Biomimetic fishway fish passage effect evaluation method based on multi-factor analysis

Abstract

The present application relates to the technical field of data processing, in particular to a kind of bionic fishway fish passing effect evaluation method based on multi-factor analysis. Multi-dimensional data of each batch of fish swimming through the test section in each monitoring period, multi-factor evaluation calculation model and engineering parameter are obtained;In each cycle, the theoretical environmental compression rate is calculated using the model according to the water temperature and flow rate sequence;The physical exertion index is determined by comparing the total time consumption with the preset reference time consumption;The effective swimming weight is determined by combining the deviation of the swimming trajectory time sequence change and the engineering parameter, and the invalid time consumption data weight of the backwater rest area is reduced;The long-term evaluation deviation index is determined by fusing the multiple indexes of all batches of fish, and the effective error cycle is screened out;The environmental parameter constraint space is constructed, and the related data of each batch of fish in the effective error cycle are combined to perform traversal optimization, eliminate the data pollution of the rest area, and improve the adaptability and prediction accuracy of the model to different environments and fish populations.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a method for evaluating the fish passage effect of an eco-friendly fishway based on multi-factor analysis. Background Technology

[0002] In water conservancy projects, biomimetic fishways serve as important ecological protection facilities, aiming to provide migratory channels for fish. A fundamental task in the daily operation and management of biomimetic fishways is assessing whether the internal water flow field is suitable for the target fish species to migrate upstream. Existing monitoring systems typically deploy environmental sensors such as water temperature and flow velocity within the fish tank, using this sensor data to calculate the theoretical environmental pressure rate exerted by the current aquatic environment on fish movement.

[0003] However, as naturally cold-blooded aquatic animals, fish exhibit significant fluctuations in their physical characteristics and tolerance to water temperature and flow rate with the natural changing seasons. Therefore, the fixed central parameters within the evaluation calculation model will gradually deviate from the current physiological adaptability of the fish after long-term operation. Existing technologies typically record the total time taken by the fish to pass through the test section and then correct the parameter model. However, low-flow-rate backwater rest areas are usually built on both sides of the fishway, where the fish usually hover and rest. Therefore, correcting the parameter model based solely on the total time will lead to the data being contaminated by the resting behavior of the fish. Ultimately, the environmental assessment model will violate the true physiological laws, greatly reducing its credibility and accuracy. Summary of the Invention

[0004] To address the problem that existing technologies typically use reverse-correction parameter models that record the total time it takes for fish to pass through a test section, but fishways usually have low-flow-rate backwater rest areas on both sides where fish often hover and rest, relying solely on the total time correction parameter model can lead to data contamination due to the fish's resting behavior, this invention aims to provide a multi-factor analysis-based method for evaluating the fish passage effect in an eco-friendly fishway. The specific technical solution adopted is as follows: The total time spent by each batch of fish swimming through the test section, the time sequence of their swimming trajectory, the water temperature sequence, and the flow velocity sequence are obtained for each monitoring period. The multi-factor evaluation calculation model and the engineering parameters of the test section are also obtained. In each monitoring cycle, based on the water temperature and flow velocity sequences corresponding to each batch of fish, the theoretical environmental pressure rate corresponding to each batch of fish is calculated using the multi-factor evaluation calculation model; the physical energy consumption index of each batch of fish is determined by comparing the total time spent by each batch of fish with the preset benchmark time; and the effective swimming weight of each batch of fish in the test section is determined by the deviation of the swimming trajectory time sequence of each batch of fish and in combination with the engineering parameters of the test section. By integrating the theoretical environmental pressure rate, energy consumption index, and effective swimming weight of all batches of fish, a long-term evaluation deviation index is determined, which is used to screen out the effective error period in all monitoring periods. An environmental parameter constraint space is constructed based on the biological constants of fish populations. On this basis, the energy consumption index, effective swimming weight, and water temperature and flow velocity sequences of each batch of fish populations within the effective error period are combined to perform traversal optimization and generate final state environmental evaluation parameters for updating the multi-factor evaluation calculation model.

[0005] Furthermore, the method for obtaining the theoretical environmental pressure rate includes: The multi-factor evaluation calculation model includes a temperature central term, a flow velocity central term, and a tolerance coefficient term; In each monitoring cycle, in the water temperature sequence and flow velocity sequence corresponding to each batch of fish, the water temperature and flow velocity at the same moment are combined to form a data point pair. All data point pairs are input into the Gaussian decay function of the multi-factor evaluation calculation model, and combined with the temperature central term and the flow velocity central term, the instantaneous lag rate corresponding to each data point pair is calculated. The average instantaneous retardation rate of all data point pairs corresponding to each batch of fish is taken as the theoretical environmental pressure rate corresponding to each batch of fish.

[0006] Furthermore, the method for obtaining the physical exertion index includes: The ratio of the total time spent on each batch of fish to the preset baseline time is used as the actual time multiplier for each batch of fish. The difference between the actual time taken for each batch of fish and the preset time is taken as the excess delay multiple, and the ratio of the excess delay multiple to the upper limit of the preset limit multiple is taken as the energy consumption index of each batch of fish.

