oxygen concentration change value, the calculation process considers the physical process of oxygen diffusion and the dynamic change of shrimp consumption. The environmental control deviation data is processed by statistical analysis method, including the average value, standard deviation and maximum deviation value of the deviation, reflecting the stability and reliability of control accuracy. Deviation calculation also analyzes the time variation trend of deviation, identifies the different characteristics of systematic deviation and random deviation, and provides data basis for subsequent compensation calculation.

[0094] The time-weighted analysis process assigns importance weight to the environmental control deviation data based on the predicted value of the molting period, reflecting the differentiated requirements of shrimp in different physiological stages for environmental control accuracy. The core idea of time-weighted analysis is that shrimp is extremely sensitive to environmental changes during molting period, and relatively tolerant to environmental changes during non-molting period, so the same control deviation has different impact in different periods. The calculation of molting period deviation sensitivity coefficient is based on the physiological vulnerability and environmental adaptability of shrimp during molting period. During molting period, shrimp loses the protection of shell, the immune system function decreases, and small changes in temperature, humidity and oxygen concentration will produce strong stress response. The sensitivity coefficient is determined by physiological research data and experimental statistical results, generally set to two to three times the value of normal period. The non-molting period deviation tolerance coefficient reflects the tolerance of shrimp to environmental fluctuations in normal physiological state. During non-molting period, the shell of shrimp is complete, the physiological function is stable, and the adaptability to environmental changes is strong. The value of tolerance coefficient is usually less than the normal period reference value, indicating that larger control deviation is allowed in non-molting period without causing significant impact on shrimp health. The molting period deviation weight factor is obtained by matching the deviation sensitivity coefficient and the deviation tolerance coefficient in different time periods, forming a dynamic changing weight function for deviation importance evaluation.

[0095] The cumulative error prediction algorithm analyzes the long-term deviation trend of the transport time change, and predicts the cumulative deviation of the environmental control parameters during the long-term transport process. The basis of cumulative error prediction is to identify the systematic error sources and error accumulation rules in the environmental control process, and to predict the development trend of the error over time through mathematical modeling. The calculation of temperature drift prediction value is based on the heat efficiency attenuation of refrigeration equipment, environmental temperature change and the cumulative effect of heat conduction. The efficiency of refrigeration equipment gradually decreases after long-term work, which leads to the decrease of control accuracy. The change of external environment temperature affects the temperature stability in the container. The cumulative effect of heat conduction increases the temperature distribution gradient. The prediction algorithm uses a linear regression model to analyze the change trend of historical temperature control data, and establishes a functional relationship between time and temperature deviation. The humidity attenuation prediction value is based on the water loss characteristics of sawdust packaging materials and the sealing performance of the container. The water content of sawdust materials gradually decreases during long-term use, and the aging of the container seal leads to accelerated humidity loss. The attenuation prediction describes the change rule of humidity over time through an exponential attenuation model, and the parameters include the initial humidity value, the attenuation constant and the environmental influence factor. The oxygen consumption cumulative value is based on the persistence of shrimp metabolism and the change of oxygen supply efficiency. Shrimp continuously consumes oxygen through respiration, the efficiency of oxygen generator may decrease due to long-term work, and the oxygen distribution in the container may be uneven due to airflow change. The transport time deviation prediction data is obtained by comprehensive analysis of various cumulative effects, which provides a prediction basis for long-term control strategy adjustment.

[0096] The precision compensation calculation process analyzes and mathematically operates the environmental control deviation data, the molting period deviation weight factor and the transport time deviation prediction data to calculate the compensation adjustment amount of environmental control. The goal of precision compensation calculation is to offset the influence of various error factors through predictive adjustment, and to maintain the long-term precision and stability of environmental control. The calculation of temperature compensation increment is based on the weighted sum of current temperature control deviation, molting period sensitivity weight and temperature drift prediction value. The calculation process considers the urgency of deviation and the development trend of prediction error. The humidity compensation increment is calculated by analyzing the superposition effect of current humidity deviation and predicted attenuation trend. The compensation strategy not only corrects the current deviation, but also prevents the risk of future humidity deficiency. The oxygen concentration compensation increment is based on the comprehensive analysis of oxygen consumption cumulative prediction and current concentration deviation. The calculation process considers the dual influence of shrimp metabolism change and oxygen supply equipment efficiency change. The environmental control precision compensation data determines the optimal compensation amount of each parameter through optimization algorithm, which corrects the control deviation while minimizing energy consumption and equipment load, and forms the compensation control strategy.

