In-Pavement Wireless Sensor Network for Vehicle Classification

In-Pavement Wireless Sensor Network for Vehicle Classification

In-Pavement Wireless Sen sor Network for Vehicle Classification A U T H O R S : R AV N E E T B A J WA , R A M R A J A G O PA L , P R AV I N VA R A I YA A N D R O B E R T KAVA L E R PRESENTER: XIANGYI GU Outline Motivation Introduction Description Communication Protocol Design Experiment Setup

Performance Conclusion & Future Work Outline Motivation Introduction Description Communication Protocol Design Experiment Setup Performance Conclusion & Future Work Motivation

Intrusive technologies Piezoelectric sensors, inductive loops (examples) High installation and maintenance costs Non-intrusive technologies Infrared, video imaging(examples) Sensitive to traffic and weather condition Propose an alternative system base on a WSN that is both cost effective and insensitive t

o environmental conditions Transportation agencies collect vehicle classification information to plan highway maintenance programs, evaluate highway usage and optimize the deloyment of various resources on the road Motivation Introduction Description Communication Protocol Design Experiment Setup Performance Conclusion & Future Work

Problem Statement Cars, buses, three-axle single unit trucks, and five-axle single trailer trucks (classifying vehi cles) A vehicle travels in a traffic lane at some vary ing speed and we wish to count the number o f axles and the spacing between each axle in an accurate manner Proposed WSN System Vibration sensor (accelerometer) embedded in the r

oad Calculate the axle spacings Vehicle detection sensor (magnetometers) Report the arrival and departure times of a vehicle Access point (AP) Send commands to sensors Log the incoming data

First in-pavement, easy to deploy, WSN based system for counting axles and axle spacing Outline Motivation Introduction Description Communication Protocol Design Experiment Setup

Performance Conclusion & Future Work Wireless Vehicle Detection Sensor Measures the changes in magnetic field to infer the local presence of a vehicle Synchronous Nanopower Protocol(SNP), a TDMA based protocol Last 10 years with a single 7200 mAhr battery

Given the arrival times tai and taj at the two sensors i and j, the speed v will be v = dij / |taj tai| Estimate the length(L) of the vehicle L = v(tdj - taj) Wireless Vibration Sensor Sample the analog output of an accelerometer and transmit the data via a radio Designing a sensor that measures pavement vibrations for axle detection have many unique challenges Sensor needs to be insensitive

to the vehicles traveling in the neighboring lanes Sample fast enough to apture the transient vibrations nsensitive to the truck engine nd environmental noise The sensor has to be well coupled to the road way and be resistant to heavy vehicle traffic

Challenges Sensor resolution target is 500ug Bandwidth 50Hz Sampling frequency 512 Hz( > 5 times Nyquist Frequency) -Power consumption increases for higher sampling rates

Axle detection and counting Given vehicle speed measurement and reliable measurement from the wireless vibration sensor, we still need to construct an axle detection algorithm that has good performance There are two important challenges in detecting individual axles: B A The vibration signals from successive axles tend to blend.

. In wide highway lanes, vehicles can experience significant wander Sensor Design Resolution:Selecting an accelerometer

SD1221-005 has higher sensitivity and lower noise de nsity However, it consumes more than 20 times the current than MS9002.D and has to be operated at higher volta ge Both devices achieved the aimed minimum resolution of 500 ug Select MS9002.D due to its low operating voltage and low cu rrent consumption

Noise: Filters for mitigating sound noi se Accelerometer is sensitive to sound MS9002.D behaves like a microphone under the devices bandwidth 3rd order low-pass filter with cutoff frequenc y of 50 Hz is sufficiently aggressive to filter out most of the sound in the audible spectru m Casing Sound isolation

Protect the electronics from rain water and oil spill on the road Circuit Description 2.5 V supply voltage Amplifier with gain 10 The gain of 10 reduces the range of the accelerometer to 225mg This is necessary in order to ensure that the quantization noise from the ADC is less than the noise from the accelerometer

Otherwise, the resolution of the system will be limited by A DC noise The reduced range is still sufficient For heavy trucks 200 mg Outline Motivation Introduction Description Communication Protocol Design

