CN108120651B - Automatic detection device of rut tester and control method - Google Patents
Automatic detection device of rut tester and control method Download PDFInfo
- Publication number
- CN108120651B CN108120651B CN201711281314.3A CN201711281314A CN108120651B CN 108120651 B CN108120651 B CN 108120651B CN 201711281314 A CN201711281314 A CN 201711281314A CN 108120651 B CN108120651 B CN 108120651B
- Authority
- CN
- China
- Prior art keywords
- test
- base
- groove
- displacement
- test wheel
- 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
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title abstract description 17
- 238000012360 testing method Methods 0.000 claims abstract description 135
- 238000006073 displacement reaction Methods 0.000 claims abstract description 49
- 239000003638 chemical reducing agent Substances 0.000 claims abstract description 20
- 230000008859 change Effects 0.000 claims description 16
- 230000033001 locomotion Effects 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 10
- 239000003990 capacitor Substances 0.000 claims description 6
- 230000006698 induction Effects 0.000 claims description 6
- 238000009413 insulation Methods 0.000 claims description 2
- 230000002093 peripheral effect Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 230000008878 coupling Effects 0.000 claims 1
- 238000010168 coupling process Methods 0.000 claims 1
- 238000005859 coupling reaction Methods 0.000 claims 1
- 238000013528 artificial neural network Methods 0.000 abstract description 17
- 238000005070 sampling Methods 0.000 description 18
- 238000012549 training Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000005259 measurement Methods 0.000 description 5
- 230000033228 biological regulation Effects 0.000 description 4
- 239000010426 asphalt Substances 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 239000000523 sample Substances 0.000 description 3
- 230000001276 controlling effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- BASFCYQUMIYNBI-UHFFFAOYSA-N platinum Chemical compound [Pt] BASFCYQUMIYNBI-UHFFFAOYSA-N 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 244000261422 Lysimachia clethroides Species 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013101 initial test Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 229910052697 platinum Inorganic materials 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/62—Manufacturing, calibrating, or repairing devices used in investigations covered by the preceding subgroups
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)
- Force Measurement Appropriate To Specific Purposes (AREA)
Abstract
The invention discloses an automatic detection device of a rut tester, which comprises a square base, wherein the upper surface of the square base is coaxially provided with a columnar groove, and a plurality of columnar guide pillars are uniformly arranged in the groove close to the circumference; the worm gear reducer is fixedly arranged in the middle of the groove, and an encoder is arranged in the center of the upper surface of the worm gear reducer; the hollow disc-shaped supporting part is provided with a columnar through hole matched with the guide pillar, is coaxial with the base and is sleeved on the guide pillar in a vertically movable manner; the butterfly force value sensor is fixedly arranged above the encoder through a threaded sleeve; and the lower ends of the linear temperature and humidity sensors are internally arranged at four opposite angles of the base. The invention also provides a control method for the automatic detection of the rut tester, and the test wheel displacement and the detection circuit voltage are adjusted based on the BP neural network during the automatic detection of the rut tester. The invention realizes integrated automatic detection; meanwhile, the accuracy of the test system in the same test environment is improved.
Description
Technical Field
The invention relates to the field of rut tests, in particular to an automatic detection device of a rut tester.
Background
The rut tester is mainly used for testing the high-temperature rut resistance of the asphalt mixture and can also be used for auxiliary test of the proportioning design of the asphalt mixture. The rut tester is the most ideal simulator for road compaction. The characteristics of the prepared sample are very similar to those of a compacted road layer, and the prepared sample can also be directly used for a rutting test. The rut tester is widely applied to road construction and laboratory detection.
In recent years, China vigorously builds traffic infrastructure and increases the investment of the traffic infrastructure. The space of the road construction market in China is still larger in the coming years, particularly, the road construction investment in western regions is increased more quickly, and the space of the market is also larger. In order to ensure the road quality, the rut tester is inevitably applied in a large quantity, so the invention of the automatic detection device of the rut tester further provides guarantee for the road quality safety and fills the domestic blank.
At present, each third-party detection mechanism detects the rut tester in different items, and multiple measuring devices are used for detecting one by one, so that resources and time are wasted, most of universal detection instruments cannot meet the requirements of the environment and space on site (for example, force values measured by universal force sensors are restricted by space, a fixing mode, temperature and humidity, and the like, while balance weights are directly weighed by using electronic scales, force value changes caused by friction and coaxiality errors generated by a connecting guide mechanism are ignored), and the real and effective test state under the comprehensive action cannot be reflected by the item detection, and meanwhile, uncertainty of the measurement results is increased due to multiple instruments and multiple detection personnel.
