CN113945729A - Average flow velocity calculation method based on channel vertical section - Google Patents
Average flow velocity calculation method based on channel vertical section Download PDFInfo
- Publication number
- CN113945729A CN113945729A CN202111197734.XA CN202111197734A CN113945729A CN 113945729 A CN113945729 A CN 113945729A CN 202111197734 A CN202111197734 A CN 202111197734A CN 113945729 A CN113945729 A CN 113945729A
- Authority
- CN
- China
- Prior art keywords
- flow velocity
- vertical
- perpendicular bisector
- neural network
- section
- 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.)
- Granted
Links
- 238000004364 calculation method Methods 0.000 title abstract description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 70
- 238000000034 method Methods 0.000 claims abstract description 49
- 238000005259 measurement Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims description 54
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 238000005520 cutting process Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 4
- 238000012360 testing method Methods 0.000 abstract description 4
- 230000008859 change Effects 0.000 abstract description 3
- 238000009826 distribution Methods 0.000 description 9
- 230000005888 antibody-dependent cellular phagocytosis Effects 0.000 description 7
- 238000003062 neural network model Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 210000000349 chromosome Anatomy 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000008303 genetic mechanism Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P5/00—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measuring Volume Flow (AREA)
Abstract
The invention discloses a channel vertical section-based average flow velocity calculation method, which comprises the following steps of: step 1: setting a plurality of vertical lines uniformly distributed on the same plane, and dividing the cross section of the channel into a plurality of vertical sections; step 2: acquiring the surface flow velocity of the perpendicular bisectors of the channel and the surface flow velocity of each perpendicular bisector by using a velocimeter, and acquiring the water depth of each perpendicular bisector by using water level measurement equipment; and step 3: establishing the relationship between the surface flow velocity of the perpendicular bisector and the relative positions of other perpendicular bisectors and the perpendicular bisector and the surface flow velocities of other perpendicular bisectors; and 4, step 4: establishing a linear relation between the surface flow velocity and the water depth of the channel vertical section and the average flow velocity of the vertical section; and 5: and obtaining the river cross section flow through the surface velocity and the water level of the perpendicular bisector. The invention solves the problem that the water level change needs to be measured again by the traditional flow velocity area method, so that the measurement and test work is more efficient and accurate, and the invention has important innovative significance and application value.
Description
Technical Field
The invention relates to the technical field of hydrological test application, in particular to a channel vertical section-based average flow velocity calculation method.
Background
The accurate measurement of the river section flow is an important link for carrying out water resource optimal configuration and scientific management, and is also a technical problem which needs to be solved urgently by accurately measuring the water intake in real time in irrigation areas and water diversion projects.
Natural open channel flow is more complex and variable than pipe flow; and are mostly turbulent flow. The velocity in the turbulent boundary layer is not only determined by viscous force, but also related to reynolds stress generated by pulsation; therefore, the turbulent flow boundary layer is not determined by a single rule, but can be divided into an inner layer and an outer layer; wherein the outer layer is thicker, the inner layer is thinner, and the inner layer and the outer layer are overlapped. (the outer layer is mainly affected by the main flow and the inner layer is mainly affected by the wall surface). The flow velocity distribution of the open channel approximately meets a logarithmic distribution rule, but actually has more deviation; many scientists have derived from experiments different parameters k and B, and various laws are responsible for the deviation of this flow rate from the logarithmic distribution.
The traditional flow measuring and calculating method comprises a hydraulic building flow measuring method: the flow is measured using standard type of flow structures, such as weir and trough methods. The most widely used method for measuring and calculating the flow at present is a flow velocity area method, wherein some local (point, line or small area) flow velocities of a flow cross section are measured on the cross section of an open channel, the average flow velocity of the flow cross section is calculated by using the flow velocities, then the water level is measured to obtain the area of the flow cross section, and finally the average flow velocity of the flow cross section is multiplied by the area of the flow cross section to obtain the flow. However, the traditional flow velocity area method measures the flow velocity of a plurality of points at the same time, calculates the average flow velocity of a partial area, then calculates the section flow rate by combining the section area one by one and accumulating, and simultaneously measures the flow velocity of each point again when the water level changes each time, and is tedious and time-consuming in process. How to obtain the average flow velocity quickly and accurately is a difficulty in flow calculation. In actual river section flow measurement, due to the irregularity of the river section, the water depth changes along with the section position and the river bank distance, and the change of the flow velocity is more complex, so that the river flow measurement is very troublesome.
