Disclosure of Invention
In view of this, the present application provides a measurement system for water channel flow, which is used for measuring the flow of water in a water channel and providing a data reference basis for scientific allocation of water resources.
In order to achieve the above object, the following solutions are proposed:
the utility model provides a measurement system of ditch flow, measurement system includes ultrasonic flowmeter box, flowmeter control system and host computer, wherein:
the ultrasonic flowmeter box body comprises a box-shaped body arranged at the front end of the automatic gate;
the inner cavity of the box-shaped body is a water flow channel, a water level sensor is arranged in the box-shaped body, and a plurality of ultrasonic probes are transversely arranged on the inner side of the side wall of the box-shaped body along the same water level height;
the flowmeter control system is provided with a water level signal interface, a plurality of flow velocity signal interfaces, a gate opening degree signal interface and a data interaction interface;
the water level signal interface is connected with the water level sensor and used for receiving a water level signal output by the water level sensor;
each flow velocity signal interface is connected with the corresponding ultrasonic probe and used for receiving a flow velocity signal output by the ultrasonic probe so that the flowmeter control system can obtain a plurality of flow velocity signals;
the gate opening signal interface is connected with a gate opening signal output end of the automatic gate and used for receiving a gate opening signal;
the data interaction end is connected with the upper computer and used for outputting flow data obtained by the flowmeter control system based on the water level signal, the flow signals, the gate opening degree signal and the flow model to the upper computer;
the upper computer is used for receiving the flow data so that a user can read the flow data.
Scientifically, the flow meter control system comprises a microcontroller module, a first-in first-out memory, a multi-way selection switch, a Fourier transform module, a random access memory and a convolutional neural network module, wherein:
the microcontroller is respectively connected with the water level signal interface, the flow rate signal interface, the gate opening interface and the data interaction interface, and is also respectively connected with the first-in first-out memory, the multi-path selection switch, the Fourier transform module, the random access memory and the convolutional neural network;
the first-in first-out memory is respectively connected with each flow speed signal interface and is also connected with the multi-way selection switch;
the Fourier transform module is also respectively connected with the multi-path selection switch and the random access memory;
the random access memory is also connected with the convolutional neural network module.
Optionally, the data interaction interface is further configured to send the water level signal, the flow rate signal, and the gate opening signal to the upper computer.
Optionally, the data interaction interface is further configured to send model update data output by the upper computer based on the water level signal, the flow rate signal, and/or the gate opening degree signal to the microcontroller module, so that the microcontroller module updates the flow model in the convolutional neural network module based on the model update data.
According to the technical scheme, the application discloses a measuring system for the flow of a water channel, which comprises an ultrasonic flowmeter box body, a flowmeter control system and an upper computer. The ultrasonic flowmeter box body comprises a box-shaped body arranged at the front end of the automatic gate; a water level sensor and a plurality of ultrasonic probes are arranged in the box-shaped body; the flowmeter control system is provided with a water level signal interface, a plurality of flow velocity signal interfaces, a gate opening interface and a data interaction interface; the water level signal interface is used for receiving a water level signal; each flow velocity signal interface is used for receiving a flow velocity signal; the gate opening signal interface is used for receiving a gate opening signal; the data interaction end is connected with the upper computer and used for outputting flow data obtained by the flowmeter control system based on the water level signal, the plurality of flow signals, the gate opening degree signal and the flow model to the upper computer; the upper computer is used for receiving the traffic data so that a user can read the traffic data. By the scheme, the user can obtain accurate flow data, so that a data reference basis is provided for scientific allocation of water resources.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
Fig. 1 is a schematic view of a system for measuring flow rate in a canal according to an embodiment of the present disclosure.
As shown in fig. 1, the measurement system provided in the present embodiment is used for accurately measuring the flow rate of a canal, and specifically includes an ultrasonic flow meter box 10, a flow meter control system 20, and an upper computer 30. Wherein, this flowmeter control system passes through data line signal connection with ultrasonic wave flow metering box, host computer respectively.
This ultrasonic flow meter case sets up the front end at the automatic gate 100 of ditch, and the user can control its gate aperture through programme-controlled mode or manual mode when needs to the realization is controlled the ditch flow. The automatic gate is provided with a gate opening signal output end 101 for outputting a gate opening signal.