Therefore, it is becoming more and more important to design an integrated automatic detection device to greatly improve the detection accuracy.
Disclosure of Invention
The invention provides an automatic detection device of a rut tester, which solves the problem of sectional testing and realizes integrated automatic detection to overcome the defects of the prior art;
it is another object of the present invention to improve the accuracy of testing under different testing environments.
The technical scheme provided by the invention is as follows: the utility model provides a rut tester automatic checkout device, includes:
the square base is coaxially provided with a columnar groove on the upper surface, and a plurality of columnar guide pillars are uniformly arranged in the groove close to the circumference;
the worm gear reducer is fixedly arranged in the middle of the groove, and an encoder is arranged in the center of the upper surface of the worm gear reducer;
the hollow disc-shaped supporting part is provided with a columnar through hole matched with the guide pillar, is coaxial with the base and is sleeved on the guide pillar in a vertically movable manner;
the butterfly force value sensor is fixedly arranged above the encoder through a threaded sleeve and is used for testing the pressure of the test wheel;
and the lower ends of the linear temperature and humidity sensors are internally arranged at four opposite angles of the base.
Preferably, the method further comprises the following steps:
and the columnar planetary gear speed reducing motor is fixedly arranged at the bottom of the groove of the base through a bolt and is fixedly arranged on one side surface of the worm gear speed reducer through a coupler.
Preferably, the worm gear reducer is quadrangular prism-shaped, a cylindrical boss is arranged in the center of the upper surface of the worm gear reducer, and the diagonal length of the worm gear reducer is smaller than that of the support component.
Preferably, a circular through hole is formed in the center of the encoder, and the circular through hole is sleeved on the boss.
Preferably, the controller is fixed at the bottom of the base groove through bolts.
Preferably, the controller is internally provided with an integrated force detection unit, a temperature detection unit, a displacement control unit and a Bluetooth transmission unit, and the integrated force detection unit, the temperature detection unit, the displacement control unit and the Bluetooth transmission unit are used for respectively testing a transmission force value, a temperature and a displacement.
Preferably, an outer diameter of the support member is smaller than a radius of the groove, and an inner diameter of the support member is larger than an outer diameter of the force value sensor.
Preferably, the friction force sensor is arranged on the surface of the pressure plate and used for testing the friction force between the test wheel and the surface of the pressure plate;
the speed sensor is arranged on the surface of the pressure plate and used for measuring the movement rate of the test wheel;
the test wheel controller is arranged at the axle center of the test wheel and is used for controlling the test displacement of the test wheel;
the controller, it passes through the bolt fastening and is in base recess bottom, inside integrated power detecting element, temperature detecting element, displacement control unit and the bluetooth transmission unit of being equipped with of controller, and connect friction force sensor, speedtransmitter, pressure sensor, detection circuitry, examination wheel controller for receive the detection data of sensor and examination wheel controller, control detection circuitry, motor and examination wheel displacement volume.
Preferably, the control method for the automatic detection of the rut tester is characterized in that when the rut tester is automatically detected, the test wheel displacement and the detection circuit voltage are adjusted based on a BP neural network, and the control method comprises the following steps:
step one, acquiring temperature T, humidity H, pressure P of a test wheel, surface friction force f of the test wheel and a pressing plate and initial motion speed V of the test wheel through a sensor according to a sampling period;
step two, normalizing the temperature T, the humidity H, the grounding pressure P of the test wheel, the friction force f between the test wheel and the surface of the pressing plate and the initial movement rate V of the test wheel in sequence, and determining the input layer vector x ═ x { of the three layers of BP neural networks1,x2,x3,x4,x5}; wherein x is1Is a temperature coefficient, x2Is the coefficient of humidity, x3For the test wheel pressure coefficient, x4Is the friction coefficient of the surface of the test wheel and the pressure plate, x5The initial rate coefficient of the test wheel movement is obtained;
step three, the input layer vector is mapped to a middle layer, and the middle layer vector y is { y ═ y1,y2,…,ym}; m is the number of intermediate layer nodes;
step four, obtaining an output layer vector z ═ z1,z2}; wherein z is1Adjustment coefficient for test wheel travel displacement, z2For detecting the voltage regulation factor of the circuit, so that
si+1=z1 ismax,
Ei+1=z2 iEmax,
Wherein z is1 i、z2 iOutput layer vector parameters, s, for the ith sampling periodmax、EmaxThe maximum displacement of the test wheel and the maximum voltage of the detection circuit are set respectively; and
in the second step, the temperature T, the humidity H, the grounding pressure P of the test wheel, the surface friction force f of the test wheel and the pressing plate and the initial movement rate V of the test wheel are normalized and formulated in sequence as follows:
wherein x isjFor parameters in the input layer vector, XjMeasurement parameters T, H, P, f, V, j are 1,2,3,4,5, respectively; xjmaxAnd XjminRespectively, a maximum value and a minimum value in the corresponding measured parameter.
