A water quality monitoring method and system for fresh aquatic product transport vehicles

Abstract

This application provides a water quality monitoring method and system for fresh aquatic product transport vehicles, belonging to the field of aquatic product preservation. The method and system include: obtaining real-time water quality monitoring indicator data for the fresh aquatic product transport vehicle, performing data cleaning and data verification on the water quality monitoring indicator data to obtain data to be monitored; predicting the water quality change trend of the fresh aquatic product transport vehicle based on the data to be monitored to obtain the water quality change trend; determining the water quality preservation mode of the fresh aquatic product transport vehicle based on the water quality change trend, and controlling the operating status of the preservation equipment in the fresh aquatic product transport vehicle according to the preservation mode. This application realizes dynamic monitoring and intelligent regulation of water quality status, effectively responding to the complex changes in water quality during transportation.

Description

Technical Field

[0001] The present application relates to the technical field of aquatic product preservation, and in particular to a water quality monitoring method and system for a fresh aquatic product transport vehicle. Background Art

[0002] Fresh aquatic products are highly sensitive to the transport environment and water quality, often facing significant challenges during transportation. Water quality can easily deteriorate due to vibrations, temperature fluctuations, and environmental changes in transport vehicles. Once certain water quality parameters (such as dissolved oxygen) drop below critical values, the metabolic function of aquatic products is impaired, significantly reducing their survival rate and potentially even leading to transport failure.

[0003] However, due to the complexity of the transportation environment, there are still many problems in monitoring the water quality of fresh aquatic product transport vehicles: water quality monitoring mostly adopts intermittent sampling of a single sensor or manual detection, which is not only difficult to meet real-time requirements, but also leads to inaccurate data due to insufficient equipment performance or interference from the on-board environment; if water quality is indirectly detected through an external monitoring system, it often faces problems such as poor real-time performance and data delays, and cannot reflect water quality changes at any time, resulting in unreliable detection data.

[0004] Therefore, finding a method that can monitor water quality in real time to prevent water quality from deteriorating and make intelligent adjustments based on actual water quality conditions is a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0005] The present application provides a water quality monitoring method and system for fresh aquatic product transport vehicles, which is used to solve the defects of inaccurate and unreliable water quality monitoring and detection data in the existing technology, realize dynamic monitoring and intelligent regulation of water quality status, and can effectively respond to complex changes in water quality during transportation, thereby ensuring the survival rate and transportation quality of aquatic products in fresh aquatic product transport vehicles.

[0006] In a first aspect, the present application provides a method for monitoring water quality of a fresh aquatic product transport vehicle, comprising the following steps:

[0007] S1. Acquire water quality monitoring index data of fresh aquatic product transport vehicles in real time, and perform data cleaning and data verification on the water quality monitoring index data to obtain data to be monitored;

[0008] S2. Predicting a water quality change trend of the water quality of the fresh aquatic product transport vehicle based on the data to be monitored to obtain a water quality change trend;

[0009] S3. Determine a water quality preservation mode for the fresh aquatic product transport vehicle based on the water quality change trend, and control the operating state of the preservation equipment in the fresh aquatic product transport vehicle according to the preservation mode.

[0010] According to a water quality monitoring method for a fresh aquatic product transport vehicle provided in the present application, the water quality monitoring index data include dissolved oxygen, pH value, water temperature, salinity, ammonia nitrogen concentration, turbidity and redox potential.

[0011] According to a water quality monitoring method for a fresh aquatic product transport vehicle provided by this application, the data verification specifically includes:

[0012] A real-time monitoring matrix is ​​constructed based on the water quality monitoring index data, and the changes in each water quality monitoring index data are judged according to the real-time monitoring matrix to determine whether they conform to the synergy law between the water quality monitoring index data:

[0013] If not, the water quality monitoring indicator data is abnormal and marked as abnormal data;

[0014] Perform time series clustering on water quality monitoring indicator data to identify normal and abnormal change patterns of each water quality monitoring indicator data;

[0015] Verify whether the abnormal data conforms to the synergy between water quality monitoring indicator data, and compare the abnormal data with normal change patterns and abnormal change patterns:

[0016] If the abnormal data does not conform to the synergistic law between water quality monitoring indicator data or the abnormal data belongs to the normal change model.

[0017] According to a water quality monitoring method for fresh aquatic product transport vehicles provided by the present application, time series modeling is performed on the monitored data before step S2 to obtain a time series of the monitored data. The water quality change trend prediction includes short-term change capture and long-term trend prediction, wherein:

[0018] The short-term change capture is used to perform adaptive modal decomposition on the time series of the data to be monitored to obtain an intrinsic mode function and a residual function, and based on the intrinsic mode function, capture the short-term highly non-stationary sequence of the water quality data to be monitored, and determine the short-term fluctuation of the water quality monitoring data based on the short-term non-stationary sequence;

[0019] The long-term trend prediction is used to predict the change trend of the time series of the data to be monitored to obtain the water quality change trend.

