A method and device for monitoring water in an aquaculture area

Abstract

The present invention relates to the field of water body detection technology, and more specifically to a method and apparatus for monitoring water bodies in an aquaculture area. The aquaculture area comprises N categories of sensors, with a plurality of sensors of each category deployed. Based on the monitoring range of the nth category sensor in still water, a plurality of nth category sensors are evenly deployed in the area to be detected. Monitoring data from all nth category sensors is analyzed to define some nth category sensors as nth core sensors. The remaining nth category sensors, except for the nth core sensors, are removed. All N categories of sensors in all areas to be detected within the aquaculture area are traversed. The water environment is then monitored online using all re-deployed sensors. The present invention dynamically optimizes the sensor deployment locations and monitoring ranges to ensure comprehensive and accurate monitoring of the water environment within the aquaculture area, while minimizing sensor deployment and maintenance costs.

Description

Technical Field

[0001] The present invention relates to the technical field of water body detection, and in particular to a method and equipment for monitoring water bodies in an aquaculture area. Background Art

[0002] In aquaculture, the quality of the water environment is directly related to the health of farmed animals, production efficiency, and the stability of ecological equipment. The factors affecting the water environment are very complex, but several key factors have the most significant impact on aquaculture: excess nutrients (nitrogen and phosphorus pollution), dissolved oxygen depletion, water temperature fluctuations, pH fluctuations, etc. However, as farmers' production capacity expands, the density of farmed animals in the water increases, so it is necessary to monitor them through sensors. However, due to the different fluidity and stability of water bodies in different areas, if the same density is used to arrange monitoring points, the monitoring range of some areas will overlap, resulting in a waste of resources. In other areas, the fluidity is greater and the monitoring range is smaller, resulting in some areas not being monitored. Therefore, it is necessary to adjust the layout of different sensors at the monitoring points based on the different parameters of different areas. Summary of the Invention

[0003] In order to solve the technical problem of how to achieve comprehensive and accurate monitoring of the water environment in an aquaculture area with the lowest sensor deployment and maintenance costs, the present invention aims to provide a method and equipment for monitoring water in an aquaculture area. The technical solutions adopted are as follows:

[0004] The first aspect of the present invention is a water monitoring method for an aquaculture area, wherein the sensors in the aquaculture area are of N categories, and a plurality of sensors of each category are arranged; the method comprises: step 1, evenly arranging a plurality of sensors of the nth category in the area to be detected according to the monitoring range of the sensors of the nth category in still water; step 2, defining some of the sensors of the nth category as nth core sensors by analyzing the monitoring data of all the sensors of the nth category in the area to be detected within a preset time period; step 3, removing the remaining sensors of the nth category except the nth core sensor in the area to be detected; step 4, traversing all the sensors of the N categories in all the areas to be detected in the aquaculture area to complete the arrangement of the sensors; and performing online monitoring of the water environment by all the rearranged sensors; wherein, , n and N are both natural numbers.

[0005] In response to the existing technology that uses the same density to arrange monitoring points, the present invention selects and discards sensors in the original layout positions through analysis of sensor monitoring data, retains the position of core sensors, and the positional relationship between the core sensors just achieves the minimum overlap between the monitoring ranges of sensors at different monitoring points. The minimum number of sensors is arranged, which not only avoids monitoring gaps but also achieves the most appropriate layout of monitoring points.

[0006] Furthermore, by analyzing the monitoring data of all n-category sensors in the area to be detected within a preset time period, some of the n-category sensors are defined as n-th core sensors; specifically, the method includes: calculating the n-th standard value of the monitoring range of the n-category sensor at different flow rates; calculating the stability of the consistency between the detection range of each n-category sensor in the area to be detected and the detection range at the water flow rate in the area based on the monitoring data and the n-standard value; virtually adjusting the distance between the n-category sensors in the area to be detected based on the stability; and selecting the n-th core sensor from the several n-category sensors after the virtual adjustment.

[0007] Furthermore, the nth standard value of the monitoring range of the nth category sensor at different flow rates is calculated; specifically comprising: clustering the detection data and water flow rate of the nth category sensor in the area to be detected, as well as the detection data and water flow rate of the nth category sensor in the historical data of other areas to be detected, to obtain clusters of several nth category sensors; obtaining the monitoring range of each nth category sensor based on an analysis of the number of clusters of each nth category sensor with other nth category sensors in the horizontal direction in the area to be detected; determining the nth standard value of the monitoring range of the nth category sensor at different flow rates based on the monitoring range of each nth category sensor in the area to be detected and the water flow rate at the location to which each nth category sensor belongs.

