CN114698573B - Fish health degree detection method and system based on flexible bending sensor - Google Patents
Fish health degree detection method and system based on flexible bending sensor Download PDFInfo
- Publication number
- CN114698573B CN114698573B CN202210350042.2A CN202210350042A CN114698573B CN 114698573 B CN114698573 B CN 114698573B CN 202210350042 A CN202210350042 A CN 202210350042A CN 114698573 B CN114698573 B CN 114698573B
- Authority
- CN
- China
- Prior art keywords
- fish
- bending angle
- fish body
- current
- detected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005452 bending Methods 0.000 title claims abstract description 219
- 238000001514 detection method Methods 0.000 title claims abstract description 104
- 230000036541 health Effects 0.000 title claims abstract description 90
- 241000251468 Actinopterygii Species 0.000 claims abstract description 477
- 230000009182 swimming Effects 0.000 claims abstract description 50
- 238000000034 method Methods 0.000 claims abstract description 28
- 239000000463 material Substances 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 7
- 238000011897 real-time detection Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 239000006185 dispersion Substances 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003862 health status Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000001953 sensory effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000010146 3D printing Methods 0.000 description 1
- 206010021143 Hypoxia Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 210000000436 anus Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 210000002816 gill Anatomy 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000000016 photochemical curing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000002791 soaking Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K61/00—Culture of aquatic animals
- A01K61/10—Culture of aquatic animals of fish
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K29/00—Other apparatus for animal husbandry
- A01K29/005—Monitoring or measuring activity, e.g. detecting heat or mating
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/02—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/22—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring angles or tapers; for testing the alignment of axes
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Biophysics (AREA)
- Marine Sciences & Fisheries (AREA)
- Zoology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a method and a system for detecting health degree of fish based on a flexible bending sensor, belonging to the field of fish activity detection, and the method for detecting the health degree of fish comprises the following steps: obtaining the bending angles of a fish body detection sensor and a fish tail detection sensor at the current moment to obtain the current fish body bending angle and the current fish tail bending angle; the fish body detection sensor is arranged at the fish body position of the fish to be detected, and the fish tail detection sensor is arranged at the fish tail position of the fish to be detected; determining the current swimming amplitude of the fish to be detected according to the current fish body bending angle and the current fish tail bending angle; and determining the health index of the fish to be detected at the current moment according to the current swimming amplitude, thereby realizing the automatic real-time detection of the health degree of the fish.
Description
Technical Field
The invention relates to the field of fish activity detection, in particular to a method and a system for detecting health degree of fish based on a flexible bending sensor.
Background
In the process of fish culture, sudden conditions such as diseases, oxygen deficiency and the like often occur, and even death of the fish can be caused in severe cases. The methods generally adopted in the prior art are sensory evaluation, and the methods comprise the steps of judging whether the fish is active, whether the surface is injured, whether gills of the fish are bright red, whether eyeballs are full, whether anus is contracted and the like. However, the method of sensory analysis requires strong expertise and practice, and ordinary people have no way to make judgments based on these methods for health of fish. In summary, because the fish health management system is not perfect, there is no good method for detecting the health degree of fish at present. There is therefore a need for a scientific and effective method for the effective assessment of the health status of fish.
Disclosure of Invention
The invention aims to provide a method and a system for detecting the health degree of fish based on a flexible bending sensor, which can automatically detect the health degree of fish.
In order to achieve the purpose, the invention provides the following scheme:
a fish health degree detection method based on a flexible bending sensor comprises the following steps:
obtaining the bending angles of a fish body detection sensor and a fish tail detection sensor at the current moment to obtain the current fish body bending angle and the current fish tail bending angle; the fish body detection sensor is arranged at the position of the fish body of the fish to be detected, and the fish tail detection sensor is arranged at the position of the fish tail of the fish to be detected;
determining the current swimming amplitude of the fish to be detected according to the current fish body bending angle and the current fish tail bending angle;
determining the health index of the fish to be detected at the current moment according to the current swimming amplitude; the health degree of the fish to be detected.
Optionally, the fish body detection sensor and the fish tail detection sensor are both flexible bending sensors.
Optionally, the method for detecting health degree of fish based on flexible bending sensor further comprises:
in a set time period, obtaining bending angles of two fish body sensors and two fish tail sensors to obtain a first fish body bending angle set, a second fish body bending angle set, a first fish tail bending angle set and a second fish tail bending angle set; the two fish body sensors are respectively arranged on two sides of the fish body of the fish to be detected, and the two fish tail sensors are respectively arranged on two sides of the fish tail of the fish to be detected;
determining an optimal bending angle set of the fish body according to the first fish body bending angle set and the second fish body bending angle set; the position of the fish body sensor corresponding to the optimal bending angle set of the fish body is the optimal position of the fish body; the fish body detection sensor is arranged at the optimal position of the fish body of the fish to be detected;
determining an optimal fishtail bending angle set according to the first fishtail bending angle set and the second fishtail bending angle set; the position of the fishtail sensor corresponding to the fishtail optimal bending angle set is the fishtail optimal position; the fish tail detection sensor is arranged at the optimal position of the fish tail of the fish to be detected.
