Aquaculture environment monitoring system and method based on Internet of Things

Abstract

The invention discloses an aquaculture environment monitoring system and method based on the Internet of Things, and relates to the technical field of the Internet of Things. By forming a feature vector TIV, the temperature standard deviation Q of each region is calculated, a possible heat island effect region is identified through the standard deviation value, and finally a heat island effect identification mark is generated. A heat island effect data set TIVh is constructed, and data support is provided for temperature control adjustment. On the basis of the data set, the system further calculates the temperature adjusting quantity T, a control instruction is generated according to the quantity, the temperature is accurately adjusted, and then the situation that the health of fish schools is affected due to local overheating is avoided. And finally, through continuous monitoring and analysis of temperature change, a temperature control effect index E is calculated, through dynamic optimization of the index, iterative improvement of a temperature control strategy is ensured, and the problem of temperature fluctuation caused by the fact that the heat island effect cannot be recognized and adjusted in real time in a traditional method can be effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of the Internet of Things, and particularly to an aquaculture environment monitoring system and method based on the Internet of Things. Background Art

[0002] In the context of the rapid development of today's technology, the Internet of Things (IoT) technology has penetrated into various fields. As a part of the agricultural industry, aquaculture increasingly relies on modern technical means for management and optimization. Aquaculture, as a production activity with water as the carrier, mainly includes the breeding and cultivation of aquatic organisms such as fish, shellfish, and crustaceans. With the continuous expansion of the scale of aquaculture, the refined management of the aquaculture environment has gradually become the key to improving the aquaculture efficiency. And "aquaculture environment monitoring" is an important technology that emerged in this process. It uses Internet of Things sensors, data analysis, and automation control to monitor and optimize various parameters of the aquaculture environment in real time to ensure an ideal environment for fish growth.

[0003] Currently, although many farms have adopted Internet of Things technology to monitor key parameters such as water quality, dissolved oxygen, and temperature, when faced with large-scale aquaculture areas, the application of the existing systems in temperature management still has relatively large limitations. The existing monitoring systems mostly focus on the collection and real-time feedback of single parameters. Although they can provide comprehensive data support, they lack the fine monitoring and adjustment of regional temperature differences. This management method often cannot accurately identify the temperature fluctuations within the aquaculture area. Especially in some local areas, due to uneven water flow, climatic factors, or uneven equipment, etc., a "heat island effect" with too high temperature may be formed, which has an adverse impact on the aquaculture environment.

[0004] At present, most farms lack an automated adjustment system. Especially when faced with a large-scale aquaculture area, traditional management methods often rely on manual observation and intervention. The response speed of manual adjustment is slow, and the operation is not precise enough, resulting in the inability to improve the local areas with too high or too low temperature in a timely manner. The lag or failure of temperature management will not only affect the healthy growth of the fish population, but also may lead to a series of problems such as the stress response of the fish population and the spread of diseases, resulting in a decline in aquaculture efficiency. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides an aquaculture environment monitoring system and method based on the Internet of Things, which solves the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: An aquaculture environment monitoring method based on the Internet of Things includes the following steps:

[0007] S1. Collect the water temperature data of the aquaculture area through a temperature sensor, and integrate the temperature data points obtained in each area to obtain the feature vector TIV;

[0008] S2. Conduct spatial analysis based on the obtained feature vector TIV. By dividing the aquaculture area, obtain the temperature standard deviation Q of each area, and identify the heat island effect based on the temperature standard deviation Q to obtain the heat island effect identification flag of each area;

[0009] S3. Mark and integrate the aquaculture area based on the obtained heat island effect identification flag to obtain the heat island effect data set TIVh;

[0010] S4. Conduct data interaction analysis on the obtained heat island effect data set TIVh to obtain the temperature adjustment amount △T required for the current aquaculture area, and generate a control instruction based on the temperature adjustment amount △T to adjust the temperature of the aquaculture area;

[0011] S5. Conduct temperature changes in the aquaculture areas with heat island effect identification flags at a fixed period after the control instruction is triggered. By analyzing the temperature changes, obtain the temperature control effect index E, and trigger the iterative optimization mechanism based on the temperature control effect index E.

[0012] Preferably, the S1 includes S11 and S12;

[0013] S11. By arranging multiple temperature sensors in the aquaculture area, collect the water temperature data T of different three-dimensional positions (x, y, z) in the aquaculture area in real time. At the same time, when the temperature sensor collects the water temperature data T at a fixed period, mark the collection time t to obtain the water temperature data T(x, y, z, t) of the three-dimensional position (x, y, z) of the water area at time t;

[0014] Among them, x, y, and z respectively represent the horizontal axis coordinate, the vertical axis coordinate, and the vertical axis coordinate;

[0015] S12. Aggregate the water temperature data T(x, y, z, t) of different three-dimensional positions (x, y, z) at time t according to the obtained water temperature data T(x, y, z, t) of the three-dimensional position (x, y, z) of the water area at time t, obtain the water temperature data T(x, y, z, t) within the two-dimensional position (x, y) of the water area in the same area, and calculate the average value of the water temperature data T(x, y, z, t) at the two-dimensional position (x, y) of the water area to obtain the average temperature Tavg(x, y, t) of the two-dimensional position (x, y) of the water area. Then integrate the average temperature Tavg(x, y, t) of the two-dimensional position (x, y) of the water area to obtain the feature vector TIV;

[0016] The average temperature Tavg(x, y, t) is obtained through the following calculation formula:

[0017] ;

[0018] Wherein, N(x, y) represents the total number of sensor data points at the water area position (x, y).