[0008] Furthermore, the stability of the consistency between the detection range of each n-th category sensor and the detection range under the water flow velocity in its area is calculated; specifically, the stability includes: determining the consistency between the detection range of the i-th category sensor in time series and the detection range under the water flow velocity in its area according to the detection range of the i-th category sensor at different flow velocities in time series; obtaining the mean value of the consistency between the detection range of the i-th category sensor in time series and the detection range under the water flow velocity in its area, the maximum value of the consistency between the detection range of the i-th category sensor in time series and the detection range under the water flow velocity in its area, and the maximum value of the consistency between the detection range of the i-th category sensor in time series and the detection range under the water flow velocity in its area, and the maximum value of the consistency between the detection range of the i-th category sensor in time series and the detection range The variance value of the consistency of the detection range under the regional water flow velocity; according to the mean value of the consistency between the detection range of the ith nth category sensor in time series and its detection range under the regional water flow velocity, the maximum value of the consistency between the detection range of the ith nth category sensor in time series and its detection range under the regional water flow velocity, and the variance value of the consistency between the detection range of the ith nth category sensor in time series and its detection range under the regional water flow velocity, the stability of the consistency between the detection range of the ith nth category sensor and its detection range under the regional water flow velocity is obtained; each nth category sensor in the area to be detected is traversed to obtain the stability of the consistency between the detection range of each nth category sensor and its detection range under the regional water flow velocity; wherein i is a natural number and t is a natural number.

[0009] Furthermore, based on the detection range of the ith nth category sensor at different flow rates at different moments in the time series, the consistency of the detection range of the ith nth category sensor in the time series and the detection range at the water flow velocity in its area is determined; specifically, the following steps are performed: obtaining in real time the monitoring range of the nth category sensor in the area to be detected and the water flow velocity at its location; based on the maximum monitoring range of the nth category sensor, the minimum monitoring range of the nth category sensor, the monitoring range of the ith nth category sensor at the tth moment, and the nth standard value of the monitoring range corresponding to the water flow velocity of the nth category sensor at the tth moment, the consistency of the monitoring range of the ith nth category sensor at the flow velocity at the tth moment and the nth standard value is obtained; traversing all moments in the time series, the consistency of the detection range of the ith nth category sensor in the time series and the detection range at the water flow velocity in its area is obtained.

[0010] Furthermore, based on the stability, the distance between the n-th category sensors is virtually adjusted; specifically, the adjustment includes: determining the virtual distance between the i-th n-th category sensor and the j-th n-th category sensor based on the actual distance between the i-th n-th category sensor and the j-th n-th category sensor, the average value of the stability in the area to be detected, the stability of the consistency between the detection range of the i-th n-th category sensor and the detection range under the water flow velocity in its area, and the stability of the consistency between the detection range of the j-th n-th category sensor and the detection range under the water flow velocity in its area; traversing all n-th category sensors, and virtually adjusting all the n-th category sensors based on the virtual distance between the n-th category sensors; wherein i is a natural number, j is a natural number, and i≠j.

[0011] Furthermore, the nth core sensor is selected from the plurality of nth category sensors after virtual adjustment; specifically, the method includes: clustering all nth category sensors according to the virtual distances between all nth category sensors to obtain a plurality of cluster groups; and using the nth category sensor at the center of the cluster group as the nth core sensor.

[0012] Furthermore, a plurality of sensors of the nth category are evenly arranged in the area to be detected; specifically comprising:

[0013] The n-th category sensors are evenly arranged on monitoring rods, and the monitoring rods are evenly arranged in the water environment of the area to be detected.

[0014] In a second aspect, the present invention further provides a water monitoring device for an aquaculture area, comprising N categories of sensors, each category of sensors comprising a number of sensors; and all sensors change their respective categories of monitoring range in still water and are initially deployed in the area to be detected; further comprising: a core sensor determination unit: for defining part of the nth category sensors as nth core sensors by analyzing the monitoring data of all nth category sensors in the area to be detected within a preset time period; a sensor position reset unit: for removing the remaining nth category sensors except the nth core sensor in the area to be detected; and traversing all N categories of sensors in all areas to be detected in the aquaculture area to complete the deployment of sensors; an online monitoring unit: for online monitoring of the water environment through all rearranged sensors; wherein, .

[0015] The present invention has the following beneficial effects:

[0016] The present invention selects and discards sensors in the original deployment positions by analyzing the sensor monitoring data, retaining the positions of the core sensors. The positional relationship between the core sensors just achieves the minimum overlap between the monitoring ranges of sensors at different monitoring points. The present invention deploys a minimum number of sensors, which not only avoids monitoring gaps but also achieves the most appropriate deployment of monitoring points.

[0017] The present invention uses intelligent monitoring equipment to dynamically optimize the sensor layout and monitoring range to ensure comprehensive and accurate monitoring of the water environment in the aquaculture area and minimize the sensor layout and maintenance costs.

[0018] The present invention avoids the generation of monitoring blind spots and overlapping areas in traditional methods by intelligently adjusting the layout position and number of sensors, ensuring comprehensive monitoring of various water layers and different areas in the aquaculture area.