[0020] According to a water quality monitoring method for a fresh aquatic product transport vehicle provided by this application, the adaptive modal decomposition specifically includes:

[0021] a. Standardize the time series of the monitoring data to obtain the decomposed input signal;

[0022] b. Determine all local maximum and local minimum points of the decomposed input signal, and calculate the adaptive coefficient based on all local maximum and local minimum points. The calculation formula is:

[0023] ;

[0024] in, represents the adaptive coefficient, represents the adaptive parameter, represents the attenuation factor, Represents the time series of data to be monitored, Represents the decomposition input signal gradient;

[0025] c. constructing an upper envelope and a lower envelope using the adaptive coefficient, and calculating an envelope mean based on the upper envelope and the lower envelope;

[0026] d. Calculating the difference between the decomposed input signal and the envelope mean to obtain detailed components;

[0027] e. Repeat steps b to d until the conditions of the intrinsic mode function are met, and record it as the first intrinsic mode function;

[0028] f. Subtract the first intrinsic mode function from the time series of the data to be monitored to obtain a new input signal. Repeat steps be until the intrinsic mode function cannot be decomposed. The corresponding input signal is the residual function.

[0029] According to a water quality monitoring method for a fresh aquatic product transport vehicle provided by this application, the change trend prediction specifically includes:

[0030] Calculate the first-order difference and second-order difference of any two adjacent time points in the monitoring data time series to obtain the difference sequence;

[0031] The change direction of the data to be monitored is determined according to the differential sequence, and the trend index of the data to be monitored is calculated based on the change direction of the data to be monitored. The calculation formula of the trend index is:

[0032] ;

[0033] in, represents the trend index, represents the first-order difference, represents the second-order difference, represents the adjustment amplification factor of the first-order difference, represents the adjustment amplification factor of the second-order difference, Indicates the rising or falling direction of the current water quality monitoring index;

[0034] Based on the positive or negative sign and the numerical value of the trend index, the fluctuation range of the water quality monitoring index is judged to obtain the water quality change trend of the data to be monitored.

[0035] According to a water quality monitoring method for a fresh aquatic product transport vehicle provided by this application, step S3 specifically includes:

[0036] A comprehensive evaluation function is constructed based on the water quality change trend, and a comprehensive evaluation value of each water quality monitoring indicator data is determined based on the comprehensive evaluation function; the comprehensive evaluation function includes the time accumulation and change acceleration of the water quality change trend; the water quality state of the water quality monitoring indicator data includes a stable state, a fluctuating state, and a drastic change state;

[0037] When the comprehensive evaluation value is less than the first threshold, the water quality monitoring index data is in a stable state, and the conventional preservation mode is adopted to achieve stable water quality by maintaining a reference oxygen supply and a constant water temperature;

[0038] When the comprehensive evaluation value is greater than the first threshold and less than the second threshold, the water quality monitoring index data is in a fluctuating state, and a compensation preservation mode is adopted to suppress water quality fluctuations by increasing the oxygen supply and increasing the water purification frequency;

[0039] When the comprehensive evaluation value is greater than the second threshold, the water quality monitoring indicator data is in a state of drastic change, and an emergency preservation mode is adopted to prevent water quality deterioration through maximum oxygen supply capacity and rapid temperature correction;

[0040] By establishing a deviation function between the target value of the water quality monitoring indicator and the current water quality monitoring indicator data, the optimal control parameters are calculated in combination with the water quality change trend, and a mapping relationship is established between the control parameters and the execution time to generate a priority-based device control instruction sequence;

[0041] The operating state of the fresh-keeping equipment in the fresh aquatic product transport vehicle is controlled by the equipment control instruction sequence.

[0042] In a second aspect, the present application further provides a water quality monitoring system for a fresh aquatic product transport vehicle, which applies the water quality monitoring method described above, comprising:

[0043] The data acquisition module is used to obtain water quality monitoring index data of fresh aquatic product transport vehicles in real time, and to perform data cleaning and data verification on the water quality monitoring index data to obtain the data to be monitored;

[0044] A water quality prediction module is used to predict the water quality change trend of the fresh aquatic product transport vehicle based on the data to be monitored to obtain the water quality change trend;

[0045] The equipment control module is used to determine the water quality preservation mode of the fresh aquatic product transport vehicle based on the water quality change trend, and control the operating state of the preservation equipment in the fresh aquatic product transport vehicle according to the preservation mode.

[0046] In a third aspect, the present application further provides a fresh aquatic product transport vehicle, which implements the water quality monitoring method as described above, comprising:

[0047] Sensor collection equipment, used to collect water quality monitoring index data of fresh aquatic product transport vehicles and transmit the water quality monitoring index data to the water quality monitoring system;

[0048] Water quality monitoring system, used to receive data transmitted by sensor collection equipment and monitor and manage the water quality of fresh aquatic product transport vehicles;

[0049] Control equipment used to regulate the water quality of fresh aquatic product transport vehicles.

[0050] In a fourth aspect, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which implements the water quality monitoring method as described above when executed by a processor.

[0051] The water quality monitoring method and system for fresh aquatic product transport vehicles provided in this application realize dynamic monitoring and intelligent regulation of water quality status by acquiring water quality monitoring indicator data in real time, performing data cleaning and verification, predicting water quality change trends, and adjusting the operating status of preservation equipment based on the prediction results. It can effectively cope with the complex changes in water quality during transportation, ensure the survival rate and transportation quality of aquatic products in fresh aquatic product transport vehicles, and at the same time reduce the need for manual intervention and improve the intelligence level of the transportation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0053] Figure 1 This is a flow chart of the water quality monitoring method for fresh aquatic product transport vehicles provided by this application;

[0054] Figure 2 It is a structural diagram of the electronic device provided in this application. DETAILED DESCRIPTION

[0055] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions in this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0056] like Figure 1 As shown, the present application provides a water quality monitoring method for a fresh aquatic product transport vehicle, comprising the following steps:

[0057] S1. Acquire water quality monitoring index data of fresh aquatic product transport vehicles in real time, and perform data cleaning and data verification on the water quality monitoring index data to obtain data to be monitored.