Optionally, the determining an optimal bending angle set of the fish body according to the first fish body bending angle set and the second fish body bending angle set specifically includes:
respectively calculating the mean value and the variance of the data in the first fish body bending angle set and the second fish body bending angle set;
and taking the fish body bending angle set with the maximum mean value and/or the minimum variance as the optimal fish body bending angle set.
Optionally, the determining, according to the current fish body bending angle and the current fish tail bending angle, the current swimming range of the fish to be detected specifically includes:
randomly extracting n times of data from the optimal bending angle set of the fish body, and calculating the average value of the extracted n times of data to obtain a first average value;
randomly extracting n times of data from the optimal bending angle set of the fishtail, and calculating the average value of the extracted n times of data to obtain a second average value;
and determining the current swimming amplitude of the fish to be detected according to the first average value, the second average value, the current fish body bending angle and the current fish tail bending angle.
Optionally, determining the current swimming amplitude of the fish to be detected according to the following formula:
wherein theta is the current swimming amplitude of the fish to be detected, alpha is the current fish body bending angle, beta is the current fish tail bending angle, and alpha is averandom Is firstAverage value, beta arerandom Is the second average value.
Optionally, determining the health index of the fish to be detected at the current moment according to the following formula:
F＝l+kθ+qt；
wherein F is the health index of the fish to be detected at the current moment, l is an environment angle coefficient, k is an angle coefficient, theta is the swimming amplitude, q is a temperature coefficient, and t is the environment temperature of the fish to be detected in the swimming state.
In order to achieve the above purpose, the invention also provides the following scheme:
a flexible bend sensor based fish health detection system comprising: a fish body detection sensor, a fish tail detection sensor and a main controller;
the fish body detection sensor is arranged at the position of the fish body of the fish to be detected; the fish tail detection sensor is arranged at the position of the fish tail of the fish to be detected; when the fish to be detected swims, the fish body detection sensor and the fish tail detection sensor are bent;
the main controller includes:
the data acquisition unit is respectively connected with the fish body detection sensor and the fish tail detection sensor and is used for acquiring the bending angles of the fish body detection sensor and the fish tail detection sensor at the current moment to obtain the current fish body bending angle and the current fish tail bending angle;
the moving amplitude determining unit is connected with the data acquisition unit and is used for determining the current moving amplitude of the fish to be detected according to the current fish body bending angle and the current fish tail bending angle;
the health degree determining unit is connected with the swimming amplitude determining unit and used for determining the health index of the fish to be detected at the current moment according to the current swimming amplitude; the health degree of the fish to be detected.
Optionally, the flexible bending sensor based fish health detection system further comprises a main controller housing; the main controller is arranged in the main controller shell; the main controller shell is triangular.
Optionally, the material of the main control housing is a light-cured material.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: determining the current fish body bending angle and the current fish tail bending angle by detecting the bending angles of a fish body detection sensor of the fish body part and a fish tail detection sensor of the fish tail part; the current swimming amplitude of the fish to be detected is determined according to the current fish body bending angle and the current fish tail bending angle, and the health index of the fish to be detected for detecting the fish is determined according to the current swimming amplitude, so that the health degree of the fish is automatically detected in real time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a method for detecting health degree of fish based on a flexible bending sensor according to the present invention;
FIG. 2 is a schematic structural diagram of a fish health detection system based on a flexible bending sensor according to the present invention;
FIG. 3 is a schematic view of the installation position of the sensor;
FIG. 4 is a schematic view of a sensor bending angle;
FIG. 5 is a schematic view of a sensor housing and a main controller housing;
FIG. 6 is a schematic view of the structure of the cultivation system;
FIG. 7 is a diagram of the overall structure of the health detection of fish according to the present invention.
Description of the symbols:
the system comprises a fish body detection sensor-1, a fish tail detection sensor-2, a main controller-3, a data acquisition unit-31, a swimming amplitude determination unit-32, a health degree determination unit-33, a sensor shell-4, a main controller shell-5, a culture system-6, a liquid crystal display screen-7, a receiving controller-8 and a support rod-9.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a method and a system for detecting health degree of fish based on a flexible bending sensor, which determine the current bending angle of a fish body and the current bending angle of a fish tail by detecting the bending angles of a fish body detection sensor of the fish body part and a fish tail detection sensor of the fish tail part; the current swimming amplitude of the fish to be detected is determined according to the current fish body bending angle and the current fish tail bending angle, the health condition of the fish to be detected for detecting the fish is determined according to the current swimming amplitude, and the automatic real-time detection of the health degree of the fish is realized.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in fig. 1, the method for detecting health degree of fish based on flexible bending sensor of the present invention comprises:
s1: and obtaining the bending angles of the fish body detection sensor and the fish tail detection sensor at the current moment to obtain the current fish body bending angle and the current fish tail bending angle. The fish body detection sensor is arranged at the position of the fish body of the fish to be detected, and the fish tail detection sensor is arranged at the position of the fish tail of the fish to be detected. In this embodiment, the fish body detection sensor and the fish tail detection sensor are both flexible bending sensors, and are packaged in a waterproof manner and are carried out underwater for a long time. The fish body detection sensor and the fish tail detection sensor are both mounted along the axial direction of the fish to be detected, so that the sensors can be guaranteed to bend along with the swinging of the fish.
