Bait casting ship path optimization method based on blue crab growth model

Abstract

The invention discloses a bait casting ship path optimization method based on a blue crab growth model. The bait casting ship path optimization method comprises the following steps: step 1, establishing a dynamic blue crab growth model; 2, calculating the feeding amount, wherein the total feeding amount is calculated according to the growth stage of the blue crabs; step 3, carrying out zoning and weight distribution on the breeding area: dividing the area based on the blue crab distribution density, and distributing differentiated feeding weights; 4, planning a path of a bait casting boat: planning an optimal path meeting the bait casting amount of each region by taking constant boat speed as a constraint; according to the method, the error 1t is dynamically corrected in combination with a growth model, environmental factors and the feeding amount; 5%. The bait waste rate is reduced by 40% or above through regional weight distribution, accurate feeding is achieved, residual bait deposition is effectively reduced, and the water quality pollution risk is reduced.

Description

Technical Field

[0001] The present invention belongs to the field of aquaculture, and relates to a method for optimizing the path of a feeding boat based on a mud crab growth model. Background Art

[0002] Traditional feeding boats mostly adopt the "uniform sowing" method, without considering the distribution density, growth stage and environmental differences of mud crabs, resulting in waste of bait (about 30%-50%), water pollution and increased breeding costs. Existing path planning methods (such as the shortest path algorithm) are not combined with the dynamic allocation of feeding amount and cannot meet the needs of precise feeding. Summary of the Invention

[0003] In order to overcome at least one of the deficiencies of the prior art, the present invention provides a method for optimizing the path of a feeding boat based on a mud crab growth model.

[0004] To achieve the above object, the present invention adopts the following technical solutions: A method for optimizing the path of a feeding boat based on a mud crab growth model, comprising the following steps:

[0005] Step 1: Establish a dynamic growth model of mud crabs;

[0006] Step 2: Calculate the feeding amount: Calculate the total feeding amount according to the growth stage of mud crabs;

[0007] Step 3: Divide the breeding area and allocate weights: Divide the area based on the distribution density of mud crabs and allocate different feeding weights;

[0008] Step 4: Plan the path of the feeding boat: Plan the optimal path that meets the feeding amount of each area with the constraint of constant ship speed.

[0009] Further, the dynamic growth total mass prediction model of mud crabs:

[0010] M(t) = A × ρ × S(t) × W(t)

[0011] A: The area of the breeding area (unit: m 2 )), A is a known parameter;

[0012] ρ: Breeding density (unit: number / m 2 ), ρ is a known parameter;

[0013] S(t): The survival rate of the mud crab population on the t-th day;

[0014] W(t): The average individual weight on the t-th day;

[0015] M(t): The total mass of mud crabs in the breeding area on the t-th day.

[0016] Further, the function of the survival rate S(t) is:

[0017]

[0018] S max : Initial survival rate;

[0019] S min : Final survival rate;

[0020] r: Survival rate decline rate;

[0021] t mid : Time point when the survival rate drops to the intermediate value;

[0022] According to the actual aquaculture data, sampling was completed for the survival rate investigation of mud crabs, and S min , S max , r, t mid parameters were obtained to get the survival rate curve function.

[0023] Furthermore, based on the environmental factor correction growth model, let the instantaneous change rate of the average individual weight W(t) with respect to time t

[0024]

[0025] W max : Theoretical maximum weight, which is a set value;

[0026] α: Basic growth rate coefficient, which is a constant;

[0027] E(t): Environmental factor influence coefficient.

[0028] Furthermore, the formula for the said E(t) is as follows:

[0029] E(t) = E T (t) × E DO (t) × E pH (t)

[0030] E T (t) is the temperature influence factor, E O (t) is the dissolved oxygen influence factor, E pH (t) is the pH value influence factor, and the value range of each factor is [0, 1], where 1 represents the best environment,

[0031] 0 represents complete growth inhibition;

[0032] ①E T (t): Temperature influence factor, and the formula is as follows:

[0033]

[0034] Among them, T is the current water temperature, and the T parameter is detected in real time by a sensor. T min is the lowest survival water temperature, and T max is the highest survival water temperature, and T opt is the most suitable survival water temperature. According to actual aquaculture data, the survival rates of mud crabs at different water temperatures are investigated by sampling to obtain the T min , T max , and T opt parameters.