[0019] The present invention can effectively reduce the deployment and maintenance costs of sensors and avoid waste of resources by dynamically adjusting the layout scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A method for monitoring water bodies in an aquaculture area is provided in one embodiment of the present invention;

[0022] Figure 2 A schematic diagram of a sensor clustering field in one embodiment of the present invention;

[0023] Figure 3 An embodiment of the present invention provides a water monitoring device for an aquaculture area. DETAILED DESCRIPTION

[0024] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail a method and apparatus for monitoring water bodies in aquaculture areas, including its specific implementation, structure, features, and effectiveness. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0025] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0026] The following describes in detail a method and device for monitoring water bodies in an aquaculture area provided by the present invention in conjunction with the accompanying drawings.

[0027] See also Figure 1 , which shows a flow chart of a water monitoring method for an aquaculture area provided by an embodiment of the present invention. Generally, there are many categories of sensors in the water environment of an aquaculture area, and there are several sensors of each category. The embodiment of the present invention first arranges the layout of one category of sensors in a certain area to be detected, and then arranges the layout of other categories of sensors in the area to be detected. After completing the layout of all categories of sensors in the current area to be detected, other categories of sensors in other detection areas in the aquaculture area are arranged in sequence, thereby completing the layout of all categories of sensors in the aquaculture area, and achieving the optimization of the positions of all sensors in the aquaculture area. In an embodiment of the present invention, , i≠j, n, N, i and j are natural numbers.

[0028] Since there are N categories of sensors in the aquaculture area, a number of sensors of each category are deployed. Specifically, the deployment of sensors of one category in a certain area to be detected is as follows:

[0029] 1. Based on the monitoring range of the nth type of sensor in still water, evenly distribute several nth type of sensors throughout the area to be monitored. Because the sensor's monitoring range is minimal in still water, it increases in water environments with a certain flow rate. To avoid blind spots, the first step in this embodiment of the present invention is to distribute the sensors based on the minimum monitoring range.

[0030] 2. By analyzing the monitoring data of all n-category sensors in the detection area over a preset period of time, a subset of n-category sensors is defined as n-core sensors. The n-category sensor is any sensor from all categories. This step aims to select core sensors for this category. The core sensors are positioned so that their monitoring range covers all locations in the detection area. There are no gaps or overlaps in the monitoring ranges of the core sensors. This allows monitoring of all locations in the detection area to be achieved with the minimum number of core sensors deployed.

[0031] 2.1. Calculate the nth standard value of the monitoring range of the nth sensor at different flow rates. Cluster the detection data and water flow rate of the nth sensor in the detection area, as well as the detection data and water flow rate of the nth sensor in the historical data of other detection areas, to obtain several clusters of nth sensors. Analyze the number of horizontal clusters of each nth sensor with other nth sensors in the detection area to obtain the monitoring range of each nth sensor. Based on the monitoring range of each nth sensor in the detection area and the water flow rate at the location of each nth sensor, determine the nth standard value of the monitoring range of the nth sensor at different flow rates.

[0032] 2.2. Based on the monitoring data and the nth standard value, calculate the consistency stability of the detection range of each nth category sensor in the area to be detected and the detection range under the water flow velocity in the area.

[0033] First, according to the detection range of the ith nth category sensor at different flow rates in the time series, the consistency of the detection range of the ith nth category sensor in the time series and the detection range at the water flow rate in its area is determined.

[0034] The monitoring range of the nth category sensor and the water flow velocity at the location to be detected are obtained in real time. Based on the maximum monitoring range of the nth category sensor, the minimum monitoring range of the nth category sensor, the monitoring range of the ith nth category sensor at the tth moment, and the nth standard value of the monitoring range corresponding to the water flow velocity of the nth category sensor at the tth moment, the consistency of the monitoring range of the ith nth category sensor at the flow velocity at the tth moment and the nth standard value is obtained. All moments in the time series are traversed to obtain the consistency of the detection range of the ith nth category sensor in the time series and the detection range at the water flow velocity in its area.

[0035] Secondly, based on the consistency between the detection range of the i-th n-th category sensor in time series and the detection range under the water flow velocity in the area obtained above, the mean value of the consistency between the detection range of the i-th n-th category sensor in time series and the detection range under the water flow velocity in the area, the maximum value of the consistency between the detection range of the i-th n-th category sensor in time series and the detection range under the water flow velocity in the area, and the variance value of the consistency between the detection range of the i-th n-th category sensor in time series and the detection range under the water flow velocity in the area are obtained.

[0036] Finally, based on the mean value of the consistency between the detection range of the i-n-th category sensor in time series and the detection range under the water flow velocity in its area, the maximum value of the consistency between the detection range of the i-n-th category sensor in time series and the detection range under the water flow velocity in its area, and the variance value of the consistency between the detection range of the i-n-th category sensor in time series and the detection range under the water flow velocity in its area, the stability of the consistency between the detection range of the i-n-th category sensor and the detection range under the water flow velocity in its area is obtained; traversing each n-th category sensor in the area to be detected, the stability of the consistency between the detection range of each n-th category sensor and the detection range under the water flow velocity in its area is obtained.