S2: and determining the current swimming amplitude of the fish to be detected according to the current fish body bending angle and the current fish tail bending angle.
S3: and determining the health index of the fish to be detected at the current moment according to the current swimming amplitude. Specifically, the health index of the fish to be detected at the current moment is determined according to the following formula:
F＝l+kθ+qt；
wherein F is the health index of the fish to be detected at the current moment, l is an environment angle coefficient, k is an angle coefficient, theta is the swimming amplitude, q is a temperature coefficient, and t is the environment temperature of the fish to be detected in the swimming state.
In this embodiment, the fish to be detected is any fish. A higher health index indicates a healthier fish.
In order to improve the accuracy of detecting the health degree of the fish, the method for detecting the health degree of the fish based on the flexible bending sensor further comprises the following steps:
s101: in a set time period, the bending angles of the two fish body sensors and the two fish tail sensors are obtained, and a first fish body bending angle set, a second fish body bending angle set, a first fish tail bending angle set and a second fish tail bending angle set are obtained. The two fish body sensors are respectively arranged on two sides of the fish body of the fish to be detected, and the two fish tail sensors are respectively arranged on two sides of the fish tail of the fish to be detected. Preferably, both fish body sensors and both fish tail sensors are bending sensors.
S102: and determining the optimal bending angle set of the fish body according to the first fish body bending angle set and the second fish body bending angle set. And the position of the fish body sensor corresponding to the optimal bending angle set of the fish body is the optimal position of the fish body. The fish body detection sensor is arranged at the optimal position of the fish body of the fish to be detected. Specifically, the mean and variance of the data in the first fish body bending angle set and the second fish body bending angle set are calculated respectively. And taking the fish body bending angle set with the maximum mean value and/or the minimum variance as the optimal fish body bending angle set.
S103: and determining the optimal bending angle set of the fishtail according to the first fishtail bending angle set and the second fishtail bending angle set. And the position of the fishtail sensor corresponding to the fishtail optimal bending angle set is the fishtail optimal position. The fish tail detection sensor is arranged at the optimal position of the fish tail of the fish to be detected. The specific determination method of the optimal bending angle set of the fishtail is the same as that of the optimal bending angle set of the fish body, and is not described herein again.
Therefore, the fish body detecting sensor and the fish body detecting sensor may be disposed on the same side of the fish to be detected, or may be disposed on both sides of the fish to be detected. In addition, the fish body detection sensor can directly adopt the first fish body sensor or the second fish body sensor, and also can set up the fish body detection sensor at the optimum position of the fish body again, and the setting mode of fish tail detection sensor is the same as the setting mode of fish body detection sensor, and is not repeated here. Through installing fish tail detection sensor and fish body detection sensor in optimal position, improved fish tail bending angle and fish body bending angle's accuracy, and then improved the precision that the healthy degree of fish detected.
Specifically, the mounting position, the observed value, and the mean value of the fishtail sensor are as shown in table 1:
TABLE 1
Wherein (beta) 11 ,β 12 …β 1n ) Is the first fishtail bending angle set (beta) 21 ,β 22 …β 2n ) Is a second fishtail bending angle set and n is the time.
The mounting position, observed value and mean value of the fish body sensor are shown in table 2:
TABLE 2
Wherein (alpha) 11 ,α 12 …α 1n ) Is a first fish body bending angle set (alpha) 21 ,α 22 …α 2n ) Is the second fish body bending angle set, and n is the time.
In the test, one hundred samples were taken, but the invention is not limited to one fish and the number of samples. But is applicable to data of various fishes, and the number of samples is selected according to the actual experimental conditions.
Specifically, when the optimal position of the fish body and the optimal position of the fish tail are selected, two basic principles are used:
(1) In order to obtain a better data to ensure the accuracy of the final performance evaluation, the sensor position corresponding to the bending angle set with the maximum mean value is selected as the optimal position in the bending angle sets at different positions. Namely that
When the fish moves, if the data obtained by the sensor is small, the large error is easy to occur in data analysis, so that the error is generated in the judgment of the health condition, the judgment accuracy rate is reduced, the error rate is improved, and the position with the maximum mean value is selected as the optimal position.
(2) And when the mean values of the bending angle sets are close, selecting the sensor position corresponding to the bending angle set with smaller variance as the optimal position. Namely, it is
S m 2 ＝nin{S 1 2 ,S 2 2 M =1 or 2;
wherein the content of the first and second substances,
the variance directly reflects the fluctuation degree of data in the bending angle set, and when the variance is too large, the fluctuation degree of the data in the bending angle set is relatively large, which indicates that the data result at the position is not very stable, so that the bending angle set with the smaller variance needs to be selected.