In patent application No. 201911180284.6, a river flow measuring method for measuring a vertical flow velocity distribution based on horizontal ADCP is disclosed, which comprises the steps of: 1) horizontal ADCP horizontal survey line arrangement; 2) acquiring the flow velocity of a vertical line measuring point; 3) fitting flow velocity distribution parameters of a vertical speed measurement vertical line; 4) calculating the flow of the flow measuring section; according to the method, the horizontal ADCP is moved, so that a horizontal representation correlation method can be converted into a mature river flow measuring method, and the flow measuring precision is improved; the difficulty of line selection represented by partial flow level ADCP is avoided, and the application range of the horizontal ADCP measuring method is widened; and can guide frequency selection of the level ADCP. However, the ADCP equipment in this solution is expensive, and needs to measure a plurality of point positions on each vertical line, which is costly.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a channel vertical section-based average flow velocity calculation method.
The purpose of the invention is realized by the following technical scheme:
a method for calculating average flow velocity based on a channel vertical section comprises the following steps:
step 1: setting a plurality of vertical lines uniformly distributed on the same plane, and dividing the cross section of the channel into a plurality of vertical sections; the vertical line is a cutting line vertical to the water surface;
step 2: acquiring the surface flow velocity of the perpendicular bisectors of the channel and the surface flow velocity of each perpendicular bisector by using a velocimeter, and acquiring the water depth of each perpendicular bisector by using water level measurement equipment; the perpendicular bisector is a cutting line vertical to the middle point of the water surface of the channel;
and step 3: establishing the relationship between the surface flow velocity of the perpendicular bisector and the relative positions of other perpendicular bisectors and the perpendicular bisector and the surface flow velocities of other perpendicular bisectors;
and 4, step 4: establishing a linear relation between the surface flow velocity and the water depth of the channel vertical section and the average flow velocity of the vertical section;
and 5: and obtaining the river cross section flow through the surface velocity and the water level of the perpendicular bisector.
Further, the step 1 specifically comprises: analyzing the channel section structure, and if the width of the water surface is more than 5m, dividing a vertical section every 0.4m for the section with the width-depth ratio more than 5; if the width of the water surface is more than 2m and not more than 5m, dividing a vertical tangent plane every 0.25 m; if the width of the water surface is not more than 2m, dividing a vertical tangent plane every 0.2 m; for the section with the width-depth ratio less than or equal to 5, dividing precision in the area which is 20% of the water surface width away from the left side and the right side of the perpendicular bisector is doubled according to the rule, and dividing rules at other positions are unchanged; the width-depth ratio is the ratio of the length of the horizontal median of the river course to the depth of the river.
Further, the step 3 specifically includes: using a GA _ BP neural network, taking the surface flow velocity of the perpendicular bisector and the relative position of each perpendicular bisector and the perpendicular bisector as input, and taking the surface flow velocity of each perpendicular as characteristic output to obtain the relationship between the surface flow velocity of the perpendicular bisector and the surface flow velocities of other perpendicular lines; the GA _ BP neural network comprises: and constructing a basic BP neural network, optimizing the initial weight and threshold of the neural network by adopting a GA algorithm, selecting the optimal weight and threshold, and finally continuing to train by using the BP neural network.
Further, the step 4 specifically includes: using a BP supervision RBF neural network to input the water depth and the surface flow velocity at the position of the vertical line as characteristics, and using the average flow velocity of the vertical section as characteristic output to obtain the linear relation; the RBF neural network comprises: training parameters of the RBF neural network by adopting a supervised learning algorithm; carrying out gradient reduction on the cost function, and then correcting each parameter; the parameters include the center of the radial basis function, the variance, and the weight from the hidden layer to the output layer.
Further, the training process of the GA _ BP neural network is as follows: measuring the flow velocity of each point on a vertical line with the same interval between the cross sections of the river channels according to a dividing mode; and (3) using the GA _ BP neural network to obtain the relationship between the surface flow velocity of the perpendicular bisector and the surface flow velocities of other perpendicular lines by taking the surface flow velocities of the perpendicular bisector and the relative positions of the other perpendicular lines and the perpendicular bisector as characteristic input and taking the surface speeds of the other perpendicular lines as characteristic output.
Further, the training process of the RBF neural network is as follows: calculating to obtain the average velocity of the vertical lines according to the point velocity of each measured vertical line, and using an RBF neural network to input the water depth and the surface velocity of each vertical line as characteristics, and using the average velocity of each vertical line as characteristic output to obtain the relationship between the water depth and the surface velocity of each vertical line; the point flow velocity includes the surface flow velocity and the water depth of the vertical.