[0035] ②E O (t): Dissolved oxygen impact factor, and the formula is as follows:

[0036]

[0037] Among them, O crit is the critical dissolved oxygen concentration, k O is the dissolved oxygen sensitivity, O(t) is the current dissolved oxygen concentration, and the O(t) parameter is detected in real time by a sensor; according to actual aquaculture data, the survival rates of mud crabs at different dissolved oxygen concentrations are investigated by sampling to obtain the O crit parameter; in the model, the k O parameter can be simplified to a constant and obtained through experiments.

[0038] ③E pH (t): pH value impact factor, adopting a parabolic response, and the formula is as follows:

[0039]

[0040] Among them, pH opt is the optimal pH value, ΔpH is the tolerance range radius, pH(t) is the current pH value, and the pH(t) parameter is detected in real time by a sensor; according to actual aquaculture data, the survival rates of mud crabs at different pH values are investigated by sampling to obtain the pH opt parameter; in the model, the ΔpH parameter is simplified to a constant and can be obtained through experiments and curve fitting. Further, the formula for the feeding amount is as follows:

[0041] Q(t) = M(t) × f(t)

[0042] Q(t): The total feeding amount on the t-th day;

[0043] f(t): Feeding rate at the growth stage, and the empirical feeding amount is obtained according to the feeding rates of mud crabs at different growth stages.

[0044] Furthermore, the step 3 includes the following steps:

[0045] Step 31: The breeding area is divided into m areas in length and n areas in width, that is, the breeding area is divided into m×n areas. The area to be fed is set as the (i, j) area, where 1≤i≤m and 1≤j≤n;

[0046] Step 32: Construct a mud crab distribution density matrix D, D = [d ij m×n ;

[0047] d ij : The distribution density of the (i, j) area (number / m 2 ), and density data is obtained through an underwater camera or sampling;

[0048] Step 33: Calculate the density ratio ω ij ;

[0049]

[0050] ω ij : The ratio of the distribution density of the area to be fed to the distribution density of the breeding area;

[0051] Step 34: Calculate the feeding amount Q ij ;

[0052] Q ij = Q(t)×ω ij .

[0053] Furthermore, step 4 includes the following steps:

[0054] Step 41: Perform a priority ranking according to the feeding amount Q ij of each area obtained in step 3;

[0055] Step 42: Determine the starting point and the arrival point of the feeding boat, and use the A * algorithm to plan the optimal path.

[0056] Furthermore, the feeding boat includes a controller and a feeding device, a driving mechanism, a vision device, a positioning device, a communication module, and a collection device connected to the controller;

[0057] The controller is built-in with a growth model and a feeding amount calculation algorithm, generates a regional feeding amount distribution table based on the growth model, and performs path planning and execution;

[0058] The collection device includes several sensor integrations with different functions. The sensor integration includes a temperature sensor, a PH sensor, and a dissolved oxygen sensor, and is used to monitor the water temperature, dissolved oxygen, and pH value in real time;

[0059] ​A vision device, a drone or an underwater camera, obtains the distribution density of mud crabs through the drone or the underwater camera.

[0060] The positioning device is set as GPS. The baiting boat is equipped with GPS and a controller, sails along an optimized path and dynamically adjusts the baiting rate.

[0061] The baiting device feeds bait under the control of the controller.

[0062] The driving mechanism drives or shuts down the baiting boat under the control of the controller.

[0063] In summary, the advantages of the present invention are as follows:

[0064] 1) The present invention combines a growth model and environmental factors, and the dynamic correction error of the baiting amount is <5%. The regional weight distribution reduces the bait waste rate by more than 40%, realizes precise feeding, effectively reduces the deposition of residual bait, and reduces the risk of water quality pollution.

[0065] 2) The intelligent path optimization of the present invention improves the efficiency by 30% compared with the traditional shortest path, and supports dynamic weight adjustment.