[0097] The above describes the live shrimp waterless transport environment automatic optimization method based on Internet of Things in the embodiments of the present application. The live shrimp waterless transport environment automatic optimization system based on Internet of Things in the embodiments of the present application is described below. Please refer to Figure 2In an embodiment of the present application, an embodiment of the live shrimp non-water transportation environment automatic optimization system based on the Internet of Things comprises:

[0098] The acquisition module is configured to acquire and process environment parameters in the live shrimp non-water transportation container through a distributed sensor network to obtain a multi-dimensional environment parameter data set including temperature field data, humidity distribution data, and oxygen concentration data. The identification module is configured to intelligently identify and process the physiological state of the shrimp body according to the multi-dimensional environment parameter data set to obtain shrimp body physiological state evaluation data including a shrimp body dormancy degree index, a stress level grade, and a molting cycle prediction value. The calculation module is configured to calculate and process an environment adjustment strategy for the shrimp body physiological state evaluation data through a multivariate coupling control algorithm to obtain a temperature-humidity-oxygen concentration collaborative control instruction set. The driving module is configured to coordinate and drive the adaptive actuator group according to the collaborative control instruction set to obtain actuator response parameters including a refrigeration power adjustment amount, a spraying frequency parameter, and an oxygen supply flow set value. The correction module is configured to dynamically correct the actuator response parameters through a predictive bias correction mechanism to obtain environment control precision compensation data based on changes in the shrimp body molting cycle and the transportation time.

[0099] The above Figure 2 The live shrimp non-water transportation environment automatic optimization system based on the Internet of Things in the embodiment of the present application is described in detail from the perspective of modular functional entities, and the live shrimp non-water transportation environment automatic optimization device based on the Internet of Things in the embodiment of the present application is described in detail from the perspective of hardware processing.

[0100] Referring to Figure 3 In an embodiment of the present application, a live shrimp non-water transportation environment automatic optimization device based on the Internet of Things is also provided. Figure 3 The live shrimp non-water transportation environment automatic optimization device based on the Internet of Things can be a server, and its internal structure can be as shown in the figure. The live shrimp non-water transportation environment automatic optimization device based on the Internet of Things comprises a processor, a memory, a display screen, an input device, a network interface, and a database connected through a system bus. The memory of the live shrimp non-water transportation environment automatic optimization device based on the Internet of Things comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the live shrimp non-water transportation environment automatic optimization device based on the Internet of Things is used to store the corresponding data in the embodiment. The network interface of the live shrimp non-water transportation environment automatic optimization device based on the Internet of Things is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement the above method.

[0101] Those skilled in the art can understand that,Figure 3 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the Internet of Things based live shrimp non-water transportation environment automatic optimization device to which the scheme of the present application is applied.

[0102] The present application also provides a computer readable storage medium, which can be a non-volatile computer readable storage medium, and can also be a volatile computer readable storage medium, and instructions are stored in the computer readable storage medium, and when the instructions are run on a computer, the computer executes the steps of the Internet of Things based live shrimp non-water transportation environment automatic optimization method.

[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, system and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0104] The integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical scheme of the present application or the part of the prior art that essentially contributes or the whole or part of the technical scheme can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a Internet of Things based live shrimp non-water transportation environment automatic optimization device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0105] The above embodiments are only used to illustrate the technical scheme of the present application, but not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical scheme recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical scheme deviate from the spirit and scope of the technical scheme of each embodiment of the present application.

Claims

1. An automatic optimization method for the waterless transportation environment of live shrimp based on the Internet of Things, characterized in that, The method includes: The environmental parameters inside the waterless transport container for live shrimp are collected and processed in real time by a distributed sensor network to obtain a multi-dimensional environmental parameter dataset containing temperature field data, humidity distribution data, and oxygen concentration data. Based on the multidimensional environmental parameter dataset, the shrimp physiological state is intelligently identified and processed to obtain shrimp physiological state assessment data including shrimp dormancy index, stress level and molting cycle prediction value. The shrimp physiological state assessment data are processed by a multivariate coupling control algorithm to calculate environmental regulation strategies, resulting in a coordinated control instruction set for temperature, humidity, and oxygen concentration. The adaptive actuator group is coordinated and driven according to the cooperative control instruction set to obtain actuator response parameters including cooling power adjustment, spray frequency parameters and oxygen supply flow rate set value. The actuator response parameters are dynamically corrected using a predictive deviation correction mechanism to obtain environmental control accuracy compensation data based on changes in the shrimp molting cycle and transportation time.