[0037] 2.3. Based on 2.2, the consistency stability of the detection range of each n-th type sensor and the detection range under the water flow velocity in its area is obtained, and the distance between the n-th type sensors in the detection area is virtually adjusted.

[0038] The virtual distance between the ith n-th sensor and the jth n-th sensor is determined based on the actual distance between the ith n-th sensor and the jth n-th sensor, the average stability in the detection area, the stability of the consistency between the detection range of the ith n-th sensor and the detection range under the water flow velocity in the area, and the stability of the consistency between the detection range of the jth n-th sensor and the detection range under the water flow velocity in the area. All n-th sensors are traversed and virtually adjusted for all n-th sensors based on the virtual distances between them.

[0039] An nth core sensor is selected from the nth category sensors after virtual adjustment. All nth category sensors are clustered according to the virtual distances between them to obtain several clusters. The nth category sensor at the center of the cluster is used as the nth core sensor.

[0040] 3. Remove all n-category sensors except the n-th core sensor in the area to be detected. Since the monitoring range formed by the deployment of the core sensors can just cover all locations in the current area to be detected, there will be no gaps or overlaps in the monitoring ranges of the core sensors. Therefore, by removing all n-category sensors except the core sensor, the minimum number of sensors can be deployed, that is, the position of the core sensor, to achieve monitoring of all locations in the current area to be detected.

[0041] 4. According to steps 1 to 3 above in the embodiment of the present invention, all N types of sensors in all areas to be detected in the aquaculture area are traversed to complete the sensor deployment; and the water environment is monitored online through all the re-deployed sensors.

[0042] In an embodiment of the present invention, a number of n-th category sensors are evenly arranged in the area to be detected, the n-th category sensors are evenly arranged on monitoring poles, and the monitoring poles are evenly arranged in the water environment of the area to be detected, thereby completing the arrangement of sensors in the most convenient way.

[0043] In response to the prior art that uses the same density to arrange monitoring points, the embodiment of the present invention selects and discards sensors in the original layout positions through analysis of sensor monitoring data, retains the positions of core sensors, and the positional relationship between the core sensors just achieves the minimum overlap between the monitoring ranges of sensors at different monitoring points. The minimum number of sensors is deployed, which not only avoids monitoring gaps but also achieves the most appropriate layout of monitoring points.

[0044] Another method embodiment of the present invention considers how to minimize overlap between the monitoring ranges of different monitoring points while minimizing gaps in monitoring when deploying sensors at monitoring points, thereby achieving the most appropriate deployment of monitoring points. The core of this embodiment of the present invention is how to dynamically optimize sensor deployment locations and monitoring ranges through intelligent monitoring equipment to ensure comprehensive and accurate monitoring of the water environment within aquaculture areas while minimizing sensor deployment and maintenance costs.

[0045] When conducting aquaculture, the quality of the water environment is directly related to the efficiency of aquaculture, so it is necessary to detect the water environment at each location in the aquaculture area. Since the aquaculture area is large and farmers often adopt intensive aquaculture schemes when conducting aquaculture, the changes in the water environment in the aquaculture area are complex. Therefore, when using sensors to detect them, there are some problems with the installation of the sensors. It is necessary to ensure that the changes in each area of ​​the water body can be monitored during monitoring. However, when the sensors are arranged, the cost and convenience of only adjusting the installation and disassembly of the sensors on the monitoring rods are greatly improved compared to adjusting the layout of the entire monitoring rod. Therefore, for the aquaculture area, the position distribution of the sensors on the monitoring rods can be adjusted by adjusting the influence of the monitoring range of the sensors on the monitoring rods on different water layers. And since the monitoring ranges of different sensors are not the same, adjusting the position distribution of the sensors is more conducive to reducing the cost during monitoring. The specific steps of the embodiment of the method of the present invention are as follows:

[0046] step : Division of aquatic areas, arrangement of monitoring poles and preliminary data collection.

[0047] Because the cost of deploying monitoring poles is lower than that of sensors, they can be evenly spaced according to the average of the main sensors' monitoring ranges in still water (using dissolved oxygen sensors as an example; the deployment method for other sensor types is similar). However, for subsequent sensor installation, the sensor placement can be adjusted based on the impact of other factors, such as flow rate, on the sensor's monitoring range. Therefore, after the monitoring poles are deployed, the area to be monitored is divided into several areas to be deployed. Each monitoring pole in each area is adjusted based on the sensor's monitoring data over a period of time. (The spacing of the monitoring poles is primarily based on the minimum monitoring range of the sensors required for various aquaculture applications in still water. Because the water in aquaculture is flowing, the monitoring range at different flow rates is also increased to varying degrees compared to the monitoring range in still water.)