[0058] Specifically, the water quality monitoring index data include dissolved oxygen, pH value, water temperature, salinity, ammonia nitrogen concentration, turbidity and redox potential.

[0059] Understandably, dissolved oxygen (DO) is an important indicator for measuring the oxygen content in water bodies. Too low dissolved oxygen will cause aquatic products to die from lack of oxygen, while too high dissolved oxygen may cause oxygen poisoning; pH value reflects the acidity and alkalinity of water bodies. An overly acidic or overly alkaline environment will have an adverse effect on the survival of aquatic products; water temperature directly affects the metabolic rate of aquatic products, and will also affect the solubility of dissolved oxygen and the rate of other chemical reactions in the water body; fluctuations in salinity may cause osmotic pressure regulation disorders in aquatic products; ammonia nitrogen is a product of nitrogen metabolism in water bodies, and excessive ammonia nitrogen concentrations will cause poisoning to aquatic products; turbidity reflects the concentration of suspended particulate matter in water bodies, and excessive turbidity may affect the respiration and health of aquatic products; oxidation-reduction potential (ORP) is an indicator reflecting the oxidation and reduction capacity in water bodies, which can indirectly reflect whether the water body is suitable for the survival of aquatic products.

[0060] In one embodiment of the present application, a high-precision sensor array or an embedded data acquisition system is used to obtain water quality monitoring index data of fresh aquatic product transport vehicles.

[0061] In one embodiment of the present application, data cleaning includes noise filtering of water quality monitoring index data, such as using mean filtering, median filtering, Kalman filtering, etc. to remove noise, including outlier detection of water quality monitoring index data. For example, if the dissolved oxygen data suddenly has a jump value that exceeds a reasonable range, the data can be judged as abnormal data. It also includes smoothing the water quality monitoring index data using a sliding average or an exponentially weighted moving average to reduce the short-term fluctuations of the water quality monitoring index data for subsequent data quality analysis.

[0062] In one embodiment of the present application, the data verification specifically includes:

[0063] A real-time monitoring matrix is ​​constructed based on the water quality monitoring index data, and the changes in each water quality monitoring index data are judged according to the real-time monitoring matrix to determine whether they conform to the synergy law between the water quality monitoring index data:

[0064] If not, the water quality monitoring indicator data is abnormal and marked as abnormal data;

[0065] Perform time series clustering on water quality monitoring indicator data to identify normal and abnormal change patterns of each water quality monitoring indicator data;

[0066] Verify whether the abnormal data conforms to the synergy between water quality monitoring indicator data, and compare the abnormal data with normal change patterns and abnormal change patterns:

[0067] If the abnormal data does not conform to the synergistic law between water quality monitoring indicator data or the abnormal data belongs to the normal change model.

[0068] It is understandable that the synergistic laws between water quality monitoring indicator data include the synergistic laws between dissolved oxygen and temperature, the synergistic laws between dissolved oxygen and salinity, the synergistic laws between dissolved oxygen and redox potential (ORP), and the synergistic laws between dissolved oxygen and pH. The solubility of dissolved oxygen decreases with increasing temperature. For every 10°C increase in temperature, the saturation value of dissolved oxygen will decrease by about 10%-15%. Increased salinity will reduce the dissolved oxygen saturation value of the water body. High dissolved oxygen usually corresponds to a higher redox potential. An increase in dissolved oxygen concentration will increase the oxidation capacity of the water body. Changes in dissolved oxygen will be accompanied by changes in pH. For example, the decomposition of organic matter in the water body will consume oxygen and release acidic substances, leading to a decrease in dissolved oxygen and a decrease in pH.

[0069] By constructing a real-time monitoring matrix and combining the synergy between water quality monitoring indicators, the collected water quality monitoring data is cleaned and verified, which can effectively identify abnormal data and mark them. At the same time, time series clustering is used to distinguish normal change patterns from abnormal change patterns, ensuring the accuracy and reliability of the data and reducing data deviations caused by sensor errors or environmental interference.

[0070] Furthermore, the water quality monitoring indicator data is clustered in time series to identify the normal change pattern and abnormal change pattern of each water quality monitoring indicator data, including:

[0071] Perform time series clustering on water quality monitoring indicator data to determine whether the fluctuation range of water quality monitoring indicator data is within the historical normal range, whether the fluctuation range shows common trend characteristics, whether the change characteristics of the fluctuation range are highly consistent, and whether the results of each time series clustering are significantly different:

[0072] If the fluctuation range of water quality monitoring indicator data exceeds the historical normal range and / or the fluctuation range shows abnormal trend characteristics and / or the change direction and amplitude of the fluctuation range are greatly different and / or the results of time series clustering are significantly different from the results of other time series clustering and deviate from the normal change pattern, then the water quality monitoring data will be marked as an abnormal change state mode.

[0073] It can be understood that common trend characteristics include slow rise or fall, periodic fluctuations, and abnormal trend characteristics include violent fluctuations, sudden changes or irregular changes.

[0074] Time series clustering can use the K-means algorithm or the DBSCAN algorithm, which is not specifically limited in this application. The normal variation pattern is based on the normal fluctuation range, trend characteristics, and periodicity of each water quality monitoring indicator obtained through statistical analysis of historical water quality monitoring indicator data. For example, if the historical mean of dissolved oxygen content is 8 mg / L and the standard deviation is 0.5 mg / L, its normal fluctuation range can be determined to be 7.5-8.5 mg / L.