Preferably, in the first step, in the initial operating state, the test wheel test displacement and the detection circuit voltage satisfy an empirical value:
s0=0.87smax,
E0=0.88Emax,
wherein s is0、E0Respectively setting the initial test displacement of the test wheel and the initial voltage of the detection circuit; smax、EmaxRespectively the set maximum test displacement of the test wheel and the maximum voltage of the detection circuit
The invention has the following beneficial effects: 1) the capacitance type displacement sensor has the characteristics of no friction, no abrasion and no inertia, and has the advantages of large signal-to-noise ratio, high sensitivity, small zero drift, wide frequency response, small nonlinearity, good precision stability, strong anti-electromagnetic interference capability, convenient use and operation and the like; 2) compared with the defect that the prior art cannot acquire a plurality of measurement indexes in real time, the method can truly reflect the test result in the test state; 3) the measurement activity is simplified, and the mutual influence among equipment, multiple readings and extra uncertainty generated by an operator caused by carrying multiple measurement equipment at one time are avoided; 4) according to different installation test environments, the displacement of the test wheel and the voltage of the test circuit are adjusted during testing, so that the influence of the test conditions on the test precision is reduced.
Drawings
Fig. 1 is a schematic view of an automatic testing apparatus of a rut tester according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of an automatic testing apparatus of a rut tester according to an embodiment of the present invention.
Fig. 3 is a side view of an automatic testing apparatus of a rut tester according to an embodiment of the present invention.
Fig. 4 is a horizontal sectional view of an automatic testing apparatus of a rut tester according to an embodiment of the present invention.
Fig. 5 is a vertical sectional view of an automatic testing apparatus of a rut tester according to an embodiment of the present invention.
Fig. 6 is a schematic workflow diagram of an embodiment of the present invention.
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
As shown in fig. 1 to 3, in the present embodiment, the rut tester apparatus includes a square base 1, wherein the upper surface of the square base 1 is provided with coaxial cylindrical grooves, and four opposite corners of the upper surface are respectively provided with four cylindrical small grooves. A plurality of cylindrical guide posts 14 are uniformly arranged in the groove of the base 1 along the circumference, and a quadrangular-prism-shaped worm gear reducer 13 is coaxially fixed at the center of the bottom of the cylindrical groove of the base 1 through a plurality of bolts 12. The planetary gear motor 2 is fixed at the bottom of a groove at one side of the worm gear reducer 13 through a bolt 12 and is connected with the planetary gear motor 2 through a coupler 3. The controller 4 is fixed at the bottom of the groove at the other side of the worm gear reducer 13 through a bolt 12.
The disc-shaped inner support part 7 is provided with a columnar through hole matched with the columnar guide post 14, can be movably sleeved on the guide post 14 up and down, and is coaxial with the axis of the base. And the inner diameter of the inner support member 7 is larger than the diagonal length of the worm gear reducer 13, so that the up-and-down movement of the worm gear reducer 13 in the inner support member 7 is not influenced. The center of the upper surface of the worm gear reducer 13 is provided with a cylindrical bulge, the bulge is sleeved with an encoder 5, and the encoder can convert displacement signals into electric signals. The butterfly force value sensor 8 is in transmission connection with the encoder 5 through the thread bush 6. And the diameter of the force value sensor 8 is smaller than the inner diameter of the inner support part 7, the force value sensor 8 can move up and down without limitation. And a pressure plate 9 is coaxially arranged above the butterfly force value sensor 8, and the upper part of the butterfly force value sensor bears a load 0 for testing.