[0048] When monitoring the aquatic environment in aquaculture areas, dissolved oxygen, pH, and water temperature are fundamental parameters. Therefore, sensors on monitoring poles are required to initially collect data from each water layer in each area to be deployed. This data collection process takes 12 hours and a 15-minute cycle. (Horizontally, monitoring poles are deployed in each area to be deployed, and vertically, they are deployed in 0.5-meter increments. This is used as an example; actual deployment can be modified.)

[0049] step : Selection of core sensors.

[0050] a. Determine the standard value of the monitoring range of each test data at different flow rates based on the test data.

[0051] For each area to be detected, in order to determine whether the layout of each sensor in each area is reasonable, the purpose is to make the overlapping range as small as possible under the premise that there is no undetected range in the detection range of the arranged sensors, so as to achieve the layout of the monitoring sensors in the breeding area; therefore, it is necessary to judge the data monitoring range of the sensor based on the detection data of the sensor and the surrounding sensors in the current area, and the degree of similarity with its monitoring data in the horizontal direction of the sensor and the monitoring data at different depths in the vertical direction (that is, the monitoring range of the sensor is judged by the similarity of the monitoring data of the sensor, the monitoring data of the sensors at adjacent positions in the horizontal direction of the sensor, and the monitoring data of the sensors at adjacent positions in the vertical direction), and judge the monitoring range of the sensor at the current flow rate; and since the data monitoring range in the area to be detected is small, the acquisition of the monitoring range at different speeds is incomplete, so it is necessary to obtain the standard change curve of the detection range of this sensor at different flow rates based on the change of the monitoring range at each flow rate.

[0052] Take a sensor (dissolved oxygen sensor) in an area to be tested as an example: Due to the complex environment in the water body, the water flow rate at different depths in the same area is different, which causes the detected data to change. Therefore, the standard value calculated based on the sensor detection data of only one area to be tested will be affected by its environmental factors, resulting in a large deviation between the obtained standard value and the actual standard value.

[0053] The detection data of the dissolved oxygen sensor in the current detection area and the water flow rate in the area where each sensor is located are obtained; at the same time, the detection data and water flow rate of each dissolved oxygen sensor in other detection areas in the historical data are obtained.

[0054] According to the flow rate and detection data corresponding to each sensor, The clustering algorithm is used for analysis to obtain several clusters, which represent several sensors with similar flow rates and detection data.

[0055] For each sensor, since its monitoring range in the horizontal direction is affected by different factors, it is necessary to count the clusters to which each sensor in the horizontal direction belongs, and then obtain its corresponding monitoring range; in the horizontal direction, with the monitoring pole where the current sensor is located as the center, count the number of sensors with the same water depth on the monitoring pole within its 8-neighborhood (3×3) that are in the same cluster as the current sensor; the preset threshold is 0.9. Whether the ratio of the above number to the number of sensors with the same depth in its neighborhood is greater than the threshold, if it is greater, the scale will be expanded, and the 24-neighborhood (5×5), 48-neighborhood (7×7), etc. neighborhoods will be calculated respectively (e.g. Figure 2 The sensor monitors the water flow rate at each sensor location in real time.

[0056] After obtaining the monitoring range of each sensor in the current area to be detected, since the sensors in the breeding area may be affected by other environmental factors and there is uncertainty, the monitoring range of some sensors will fluctuate, and the detection range at some flow rates may be missing, etc., which needs to be supplemented.

[0057] by To divide the flow rate into stages, the sensor's monitoring range in each flow rate stage is counted, and the average value is used as the standard value for the monitoring range in that stage. Based on the available standard values ​​for each flow rate stage, a two-dimensional rectangular coordinate system is constructed with water flow velocity as the horizontal axis and the standard value of the detection data as the vertical axis. Curve fitting is performed using the standard value of the monitoring range for each flow rate stage as the key point to obtain a standard curve model for the monitoring range of the current sensor type at different flow rates.

[0058] Similarly, for other types of sensors, the standard values ​​(standard curves) of the corresponding monitoring ranges of their detection data at different flow rates are obtained.

[0059] b. Calculate the stability of the consistency between the monitoring range of each sensor and the standard value in time series.

[0060] After obtaining the standard value for each sensor, it is necessary to remove the remaining sensors of the same type within the monitoring range of each sensor according to the standard value of the sensor's monitoring range to reduce monitoring costs. However, due to the more complex environment in some areas, there are more interference factors in the area, such as frequent changes in flow rate and animal and plant activities, which cause the detection range in the area to constantly change over time. In this case, to monitor the area, multiple sensors are required, that is, the density of the required sensors is high. When removing sensors, it is necessary to remove fewer sensors accordingly to increase the number of monitoring sensors in the area.

[0061] Determine the consistency of the monitoring range of the sensor in each area with the standard value.

[0062] In the same manner as step a, the real-time monitoring range and regional water flow velocity of each sensor in the area to be detected are obtained; and the standard value of the corresponding monitoring range is obtained according to the obtained regional water flow velocity.

