Materials and parts in complex systems, such as ground vehicles, can suffer from fatigue due to use, age and other stresses experienced during service. It is therefore essential to evaluate damage and predict the remaining life, reliability and safety of the vehicle. This paper describes the design of a wireless system for real-time monitoring of ground vehicles using Lamb waves. The proposed approach integrates sensor technology, signal processing and wireless networking into a single solution for online structural health monitoring (SHM). Lamb wave inspection is accomplished by inexpensive piezoelectric transducer patches (PZT), which are surface-mounted on the critical components of the vehicle without interrupting its operation. Lamb wave scattering from damage is obtained by comparing the recorded signal with the healthy sample and then damage-related features are identified using Probability Diagnostic Imaging (PDI). The problem of multiple Lamb wave modes is addressed by new Mode Decomposition (MD) algorithm based on Time-Frequency Representation (TFR) of the differenced signal. Hardware components of the proposed system include Sensor Nodes (SN) designed for Lamb wave actuation and data acquisition; and a basestation, where signal processing is implemented. The schematic of wireless sensor network (WSN) is presented and finally, communication protocol for wireless data transmission between SN's and a basestation is described.