Thereby obtaining the optimal bending angle set (alpha) of the fish body 1 ,α 2 …α n ) I.e. the optimal bending angle set (beta) of the fish tail 1 ,β 2 …β n )：
α 1 ,α 2 …α n ＝Best{α 11 ,α 12 …α 1n ,α 21 ,α 22 …α 2n }；
β 1 ,β 2 …β n ＝Best{β 11 ,β 12 …β 1n ,β 21 ,β 22 …β 2n }。
Further, step S2 specifically includes:
s21: randomly extracting n times of data from the optimal bending angle set of the fish body, and calculating the average value of the extracted n times of data to obtain a first average value.
S22: and randomly extracting n times of data from the optimal fishtail bending angle set, and calculating the average value of the extracted n times of data to obtain a second average value.
S23: and determining the current swimming amplitude of the fish to be detected according to the first average value, the second average value, the current fish body bending angle and the current fish tail bending angle. Specifically, the current swimming amplitude of the fish to be detected is determined according to the following formula:
wherein theta is the current swimming amplitude of the fish to be detected, alpha is the current fish body bending angle, beta is the current fish tail bending angle, and alpha is averandom Is a first mean value, beta averandom Is the second average.
Since two values are obtained: the current fish body bending angle α and the current fish tail bending angle β also mean that two independent variables appear in the calculation process, which adversely affects the subsequent calculation: the more independent variables, the greater the precision influence on the subsequent data, which directly influences the precision of the walking amplitude. But also causes the subsequent calculation process to be more complicated, thereby affecting the speed and efficiency of calculation. Therefore, it is necessary to reduce two arguments to one argument to facilitate subsequent calculations.
The specific calculation method of the current walk amplitude is as follows:
assuming θ = a α + b β, where a and b are unknown coefficients, the final objective of the invention is to combine the walk-away amplitude with the health index, and the rationale is the translation of the walk-away amplitude at each position to its effective amplitude, then a sum of weights equal to 1, i.e. a + b =1, and the two relations are combined to give the formula: θ = a (α - β) + β. The relation between a and b needs to be determined from the optimal bending angle set of the fish body and the optimal bending angle set of the fish tail, which are shown in table 3:
TABLE 3
| Mounting location | Observed value (Angle) |
| Fish body sensor | α 1 ,α 2 …α n |
| Fish tail sensor | β 1 ,β 2 …β n |
In order to reduce the data amount, reduce errors and improve the precision, data are randomly extracted 10 times from the optimal bending angle sets 1 to n and the random is obtainedAveraging the extracted data to obtain a first average value alpha ave random And a second average value beta ave random . Order to
Since the weight is mainly based on the magnitude of the walking amplitude, then: />
Additionally a + b =1, i.e. a->
Thus, the effective current walk-around amplitude is finally obtained:
in step S3, when determining the relationship between the health index and the swimming range, it is assumed that a linear relationship exists between the swimming range θ and the ambient temperature t of the fish to be detected in the swimming state. Obtaining c fish, measuring the angle of the fish under the free swimming condition at different temperatures, wherein the different temperatures are t 1, t 2 ,t 3, …t c The different swimming angles are respectively theta 1, θ 2 ,θ 3, …θ c I.e. a sample of c fish is currently obtained, based on the c fish sample value (t) j ,θ j ；F j ) (j =1,2,3 … c) calculating least square estimation quantities of environment angle coefficient l, angle coefficient k and temperature coefficient q
Thus, the final regression equation is obtained: />
Wherein it is present>
Is an empirical regression equation, the concrete solution is as follows:
wherein G (l, k, q) is a non-inverse quadratic form, which ensures that the multivariate function is a sufficient condition for the existence of an extremum, i.e., the quadratic form has a minimum value, k is a minimum value k And q is j Is t j ,θ j The corresponding coefficients.
In order to obtain the minimum of the quadratic form, assume that
When a quadratic form has a minimum, and for determining->
The first partial derivative of l, k, q in G (l, k, q) is required to be equal to 0:
the linear equation system about l, k and q is obtained after the arrangement:
after the processing, a positive solution equation set of an environment angle coefficient l, an angle coefficient k and a temperature coefficient q is obtained, and a solution set of the equation set is
For the sake of easy differentiation, call->
For l, k, q least squares estimates, it is apparent from the first set of equations that +>
Wherein +>
Will be provided with
Integrating with the above formula, the following equation is finally obtained:
in order to avoid too complicated calculation for obtaining sample data and error, each summation formula needs to be converted necessarily. The conversion process is as follows:
the converted formula is of the form:
the equation is a linear equation set of two-dimensional equations, and the least square estimation value of k and q is obtained after the equation set is solved
At this time only->
Is unknown, will be known->
Is substituted into the formula->
Finally, a regression equation of the temperature, the walk amplitude and the health index can be obtained: />
After the relationship between the swimming amplitude and the health index is determined, the significance test of the regression effect is needed to ensure that the swimming amplitude and the health condition under a certain temperature condition have a regression relationship, and further ensure that the obtained health index has practical significance.
