Runtao Ding

Neural based dynamic modeling of nonlinear microwave circuits

A neural network formulation for modeling nonlinear microwave circuits is achieved in the most desirable format, i.e., continuous time-domain dynamic system format. The proposed dynamic neural network (DNN) model can be developed directly from input-output data without having to rely on internal details of the circuit. An algorithm is developed to train the model with time or frequency domain information. A circuit representation of the model is proposed such that the model can be incorporated into circuit simulators for high-level design. Examples of dynamic-modeling of amplifiers, mixer and their use in system simulation are presented.

Efficient analytical formulation and sensitivity analysis of neuro-space mapping for nonlinear microwave device modeling

A new computer-aided design (CAD) method for automated enhancement of nonlinear device models is presented, advancing the concept of Neuro-space mapping (Neuro-SM). It is a systematic computational method to address the situation where an existing device model cannot fit new device data well. By modifying the current and voltage relationships in the model, Neuro-SM produces a new model exceeding the accuracy limit of the existing model. In this paper, a novel analytical formulation of Neuro-SM is proposed to achieve the same accuracy as the basic formulation of Neuro-SM (known as circuit-based Neuro-SM) with much higher computational efficiency. Through our derivations, the mapping between the existing (coarse) model and the overall Neuro-SM model is analytically achieved for dc, small-signal, and large-signal simulation and sensitivity analysis. The proposed analytical formulation is a significant advance over the circuit-based Neuro-SM, due to the elimination of extra circuit equations needed in the circuit-based formulation. A two-phase training algorithm utilizing gradient optimization is also developed for fast training of the analytical Neuro-SM models. Application examples on modeling heterojunction bipolar transistor (HBT), metal-semiconductor-field-effect transistor (MESFET), and high-electron mobility transmistor (HEMT) devices and the use of Neuro-SM models in harmonic balance simulations demonstrate that the analytical Neuro-SM is an efficient approach for modeling various types of microwave devices. It is useful for systematic and automated update of nonlinear device model library for existing circuit simulators.

Neural-based dynamic modeling of nonlinear microwave circuits

A neural network formulation for modeling nonlinear microwave circuits is achieved in the most desirable format, i.e., continuous time-domain dynamic system format. The proposed dynamic neural network (DNN) model can be developed directly from input-output data without having to rely on internal details of the circuit. An algorithm is developed to train the model with time or frequency domain information. A circuit representation of the model is proposed such that the model can be incorporated into circuit simulators for high-level design. Examples of dynamic-modeling of amplifiers, mixer and their use in system simulation are presented.

Exact adjoint sensitivity analysis for neural-based microwave modeling and design

For the first time, an adjoint neural network method is introduced for sensitivity analysis in neural-based microwave modeling and design. Exact first and second order sensitivities are systematically calculated for generic microwave neural models including variety of knowledge based neural models embedding microwave empirical information. A new formulation allows the models to learn both the input/output behavior of the modeling problem and its derivative data simultaneously. Examples for passive and active microwave modeling and simulation are presented.

State-space dynamic neural network technique for high-speed IC applications: modeling and stability analysis

We present a state-space dynamic neural network (SSDNN) method for modeling the transient behaviors of high-speed nonlinear circuits. The SSDNN technique extends the existing dynamic neural network (DNN) approaches into a more generalized and robust formulation. For the first time, stability analysis methods are presented for neural modeling of nonlinear microwave circuits. We derive the stability criteria for both the local stability and global stability of SSDNN models. Stability test matrices are formulated from SSDNN internal weight parameters. The proposed criteria can be conveniently applied to the stability verification of a trained SSDNN model using the eigenvalues of the test matrices. In addition, a new constrained training algorithm is introduced by formulating the proposed stability criteria as training constraints such that the resulting SSDNN models satisfy both the accuracy and stability requirements. The validity of the proposed technique is demonstrated through the transient modeling of high-speed interconnect driver and receiver circuits and the stability verifications of the obtained SSDNN models

Neuro-Space Mapping technique for nonlinear device modeling and large signal simulation