The lower ends of the four temperature and humidity sensors 11 are cylinders which can be inserted into four small grooves of the base 1. The signal line of the temperature and humidity sensor 11 is outside, and the outside is covered with the gooseneck, and can be randomly arranged in space. The temperature and humidity sensor probe 10 adopts a four-wire A-level Pt100 platinum resistance temperature and humidity sensor. The controller 4 inside the base 1 is equipped with integrated power detecting element of controller, temperature detecting element, displacement control unit and bluetooth transmission unit. The integrated force detection unit inside the controller 4 is in transmission connection with the force value sensor 8, the temperature detection unit is in transmission connection with the four temperature and humidity sensors 11, and the detection circuit inside the displacement control unit can detect the change of capacitance, so that the capacitance is converted into an electric signal (change of frequency) to measure displacement.
The inner support part 7 is driven by the planetary gear motor 2 to move up and down through the guide post 14, the inner side surface A of the base 1 and the outer peripheral side surface B of the inner support part 7 are used as two stages of capacitors, insulation processing is carried out, the inner support part 7 moves up and down to cause the change of the induction area between the surface B of the inner support part 7 and the surface A of the base 1, the change of the capacitors is caused by the change of the induction area S, and then the change of the capacitors is converted into electric signals (the change of frequency) through the detection circuit to measure displacement.
As shown in fig. 6, when the automatic detection device of the rut tester starts to work, the temperature, the force value and the displacement can be respectively obtained through the temperature and humidity sensor, the force value sensor and the displacement sensor, and the data is collected and then processed, stored and printed to obtain the final required data result. And three data are tested and collected simultaneously, so that the efficiency and the accuracy are improved.
In the specific embodiment, during detection, the calibrating device is fixed on a test bed through a clamp, the rut tester calibrating device is moved to the test bed of the rut testing machine at the beginning of the test, the test wheel is arranged at the central part of the rut tester calibrating device, the rut deformation automatic recorder is started, then the test instrument is started, the test wheel travels back and forth on the upper surface of the pressing plate 9, the vertical acting force is arranged on the force value sensor 8, the force value applied by the test wheel is recorded, the planetary gear motor 2 drives the inner support component 7, the force value sensor 8 and the pressing plate 9 to move downwards, the induction area between the surface B of the component 7 and the surface A of the component 1 is changed, the change of the capacitance is caused by the change of the induction area S, and the change of the capacitance is converted into an electric signal (the change of the frequency) through the detection circuit to measure the displacement of. The temperature and humidity sensor measures the temperature change in the test process in real time. The test was ended when the displacement reached 25mm, the time being about 30 min. In the test process, the rut tester and the rut tester calibration device simultaneously record test data. And finally comparing the test data of the two to obtain the data of the deviation and the like of the rut tester.
The rut tester calibrating device simulates an asphalt test block to test and simultaneously detects and records temperature, force value and displacement parameters.
In this embodiment, the method further includes: the pressure sensor is arranged on the test bed and used for detecting the grounding pressure of the test wheel; the friction force sensor is arranged on the surface of the pressure plate and used for testing the friction force between the test wheel and the surface of the pressure plate; the speed sensor is arranged on the surface of the pressure plate and used for measuring the movement rate of the test wheel; the test wheel controller is arranged at the axle center of the test wheel and is used for controlling the test displacement of the test wheel;
the controller, it passes through the bolt fastening and is in base recess bottom, inside integrated power detecting element, temperature detecting element, displacement control unit and the bluetooth transmission unit of being equipped with of controller, and connect friction force sensor, speedtransmitter, pressure sensor, detection circuitry, examination wheel controller for receive the detection data of sensor and examination wheel controller, control detection circuitry, motor and examination wheel displacement volume.
The invention also provides a control method for the automatic detection of the rut tester, which adjusts the displacement of the test wheel and the voltage of the detection circuit based on the BP neural network when the rut tester is automatically detected, and comprises the following steps:
step one, establishing a BP neural network model;
the BP network system structure adopted by the invention is composed of three layers, wherein the first layer is an input layer, n nodes are provided in total, n detection signals representing the working state of the equipment are correspondingly provided, and the signal parameters are provided by a data preprocessing module. The second layer is a hidden layer, and has m nodes, and is determined by the training process of the network in a self-adaptive mode. The third layer is an output layer, p nodes are provided in total, and the output is determined by the response actually needed by the system.