[0007] Furthermore, the method for obtaining the effective movement weight includes: The engineering parameters include the ideal water flow axis of the test section, the width of the reference tank, and the width of the return water rest area; The deviation between the swimming trajectory time sequence of each batch of fish and the ideal water flow axis is analyzed to determine the deviation of each batch of fish from the main channel. The difference between half the reference channel width of the test section and the width of the backwater rest area is divided by the reference channel width to obtain the lower limit threshold for deformation. The difference between the main channel deviation and the lower limit threshold for deformation is negatively correlated and normalized to obtain the effective swimming weight of each batch of fish swimming through the test section.

[0008] Furthermore, the method for obtaining the main channel deviation includes: The spatial deformation distance between the time sequence of the swimming trajectory of each batch of fish and the ideal water flow axis sequence is calculated by the discrete Fraser algorithm and used as the geometric deformation distance. The ratio of the geometric deformation distance to the reference channel width is used as the main channel deviation of each batch of fish.

[0009] Furthermore, the method for obtaining the evaluation deviation index includes: The absolute value of the difference between the theoretical environmental pressure rate and the physical exertion index corresponding to each batch of fish is used as the individual evaluation error of each batch of fish. The individual evaluation error was weighted and averaged using the effective swimming weights corresponding to all batches of fish, and the result was used as a long-term evaluation deviation index for each monitoring period.

[0010] Furthermore, the method for obtaining the effective error period includes: If the long-term evaluation deviation index of a certain monitoring period is greater than the preset allowable deviation threshold, then the monitoring period is regarded as the effective error period.

[0011] Furthermore, the method for obtaining the final state environmental evaluation parameters includes: The biological constants include the lethal high temperature threshold, the upper limit of the ultimate resistance to flow velocity, the lower limit of the dormant low temperature, and the lower limit of the basic flow velocity. The lower limit of dormancy low temperature and the lethal high temperature threshold are respectively used as two boundary values ​​to obtain the central temperature range to be optimized. The lower limit of basic flow velocity and the upper limit of ultimate flow resistance velocity are respectively used as two boundary values ​​to obtain the central velocity range to be optimized. In the temperature mid-axis range and the flow velocity mid-axis range to be optimized, the temperature mid-axis value and the flow velocity mid-axis value to be optimized are combined in pairs using an exhaustive method, and each pair of combinations is used as the environmental parameter to be measured. In each effective error period, all data point pairs corresponding to each batch of fish are input into the Gaussian decay function of the multi-factor evaluation calculation model, and combined with each set of environmental parameters to be tested, the instantaneous lag rate corresponding to each data point pair is calculated. The mean of the instantaneous retardation rate of all data point pairs corresponding to each batch of fish is used as the new theoretical environmental pressure rate for each batch of fish. The absolute value of the difference between the new theoretical environmental pressure rate and the physical exertion index corresponding to the fish is used as the error factor. The error factor is weighted and fused using the effective swimming weights of all batches of fish, and the accumulated result is used as the candidate value corresponding to each set of environmental parameters to be tested. The mean of the candidate values ​​of each set of environmental parameters under test in all effective error periods is used as the error index. Among all environmental parameters under test, the environmental parameter corresponding to the minimum error index is used as the final state environmental evaluation parameter.

[0012] Furthermore, the updated multi-factor evaluation calculation model includes: The temperature and flow rate midline values ​​in the final environmental evaluation parameters are replaced with the original temperature and flow rate midline terms in the multi-factor evaluation parameter model to obtain the updated evaluation parameter model.

[0013] Furthermore, after updating the multi-factor evaluation calculation model, the method also includes: The latest water temperature and flow velocity sequences from the monitoring period are obtained. The updated evaluation parameter model is used in conjunction with the latest water temperature and flow velocity sequences to calculate the real-time environmental pressure rate of the fish passage effect of the simulated fishway. When the real-time environmental pressure rate exceeds the preset pressure threshold, the environment is considered to be deteriorating and an alarm is required; otherwise, no alarm is required.