[0066] 3) The present invention can be applied to ponds of different scales, and the model parameters can be quickly calibrated through historical data, having the advantage of universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a flow chart of the path planning of the present invention.

[0068] Figure 2 It is a modular schematic diagram of the baiting boat of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0069] The following specific examples illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0070] It should be noted that the drawings provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the components related to the present invention are shown in the drawings, rather than being drawn according to the number, shape and size of the components in actual implementation. The types, quantities and proportions of the components in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0071] In the embodiments of the present invention, all directional indications (such as up, down, left, right, front, back, horizontal, vertical...) are only used to explain the relative positional relationship, movement conditions, etc. between components in a specific posture. If the specific posture changes, the directional indications will also change accordingly.

[0072] Due to installation errors and other reasons, the parallel relationship referred to in the embodiments of the present invention may actually be an approximate parallel relationship, and the perpendicular relationship may actually be an approximate perpendicular relationship.

[0073] Embodiment 1:

[0074] As Figure 1 - Figure 2 shown, a method for optimizing the path of a bait-feeding boat based on the growth model of mud crabs includes the following steps:

[0075] Step 1: Establish a dynamic growth model of mud crabs;

[0076] Dynamic growth total mass prediction model of mud crabs:

[0077] M(t) = A × ρ × S(t) × W(t)

[0078] A: Area of the breeding area (unit: m 2 ), A is a known parameter;

[0079] ρ: Breeding density (unit: individuals / m 2 ), ρ is a known parameter;

[0080] S(t): Survival rate of the mud crab population on the t-th day;

[0081] W(t): Average individual weight on the t-th day;

[0082] M(t): Total mass of mud crabs in the breeding area on the t-th day;

[0083] Assume that the survival rate decreases over time and finally stabilizes. The function of the survival rate S(t) is set as:

[0084]

[0085] S max : Initial survival rate (when the seedlings are just put in, the survival rate is close to the maximum value);

[0086] S min : Final survival rate (when captured, the survival rate is close to the minimum value);

[0087] r: Rate of decrease in the survival rate;

[0088] t mid : Time point when the survival rate drops to the intermediate value;

[0089] According to the actual aquaculture data, the survival rate of mud crabs was investigated by sampling, and S was fitted by non - linear regression. min , S max , t, t mid and other parameters, and finally the survival rate curve function was obtained.

[0090] Since water temperature, dissolved oxygen, etc. in the aquaculture area have a great impact on mud crab aquaculture, it is necessary to correct the growth model through environmental factors. The instantaneous change rate of the average individual weight W(t) with respect to time t. This equation shows that the individual growth rate slows down as time increases. The specific formula is as follows:

[0091]

[0092] W max : The theoretical maximum weight, which is a set value;

[0093] α: The basic growth rate coefficient, which is a constant;

[0094] E(t): The environmental factor influence coefficient;

[0095] E(t)=E T (t)×E DO (t)×E pH (t)

[0096] E T (t) is the temperature influence factor, E O (t) is the dissolved oxygen influence factor, E pH (t) is the pH value influence factor. The value range of each factor is [0, 1], where 1 represents the best environment and 0 represents complete growth inhibition.

[0097] ①E T (t): The temperature influence factor, and the formula is as follows:

[0098]

[0099] Among them, T is the current water temperature, T min is the lowest survival water temperature, T max is the highest survival water temperature, T opt is the most suitable survival water temperature. According to the actual aquaculture data, the survival rate of mud crabs at different water temperatures was investigated by sampling, and T min , T max , T opt parameters were obtained, and the T parameters were detected in real - time by sensors.

[0100] ②E O (t): The dissolved oxygen influence factor, and the formula is as follows:

[0101]

[0102] Among them, O crit is the critical dissolved oxygen concentration, k O is the dissolved oxygen sensitivity, O(t) is the current dissolved oxygen concentration, and the O(t) parameter is detected in real time by a sensor; according to the actual aquaculture data, the survival rate of mud crabs at different dissolved oxygen concentrations is sampled and investigated to obtain the O crit parameter; in the model, the k O parameter can be simplified to a constant, that is, it is considered that the sensitivity of mud crabs to dissolved oxygen remains unchanged during the entire aquaculture cycle, and it can be obtained specifically through experimental methods. For example, multiple dissolved oxygen levels are set, mud crabs are cultured under constant temperature and stable pH conditions, and the growth rates at different dissolved oxygen levels are recorded, and then the k O parameter is obtained through curve fitting.

