使用概率正则化生成对抗网络（PR-GAN）和反事实方法生成用户指定故障概率的轴承振动信号

中文摘要 AI 辅助

在轴承振动数据集中，大多数样本预测的故障概率接近0或1，中间概率（灰色区域）的样本很少。这些临界样本很重要，因为它们反映了维护决策可能需要额外检查或保守响应的情况，对研究决策边界很有用。为解决样本稀缺问题，本文提出并比较了两种方法来生成预测故障概率与目标概率（0.25、0.50或0.75）匹配的振动信号。我们使用具有不同架构和随机初始化的异构集成分类器的平均输出作为固定的、可梯度访问的概率预言机。第一种基于训练的方法，概率正则化生成对抗网络（PR-GAN），扩展了带梯度惩罚的瓦瑟斯坦生成对抗网络（WGAN-GP），通过残差生成器编辑真实信号，同时将分类器输出推向目标概率。第二种是无训练的、逐个样本的瓦赫特式反事实（CF）过程，直接优化每个输入信号以达到目标概率，同时接近源信号。我们在凯斯西储大学（CWRU）和帕德博恩轴承数据集上使用平均绝对目标概率误差、时域总变差和频域对数功率谱密度（log-PSD）差异评估了这两种方法。在所有设置下，CF在保留样本上以平均绝对概率误差0.005 - 0.008达到目标，成功率为1.000，而PR-GAN的平均误差为0.046 - 0.059，成功率在0.501和0.680之间。因此，CF能更可靠地控制概率，所需平均L1变化更小，而PR-GAN在大多数设置下运行时间更低。

英文摘要

In bearing vibration datasets, most samples receive predicted fault probabilities close to 0 or 1, while samples with intermediate (gray-zone) probabilities are rare. Such borderline samples are important because they reflect conditions in which maintenance decisions may require additional inspection or a conservative response and are useful for studying decision boundaries. To address this scarcity, this paper proposes and compares two approaches that generate vibration signals whose predicted fault probability matches a target probability of 0.25, 0.50, or 0.75. We use the average output of a heterogeneous ensemble classifier with different architectures and random initializations as a fixed, gradient-accessible probability oracle. The first, training-based approach, Probability-Regularized Generative Adversarial Network (PR-GAN), extends Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) and edits a real signal through a residual generator while pushing the classifier output toward the target probability. The second is a training-free, per-sample Wachter-style counterfactual (CF) procedure that directly optimizes each input signal to reach the target probability while remaining close to the source signal. We evaluate both methods on the Case Western Reserve University (CWRU) and Paderborn bearing datasets using mean absolute target-probability error, time-domain total variation, and frequency-domain log power spectral density (log-PSD) differences. Across all settings, CF reaches the target with a mean absolute probability error of 0.005-0.008 and a within-tolerance success rate of 1.000 on retained samples, whereas PR-GAN's mean error is 0.046-0.059 with success rates between 0.501 and 0.680. CF therefore steers the probability more reliably and requires smaller average L1 changes, whereas PR-GAN has a lower reported runtime in most settings.

发表机构

• University of Tehran（德黑兰大学）
• University of Victoria（维多利亚大学）
• Tampere University（坦佩雷大学）
• Aalto University（阿尔托大学）
• Khatam University（哈塔姆大学）

机构由 AI 辅助整理，请以论文原文为准。