[0014] The present invention has the following beneficial effects: First, multidimensional data on each batch of fish swimming through the test section were acquired within each monitoring period. Simultaneously, a multi-factor evaluation calculation model and engineering parameters of the test section were obtained. Within each monitoring period, based on the water temperature and flow velocity sequences corresponding to each batch of fish, the theoretical environmental pressure rate was calculated using the multi-factor evaluation calculation model to accurately quantify the pressure exerted by the water environment resistance on the fish. The total time spent by each batch of fish was compared with a preset baseline time to determine the energy consumption index, quantifying the actual energy consumption of the fish during their swim through the test section. Since time alone cannot distinguish whether the fish were swept away by the current or in the backwater resting area, the effective swimming weight was determined based on the deviation of the swimming trajectory time sequence of each batch of fish, combined with the engineering parameters of the test section. This accurately identifies and significantly reduces the weight of invalid time data in the backwater resting area. Furthermore, multiple indicators corresponding to all batches of fish were integrated to determine the long-term evaluation deviation index, and the effective error periods were selected from all monitoring periods using this index. Finally, an environmental parameter constraint space was constructed based on the biological constants of the fish population to ensure that the subsequent traversal optimization process was carried out within a framework that conformed to the biological characteristics of the fish population. The traversal optimization was carried out by combining the energy consumption index, effective swimming weight, and water temperature and flow velocity sequences of all batches of fish populations within the effective error period. This enabled the evaluation model to be adaptively calibrated according to seasonal changes and eliminated data pollution caused by the rest area, making the model more in line with the actual situation and improving the model's adaptability and prediction accuracy to different environments and fish population states. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 The flowchart illustrates a method for evaluating the fish passage effect of an eco-friendly fishway based on multi-factor analysis, as provided in one embodiment of the present invention. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a multi-factor analysis-based method for evaluating the fish passage effect in an eco-friendly fishway according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, 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 pertains.

[0019] The following description, in conjunction with the accompanying drawings, details a specific scheme for evaluating the fish passage effect of an eco-friendly fishway based on multi-factor analysis, provided by this invention.

[0020] Please see Figure 1 The diagram illustrates a flowchart of a method for evaluating the fish passage effect of an eco-friendly fishway based on multi-factor analysis, according to an embodiment of the present invention. The method includes the following steps: Step S1: Obtain the total time spent by each batch of fish swimming through the test section, the time sequence of their swimming trajectory, the water temperature sequence, and the flow velocity sequence within each monitoring period, and obtain the multi-factor evaluation calculation model and the engineering parameters of the test section.

[0021] First, set the length of the monitoring period, for example, 24 hours. Then, within each monitoring period, use monitoring cameras mounted above the fishway, combined with computer vision target detection algorithms (such as the YOLO series), to identify and lock onto fish entering the test section, and record the time when the heads of each group of fish cross the inlet section of the test section. and the moment when the tail crosses the outlet section of the test section The difference between the two values ​​is taken as the total time spent by each batch of fish. At the same time, the water flow and temperature sensor group deployed in the test section obtains the time at two points ( and The water temperature sequence and flow velocity sequence between (the sampling frequency can be adjusted according to the implementation scenario).

[0022] exist and Video frames were continuously captured at a fixed sampling rate of 30 frames per second, and the two-dimensional pixel coordinates of the centroid of the bounding box of each group of fish were extracted frame by frame. After extracting the two-dimensional pixel coordinates, a homography transformation matrix, pre-calculated through camera calibration, was obtained. This matrix describes the perspective projection relationship between the camera image plane and the two-dimensional world plane of the fishway water surface. Using this matrix, the extracted two-dimensional pixel coordinates were transformed into a two-dimensional world plane coordinate system based on the water surface, yielding the corresponding two-dimensional projection coordinate points. After obtaining all the two-dimensional projection coordinate points, these coordinate points were arranged in chronological order of sampling time to generate a time sequence of the swimming trajectory of each group of fish. This sequence is a set of two-dimensional discrete spatial coordinate points reflecting the true physical scale, recording the two-dimensional horizontal projection path of each group of fish under the scouring of the water flow within the test section.

[0023] Simultaneously, the multi-factor evaluation calculation model and the engineering parameters of the test section are also obtained. In this embodiment of the invention, the engineering parameters of the test section include the ideal water flow axis, the reference tank width, and the width of the return water rest area. The ideal water flow axis is the centerline of the main water flow in the test section. The reference tank width and the width of the return water rest area can be obtained from design drawings, etc. The multi-factor evaluation calculation model adopts a Gaussian decay function form. Its core includes the initial values ​​of the temperature central term, the flow velocity central term, and the tolerance coefficient term. These can be retrieved from biological parameter databases or pre-entered by experts based on laboratory test results of fish populations or ecological literature.

[0024] Step S2: In each monitoring cycle, based on the water temperature and flow velocity sequences corresponding to each batch of fish, the theoretical environmental pressure rate corresponding to each batch of fish is calculated using a multi-factor evaluation calculation model; the total time consumed by each batch of fish is compared with the preset baseline time to determine the energy consumption index of each batch of fish; based on the deviation of the swimming trajectory time sequence of each batch of fish, and in combination with the engineering parameters of the test section, the effective swimming weight of each batch of fish swimming through the test section is determined.

[0025] Water temperature and current velocity are two critical environmental factors affecting fish survival and movement. Water temperature directly impacts fish metabolism, physiological functions, and reproductive activities, while current velocity affects swimming energy consumption, foraging efficiency, and the ability to evade predators. Therefore, by using a multi-factor evaluation calculation model to integrate water temperature and current velocity sequences to calculate the theoretical environmental pressure rate, we can more comprehensively and scientifically assess the living environment of fish and more accurately reflect the environmental pressure they experience throughout their swimming process.