[0019] Preferably, the S2 includes S21 and S22;

[0020] S21, perform spatial analysis according to the obtained feature vector TIV, specifically divide the area according to the two-dimensional water area position (x, y), and obtain the temperature standard deviation Q of each area by dividing the aquaculture area, reflecting the temperature volatility at the two-dimensional water area position (x, y);

[0021] The temperature standard deviation Q is obtained through the following calculation formula:

[0022] ;

[0023] Wherein, Q(x, y, t) represents the temperature standard deviation at the two-dimensional water area position (x, y) at time t, and T(x, y, z, t, i) represents the water temperature data obtained by the i-th sensor at the three-dimensional water area position (x, y, z) at time t.

[0024] Preferably, S22, according to the temperature standard deviation Q(x, y, t) at the obtained two-dimensional water area position (x, y), compare the temperature standard deviations Q(x, y, t) at different two-dimensional water area positions (x, y) with the preset heat island effect threshold Qt to perform heat island identification on the two-dimensional water area position (x, y), and obtain the heat island effect identification marks for different two-dimensional water area positions (x, y);

[0025] The heat island effect identification mark is obtained through the following comparison method:

[0026] When the temperature standard deviation Q(x, y, t) at the two-dimensional water area position (x, y) at time t ≥ the heat island effect threshold Qt, the heat island effect identification mark for the area at the two-dimensional water area position (x, y) is a heat island mark, and a heat island effect identification mark RBS = 1 is generated;

[0027] When the temperature standard deviation Q(x, y, t) at the two-dimensional water area position (x, y) at time t < the heat island effect threshold Qt, the heat island effect identification mark for the area at the two-dimensional water area position (x, y) is a non-heat island mark, and a heat island effect identification mark RBS = 0 is generated.

[0028] Preferably, the S3 includes S31;

[0029] S31. Mark and integrate the aquaculture areas based on the identified heat island effect identifiers obtained. Specifically, identify the heat island effect identifier RBS at the two-dimensional positions (x, y) of all waters within the aquaculture areas. Propose the two-dimensional position (x, y) areas of the waters where the heat island effect identifier RBS = 0, and retain the two-dimensional position (x, y) areas of the waters where the heat island effect identifier RBS = 1. Then, integrate the temperature standard deviation Q(x, y, t) and the heat island effect identifier RBS at the retained two-dimensional positions (x, y) at time t to form the heat island effect dataset TIVh.

[0030] Preferably, S4 includes S41 and S42;

[0031] S41. Conduct data interaction analysis on the obtained heat island effect dataset TIVh. Specifically, conduct data interaction analysis by combining the water flow rate V(x, y, t) at each two-dimensional position (x, y) area in the heat island effect dataset TIVh and the target temperature Ttarget(x, y) preset according to the aquaculture characteristics of the aquaculture area to obtain the temperature amount ΔT that needs to be adjusted in the current aquaculture area.

[0032] The temperature amount ΔT is obtained through the following calculation formula:

[0033] ;

[0034] In the formula, α1 and α2 respectively represent the difference between the target temperature Ttarget(x, y) and the temperature standard deviation Q(x, y, t) and the adjustment coefficient of the water flow rate V(x, y, t).

[0035] Preferably, S42. Compare the obtained temperature amount ΔT with the preset range threshold for generating the temperature control instruction, generate control instructions for different adjustment methods, and adjust the temperature of the aquaculture area according to the generated control instructions;

[0036] Among them, the range threshold for generating the temperature control instruction includes the upper range threshold Sthe and the lower range threshold Xthe;

[0037] The control instruction is obtained through the following generation method:

[0038] When the temperature amount ΔT > the upper range threshold Sthe, generate a heating control instruction, including turning on the water temperature heating device within the aquaculture area and starting the water flow circulation equipment to transport hot water to circulate the waters within the aquaculture area;

[0039] When the temperature difference △T < the lower limit threshold Xthe of the range, a temperature reduction control instruction is generated, including turning off the water temperature heating device in the aquaculture area, adjusting the power of the water flow circulation equipment proportionally, and putting ice cubes for temperature reduction and starting the cooling equipment.

[0040] Preferably, the S5 includes S51 and S52;

[0041] S51. Detect the temperature change of the aquaculture area with the identification mark of the heat island effect in a fixed period after the control instruction is triggered, and obtain the temperature control effect index E by analyzing the temperature change, including comparing the temperature difference information of the temperature standard deviation Q(x, y, t) before and after the control instruction is triggered, and marking it as the temperature correction amount Tchange.

[0042] The temperature correction amount Tchange(x, y, t) is obtained through the following calculation formula:

[0043] ;

[0044] Tchange(x, y, t) represents the temperature correction amount at the two-dimensional position (x, y) of the water area at time t, and Qbefore(x, y, t) represents the temperature standard deviation before the control instruction is triggered at the two-dimensional position (x, y) of the water area at time t;

[0045] The temperature control effect index E is obtained through the calculation formula, where E(x, y, t) represents the temperature control effect index at the two-dimensional position (x, y) of the water area at time t.