A new Neuro-Space Mapping (Neuro-SM) approach is presented enabling the space mapping (SM) concept to be applied to nonlinear device modeling and large signal circuit simulation. Suppose that an existing device model (namely, the coarse model) cannot match the actual device behavior (namely, the fine model). Using the proposed technique, the voltage and current signals between the coarse and the fine device models are mapped by a neural network. This mapping automatically modifies the behavior of the coarse model such that the mapped model accurately matches the actual device behavior. New training methods for such mapping neural networks are proposed. Examples of SiGe HBT and GaAs MESFET modeling and use of the models in harmonic balance simulation demonstrate that Neuro-SM is a systematic method to allow us to exceed the present capabilities of the existing device models.

An adjoint dynamic neural network technique for exact sensitivities in nonlinear transient modeling and high-speed interconnect design

We propose a new adjoint dynamic neural network (ADNN) technique aimed at enhancing computer-aided design (CAD) of high-speed VLSI modules. A novel formulation for exact sensitivities is derived employing the Lagrange functions approach, and by defining an adjoint of a dynamic neural network (DNN), for the first time. The proposed ADNN is a dynamic model that we solve using integration backwards through time. One ADNN solution can be used to efficiently compute exact sensitivities of the corresponding DNN with respect to all its parameters. Using these sensitivities, we developed a training algorithm that facilitates DNN learning of nonlinear transients directly from continuous time-domain waveform data. Resulting accurate and fast DNN models can be straightaway used for carrying out high-speed VLSI CAD in SPICE-like time-domain environment. The technique can also speed-up physics-based nonlinear circuit CAD through faster sensitivity computations. Applications of the proposed ADNN technique in transient modeling and nonlinear design are demonstrated through high-speed interconnect driver examples.

A new nonlinear transient modelling technique for high-speed integrated circuit applications based on state-space dynamic neural network

A new state-space dynamic neural network (SSDNN) method is presented to model the transient behaviours of high-speed nonlinear circuits. The proposed technique extends the existing dynamic neural network (DNN) approach into a more generalized and robust formulation. A training algorithm exploiting the adjoint sensitivity computation is developed to enable SSDNN to efficiently learn from the transient input and output waveform data without relying on the circuit internal details. An exact representation is derived to convert the proposed SSDNN into circuit format such that the trained SSDNN model can be conveniently used in SPICE-like circuit simulators. The validity of the proposed technique is demonstrated through the transient modelling of high-speed driver/receiver circuits.

Robust neural based microwave modelling and design using advanced model extrapolation

For the first time, the issue of using neural-based microwave models far outside their training range is directly addressed. A standard neural model is meaningful only outside the particular range of inputs for which it is trained, and becomes unreliable when used outside this range. This paper presents a robust neural modelling technique incorporating advanced extrapolation to address this problem. A new process is incorporated in training to formulate a set of base points to represent a regular or irregular training region. An adaptive base point selection method is developed to identify the most significant subset of base points upon any given value of model input. This method is combined with quadratic extrapolation utilizing neural network outputs and their derivatives. The proposed technique is demonstrated by examples of neural based design solution space analysis of coupled transmission lines and neural based behaviour modelling and simulation of power amplifiers. It is demonstrated that the proposed technique allows the neural based microwave models to be used far beyond their original training range.

Feedforward dynamic neural network technique for modeling and design of nonlinear telecommunication circuits and systems

A new technique based on neural networks is presented for dynamic modeling of nonlinear telecommunication circuits in continuous time domain. The proposed feedforward dynamic neural network (FDNN) model can be developed directly from input-output large-signal measurements or simulations, without having to rely on internal details of the circuit. New formulations are derived in order to handle the important circuit-load effects in system level simulation. The resulting model is fast and can be used with connections to other circuit models, allowing us to perform efficient high-level system simulation and design. It is observed that the proposed FDNN approach provides the best overall performance of being much faster than original detailed system simulation and much more accurate than the conventional behavioral modeling approach. Examples of feedforward dynamic modeling of amplifiers, mixer and their use in telecommunication system simulation are presented, demonstrating the increased efficiency in designing telecommunications systems using the proposed technique.