[0026] Preferably, in one embodiment of the present invention, the method for obtaining the theoretical environmental pressure rate includes: As can be seen from step S1, the multi-factor evaluation calculation model includes a temperature central term, a flow velocity central term, and a tolerance coefficient term.

[0027] In each monitoring cycle, in the water temperature and flow velocity sequences corresponding to each batch of fish, the water temperature and flow velocity at the same moment are combined to form a data point pair. All data point pairs are input into the Gaussian decay function of the multi-factor evaluation calculation model, and combined with the temperature central term and the flow velocity central term, the instantaneous lag rate corresponding to each data point pair is calculated.

[0028] Here, the specific form of the Gaussian decay function in the multi-factor evaluation calculation model is given in this embodiment of the invention: ,in, Indicates the first Instantaneous lag rate at a given moment; Indicates the first The water temperature at that moment; Indicates the temperature central term; This represents the tolerance coefficient corresponding to temperature. Indicates the first The flow rate at that moment; Indicates the flow velocity central term; This represents the tolerance coefficient corresponding to the flow velocity; This represents an exponential function with the natural constant e as its base.

[0029] In the above formula model, This characterizes the degree of temperature deviation; the larger the value, the greater the deviation, and the more significant the resistance. Dividing by... Its function is to normalize, which can eliminate the influence of units. The larger the size, the less sensitive the fish population is to temperature changes, and the higher its tolerance; similarly, This characterizes the degree of deviation in flow velocity; the larger the value, the greater the deviation, and the more significant the obstruction. Dividing by... Its function is to normalize, which can eliminate the influence of units. The larger the value, the less sensitive the fish population is to changes in current velocity, and the higher its tolerance. The value ranges from 0 to 1. The closer the value is to 1, the more severe the theoretical pressure resistance of the water environment on the fish during that period. Conversely, the closer the value is to 0, the more suitable the water environment is for the fish to swim upstream during that period.

[0030] Finally, the average instantaneous resistance rate of all data point pairs corresponding to each batch of fish is taken as the theoretical environmental pressure rate for each batch of fish. Based on the above analysis, it can be seen that the larger the theoretical environmental pressure rate, the more severe the theoretical pressure resistance caused to the fish by the current water environment as characterized by objective sensor data during this period.

[0031] It should be noted that in this embodiment of the invention, the tolerance coefficient corresponding to temperature can be set to 3.0, because for common warm-water target fish species (such as the four major freshwater fish), when the actual water temperature deviates from the optimal temperature by 3°C, their single-dimensional environmental suitability will decrease to about 60%. The flow rate is consistent with the physiological tolerance curve of fish at normal temperature. The tolerance coefficient corresponding to the flow rate can be set to 0.3, because fish are quite sensitive to changes in flow rate. When the actual flow rate deviates from the optimal flow rate by 0.3 m / s, their swimming suitability will decrease significantly (decay to about 60%), which is consistent with the common hydrodynamic response characteristics in the mainstream area of ​​the simulated fishway. The values ​​of these two tolerance coefficients can be adjusted according to the implementation scenario and are not limited here.

[0032] The total time spent directly reflects the time it takes for each group of fish to swim through the test section, while the preset baseline time is a set value based on the time required for fish to pass through the section under normal or ideal conditions. By comparing the total time spent by each group of fish with the preset baseline time, the actual energy expenditure of each group of fish can be quantified in the form of specific numerical values.

[0033] Therefore, preferably, in one embodiment of the present invention, the method for obtaining physical fitness indicators includes: The preset baseline time is a set value based on the time required for a school of fish to pass through a specific section under normal or ideal conditions. The ratio of the total time for each batch of fish to the preset baseline time is used as the actual time multiple for each batch of fish. The actual time multiple obtained by the ratio can unify the total time of different batches of fish to a relative scale. The larger the value, the longer the time for that batch of fish.

[0034] In this embodiment of the invention, a preset multiple is set to 1, representing the normal swimming time of the fish according to a preset benchmark. The difference between the actual time multiple of each batch of fish and the preset multiple is then used as the excess delay multiple (in this embodiment, the actual time multiple is considered to be greater than or equal to the preset multiple, so the value of the excess delay multiple is non-negative). The excess delay multiple reflects the extra time spent by the fish during swimming, which may be due to the degree of energy depletion caused by environmental factors. Finally, the ratio of the excess delay multiple to the upper limit of the preset limit multiple is used as an indicator of the energy consumption of each batch of fish. This serves to convert the excess delay multiple to between 0 and 1. The closer it is to 1, the greater the energy consumption of the fish, approaching exhaustion; conversely, the closer it is to 0, the smaller the energy consumption. If the ratio exceeds 1, it is truncated and directly assigned a value of 1.

[0035] It should be noted that if the test section is 10 meters long and the swimming speed of the fish is about 0.5 meters per second, the preset baseline time can be set to 20 seconds; the preset limit multiple is set to 5. Both of the aforementioned values ​​can be adjusted according to the implementation scenario and are not limited here.