[0103] ③ E pH (t): The pH value influence factor, which adopts a parabolic response, and the formula is as follows:

[0104]

[0105] Among them, pH opt is the optimal pH value, ΔpH is the radius of the tolerance range, pH(t) is the current pH value, and the pH(t) parameter is detected in real time by a sensor; according to the actual aquaculture data, the survival rate of mud crabs at different pH values is sampled and investigated to obtain the pH opt parameter; in the model, the ΔpH parameter is simplified to a constant, that is, it is considered that the pH tolerance of mud crabs remains unchanged during the entire aquaculture cycle, and the ΔpH parameter can be obtained through experiments and curve fitting. Assuming that the optimal pH value is 7.5 and the radius of the tolerance range is 1.5, it is considered that the required pH tolerance range for mud crabs is 6 to 9.0. When the above limit is exceeded, the generation completely stops.

[0106] The instantaneous change rate of the average individual weight W(t) with respect to time t can be solved by the Euler method:

[0107]

[0108] Δt: The time interval;

[0109] W(t + Δt): The average individual weight at the (t + Δt)-th day;

[0110] The Euler method is an explicit time integration method used to approximately solve ordinary differential equations. By discretizing the time step, the differential equation is converted into a recurrence formula. The weight at the next moment t + Δt is predicted through the weight W(t) at the current moment t and the instantaneous change rate .

[0111] Step 2: Calculate the amount of feed: Calculate the total amount of feed based on the growth stage;

[0112] The formula for feeding amount is as follows:

[0113] Q(t)=M(t)×f(t)

[0114] Q(t): total feeding amount on day t;

[0115] f(t): Feeding rate during growth phase. This is an empirically calculated feed rate based on the feeding rates for different growth stages of blue crabs. This can be found in aquaculture manuals, for example, a 5% to 8% feeding rate for juvenile crabs and a 3% to 5% feeding rate for growing crabs. Alternatively, the feeding rate can be determined experimentally as the ratio of daily feed intake to body weight.

[0116] Step 3: Zoning and weighting of the breeding area: Divide the area based on the distribution density of blue crabs and assign differentiated feeding weights;

[0117] Step 31: The aquaculture area is divided into m areas in length and n areas in width, that is, the aquaculture area is divided into m×n areas, and the area to be fed is set as the (i, j)th area, 1≤i≤m, 1≤j≤n;

[0118] Step 32: Construct the blue crab distribution density matrix D, D = [d ij ] m×n

[0119] d ij : Distribution density of the (i,j) region (units / m 2 ), density data can be obtained by underwater cameras or sampling;

[0120] Step 33: Calculate the density ratio ω of the area to be baited ij ;

[0121]

[0122] ω ij : The ratio of the distribution density of the area to be fed to the distribution density of the breeding area;

[0123] Step 34: Calculate the amount of bait Q in the area to be fed ij ;

[0124] Q ij =Q(t)×ω ij

[0125] Step 4: Plan the path of the baiting boat: With the boat speed constrained to be constant, plan the optimal path that meets the baiting amount in each area;

[0126] Step 41: The amount of bait Q in each area obtained in step 3 ijSort by size for priority;

[0127] Step 42: Determine the starting point and the arrival point of the bait boat, A * The algorithm plans the optimal path;

[0128] For path planning within the area, a breadth-first search combined with a priority queue algorithm is used to find the optimal path that covers all obstacle-free grids and has the fewest number of turns.

[0129] The following is the method for path optimization within the area:

[0130] Abstract the grids of each area to be planned into a two-dimensional array, where 0 represents obstacle-free and 1 represents an obstacle, and the above-mentioned list sequence of area abstraction can be obtained.