Further, the step 5 specifically includes: inputting the surface flow velocity of the perpendicular bisector, and obtaining the surface flow velocities of other perpendicular bisectors according to the relationship between the surface flow velocity of the perpendicular bisector and the surface flow velocities of other perpendicular bisectors obtained by the GA _ BP neural network; then obtaining the average flow velocity of each vertical section through the trained RBF neural network; and finally, calculating the river cross section flow according to the area of each vertical section.
The invention has the beneficial effects that: the river channel section flow can be measured mainly by means of one point flow velocity on the surface of the perpendicular bisector based on a neural network algorithm. The problem that all data need to be measured again when the water level is changed by the traditional flow velocity area method is solved, so that the measurement and test work is more efficient and accurate, and the method has important innovation significance and application value.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a schematic view of a river slice.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
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.
Embodiment 1, as shown in fig. 1, a method for calculating an average flow velocity based on a channel vertical section, includes the following steps:
step 1: setting a plurality of vertical lines uniformly distributed on the same plane, and dividing the cross section of the channel into a plurality of vertical sections; the vertical line is a cutting line vertical to the water surface;
step 2: acquiring the surface flow velocity of the perpendicular bisectors of the channel and the surface flow velocity of each perpendicular bisector by using a velocimeter, and acquiring the water depth of each perpendicular bisector by using water level measurement equipment; the perpendicular bisector is a cutting line vertical to the middle point of the water surface of the channel;
and step 3: establishing the relationship between the surface flow velocity of the perpendicular bisector and the relative positions of other perpendicular bisectors and the perpendicular bisector and the surface flow velocities of other perpendicular bisectors;
and 4, step 4: establishing a linear relation between the surface flow velocity and the water depth of the channel vertical section and the average flow velocity of the vertical section;
and 5: and obtaining the river cross section flow through the surface velocity and the water level of the perpendicular bisector.
Wherein, the step 1 specifically comprises the following steps: analyzing the channel section structure, and if the width of the water surface is more than 5m, dividing a vertical section every 0.4m for the section with the width-depth ratio more than 5; if the width of the water surface is more than 2m and not more than 5m, dividing a vertical tangent plane every 0.25 m; if the width of the water surface is not more than 2m, dividing a vertical tangent plane every 0.2 m; for the section with the width-depth ratio less than or equal to 5, dividing precision in the area which is 20% of the water surface width away from the left side and the right side of the perpendicular bisector is doubled according to the rule, and dividing rules at other positions are unchanged; the width-depth ratio is the ratio of the length of the horizontal median of the river course to the depth of the river.
Wherein, the step 3 specifically comprises the following steps: and (3) using the GA _ BP neural network, taking the surface flow velocity of the perpendicular bisector and the relative position of each perpendicular bisector and the perpendicular bisector as input, and taking the surface flow velocity of each perpendicular bisector as characteristic output to obtain the relationship between the surface flow velocity of the perpendicular bisector and the surface flow velocities of other perpendicular bisectors.
Wherein, the step 4 specifically comprises the following steps: and (3) using the BP supervised RBF neural network to obtain the linear relation by taking the water depth and the surface flow velocity at the position of the vertical line as characteristic inputs and taking the average flow velocity of the vertical section as characteristic output.
Wherein the GA _ BP neural network comprises: constructing a basic BP neural network, optimizing the initial weight and threshold of the neural network by adopting a GA algorithm, selecting the optimal weight and threshold, and finally continuing to train by using the BP neural network; the RBF neural network comprises: training parameters of the RBF neural network by adopting a supervised learning algorithm; carrying out gradient reduction on the cost function, and then correcting each parameter; the parameters include the center of the radial basis function, the variance, and the weight from the hidden layer to the output layer.
Further, the training process of the neural network model is as follows: measuring the flow velocity of each point on a vertical line with the same interval between the cross sections of the river channels according to a dividing mode; using a GA _ BP neural network to input the surface flow velocity of the perpendicular bisector and the relative positions of other perpendicular bisectors and the perpendicular bisector as characteristics, and using the surface velocities of other perpendicular lines as characteristic outputs to obtain the relationship between the surface flow velocity of the perpendicular bisector and the surface flow velocities of other perpendicular lines; calculating to obtain the average velocity of the vertical lines according to the point velocity of each measured vertical line, and using an RBF neural network to input the water depth and the surface velocity of each vertical line as characteristics, and using the average velocity of each vertical line as characteristic output to obtain the relationship between the water depth and the surface velocity of each vertical line; the point flow velocity includes the surface flow velocity and the water depth of the vertical.
