00741871

Component

https://doi.org/10.3141/1570-15

http://scholar.google.com...eman&publication_year=1997

In recent years, artificial neural networks have successfully been trained to backcalculate pavement layer moduli from the results of falling weight deflectometer (FWD) tests. These neural networks provide the same solutions as existing programs, only thousands of times faster. Unfortunately, their use is constrained to the test conditions assumed during network training. These limitations arise from practical aspects of neural network training and cannot be circumvented easily. The goal of this research was to develop a backcalculation program combining the speed of neural networks and the flexibility of conventional programs to produce the same solutions as existing programs. This was accomplished by forgoing neural network backcalculation in favor of neural network forward-calculation, that is, using neural networks in place of complex numerical models for computing the forward-problem solutions used by the conventional backcalculation programs. A suite of neural networks, covering a range of flexible pavement structures, was trained using data generated by WESLEA, the forward-problem solver used in the WESDEF backcalculation program. When tested on 110 experimental FWD results, a version of WESDEF augmented by the neural networks provided statistically identical answers 42 times faster, on average, than the original. Provisions have been made for periodic upgrades as additional networks are trained for other pavement types and test conditions. Meanwhile, the original WESLEA can still be used when an appropriate network is unavailable. This preserves the flexibility of the original program while taking maximum advantage of the speed gains afforded by the neural networks.

This paper appears in Transportation Research Record No. 1570, Pavement Research Issues.

English

p. 126-133

1997

Transportation Research Record

0309061539

Figures (3) ; References (11) ; Tables (3)

Backcalculation; Computer programs; Deflection; Falling weight deflectometers; Flexible pavements; Layer coefficient (Pavements); Modulus; Neural networks; Pavements

Layer moduli; Limitations

Data and Information Technology; Design; Highways; Pavements; I22: Design of Pavements, Railways and Guideways; I23: Properties of Road Surfaces

TRIS, TRB, ATRI

Oct 1 1997 12:00AM

• ANALYSIS OF LTPP PROFILE DATA FOR JOINTED CONCRETE PAVEMENT SECTIONS
• BACKCALCULATION ANALYSIS OF PAVEMENT-LAYER MODULI USING GENETIC ALGORITHMS
• CRACK DEVELOPMENT IN LINEAR TRACKING TEST PAVEMENTS FROM VISUAL SURVEY TO PIXEL ANALYSIS
• DETECTION AND MONITORING OF CRACKS IN ASPHALT PAVEMENT UNDER TEXAS MOBILE LOAD SIMULATOR TESTING
• DEVELOPMENT OF PROTOTYPE VIDEO-BASED SENSOR FOR VEHICLE DETECTION FROM STAND-STILL IMAGES
• DIPLOBACK: NEURAL-NETWORK-BASED BACKCALCULATION PROGRAM FOR COMPOSITE PAVEMENTS
• DYNAMIC PERFORMANCE OF COMPOSITE PAVEMENTS UNDER IMPACT
• EFFECT OF INITIAL PAVEMENT SMOOTHNESS ON FUTURE SMOOTHNESS AND PAVEMENT LIFE
• EFFECT OF VEHICLE-PAVEMENT INTERACTION ON PAVEMENT RESPONSE
• EVALUATION OF FATIGUE CRACKING
• EVASION OF WEIGHT-ENFORCEMENT STATIONS BY TRUCKS
• INVESTIGATION OF BACKCALCULATED MODULI USING DEFLECTIONS OBTAINED AT VARIOUS LOCATIONS IN A PAVEMENT STRUCTURE
• LINEAR TRACKING PERFORMANCE TESTS ON FULL-DEPTH ASPHALT PAVEMENT
• LINEAR TRACKING RESPONSE MEASUREMENTS: DETERMINING EFFECTS OF WHEEL-LOAD CONFIGURATIONS
• MALFUNCTION DETECTION AND DATA REPAIR FOR INDUCTION-LOOP SENSORS USING I-880 DATA BASE
• MONTANA'S AUTOMATED DEFLECTION ANALYSIS PROCEDURE
• PRIMARY RESULTS FOR THE FIRST TEXAS MOBILE LOAD SIMULATOR TEST PAD
• ROADWAY-VEHICLE INTERACTION, PHYSICAL INDEXES, AND HUMAN JUDGMENT OF RIDE QUALITY
• RUTTING DEVELOPMENT IN LINEAR TRACKING TEST PAVEMENTS TO EVALUATE SHELL SUBGRADE STRAIN CRITERION
• SINGLE-MEASUREMENT ESTIMATION OF IN SITU ASPHALT-LAYER MODULI WITH PORTABLE FALLING WEIGHT DEFLECTOMETER
• TEMPERATURE CORRECTION OF BACKCALCULATED MODULI AND DEFLECTIONS USING LINEAR VISCOELASTICITY AND TIME-TEMPERATURE SUPERPOSITION
• USING GEOGRAPHIC INFORMATION SYSTEM TECHNOLOGY TO SYNTHESIZE CENSUS AREAWIDE AND LINEAR HIGHWAY DATA FOR LOCATION OF WEIGH-IN-MOTION SITES