Experiment Setup Performance Conclusion & Future Work Communication Protocol Design MAC Layer TDMA based Time is divided into multiple frames with each fra mes about 125 ms long Each frame is further divided into 64 time slots Slot 0 is used by AP to send clock synchronization information and other commands to the sensors

AP assigns every node unique time slots and a no de ID to communicate with it. Application Layer Sync Application AP sends sync packets on a periodic basis Sensor node listens to sync packets every 125 ms When the clock converges to steady state, then is listens for a sync packet only once in 30 s Sync application is also used to send commands Set Mode, Reset, Set Timeslot, Set RF, Download

Firmware, Set ID Application Layer Accelerometer Application Idle Mode: accelerometer and related circuitry are tu rned off by disabling the voltage regulator Once every 30 s, the microcontroller and the transceiver wake up and acquire the sync packet Application Layer

Raw Data Mode: microcontroller wake up every 1/51 2 s, and samples the analog output from acceleromete r 32 samples at a sampling freq. 512Hz, and each sample c ontaining 12 bits of information

In every frame(125ms) we accumulate 96 bytes of inform ation to transmit To have a reasonable packet size, we fragment the data i n two parts, 48 bytes each, and transmit it using two diffe rent time slots 62.5ms apart Application Layer Download Firmware Application Reprogram the entire flash memory of a sensor n ode over the air AP transmits new code repeatedly and the node u pdating its code in small pieces

Only the data that do not overwrite the current ru nning program are updated by the node Axle Detection(ADET) Algorithm Results of ADET on truck49( two single axles and one tandem axle), a(n) is the measured acceleration in mg, e(n) is the scaled energy in mg2, and s(n) is smooth energy in mg2. The red asterisks on s(n) are the axle locations found by ADET. By reducing the minimum axle sepatation, the individual axles in the tandem axle can also be detected as shown by black circle Axle Detection(ADET) Algorithm

Using data from 4 trucks at different speeds, we observed the bandwidth of the energy sig nal and empirically defined by M(v) = 900/v Low-pass filter is optional Minimum time separation (v) was chosen by assuming that the axles are at least 6ft apart Wide Lane ADET Algorithm Wander movement in a lane Combining vibration readings from multiple sens ors

Delay Di = di / v sennor2 will measures the peak enery a little later tha n sensor 1, so the individual energy measurements nedd to be appropriately delayed System representation of the adjustment made to correct vehicle wander. The energy if the total signal at time n is the maximum of the energy of the individual signals ei(n) is each Outline Motivation Introduction Description

Communication Protocol Design Experiment Setup Performance Conclusion & Future Work Experiment Setup 4 vibration sensors and 4 vehicle detection sensor were installed on California Highway I-680 Vehicles come from Sunol Weigh Station Slow down at weigh station

Easy to collect ground truth Data from 53 different trucks, ranging from pickup trucks to 5-axle commercial trucks The WSN setup at Suno; site. DHMN are vehicle detection sensors shereas I,J,K,L are vibration sensors Installation

Boring a 4-inch diameter hole approximately 2.25 i nches deep Installed on a road in less than 20 minutes Installation of a small sensor is much cheaper and convenient than installing special material paveme nts required for piezoelectric sensors Deployment Challenges Packet Drops Drop rate was low(1%) (compare 50 feet away) ret

ransmit packets with a delay of 1 packet drop rate is almost 0 Packet 1, 2, 1again, 2again Vehicle Wander Because vehicles are not taveling stright in a lane we would lik e to choose data from vehicle sensor that was closest to the tires use Wide Lane ADET algorithm Sensor failure Sensor k did not work

Vibration data was available from 3 sensors Outline Motivation Introduction Description Communication Protocol Design Experiment Setup Performance Conclusion & Future Work Vibration Sensor Performance Noise with no vehicle in vicinity