Further, the step 5 specifically includes: inputting the surface flow velocity of the perpendicular bisector, and obtaining the surface flow velocities of other perpendicular bisectors according to the relationship between the surface flow velocity of the perpendicular bisector and the surface flow velocities of other perpendicular bisectors obtained by the GA _ BP neural network; then obtaining the average flow velocity of each vertical section through the trained RBF neural network; and finally, calculating the river cross section flow according to the area of each vertical section.
In this embodiment, as shown in fig. 2, a cross-section structure is analyzed, and for a cross section with a width-depth ratio greater than 5, if the width of the water surface exceeds 5m, a vertical section is divided every 0.4 m; the width of the water surface is more than 2m and less than 5m, and a vertical tangent plane is divided every 0.25 m; the width of the water surface is less than 2m, and a vertical tangent plane is divided every 0.2 m; for the section with the width-depth ratio smaller than 5, the dividing precision in the region 20% away from the perpendicular bisector is doubled according to the rule, and the dividing rule of the rest positions is unchanged. N +1 vertical sections are obtained, the areas of which are S from left to right respectively1、S2、S3、……、Sn+1。
The width-depth ratio (the width of the bottom of the channel plus the width of the water surface divided by twice the depth of water to obtain the width-depth ratio) is calculated first, and then the width is divided according to the width of the water surface. The open channel is divided into a wide and shallow open channel and a narrow and deep open channel according to the difference of the width-depth ratio, wherein the wide and deep ratio is mainly used for judging whether the open channel is the narrow and deep open channel or the wide and shallow open channel, and the open channel type is generally divided by taking the width-depth ratio b/h as 5 as a limit in a rectangular open channel. Compared with a wide-shallow open channel, the narrow-deep open channel (the width-depth ratio is less than 5) needs to be divided more densely in the areas which are 20% away from the perpendicular bisector respectively, the dividing precision is doubled on the basis of the wide-shallow open channel, for example, a vertical tangent plane is divided every 0.4m for the wide channel, and only a vertical tangent plane is divided every 0.2m for the narrow depth in the areas which are 20% away from the perpendicular bisector respectively.
In this embodiment, the surface velocity v of the perpendicular bisector is measured by a velocimeterpbDepth h of each vertical tangent planeiAnd the relative position d of each vertical line and the perpendicular bisectori。
In this embodiment, a new non-contact river channel flow rapid flow measurement technology is developed to realize real-time monitoring of river channel flow. Different from the traditional manual flow measurement, which has overhigh time and labor cost, the novel non-contact flow measurement technology can only measure the flow velocity of a certain point or a certain partial area (measuring the surface flow velocity by a radar or measuring the partial area flow velocity of a cross section by ultrasonic waves), and the flow velocity distribution condition of the whole cross section cannot be obtained. Aiming at the pain points, an actual simulation model is established by combining a computational fluid mechanics method, and a deep learning method is utilized to reconstruct a fracture surface field; therefore, the flow velocity distribution condition of the whole section can be obtained from the flow velocity of a single point or a partial area.
Based on the above description of the problems, a preliminary solution (non-contact rapid flow measurement solution) is proposed. Firstly, a measuring cable is arranged along two banks of a river channel, a plurality of measuring points are calibrated according to the width of the river channel, and the surface flow velocity and the river channel water level of the river channel water surface of each calibration point are measured through a radar technology. Secondly, measuring the river water level of each measuring point, dividing the section into a plurality of gridding sections, and adopting a proper area reconstruction method for each grid section to obtain accurate calculation of each section grid; by fitting the relation between the distribution of the cross-section flow velocity field and the surface flow velocity, a cross-section flow velocity distribution model is established, and the cross-section flow velocity field can be reconstructed through the surface flow velocity, so that the average flow velocity of each cross-section grid can be obtained. And finally, multiplying the area of each section grid by the average flow velocity to obtain the flow of the section grid, and finally obtaining the flow of the whole section by adopting an area surrounding method.
The bp (back propagation) neural network is a concept proposed by scientists including Rumelhart and McClelland in 1986, is a multi-layer feedforward neural network trained according to an error back propagation algorithm, and is the most widely applied neural network.