[0046] Preferably, S52. Compare the obtained temperature control effect index E(x, y, t) at the two-dimensional position (x, y) of the water area at time t with the preset temperature control adjustment effect threshold Ethe to obtain the trigger state for triggering the iterative optimization mechanism;

[0047] The trigger state is obtained through the following comparison method:

[0048] When the temperature control effect index E(x, y, t) at the two-dimensional position (x, y) of the water area at time t ≥ the temperature control adjustment effect threshold Ethe, the trigger state for triggering the iterative optimization mechanism is obtained as the non-trigger state;

[0049] When the temperature control effect index E(x, y, t) at the two-dimensional position (x, y) of the water area at time t ≥ the temperature control adjustment effect threshold Ethe, the trigger state for triggering the iterative optimization mechanism is obtained as the trigger state, and the power ratio of the equipment adjusted by the control instruction is increased until the trigger state for triggering the iterative optimization mechanism is the non-trigger state.

[0050] An aquaculture environment monitoring system based on the Internet of Things, comprising an aquaculture area data collection module, a data analysis and recognition module, a marking and integration module, an adjustment generation module, and an evaluation and optimization module;

[0051] The aquaculture area data collection module collects water temperature data of the aquaculture area through temperature sensors, and integrates the temperature data points obtained in each area to obtain a feature vector TIV;

[0052] The data analysis and recognition module performs spatial analysis based on the obtained feature vector TIV. By dividing the aquaculture area, the temperature standard deviation Q of each area is obtained, and the heat island effect is identified based on the temperature standard deviation Q to obtain the heat island effect identification flag of each area;

[0053] The marking and integration module marks and integrates the aquaculture area through the obtained heat island effect identification flag to obtain a heat island effect data set TIVh;

[0054] The adjustment generation module performs data interaction analysis on the obtained heat island effect data set TIVh, obtains the temperature adjustment amount △T that needs to be adjusted in the current aquaculture area, and generates a control instruction according to the temperature adjustment amount △T to adjust the temperature of the aquaculture area;

[0055] The evaluation and optimization module monitors the temperature change of the aquaculture area with the heat island effect identification flag in a fixed period after the control instruction is triggered, analyzes the temperature change to obtain a temperature control effect index E, and triggers an iterative optimization mechanism according to the temperature control effect index E.

[0056] The present invention provides an aquaculture environment monitoring system and method based on the Internet of Things, having the following beneficial effects:

[0057] (1) By forming the feature vector TIV, the comprehensive monitoring of the regional temperature is realized. Then, based on this feature vector, spatial analysis is carried out, the temperature standard deviation Q of each area is calculated, and the possible heat island effect areas are identified through the standard deviation value, and finally the heat island effect identification flag is generated, providing a basis for subsequent precise adjustment. Through the marking and integration of the heat island effect areas, a heat island effect data set TIVh is constructed, providing data support for temperature control adjustment. Based on this data set, the system further calculates the temperature adjustment amount △T, generates a control instruction according to this amount, precisely adjusts the temperature, and thus avoids affecting the health of the fish population due to local overheating. Finally, through the continuous monitoring and analysis of the temperature change, the temperature control effect index E is calculated, and through the dynamic optimization of this index, the iterative improvement of the temperature control strategy is ensured, thereby improving the temperature control effect. This series of steps can effectively reduce the temperature fluctuation problem caused by the inability to identify and adjust the heat island effect in real time in the traditional method.

[0058] (2) By screening the obtained heat island effect identification label RBS, the system can accurately distinguish the water areas with heat island effect, and integrate the temperature standard deviation Q(x, y, t) and the heat island effect identification label RBS of these areas to form a heat island effect data set TIVh, providing effective data support for subsequent regulation. Step S4 further combines the water flow rate V(x, y, t) in the two-dimensional position (x, y) area of each water area in the heat island effect data set TIVh with the preset target temperature Ttarget(x, y), calculates the temperature adjustment amount △T through interactive analysis, and can generate regulation instructions for heating or cooling. By means of starting the water temperature heating device, adjusting the water flow circulation equipment, putting ice cubes for cooling, etc., the temperature adjustment can be quickly realized. Finally, through this efficient temperature control strategy, the aquaculture area can maintain a more stable and balanced temperature environment, thus promoting the healthy development and benefit improvement of aquaculture.

[0059] (3) By comparing the temperature standard deviation Q(x, y, t) before and after the regulation instruction is triggered, the temperature correction amount Tchange(x, y, t) is calculated to evaluate the effect of temperature adjustment. This process can effectively identify the actual effect of the temperature control operation and provide a quantitative basis for subsequent optimization. The temperature control effect index E(x, y, t) further evaluates the effect of temperature control adjustment through the temperature change situation reflected by the temperature correction amount Tchange(x, y, t). Through this index, the system can monitor and evaluate the temperature control state at each two-dimensional position (x, y) of the water area in real time, so as to start the iterative optimization mechanism when needed to ensure that the temperature control system can automatically adjust according to the real-time feedback. By comparing with the preset temperature control adjustment effect threshold Ethe, it is judged whether to trigger the optimization mechanism. Through this closed-loop iterative optimization mechanism, the environmental stability of the aquaculture area can be significantly improved, the negative impact of temperature fluctuations on aquaculture can be reduced, and the aquaculture benefit can be promoted. Description of the Drawings

[0060] Figure 1 It is a schematic diagram of the steps of an aquaculture environment monitoring method based on the Internet of Things according to the present invention;