[0131] First, define a group of initialized priority queues. This queue consists of several groups of key-value pairs. The key is the serial number, and the value contains information on the number of turns (n), coordinate position information (x, y), direction information (up, down, left, right), access mask information (a bit mask records the grids that have been visited, and each bit corresponds to a grid), and the current path sequence. Since the goal is to start from the starting point, traverse all obstacle-free points, and have the fewest number of turns in the path, the above priority queue is sorted by the number of turns to ensure that the sequence with fewer turns is always at the front of the queue, that is, the state with fewer turns is preferentially expanded to gradually approach the optimal solution. When finding the path, take out the key-value pair from the front of the queue and try to move in four directions. If the new position after moving is legal and has not been visited, update the visited mask and calculate the number of turns in the new direction. Push the new state into the queue to avoid duplicate states (duplicate removal through a set). When the visited mask of a certain state covers all obstacle-free grids, the path is the optimal solution.

[0132] This application also provides a bait boat, which includes a controller and a baiting device, a driving mechanism, a vision device, a positioning device, a communication module, and a collection device connected to the controller.

[0133] The controller has a built-in growth model and a bait amount calculation algorithm, generates a regional bait amount distribution table based on the growth model, and performs path planning and execution;

[0134] The collection device includes several sensor integrations with different functions. The sensor integration includes a temperature sensor, a PH sensor, and a dissolved oxygen sensor, which are used to monitor water temperature, dissolved oxygen, and pH value in real time;

[0135] The vision device and a drone or an underwater camera are used to obtain the distribution density of mud crabs through the drone or the underwater camera.

[0136] The positioning device is set as GPS. The bait boat is equipped with GPS and a controller, sails according to the optimized path, and dynamically adjusts the baiting rate;

[0137] The feeding device feeds bait under the control of the controller;

[0138] The driving mechanism drives or shuts down the bait-feeding boat under the control of the controller.

[0139] Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts shall fall within the protection scope of the present invention.

Claims

1. A method for optimizing the path of a bait boat based on a mud crab growth model, characterized in that: It includes the following steps: Step 1: Establish a dynamic growth model for mud crabs; Step 2: Calculate the amount of feed: Calculate the total amount of feed according to the growth stage of mud crabs; Step 3: Divide the breeding area and allocate weights: Divide the area based on the distribution density of mud crabs and allocate differential feeding weights; Step 4: Plan the path of the feeding boat: With a constant ship speed as a constraint, plan the optimal path to meet the feeding amount in each area.

2. The method for optimizing the path of a bait boat based on the mud crab growth model according to claim 1, wherein: The total mass prediction model of the dynamic growth of mud crabs: M(t) = A × ρ × S(t) × W(t) A: Area of the aquaculture area (unit: m 2 ), where A is a known parameter; ρ: Breeding density (unit: number / m 2 ), ρ is a known parameter; S(t): The survival rate of the mud crab population on the t-th day; W(t): The average individual weight on the t-th day; M(t): The total mass of mud crabs in the breeding area on the t-th day.

3. The path optimization method of a bait-feeding boat based on the mud crab growth model according to claim 2, wherein: The function of the survival rate S(t) is: S max : Initial survival rate; S min : Final survival rate; r: The decline rate of the survival rate; t mid : The time point when the survival rate drops to the median value; According to the actual aquaculture data, sampling was completed for the survival rate survey of mud crabs, and S was fitted by non-linear regression min , S max , r, t mid parameters to obtain the survival rate curve function.

4. The method for optimizing the path of a bait feeding boat based on the mud crab growth model according to claim 2, wherein: Based on the environmental factor corrected growth model, assuming that the instantaneous change rate of the average individual weight W(t) with respect to time t W max : Theoretical maximum weight, which is a set value; α: The basic growth rate coefficient, which is a constant; E(t): The environmental factor influence coefficient.