Specifically, when a regression relationship exists between the walk amplitude and the health condition under a certain temperature condition, three unknown coefficients are mainly used, and whether a linear relationship exists between the data is determined under the three unknown coefficients:
in order to find out whether the problem is significant or not, the problem needs to be converted into whether all the environmental angle coefficients l, k and q are 0 or not, if all the coefficients are 0, the linear relation is proved to be insignificant, and if not all the coefficients are 0, the relation is proved to be significant.
For significance testing, hypothesis H was proposed 0 : l = k = q =0, remember
Where j =1,2,3 … c.
The variance sum of squares of the data is decomposed:
wherein S is Total The sum of the squares of the total deviations reflects the volatility and dispersion of the health status of the fish in the sample data, S SE Is the residual sum of squares, which mainly reflects the influence of the swimming amplitude on the dispersion degree of the health condition by the residual factors except the linear influence factors, S Regression Is a regression sum of squares, mainly reflecting the magnitude of the walk theta 1, θ 2, θ 3, …θ c By changing of
And a running amplitude theta 1, θ 2, θ 3, …θ c The linear relationship of (a) has an effect on busyness.
Due to the fact that
Where χ () is the chi-square distribution, g is the number of variables, g =2, i.e. </>, i.e. </or>
And S SE And S Regression Are independent of each other. And secondly->
And S SE And (k, q) are independent of each other, where c is the number of independent samples.
From the above, it can be seen that when H 0 : l = k = q =0 isWhen the real time is true, the user can select the specific time,
f is used to check when H is 0 : l = k = q =0 is a hypothesis statistic when true. When H is present 0 When it is true, and F is greater, H should be rejected 0 Namely:
P F {F≥F 1-α (g,c-g-1)}＝α
in this case, if F ≧ F 1-α (g, c-g-1, then there is a significant linear correlation between health and independent variable temperature and the magnitude of the wandering.
If F is less than or equal to F 1-α (g, c-g-1) indicates that the linear relationship between the health condition and the independent variable temperature and the swimming range is not obvious, namely that the linear relationship does not exist between the health condition and the independent variable temperature.
Through experimental exploration, when the fish swim in water, the body swing amplitude and frequency have a close relation with the activity condition of the fish, and the health index calculated according to the formula F = l + ktheta + qt is obtained accurately.
As shown in fig. 2 and 3, the fish health detecting system based on the flexible bending sensor of the present invention includes: fish body detection sensor 1, fish tail detection sensor 2 and main controller 3.
Wherein, the fish body detection sensor 1 is arranged at the fish body position of the fish to be detected. The fishtail detection sensor 2 is arranged at the position of the fishtail of the fish to be detected. When the fish to be detected moves, the fish body detection sensor 1 and the fish tail detection sensor 2 are bent. In this embodiment, the fish body detecting sensor 1 and the fish tail detecting sensor 2 are both flexible bending sensors. The fish body detection sensor 1 and the fish tail detection sensor 2 are adhered to the fish body and the fish tail by using special glue, and after adhesion, the fish body detection sensor 1 and the fish tail detection sensor 2 are in contact with the fish scales, so that the surface of the fish body is not damaged. The fish body detection sensor 1 and the fish tail detection sensor 2 are about 0.2 multiplied by 4cm in size, soft in texture and free from influencing the normal swimming of fish.
The optimal position of the fish body is about the middle part of the fish body, and the optimal position of the fish tail is about the middle part of the fish tail.
The main controller 3 includes: a data acquisition unit 31, a walking amplitude determination unit 32 and a health degree determination unit 33.
The data acquisition unit 31 is respectively connected with the fish body detection sensor 1 and the fish tail detection sensor 2, and the data acquisition unit 31 is used for acquiring the bending angles of the fish body detection sensor 1 and the fish tail detection sensor 2 at the current moment to obtain the current fish body bending angle and the current fish tail bending angle. Specifically, as shown in fig. 4, when the fish to be detected is not moving, the fish body detecting sensor 1 and the fish tail detecting sensor 2 are 180 ° flat, and are not bent and do not respond. When the fish moves, the fish body detecting sensor 1 and the fish tail detecting sensor 2 are bent, the fish body detecting sensor 1 and the fish tail detecting sensor 2 generate a response, the response is an analog signal, and the data acquisition unit 31 converts the analog signals of the bending of the fish body detecting sensor 1 and the fish tail detecting sensor 2 into digital signals to obtain the current fish body bending angle and the current fish tail bending angle.
The moving amplitude determining unit 32 is connected to the data collecting unit 31, and the moving amplitude determining unit 32 is configured to determine the current moving amplitude of the fish to be detected according to the current fish body bending angle and the current fish tail bending angle.
The health degree determining unit 33 is connected to the swimming amplitude determining unit 32, and the health degree determining unit 33 is configured to determine a health index of the fish to be detected at the current time according to the current swimming amplitude.
In order to improve the accuracy of fish health degree detection, the fish health degree detection system based on the flexible bending sensor further comprises two fish body sensors and two fish tail sensors. The two fish body sensors are respectively arranged on two sides of the fish body of the fish to be detected, and the two fish tail sensors are respectively arranged on two sides of the fish tail of the fish to be detected.