The mathematical model of the network is:
inputting a layer vector: x ═ x1,x2,…,xn)T
Intermediate layer vector: y ═ y1,y2,…,ym)T
Outputting a layer vector: z is (z)1,z2,…,zp)T
In the invention, the number of nodes of an input layer is 5, and the number of nodes of an output layer is p-2. The number m of hidden layer nodes is estimated by the following formula:
according to the sampling period, the input 5 parameters are: x is the number of1Is a temperature coefficient, x2Is the coefficient of humidity, x3For the test wheel pressure coefficient, x4Is the friction coefficient of the surface of the test wheel and the pressure plate, x5The initial rate coefficient of the test wheel movement is obtained;
the data acquired by the sensors belong to different physical quantities, and the dimensions of the data are different. Therefore, the data needs to be normalized to a number between 0-1 before it is input into the neural network.
Specifically, the temperature T is normalized to obtain a temperature coefficient x1:
Wherein, Delta TminAnd Δ TmaxRespectively the minimum and maximum of the height difference between the cameras.
Similarly, the humidity H is normalized to obtain a humidity coefficient x2:
Wherein HminAnd HmaxMinimum and maximum humidity during the test, respectively.
Normalizing the pressure P of the test wheel to obtain a pressure coefficient x of the test wheel3:
Wherein, PminAnd PmaxThe minimum test wheel grounding pressure and the maximum test wheel grounding pressure in the test process are respectively.
Normalizing the friction force f between the test wheel and the surface of the pressing plate to obtain the motion friction coefficient x of the test wheel4:
Normalizing the initial speed V of the test wheel movement to obtain a speed coefficient x5:
Wherein, VminAnd VmaxThe minimum initial speed and the maximum initial speed of the test wheel motion are respectively.
The 2 parameters of the output signal are respectively expressed as: z is a radical of1Adjustment factor for test wheel test displacement, z2For detecting circuitsA voltage regulation factor;
test wheel test displacement adjustment coefficient z1Expressed as the ratio of the test wheel test displacement in the next sampling period to the maximum displacement set in the current sampling period, i.e. in the ith sampling period, the test wheel test displacement is collected asOutputting a test wheel test displacement adjusting coefficient s of the ith sampling period through a BP neural network1 iThen, the test wheel test displacement in the (i + 1) th sampling period is controlled to beMake it satisfy
Voltage regulation factor z of detection circuit2Expressed as the ratio of the voltage of the detection circuit in the next sampling period to the maximum voltage set in the current sampling period, i.e. in the ith sampling period, the voltage of the detection circuit is collected asOutputting a second camera height adjusting coefficient z of the ith sampling period through a BP neural network2 iThen, the voltage of the detection circuit in the (i + 1) th sampling period is controlled to beMake it satisfy
Step two: and (5) training the BP neural network.
After the BP neural network node model is established, the training of the BP neural network can be carried out. Obtaining training samples according to empirical data of the product, and giving a connection weight w between an input node i and a hidden layer node jijConnection weight w between hidden layer node j and output layer node kjkThreshold value theta of hidden layer node jjThreshold value w of node k of output layerij、wjk、θj、θkAre all random numbers between-1 and 1.
Continuously correcting w in the training processijAnd wjkUntil the system error is less than or equal to the expected error, the training process of the neural network is completed.
As shown in table 1, a set of training samples is given, along with the values of the nodes in the training process.