[0036] In traditional fishway evaluation, longer swimming time is usually equated with greater resistance or a harsher environment. However, in simulated fishways, there is a significant interfering factor: the backwater rest area. This area provides fish with a place to hover and rest, thus increasing the swimming time. If this situation is not distinguished, it is easy to make a misjudgment. Therefore, in this embodiment of the invention, since the changes in the time sequence of the swimming trajectory of different batches of fish swimming through the test section can intuitively reflect the smoothness and effectiveness of swimming, based on the aforementioned characteristics and combined with the engineering parameters of the test section, an effective swimming weight is determined, which can more accurately measure the proportion of actual effective swimming of each batch of fish in this section.

[0037] Preferably, in one embodiment of the present invention, the method for obtaining the effective floating weight includes: In this embodiment of the invention, the ideal water flow axis, reference tank width, and return water rest area width of the test section are obtained in step S1.

[0038] The Discrete Fraser algorithm can measure the similarity between two curves. In the scenario of fish swimming, the actual swimming trajectory sequence of the fish and the ideal water flow axis sequence of the test section represent the actual swimming path and the expected optimal swimming path of the fish, respectively. Therefore, the spatial deformation distance between the swimming trajectory sequence of each batch of fish and the ideal water flow axis sequence is calculated by the Discrete Fraser algorithm and used as the geometric deformation distance. The larger the geometric deformation distance, the lower the similarity between the two, which means that the fish are deviating from the main channel.

[0039] It should be noted that spatial equidistant resampling discretization can be performed on the time sequence of the swimming trajectory and the ideal water flow axis sequence to avoid algorithm failure.

[0040] Given that different fishway widths vary, the ratio of geometric deformation distance to the reference channel width is used as the main channel deviation for each batch of fish. The main channel deviation is a relative deviation ratio, and the larger the value, the more severe the horizontal geometric deformation of the batch of fish deviates from the most unobstructed route in the center of the fishway.

[0041] The backwater rest area is typically located on both sides of the fishway. The difference between half the width of the reference channel in the test section and the width of the backwater rest area (the width of the backwater rest area on both sides of the fishway is the same) is divided by the reference channel width to obtain the lower deformation threshold. This threshold represents the minimum acceptable deviation of the fish's swimming trajectory from the main channel. When the deviation exceeds this threshold, the fish are considered to have "gone out of bounds" and may be resting, thus reducing data reliability and validity. Therefore, the difference between the main channel deviation and the lower deformation threshold is calculated. A positive and larger difference indicates lower data validity, while a negative and smaller difference indicates higher data validity. This difference is then negatively correlated and normalized to correct the logical relationship, thus obtaining the effective swimming weight of each batch of fish swimming through the test section. A larger effective swimming weight indicates higher data validity. The negative correlation mapping and normalization here can use the negative correlation Sigmoid function, in the form of... Where e represents the natural constant and x represents the independent variable.

[0042] It should be noted that the Discrete Frescher algorithm is a well-known technique, and the specific process will not be elaborated here.

[0043] Step S3: Integrate the theoretical environmental pressure rate, energy consumption index and effective swimming weight of all batches of fish to determine the long-term evaluation deviation index, which is used to screen out the effective error period in all monitoring periods.

[0044] The theoretical environmental pressure rate obtained from the aforementioned steps can characterize the potential pressure exerted on the fish by the environment. The energy consumption index reflects the actual resistance experienced by the fish in the environment. Therefore, comparing the differences between the two can characterize the deviation between theory and reality. At the same time, since the effective movement weight is obtained based on the actual physical swimming trajectory of the fish, combining this index can eliminate the contamination of error statistics by the spontaneous resting behavior of the fish, thus obtaining a more accurate evaluation deviation index to explain the model error at this time.

[0045] Preferably, in one embodiment of the present invention, the method for obtaining the evaluation deviation index includes: The absolute value of the difference between the theoretical environmental pressure rate and the physical exertion index for each batch of fish is taken as the individual evaluation error of each batch of fish. The larger the individual evaluation error, the greater the deviation between the original parameters in the multi-factor evaluation calculation model and the actual situation of the fish in the current environment, and the higher the possibility of model failure. In other words, if the original parameters in the multi-factor evaluation calculation model are still used under the current circumstances, it will lead to an increase in error.

[0046] Based on the analysis in step S2, it can be seen that the larger the effective swimming weight, the higher the data validity, and the data is not affected by the resting behavior of the fish. Therefore, the reference value of the individual evaluation error of this batch of fish is also higher. So, the effective swimming weights corresponding to all batches of fish are used to calculate the weighted average of the individual evaluation error, and the result is used as the long-term evaluation deviation index for each monitoring period. Based on the above analysis, it can be seen that the larger the long-term evaluation deviation index, the more serious the model failure is, and the more adjustments are needed.

[0047] It should be noted that in the weighted averaging process, the denominator is the sum of all effective swimming weights, and the numerator is the sum of the individual evaluation errors of all batches of fish multiplied by the effective swimming weights. In this process, if the denominator is 0, a preset constant is added to the denominator as an addend to prevent the denominator from being 0. The specific value can be 0.001, and the specific value is not limited here.

