LU504055B1 - Embedded sediment concentration measurement system based on recurrent neural network and control method thereof - Google Patents
Embedded sediment concentration measurement system based on recurrent neural network and control method thereof Download PDFInfo
- Publication number
- LU504055B1 LU504055B1 LU504055A LU504055A LU504055B1 LU 504055 B1 LU504055 B1 LU 504055B1 LU 504055 A LU504055 A LU 504055A LU 504055 A LU504055 A LU 504055A LU 504055 B1 LU504055 B1 LU 504055B1
- Authority
- LU
- Luxembourg
- Prior art keywords
- unit
- module
- neural network
- turbidity
- water surface
- Prior art date
Links
- 238000005259 measurement Methods 0.000 title claims abstract description 40
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 38
- 230000000306 recurrent effect Effects 0.000 title claims abstract description 35
- 239000013049 sediment Substances 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 10
- 238000004891 communication Methods 0.000 claims abstract description 63
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 53
- 238000009413 insulation Methods 0.000 claims abstract description 24
- 230000003993 interaction Effects 0.000 claims abstract description 20
- 238000013500 data storage Methods 0.000 claims abstract description 10
- 230000005540 biological transmission Effects 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims description 10
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 claims description 9
- 125000004122 cyclic group Chemical group 0.000 claims description 9
- 229910052744 lithium Inorganic materials 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 5
- 230000002452 interceptive effect Effects 0.000 claims description 5
- 230000002441 reversible effect Effects 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
- G01N15/075—Investigating concentration of particle suspensions by optical means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N2015/0042—Investigating dispersion of solids
- G01N2015/0053—Investigating dispersion of solids in liquids, e.g. trouble
Landscapes
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Engineering & Computer Science (AREA)
- Dispersion Chemistry (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
The present invention discloses an embedded sediment concentration measurement system based on a recurrent neural network and a control method thereof, wherein the measurement system comprises a water surface parameter display unit, an underwater parameter acquisition unit, an insulation protection unit, a power supply unit, a temperature acquisition unit, a voltage acquisition unit, a man-machine interaction unit, a communication unit and a GPS module. The present invention is applied to monitoring of water resources and water environment in river basins such as river channels and has the advantages of convenient operation, multi-channel measurement, high measurement accuracy, convenient data storage and viewing, and remote control and data transmission.
Description
DESCRIPTION LU504055
EMBEDDED SEDIMENT CONCENTRATION MEASUREMENT SYSTEM BASED ON
RECURRENT NEURAL NETWORK AND CONTROL METHOD THEREOF
The present invention relates to the technical field of turbidity and sediment concentration measurement, in particular to an embedded sediment concentration measurement system based on a recurrent neural network and a control method thereof.
Background technology
Water resources survey 1s the basic work necessary for national economic construction.
With rapid development of national economy, a contradiction between supply and demand of water resources is increasingly prominent, which requires hydrological work to support sustainable utilization of water resources with better water resources information, among which turbidity and sediment concentration are two very important indicators. Therefore, based on market demands and needs of engineering projects, there is an urgent need for a measuring system that can measure the turbidity and sediment concentration of water in real time for accurate monitoring of water quality.
In view of the above defects or deficiencies in the prior art, it is expected to provide an embedded sediment concentration measurement system based on a recurrent neural network and a control method thereof, which is applied to monitoring of water resources and water environment in river channels and other river basins, with convenient operation, multi-channel measurement, high measurement accuracy, convenient data storage and viewing, and remote control and transmission.
The present invention provides an embedded sediment concentration measurement system based on a recurrent neural network, comprising: a water surface parameter display unit, which comprises a microprocessor and a hardware reset module, a real-time clock module, a parameter display module, a wake-up module, a data download module, a data storage module and a serial communication module which are 504055 respectively connected with the microprocessor; an underwater parameter acquisition unit, which is connected with the water surface parameter display unit through a insulation protection unit, and is used for acquiring relevant information of underwater turbidity; an insulation protection unit, which comprises a power insulation circuit and a signal insulation circuit; a power supply unit, which is respectively connected with the water surface parameter display unit and the underwater parameter acquisition unit; a temperature acquisition unit, which is connected with the water surface parameter display unit through the insulation protection unit; a voltage acquisition unit, which is connected with the underwater parameter acquisition unit for acquiring working voltage of the underwater parameter acquisition unit, and the voltage acquisition unit is connected with the water surface parameter display unit through the insulation protection unit; a man-machine interaction unit, which is connected with the water surface parameter display unit; a communication unit, which is connected with the water surface parameter display unit; and a GPS module, which is connected with the water surface parameter display unit.
Further, the underwater parameter acquisition unit is composed of a plurality of independent turbidity sensors.
Further, the power supply unit comprises: a lithium battery, which is sequentially connected with the water surface parameter display unit and the underwater parameter acquisition unit through a rectification filter circuit, a voltage conversion circuit, a low-power processing circuit, an overload and overcurrent protection circuit and a reverse connection protection circuit; a charging module, which is connected with the lithium battery.
Further, the man-machine interaction unit comprises: a voice interaction module, which is connected with the microprocessor through the serial communication module; and a Bluetooth interactive module, which is connected with the microprocessor through the so 4055 serial communication module, and is used for communication and connection between the water surface parameter display unit and a mobile terminal.
Further, the communication unit comprises: a RS485 communication module, which is connected with the microprocessor through the serial communication module, and is used for communication connection between the water surface parameter display unit and a computer; a NB-IoT communication module, which is connected with the microprocessor through the serial communication module, and is used for communication connection between the water surface parameter display unit and a remote server.
In addition, the present invention also provides a control method of the embedded sediment concentration measurement system based on the recurrent neural network, which comprises following steps:
S11, initial setting: initializing a single-chip computer program, setting a time interval Ts of sampling, setting parameters of the communication serial ports, and configuring values of turbidity sensor coefficients A, B and C and parameters of the recurrent neural network V, U and
W,
S12, data acquiring: selecting a measurement channel, acquiring a group of temperature values and a group of turbidity analog values every time interval Ts, wherein the turbidity analog values are photoelectric signals acquired by the turbidity sensors, and acquiring latitudes and longitudes of measurement points and measurement time;
S13, data processing: taking a current temperature value as an effective temperature value according to a sampling order, performing A/D conversion on the last N groups of turbidity analog values, and averaging to obtain current signal values;
S14, data calculation: calculating the turbidity value by a curve fitting equation ym=a(Xm)*+b(xm)+c; wherein m is a positive integer, xm is the current signal value obtained for the mth time, and ym is the turbidity value corresponding to xm; according to effective temperature values and a temperature comparison array TEP[n]={ti,t2,- ",ta}, correcting the turbidity value to obtain a corrected turbidity value Yu;
Ym=ymttemperture scale*(temperture-ti)/(ti+1-ti), ti<temperture <ti+1; wherein n is a natural number greater than 1, tn is the nth control temperature value, tn>tn-1,
and i={1,2,--,n-1}; the temperture scale is a temperature correction coefficient, and the so 4055 temperature is an effective temperature value; according to the corrected turbidity value Ym, the sediment concentration value Mn is calculated by using the circulating neural network system;
Mn =g(Vsm) (I)
Sm=f(UY n°+Wsm-1) (2) wherein so=0; the formula (1) is a calculation formula of an output layer of the recurrent neural network, which is a fully connected layer, that is, each node of the output layer is connected with each node of a hidden layer; V is a weight matrix of the output layer, and g is an activation function of the output layer; the formula (2) is a calculation formula of the hidden layer of the recurrent neural network; the hidden layer is a cyclic layer; U is a weight matrix of the input layer, W is a weight matrix of the cyclic layer, and F is an activation function of the cyclic layer;
S15, data display: displaying the corrected turbidity value and the sediment concentration value in real time in the form of curves;
S16, data storage: according to the data acquiring order, storing a set of data of the current signal value, the corrected turbidity value, the sediment concentration value, the latitude and longitude, and the measurement time;
S17, data transmission: the stored data are sent to a local computer through the RS485 communication module, to the management center server through NB-IoT communication module and to the mobile terminal through Bluetooth.
Further, the parameters of communication serial ports comprise parameters of voice interaction serial port, Bluetooth interaction serial ports, RS485 communication serial ports and
NB-IoT communication serial ports.
In the present invention, N groups of turbidity analog quantities are obtained by the underwater parameter acquisition unit, and after A/D conversion, the average value is obtained to obtain the current signal value; the turbidity value is calculated according to the curve fitting equation ym=a(xm)’+b(xm)+c; the corrected turbidity value is obtained through temperature compensation correction, and the sediment concentration value is calculated by using the recurrent neural network according to the corrected turbidity value. The data transmission between the underwater parameter acquisition unit and the surface parameter display unit (550 4055 protected by the power isolation circuit and the signal isolation circuit, which improves security of the system. The present invention takes the single chip microcomputer as the core, realizes automatic measurement and accurate detection, and ensures users to know the water quality accurately.
The voice interaction module of the present invention has functions of voice recognition and broadcasting, and the microprocessor can perform corresponding operations by itself after recognizing voice results; the present invention has a Bluetooth communication function, which can be connected to a mobile phone when Bluetooth is turned on, and can receive and view data in cooperation with a mobile phone app; the present invention has the function of RS485 communication, and users can connect the present invention to the computer in a wired way to receive and view data with local software; the present invention has the function of NB-IoT wireless communication, and can be connected to the server of a management system after the corresponding IP and port are configured, which is convenient for remote data viewing and receiving.
It should be understood that what is described in the summary of the invention is not intended to define key or important features of embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will be readily understood from the following description.
Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments with reference to the following drawings:
Fig. 1 is a structural block diagram of an embedded sediment concentration measurement system based on recurrent neural network;
Fig. 2 is a flowchart of a control method of the embedded sediment concentration measurement system based on the recurrent neural network; and
Fig. 3 is a schematic diagram of the recurrent neural network.
In the drawings, 1. water surface parameter display unit; 2. underwater parameter acquisition unit; 3. insulation protection unit; 4. power supply unit; 5. temperature acquisition unit; 6. voltage acquisition unit; 7. man-machine interaction unit; 8. communication unit; 9. GES 50 4055 module; 11. microprocessor; 12. hardware reset module; 13. real-time clock module; 14. parameter display module; 15. wake-up module; 16. data download module; 17. data storage module; 18. serial communication module; 21. turbidity sensor; 31. power insulation circuit; 32. signal insulation circuit; 41. lithium battery; 42. rectification filter circuit; 43. voltage conversion circuit; 44. low power processing circuit; 45. overload and overcurrent protection circuit; 46. reverse protection circuit, 47. charging module; 71. voice interaction module; 72. Bluetooth interactive module; 81. RS485 communication module; 82. NB-IoT communication module.
The present invention will be further described in detail with the attached drawings and embodiments. It can be understood that the specific embodiments described here are only used to explain the related invention, but not to limit the invention. In addition, for the convenience of description, only the parts related to the invention are shown in the drawings.
It should be noted that the embodiments in the present invention and the features in the embodiments can be combined with each other when no conflict will occur. The present invention will be described in detail with reference to the attached drawings and embodiments.
Referring to fig. 1, an embodiment of the present invention provides an embedded sediment concentration measurement system based on a recurrent neural network and the system comprises: a water surface parameter display unit 1, which comprises a microprocessor 11 and a hardware reset module 12, a real-time clock module 13, a parameter display module 14, a wake-up module 15, a data download module 16, a data storage module 17 and a serial communication module 18 which are respectively connected with the microprocessor 11; an underwater parameter acquisition unit 2, which is connected with the water surface parameter display unit 1 through an insulation protection unit 3, and is used for acquiring relevant information of underwater turbidity; the insulation protection unit 3, which comprises a power insulation circuit 31 and a signal insulation circuit 32; a power supply unit 4, which is respectively connected with the water surface parameter display unit 1 and the underwater parameter acquisition unit 2;
a temperature acquisition unit 5, which is connected with the water surface parameter,504055 display unit 1 through the insulation protection unit 3; a voltage acquisition unit 6, which is connected with the underwater parameter acquisition unit 2 for acquiring working voltage of the underwater parameter acquisition unit 2, and the voltage acquisition unit 6 is connected with the water surface parameter display unit 1 through the insulation protection unit 3; a man-machine interaction unit 7, which is connected with the water surface parameter display unit 1; a communication unit 8, which is connected with the water surface parameter display unit 1; and a GPS module 9, which is connected with the water surface parameter display unit 1.
In the present embodiment, a recurrent neural network is configured in the microprocessor 11 of the water surface parameter display unit 1, and underwater turbidity analog quantities are obtained through the underwater parameter acquisition unit 2, converted into current signal values, and then transmitted to the water surface parameter display unit 1 through the power supply insulation circuit 31 and the signal insulation circuit 32 for data calculation. According to a curve fitting equation y=ax’+bx-+c, turbidity values are calculated, and then corrected turbidity values are obtained through temperature compensation correction. According to the corrected turbidity values, sediment concentration values are calculated by using the recurrent neural network.
The corrected turbidity values and sediment concentration values are displayed in real time by the parameter display module 14 in form of curves, and the parameter display module 14 is preferably a touch screen. Data storage and data transmission are carried out simultaneously, and current signal values, the corrected turbidity values, the sediment concentration values, latitude and longitude, measuring time are stored as a group of data; transmission of data is completed through the communication unit 8.
The present invention takes a single chip microcomputer as a core, and realizes automatic measurement with convenient operation and accurate detection. The data can be stored and viewed conveniently, and remote control and transmission can be realized, so as to ensure users to know water quality accurately.
In a preferred embodiment, as shown in fig. 1, the underwater parameter acquisition unit 2 is composed of a plurality of independent turbidity sensors 21, and turbidity information of the =o 4055 water body is acquired through the plurality of independent turbidity sensors 21.
In a preferred embodiment, as shown in fig. 1, the power supply unit 4 comprises: a lithium battery 41, which is sequentially connected with the water surface parameter display unit 1 and the underwater parameter acquisition unit 2 through a rectification filter circuit 42, a voltage conversion circuit 43, a low-power processing circuit 44, an overload and overcurrent protection circuit 45 and a reverse connection protection circuit 46; and a charging module 47, which is connected with the lithium battery 41.
In the present embodiment, the system uses the lithium battery 41 for power supply, and power supply safety of the system is ensured through various protection circuits, and the lithium battery 41 is charged by the charging module 47.
In a preferred embodiment, as shown in fig. 1, the man-machine interaction unit 7 comprises: a voice interaction module 71, which is connected with the microprocessor 11 through the serial communication module 18; and a Bluetooth interactive module 72, which is connected with the microprocessor 11 through the serial communication module 18, and is used for communication connection between the water surface parameter display unit 1 and a mobile terminal.
In the present embodiment, voice control of the measurement system is realized by the voice interaction module 71; through the Bluetooth interactive module 72, operation control and information viewing through the mobile terminal is realized; thus convenience of system operation is improved.
In a preferred embodiment, as shown in fig. 1, the communication unit 8 comprises: a RS485 communication module 81, which is connected with the microprocessor 11 through the serial communication module 18, and is used for communication and connection between the water surface parameter display unit 1 and a computer; and a NB-IoT communication module 82, which is connected with the microprocessor 11 through the serial communication module 18, and is used for communication and connection between the water surface parameter display unit 1 and a remote server.
In addition, referring to Figures 2 and 3, the embodiment of the present invention also provides a control method of the embedded sediment concentration measurement system based on the recurrent neural network, which comprises following steps: LU504055
S11, initial setting: initializing a single-chip computer program 1s initialized, setting a time interval Ts of sampling, setting parameters of the communication serial ports, and configuring values of turbidity sensor coefficients A, B and C and parameters of the recurrent neural network
V, U and W; the parameters of communication serial ports comprise parameters of voice interaction serial port, Bluetooth interaction serial ports, RS485 communication serial ports and
NB-IoT communication serial ports;
S12, data acquiring: selecting a measurement channel, acquiring a group of temperature values and a group of turbidity analog values every time interval Ts, wherein the turbidity analog values are photoelectric signals acquired by the turbidity sensors, and acquiring latitudes and longitudes of measurement points and measurement time;
S13, data processing: taking a current temperature value as an effective temperature value according to a sampling order, performing A/D conversion on the last N groups of turbidity analog values, and averaging to obtain current signal values;
S14, data calculation: the turbidity value is calculated by a curve fitting equation ym=a(xm)>+b(xm)+c; wherein m is a positive integer, xm is the current signal value obtained for the mth time, and ym is the turbidity value corresponding to xm; according to effective temperature values and a temperature comparison array TEP[n]={ti,t, ta}, the turbidity value is corrected to obtain a corrected turbidity value Yum;
Ym=ÿnttemperture_scale*(temperture-ti)/(ti-1-ti), ti<temperture <ti+1; wherein n is a natural number greater than 1, tn is the nth control temperature value, tn>tn-1, and i={1,2,--,n-1}; the temperture scale is a temperature correction coefficient, and the temperature is an effective temperature value; the curve fitting equation ym=a(<m)"+b(<m)+e is a functional relationship between the turbidity value and the current signal value obtained by the calibration test in the laboratory standard environment; according to the corrected turbidity value Ym, the sediment concentration value Mn is calculated by using the circulating neural network system;
Mn =g(Vsm) (I)
Sm=F(UY m°+W Sm-1) (2) wherein so=0;
the formula (1) is a calculation formula of an output layer of the recurrent neural network, 504055 which is a fully connected layer, that is, each node of the output layer is connected with each node of a hidden layer; V is a weight matrix of the output layer, and g is an activation function of the output layer; the formula (2) is a calculation formula of the hidden layer of the recurrent neural network; the hidden layer is a cyclic layer with 8 neurons, and each node of the output layer is connected with these 8 nodes; U is a weight matrix of the input layer, W is a weight matrix of the cyclic layer, and F is an activation function of the cyclic layer; f and g use tanh function, that is, tanh(x)=(e*-e*)/(e*+e*); wherein e is a natural logarithm;
S15, data display: displaying the corrected turbidity value and the sediment concentration value in real time in the form of curves;
S16, data storage: according to the data acquiring order, storing a set of data of the current signal value, the corrected turbidity value, the sediment concentration value, the latitude and longitude, and the measurement time;
S17, data transmission: the stored data are sent to a local computer through the RS485 communication module, to the management center server through NB-IoT communication module and to the mobile terminal through Bluetooth; and in some embodiments, taking the temperature comparison array TEP[9]={0°C, 5°C, 10°C, 15°C, 20°C, 25°C, 30°C, 35°C, 40°C} as an example, when the actual temperature value obtained by the measurement is 18°C, the turbidity value
Ym=ymttemperture scale*(18-15)/(20-15), 15<18<20.
Different sand samples have different parameters of recurrent neural network, and the sample table is shown in Table 1. See Table 2 for the parameter table of recurrent neural network of black mud.
Table 1: Parameter Table of Recurrent neural network (Sample Table) ee em
Parameter Format number
Table 2: Parameter Table of Recurrent neural network (black mud, initial parameters) LU504055 l= we
Parameter Values number [-14.0150, 0.0012, 0.0075, -0.0002, 0.0354, v 0.4836, 48.1249, 1245.1035] [0.0001, 0.0451, -0.1254, 21.2489, -14.7460, 7 Y -0.0841, 45172.0215, 0.1642] [0.0000, -0.0004, 1.3242, 1245.1203, 26.2314, ) x -0.0001, 0.0000, 4321.1023]
In the description of the present specification, the terms "one embodiment", "some embodiments" and so on mean that the specific features, structures or characteristics described in connection with the present embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
The above are only the preferred embodiments of this application, and it is not used to limit the present application. For those skilled in the art, the present application can be modified and varied. Any modification, equivalent substitution, improvement, etc. made within the spirit and principles of the present application shall be included in the protective scope of the present application.
Claims (7)
1. An embedded sediment concentration measurement system based on a recurrent neural network, comprising: a water surface parameter display unit, which comprises a microprocessor and a hardware reset module, a real-time clock module, a parameter display module, a wake-up module, a data download module, a data storage module and a serial communication module which are respectively connected with the microprocessor; an underwater parameter acquisition unit, which is connected with the water surface parameter display unit through an insulation protection unit, and is used for acquiring relevant information of underwater turbidity; the insulation protection unit, which comprises a power insulation circuit and a signal insulation circuit; a power supply unit, which is respectively connected with the water surface parameter display unit and the underwater parameter acquisition unit; a temperature acquisition unit, which is connected with the water surface parameter display unit through the insulation protection unit; a voltage acquisition unit, which is connected with the underwater parameter acquisition unit for acquiring working voltage of the underwater parameter acquisition unit, and the voltage acquisition unit is connected with the water surface parameter display unit through the insulation protection unit; a man-machine interaction unit, which is connected with the water surface parameter display unit; a communication unit, which is connected with the water surface parameter display unit; and a GPS module, which is connected with the water surface parameter display unit.
2. The embedded sediment concentration measurement system based on the recurrent neural network according to claim 1, wherein the underwater parameter acquisition unit is composed of a plurality of independent turbidity sensors.
3. The embedded sediment concentration measurement system based on the recurrent neural network according to claim 1, wherein the power supply unit comprises: a lithium battery, which is sequentially connected with the water surface parameter display unit and the underwater parameter acquisition unit through a rectification filter circuit, a voltage, 504055 conversion circuit, a low-power processing circuit, an overload and overcurrent protection circuit and a reverse connection protection circuit; and a charging module, which is connected with the lithium battery.
4. The embedded sediment concentration measurement system based on the recurrent neural network according to claim 1, wherein the man-machine interaction unit comprises: a voice interaction module, which is connected with the microprocessor through the serial communication module; and a Bluetooth interactive module, which is connected with the microprocessor through the serial communication module, and is used for communication and connection between the water surface parameter display unit and a mobile terminal.
5. The embedded sediment concentration measurement system based on the recurrent neural network according to claim 1, wherein the communication unit comprises: a RS485 communication module, which is connected with the microprocessor through the serial communication module, and is used for communication and connection between the water surface parameter display unit and a computer; and a NB-IoT communication module, which is connected with the microprocessor through the serial communication module, and is used for communication and connection between the water surface parameter display unit and a remote server.
6. A control method of the embedded sediment concentration measurement system based on the recurrent neural network, wherein following steps are comprised: S11, initial setting: initializing a single-chip computer program, setting a time interval Ts of sampling, setting parameters of the communication serial ports, and configuring values of turbidity sensor coefficients A, B and C and parameters of the recurrent neural network V, U and W, S12, data acquiring: selecting a measurement channel, acquiring a group of temperature values and a group of turbidity analog values every time interval Ts, wherein the turbidity analog values are photoelectric signals acquired by the turbidity sensors, and acquiring latitudes and longitudes of measurement points and measurement time; S13, data processing: taking a current temperature value as an effective temperature value according to a sampling order, performing A/D conversion on the last N groups of turbidity analog values, and averaging to obtain current signal values; LU504055 S14, data calculation: the turbidity value is calculated by a curve fitting equation ym=a(xm)>+b(xm)+c; wherein m is a positive integer, xm is the current signal value obtained for the mth time, and ym is the turbidity value corresponding to xm; according to effective temperature values and a temperature comparison array TEP[n]={ti,t, ta}, the turbidity value is corrected to obtain a corrected turbidity value Yum; Ym=ÿnttemperture_scale*(temperture-ti)/(ti-1-ti), ti<temperture <ti+1; wherein n is a natural number greater than 1, tn is the nth control temperature value, tn>tn-1, and i={1,2,--,n-1}; the temperture scale is a temperature correction coefficient, and the temperature is an effective temperature value; according to the corrected turbidity value Ym, the sediment concentration value Mn is calculated by using the circulating neural network system; Mn =g(Vsm) (I) Sm=f(UY n°+Wsm-1) (2) wherein so=0; the formula (1) is a calculation formula of an output layer of the recurrent neural network, which is a fully connected layer, that is, each node of the output layer is connected with each node of a hidden layer; V is a weight matrix of the output layer, and g is an activation function of the output layer; the formula (2) is a calculation formula of the hidden layer of the recurrent neural network; the hidden layer is a cyclic layer; U is a weight matrix of the input layer, W is a weight matrix of the cyclic layer, and F is an activation function of the cyclic layer; S15, data display: displaying the corrected turbidity value and the sediment concentration value in real time in the form of curves; S16, data storage: according to the data acquiring order, storing a set of data of the current signal value, the corrected turbidity value, the sediment concentration value, the latitude and longitude, and the measurement time; S17, data transmission: the stored data are sent to a local computer through the RS485 communication module, to the management center server through NB-IoT communication module and to the mobile terminal through Bluetooth.
7. The control method of the embedded sediment concentration measurement system based on the recurrent neural network according to claim 6, wherein the parameters of communication 4055 serial ports comprise parameters of voice interaction serial ports, Bluetooth interaction serial ports, RS485 communication serial ports and NB-IoT communication serial ports.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| LU504055A LU504055B1 (en) | 2023-04-24 | 2023-04-24 | Embedded sediment concentration measurement system based on recurrent neural network and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| LU504055A LU504055B1 (en) | 2023-04-24 | 2023-04-24 | Embedded sediment concentration measurement system based on recurrent neural network and control method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| LU504055B1 true LU504055B1 (en) | 2023-10-24 |
Family
ID=88469829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| LU504055A LU504055B1 (en) | 2023-04-24 | 2023-04-24 | Embedded sediment concentration measurement system based on recurrent neural network and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| LU (1) | LU504055B1 (en) |
-
2023
- 2023-04-24 LU LU504055A patent/LU504055B1/en active IP Right Grant
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104820250B (en) | The processing method of cloud detection on a kind of polar orbiting meteorological satellite VIRR oceans | |
| CN103543179A (en) | Networked system and method for testing soil humidity and pH (Potential of Hydrogen) value | |
| Qin et al. | Noisesense: A crowd sensing system for urban noise mapping service | |
| CN104391250A (en) | Electric vehicle battery mobile phone monitoring system | |
| CN110958059A (en) | Testing device, system and method of satellite receiver | |
| WO2020233519A1 (en) | Measuring instrument and remote volume value transmission/quantity value traceability method | |
| CN108489543B (en) | Enterprise pollution discharge index monitoring equipment and use method | |
| CN103616732A (en) | Quality control method and quality monitoring device of upper-air wind data | |
| CN110568458B (en) | Ionosphere VTEC closed-loop test system and method based on GNSS | |
| Ustad et al. | Zigbee based wireless air pollution monitoring system using low cost and energy efficient sensors | |
| LU504055B1 (en) | Embedded sediment concentration measurement system based on recurrent neural network and control method thereof | |
| CN105806915A (en) | Device and method for detecting concentration of potassium and sodium ions in nutrient solution | |
| CN115266708B (en) | Embedded sand content measuring method based on cyclic neural network | |
| CN116069783B (en) | Hydrologic data processing method and device, computer equipment and storage medium | |
| CN203981771U (en) | A kind of instrument | |
| CN111707803B (en) | Use method of portable soil multi-parameter in-situ measurement and calibration device | |
| CN116186950A (en) | Processing method, system, device and storage medium for gas pipe network simulation | |
| CN112161779B (en) | Method for improving measurement precision of polarization extinction ratio | |
| CN211124139U (en) | System for remotely surveying azimuth | |
| CN114295173A (en) | Surface runoff water quality sampling monitoring device | |
| CN203055143U (en) | Light metering device | |
| CN109298376B (en) | Electric energy value transmission method and system based on standard electric energy meter group | |
| CN114839577A (en) | System for determining the metering quality of a standard device for remote calibration of a high-voltage tester | |
| CN220933181U (en) | Remote calibration system for electric quantity metering chip of charging pile | |
| CN201532554U (en) | Wireless data acquisition system based on MSP430 single chip microcomputer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FG | Patent granted |
Effective date: 20231024 |