The basic principle is as follows: the basic idea is a gradient descent method, which uses a gradient search technique in order to minimize the mean square error of the actual output value and the expected output value of the network. The basic BP algorithm includes two processes, forward propagation of signals and back propagation of errors. That is, the error output is calculated in the direction from the input to the output, and the weight and the threshold are adjusted in the direction from the output to the input. During forward propagation, an input signal acts on an output node through a hidden layer, an output signal is generated through nonlinear transformation, and if actual output does not accord with expected output, the process of backward propagation of errors is carried out. The error back transmission is to back transmit the output error to the input layer by layer through the hidden layer, and to distribute the error to all units of each layer, and to use the error signal obtained from each layer as the basis for adjusting the weight of each unit. The error is reduced along the gradient direction by adjusting the connection strength of the input node and the hidden node, the connection strength of the hidden node and the output node and the threshold value, the network parameters (weight and threshold value) corresponding to the minimum error are determined through repeated learning and training, and the training is stopped immediately. At the moment, the trained neural network can process and output the information which is subjected to nonlinear conversion and has the minimum error to the input information of similar samples.
Bp (back propagation) neural network structure: in the BP network, a plurality of (one or more) layers of neurons are added between an input layer and an output layer, the neurons are called hidden units, the hidden units are not directly connected with the outside, but the state change of the hidden units can affect the relation between the input and the output, and each layer can have a plurality of nodes.
Genetic Algorithm (GA) is designed and proposed according to the evolution rule of organisms in nature, is a calculation model of a biological evolution process simulating natural selection and Genetic mechanism of Darwinian biological evolution theory, and is a method for searching an optimal solution by simulating the natural evolution process. The algorithm converts the solving process of the problem into the processes of crossover, variation and the like of chromosome genes in the similar biological evolution by a mathematical mode and by utilizing computer simulation operation. When a complex combined optimization problem is solved, a better optimization result can be obtained faster compared with some conventional optimization algorithms.
After analyzing the problems of the BP neural network and the advantages of the genetic algorithm, the two algorithms are combined to train and predict the model, so that the precision of the model can be greatly improved.
In this embodiment, the GA _ BP neural network model construction includes: constructing a basic BP neural network, optimizing the initial weight and threshold of the neural network by adopting a GA algorithm, selecting the optimal weight and threshold, and finally continuing to train by using the BP neural network; the RBF neural network model construction comprises the following steps: training all parameters of the network by adopting a supervised learning algorithm; carrying out gradient reduction on the cost function, and then correcting each parameter; calculating to obtain the average flow velocity of the vertical line according to the flow velocity of each point on the measured vertical line
Using a BP (back propagation) supervision RBF (radial basis function) neural network to input the water depth and the surface flow velocity of the vertical line position as characteristics, and using the average flow velocity of the vertical line as characteristic output to obtain the relationship between the water depth and the surface flow velocity;
the parameters include the center of the radial basis function, the variance, and the weight from the hidden layer to the output layer.
In this embodiment, 5 sets of river sections are measured on the same vertical line hiAnd the flow speed of each point of 0.1m is measured when the water level difference is large. The measured surface flow velocity v of each vertical linesi(i is 1, 2, 3, …, n), and using a GA _ BP neural network to input the surface flow velocity of the perpendicular bisector and the relative positions of other perpendicular lines and the perpendicular bisector as features, and using the surface velocities of other perpendicular lines as feature outputs to obtain the relationship between the surface flow velocity of the perpendicular bisector and the surface flow velocities of other perpendicular lines;
calculating to obtain the average velocity of the vertical line according to the velocity of each point on the measured vertical line, and using a BP (back propagation) supervision RBF (radial basis function) neural network to input the water depth and the surface velocity of the vertical line as characteristics, and using the average velocity of the vertical line as characteristic output to obtain the relationship between the water depth and the surface velocity of the vertical line; the point flow velocity includes the surface flow velocity and the water depth of the vertical.
In this embodiment, the step 4 specifically includes: and (3) sequentially inputting the data measured in the step (2) into the GA _ BP neural network model and the RBF neural network model to obtain the average flow velocity of each vertical line, and calculating the cross section flow of the river channel according to the area of each vertical section.
The specific calculation formula is as follows:
the river channel section flow can be measured mainly by means of one point flow velocity on the surface of the perpendicular bisector based on a neural network algorithm. The problem that all data need to be measured again when the water level is changed by the traditional flow velocity area method is solved, so that the measurement and test work is more efficient and accurate, and the method has important innovation significance and application value.