[0048] After obtaining the long-term evaluation deviation index for each monitoring period, the index can be used to screen out the effective error periods from all monitoring periods.

[0049] Preferably, in one embodiment of the present invention, the method for obtaining the effective error period includes: If the long-term evaluation deviation index of a certain monitoring period is greater than the preset allowable deviation threshold, it means that the error exceeds the acceptable error range. In this case, the monitoring period is regarded as an effective error period, and the subsequent parameter reconstruction process needs to be triggered.

[0050] It should be noted that in this embodiment of the present invention, the preset allowable deviation threshold is set to 0.15. The specific value can be adjusted according to the implementation scenario and is not limited here.

[0051] Step S4: Construct an environmental parameter constraint space based on the biological constants of the fish population, and on this basis, combine the energy consumption index, effective swimming weight, and water temperature and flow velocity sequences of all batches of fish populations within the effective error period to perform traversal optimization and generate final state environmental evaluation parameters for updating the multi-factor evaluation calculation model.

[0052] Because conventional mathematical function fitting algorithms, when processing data with a certain degree of dispersion, may derive extreme environmental parameters that violate the basic physiological common sense of aquatic organisms in order to seek the absolute minimum in a purely mathematical sense, in this embodiment of the invention, an environmental parameter constraint space can be constructed based on the biological constants of the fish population as a hard constraint. Then, based on this, the energy consumption index, effective swimming weight, and water temperature and flow velocity sequences of all batches of fish populations within the effective error period are combined to perform traversal optimization to generate final state environmental evaluation parameters.

[0053] Preferably, in one embodiment of the present invention, the method for obtaining the final state environmental evaluation parameters includes: Biological constants, including the lethal high temperature threshold, the upper limit of the ultimate resistance to flow velocity, the lower limit of the dormant low temperature, and the lower limit of the basic flow velocity, can all be obtained from relevant biological literature databases.

[0054] The lower limit of dormancy low temperature (lower boundary value) and the upper limit of lethal high temperature (upper boundary value) are used as two boundary values ​​to obtain the temperature mid-axis interval to be optimized. Similarly, the lower limit of basic flow velocity (lower boundary value) and the upper limit of ultimate flow resistance velocity (upper boundary value) are used as two boundary values ​​to obtain the velocity mid-axis interval to be optimized. The purpose of constructing the temperature mid-axis interval and the velocity mid-axis interval to be optimized is to limit the constraint space of parameter optimization and prevent the generation of extreme parameters that violate common sense.

[0055] Then, within the temperature and flow rate ranges to be optimized, the temperature and flow rate values ​​to be optimized are combined in pairs using an exhaustive search method. Each pair is used as a parameter to be measured. At this time, each set of environmental parameters to be measured contains a temperature value to be optimized and a flow rate value to be optimized. In this embodiment of the invention, a preset search step size can be set, such as 0.5℃ or 0.1m / s.

[0056] In each effective error period, all data points corresponding to each batch of fish (water temperature and flow velocity at the same moment constitute a data point pair) are input into the Gaussian decay function of the multi-factor evaluation calculation model, and combined with each set of environmental parameters to be measured, the instantaneous retardation rate corresponding to each data point pair is calculated. The formula model is the same as in step S2. ,in, Indicates the first Instantaneous lag rate at any given moment; Indicates the first The water temperature at that moment; This represents the central value of the temperature to be optimized in the environmental parameters to be measured. This represents the tolerance coefficient corresponding to temperature. Indicates the first The flow rate at that moment; This represents the central value of the flow velocity to be optimized in the environmental parameters to be measured. This represents the tolerance coefficient corresponding to the flow velocity; This represents an exponential function with the natural constant e as its base.

[0057] The mean of the instantaneous resistance rate of all data point pairs corresponding to each batch of fish is taken as the new theoretical environmental pressure rate for each batch of fish. The new theoretical environmental pressure rate represents the potential pressure on the fish under the new environmental parameters. The absolute value of the difference between the new theoretical environmental pressure rate and the energy consumption index of the fish (representing the actual resistance experienced by the fish in the environment) is taken as the error factor. The error factor is weighted and fused using the effective swimming weights of all batches of fish. The accumulated result is taken as the candidate value for each set of environmental parameters to be tested. The larger the candidate value, the larger the error under the set of environmental parameters to be tested, and the lower the application probability.

[0058] Finally, the mean of the candidate values ​​of each set of environmental parameters under test in all effective error periods is used as the error index. Based on the above analysis, it can be seen that the smaller the error index, the higher the degree of matching between the environmental parameters under test and the current environment. Therefore, among all environmental parameters under test, the environmental parameter corresponding to the smallest error index is used as the final state environmental evaluation parameter.

[0059] After obtaining the final environmental assessment parameters, they can be used to update the multi-factor parity calculation model.