[0063] Since the environmental complexity of each area in the aquaculture area is different, the consistency with the standard value is also different when compared with the standard value. The worse the consistency, the higher the complexity of the area. Therefore, it is necessary to check the consistency of the detection range of each sensor with the detection range of the water flow velocity in the current area:

[0064]

[0065] in, Indicates the consistency between the monitoring range of the i-th sensor at time t and the standard; is the maximum value of the monitoring range of this type of sensor; is the standard value of the water flow velocity corresponding to this type of sensor at time t; is the monitoring range of the i-th sensor in this type of sensor at the t-th moment; It is the minimum value of the monitoring range of this type of sensor.

[0066] pass Normalizing the data to a value between 0 and 1 indicates that the greater the difference between the actual value and the standard value, the less consistent it is, indicating that the environment is subject to greater interference, so sensors in this area need to be deployed at a higher density. It should be noted that to ensure meaningful calculation results, when performing fractional operations in the embodiments of the present invention, when the denominator is 0, a parameter adjustment factor greater than 0 must be added to the denominator to avoid the denominator being 0. The value of the parameter adjustment factor is set by the implementer based on actual conditions and is not specifically limited by this application.

[0067] Determine the stability of the consistency between the monitoring range of the sensor in each area at different times and the standard value.

[0068] After obtaining the monitoring range of each sensor in the area at different times, under ideal conditions, the flow velocity in each area will not change. However, since the flow velocity in different areas will be affected differently by environmental factors, the degree of change in the flow velocity in each area will also be different. Therefore, as time changes, different areas are subject to different interference from environmental factors, that is, the degree of change in the consistency between the monitoring range of each area and the standard value in time series is also different. Therefore, the stability of the consistency between the monitoring range of each area and the standard value can be calculated.

[0069] Sort the collected data of each sensor within the 12-hour collection time range in chronological order to obtain the time series data sequence of each sensor. For each data in the time series data sequence of the current sensor, the above steps are used to determine the consistency between the monitoring range and the standard value at the time corresponding to each data.

[0070] Since the consistency between the detection range of different sensors and their detection range at the water flow rate will change over time, and the degree of change is different due to different environmental influences, the stability of the consistency between the detection range of each sensor and its detection range at the regional water flow rate can be calculated:

[0071]

[0072] in, is the consistency stability between the detection range of the i-th sensor and its detection range under the water flow velocity in the area; is the mean value of the consistency between the detection range of the i-th sensor in time series and the detection range under the water flow velocity in its area; is the maximum value of the consistency between the detection range of the i-th sensor in time sequence and the detection range at the water flow velocity in its area; is the variance of the consistency between the detection range of the i-th sensor in time series and its detection range under the water flow velocity in the area.

[0073] Among them, through It indicates the overall level of consistency of the sensor in terms of timing. The larger the value, the greater the stability of the sensor in this area. It shows the stability of the sensor's consistency at different times. The smaller it is, the smaller the fluctuation of the sensor is, that is, the greater the stability is.

[0074] c. Distance adjustment and core sensor selection in DBSCAN clustering algorithm.

[0075] When deploying sensors, for the area to be detected, a saturated layout is initially performed and the stability of each sensor is obtained through the above calculation. Since the monitoring range of the sensor is larger than the initial layout distance, the deployed sensors need to be disassembled, and the sensors that exist in the monitoring range of other sensors need to be removed to reduce waste in the sensor layout. However, since the stability of each sensor during detection is different, it is necessary to adjust the stability of each sensor to perform selective removal of the sensors.

[0076] When clustering the sensors in each area to be detected by density using the DBSCAN clustering algorithm, the sensors are evenly distributed during layout and cannot be clustered using the DBSCAN clustering algorithm. Therefore, it is necessary to adjust the stability of each sensor calculated above. For two sensors with high stability, the distance between them needs to be shortened, while the distance between two unstable areas should be increased. The adjusted virtual distance between any two sensors is:

[0077]

[0078] in, is the adjusted virtual distance between the i-th sensor and the j-th sensor; is the actual distance between the i-th sensor and the j-th sensor; is the mean value of stability in the current area to be detected, and They represent the stability of the consistency between the detection range of the i-th sensor and the j-th sensor and the detection range under the water flow velocity in their area.

[0079] pass Adjust the actual distance. By increasing the distance between sensors with large stability differences within the region, unstable sensors can be prevented from being mistakenly clustered into the same cluster during clustering. The greater the difference, the farther the virtual distance between them will be adjusted. This is because sensors with large differences in stability may be affected by different degrees of environmental interference, so their greater separation should be considered when clustering.

[0080] The obtained virtual distance is used as a parameter for clustering using the DBSCAN clustering algorithm to obtain several clusters. The cluster center in each cluster is used as the core sensor in the area represented by the cluster.

[0081] step : Removal of sensors and deployment of sensors in other areas.

[0082] For each area to be detected, the core sensor of each sensor in the area is retained, and the remaining sensors are removed to achieve the final dynamic deployment of sensors in the area to be detected. The above steps are repeated in other subsequent areas to be detected with the removed sensors, so that sensors are deployed in each area to be detected.