2. The method for automatic optimization of the waterless transportation environment for live shrimp based on the Internet of Things according to claim 1, characterized in that, The process involves real-time acquisition and processing of environmental parameters within the anhydrous transport container for live shrimp using a distributed sensor network, resulting in a multi-dimensional environmental parameter dataset containing temperature field data, humidity distribution data, and oxygen concentration data. Temperature data are collected and processed at different levels within the transport container by a temperature sensor array to obtain raw temperature field data containing three-dimensional spatial coordinates and corresponding temperature values. The original temperature field data is reconstructed using a spatial interpolation algorithm to obtain temperature field data showing a continuous temperature distribution inside the transport container. Humidity data of the area near the wood chip packaging material is detected and processed based on a humidity sensor array to obtain humidity distribution data including humidity value and collection timestamp; The oxygen concentration data is obtained by measuring the concentration of the gas composition at the top and bottom of the container using an oxygen concentration sensor, which includes the oxygen volume percentage and carbon dioxide concentration value. The temperature field data, humidity distribution data, and oxygen concentration data are processed through time synchronization calibration to obtain the multidimensional environmental parameter dataset based on a unified timestamp.

3. The method for automatic optimization of the waterless transportation environment for live shrimp based on the Internet of Things as described in claim 1, characterized in that, The intelligent identification and processing of shrimp physiological state based on the multidimensional environmental parameter dataset yields shrimp physiological state assessment data including shrimp dormancy index, stress level, and molting cycle prediction value, including: The multidimensional environmental parameter dataset is processed by frequency domain feature extraction using wavelet transform algorithm to obtain shrimp respiratory frequency identification data containing temperature change frequency features and humidity fluctuation period features. Based on the shrimp respiratory frequency identification data, the intensity of shrimp metabolic activity is quantitatively calculated to obtain the shrimp dormancy index, which characterizes the shrimp's metabolic level. Based on the temperature field data and the oxygen concentration data, continuous frame difference analysis was performed on the shrimp activity frequency to obtain the stress level reflecting the changes in the shrimp's movement state. The shrimp's dormancy index and stress level are processed by deep learning neural network for biological cycle pattern recognition to obtain the predicted value of the molting cycle according to the change pattern of the shrimp's biological clock. The shrimp's physiological state assessment data are obtained by comprehensively evaluating and calculating the shrimp's dormancy index, stress level, and molting cycle prediction value.

4. The method for automatic optimization of the waterless transportation environment for live shrimp based on the Internet of Things according to claim 1, characterized in that, The process of calculating environmental regulation strategies using the shrimp physiological state assessment data through a multivariate coupled control algorithm yields a coordinated control instruction set for temperature, humidity, and oxygen concentration, including: The shrimp physiological state assessment data is processed by a fuzzy PID control algorithm to match control parameters, resulting in environmental control baseline parameters including target values ​​for temperature, humidity, and oxygen concentration. The environmental control baseline parameters are dynamically corrected based on the shrimp dormancy index to obtain temperature correction, humidity correction, and oxygen correction based on the shrimp's metabolic level. Based on the stress level, the environmental parameter coupling relationship is weighted and calculated to obtain the parameter coupling weight matrix of temperature-humidity coupling coefficient, temperature-oxygen coupling coefficient, and humidity-oxygen coupling coefficient. The predicted value of the molting cycle is processed by a time series prediction algorithm to generate a forward-looking control strategy, thereby obtaining a pre-adjustment instruction for environmental parameters based on the changes in the molting cycle stages. Based on the environmental control baseline parameters, the parameter coupling weight matrix, and the environmental parameter pre-adjustment instructions, a collaborative optimization calculation is performed to obtain the collaborative control instruction set for temperature-humidity-oxygen concentration.

5. The method for automatic optimization of the waterless transportation environment for live shrimp based on the Internet of Things according to claim 4, characterized in that, The step of generating a forward-looking control strategy by using a time series prediction algorithm to process the predicted value of the molting cycle, and obtaining a pre-adjustment instruction for environmental parameters based on the changes in the molting cycle stages, includes: The predicted shelling cycle value is processed into time window segments using a shelling stage segmentation algorithm to obtain shelling cycle time node data including the pre-shelling period, shelling period, and post-shelling period. Based on the time node data of the molting cycle, the environmental requirements of each molting stage are analyzed differently to obtain the staged environmental regulation parameters of temperature increase during the pre-molting stage, humidity enhancement coefficient during the molting stage, and oxygen concentration compensation during the post-molting stage. The ARIMA time series prediction algorithm is used to perform future state prediction processing on the time node data of the unshelling cycle to obtain the unshelling time series prediction results of the occurrence time and duration of the unshelling event. The phased environmental adjustment parameters and the shell-removal timing prediction results are processed by a time matching algorithm to calculate the control timing, thereby obtaining the pre-adjustment timing control data of the environmental parameter advance adjustment trigger point and adjustment duration. The environmental control strategy is processed by timing arrangement based on the pre-adjustment timing control data to obtain the environmental parameter pre-adjustment command, which includes the adjustment start time, parameter change gradient, and adjustment end time.