414 ug RMS Truck was parked on top of the sensor with e ngine were on vs. truck blew its horn 7% vs. 4% With a heavy truck traveled in the closed lane Sensor did not register any noticeable peaks Axle Count Error difference between the ground truth axle c

ount and the estimated axle count By combining the measurements from all sensors, t he algorithm always gives the correct axle count Error results form the wander movement( Strongly affected by truck wander Performance of ADET using individual sensors and combinations of sensors. Count Err. Is the difference between the ground truth and ADET estimate. Under each sensor column is the observed frequency of the errors. Axle Spacing Left: for tandem axle

Middle: pick up trucks, small two axle comm ercial trucks Right: axles of trailers Distribution of estimated axle spacings. There are three clusters in the data separated by empty bins. The dotted lines represent

the means of there clusters Outline Motivation Introduction Description Communication Protocol Design Experiment Setup Performance Conclusion & Future Work Conclusion

A novel algorithm that estimates the axle count and spaci ng from pavement acceleration was designed and tested o n the collected data ADET is simple enough to implement a sensor node with li mited processing power Majorities of the existing technologies are wired solutions Both the sensors and the AP are powered by batteries and consume much less power than other technologies The installation procedure and sensors themselves are mu ch cheaper There is minimal maintenance compared to other technol ogies

Future Work Find an optimal arrangement of sensors in order to minimize the number of sensors de ployed Reduce the amount of data transmitted Reduce the sensor power consumption Thank you very much!

Recently Viewed Presentations

  • Multimedia-Kommunikation: Prof.Dr.-Ing. Ralf Steinmetz

    Multimedia-Kommunikation: Prof.Dr.-Ing. Ralf Steinmetz

    Each person hand in: A short description of what you plan to evaluate in assignment 2 (2-3 lines is enough) Each group hand in: Names of group members Your proposal for assignment 1 What you will evaluate Who you will...
  • Knights of the "Rectangular Table"

    Knights of the "Rectangular Table"

    Knights of the "Rectangular Table" ... Since most people could not read in Medieval times symbols and sayings were used on coat of arms. Coat of Arms. Common Coat of Arms symbols. Antlers-strength and fortitude. Bear-strength and protection. Beaver-perseverance. Bow...
  • Introduction to Shakespeare's Othello

    Introduction to Shakespeare's Othello

    Received a classical education including Latin, Greek, history, math, astronomy, and music. Most likely began as an actor. Wrote 38plays, including comedies, histories, tragedies, and romances. Wrote 4 lengthy poems and a sonnet cycle
  • Flue gas flow rate measurement for verifying continuous ...

    Flue gas flow rate measurement for verifying continuous ...

    Method testing on wet stacks . Method testing on flows with swirl (no appropriate location found) Provide tools to cross-compare calculated and measured flue gas flow rate and to apply the statistical tests required by the standard. Project objectives. Define...
  • Widening Participation in Dual-Sector Settings

    Widening Participation in Dual-Sector Settings

    Widening Participation in Dual-Sector Settings ... Vocationalism The 'new HE' vocationalism Cooling out Learning and practising desired behaviours Lower grade, lower paid, less secure employment Conclusions: seamlessness Seamless transitions within single institutions may not be possible or ...
  • Goldman Sachs Risk Management November 17 2010 Presented

    Goldman Sachs Risk Management November 17 2010 Presented

    Fixed Income, Currency & Commodities. Commodities & commodity derivatives. Credit products, derivatives, investment-grade, high-yield, and distressed debt among many others. ... Trading & Arbitrage opportunities depend on market volatility.
  • Lab 3: Land Navigation (1)

    Lab 3: Land Navigation (1)

    Lab 3: Land Navigation (2) Yingjie Hu Dead Reckoning Dead Reckoning is the process of estimating current position based upon a previously determined position and advancing that position based upon known or estimated speeds over elapsed time (distance travelled), and...
  • Gene plot Frankia ACN vs Frankia CCI3

    Gene plot Frankia ACN vs Frankia CCI3

    Gene plot Frankia ACN vs Frankia CCI3 Author: Gogarten, J. Peter ... Calibri MS Pゴシック Arial Times New Roman Office Theme PowerPoint Presentation Typical multiple sequence fasta file PowerPoint Presentation Feature table PowerPoint Presentation Genome fasta file with location in...