[0061] Figure 2 It is a schematic block diagram of an aquaculture environment monitoring system based on the Internet of Things according to the present invention. Detailed Embodiment

[0062] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0063] Embodiment 1

[0064] The present invention provides an aquaculture environment monitoring method based on the Internet of Things. Please refer to Figure 1 , which includes the following steps:

[0065] S1. Collect the water temperature data of the aquaculture area through a temperature sensor, and integrate the temperature data points obtained in each area to obtain the feature vector TIV;

[0066] S2. Perform spatial analysis according to the obtained feature vector TIV. By dividing the aquaculture area, obtain the temperature standard deviation Q of each area, and identify the heat island effect according to the temperature standard deviation Q to obtain the heat island effect identification flag of each area;

[0067] S3. Mark and integrate the aquaculture area according to the obtained heat island effect identification flag to obtain the heat island effect data set TIVh;

[0068] S4. Perform data interaction analysis on the obtained heat island effect data set TIVh to obtain the temperature amount △T that needs to be adjusted in the current aquaculture area, and generate a control command according to the temperature amount △T to adjust the temperature of the aquaculture area;

[0069] S5. Perform temperature changes in the aquaculture areas with heat island effect identification flags at a fixed period after the control command is triggered, and obtain the temperature control effect index E by analyzing the temperature changes, and trigger the iterative optimization mechanism according to the temperature control effect index E.

[0070] In this embodiment, through multi-step intelligent regulation and analysis, the temperature management in the aquaculture area is significantly optimized, especially in solving the problem that traditional temperature control methods cannot effectively identify and adjust local temperature differences and the heat island effect. First, temperature sensors are used to collect and integrate the temperature data in the aquaculture area to form a feature vector TIV, thereby achieving comprehensive monitoring of the regional temperature. Then, based on this feature vector, spatial analysis is carried out to calculate the temperature standard deviation Q of each area, and the possible heat island effect areas are identified through the standard deviation values. Finally, a heat island effect identification label is generated, providing a basis for subsequent precise adjustment. By marking and integrating the heat island effect areas, a heat island effect data set TIVh is constructed, providing data support for temperature control adjustment. Based on this data set, the system further calculates the temperature adjustment amount △T and generates a control instruction according to this amount to precisely adjust the temperature, thereby avoiding affecting the health of the fish population due to local overheating. Finally, through continuous monitoring and analysis of the temperature change, the temperature control effect index E is calculated, and through the dynamic optimization of this index, the iterative improvement of the temperature control strategy is ensured, thereby improving the temperature control effect. This series of steps can not only effectively reduce the temperature fluctuation problem caused by the inability to identify and adjust the heat island effect in real time in the traditional method, but also improve the temperature management efficiency in the aquaculture area by continuously optimizing the adjustment strategy, promoting the healthy growth of the fish population and the improvement of the aquaculture benefit.

[0071] Embodiment 2

[0072] This embodiment is an explanatory description based on Embodiment 1. Please refer to Figure 1 , specifically: S1 includes S11 and S12;

[0073] S11. By arranging multiple temperature sensors in the aquaculture area, the water temperature data T at the three-dimensional positions (x, y, z) of different waters in the aquaculture area are collected in real time. At the same time, when the temperature sensors collect the water temperature data T at a fixed period, the collection time t is marked, and the water temperature data T(x, y, z, t) at the three-dimensional position (x, y, z) of the water area at time t is obtained;

[0074] Among them, x, y, and z respectively represent the horizontal axis coordinate, the vertical axis coordinate, and the vertical axis coordinate;

[0075] S12. Aggregate the water temperature data T(x, y, z, t) at different three-dimensional water positions (x, y, z) at time t according to the obtained three-dimensional water position (x, y, z) at time t, obtain the water temperature data T(x, y, z, t) within the two-dimensional water position (x, y) of the same area, calculate the mean value of the water temperature data T(x, y, z, t) at the two-dimensional water position (x, y), obtain the average temperature Tavg(x, y, t) of the two-dimensional water position (x, y), and then integrate the average temperature Tavg(x, y, t) of the two-dimensional water position (x, y) to obtain the feature vector TIV;

[0076] The average temperature Tavg(x, y, t) is obtained through the following calculation formula:

[0077] ;

[0078] In the formula, N(x, y) represents the total number of sensor data points at the water position (x, y).

[0079] S2 includes S21 and S22;

[0080] S21. Conduct spatial analysis according to the obtained feature vector TIV. Specifically, divide the area according to the two-dimensional water position (x, y). By dividing the aquaculture area, obtain the temperature standard deviation Q of each area, which reflects the temperature volatility at the two-dimensional water position (x, y);

[0081] The temperature standard deviation Q is obtained through the following calculation formula:

[0082] ;

[0083] In the formula, Q(x, y, t) represents the temperature standard deviation at the two-dimensional water position (x, y) at time t, and T(x, y, z, t, i) represents the water temperature data obtained by the i-th sensor at the three-dimensional water position (x, y, z) at time t.

