Lagrange programming neural network for radar waveform design

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)12_Chapter in an edited book (Author)peer-review

1 Scopus Citations
View graph of relations

Author(s)

  • Junli Liang
  • Yang Jing
  • Jian Li
  • Alfonso Farina

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationRadar Waveform Design Based on Optimization Theory
EditorsGuolong Cui, Antonio De Maio, Alfonso Farina, Jian Li
PublisherInstitution of Engineering and Technology
Chapter8
Pages221-261
ISBN (Electronic)9781785619441
ISBN (Print)9781785619434
Publication statusPublished - 2020

Abstract

In this chapter, Lagrange programming neural network (LPNN) that is a constrained optimization solver is exploited to design radar probing waveforms under constraints due to unit-modulus, spectral requirement and/or ambiguity function (AF). In the LPNN, there are two types of neurons to compute the optimum solution, namely, variable and Lagrangian neurons, which are responsible for finding a minimum point of the cost function as well as the solution at an equilibrium point and leading the dynamic trajectory into the feasible region. The local stability conditions of the dynamic neuron model are also analyzed. Simulation results show that the LPNN-based approach is a competitive alternative for waveform design.

Citation Format(s)

Lagrange programming neural network for radar waveform design. / Liang, Junli; Jing, Yang; So, Hing Cheung; Leung, Chi Sing; Li, Jian; Farina, Alfonso.

Radar Waveform Design Based on Optimization Theory. ed. / Guolong Cui; Antonio De Maio; Alfonso Farina; Jian Li. Institution of Engineering and Technology, 2020. p. 221-261.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)12_Chapter in an edited book (Author)peer-review