[0075] Specifically, take dissolved oxygen as an example to explain data verification:

[0076] A real-time monitoring matrix is ​​constructed based on water quality monitoring indicator data. The real-time monitoring matrix is ​​used to determine whether the change in dissolved oxygen content conforms to the synergistic law between water quality monitoring indicator data:

[0077] If not, the dissolved oxygen data is abnormal and marked as abnormal dissolved oxygen data;

[0078] Perform time series clustering on water quality monitoring indicator data to identify normal and abnormal change patterns of each water quality monitoring indicator data;

[0079] Verify whether the abnormal dissolved oxygen data conforms to the synergy law between water quality monitoring indicator data, and compare the abnormal dissolved oxygen data with the normal change pattern and the abnormal change pattern:

[0080] If the abnormal dissolved oxygen data conforms to the synergistic law between the water quality monitoring index data and the abnormal dissolved oxygen data belongs to the normal change pattern, the abnormal dissolved oxygen data is identified as abnormal and marked as abnormal data. When the abnormal data appears frequently, the threshold of time series clustering is adjusted;

[0081] If the abnormal dissolved oxygen data does not conform to the synergistic law between water quality monitoring index data or the abnormal dissolved oxygen data belongs to the normal change model.

[0082] S2. Predicting a water quality change trend of the water quality condition of the fresh aquatic product transport vehicle based on the data to be monitored to obtain a water quality change trend.

[0083] Specifically, before step S2, the time series modeling is performed on the monitoring data to obtain the time series of the monitoring data. The water quality change trend prediction includes short-term change capture and long-term trend prediction, wherein,

[0084] The short-term change capture is used to perform adaptive modal decomposition on the time series of the data to be monitored to obtain an intrinsic mode function and a residual function, and based on the intrinsic mode function, capture the short-term highly non-stationary sequence of the water quality data to be monitored, and determine the short-term fluctuation of the water quality monitoring data based on the short-term non-stationary sequence;

[0085] The long-term trend prediction is used to predict the change trend of the time series of the data to be monitored to obtain the water quality change trend.

[0086] It is understandable that the intrinsic mode function obtained after adaptive modal decomposition of the monitored data contains the short-term turbulent components of the monitored data, such as a sudden drop in dissolved oxygen or a sharp change in water temperature in a short period of time; while the residual function represents the non-high-frequency, long-term, gentle changes in the monitored data. Based on the short-term highly non-stationary sequence, it is possible to capture the sharp fluctuations in the monitored data in a short period of time. If the short-term fluctuation amplitude of the monitored data exceeds the normal range, it means that the water quality of the fresh aquatic product transport vehicle has changed from a stable state to a severe state, and the operating status of the fresh aquatic product transport equipment in the fresh aquatic product transport vehicle needs to be adjusted immediately. When the fluctuation amplitude or frequency of the short-term highly non-stationary sequence exceeds the set threshold, the system will adjust the preservation mode according to the fluctuation characteristics (such as switching from the normal preservation mode to the compensation preservation mode or the emergency preservation mode).

[0087] This application combines the dual mechanisms of short-term change capture and long-term trend prediction, and uses adaptive modal decomposition to extract short-term highly non-stationary features. The short-term highly non-stationary sequence provides detailed information on sudden changes, and the long-term trend prediction provides the overall change direction of water quality. It can comprehensively and accurately reflect the dynamic change characteristics of water quality, and can identify water quality fluctuations or deterioration trends in advance, providing a scientific basis for the dynamic adjustment of the preservation mode.

[0088] In one embodiment of the present application, a short-term highly non-stationary sequence refers to a signal that exhibits high frequency, violent fluctuations, and no obvious periodicity in the time series.

[0089] Furthermore, the adaptive modal decomposition specifically includes:

[0090] a. Standardize the time series of the monitoring data to obtain the decomposed input signal;

[0091] b. Determine all local maximum and local minimum points of the decomposed input signal, and calculate the adaptive coefficient based on all local maximum and local minimum points. The calculation formula is:

[0092] ;

[0093] in, represents the adaptive coefficient, represents the adaptive parameter, represents the attenuation factor, Represents the time series of data to be monitored, Represents the decomposition input signal gradient;

[0094] c. Constructing an upper envelope and a lower envelope using the adaptive coefficient, and calculating an envelope mean based on the upper envelope and the lower envelope; the calculation formula is:

[0095]

[0096]

[0097]

[0098] in, represents the upper envelope, represents the lower envelope, represents the local standard deviation, represents the envelope mean;

[0099] d. Calculating the difference between the decomposed input signal and the envelope mean to obtain detailed components;

[0100] e. Repeat steps b to d until the conditions of the intrinsic mode function are met, and record it as the first intrinsic mode function;

[0101] f. Subtract the first intrinsic mode function from the time series of the data to be monitored to obtain a new input signal. Repeat steps be until the intrinsic mode function cannot be decomposed. The corresponding input signal is the residual function.

[0102] Among them, the intrinsic mode function condition is:

[0103] Within the range of the time series of the data to be monitored, the difference between the number of zero crossing points and the number of extreme value points does not exceed 1, and at any time, the mean value of the envelope is close to zero.