[0084] S22. According to the obtained temperature standard deviation Q(x, y, t) at the two-dimensional water position (x, y), compare the temperature standard deviations Q(x, y, t) at different two-dimensional water positions (x, y) with the preset heat island effect threshold Qt to identify the heat island at the two-dimensional water position (x, y), and obtain the heat island effect identification marks for different areas at the two-dimensional water position (x, y);

[0085] The heat island effect identification marks are obtained through the following comparison method:

[0086] When the temperature standard deviation Q(x, y, t) of the two-dimensional water area position (x, y) at time t ≥ the heat island effect threshold Qt, the identification of the regional heat island effect at the two-dimensional water area position (x, y) is the heat island identifier, and the heat island effect identification identifier RBS = 1 is generated;

[0087] When the temperature standard deviation Q(x, y, t) of the two-dimensional water area position (x, y) at time t < the heat island effect threshold Qt, the identification of the regional heat island effect at the two-dimensional water area position (x, y) is the non-heat island identifier, and the heat island effect identification identifier RBS = 0 is generated.

[0088] In this embodiment, by arranging multiple temperature sensors, the water temperature data T at different three-dimensional water area positions (x, y, z) is collected in real time, and the collection time t is marked, ensuring the comprehensive monitoring of the water temperature distribution in the aquaculture area. By aggregating the water temperature data at different water area positions, the average temperature Tavg(x, y, t) at each two-dimensional position (x, y) is calculated, thus forming the feature vector TIV, providing a clear description of the overall temperature state of the water area. Then, in step S2, by performing spatial analysis on the obtained feature vector, the temperature standard deviation Q of each region is accurately calculated, reflecting the temperature volatility of the water area, and further helping to identify the heat island effect. In particular, by comparing with the preset heat island effect threshold Qt, the method can not only accurately identify the heat island effect area in the water area, but also clearly identify the heat island area and the non-heat island area, providing reliable data support for subsequent temperature control adjustment. Finally, relying on these accurate temperature monitoring and heat island effect identification, the system can perform dynamic temperature control more efficiently, improving the stability of the aquaculture environment, thereby enhancing the aquaculture benefit and the quality of the growth environment of the fish population. This method avoids the problems of slow response and inaccurate adjustment of traditional temperature control means to regional temperature changes, ensuring that the temperature in the aquaculture area fluctuates within an optimal range, greatly improving the scientificity and efficiency of aquaculture management.

[0089] Embodiment 3

[0090] This embodiment is an explanatory description based on Embodiment 2, please refer to Figure 1 , specifically: The said S3 includes S31;

[0091] S31. Mark and integrate the aquaculture areas based on the identified heat island effect identifiers obtained. Specifically, identify the heat island effect identifier RBS at the two-dimensional positions (x, y) of all waters in the aquaculture area, propose the two-dimensional position (x, y) area of the waters where the heat island effect identifier RBS = 0, retain the two-dimensional position (x, y) area of the waters where the heat island effect identifier RBS = 1, and then combine the temperature standard deviation Q(x, y, t) and the heat island effect identifier RBS at the two-dimensional position (x, y) of the retained waters at time t to form the heat island effect dataset TIVh.

[0092] S4 described above includes S41 and S42;

[0093] S41. Conduct data interaction analysis on the obtained heat island effect dataset TIVh. Specifically, conduct data interaction analysis by combining the water flow rate V(x, y, t) at each two-dimensional position (x, y) area in the heat island effect dataset TIVh and the target temperature Ttarget(x, y) preset according to the aquaculture characteristics of the aquaculture area to obtain the temperature adjustment amount △T required for the current aquaculture area.

[0094] The temperature adjustment amount △T is obtained through the following calculation formula:

[0095] ;

[0096] In the formula, α1 and α2 respectively represent the difference between the target temperature Ttarget(x, y) and the temperature standard deviation Q(x, y, t) and the adjustment coefficient of the water flow rate V(x, y, t). The purpose of this formula is that the faster the water flow, the faster the heat is propagated, and the easier it is to eliminate the temperature non-uniformity. Therefore, when calculating the adjustment amount, multiplying the water flow rate by the temperature difference can better reflect the dynamic process of water body heat balance and adjustment, and achieve the adjustment of temperature control requirements according to the water flow rate. For example, if the temperature difference is large but the water flow rate is high, a smaller adjustment amount may be required because the water flow is already helping to balance the temperature; if the water flow is slow, the adjustment amount needs to be increased to help the temperature reach consistency throughout the area. The practical significance is that when the water flow rate is high, the heat distribution is more uniform, the temperature difference decreases, so the adjustment amplitude should be reduced, and the system should automatically reduce the temperature control intensity; when the water flow rate is low, the heat transfer is not fast enough, and the temperature difference may be large, so the adjustment amount should be increased to accelerate the process of temperature balance.

[0097] S42. Compare the obtained temperature adjustment amount △T with the preset range threshold of the temperature control instruction to generate control instructions of different adjustment methods, and adjust the temperature of the aquaculture area according to the generated control instructions.

[0098] Among them, the temperature control instruction generation range threshold includes the range upper limit threshold Sthe and the range lower limit threshold Xthe;

[0099] The control instruction is obtained through the following generation method:

[0100] When the temperature difference △T > the range upper limit threshold Sthe, a heating control instruction is generated, including turning on the water temperature heating device in the aquaculture area, and starting the water flow circulation equipment to transport hot water to circulate the water area in the aquaculture area;

[0101] When the temperature difference △T < the range lower limit threshold Xthe, a cooling control instruction is generated, including turning off the water temperature heating device in the aquaculture area, adjusting the power of the water flow circulation equipment proportionally, and putting in cooling ice cubes and starting the cooling equipment.