[0060] Preferably, in one embodiment of the present invention, updating the multi-factor evaluation calculation model includes: The temperature and velocity midline values ​​in the final state environmental assessment parameters are replaced with the original temperature and velocity midline terms in the multi-factor assessment parameter model to obtain the updated assessment parameter model.

[0061] After updating the evaluation parameter model, it can be applied to the subsequent evaluation of fish passage effect: obtain the latest water temperature and flow velocity sequences for the monitoring period, and use the updated evaluation parameter model in combination with the latest water temperature and flow velocity sequences to calculate the real-time environmental pressure rate of the simulated fish passage effect. The larger the real-time environmental pressure rate, the more severe the deviation of the current water temperature or flow velocity from the fish's most adapted living space, and the greater the physiological stress and energy consumption on the fish.

[0062] Therefore, when the real-time environmental pressure rate exceeds the preset pressure threshold, the environment is considered to be deteriorating, and an alarm is required to remind the management personnel to make hydraulic adjustments; otherwise, no alarm is required.

[0063] It should be noted that the preset compression threshold can be set to 0.8, and the specific value can be adjusted according to the implementation scenario, without limitation here.

[0064] In summary, firstly, multidimensional data on each batch of fish swimming through the test section were acquired within each monitoring period, along with a multi-factor evaluation calculation model and engineering parameters of the test section. Within each monitoring period, based on the water temperature and flow velocity sequences corresponding to each batch of fish, the theoretical environmental pressure rate was calculated using the multi-factor evaluation calculation model, accurately quantifying the degree of pressure exerted on the fish by the water environment resistance. Based on a comparison between the total time spent by each batch of fish and a preset baseline time, an energy consumption index was determined, quantifying the actual energy consumption of the fish during their swim through the test section. Since time alone cannot distinguish whether the fish were swept away by the current or in the backwater resting area, the effective swimming weight was determined based on the deviation of the swimming trajectory time sequence of each batch of fish, combined with the engineering parameters of the test section. This accurately identifies and significantly reduces the weight of invalid time data in the backwater resting area. Furthermore, multiple indicators corresponding to all batches of fish were integrated to determine a long-term evaluation deviation index, and this index was used to screen out effective error periods across all monitoring periods. Finally, an environmental parameter constraint space was constructed based on the biological constants of the fish population to ensure that the subsequent traversal optimization process was carried out within a framework that conformed to the biological characteristics of the fish population. The traversal optimization was carried out by combining the energy consumption index, effective swimming weight, and water temperature and flow velocity sequences of all batches of fish populations within the effective error period. This enabled the evaluation model to be adaptively calibrated according to seasonal changes and eliminated data pollution caused by the rest area, making the model more in line with the actual situation and improving the model's adaptability and prediction accuracy to different environments and fish population states.

[0065] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for evaluating the fish passage effect of an eco-friendly fishway based on multi-factor analysis, characterized in that, The method includes: The total time spent by each batch of fish swimming through the test section, the time sequence of their swimming trajectory, the water temperature sequence, and the flow velocity sequence are obtained for each monitoring period. The multi-factor evaluation calculation model and the engineering parameters of the test section are also obtained. In each monitoring cycle, based on the water temperature and flow velocity sequences corresponding to each batch of fish, the theoretical environmental pressure rate corresponding to each batch of fish is calculated using the multi-factor evaluation calculation model; the physical energy consumption index of each batch of fish is determined by comparing the total time spent by each batch of fish with the preset benchmark time; and the effective swimming weight of each batch of fish in the test section is determined by the deviation of the swimming trajectory time sequence of each batch of fish and in combination with the engineering parameters of the test section. By integrating the theoretical environmental pressure rate, energy consumption index, and effective swimming weight of all batches of fish, a long-term evaluation deviation index is determined, which is used to screen out the effective error period in all monitoring periods. An environmental parameter constraint space is constructed based on the biological constants of fish populations. On this basis, the energy consumption index, effective swimming weight, and water temperature and flow velocity sequences of each batch of fish populations within the effective error period are combined to perform traversal optimization and generate final state environmental evaluation parameters for updating the multi-factor evaluation calculation model. The method for obtaining the theoretical environmental pressure rate includes: The multi-factor evaluation calculation model includes a temperature central term, a flow velocity central term, and a tolerance coefficient term; In each monitoring cycle, in the water temperature and flow velocity sequences corresponding to each batch of fish, the water temperature and flow velocity at the same moment are combined to form a data point pair. All data point pairs are input into the Gaussian decay function of the multi-factor evaluation calculation model, and combined with the temperature central term, flow velocity central term and tolerance coefficient term, the instantaneous lag rate corresponding to each data point pair is calculated. The average instantaneous retardation rate of all data point pairs corresponding to each batch of fish is taken as the theoretical environmental pressure rate corresponding to each batch of fish.