[0104] It is understandable that the existing classical modal decomposition does not take into account the local variation characteristics of the signal (such as the variation amplitude, oscillation frequency or the non-stationarity of the signal), which results in the envelope being too smooth or too sharp, and losing the details of the signal. Therefore, the adaptive coefficient is introduced to dynamically adjust the envelope shape so that it can reflect the local characteristics of the signal. The calculation formula of the adaptive coefficient is to achieve an adaptive response to the local characteristics of the decomposed input signal through the gradient term, reflecting the characteristics of the change in the strength of the decomposed input signal, and through the adaptive parameter Control the flexibility of the overall adjustment range through the attenuation factor Balancing noise suppression and signal decomposition accuracy, and because the exponential function ensures that the coefficients are always positive and bounded, avoiding numerical instability, it can provide nonlinear suppression performance, and is continuous and stable. Therefore, the adaptive coefficients enable the adaptive modal decomposition process to perform better in high-frequency fluctuations and non-stationary states, automatically reducing the weight in areas of drastic signal changes and maintaining a higher weight in areas of smoothness, thereby achieving adaptive smoothing. The adaptive coefficients construct a better envelope. That is, in areas of sudden signal changes, smaller adaptive coefficients make the envelope closer to the actual data points; in areas of smooth signal, larger adaptive coefficients provide better smoothing. This dynamic adjustment feature allows the envelope to maintain a detailed depiction without being overly sensitive to noise.

[0105] Among them, the adaptive parameters The value range of is between 0.1 and 1, which is adapted to the amplitude range of the signal, that is, a larger β value will produce a smoother envelope; the attenuation factor The value range of γ is between 0.01 and 0.1, which matches the typical gradient variation range of the signal. That is, the larger the γ value, the more sensitive it is to gradient variations. Different adaptive parameters and attenuation factors can be set for different water quality monitoring indicator data in fresh aquatic product transport vehicles, and this application does not impose specific restrictions on this.

[0106] This application improves the accuracy and robustness of modal decomposition by constructing precise envelopes, and can better capture the short-term fluctuation characteristics in water quality monitoring data.

[0107] Furthermore, the change trend prediction specifically includes:

[0108] Calculate the first-order difference and second-order difference of any two adjacent time points in the monitoring data time series to obtain the difference sequence;

[0109] The change direction of the data to be monitored is determined according to the differential sequence, and the trend index of the data to be monitored is calculated based on the change direction of the data to be monitored. The calculation formula is:

[0110] ;

[0111] in, represents the trend index, represents the first-order difference, represents the second-order difference, represents the adjustment amplification factor of the first-order difference, represents the adjustment amplification factor of the second-order difference, Indicates the rising or falling direction of the current water quality monitoring index;

[0112] Based on the positive or negative sign and the numerical value of the trend index, the fluctuation range of the water quality monitoring index is judged to obtain the water quality change trend of the data to be monitored.

[0113] It can be understood that the first-order difference reflects the rate of change between adjacent time points, while the second-order difference reflects the change in the rate of change, that is, the acceleration information, through It can simultaneously consider the current state of change of the data (determined by the first-order difference) and the change trend (determined by the second-order difference), comprehensively describe the overall change trend of the data, and nonlinearly amplify the intensity of the trend through the exponential function, so that larger change trends (whether rising or falling) can be more significantly reflected in numerical values. When it is larger, the trend index The value of will grow rapidly, indicating that the current data change trend is very strong. For smaller change trends, the exponential function can compress its value to close to 1, thereby avoiding the interference of weak changes on the overall trend judgment. And because the output of the exponential function is continuous, It can smoothly reflect the intensity of trend changes and avoid drastic changes caused by data fluctuations. The output value of the exponential function represents the intensity of the trend. The larger the value, the stronger the trend. The exp() function maps the change amplitude to the (0,∞) interval. When it is positive, it takes +1, indicating an upward trend. When it is negative, it takes -1, indicating a downward trend.

[0114] This application can more keenly capture the acceleration or deceleration turning points of water quality changes through trend index calculation, and quickly and accurately judge the fluctuation amplitude and potential drastic change trend of water quality.

[0115] S3. Determine a water quality preservation mode for the fresh aquatic product transport vehicle based on the water quality change trend, and control the operating state of the preservation equipment in the fresh aquatic product transport vehicle according to the preservation mode.

[0116] Step S3 specifically includes:

[0117] A comprehensive evaluation function is constructed based on the water quality change trend, and a comprehensive evaluation value of each water quality monitoring indicator data is determined based on the comprehensive evaluation function; the comprehensive evaluation function includes the time accumulation and change acceleration of the water quality change trend; the water quality state of the water quality monitoring indicator data includes a stable state, a fluctuating state, and a drastic change state;

[0118] When the comprehensive evaluation value is less than the first threshold, the water quality monitoring index data is in a stable state, and the conventional preservation mode is adopted to achieve stable water quality by maintaining a reference oxygen supply and a constant water temperature;

[0119] When the comprehensive evaluation value is greater than the first threshold and less than the second threshold, the water quality monitoring index data is in a fluctuating state, and a compensation preservation mode is adopted to suppress water quality fluctuations by increasing the oxygen supply and increasing the water purification frequency;

[0120] When the comprehensive evaluation value is greater than the second threshold, the water quality monitoring indicator data is in a state of drastic change, and an emergency preservation mode is adopted to prevent water quality deterioration through maximum oxygen supply capacity and rapid temperature correction;

[0121] By establishing a deviation function between the target value of the water quality monitoring indicator and the current water quality monitoring indicator data, the optimal control parameters are calculated in combination with the water quality change trend, and a mapping relationship is established between the control parameters and the execution time to generate a priority-based device control instruction sequence;

[0122] The operating state of the fresh-keeping equipment in the fresh aquatic product transport vehicle is controlled by the equipment control instruction sequence.