The ultrasonic flowmeter box comprises a box-shaped body, wherein the box-shaped body is a box-shaped channel which is forward and reverse or rectangular, and water flows through the box-shaped channel. A water level sensor (not shown) and a plurality of ultrasonic probes (not shown) arranged laterally are provided in the box-shaped passage. The water level sensor is used for detecting the water level of water flowing through the box-shaped body and outputting a water level signal reflecting the water level based on the detection result.
The ultrasonic probes are arranged on the side wall of the inner side of the box-shaped body, are arranged at different heights of the box-shaped body, and are used for detecting the flow velocity of the water flow in different flow layers of the water flow in the box-shaped body and outputting flow velocity signals reflecting the flow velocity of the different flow layers.
The flowmeter control system is provided with a water level signal interface 21, a plurality of flow rate signal interfaces 22, a gate opening degree signal interface 23 and a data interaction interface 24. The water level signal interface is connected with the water level sensor and used for receiving a water level signal output by the water level sensor; the gate opening interface is connected with a gate opening signal output end of the automatic gate and used for receiving a gate opening signal. So that the fault identification flowmeter control system receives a water level signal and a gate opening signal.
The quantity of velocity of flow signal interface is the same with ultrasonic transducer's quantity, and the one-to-one connection, and every ultrasonic transducer can export the velocity of flow signal interface that corresponds in proper order through surveying produced velocity of flow signal to corresponding flow layer like this to make this intelligence trouble flowmeter control system obtain a plurality of velocity of flow signals.
The flowmeter control system calculates flow data based on the water level signal, the flow signal, the gate opening and the flow model.
The flow velocity v is measured by a time difference method, and the calculation formula is as follows:
wherein L is the distance of the ultrasonic probe,
angle with direction of water flow, t
1And t
2Is the time of flight of the ultrasound.
The data interaction interface is connected with an upper computer, the upper computer can be a computer or a mobile device, and the data interaction interface can be a wireless data interface capable of bidirectionally transmitting data, such as a wifi interface or a Bluetooth interface, in order to be connected with the upper computer. The data interaction interface is used for outputting flow data obtained by the flowmeter control system based on the water level signal, the flow signals, the gate opening degree signal and the flow model to an upper computer.
The upper computer is used for receiving the flow data so that a user can read the flow data, and can record and file the flow data so as to meet the requirement of the user on calling of historical data.
According to the technical scheme, the embodiment provides a canal flow measuring system which comprises an ultrasonic flowmeter box body, a flowmeter control system and an upper computer. The ultrasonic flowmeter box body comprises a box-shaped body arranged at the front end of the automatic gate; a water level sensor and a plurality of ultrasonic probes are arranged in the box-shaped body; the flowmeter control system is provided with a water level signal interface, a plurality of flow velocity signal interfaces, a gate opening interface and a data interaction interface; the water level signal interface is used for receiving a water level signal; each flow velocity signal interface is used for receiving a flow velocity signal; the gate opening signal interface is used for receiving a gate opening signal; the data interaction end is connected with the upper computer and used for outputting flow data obtained by the flowmeter control system based on the water level signal, the plurality of flow signals, the gate opening degree signal and the flow model to the upper computer; the upper computer is used for receiving the traffic data so that a user can read the traffic data. By the scheme, the user can obtain accurate flow data, so that a data reference basis is provided for scientific allocation of water resources.
The flow meter control system in this embodiment specifically includes a microcontroller module 201, a first-in first-out memory 202, a multiplexer 203, a fourier transform module 204, a random access memory 205, and a convolutional neural network module 206, as shown in fig. 2. The microcontroller is respectively connected with the water level signal interface, the flow rate signal interface, the gate opening interface and the data interaction interface, and is also respectively connected with the first-in first-out memory, the multi-path selection switch, the Fourier transform module, the random access memory and the convolutional neural network;
the first-in first-out memory is respectively connected with each flow velocity signal interface and is also connected with the multi-path selection switch; the Fourier transform module is also respectively connected with the multi-path selection switch and the random access memory; the random access memory is also connected with the convolutional neural network module.