2. The method for evaluating the fish passage effect of a biomimetic fishway based on multi-factor analysis according to claim 1, characterized in that, The methods for obtaining the physical fitness expenditure indicators include: The ratio of the total time spent on each batch of fish to the preset baseline time is used as the actual time multiplier for each batch of fish. The difference between the actual time taken for each batch of fish and the preset time is taken as the excess delay multiple, and the ratio of the excess delay multiple to the upper limit of the preset limit multiple is taken as the energy consumption index of each batch of fish.

3. The method for evaluating the fish passage effect of a biomimetic fishway based on multi-factor analysis according to claim 1, characterized in that, The method for obtaining the effective movement weight includes: The engineering parameters include the ideal water flow axis of the test section, the width of the reference tank, and the width of the return water rest area; The deviation between the swimming trajectory time sequence of each batch of fish and the ideal water flow axis is analyzed to determine the deviation of each batch of fish from the main channel. The difference between half the reference channel width of the test section and the width of the backwater rest area is divided by the reference channel width to obtain the lower limit threshold for deformation. The difference between the main channel deviation and the lower limit threshold for deformation is negatively correlated and normalized to obtain the effective swimming weight of each batch of fish swimming through the test section.

4. The method for evaluating the fish passage effect of a biomimetic fishway based on multi-factor analysis according to claim 3, characterized in that, The method for obtaining the main channel deviation includes: The spatial deformation distance between the time sequence of the swimming trajectory of each batch of fish and the ideal water flow axis is calculated by the discrete Fraser algorithm and used as the geometric deformation distance. The ratio of the geometric deformation distance to the reference channel width is used as the main channel deviation of each batch of fish.

5. The method for evaluating the fish passage effect of a biomimetic fishway based on multi-factor analysis according to claim 1, characterized in that, The method for obtaining the evaluation deviation index includes: The absolute value of the difference between the theoretical environmental pressure rate and the physical exertion index corresponding to each batch of fish is used as the individual evaluation error of each batch of fish. The individual evaluation error was weighted and averaged using the effective swimming weights corresponding to all batches of fish, and the result was used as a long-term evaluation deviation index for each monitoring period.

6. The method for evaluating the fish passage effect of a biomimetic fishway based on multi-factor analysis according to claim 1, characterized in that, The method for obtaining the effective error period includes: If the long-term evaluation deviation index of a certain monitoring period is greater than the preset allowable deviation threshold, then the monitoring period is regarded as the effective error period.

7. The method for evaluating the fish passage effect of a biomimetic fishway based on multi-factor analysis according to claim 1, characterized in that, The method for obtaining the final state environmental evaluation parameters includes: The biological constants include the lethal high temperature threshold, the upper limit of the ultimate resistance to flow velocity, the lower limit of the dormant low temperature, and the lower limit of the basic flow velocity. The lower limit of dormancy low temperature and the lethal high temperature threshold are respectively used as two boundary values ​​to obtain the central temperature range to be optimized. The lower limit of basic flow velocity and the upper limit of ultimate flow resistance velocity are respectively used as two boundary values ​​to obtain the central velocity range to be optimized. In the temperature mid-axis range and the flow velocity mid-axis range to be optimized, the temperature mid-axis value and the flow velocity mid-axis value to be optimized are combined in pairs using an exhaustive method, and each pair of combinations is used as the environmental parameter to be measured. In each effective error period, all data point pairs corresponding to each batch of fish are input into the Gaussian decay function of the multi-factor evaluation calculation model, and combined with each set of environmental parameters to be tested, the instantaneous lag rate corresponding to each data point pair is calculated. The mean of the instantaneous retardation rate of all data point pairs corresponding to each batch of fish is used as the new theoretical environmental pressure rate for each batch of fish. The absolute value of the difference between the new theoretical environmental pressure rate and the physical exertion index corresponding to the fish is used as the error factor. The error factor is weighted and fused using the effective swimming weights of all batches of fish, and the accumulated result is used as the candidate value corresponding to each set of environmental parameters to be tested. The mean of the candidate values ​​of each set of environmental parameters under test in all effective error periods is used as the error index. Among all environmental parameters under test, the environmental parameter corresponding to the minimum error index is used as the final state environmental evaluation parameter.

8. The method for evaluating the fish passage effect of a biomimetic fishway based on multi-factor analysis according to claim 7, characterized in that, The updated multi-factor evaluation calculation model includes: The temperature and flow rate midline values ​​in the final environmental evaluation parameters are replaced with the original temperature and flow rate midline terms in the multi-factor evaluation parameter model to obtain the updated evaluation parameter model.

9. The method for evaluating the fish passage effect of a biomimetic fishway based on multi-factor analysis according to claim 8, characterized in that, After updating the multi-factor evaluation calculation model, it also includes: The latest water temperature and flow velocity sequences from the monitoring period are obtained. The updated evaluation parameter model is used in conjunction with the latest water temperature and flow velocity sequences to calculate the real-time environmental pressure rate of the fish passage effect of the simulated fishway. When the real-time environmental pressure rate exceeds the preset pressure threshold, the environment is considered to be deteriorating and an alarm is required; otherwise, no alarm is required.

Images