5. The path optimization method of a bait-feeding boat based on the mud crab growth model according to claim 4, characterized in that: The formula of E(t) is as follows: E(t) = E T (t) × E DO (t) × E pH (t) E T (t) is the temperature influence factor, E O (t) is the dissolved oxygen influence factor, E pH (t) is the pH value influence factor, and the value range of each factor is [0, 1]. 1 indicates the best environment, and 0 indicates complete growth inhibition; ①E T (t): Temperature influence factor, and the formula is as follows: Among them, T is the current water temperature, and the T parameter is detected in real time by a sensor, T min is the lowest survival water temperature, T max is the highest survival water temperature, T opt is the most suitable survival water temperature. According to the actual aquaculture data, the survival rates of mud crabs at different water temperatures are investigated by sampling to obtain T min , T max , T opt parameters. ②E O (t): Dissolved oxygen influence factor, and the formula is as follows: Among them, O crit is the critical dissolved oxygen concentration, k O is the dissolved oxygen sensitivity, O(t) is the current dissolved oxygen concentration, and the O(t) parameter is detected in real time by a sensor; according to the actual aquaculture data, the survival rates of mud crabs at different dissolved oxygen concentrations are investigated by sampling to obtain the O crit parameter; in the model, the k O parameter can be simplified to a constant and obtained through experiments. ③E pH (t): pH value influence factor, adopting a parabolic response, and the formula is as follows: Among them, pH opt is the optimal pH value, ΔpH is the radius of the tolerance range, pH(t) is the current pH value, pH(t) Parameters are detected in real time by sensors; according to the actual aquaculture data, sampling is carried out to complete the investigation of the survival rate of mud crabs at different pH values, and the pH opt parameter is obtained; in the model, the ΔpH parameter is simplified to a constant, which can be obtained by experiments and curve fitting.

6. The path optimization method of a bait-feeding boat based on the mud crab growth model according to claim 4, wherein: The formula of the amount of feed is as follows: Q(t) = M(t) × f(t) Q(t): The total amount of feed on the t-th day; f(t): The feeding rate in the growth stage, an empirical feeding amount obtained according to the feeding rates in different growth stages of mud crabs.

7. A method for optimizing the path of a bait boat based on the growth model of mud crabs according to claim 4, characterized in that: Step 3 includes the following steps: Step 31: The breeding area is divided into m areas in length and n areas in width, that is, the breeding area is divided into m×n areas, and the area to be fed is set as the (i,j) area, 1 ≤ i ≤ m, 1 ≤ j ≤ n; Step 32: Construct the mud crab distribution density matrix D, D = [d ij m×n ;​ d ij : Distribution density of the (i, j) area (number / m 2 ), and density data is obtained through an underwater camera or sampling method; Step 33: Calculate the density ratio ω of the area to be fed ij ; ω ij : The ratio of the distribution density of the area to be fed to the distribution density of the aquaculture area; Step 34: Calculate the bait feeding amount Q of the area to be fed ij ; Q ij = Q(t) × ω ij .

8. A method for optimizing the path of a bait boat based on the growth model of mud crabs according to claim 4, characterized in that: Step 4 includes the following steps: Step 41: Perform priority sorting according to the amount of bait Q in each area obtained in Step 3 ij by size; Step 42: Determine the starting point and the arrival point of the bait boat, A * The algorithm plans the optimal path.

9. The method for optimizing the path of a bait boat based on the mud crab growth model according to claim 5, wherein: The feeding boat includes a controller and a feeding device, a driving mechanism, a vision device, a positioning device, a communication module, and a collection device connected to the controller; The controller is built-in with a growth model and a feeding amount calculation algorithm, generates a regional feeding amount allocation table based on the growth model, and performs path planning and execution; The collection device includes several sensor integrations with different functions. The sensor integration includes a temperature sensor, a PH sensor, and a dissolved oxygen sensor, which are used to monitor the water temperature, dissolved oxygen, and pH value in real time; The vision device and a drone or an underwater camera, obtain the distribution density of mud crabs through the drone or the underwater camera; The positioning device is set as GPS. The feeding boat is equipped with GPS and a controller, sails along the optimized path, and dynamically adjusts the feeding rate; The feeding device feeds under the control of the controller; The driving mechanism drives or shuts down the feeding boat under the control of the controller.

Images