The main controller 3 further includes: the device comprises a bending angle set determining unit, a fish body optimal position determining unit and a fish tail optimal position determining unit.
The bending angle set determining unit is respectively connected with the two fishtail sensors and the two fish body sensors. The bending angle set determining unit is used for acquiring bending angles of the two fish body sensors and the two fish tail sensors in a set time period to obtain a first fish body bending angle set, a second fish body bending angle set, a first fish tail bending angle set and a second fish tail bending angle set.
The fish body optimal position determining unit is connected with the bending angle set determining unit and used for determining the optimal bending angle set of the fish body according to the first fish body bending angle set and the second fish body bending angle set. And the position of the fish body sensor corresponding to the optimal bending angle set of the fish body is the optimal position of the fish body. The fish body detection sensor is arranged at the optimal position of the fish body of the fish to be detected.
The fishtail optimal position determining unit is connected with the bending angle set determining unit and used for determining the fishtail optimal bending angle set according to the first fishtail bending angle set and the second fishtail bending angle set. And the position of the fishtail sensor corresponding to the fishtail optimal bending angle set is the fishtail optimal position. The fish tail detection sensor is arranged at the optimal position of the fish tail of the fish to be detected.
In addition, the main controller 3 is also used for transmitting the current swimming amplitude of the fish to be detected and the health index of the current moment to the remote end app through 5G long-distance transmission. No matter where the breeder is, the health condition of the fish can be monitored in real time, so that unhealthy conditions can be conveniently operated
As shown in fig. 5, in order to avoid the main controller 3 increasing the resistance of the fish when swimming, the fish health detection system based on the flexible bending sensor of the present invention further comprises a main controller housing 5. The main controller 3 is arranged in the main controller shell 5; the main controller housing 5 is triangular. Design into triangle-shaped with main control unit shell 5, reduced weight on the one hand, on the other hand has also guaranteed to reduce the resistance of water after installing detecting system in the fish body or fish tail to guarantee not to influence the free swimming of fish.
The fish health detection system based on the flexible bending sensor of the invention further comprises a sensor housing 4. The fish body detection sensor 1 and the fish tail detection sensor 2 are both arranged in the sensor shell 4. Sensor housing 4 adopts professional waterproof material, can not influence the effect or cause the damage because of soaking for a long time in aqueous.
In addition, in order to ensure the waterproof performance of the fish health degree detection system, the main controller shell 5 and the sensor shell 4 are both prepared by 3D printing with a photocuring material.
The invention can also acquire data of a plurality of sensors through 5G communication, which means that a plurality of fishes can be monitored for health at the same time, and the working efficiency of the fish health degree detection system is ensured.
In addition, the fish health degree detection system based on the flexible bending sensor further comprises: a transmitting module, a receiving controller 8 and a liquid crystal display screen 7. The transmitting module is respectively connected to the moving amplitude determining unit 32, the health degree determining unit 33 and the receiving controller 8, and the transmitting module is configured to send the current moving amplitude of the fish to be detected and the health index of the current moment to the receiving controller 8. The receiving controller 8 is connected with the liquid crystal display 7, and the receiving controller 8 is used for sending the current swimming amplitude of the fish to be detected and the health index of the current moment to the liquid crystal display 7 for displaying. As shown in fig. 6, the lcd screen 7 and the receiving controller 8 are disposed on the cultivation system 6, and the cultivation system 6 is fixed by a support rod 9.
Fig. 7 is an overall architecture diagram of the system and method for detecting health level of fish based on flexible bending sensor according to the present invention, showing the overall process of detecting health level of fish according to the present invention.
Compared with the prior art, the fish health degree detection system based on the flexible bending sensor has the same beneficial effects as the fish health degree detection method based on the flexible bending sensor, and the detailed description is omitted.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principle and the embodiment of the present invention are explained by applying specific examples, and the above description of the embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (7)
1. A fish health degree detection method based on a flexible bending sensor is characterized by comprising the following steps:
in a set time period, obtaining bending angles of two fish body sensors and two fish tail sensors to obtain a first fish body bending angle set, a second fish body bending angle set, a first fish tail bending angle set and a second fish tail bending angle set; the two fish body sensors are respectively arranged on two sides of the fish body of the fish to be detected, and the two fish tail sensors are respectively arranged on two sides of the fish tail of the fish to be detected;
determining an optimal bending angle set of the fish body according to the first fish body bending angle set and the second fish body bending angle set; the position of the fish body sensor corresponding to the optimal bending angle set of the fish body is the optimal position of the fish body; the fish body detection sensor is arranged at the optimal position of the fish body of the fish to be detected;
determining an optimal fishtail bending angle set according to the first fishtail bending angle set and the second fishtail bending angle set; the position of the fishtail sensor corresponding to the fishtail optimal bending angle set is the fishtail optimal position; the fish tail detection sensor is arranged at the optimal position of the fish tail of the fish to be detected;
obtaining the bending angles of a fish body detection sensor and a fish tail detection sensor at the current moment to obtain the current fish body bending angle and the current fish tail bending angle; the fish body detection sensor is arranged at the position of the fish body of the fish to be detected, and the fish tail detection sensor is arranged at the position of the fish tail of the fish to be detected;
determining the current swimming amplitude of the fish to be detected according to the current fish body bending angle and the current fish tail bending angle, and specifically comprising:
randomly extracting n times of data from the optimal bending angle set of the fish body, and calculating the average value of the extracted n times of data to obtain a first average value;
randomly extracting n times of data from the optimal bending angle set of the fishtail, and calculating the average value of the extracted n times of data to obtain a second average value;
according to the first average value, the second average value, the current fish body bending angle, the current fish tail bending angle and a formula
Determining the current swimming amplitude of the fish to be detected; wherein theta is the current swimming amplitude of the fish to be detected, alpha is the current fish body bending angle, beta is the current fish tail bending angle, and alpha is averandom Is a first mean value, beta averandom Is a second average value;
determining the health index of the fish to be detected at the current moment according to the current swimming amplitude; the health index characterizes the health degree of the fish to be detected.
