Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Fault Diagnosis and Quantification for Photovoltaic Arrays based on Differentiable Physical Models

Zenan Yang, Yuanliang Li, Jingwei Zhang, Yongjie Liu, Kun Ding

TL;DR

The paper tackles reliable fault diagnosis and quantification in PV arrays under diverse faults. It introduces a differentiable fast fault simulation model (DFFSM) that yields I–V curves and computes analytical gradients with respect to fault parameters, enabling physics-informed gradient-based identification via the GFPI framework. Using Adahessian optimization with projection constraints, GFPI quantifies partial shading, short-circuit, and series-resistance degradation, achieving high accuracy and I–V reconstruction errors below 3% on both simulated and measured data. The work also highlights computational efficiency and portability to edge devices, and provides an open-source implementation to foster further development in differentiable PV fault analysis.

Abstract

Accurate fault diagnosis and quantification are essential for the reliable operation and intelligent maintenance of photovoltaic (PV) arrays. However, existing fault quantification methods often suffer from limited efficiency and interpretability. To address these challenges, this paper proposes a novel fault quantification approach for PV strings based on a differentiable fast fault simulation model (DFFSM). The proposed DFFSM accurately models I-V characteristics under multiple faults and provides analytical gradients with respect to fault parameters. Leveraging this property, a gradient-based fault parameters identification (GFPI) method using the Adahessian optimizer is developed to efficiently quantify partial shading, short-circuit, and series-resistance degradation. Experimental results on both simulated and measured I-V curves demonstrate that the proposed GFPI achieves high quantification accuracy across different faults, with the I-V reconstruction error below 3%, confirming the feasibility and effectiveness of the application of differentiable physical simulators for PV system fault diagnosis.

Fault Diagnosis and Quantification for Photovoltaic Arrays based on Differentiable Physical Models

TL;DR

The paper tackles reliable fault diagnosis and quantification in PV arrays under diverse faults. It introduces a differentiable fast fault simulation model (DFFSM) that yields I–V curves and computes analytical gradients with respect to fault parameters, enabling physics-informed gradient-based identification via the GFPI framework. Using Adahessian optimization with projection constraints, GFPI quantifies partial shading, short-circuit, and series-resistance degradation, achieving high accuracy and I–V reconstruction errors below 3% on both simulated and measured data. The work also highlights computational efficiency and portability to edge devices, and provides an open-source implementation to foster further development in differentiable PV fault analysis.

Abstract

Accurate fault diagnosis and quantification are essential for the reliable operation and intelligent maintenance of photovoltaic (PV) arrays. However, existing fault quantification methods often suffer from limited efficiency and interpretability. To address these challenges, this paper proposes a novel fault quantification approach for PV strings based on a differentiable fast fault simulation model (DFFSM). The proposed DFFSM accurately models I-V characteristics under multiple faults and provides analytical gradients with respect to fault parameters. Leveraging this property, a gradient-based fault parameters identification (GFPI) method using the Adahessian optimizer is developed to efficiently quantify partial shading, short-circuit, and series-resistance degradation. Experimental results on both simulated and measured I-V curves demonstrate that the proposed GFPI achieves high quantification accuracy across different faults, with the I-V reconstruction error below 3%, confirming the feasibility and effectiveness of the application of differentiable physical simulators for PV system fault diagnosis.

Paper Structure

This paper contains 25 sections, 32 equations, 9 figures, 3 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Differentiable Fast Fault Simulation Model
  3. Reverse-biased Single Diode Model
  4. Fault Vector
  5. Forward Calculation of DFFSM
  6. Construct ambient vectors
  7. Calculate the five components of PV cell under each environmental condition
  8. Calculate the output voltages of PV cell for each environmental condition
  9. Construct $\mathbf{Q_{sub}}$ and $\mathbf{Q_{cell}}$
  10. Calculate the output voltages of substrings
  11. Calculate the output voltages of the PV string
  12. Backward Calculation of DFFSM
  13. ${\rm d} V /{\rm d} n_{\rm s}$
  14. ${\rm d} V /{\rm d} n_{\rm c}$
  15. ${\rm d} V /{\rm d} r$
  16. ...and 10 more sections

Figures (9)

  • Figure 1: Framework of the proposed fault quantification method.
  • Figure 2: Electrical equivalent circuit of PV cells based on the RSDM.
  • Figure 3: The computation flow for solving RSDM using Newton method: (a) conventional recursive method, (b) our approach.
  • Figure 4: Performance comparison between optimizers: (a) The average loss, (b) The average gradient norm.
  • Figure 5: The experimental platform and fault settings.
  • ...and 4 more figures