TABLE 1 training Process node values
Step three, collecting data operation parameters and inputting the data operation parameters into a neural network to obtain a regulation and control coefficient;
the trained artificial neural network is solidified in the chip, so that the hardware circuit has the functions of prediction and intelligent decision making, and intelligent hardware is formed. After the intelligent hardware is powered on and started, the automatic detection system of the track tester starts to operate, the test wheel test starts to operate at the maximum displacement, and the voltage maximum value of the detection circuit, namely the test wheel test initial displacement s0=0.87smaxTesting the initial voltage E of the circuit0=0.88Emax;
At the same time, the initial temperature T is measured using a sensorOInitial humidity coefficient H0Initial pressure P of test wheel grounding0Initial friction force f of test wheel movementOInitial speed V of test wheel movementONormalizing the parameters to obtain an initial input vector of the BP neural networkObtaining an initial output vector through operation of a BP neural network
Step four: testing displacement and detecting circuit voltage by a test wheel; obtaining an initial output vectorAfter, can adjust the experimental displacement of examination wheel, detection circuitry voltage, make the height of next sampling cycle lifting device, the experimental displacement of examination wheel, the detection circuitry voltage of the device of drenching with the rain respectively be:
s1=z1 0smax
E1=z2 0Emax
obtaining the temperature T, the humidity H, the pressure P of a test wheel, the surface friction force f of the test wheel and a pressure plate and the initial movement rate V of the test wheel in the ith sampling period through a sensor, and obtaining an input vector x of the ith sampling period through normalizationi=(x1 i,x2 i,x3 i,x4 i,x5 i) Obtaining an output vector z of the ith sampling period through the operation of a BP neural networki=(z1 i,z2 i) Then, the test wheel test displacement and the detection circuit voltage are controlled and adjusted, so that the test wheel test displacement and the detection circuit voltage in the (i + 1) th sampling period are respectively as follows:
si+1=z1 ismax,
Ei+1=z2 iEmax,
through the arrangement, the temperature, the humidity, the pressure of the test wheel, the surface friction force between the test wheel and the pressing plate and the initial motion rate of the test wheel are detected in real time through the sensor, and the test displacement of the test wheel and the voltage of the detection circuit are regulated and controlled by adopting a BP neural network algorithm, so that the test wheel reaches the optimal running state, and the running efficiency is improved.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.
Claims (5)
1. The utility model provides a rut tester automatic checkout device which characterized in that includes:
the square base is coaxially provided with a columnar groove on the upper surface, and a plurality of columnar guide pillars are uniformly arranged in the groove close to the circumference;
the worm gear reducer is fixedly arranged in the middle of the groove, and an encoder is arranged in the center of the upper surface of the worm gear reducer;
the hollow disc-shaped supporting part is provided with a columnar through hole matched with the guide pillar, is coaxial with the base and is sleeved on the guide pillar in a vertically movable manner;
the butterfly force value sensor is fixedly arranged above the encoder through a threaded sleeve;
the lower ends of the linear temperature and humidity sensors are internally arranged at four opposite angles of the base;
the cylindrical planetary gear reduction motor is fixedly arranged at the bottom of the groove of the base through a bolt and is fixedly arranged on one side surface of the worm gear reducer through a coupling;
the encoder is used for converting the displacement signal into an electric signal;
the disc pressing plate is coaxially arranged above the force value sensor;
the diagonal length of the worm gear and worm reducer is smaller than the inner diameter of the supporting component;
the outer diameter of the supporting part is smaller than the radius of the groove, and the inner diameter of the supporting part is larger than the outer diameter of the force value sensor;
the inner supporting part is driven by a planetary gear motor to move up and down through a guide post, the inner side surface A of the base and the outer peripheral side surface B of the inner supporting part are used as two stages of capacitors, insulation processing is carried out, the inner supporting part moves up and down to cause the change of the induction area between the surface B of the inner supporting part and the surface A of the base, the change of the capacitors is caused by the change of the induction area S, and then the change of the capacitors is converted into electric signals through a detection circuit to measure displacement.
2. The automatic detection device of the rut tester according to claim 1, wherein the worm gear reducer is quadrangular, and a cylindrical boss is arranged in the center of the upper surface of the worm gear reducer.
3. The automatic detection device of a rut tester according to claim 2, further comprising:
the center of the encoder is provided with a circular through hole which is sleeved on the boss.
4. The automatic detection device of a rut tester according to claim 1,
and the detection circuit is arranged in the base groove and is connected with the inner side surface of the groove and the outer side surface of the supporting part.