[0102] In this embodiment, by screening the obtained heat island effect identification label RBS, the system can accurately distinguish the water areas with heat island effect, and integrate the temperature standard deviation Q(x, y, t) and the heat island effect identification label RBS of these areas to form the heat island effect data set TIVh, providing effective data support for subsequent control. In step S4, further combining the water flow rate V(x, y, t) in the two-dimensional position (x, y) area of each water area in the heat island effect data set TIVh with the preset target temperature Ttarget(x, y), the temperature adjustment amount △T is calculated through interactive analysis, and the adjustment amount is dynamically adjusted in combination with the water flow rate to ensure more accurate adjustment effect. In particular, the influence of the water flow rate on the adjustment amount can reflect the heat propagation speed of the water body. The faster the water flow, the more uniform the heat distribution, and the corresponding reduction in the adjustment amount; when the water flow is slower, the adjustment amount needs to be increased. This refined adjustment mechanism can be optimized according to the actual water flow conditions, improving the response speed and effect of temperature control adjustment. When the temperature difference △T exceeds the preset range threshold, the system can generate heating or cooling control instructions, and quickly realize temperature adjustment by starting the water temperature heating device, adjusting the water flow circulation equipment, putting in cooling ice cubes, etc. Finally, through this efficient temperature control strategy, the aquaculture area can maintain a more stable and balanced temperature environment, thus promoting the healthy development and benefit improvement of aquaculture.

[0103] Embodiment 4

[0104] This embodiment is an explanatory description based on Embodiment 3, please refer to Figure 1 , specifically: The S5 includes S51 and S52;

[0105] S51. Conduct temperature changes in the aquaculture areas with heat island effect identification marks in a fixed period after the control instruction is triggered, and obtain the temperature control effect index E by analyzing the temperature changes, including comparing the temperature difference information of the temperature standard deviation Q(x, y, t) before and after the control instruction is triggered, and marking it as the temperature correction amount Tchange.

[0106] The temperature correction amount Tchange(x, y, t) is obtained through the following calculation formula:

[0107] ;

[0108] Tchange(x, y, t) represents the temperature correction amount at the two-dimensional position (x, y) of the water area at time t, and Qbefore(x, y, t) represents the temperature standard deviation before the control instruction is triggered at the two-dimensional position (x, y) of the water area at time t.

[0109] The temperature control effect index E is obtained through the calculation formula. In the formula, E(x, y, t) represents the temperature control effect index at the two-dimensional position (x, y) of the water area at time t.

[0110] S52. Compare the obtained temperature control effect index E(x, y, t) at the two-dimensional position (x, y) of the water area at time t with the preset temperature control adjustment effect threshold Ethe to obtain the trigger status for triggering the iterative optimization mechanism.

[0111] The trigger status is obtained through the following comparison method:

[0112] When the temperature control effect index E(x, y, t) at the two-dimensional position (x, y) of the water area at time t ≥ the temperature control adjustment effect threshold Ethe, obtain the trigger status for triggering the iterative optimization mechanism as the non-trigger status.

[0113] When the temperature control effect index E(x, y, t) at the two-dimensional position (x, y) of the water area at time t ≥ the temperature control adjustment effect threshold Ethe, obtain the trigger status for triggering the iterative optimization mechanism as the trigger status, and perform a power ratio increase adjustment on the equipment adjusted by the control instruction until the trigger status for triggering the iterative optimization mechanism is the non-trigger status.

[0114] In this embodiment, by comparing the temperature standard deviation Q(x, y, t) before and after the trigger of the regulation instruction, the temperature correction amount Tchange(x, y, t) is calculated, so as to evaluate the effect of temperature regulation. This process can effectively identify the actual effect of the temperature control operation and provide a quantitative basis for subsequent optimization. The temperature control effect index E(x, y, t) further evaluates the effect of temperature control adjustment through the temperature change situation reflected by the temperature correction amount Tchange(x, y, t). Through this index, the system can monitor and evaluate the temperature control status at each two-dimensional position (x, y) of each water area in real time, so as to start the iterative optimization mechanism when needed to ensure that the temperature control system can automatically adjust according to real-time feedback. By comparing with the preset temperature control adjustment effect threshold Ethe, it is judged whether to trigger the optimization mechanism. If it is lower than the threshold, the optimization mechanism is triggered to enhance the temperature control effect, otherwise the status quo is maintained. This mechanism optimizes the temperature regulation process by automatically adjusting the power ratio of the regulation instruction device, and finally realizes the continuous improvement of the temperature control efficiency in the aquaculture area and the precise control of temperature balance. Through this closed-loop iterative optimization mechanism, the environmental stability of the breeding area can be significantly improved, the negative impact of temperature fluctuations on aquaculture can be reduced, and the breeding efficiency can be promoted.

[0115] Embodiment 5

[0116] An aquaculture environment monitoring system based on the Internet of Things, please refer to Figure 2 , specifically: including an aquaculture area data collection module, a data analysis and recognition module, a marking and integration module, an adjustment generation module and an evaluation and optimization module;

[0117] The aquaculture area data collection module collects the water temperature data of the aquaculture area through temperature sensors, and integrates the temperature data points obtained in each area to obtain the feature vector TIV;

[0118] The data analysis and recognition module performs spatial analysis according to the obtained feature vector TIV. By dividing the aquaculture area, the temperature standard deviation Q of each area is obtained, and the heat island effect is identified according to the temperature standard deviation Q to obtain the heat island effect identification mark of each area;

[0119] The marking and integration module marks and integrates the aquaculture area through the obtained heat island effect identification mark to obtain the heat island effect data set TIVh;

[0120] The adjustment generation module performs data interaction analysis on the obtained heat island effect data set TIVh to obtain the temperature amount △T that needs to be adjusted in the current aquaculture area, and generates a regulation instruction according to the temperature amount △T to adjust the temperature of the aquaculture area;

[0121] The evaluation and optimization module measures the temperature change of the aquaculture area with the identification of the heat island effect at fixed intervals after the triggering of the control instruction. By analyzing the temperature change, the temperature control effect index E is obtained, and the iterative optimization mechanism is triggered based on the temperature control effect index E.

[0122] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring an aquaculture environment based on the Internet of Things, characterized in that: The following steps are involved: S1. Collect water temperature data of aquaculture areas through temperature sensors, and integrate the temperature data points obtained in each area to obtain a feature vector TIV; S2. Perform spatial analysis based on the acquired characteristic vector TIV, segment the aquaculture area, obtain the temperature standard deviation Q of each area, and identify the heat island effect based on the temperature standard deviation Q to obtain the heat island effect identification mark of each area; S3, marking and regional integration of aquaculture areas by using the obtained heat island effect identification marks to obtain the heat island effect dataset TIVh; S4, by performing data interactive analysis on the obtained heat island effect data set TIVh, the temperature △T that needs to be adjusted in the current aquaculture area is obtained, and a control instruction is generated according to the temperature △T to adjust the temperature of the aquaculture area; S5. After the control command is triggered, the temperature change of the aquaculture area with the heat island effect identification mark is carried out at a fixed period, and the temperature control effect index E is obtained by analyzing the temperature change, and the iterative optimization mechanism is triggered according to the temperature control effect index E.

2. The aquaculture environment monitoring method based on the Internet of Things according to claim 1 is characterized in that: Said S1 includes S11 and S12; S11, by arranging multiple temperature sensors in the aquaculture area, collecting water temperature data T of different three-dimensional positions (x, y, z) in the aquaculture area in real time, and marking the collection time t when the temperature sensor collects water temperature data T in a fixed period, and obtaining water temperature data T (x, y, z, t) of the three-dimensional position (x, y, z) of the water area at time t; Among them, x, y and z represent the horizontal axis coordinate, the vertical axis coordinate and the vertical axis coordinate respectively; S12, according to the water temperature data T(x, y, z, t) of the three-dimensional position (x, y, z) of the water area at time t, the water temperature data T(x, y, z, t) of different three-dimensional positions (x, y, z) of the water area at time t are aggregated, the water temperature data T(x, y, z, t) within the two-dimensional position (x, y) of the water area in the same area are obtained, and the water temperature data T(x, y, z, t) at the two-dimensional position (x, y) of the water area are averaged to obtain the average temperature Tavg(x, y, t) of the two-dimensional position (x, y) of the water area, and then the average temperature Tavg(x, y, t) of the two-dimensional position (x, y) of the water area is integrated to obtain the feature vector TIV; The average temperature Tavg (x, y, t) is obtained by the following calculation formula: ； Where N(x, y) represents the total number of sensor data points at the water location (x, y).

3. The aquaculture environment monitoring method based on the Internet of Things according to claim 2 is characterized in that: The S2 includes S21 and S22; S21, performing spatial analysis based on the acquired characteristic vector TIV, specifically segmenting the area according to the two-dimensional position (x, y) of the water area, and obtaining the temperature standard deviation Q of each area by segmenting the aquaculture area, reflecting the temperature volatility at the two-dimensional position (x, y) of the water area; The temperature standard deviation Q is obtained by the following calculation formula: ； Where Q(x, y, t) represents the temperature standard deviation of the two-dimensional position (x, y) of the water area at time t, and T(x, y, z, t, i) represents the water temperature data obtained by the i-th sensor at the three-dimensional position (x, y, z) of the water area at time t.

4. The aquaculture environment monitoring method based on the Internet of Things according to claim 3 is characterized in that: S22, according to the obtained temperature standard deviation Q (x, y, t) at the two-dimensional position (x, y) of the water area, the temperature standard deviation Q (x, y, t) at the two-dimensional position (x, y) of different water areas is compared with a preset heat island effect threshold value Qt to identify the heat island at the two-dimensional position (x, y) of the water area, and obtain heat island effect identification marks of the areas at the two-dimensional positions (x, y) of different water areas; The heat island effect identification mark is obtained by the following comparison method: When the temperature standard deviation Q(x, y, t) of the two-dimensional position (x, y) of the water area at time t is ≥ the heat island effect threshold Qt, the regional heat island effect identification mark at the two-dimensional position (x, y) of the water area is a heat island mark, and the heat island effect identification mark RBS=1 is generated; When the temperature standard deviation Q(x, y, t) of the two-dimensional position (x, y) of the water area at time t is less than the heat island effect threshold Qt, the regional heat island effect identification mark at the two-dimensional position (x, y) of the water area is marked as a non-heat island mark, and the heat island effect identification mark RBS=0 is generated.

5. The aquaculture environment monitoring method based on the Internet of Things according to claim 4 is characterized in that: The S3 includes S31; S31. Mark and integrate the aquaculture areas by using the obtained heat island effect identification marks. Specifically, identify the heat island effect identification mark RBS at the two-dimensional position (x, y) of all water areas in the aquaculture area, propose the water area two-dimensional position (x, y) where the heat island effect identification mark RBS=0, retain the water area two-dimensional position (x, y) where the heat island effect identification mark RBS=1, and then integrate the temperature standard deviation Q(x, y, t) of the retained water area two-dimensional position (x, y) at time t and the heat island effect identification mark RBS to form the heat island effect dataset TIVh.

6. The aquaculture environment monitoring method based on the Internet of Things according to claim 5 is characterized in that: The S4 includes S41 and S42; S41, by performing data interactive analysis on the obtained heat island effect data set TIVh, specifically by combining the water flow rate V(x, y, t) at each two-dimensional position (x, y) area of ​​the heat island effect data set TIVh and the target temperature Ttarget(x, y) preset in the aquaculture area according to the aquatic characteristics, to obtain the temperature △T that needs to be adjusted in the current aquaculture area; The temperature value ΔT is obtained by the following calculation formula: ； Where α1 and α2 represent the difference between the target temperature Ttarget (x, y) and the temperature standard deviation Q (x, y, t) and the adjustment coefficient of the water flow rate V (x, y, t), respectively.

7. The aquaculture environment monitoring method based on the Internet of Things according to claim 6 is characterized in that: S42, comparing the acquired temperature value ΔT with a preset temperature control instruction generation range threshold, generating control instructions of different adjustment methods, and adjusting the temperature of the aquaculture area according to the generated control instructions; The temperature control instruction generation range threshold includes an upper range threshold Sthe and a lower range threshold Xthe; The control instructions are obtained by the following generation method: When the temperature value △T> the upper limit threshold value Sthe, a heating control instruction is generated, including controlling the start of the water temperature heating device in the aquaculture area and starting the water circulation equipment to transport hot water to circulate the water area in the aquaculture area; When the temperature value △T is less than the lower limit threshold Xthe, a cooling control instruction is generated, including shutting down the water temperature heating device in the aquaculture area, proportionally adjusting the power of the water circulation equipment, and placing cooling ice cubes and starting the cooling equipment.

8. The aquaculture environment monitoring method based on the Internet of Things according to claim 7 is characterized in that: The S5 includes S51 and S52; S51, performing temperature changes in the aquaculture area with heat island effect identification marks at a fixed period after the control command is triggered, and obtaining a temperature control effect index E by analyzing the temperature changes, including comparing the temperature standard deviation Q (x, y, t) before and after the control command is triggered, and marking it as a temperature correction value Tchange; The temperature correction value Tchange (x, y, t) is obtained by the following calculation formula: ； Tchange (x, y, t) represents the temperature correction at the two-dimensional position (x, y) of the water area at time t, and Qbefore (x, y, t) represents the standard deviation of the temperature before the control instruction is triggered at the two-dimensional position (x, y) of the water area at time t; The temperature control effect index E is The calculation formula is obtained, where E (x, y, t) represents the temperature control effect index at the two-dimensional position (x, y) of the water area at time t.

9. The aquaculture environment monitoring method based on the Internet of Things according to claim 8, characterized in that: S52, comparing the temperature control effect index E(x, y, t) at the acquired two-dimensional position (x, y) of the water area at time t with a preset temperature control adjustment effect threshold Ethe, to obtain a triggering state for triggering an iterative optimization mechanism; The trigger status is obtained by the following comparison method: When the temperature control effect index E(x, y, t) of the two-dimensional position (x, y) of the water area at time t ≥ the temperature control adjustment effect threshold Ethe, the trigger state of the triggering iterative optimization mechanism is obtained as a non-trigger state; When the temperature control effect index E(x, y, t) of the two-dimensional position (x, y) of the water area at time t ≥ the temperature control adjustment effect threshold Ethe, the trigger state of the iterative optimization mechanism is obtained as the trigger state, and the power proportion of the equipment adjusted by the control instruction is increased and adjusted until the trigger state of the iterative optimization mechanism is not triggered.

10. An aquaculture environment monitoring system based on the Internet of Things, applied to an aquaculture environment monitoring method based on the Internet of Things according to any one of claims 1 to 9, characterized in that: It includes aquaculture area data collection module, data analysis and identification module, marking and integration module, adjustment generation module and evaluation optimization module; The aquaculture area data collection module collects water temperature data of the aquaculture area through a temperature sensor, and integrates the temperature data points obtained in each area to obtain a characteristic vector TIV; The data analysis and identification module performs spatial analysis based on the acquired feature vector TIV, obtains the temperature standard deviation Q of each area by segmenting the aquaculture area, and identifies the heat island effect based on the temperature standard deviation Q to obtain the heat island effect identification mark of each area; The marking and integration module marks and integrates the aquaculture area by using the obtained heat island effect identification mark to obtain the heat island effect data set TIVh; The adjustment generation module performs data interaction analysis on the acquired heat island effect data set TIVh to obtain the temperature ΔT that needs to be adjusted in the current aquaculture area, and generates a control instruction according to the temperature ΔT to adjust the temperature of the aquaculture area; The evaluation and optimization module performs temperature changes in aquaculture areas with heat island effect identification marks at a fixed period after the control instruction is triggered, obtains a temperature control effect index E by analyzing the temperature changes, and triggers an iterative optimization mechanism based on the temperature control effect index E.

Images