2. The method for detecting health degree of fish based on flexible bending sensor as claimed in claim 1, wherein the fish body detecting sensor and the fish tail detecting sensor are both flexible bending sensors.
3. The method for detecting health degree of fish based on flexible bending sensor according to claim 1, wherein determining the optimal bending angle set of the fish body according to the first bending angle set and the second bending angle set of the fish body comprises:
respectively calculating the mean value and the variance of the data in the first fish body bending angle set and the second fish body bending angle set;
and taking the fish body bending angle set with the maximum mean value and/or the minimum variance as the optimal fish body bending angle set.
4. The method for detecting the health degree of fish based on the flexible bending sensor as claimed in claim 1, wherein the health index of the fish to be detected at the current moment is determined according to the following formula:
F＝l+kθ+qt；
wherein F is the health index of the fish to be detected at the current moment, l is an environmental angle coefficient, k is an angle coefficient, theta is the swimming amplitude, q is a temperature coefficient, and t is the environmental temperature of the fish to be detected in the swimming state.
5. A flexible bending sensor-based fish health detection system, comprising: the fish body detection sensor, the fish tail detection sensor, the main controller, the two fish body sensors and the two fish tail sensors;
the fish body detection sensor is arranged at the position of the fish body of the fish to be detected; the fish tail detection sensor is arranged at the position of the fish tail of the fish to be detected; when the fish to be detected swims, the fish body detection sensor and the fish tail detection sensor are bent;
the two fish body sensors are respectively arranged on two sides of the fish body of the fish to be detected, and the two fish tail sensors are respectively arranged on two sides of the fish tail of the fish to be detected;
the main controller includes:
the bending angle set determining unit is respectively connected with the two fish tail sensors and the two fish body sensors and is used for acquiring bending angles of the two fish body sensors and the two fish tail sensors in a set time period to obtain a first fish body bending angle set, a second fish body bending angle set, a first fish tail bending angle set and a second fish tail bending angle set;
the fish body optimal position determining unit is connected with the bending angle set determining unit and used for determining a fish body optimal bending angle set according to the first fish body bending angle set and the second fish body bending angle set; the position of the fish body sensor corresponding to the optimal bending angle set of the fish body is the optimal position of the fish body; the fish body detection sensor is arranged at the optimal position of the fish body of the fish to be detected;
the fishtail optimal position determining unit is connected with the bending angle set determining unit and used for determining a fishtail optimal bending angle set according to the first fishtail bending angle set and the second fishtail bending angle set; the position of the fishtail sensor corresponding to the fishtail optimal bending angle set is the fishtail optimal position; the fish tail detection sensor is arranged at the optimal position of the fish tail of the fish to be detected;
the data acquisition unit is respectively connected with the fish body detection sensor and the fish tail detection sensor and is used for acquiring the bending angles of the fish body detection sensor and the fish tail detection sensor at the current moment to obtain the current fish body bending angle and the current fish tail bending angle;
the moving amplitude determining unit is connected with the data acquisition unit and used for determining the current moving amplitude of the fish to be detected according to the current fish body bending angle and the current fish tail bending angle, and the moving amplitude determining unit specifically comprises: randomly extracting n times of data from the optimal bending angle set of the fish body, and calculating the average value of the extracted n times of data to obtain a first average value; randomly extracting n times of data from the optimal bending angle set of the fishtail, and calculating the average value of the extracted n times of data to obtain a second average value; according to the first average value, the second average value, the current fish body bending angle, the current fish tail bending angle and a formula
Determining the current swimming amplitude of the fish to be detected; wherein theta is the current swimming amplitude of the fish to be detected, alpha is the current fish body bending angle, beta is the current fish tail bending angle, and alpha is averandom Is a first mean value, beta averandom Is a second average value;
the health degree determining unit is connected with the swimming amplitude determining unit and used for determining the health index of the fish to be detected at the current moment according to the current swimming amplitude; the health index characterizes the health degree of the fish to be detected.