[0123] By constructing a comprehensive evaluation function based on the trend of water quality changes, combining the three states of water quality: stable, fluctuating and drastic changes, and dynamically adjusting the operating mode of the preservation equipment, we can achieve precise control of water quality, effectively suppress water quality fluctuations, prevent water quality deterioration, and ensure the healthy state of aquatic products during transportation.

[0124] Among them, the first threshold and the second threshold can be set according to actual usage requirements, and this application does not make specific limitations on this.

[0125] As you can understand, control parameters include oxygen supply, temperature adjustment range, and purification frequency. Optimizing these control parameters must meet the physical constraints of the equipment's operation. For example, the oxygen supply must not exceed the maximum oxygen supply capacity of the fresh-keeping equipment in the live aquatic product transport vehicle, and the temperature adjustment range must not exceed the adjustment range of the fresh-keeping equipment in the live aquatic product transport vehicle.

[0126] This application achieves dynamic monitoring and intelligent regulation of water quality status by acquiring water quality monitoring indicator data in real time, performing data cleaning and verification, predicting water quality change trends, and adjusting the operating status of preservation equipment based on the prediction results. It can effectively respond to complex changes in water quality during transportation, ensure the survival rate and transportation quality of aquatic products, and at the same time reduce the need for manual intervention and improve the intelligence level of the transportation process.

[0127] Specifically, a specific embodiment is used to illustrate the generation of a priority-based device control instruction sequence:

[0128] When the fluctuation amplitude of a short-term highly non-stationary series exceeds a set threshold (e.g., the fluctuation amplitude of dissolved oxygen exceeds ±0.5 mg / L), a target value for the water quality monitoring indicator is set. Based on the normalized deviation, a deviation function is determined between the target value of the water quality monitoring indicator and the current water quality monitoring indicator data. The target value of the water quality monitoring indicator includes a static target value and a dynamic target value obtained from the monitoring data. The dynamic target value needs to be updated in real time based on the external environment (e.g., temperature and humidity) and specific conditions during transportation (e.g., transportation time and the preservation capacity of the transportation vehicle). For example, in the early stages of transportation, when the water quality is relatively stable, the target value can be stricter (e.g., maintaining dissolved oxygen within the range of 8.0 ± 0.5 mg / L). As transportation time increases, the water quality may gradually deteriorate. In this case, the target value can be appropriately relaxed (e.g., allowing dissolved oxygen to drop to 7.5 ± 0.5 mg / L). The deviation function reflects the water quality of fresh aquatic product transport vehicles.

[0129] Establish an optimization objective function and use genetic algorithm or particle swarm optimization algorithm to find the optimal control parameters under the constraints;

[0130] Determine the priority of control instructions. For example, in a sudden change state, the oxygen supply equipment has the highest priority, followed by the temperature control equipment, and the purification equipment has the lowest priority. In a fluctuating state, the oxygen supply equipment and the purification equipment have similar priorities, followed by the temperature control equipment. In a stable state, all equipment maintains the lowest power consumption and the priority difference is small.

[0131] A time mapping relationship is generated based on the water quality change trend. Through time mapping, different control tasks are divided into two types: immediate execution and delayed execution. Immediate execution targets short-term fluctuations or sudden abnormal changes found in water quality monitoring, requiring the equipment to respond immediately. For example, when the dissolved oxygen content drops rapidly in a short period of time (such as when the water body is depleted of oxygen due to vibration during transportation), the short-term fluctuation amplitude increases significantly. At this time, the oxygen supply equipment needs to be started immediately to increase the oxygen supply to prevent water quality deterioration. Delayed execution is a control task based on long-term trend prediction. For example, if the long-term trend prediction shows that the water temperature is gradually rising but has not yet reached the level that poses a direct threat to aquatic products, the temperature control equipment can be arranged to slowly lower the water temperature after 10 minutes.

[0132] Instruction parallelism is optimized, and the generated device control instructions are updated or terminated according to the changes in real-time monitoring data. For example, if the fluctuation range of dissolved oxygen is found to have been significantly reduced and the water quality has returned to a stable state during execution, the originally planned low-priority instructions (such as instructions for increasing purification frequency) can be terminated. Instruction parallelism means that different devices need to run simultaneously during the water quality control process to cope with various water quality changes. For example, when the dissolved oxygen content decreases and the water quality experiences short-term fluctuations in turbidity, the oxygen supply equipment and water purification equipment can run in parallel.

[0133] The present application provides a water quality monitoring system for a fresh aquatic product transport vehicle, which applies the water quality monitoring method described above, including:

[0134] The data acquisition module is used to obtain water quality monitoring index data of fresh aquatic product transport vehicles in real time, and to perform data cleaning and data verification on the water quality monitoring index data to obtain the data to be monitored;

[0135] A water quality prediction module is used to predict the water quality change trend of the fresh aquatic product transport vehicle based on the data to be monitored to obtain the water quality change trend;

[0136] The equipment control module is used to determine the water quality preservation mode of the fresh aquatic product transport vehicle based on the water quality change trend, and control the operating state of the preservation equipment in the fresh aquatic product transport vehicle according to the preservation mode.