[0083] The embodiments of the present invention rationally optimize the placement and number of sensors, avoiding blind spots and overlapping areas found in traditional monitoring methods, thereby ensuring comprehensive coverage of all levels and regions of the water environment. At the same time, by dynamically adjusting the sensor configuration, deployment and maintenance costs are reduced, and resource waste is avoided. By accurately monitoring water quality within aquaculture areas, water quality anomalies can be promptly detected and addressed, improving aquaculture efficiency, ensuring the health and production benefits of farmed animals, supporting the digital and intelligent development of the aquaculture industry, and promoting its development towards a more efficient and sustainable direction.

[0084] By intelligently adjusting the placement and number of sensors, the present invention avoids the blind spots and overlapping areas that occur in traditional methods, ensuring comprehensive monitoring of all water layers and distinct areas within an aquaculture area. Compared to existing technologies, the present invention's dynamic adjustment of sensor placement effectively reduces sensor deployment and maintenance costs, avoiding resource waste.

[0085] Based on the same inventive concept as the above method embodiment, the embodiment of the present invention also provides a water monitoring device for an aquaculture area, such as Figure 3 As shown, there are N categories of sensors, each category of sensors includes several sensors; and all sensors are initially deployed in the area to be detected according to the monitoring range of their respective categories in still water.

[0086] The online monitoring device according to the embodiment of the present invention includes:

[0087] The core sensor determination unit is configured to define some sensors of the nth category as nth core sensors by analyzing the monitoring data of all sensors of the nth category in the detection area within a preset period of time.

[0088] Sensor position resetting unit: used to remove the remaining n-th category sensors except the n-th core sensor in the area to be detected; and traverse all N categories of sensors in all areas to be detected in the aquaculture area to complete the layout of the sensors.

[0089] Online monitoring unit: Online monitoring of the water environment is performed through all rearranged sensors; where nϵ[1,N].

[0090] In another possible embodiment, the core sensor determination unit specifically includes:

[0091] Standard value determination unit: used for calculating the nth standard value of the monitoring range of the nth category sensor at different flow rates.

[0092] Stability determination unit: used to calculate the stability of the consistency between the detection range of each n-th category sensor in the area to be detected and the detection range under the water flow velocity in the area based on the monitoring data and the n-th standard value.

[0093] The virtual adjustment unit is used to virtually adjust the distance between n-th category sensors in the detection area according to stability; and select an n-th core sensor from the plurality of n-th category sensors after the virtual adjustment.

[0094] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0095] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for monitoring water bodies in an aquaculture area, characterized in that: The sensors in the aquaculture area are of N categories, and a plurality of sensors of each category are arranged; the method comprises: Step 1: evenly distributing a plurality of sensors of the nth category in the area to be detected based on the monitoring range of the sensors of the nth category in still water; Step 2: defining some of the n-th category sensors as n-th core sensors by analyzing the monitoring data of all n-th category sensors in the area to be detected within a preset period of time; Step 3: Remove the remaining n-th category sensors except the n-th core sensor in the detection area; Step 4: Traverse all N types of sensors in all areas to be detected in the aquaculture area to complete the sensor deployment; and perform online monitoring of the water environment through all the re-deployed sensors; Among them, nϵ[1,N], n and N are both natural numbers; Defining some of the n-category sensors as n-th core sensors by analyzing monitoring data of all n-category sensors in the area to be detected within a preset time period, specifically comprising: calculating an n-th standard value of the monitoring range of the n-category sensors at different flow rates; calculating the stability of consistency between the detection range of each n-category sensor in the area to be detected and the detection range at the water flow rate in the area based on the monitoring data and the n-standard value; virtually adjusting the distance between the n-category sensors in the area to be detected based on the stability; and selecting the n-th core sensor from the plurality of n-category sensors after the virtually adjusted distance. The nth core sensor is selected from the plurality of nth category sensors after virtual adjustment, specifically comprising: clustering all nth category sensors according to the virtual distances between all nth category sensors to obtain a plurality of cluster families; and using the nth category sensor located at the center of the cluster family as the nth core sensor.

2. The water body monitoring method for aquaculture areas according to claim 1, characterized in that: Calculating an nth standard value of the monitoring range of the nth type sensor at different flow rates; specifically comprising: Obtaining a plurality of clusters of n-type sensors by clustering the detection data and water flow velocity of the n-type sensor in the area to be detected, and the detection data and water flow velocity of the n-type sensor in historical data of other areas to be detected; Obtaining a monitoring range of each n-category sensor based on an analysis of the number of clusters of each n-category sensor with other n-category sensors in the horizontal direction in the area to be detected; According to the monitoring range of each n-th type of sensor in the area to be detected and the water flow velocity at the location where each n-th type of sensor belongs, the n-th standard value of the monitoring range of the n-th type of sensor at different flow velocities is determined.