It should be noted that, for simplicity of description, the above-mentioned embodiments of the method are described as a series of acts or combinations, but those skilled in the art should understand that the present application is not limited by the order of acts described, as some steps may be performed in other orders or simultaneously according to the present application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and elements referred to are not necessarily required in this application.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a ROM, a RAM, etc.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
Claims (7)
1. A method for calculating average flow velocity based on a channel vertical section comprises the following steps:
step 1: setting a plurality of vertical lines uniformly distributed on the same plane, and dividing the cross section of the channel into a plurality of vertical sections; the vertical line is a cutting line vertical to the water surface;
step 2: acquiring the surface flow velocity of the perpendicular bisectors of the channel and the surface flow velocity of each perpendicular bisector by using a velocimeter, and acquiring the water depth of each perpendicular bisector by using water level measurement equipment; the perpendicular bisector is a cutting line vertical to the middle point of the water surface of the channel;
and step 3: establishing the relationship between the surface flow velocity of the perpendicular bisector and the relative positions of other perpendicular bisectors and the perpendicular bisector and the surface flow velocities of other perpendicular bisectors;
and 4, step 4: establishing a linear relation between the surface flow velocity and the water depth of the channel vertical section and the average flow velocity of the vertical section;
and 5: and obtaining the river cross section flow through the surface velocity and the water level of the perpendicular bisector.
2. The method as claimed in claim 1, wherein the step 1 is specifically as follows: analyzing the channel section structure, and if the width of the water surface is more than 5m, dividing a vertical section every 0.4m for the section with the width-depth ratio more than 5; if the width of the water surface is more than 2m and not more than 5m, dividing a vertical tangent plane every 0.25 m; if the width of the water surface is not more than 2m, dividing a vertical tangent plane every 0.2 m; for the section with the width-depth ratio less than or equal to 5, dividing precision in the area which is 20% of the water surface width away from the left side and the right side of the perpendicular bisector is doubled according to the rule, and dividing rules at other positions are unchanged; the width-depth ratio is the ratio of the length of the horizontal median of the river course to the depth of the river.
3. The method as claimed in claim 1, wherein the step 3 is specifically as follows: using a GA _ BP neural network, taking the surface flow velocity of the perpendicular bisector and the relative position of each perpendicular bisector and the perpendicular bisector as input, and taking the surface flow velocity of each perpendicular as characteristic output to obtain the relationship between the surface flow velocity of the perpendicular bisector and the surface flow velocities of other perpendicular lines; the GA _ BP neural network comprises: and constructing a basic BP neural network, optimizing the initial weight and threshold of the neural network by adopting a GA algorithm, selecting the optimal weight and threshold, and finally continuing to train by using the BP neural network.
4. The method as claimed in claim 1, wherein the step 4 is specifically as follows: using a BP supervision RBF neural network to input the water depth and the surface flow velocity at the position of the vertical line as characteristics, and using the average flow velocity of the vertical section as characteristic output to obtain the linear relation; the RBF neural network comprises: training parameters of the RBF neural network by adopting a supervised learning algorithm; carrying out gradient reduction on the cost function, and then correcting each parameter; the parameters include the center of the radial basis function, the variance, and the weight from the hidden layer to the output layer.
5. The method as claimed in claim 3, wherein the training process of the GA _ BP neural network comprises: measuring the flow velocity of each point on a vertical line with the same interval between the cross sections of the river channels according to a dividing mode; and (3) using the GA _ BP neural network to obtain the relationship between the surface flow velocity of the perpendicular bisector and the surface flow velocities of other perpendicular lines by taking the surface flow velocities of the perpendicular bisector and the relative positions of the other perpendicular lines and the perpendicular bisector as characteristic input and taking the surface speeds of the other perpendicular lines as characteristic output.
6. The method as claimed in claim 4, wherein the RBF neural network is trained by: calculating to obtain the average velocity of the vertical lines according to the point velocity of each measured vertical line, and using an RBF neural network to input the water depth and the surface velocity of each vertical line as characteristics, and using the average velocity of each vertical line as characteristic output to obtain the relationship between the water depth and the surface velocity of each vertical line; the point flow velocity includes the surface flow velocity and the water depth of the vertical.