6. The flexible bend sensor based fish health detection system of claim 5, further comprising a main controller housing; the main controller is arranged in the main controller shell; the main controller shell is triangular; the side of the main controller is triangular.
7. The flexible bend sensor based fish health detection system of claim 6 wherein the material of the main controller housing is a light cured material.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210350042.2A CN114698573B (en) | 2022-04-02 | 2022-04-02 | Fish health degree detection method and system based on flexible bending sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210350042.2A CN114698573B (en) | 2022-04-02 | 2022-04-02 | Fish health degree detection method and system based on flexible bending sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114698573A CN114698573A (en) | 2022-07-05 |
| CN114698573B true CN114698573B (en) | 2023-04-11 |
Family
ID=82172286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210350042.2A Active CN114698573B (en) | 2022-04-02 | 2022-04-02 | Fish health degree detection method and system based on flexible bending sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114698573B (en) |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1480300A (en) * | 2003-07-09 | 2004-03-10 | 中国科学技术大学 | Pisciform biomimetic robot |
| CN102297767A (en) * | 2011-05-13 | 2011-12-28 | 东南大学 | Health monitoring method of rope system based on angle monitoring when support displaces angularly |
| CN203315746U (en) * | 2013-05-27 | 2013-12-04 | 创首科技（深圳）有限公司 | Electromechanical automatic control fishtailing mechanical fish |
| CN107047423A (en) * | 2017-04-28 | 2017-08-18 | 全椒县鮰鱼养殖专业合作社 | It is a kind of that feeding amount Channel-catfish fish culture systems are adjusted based on weight detecting |
| CN107101944A (en) * | 2017-05-22 | 2017-08-29 | 饶伊珂 | A kind of fish type water quality detecting device |
| CN108058799B (en) * | 2017-11-30 | 2023-08-29 | 浙江工业大学 | Novel bionic mechanical fish |
| US10534967B2 (en) * | 2018-05-03 | 2020-01-14 | X Development Llc | Fish measurement station keeping |
| CN111610733A (en) * | 2020-04-29 | 2020-09-01 | 合肥工业大学 | Fishing ground culture monitoring system and method based on machine fish |
| CN112931311B (en) * | 2021-02-09 | 2022-11-11 | 上海海洋大学 | Flounder health condition evaluation method |
| CN113598131B (en) * | 2021-07-24 | 2022-12-13 | 浙江中兴慧农信息科技有限公司 | Interior lake farming systems based on big data block chain |
-
2022
- 2022-04-02 CN CN202210350042.2A patent/CN114698573B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114698573A (en) | 2022-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ropert-Coudert et al. | Trends and perspectives in animal‐attached remote sensing | |
| CN103444613B (en) | Feeding control system and method for fish culture | |
| Cagua et al. | Topography and biological noise determine acoustic detectability on coral reefs | |
| CN105066885A (en) | Fish body dimension and weight rapid acquisition apparatus and acquisition method | |
| Morand et al. | Feeding and metabolism of the jellyfish Pelagia noctiluca (scyphomedusae, semaeostomae) | |
| AU2007207932B2 (en) | A method of determining the effect of a spill on a marine environment | |
| RU120766U1 (en) | Sonar meter | |
| Robert-Coudert et al. | Subjectivity in bio-logging: do logged data mislead? | |
| CN114218864A (en) | Net cage netting damage detection method and device based on mathematics twinning and storage medium | |
| NO20210919A1 (en) | Systems and methods for predicting growth of a population of organisms | |
| CN114698573B (en) | Fish health degree detection method and system based on flexible bending sensor | |
| CN206821749U (en) | A kind of neritic plankton adopts collecting net equipment | |
| CN114018317B (en) | Data acquisition device and method for marine environment | |
| CN214748140U (en) | Deep sea culture monitoring system | |
| RU2437093C1 (en) | System for rapid biological monitoring and indication | |
| CN1723772A (en) | Automatic on-line monitoring device for external factor of cage culture | |
| Medley et al. | A stock assessment for the conch (Strombus gigas L.) fishery in the Turks and Caicos Islands | |
| CN108805779A (en) | Marine environment real-time monitoring system based on underwater robot | |
| Cattet et al. | To weigh or not to weigh: conditions for the estimation of body mass by morphometry | |
| Ouréns et al. | Definition of a new unbiased gonad index for aquatic invertebrates and fish: its application to the sea urchin Paracentrotus lividus | |
| RU101838U1 (en) | AUTONOMOUS SYSTEM OF OPERATIONAL BIOLOGICAL MONITORING AND INDICATION (OPTIONS) | |
| KR102409745B1 (en) | Fish feed factor automatic measurement device for fish farms | |
| CN108132194B (en) | Remote wireless monitoring and sensing device for corrosion risk of steel bar in concrete | |
| CN1702438A (en) | Corn mass flow sensor | |
| Hsu | The length–weight relationship of Albacore, Thunnus alalunga, from the Indian Ocean |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |