CN103499374B - A kind of ultrasound wave dynamic liquid level detection method based on neutral net and system - Google Patents

A kind of ultrasound wave dynamic liquid level detection method based on neutral net and system Download PDF

Info

Publication number
CN103499374B
CN103499374B CN201310401468.7A CN201310401468A CN103499374B CN 103499374 B CN103499374 B CN 103499374B CN 201310401468 A CN201310401468 A CN 201310401468A CN 103499374 B CN103499374 B CN 103499374B
Authority
CN
China
Prior art keywords
neutral net
circuit
ultrasound wave
signal
ultrasonic
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.)
Expired - Fee Related
Application number
CN201310401468.7A
Other languages
Chinese (zh)
Other versions
CN103499374A (en
Inventor
宋寿鹏
赵腾飞
王云蛟
耿伟
晏安贵
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu University
Original Assignee
Jiangsu University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu University filed Critical Jiangsu University
Priority to CN201310401468.7A priority Critical patent/CN103499374B/en
Publication of CN103499374A publication Critical patent/CN103499374A/en
Application granted granted Critical
Publication of CN103499374B publication Critical patent/CN103499374B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
  • Measurement Of Levels Of Liquids Or Fluent Solid Materials (AREA)

Abstract

The invention discloses a kind of ultrasound wave dynamic liquid level detection method based on neutral net, including: single-chip microcomputer sends control signal to ultrasonic sensor, starts intervalometer simultaneously and starts timing and produce pulse ultrasonic wave; Echo-signal is converted into voltage signal by three ultrasonic sensors, and this voltage signal is sent to pre-amplification circuit, and the voltage signal after pre-amplification circuit amplifies is sent to ultrasound wave and receives detecting circuit, it is achieved the envelope detection to high-frequency input signal; Receive comparison circuit to be compared by the reference voltage that the voltage signal after envelope detection circuit detection and system are arranged, according to comparative result output digit signals, after external interrupt control mouth receives effective trailing edge, single-chip microcomputer produces to interrupt, the timer value of record current time, using meansigma methods with rock gradient as the input parameter needed for neutral net, the two parameter is sent to the neutral net mathematical model trained, it is thus achieved that through the output valve of neutral net.

Description

A kind of ultrasound wave dynamic liquid level detection method based on neutral net and system
Technical field
The present invention relates to a kind of detection field, particularly relate to a kind of ultrasound wave dynamic liquid level detection method based on neutral net and system.
Background technology
Liquid can produce significantly to rock in transportation, the real-time dynamic monitoring of the liquid level of liquid is always up a technical barrier, is not well solved so far.
In prior art, exist multiple in the method that the liquid level in transportation is detected, such as: a kind of dynamic liquid level monitoring method based on single sonac, when the method is by gathering long, the ultrasonic echo ripple in window reaches the moment, the ripple that the smooth echo-signal of wavelet filteration method is extracted is used to reach moment curve again, in conjunction with parameters such as the acceleration of motion of moving object, ambient temperatures, utilize support vector machine technology kinestate and pattern are classified and identify, and obtain dynamic fluid flow place value. But, the method there is also weak point, and first, sonac is arranged on above tank body, and it is big that ultrasound wave propagates sound energy attenuation in atmosphere, is unfavorable for measuring; Secondly, will expecting level parameter accurately, monitoring time window is longer, and real-time is deteriorated.
In prior art, there is also another sonar oil tank level dynamic monitoring system, this system adopts active sonar know-why, sent sonar wave by computer control sensor from tank deck mounting flange lower end to pass along transmission wirerope, feeding back different numerical value according to the physicochemical property sonar that profit is different, the data of collection are sent to acquisition module, based on RS485 agreement and upper machine communication, realize real time on-line monitoring and analysis, and show dynamic fluid flow place value. This system there is also weak point, and first, the design of this system is complicated, low being unfavorable for of integrated level is carried;Secondly, Sonar Probe is arranged on abhiseca, and sound energy attenuation is bigger.
Summary of the invention
In order to overcome current liquid Level Detection accuracy in transportation not high, it is easy to the problem producing bigger error, the present invention proposes a kind of ultrasound wave dynamic liquid level detection method based on neutral net and system.
A kind of ultrasound wave dynamic liquid level detection method based on neutral net, including: step 1: single-chip microcomputer utilizes ultrasonic emitting circuit to send control signal to three ultrasonic sensors, start intervalometer simultaneously and start timing and excitation three tunnel ultrasonic emitting circuit generation pulse ultrasonic wave; Step 2: ultrasound wave meets liquid level back reflection, after three ultrasonic sensors are respectively received the echo-signal after reflection, and echo-signal is converted into voltage signal, and this voltage signal is sent to pre-amplification circuit, step 3: after pre-amplification circuit have received voltage signal, voltage signal after pre-amplification circuit amplifies is sent to ultrasound wave and receives detecting circuit, it is achieved the envelope detection to high-frequency input signal; Step 4: the voltage signal after envelope detection circuit detection is sent to reception comparison circuit, receive comparison circuit to be compared by the reference voltage that the voltage signal after envelope detection circuit detection and system are arranged, according to comparative result output digit signals, and by export the inverted device of signal reversely after give the external interrupt control mouth of single-chip microcomputer, external interrupt control mouth is set to saltus step to be triggered, after external interrupt control mouth receives effective trailing edge, single-chip microcomputer produces to interrupt, the timer value of record current time, after singlechip interruption three times, intervalometer stops timing; Step 5: by calculating the meansigma methods of the timer value of three records and rocking gradient, wherein rock the difference of maxima and minima when gradient is record for three times, using meansigma methods with rock gradient as the input parameter needed for neutral net, the two parameter is sent to the neutral net mathematical model trained, and obtaining the output valve through neutral net, output valve is the level value of current time.
Further, the above-mentioned ultrasound wave dynamic liquid level detection method based on neutral net, also include: the error function of the mathematical model of neutral net is:
E = 1 2 N Σ t = 1 N ( y ( t ) - y d ( t ) ) 2
Wherein, N is number of training, and y (t) exports for t BP neutral net, ydT () is t desired output; During by BP Algorithm for Training neutral net, adjusting the connection weights of network, its adjustment expression formula is:
w ( t + 1 ) = w ( t ) + η ∂ E ( t ) ∂ w ( t )
Wherein, the connection weights of the neutral net that w (t) is t, w (t+1) is the connection weights of (t+1) moment neutral net, and E (t) is the mean square error of t neutral net, and η is learning rate.
Further, the above-mentioned ultrasound wave dynamic liquid level detection method based on neutral net, adopt three ultrasonic sensor composition array structures, synchronization motivationtheory emission pulse ultrasonic, utilize the Delay of the window interior echo signal envelope extraction instantaneous liquid level pip received during fixed length.
A kind of ultrasound wave dynamic fluid flow position detecting system based on neutral net, including: single-chip microcomputer, modulate circuit and three ultrasonic sensors; Wherein, single-chip microcomputer is for being loaded with the mathematical model of neutral net, and the mathematical model based on neutral net controls and processes the detection of ultrasound wave dynamic liquid level; Modulate circuit includes ultrasonic emitting circuit, ultrasound wave receives pre-amplification circuit, ultrasound wave receives signal amplification circuit, ultrasound wave receives detecting circuit, ultrasound wave receives comparison circuit and SCM peripheral circuit six part composition, ultrasonic emitting circuit is used for producing pulse ultrasonic wave, realized three roads by Single-chip Controlling and launch signal simultaneously, produce the high-voltage pulse close with ultrasonic sensor probe frequency, excitation sonac emission pulse ultrasonic simultaneously;Ultrasound wave receives pre-amplification circuit and is made up of charge amplifier, it is achieved with the impedance matching of ultrasonic reception transducer; Ultrasound wave receives signal amplification circuit and is made up of two-stage inverting amplifier, it is achieved the amplification to Weak Ultrasonic echo voltage signal; Ultrasound wave receives detecting circuit and is made up of diode peak envelope detection circuit, it is achieved the envelope detection to high-frequency input voltage signal; Ultrasound wave receives comparison circuit and is compared by the reference voltage that the voltage signal after envelope detection circuit detection and system are arranged, according to comparative result output digit signals, and by export the inverted device of signal reversely after give the external interrupt control mouth of single-chip microcomputer, external interrupt control mouth is set to saltus step to be triggered, after external interrupt control mouth receives effective trailing edge, single-chip microcomputer produces to interrupt, the timer value of record current time, and after singlechip interruption three times, intervalometer stops timing; SCM peripheral circuit is made up of crystal oscillating circuit, reset circuit, liquid crystal display circuit, collectively forms the core control portions of dynamic liquid level detection.
Further, the error function of the mathematical model of the neutral net that said system loads is:
E = 1 2 N Σ t = 1 N ( y ( t ) - y d ( t ) ) 2
Wherein, N is number of training, and y (t) exports for t BP neutral net, ydT () is t desired output;
During by BP Algorithm for Training neutral net, adjusting the connection weights of network, its adjustment expression formula is:
w ( t + 1 ) = w ( t ) + η ∂ E ( t ) ∂ w ( t )
Wherein, the connection weights of the neutral net that w (t) is t, w (t+1) is the connection weights of (t+1) moment neutral net, and E (t) is the mean square error of t neutral net, and η is learning rate.
Further, said system adopts three ultrasonic sensor composition array structures, synchronization motivationtheory emission pulse ultrasonic, utilizes the Delay of the window interior echo signal envelope extraction instantaneous liquid level pip received during fixed length.
Further, in said system, single-chip microcomputer is AT89S52 single-chip microcomputer.
Two technical schemes of summary, a kind of ultrasound wave dynamic liquid level detection method based on neutral net of present invention proposition and system, it is possible to achieve dynamically detect liquid level.
Accompanying drawing explanation
Fig. 1 is that in the embodiment of the present invention, ultrasonic sensor is structured the formation schematic diagram;
Fig. 2 is detection method principle schematic in the embodiment of the present invention;
Fig. 3 is one group of sonac echo-signal in the embodiment of the present invention;
Fig. 4 is training error curve in the embodiment of the present invention;
Fig. 5 is the testing result of neutral net in the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with accompanying drawing, technical scheme is described in detail:
First, introducing BP neutral net, BP neutral net is also called error backward propagation method, and in BP network, signal is propagated forward, and error is back propagation. In propagated forward process, input signal, through input layer, hidden layer, successively processes, and is transmitted to output layer. If signal can not obtain desired output at output layer, then proceed to back-propagation process, error amount is successively reversely transmitted, and revise each layer connection weights. For one group of given training sample, constantly with a pattern drill network, repeat propagated forward and error back propagation process, till network output error is less than set-point. BP algorithm changes weights and deviation along the opposite direction of gradient. Definition error function is:
E = 1 2 N Σ t = 1 N ( y ( t ) - y d ( t ) ) 2
Wherein, N is number of training, and y (t) exports for t BP neutral net, ydT () is t desired output.
During with BP Algorithm for Training network, adjusting the connection weights of network, its adjustment expression formula is:
w ( t + 1 ) = w ( t ) + η ∂ E ( t ) ∂ w ( t )
Wherein, the connection weights of the neutral net that w (t) is t, w (t+1) is the connection weights of (t+1) moment neutral net, and E (t) is the mean square error of t neutral net, η learning rate.
The BP algorithm of error-duration model is a relatively simple and practical learning algorithm, and it is relatively slow that the BP algorithm of standard generally learns convergence rate, and is easily trapped into Local Minimum.
The ultrasound wave dynamic liquid level detection method of the present invention is described below, as it is shown in figure 1, the present invention proposes a kind of ultrasound wave dynamic liquid level detection method based on neutral net, including:
Dynamic liquid level is monitored by the array adopting three sonac compositions in the embodiment of the present invention, and sensor array is laid as shown in Figure 1. Wherein O is container bottom center, and A, B, C are the probe of three ultrasonic sensors, and a, b, c are and the liquid level pip corresponding to ultrasonic sensor A, B, C.
The system of the ultrasound wave dynamic liquid level detection in the invention process is as in figure 2 it is shown, include single-chip microcomputer, modulate circuit and three ultrasonic sensors A, B, C. Wherein single-chip microcomputer can be AT89S52 single-chip microcomputer, is used for controlling and process the detection of ultrasound wave dynamic liquid level. Modulate circuit includes ultrasonic emitting circuit, ultrasound wave receives pre-amplification circuit, ultrasound wave receives signal amplification circuit, ultrasound wave receives detecting circuit, ultrasound wave receives comparison circuit and SCM peripheral circuit six part composition, concrete: ultrasonic emitting circuit is used for producing pulse ultrasonic wave, realized three roads by Single-chip Controlling and launch signal simultaneously, produce the high-voltage pulse close with ultrasonic sensor probe frequency, excitation sonac emission pulse ultrasonic simultaneously; Ultrasound wave receives pre-amplification circuit and is made up of charge amplifier, it is achieved with the impedance matching of ultrasonic reception transducer; Ultrasound wave receives signal amplification circuit and is made up of two-stage inverting amplifier, it is achieved the amplification to Weak Ultrasonic echo-signal; Ultrasound wave receives detecting circuit and is made up of diode peak envelope detection circuit, it is achieved the envelope detection to high-frequency input signal; Ultrasound wave receives comparison circuit and is compared by the reference voltage that the pulse signal after envelope detection circuit detection and system are arranged, comparator by output digit signals 1 or 0, the output inverted device of signal of comparator reversely after give the external interrupt control mouth P3.2 of single-chip microcomputer; SCM peripheral circuit is made up of crystal oscillating circuit, reset circuit, liquid crystal display circuit, collectively forms the core control portions of dynamic liquid level detection.
The above-mentioned ultrasound wave dynamic liquid level detection method principle based on neutral net is as follows: during detection, three ultrasonic sensor A, B, C is emission pulse ultrasonic simultaneously, but the liquid level corresponding due to the probe of three ultrasonic sensors is different, so, the echo moment that each sonac receives is also different, the acoustic signals time used back and forth obtaining these three probe can be calculated respectively according to the echo-signal that each ultrasonic sensor receives, then the liquid level that the probe obtaining each ultrasonic sensor is corresponding is calculated, and choose these three probe from liquid level liquid level meansigma methods with rock gradient as characteristic parameter, in order to train BP neutral net, obtain the mathematical model of dynamic liquid level, then this model is applied in the monitoring of Real-time and Dynamic liquid level. owing to three probes are respectively arranged in container bottom center for three quadrants of initial point, no matter how liquid rocks, and the liquid level of three probe measurements always has a maximum and a minima, and the difference of maxima and minima namely can determine that liquid rock gradient.
It is as follows that the concrete ultrasound wave dynamic liquid level based on neutral net detects process:
Step 1: single-chip microcomputer utilizes ultrasonic emitting circuit to send control signal to three ultrasonic sensors, starts intervalometer simultaneously and starts timing and excitation three tunnel ultrasonic emitting circuit generation pulse ultrasonic wave;
Step 2: ultrasound wave meets liquid level back reflection, after three ultrasonic sensors are respectively received the echo-signal after reflection, and echo-signal is converted into voltage signal, and this voltage signal is sent to pre-amplification circuit;
Step 3: after pre-amplification circuit have received voltage signal, the voltage signal after pre-amplification circuit amplifies is sent to ultrasound wave and receives detecting circuit, it is achieved the envelope detection to high-frequency input signal;
Step 4: the voltage signal after envelope detection circuit detection is sent to reception comparison circuit, receive comparison circuit to be compared by the reference voltage that the voltage signal after envelope detection circuit detection and system are arranged, according to comparative result output digit signals, and by export the inverted device of signal reversely after give the external interrupt control mouth of single-chip microcomputer, external interrupt control mouth is set to saltus step to be triggered, after external interrupt control mouth receives effective trailing edge, single-chip microcomputer produces to interrupt, the timer value of record current time, after singlechip interruption three times, intervalometer stops timing;
Step 5: by calculating the meansigma methods of the timer value of three records and rocking gradient, wherein rock the difference of maxima and minima when gradient is record for three times, using meansigma methods with rock gradient as the input parameter needed for neutral net, the two parameter is sent to the neutral net mathematical model trained, and obtaining the output valve through neutral net, output valve is the level value of current time. Then constantly circulating said process, system just can realize sloshing fluid is monitored real-time dynamicly. Native system also can realize the monitoring to static liquid level. It is little that static liquid rocks gradient, is close to zero, and now takes 3 meansigma methodss measured as static liquid place value.
In the specific embodiment of the invention, it is preferred that ultrasonic sensor all adopts transmitting-receiving integrated, frequency probe is 1MHz. In laboratory conditions, with Fluid Dynamics liquid the rocking in transportation in hand wobble iron flask, Fig. 3 is different echo-signals during three the ultrasound probes measurement sloshing fluid recorded in experiment, the echo-signal that wherein (a) and (b), (c) respectively sensors A, B, C record. During enforcement, 100 groups of data liquid level recorded from 2cm to 50cm, as training sample, extract ten groups of data as test sample within the scope of this.
BP neutral net in the embodiment of the present invention has two input parameters, an output parameter, then the input layer of BP network is set to 2 neurons, and hidden layer is set to one layer, and output layer is 1 neuron. The mean square error of neutral net is set as 1 × 10 during enforcement-5, learning rate is 0.05, and maximum train epochs is 500. Known by experiment when hidden layer neuron number is 8, frequency of training is minimum, therefore, selects the network of 2 × 8 × 1 to be trained. The transmission function of network hidden layer is tansig, and output layer is purelin. For enabling the network to Fast Convergent, adopt the learning algorithm of Levenberg-Marquardt. As shown in Figure 4, network is after 90 times are trained, and the mean square error of network meets design requirement, network deconditioning.
Testing sample by 10 groups and input the BP neutral net trained, test result is as shown in Figure 5. As shown in Figure 5, the overall relative error of test sample is less, and the accuracy of network output is higher, and output result is stable. Although needing the regular hour during network training, but network training good after, during practical application, required time is extremely short, and system can realize dynamic liquid level is monitored completely.

Claims (7)

1. the ultrasound wave dynamic liquid level detection method based on neutral net, it is characterised in that including:
Step 1: single-chip microcomputer utilizes ultrasonic emitting circuit to send control signal to three ultrasonic sensors, starts intervalometer simultaneously and starts timing and excitation three tunnel ultrasonic emitting circuit generation pulse ultrasonic wave;
Step 2: ultrasound wave meets liquid level back reflection, after three ultrasonic sensors are respectively received the echo-signal after reflection, and echo-signal is converted into voltage signal, and this voltage signal is sent to pre-amplification circuit;
Step 3: after pre-amplification circuit have received voltage signal, the voltage signal after pre-amplification circuit amplifies is sent to ultrasound wave and receives detecting circuit, it is achieved the envelope detection to high-frequency input signal;
Step 4: the voltage signal after envelope detection circuit detection is sent to reception comparison circuit, receive comparison circuit to be compared by the reference voltage that the voltage signal after envelope detection circuit detection and system are arranged, according to comparative result output digit signals, and by export the inverted device of signal reversely after give the external interrupt control mouth of single-chip microcomputer, external interrupt control mouth is set to saltus step to be triggered, after external interrupt control mouth receives effective trailing edge, single-chip microcomputer produces to interrupt, the timer value of record current time, after singlechip interruption three times, intervalometer stops timing;
Step 5: by calculating the meansigma methods of the timer value of three records and rocking gradient, wherein rock the difference of liquid level maxima and minima when gradient is record for three times, using meansigma methods with rock gradient as the input parameter needed for neutral net, the two parameter is sent to the neutral net mathematical model trained, and obtaining the output valve through neutral net, output valve is the level value of current time.
2. method as claimed in claim 1, it is characterised in that the error function of the mathematical model of neutral net is:
Wherein, N is number of training, and y (t) exports for t BP neutral net, ydT () is t desired output; During by BP Algorithm for Training neutral net, adjusting the connection weights of network, its adjustment expression formula is:
Wherein, the connection weights of the neutral net that w (t) is t, w (t+1) is the connection weights of t+1 moment neutral net, and E (t) is the mean square error of t neutral net, and η is learning rate.
3. method as claimed in claim 1, it is characterised in that adopt three ultrasonic sensor composition array structures, synchronization motivationtheory emission pulse ultrasonic, utilizes the Delay of the window interior echo signal envelope extraction instantaneous liquid level pip received during fixed length.
4. the ultrasound wave dynamic fluid flow position detecting system based on neutral net, it is characterised in that including: single-chip microcomputer, modulate circuit and three ultrasonic sensors;
Wherein, single-chip microcomputer is for loading the mathematical model of neutral net, and the mathematical model based on neutral net controls and processes the detection of ultrasound wave dynamic liquid level; Modulate circuit includes ultrasonic emitting circuit, ultrasound wave receives pre-amplification circuit, ultrasound wave receives signal amplification circuit, ultrasound wave receives detecting circuit, ultrasound wave receives comparison circuit and SCM peripheral circuit six part composition, ultrasonic emitting circuit is used for producing pulse ultrasonic wave, realized three roads by Single-chip Controlling and launch signal simultaneously, produce the high-voltage pulse close with ultrasonic sensor probe frequency, excitation sonac emission pulse ultrasonic simultaneously; Ultrasound wave receives pre-amplification circuit and is made up of charge amplifier, it is achieved with the impedance matching of ultrasonic reception transducer; Ultrasound wave receives signal amplification circuit and is made up of two-stage inverting amplifier, it is achieved the amplification to Weak Ultrasonic echo voltage signal; Ultrasound wave receives detecting circuit and is made up of diode peak envelope detection circuit, it is achieved the envelope detection to high-frequency input voltage signal; Ultrasound wave receives comparison circuit and is compared by the reference voltage that the voltage signal after envelope detection circuit detection and system are arranged, according to comparative result output digit signals, and by export the inverted device of signal reversely after give the external interrupt control mouth of single-chip microcomputer, external interrupt control mouth is set to saltus step to be triggered, after external interrupt control mouth receives effective trailing edge, single-chip microcomputer produces to interrupt, the timer value of record current time, and after singlechip interruption three times, intervalometer stops timing; SCM peripheral circuit is made up of crystal oscillating circuit, reset circuit, liquid crystal display circuit, collectively forms the core control portions of dynamic liquid level detection.
5. system as claimed in claim 4, it is characterised in that the error function of the mathematical model of neutral net is:
Wherein, N is number of training, and y (t) exports for t BP neutral net, ydT () is t desired output;
During by BP Algorithm for Training neutral net, adjusting the connection weights of network, its adjustment expression formula is:
Wherein, the connection weights of the neutral net that w (t) is t, w (t+1) is the connection weights of t+1 moment neutral net, and E (t) is the mean square error of t neutral net, and η is learning rate.
6. system as claimed in claim 4, it is characterised in that adopt three ultrasonic sensor composition array structures, synchronization motivationtheory emission pulse ultrasonic, utilizes the Delay of the window interior echo signal envelope extraction instantaneous liquid level pip received during fixed length.
7. system as claimed in claim 4, it is characterised in that single-chip microcomputer is AT89S52 single-chip microcomputer.
CN201310401468.7A 2013-09-05 2013-09-05 A kind of ultrasound wave dynamic liquid level detection method based on neutral net and system Expired - Fee Related CN103499374B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310401468.7A CN103499374B (en) 2013-09-05 2013-09-05 A kind of ultrasound wave dynamic liquid level detection method based on neutral net and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310401468.7A CN103499374B (en) 2013-09-05 2013-09-05 A kind of ultrasound wave dynamic liquid level detection method based on neutral net and system

Publications (2)

Publication Number Publication Date
CN103499374A CN103499374A (en) 2014-01-08
CN103499374B true CN103499374B (en) 2016-06-15

Family

ID=49864605

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310401468.7A Expired - Fee Related CN103499374B (en) 2013-09-05 2013-09-05 A kind of ultrasound wave dynamic liquid level detection method based on neutral net and system

Country Status (1)

Country Link
CN (1) CN103499374B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102023106819A1 (en) 2023-03-17 2024-09-19 Endress+Hauser SE+Co. KG Determination of filling material properties

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104149720B (en) * 2014-09-01 2016-03-09 江苏大学 Vehicle liquid level accurate measurements under a kind of complex working condition and response at different level method
CN105241524B (en) * 2015-10-26 2018-03-20 河海大学常州校区 A kind of city flood warning system and method based on radial basis function neural network model
CN106992819B (en) * 2017-04-10 2022-12-16 杭州戬威科技有限公司 Ultrasonic signal excitation, control, reception, conditioning and communication system
CN107506798B (en) * 2017-08-31 2020-07-10 四创科技有限公司 Water level monitoring method based on image recognition
CN107796488B (en) * 2017-11-16 2019-12-24 西安交通大学 Liquid level shaking experiment table based on motion platform and ultrasonic liquid level sensor
CN113325273A (en) * 2020-02-28 2021-08-31 西门子股份公司 Arc fault detection method and device
CN111351518A (en) * 2020-03-17 2020-06-30 交通运输部公路科学研究所 Intelligent sensing equipment and method for safety of highway bridge structure
CN111580570B (en) * 2020-05-28 2023-03-17 爱瑟福信息科技(上海)有限公司 Container liquid level monitoring method and system
CN111982207A (en) * 2020-09-17 2020-11-24 西安多普多信息科技有限公司 Tank car liquid temperature sensor based on artificial neural network algorithm and method thereof
CN112325981B (en) * 2020-11-03 2023-12-26 常州市鼎兴电子有限公司 Optimal matching parameter design method for inductive liquid level sensor
CN113566929A (en) * 2021-09-27 2021-10-29 山东西王食品有限公司 Oil tank liquid level ultrasonic measurement method, system, terminal and storage medium based on LSTM
CN115122642B (en) * 2022-05-31 2024-11-01 深圳市纵维立方科技有限公司 Fault detection method in 3D printing, 3D printer and equipment

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE4014990A1 (en) * 1990-05-10 1991-11-14 Herbert Prof Dr Zott Liquid lever measurement arrangement - uses ultrasonic pulse reflection from surface and transition time measurement for use with moving or static liquid e.g. in vehicle fuel tank
CN1441896A (en) * 2000-07-13 2003-09-10 西蒙兹精密产品公司 Liquid gauging apparatus using time delay neural network
CN1761859A (en) * 2003-01-28 2006-04-19 波音公司 Ultrasonic fuel-gauging system
CN101246034A (en) * 2008-03-07 2008-08-20 厦门大学 Acoustic liquid level alarm of liquid reservoir

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE4014990A1 (en) * 1990-05-10 1991-11-14 Herbert Prof Dr Zott Liquid lever measurement arrangement - uses ultrasonic pulse reflection from surface and transition time measurement for use with moving or static liquid e.g. in vehicle fuel tank
CN1441896A (en) * 2000-07-13 2003-09-10 西蒙兹精密产品公司 Liquid gauging apparatus using time delay neural network
CN1761859A (en) * 2003-01-28 2006-04-19 波音公司 Ultrasonic fuel-gauging system
CN101246034A (en) * 2008-03-07 2008-08-20 厦门大学 Acoustic liquid level alarm of liquid reservoir

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于ARM的油罐车油位测量系统的设计与研究;杨洪军;《中国优秀硕士学位论文全文数据库 工程科技I辑》;20120115;全文 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102023106819A1 (en) 2023-03-17 2024-09-19 Endress+Hauser SE+Co. KG Determination of filling material properties

Also Published As

Publication number Publication date
CN103499374A (en) 2014-01-08

Similar Documents

Publication Publication Date Title
CN103499374B (en) A kind of ultrasound wave dynamic liquid level detection method based on neutral net and system
CN105300508B (en) The dual threshold detection circuit and detection method of a kind of transit-time of ultrasonic
CN101173986B (en) Ultrasonic distance measuring apparatus without blind zone
CN102636252B (en) Method and device for detecting precise arrival moment of ultrasonic wave
CN104374447B (en) Guided wave formula radar levelmeter echo signal processing method based on first derivative and combination reference curve
CN104198674B (en) Pipeline gas gas hydrate synthesis on-line early warning device and method
CN103591975B (en) A kind of ultrasonic sensor index detection method and device
CN102589627B (en) Absolute propagation time measuring method for ultrasonic flow meter
CN104142195A (en) Device and method for detecting interior initial stress of steel structural member based on ultrasonic method
CN103674181A (en) Dynamic liquid level ultrasonic detection device and method
CN109579950A (en) A kind of mistake proofing wave detection device of Ultrasonic Wave Flowmeter
CN102338776A (en) Method for measuring propagation time of stress wave in wood and nondestructive test system
CN104142326A (en) Attenuation coefficient detection method
CN102841343A (en) Echo sounding apparatus calibration system based on industrial computer and calibration method
CN203148479U (en) Ultrasonic flow measuring device
CN114878684A (en) Steel pipe concrete arch rib compactness detection method based on piezoelectric ceramic ultrasound
CN103869096B (en) Ultrasonic anemoscope range broadening method
CN104913873A (en) Multi-factor influence-improved ultrasonic hydraulic measurement method and system
CN100451573C (en) Measuring circuit for measuring supersonic wave level meter transit time
CN101936953B (en) Pipeline delay-based system and method for measuring concentrations of components of fruit juice sugar
CN103630288A (en) Ultrasonic recycling triggered pressure measuring device and method
CN105467395A (en) Super-remote-distance ultrasonic measuring instrument
CN104897249B (en) A kind of measuring ultrasonic wave flow experimental rig and measuring method
CN105043647B (en) Fluid pressure monitoring system in a kind of closed container
CN106908180A (en) Oil-gas pipeline is in uniaxial stress ultrasonic device for measuring

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20160615

Termination date: 20170905