7. The method as claimed in claim 6, wherein the step 5 is specifically as follows: inputting the surface flow velocity of the perpendicular bisector, and obtaining the surface flow velocities of other perpendicular bisectors according to the relationship between the surface flow velocity of the perpendicular bisector and the surface flow velocities of other perpendicular bisectors obtained by the GA _ BP neural network; then obtaining the average flow velocity of each vertical section through the trained RBF neural network; and finally, calculating the river cross section flow according to the area of each vertical section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111197734.XA CN113945729B (en) | 2021-10-14 | Average flow velocity calculation method based on channel vertical section |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111197734.XA CN113945729B (en) | 2021-10-14 | Average flow velocity calculation method based on channel vertical section |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113945729A true CN113945729A (en) | 2022-01-18 |
| CN113945729B CN113945729B (en) | 2024-07-30 |
Family
ID=
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114814282A (en) * | 2022-04-13 | 2022-07-29 | 武汉大学 | Velocity of flow perpendicular distribution measuring device |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110116765A (en) * | 2010-04-20 | 2011-10-26 | 주식회사 하이드로소닉 | Ultrasonic flow measuring method and apparatus for canal |
| CN107490410A (en) * | 2017-08-17 | 2017-12-19 | 河海大学 | It is a kind of based on represent vertical line point flow velocity measurement Gao Hong contactless flow measurement method |
| CN108254032A (en) * | 2017-12-12 | 2018-07-06 | 水利部南京水利水文自动化研究所 | River ultrasonic wave time difference method method of calculating flux |
| CN110243423A (en) * | 2019-07-29 | 2019-09-17 | 中国电建集团中南勘测设计研究院有限公司 | Discharge of river calculation method and system |
| CN110702079A (en) * | 2019-10-12 | 2020-01-17 | 中国水利水电科学研究院 | Deduction method of flow velocity distribution under ice cover |
| CN110906992A (en) * | 2019-11-27 | 2020-03-24 | 长江水利委员会水文局 | River flow measuring method based on horizontal ADCP measuring vertical line flow velocity distribution |
| CN111288973A (en) * | 2020-01-23 | 2020-06-16 | 中山大学 | Method and device for obtaining flow rate of sea surface, computer equipment and storage medium |
| CN111461192A (en) * | 2020-03-25 | 2020-07-28 | 长江水资源保护科学研究所 | River channel water level flow relation determination method based on multi-hydrological station linkage learning |
| CN111476824A (en) * | 2020-04-08 | 2020-07-31 | 苏州浪潮智能科技有限公司 | Sea surface temperature prediction method, sea surface temperature prediction device and computer readable storage medium |
| CN112149597A (en) * | 2020-09-29 | 2020-12-29 | 中国水利水电科学研究院 | River surface flow velocity detection method based on deep learning |
| CN112305258A (en) * | 2020-09-07 | 2021-02-02 | 南京睿和致胜信息技术咨询有限公司 | Method of flow velocity of decomposed cross section |
| CN112948767A (en) * | 2021-02-24 | 2021-06-11 | 长江水利委员会水文局 | Online flow measurement scheme recommendation method based on long-sequence ADCP flow model |
| CN113124941A (en) * | 2021-04-01 | 2021-07-16 | 长江水利委员会长江科学院 | Non-contact type river channel flow measuring and accurate calculating method |
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110116765A (en) * | 2010-04-20 | 2011-10-26 | 주식회사 하이드로소닉 | Ultrasonic flow measuring method and apparatus for canal |
| CN107490410A (en) * | 2017-08-17 | 2017-12-19 | 河海大学 | It is a kind of based on represent vertical line point flow velocity measurement Gao Hong contactless flow measurement method |
| CN108254032A (en) * | 2017-12-12 | 2018-07-06 | 水利部南京水利水文自动化研究所 | River ultrasonic wave time difference method method of calculating flux |
| CN110243423A (en) * | 2019-07-29 | 2019-09-17 | 中国电建集团中南勘测设计研究院有限公司 | Discharge of river calculation method and system |
| CN110702079A (en) * | 2019-10-12 | 2020-01-17 | 中国水利水电科学研究院 | Deduction method of flow velocity distribution under ice cover |
| CN110906992A (en) * | 2019-11-27 | 2020-03-24 | 长江水利委员会水文局 | River flow measuring method based on horizontal ADCP measuring vertical line flow velocity distribution |
| CN111288973A (en) * | 2020-01-23 | 2020-06-16 | 中山大学 | Method and device for obtaining flow rate of sea surface, computer equipment and storage medium |
| CN111461192A (en) * | 2020-03-25 | 2020-07-28 | 长江水资源保护科学研究所 | River channel water level flow relation determination method based on multi-hydrological station linkage learning |