[0137] The data acquisition module includes a dissolved oxygen sensor, a pH sensor, a temperature sensor, a salinity sensor, an ammonia nitrogen sensor, a turbidity sensor, and an ORP sensor. The equipment control module includes an oxygen supply system, a temperature control system, a purification system, and a central control unit. The oxygen supply system includes a variable frequency aeration pump, a dissolved oxygen monitoring device, and a gas flow control valve for adjusting the oxygen supply according to different preservation modes. The temperature control system includes a refrigeration unit, a heating unit, and a temperature sensor array for achieving precise control of water temperature. The purification system includes a circulating water pump, a multi-stage filtration device, and a water purification device for adjusting the water purification frequency. The central control unit communicates with each system through a bus network and executes the equipment control instruction sequence. The oxygen supply system, temperature control system, and purification system are all equipped with a working status feedback device for feeding back the equipment operating parameters to the central control unit in real time. The central control unit dynamically adjusts the equipment control instruction sequence based on the feedback parameters.

[0138] The present application also provides a fresh aquatic product transport vehicle, which implements the water quality monitoring method as described above, comprising:

[0139] Sensor collection equipment, used to collect water quality monitoring index data of fresh aquatic product transport vehicles and transmit the water quality monitoring index data to the water quality monitoring system;

[0140] Water quality monitoring system, used to receive data transmitted by sensor collection equipment and monitor and manage the water quality of fresh aquatic product transport vehicles;

[0141] Control equipment used to regulate the water quality of fresh aquatic product transport vehicles.

[0142] The water quality monitoring device provided in the present application is described below. The water quality monitoring device described below and the water quality monitoring method described above can be referenced to each other.

[0143] Figure 2 An example of a physical structure diagram of an electronic device is shown below. Figure 2 As shown, the electronic device may include: a processor 210, a communication interface 220, a memory 230, and a communication bus 240, wherein the processor 210, the communication interface 220, and the memory 230 communicate with each other via the communication bus 240. The processor 210 may call logic instructions in the memory 230 to execute a water quality monitoring method, which includes: acquiring water quality monitoring indicator data of a fresh aquatic product transport vehicle in real time, and performing data cleaning and data verification on the water quality monitoring indicator data to obtain data to be monitored; predicting a water quality change trend of the water quality status of the fresh aquatic product transport vehicle based on the data to be monitored to obtain a water quality change trend; determining a water quality preservation mode of the fresh aquatic product transport vehicle based on the water quality change trend, and controlling the operating state of a preservation device in the fresh aquatic product transport vehicle according to the preservation mode.

[0144] In addition, the logic instructions in the aforementioned memory 230 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0145] On the other hand, the present application also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the water quality monitoring method provided by the above-mentioned methods, which includes: obtaining water quality monitoring index data of fresh aquatic product transport vehicles in real time, and performing data cleaning and data verification on the water quality monitoring index data to obtain data to be monitored; predicting the water quality change trend of the water quality status of the fresh aquatic product transport vehicle based on the data to be monitored to obtain a water quality change trend; determining the water quality preservation mode of the fresh aquatic product transport vehicle based on the water quality change trend, and controlling the operating status of the preservation equipment in the fresh aquatic product transport vehicle according to the preservation mode.

[0146] On the other hand, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the water quality monitoring method provided by the above-mentioned methods, the method comprising: acquiring water quality monitoring index data of a fresh aquatic product transport vehicle in real time, and performing data cleaning and data verification on the water quality monitoring index data to obtain data to be monitored; predicting a water quality change trend of the water quality condition of the fresh aquatic product transport vehicle based on the data to be monitored to obtain a water quality change trend; determining a water quality preservation mode of the fresh aquatic product transport vehicle based on the water quality change trend, and controlling the operating status of the preservation equipment in the fresh aquatic product transport vehicle according to the preservation mode.

[0147] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0148] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0149] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for monitoring water quality of a fresh aquatic product transport vehicle, characterized in that: The following steps are involved: S1. Acquire water quality monitoring index data of fresh aquatic product transport vehicles in real time, and perform data cleaning and data verification on the water quality monitoring index data to obtain data to be monitored; S2. Predicting a water quality change trend of the water quality of the fresh aquatic product transport vehicle based on the data to be monitored to obtain a water quality change trend; S3, determining the water quality preservation mode of the fresh aquatic product transport vehicle based on the water quality change trend, and controlling the operating state of the preservation equipment in the fresh aquatic product transport vehicle according to the preservation mode, wherein: Before step S2, the time series modeling of the monitored data is performed to obtain the time series of the monitored data. The water quality change trend prediction includes short-term change capture and long-term trend prediction, wherein, The short-term change capture is used to perform adaptive modal decomposition on the time series of the data to be monitored to obtain an intrinsic mode function and a residual function, and capture the short-term highly non-stationary sequence of the water quality data to be monitored based on the intrinsic mode function, and determine the short-term fluctuation of the water quality monitoring data based on the short-term highly non-stationary sequence; The long-term trend prediction is used to predict the change trend of the time series of the data to be monitored to obtain the water quality change trend; Step S3 specifically includes: A comprehensive evaluation function is constructed based on the water quality change trend, and a comprehensive evaluation value of each water quality monitoring indicator data is determined based on the comprehensive evaluation function; the comprehensive evaluation function includes the time accumulation and change acceleration of the water quality change trend; the water quality state of the water quality monitoring indicator data includes a stable state, a fluctuating state, and a drastic change state; When the comprehensive evaluation value is less than the first threshold, the water quality monitoring index data is in a stable state, and the conventional preservation mode is adopted to achieve stable water quality by maintaining a reference oxygen supply and a constant water temperature; When the comprehensive evaluation value is greater than the first threshold and less than the second threshold, the water quality monitoring index data is in a fluctuating state, and a compensation preservation mode is adopted to suppress water quality fluctuations by increasing the oxygen supply and increasing the water purification frequency; When the comprehensive evaluation value is greater than the second threshold, the water quality monitoring indicator data is in a state of drastic change, and an emergency preservation mode is adopted to prevent water quality deterioration through maximum oxygen supply capacity and rapid temperature correction; By establishing a deviation function between the target value of the water quality monitoring indicator and the current water quality monitoring indicator data, the optimal control parameters are calculated in combination with the water quality change trend, and a mapping relationship is established between the control parameters and the execution time to generate a priority-based device control instruction sequence; The operating state of the fresh-keeping equipment in the fresh aquatic product transport vehicle is controlled by the equipment control instruction sequence.