5. The automatic detection device of the rut tester according to claim 4, further comprising:
the friction force sensor is arranged on the surface of the pressing plate and used for testing the friction force between the test wheel and the surface of the pressing plate;
the speed sensor is arranged on the surface of the pressure plate and used for measuring the movement rate of the test wheel;
the test wheel controller is arranged at the axle center of the test wheel and is used for controlling the test displacement of the test wheel;
the controller, it passes through the bolt fastening and is in base recess bottom, inside integrated power detecting element, temperature detecting element, displacement control unit and the bluetooth transmission unit of being equipped with of controller, and connect friction force sensor, speedtransmitter, power value sensor, detection circuitry, examination wheel controller are used for receiving the data of sensor and examination wheel controller, control detection circuitry, motor and examination wheel displacement volume.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711281314.3A CN108120651B (en) | 2017-12-07 | 2017-12-07 | Automatic detection device of rut tester and control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711281314.3A CN108120651B (en) | 2017-12-07 | 2017-12-07 | Automatic detection device of rut tester and control method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108120651A CN108120651A (en) | 2018-06-05 |
CN108120651B true CN108120651B (en) | 2020-05-15 |
Family
ID=62229719
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711281314.3A Expired - Fee Related CN108120651B (en) | 2017-12-07 | 2017-12-07 | Automatic detection device of rut tester and control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108120651B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111351845A (en) * | 2020-03-18 | 2020-06-30 | 南京理工大学 | Intelligent detection device based on pulse eddy current |
CN111351834A (en) * | 2020-03-18 | 2020-06-30 | 南京理工大学 | Intelligent detection device based on magnetic leakage |
CN116087007A (en) * | 2023-04-11 | 2023-05-09 | 山东路达试验仪器有限公司 | Dynamic loading tracking test system for asphalt mixture pavement molding and rutting test |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2869110Y (en) * | 2006-03-02 | 2007-02-14 | 河南省高远公路养护设备有限公司 | Hand asphalt road rut detecting instrument |
CN204988883U (en) * | 2015-09-01 | 2016-01-20 | 武汉路源工程质量检测有限公司 | Bituminous mixture wheel tracking test device |
CN105404153B (en) * | 2015-12-17 | 2017-12-08 | 吉林大学 | A kind of coil winding machine control method and coil winding machine based on BP neural network |
CN206269784U (en) * | 2016-12-20 | 2017-06-20 | 吉林大学 | Adjustable automobile rutting depth measuring instrument |
CN206609717U (en) * | 2017-04-06 | 2017-11-03 | 山东交通学院 | A kind of loading wheel rolling device |
CN107044943B (en) * | 2017-05-20 | 2020-08-11 | 浙江交科工程检测有限公司 | Contrast type automatic rut tester |
-
2017
- 2017-12-07 CN CN201711281314.3A patent/CN108120651B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN108120651A (en) | 2018-06-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108120651B (en) | Automatic detection device of rut tester and control method | |
CN105571648B (en) | A kind of multi-function robot joint Performance Test System | |
CN103837299B (en) | A kind of torque spanner automatic checkout system and detection method | |
CN103293182A (en) | Automatic heat conductivity coefficient tester through protective heat flow meter method and detection method | |
CN205403838U (en) | Multifunctional robot joint capability test system | |
CN106404160A (en) | Power transmission line monitoring device metering system and method in field environment | |
CN101666726B (en) | Piston pressure-regulating high-sensitivity small-tension film-shaped biomaterial mechanic detector | |
CN108445306A (en) | A kind of electric field measurement system and its application method based on FPGA controls | |
CN108172152A (en) | The current sensing means and detection method of a kind of display panel | |
CN203587450U (en) | Test instrument for measuring shearing strength of bulk solid material | |
CN106124123B (en) | A kind of torque sensor spends experimental provision surely | |
CN203024854U (en) | Automatic pressure preloading equipment for weighing force transducer | |
CN206990097U (en) | Multichannel creep loads test machine automatically | |
CN113092968A (en) | Automatic testing system for AC/DC breakdown field intensity of film sample | |
CN211402009U (en) | Rotation type mechanical friction interface normal position information acquisition device | |
CN108279194B (en) | Droplet concentration detection apparatus and detection method | |
CN113267612B (en) | Soil moisture content detection method, detection system and penetration device | |
CN112033653B (en) | Measuring instrument | |
CN210400708U (en) | Digital display force measuring ring coefficient calibration device | |
CN209727628U (en) | A kind of strain-type unconfined compression apparatus | |
CN2290055Y (en) | Interlligence soil liquid plastic limit combination measuring instrument | |
CN103090956A (en) | Automatic pressure preloading equipment and method of weighing force measuring sensor | |
CN113280852B (en) | Point switch parameter detection device and method | |
CN110118536A (en) | A kind of measurement surface of test piece any position deformed finger target device | |
CN213239459U (en) | Loading test bed for agricultural machinery complete machine engine |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200515 |
|
CF01 | Termination of patent right due to non-payment of annual fee |