6. The method for automatic optimization of the waterless transportation environment for live shrimp based on the Internet of Things according to claim 5, characterized in that, The coordinated drive processing of the adaptive actuator group according to the coordinated control instruction set yields actuator response parameters including cooling power adjustment, spray frequency parameters, and oxygen supply flow rate setpoints, including: The power demand calculation of the collaborative control instruction set is performed through the actuator load allocation algorithm to obtain the actuator drive demand data of the semiconductor cooler power demand value, the ultrasonic humidifier working intensity and the oxygen generator output flow rate. The multi-stage TEC refrigeration system is subjected to graded power control processing based on the actuator drive demand data to obtain the refrigeration power adjustment amount of the first-stage TEC coarse adjustment power output and the second-stage TEC fine adjustment power output. Based on the temperature-humidity coupling coefficient, the working cycle of the spray actuator is adjusted compensatorily to obtain the spray frequency parameters, including ultrasonic spray frequency, micro-spray interval time, and spray particle size control parameters. The humidity-oxygen coupling coefficient is processed by the gas flow rate regulation algorithm to calculate the oxygen supply strategy, and the oxygen supply flow rate set values ​​of the oxygen generator base flow rate, CO2 adsorption device start-up threshold and gas circulation fan speed are obtained. Based on the cooling power adjustment, the spray frequency parameter, and the oxygen supply flow rate setting, the actuator coordination verification process is performed to obtain the actuator response parameters that eliminate mutual interference between actuators.

7. The method for automatic optimization of the waterless transportation environment for live shrimp based on the Internet of Things according to claim 1, characterized in that, The step of dynamically correcting the actuator response parameters through a predictive deviation correction mechanism to obtain environmental control accuracy compensation data based on changes in the shrimp molting cycle and transportation time includes: The actuator response parameters are processed by a real-time feedback acquisition algorithm to monitor the execution effect and obtain the actual output data of the actuator, which includes the actual temperature change value, the actual humidity change value, and the actual oxygen concentration change value. Based on the collaborative control instruction set and the actual output data of the actuator, deviation calculation processing is performed to obtain environmental control deviation data of temperature control deviation, humidity control deviation, and oxygen concentration control deviation. Based on the predicted molting cycle value, the environmental control deviation data is subjected to time-weighted analysis to obtain the molting cycle deviation weighting factor, which includes the molting period deviation sensitivity coefficient and the non-molting period deviation tolerance coefficient. The changes in transportation time are processed by a cumulative error prediction algorithm to calculate the long-term deviation trend, and the transportation time deviation prediction data, including temperature drift prediction, humidity decay prediction, and cumulative oxygen consumption, are obtained. Based on the environmental control deviation data, the shelling cycle deviation weighting factor, and the transportation time deviation prediction data, accuracy compensation calculations are performed to obtain the environmental control accuracy compensation data, which includes temperature compensation increment, humidity compensation increment, and oxygen concentration compensation increment.

8. An automatic optimization system for the waterless transportation environment of live shrimp based on the Internet of Things, characterized in that, For implementing the IoT-based automatic optimization method for the waterless transportation environment of live shrimp as described in any one of claims 1-7, the IoT-based automatic optimization system for the waterless transportation environment of live shrimp comprises: The data acquisition module is used to collect and process environmental parameters inside the waterless transport container for live shrimp in real time through a distributed sensor network, and obtain a multi-dimensional environmental parameter dataset containing temperature field data, humidity distribution data and oxygen concentration data. The identification module is used to intelligently identify the physiological state of shrimp based on the multidimensional environmental parameter dataset, and obtain shrimp physiological state assessment data including shrimp dormancy index, stress level and molting cycle prediction value. The calculation module is used to process the shrimp physiological state assessment data through a multivariate coupled control algorithm to calculate environmental regulation strategies and obtain a set of coordinated control instructions for temperature, humidity and oxygen concentration. The drive module is used to perform coordinated drive processing on the adaptive actuator group according to the coordinated control instruction set to obtain actuator response parameters including cooling power adjustment amount, spray frequency parameter and oxygen supply flow rate set value; The correction module is used to dynamically correct the actuator response parameters through a predictive deviation correction mechanism to obtain environmental control accuracy compensation data based on changes in the shrimp molting cycle and transportation time.

9. An automatic optimization device for the waterless transportation environment of live shrimp based on the Internet of Things, characterized in that, The method includes a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the method for automatic optimization of the waterless transportation environment for live shrimp based on the Internet of Things, as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is run on the microprocessor, it causes the processor to execute the automatic optimization method for the waterless transportation environment of live shrimp based on the Internet of Things as described in any one of claims 1 to 7.

Images