| CN111476824A (en) * | 2020-04-08 | 2020-07-31 | 苏州浪潮智能科技有限公司 | Sea surface temperature prediction method, sea surface temperature prediction device and computer readable storage medium |
| CN112305258A (en) * | 2020-09-07 | 2021-02-02 | 南京睿和致胜信息技术咨询有限公司 | Method of flow velocity of decomposed cross section |
| CN112149597A (en) * | 2020-09-29 | 2020-12-29 | 中国水利水电科学研究院 | River surface flow velocity detection method based on deep learning |
| CN112948767A (en) * | 2021-02-24 | 2021-06-11 | 长江水利委员会水文局 | Online flow measurement scheme recommendation method based on long-sequence ADCP flow model |
| CN113124941A (en) * | 2021-04-01 | 2021-07-16 | 长江水利委员会长江科学院 | Non-contact type river channel flow measuring and accurate calculating method |
Non-Patent Citations (4)
| Title |
|---|
| 张耀先, 张瑞雪: "智能化伺服跟踪明渠流量量测方法探讨", 黄河水利职业技术学院学报, no. 02, 30 April 2005 (2005-04-30), pages 9 - 16 * |
| 朱颖洁;: "侧扫雷达在线流量监测***在西江流量监测中的应用――以梧州水文站为例", 广西水利水电, no. 01, 29 February 2020 (2020-02-29), pages 44 - 48 * |
| 牟意红: "基于GA-BP神经网络的灌区水流量监测***设计", 中国优秀硕士学位论文全文数据库 农业科技辑, no. 07, 15 July 2019 (2019-07-15), pages 9 - 16 * |
| 陈文雄;朱咏;陈学林;: "基于LM-BP神经网络的黑河龙电渠流量推测研究", 地下水, no. 05, 25 September 2018 (2018-09-25), pages 115 - 117 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114814282A (en) * | 2022-04-13 | 2022-07-29 | 武汉大学 | Velocity of flow perpendicular distribution measuring device |
| CN114814282B (en) * | 2022-04-13 | 2023-03-31 | 武汉大学 | Velocity of flow perpendicular distribution measuring device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113887142A (en) | Average flow velocity calculation method based on channel cross section | |
| Verma et al. | Porosity and permeability estimation using neural network approach from well log data | |
| CN103714382B (en) | A kind of multi-index comprehensive evaluation method for reliability of urban rail train security detection sensor network | |
| CN113221342B (en) | Small-watershed flood self-adaptive intelligent networking forecasting method | |
| CN103177289B (en) | Modeling method for noise-uncertainty complicated nonlinear dynamic system | |
| CN113639805B (en) | Flow measurement method based on channel section flow velocity field reconstruction | |
| CN112926265A (en) | Atmospheric porous probe measurement calibration method based on genetic algorithm optimization neural network | |
| Samantaray et al. | Sediment assessment for a watershed in arid region via neural networks | |
| CN112464584A (en) | Method for estimating water level and flow of free surface flow | |
| CN117829035B (en) | Prediction method for flow of downstream branch channel of T-shaped bifurcate open channel | |
| CN105678417A (en) | Prediction method and device for tunnel face water inflow of construction tunnel | |
| CN108491931A (en) | A method of non-destructive testing precision is improved based on machine learning | |
| CN111412959B (en) | Flow online monitoring calculation method, monitor and monitoring system | |
| CN111104746B (en) | River flood beach elevation determination method based on wavelet analysis | |
| CN115471679A (en) | Method and intelligent system for synchronously assimilating water level and flow of natural river | |
| CN112836789A (en) | Ground connection wall deformation dynamic prediction method based on composite neural network algorithm | |
| CN104634265A (en) | Soft measurement method for thickness of mineral floating foam layer based on multivariate image feature fusion | |
| Vaghefi et al. | Application of artificial neural networks to predict flow velocity in a 180 sharp bend with and without a spur dike | |
| CN113642259B (en) | River flow field reconstruction method based on multilayer flow velocity measurement | |
| CN114912364A (en) | Natural gas well flow prediction method, device, equipment and computer readable medium | |
| Kaushik et al. | Sustainable gene expression programming model for shear stress prediction in nonprismatic compound channels | |
| CN112862200B (en) | Intelligent feedback optimization method for whole process of highway construction quality | |
| CN113111590A (en) | Urban flood model runoff sensitivity parameter identification method based on artificial neural network | |
| CN113945729A (en) | Average flow velocity calculation method based on channel vertical section | |
| CN113945729B (en) | Average flow velocity calculation method based on channel vertical section |
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 |