3. The water body monitoring method for aquaculture areas according to claim 2, characterized in that: Calculate the stability of the consistency between the detection range of each n-th category sensor and the detection range under the water flow velocity in its area; Specifically include: According to the detection range of the ith nth category sensor at different flow velocities at time, the consistency of the detection range of the ith nth category sensor in time and the detection range at the flow velocity in the area is determined; According to the consistency between the detection range of the ith nth category sensor in time series and the detection range under the regional water flow velocity, the mean value of the consistency between the detection range of the ith nth category sensor in time series and the detection range under the regional water flow velocity, the maximum value of the consistency between the detection range of the ith nth category sensor in time series and the detection range under the regional water flow velocity, and the variance value of the consistency between the detection range of the ith nth category sensor in time series and the detection range under the regional water flow velocity are obtained; The stability of the consistency between the detection range of the i-th n-th sensor in time series and its detection range at the regional water flow velocity is obtained based on the mean value of the consistency between the detection range of the i-th n-th sensor in time series and its detection range at the regional water flow velocity, the maximum value of the consistency between the detection range of the i-th n-th sensor in time series and its detection range at the regional water flow velocity, and the variance value of the consistency between the detection range of the i-th n-th sensor in time series and its detection range at the regional water flow velocity; Traversing each n-th category sensor in the area to be detected, obtaining the stability of the consistency between the detection range of each n-th category sensor and the detection range under the water flow velocity in the area; Wherein, i is a natural number.

4. The water body monitoring method for aquaculture areas according to claim 3, characterized in that: According to the detection range of the ith nth category sensor at different flow velocities at time points in the time sequence, the consistency of the detection range of the ith nth category sensor in the time sequence and the detection range at the flow velocity in the area thereof is determined; specifically, the following steps are performed: Obtain the monitoring range of the nth category sensor in the area to be detected and the water flow velocity at its location in real time; Obtaining consistency between the monitoring range of the ith n-th category sensor at the flow velocity at time t and the n-th standard value based on the maximum monitoring range of the n-th category sensor, the minimum monitoring range of the n-th category sensor, the monitoring range of the ith n-th category sensor at time t, and the n-th standard value of the monitoring range corresponding to the water flow velocity of the n-th category sensor at time t, where t is a natural number; All moments in the time series are traversed to obtain the consistency between the detection range of the i-th and n-th category sensors in the time series and the detection range at the water flow velocity in the area.

5. The water body monitoring method for aquaculture areas according to claim 1, characterized in that: According to the stability, a virtual adjustment is performed on the distance between the n-th category sensors; specifically comprising: Determine a virtual distance between the ith nth sensor and the jth nth sensor according to the actual distance between the ith nth sensor and the jth nth sensor, the average value of the stability in the to-be-detected area, the stability of the consistency between the detection range of the ith nth sensor and the detection range at the water flow velocity in the area, and the stability of the consistency between the detection range of the jth nth sensor and the detection range at the water flow velocity in the area; Traversing all sensors of the nth category, and performing virtual adjustments on all sensors of the nth category according to virtual distances between the sensors of the nth category; Where i is a natural number, j is a natural number, and i≠j.

6. The method for monitoring water bodies in an aquaculture area according to any one of claims 1 to 5, characterized in that: Evenly distributing a plurality of sensors of the nth category in the area to be detected; specifically comprising: The n-th category sensors are evenly arranged on monitoring rods, and the monitoring rods are evenly arranged in the water environment of the area to be detected.

7. A water monitoring device for an aquaculture area, characterized in that: The system includes N categories of sensors, each category of sensors includes a plurality of sensors; and all sensors are initially arranged in the area to be detected according to the monitoring range of their respective categories in still water; and further includes: A core sensor determination unit is configured to define some n-category sensors as n-th core sensors by analyzing monitoring data of all n-category sensors in the area to be detected within a preset time period. The core sensor determination unit specifically includes: a standard value determination unit is configured to calculate an n-th standard value of the monitoring range of the n-category sensor at different flow rates; a stability determination unit is configured to calculate the stability of consistency between the detection range of each n-category sensor in the area to be detected and the detection range at the water flow rate in the area based on the monitoring data and the n-th standard value; a virtual adjustment unit is configured to virtually adjust the distance between the n-category sensors in the area to be detected based on the stability; and select the n-th core sensor from the plurality of n-category sensors after the virtual adjustment. and selecting the nth core sensor from the plurality of nth category sensors after virtual adjustment, specifically comprising: clustering all nth category sensors according to virtual distances between all nth category sensors to obtain a plurality of cluster groups; and selecting the nth category sensor located at the center of the cluster group as the nth core sensor; A sensor position resetting unit is used to remove the remaining n-th category sensors except the n-th core sensor in the area to be detected; and traverse all N types of sensors in all areas to be detected in the aquaculture area to complete the sensor layout; Online monitoring unit: conducts online monitoring of the water environment through all rearranged sensors; Among them, nϵ[1,N], n and N are all natural numbers.

Images