Based on the connection, the water level signal is sent into the microcontroller module, a plurality of flow velocity signals obtained by detection of the ultrasonic sensors are sent into the microcontroller module and are simultaneously sent into the first-in first-out memory, the flow velocity signals are sequentially sent into the Fourier transform module by the multi-path selection switch under the control of the microcontroller module, so that spectral analysis is realized on the flow velocity signals, the frequency spectrum obtained by analysis is sent into the random access memory, and after the spectral analysis of the flow velocity signals of all channels is completed, all the spectral analysis results are sent into the convolutional neural network module, as shown in fig. 3.
The convolution neural network module is stored with a corresponding flow model, calculates the frequency based on the flow model and outputs a plurality of results, wherein the results comprise cyclone existence in the flow velocity channel, flow velocity channel water flow laminar flow, flow velocity channel water flow turbulent flow, flow velocity channel water flow still water state and flow velocity channel water flow return water, and a plurality of results are sent to the microcontroller module, so that the microcontroller module calculates according to the plurality of results, a plurality of flow velocity signals, a water level signal and a gate opening signal, and therefore flow velocity data are obtained.
In addition, the data interaction structure is realized by a Bluetooth model, and the Bluetooth is adopted to reduce power consumption, so that the data interaction structure is suitable for field application occasions.
The data interaction interface is also used for sending a water level signal, a flow velocity signal and a gate opening degree signal to the upper computer so that the upper computer configures parameters of the flow velocity model according to the signals, namely model updating data required for configuring the parameters of the flow velocity model once is obtained in a large working period, and the model updating data is output to the microcontroller module through the data interaction interface so that the microcontroller module updates the flow model in the neural network module based on the model updating data. So that the flow model more closely approximates the actual scene.
The flow model is realized based on a deep Convolutional Neural Network (CNN), wherein the term deep refers to the number of layers in the network, and the more the number of layers, the deeper the network. Conventional neural networks contain only 2 or 3 layers, whereas deep networks may have hundreds of layers. Convolutional Neural Networks (CNNs) are composed of an input layer, an output layer, and intermediate hidden layers, like other neural networks.
Feature detection is performed by performing one of three types of operations on the data, namely convolution, pooling, or modifying linear units. Convolution puts the input image into a set of convolution filters, each filter activating certain features in the image. Pooling reduces the number of parameters that the network needs to learn by performing non-linear downsampling, thereby simplifying the output. The modified linear unit achieves faster, more efficient training by mapping negative values to zero and maintaining positive values. After feature detection, the CNN architecture is transferred to classification, and the last layer of the CNN architecture provides classification output using the softmax function. At present, a plurality of open-source CNN models are available, and initial training and verification of data can be rapidly carried out by adopting TensorFlow. The final classification result is that the flow speed channel has cyclone, the water flow of the flow speed channel belongs to laminar flow, the water flow belongs to turbulent flow, the water flow in the box body is in a static state, and the water flow in the box body has a water return state.
Fig. 4 is a diagram of an operation mode of the measurement system according to the embodiment of the present application. The intelligent state identification and the flow metering of the flowmeter are operated in parallel. The flow rate model mode is contained in a large timing period, and after configuration is completed, the flow rate channel state can be identified, and meanwhile, the flow can be measured. The flow metering mode and the state recognition mode can be carried out in a circulating mode all the time after the gate is opened, and the flow metering mode and the state recognition mode are stopped after the gate is closed so as to reduce the power consumption of the system.
And when the flow velocity channel state is changed, storing the data of the current state as training data. The Bluetooth module of the system can be manually opened to transmit training data to the intelligent terminal, further training of the model is carried out on the intelligent terminal, and a more accurate flow model is calculated.
Fig. 5 is a flow chart of the operation of the measurement system. The flow chart describes the process that the microcontroller module coordinates each module to collect data in a metering period, the Fourier transform and the neural network module identify the state, and the flow calculation is carried out after the state is identified.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The technical solutions provided by the present invention are described in detail above, and the principle and the implementation of the present invention are explained in this document by applying specific examples, and the descriptions of the above examples are only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.