2. The water quality monitoring method for a fresh aquatic product transport vehicle according to claim 1, characterized in that: The water quality monitoring index data include dissolved oxygen, pH value, water temperature, salinity, ammonia nitrogen concentration, turbidity and redox potential.

3. The water quality monitoring method for a fresh aquatic product transport vehicle according to claim 1, characterized in that: The data verification specifically includes: A real-time monitoring matrix is ​​constructed based on the water quality monitoring index data, and the changes in each water quality monitoring index data are judged according to the real-time monitoring matrix to determine whether they conform to the synergy law between the water quality monitoring index data: If not, the water quality monitoring indicator data is abnormal and marked as abnormal data; Perform time series clustering on water quality monitoring indicator data to identify normal and abnormal change patterns of each water quality monitoring indicator data; Verify whether the abnormal data conforms to the synergy between water quality monitoring indicator data, and compare the abnormal data with normal change patterns and abnormal change patterns: If the abnormal data does not conform to the synergistic law between water quality monitoring indicator data or the abnormal data belongs to the normal change model.

4. The method for monitoring water quality of a fresh aquatic product transport vehicle according to claim 1, characterized in that: The adaptive modal decomposition specifically includes: a. Standardize the time series of the monitoring data to obtain the decomposed input signal; b. Determine all local maximum and local minimum points of the decomposed input signal, and calculate the adaptive coefficient based on all local maximum and local minimum points. The calculation formula is: ； in, represents the adaptive coefficient, represents the adaptive parameter, represents the attenuation factor, Represents the time series of data to be monitored, Represents the decomposition input signal gradient; c. constructing an upper envelope and a lower envelope using the adaptive coefficient, and calculating an envelope mean based on the upper envelope and the lower envelope; d. Calculating the difference between the decomposed input signal and the envelope mean to obtain detailed components; e. Repeat steps b to d until the conditions of the intrinsic mode function are met, and record it as the first intrinsic mode function; f. Subtract the first intrinsic mode function from the time series of the data to be monitored to obtain a new input signal. Repeat steps be until the intrinsic mode function cannot be decomposed. The corresponding input signal is the residual function.

5. The method for monitoring water quality of a fresh aquatic product transport vehicle according to claim 4, characterized in that: The change trend prediction specifically includes: Calculate the first-order difference and second-order difference of any two adjacent time points in the monitoring data time series to obtain the difference sequence; The change direction of the data to be monitored is determined according to the differential sequence, and the trend index of the data to be monitored is calculated based on the change direction of the data to be monitored. The calculation formula of the trend index is: ； in, represents the trend index, represents the first-order difference, represents the second-order difference, represents the adjustment amplification factor of the first-order difference, represents the adjustment amplification factor of the second-order difference, Indicates the rising or falling direction of the current water quality monitoring index; Based on the positive or negative sign and the numerical value of the trend index, the fluctuation range of the water quality monitoring index is judged to obtain the water quality change trend of the data to be monitored.

6. A water quality monitoring system for a fresh aquatic product transport vehicle, characterized in that: The water quality monitoring method according to any one of claims 1 to 5 is applied, comprising: The data acquisition module is used to obtain water quality monitoring index data of fresh aquatic product transport vehicles in real time, and to perform data cleaning and data verification on the water quality monitoring index data to obtain the data to be monitored; A water quality prediction module is used to predict the water quality change trend of the fresh aquatic product transport vehicle based on the data to be monitored to obtain the water quality change trend; The equipment control module is used to determine the water quality preservation mode of the fresh aquatic product transport vehicle based on the water quality change trend, and control the operating state of the preservation equipment in the fresh aquatic product transport vehicle according to the preservation mode.

7. A fresh aquatic product transport vehicle, characterized in that: Implementing the water quality monitoring method according to any one of claims 1 to 5, comprising: Sensor collection equipment, used to collect water quality monitoring index data of fresh aquatic product transport vehicles and transmit the water quality monitoring index data to the water quality monitoring system; Water quality monitoring system, used to receive data transmitted by sensor collection equipment and monitor and manage the water quality of fresh aquatic product transport vehicles; Control equipment used to regulate the water quality of fresh aquatic product transport vehicles.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the water quality monitoring method according to any one of claims 1 to 5 is implemented.

Images