ScrewSense: Mapping the Invisible - Anomaly Detection and Error Classification in Screwdriving Processes

Tobias Lettner, Tatyana Ivanovska, Anwar Al Assadi, Christian BerglerarXiv 2026 · DOI · arXiv

TL;DR

ScrewSense leverages deep learning to move beyond simple "pass/fail" checks in industrial screwdriving. By transforming torque and angle data into high-dimensional embeddings and 2D images, the framework can automatically detect anomalies and classify specific error types—like cross-threading or damaged drives—with up to 100% accuracy.

What Problem Does This Paper Address?

In modern manufacturing, screwdriving is more than just turning a fastener; it’s a data-rich process critical for quality control and sustainability (think: easy disassembly for recycling). Traditionally, engineers have relied on "monitoring windows" or "envelope curves"—fixed thresholds that trigger an alarm if torque or angle values stray too far.

However, these methods have major drawbacks: they require tedious manual tuning by experts and usually only provide a binary "OK" or "Not OK" (NOK) result. They can't tell you why a screw failed. As industries move toward lightweight materials and higher automation, these rigid systems struggle to keep up. The authors propose a deep learning framework to "map the invisible" patterns in process data, automating error identification and reducing manual analysis time.

Methods

The researchers developed a two-pronged approach:

  1. Anomaly Detection: They used a Vector Quantized Variational Autoencoder (VQVAE). The model was pre-trained on ImageNet to learn general visual features and then fine-tuned specifically on "OK" screwdriving samples. By analyzing the model's "embedding space" (a compressed mathematical representation of the data), they could visualize how different processes cluster together.
  2. Error Classification: They compared four distinct deep learning paradigms to see which best identifies specific failure modes:
  3. MLP-based: PatchTSMixer (PTSM), a lightweight model for multivariate time series.
  4. CNN-based: ConvTimeNet (CTN), which uses convolutional blocks to capture local patterns.
  5. Transformer-based: ConvTran (CTR), combining convolutions with attention mechanisms.
  6. Vision-based: A Vision Transformer (ViT). This is the most novel part: they converted 1D time-series data (torque/angle) into 2D images using techniques like Gramian Angular Fields (GAF) and Spectrograms before feeding them into the model.
Fig. 1: Example of image conversion results. From left to right: original input, density, GAF, and spectrogram representations of the torque signal. Each image has a size of 224×224 pixel. The model uses three-channel inputs, with torque, rotation angle, and time as features. Density images use a 224×224 bin size; GAF is generated with the summation method; spectrogram parameters are nfft = 512, hop length = 32, and a Hamming window.

Datasets

The study utilized five distinct datasets covering assembly, dismantling, and reassembly across different hardware setups (manual vs. robotic).

  • Lab Datasets: assm_a, dism_a, reasm_a, dism_b, and dism_c. These include various error classes like "Bursting Tube," "Cross Threading," and "Damaged Screw Drive."
  • Real-World Data: 36 unlabeled samples acquired from loosening screws on actual lawn mower housings to test the model's generalization.
  • Availability: All datasets are publicly available on GitHub.

Key Insights and Ideas

  • AI as a Data Auditor: One of the most striking "aha moments" occurred during anomaly detection. The VQVAE identified "OK" samples that clustered with "Cross Threading" errors. Upon visual inspection, the researchers realized these were mislabeled during data collection. Fixing these labels (the "adapted" dataset) significantly boosted model performance.
  • Vision is Versatile: Converting time series into images (specifically using GAF) allowed the Vision Transformer to outperform traditional time-series models on the most complex datasets.
  • Visualizing the Latent Space: By using t-SNE to reduce the VQVAE's high-dimensional embeddings to 2D, the authors created a "map" of the process. This allows engineers to see why an anomaly is an anomaly—for example, showing that a specific error occurred 50° later than normal.
Fig. 2: Embedding space of the dism a dataset. Each point represents a screw- driving sample described by torque, rotation angle, and time, with colors indi- cating class labels. Multiple anomalies occurred and are highlighted as A1 - A5.

Key Results

  • Top Performance: The ViT-GAF model achieved the highest mean Balanced Accuracy (BAC) of 0.9450 across all datasets.
  • Perfect Scores: On simpler assembly datasets (assm_a), several models achieved 100% accuracy.
  • Impact of Data Adaptation: For the challenging reassembly dataset (reasm_a), correcting the mislabeled samples found by the anomaly detector improved the BAC from 0.7812 to 0.9234.
  • Real-World Robustness: The model trained only on lab data successfully classified real-world lawn mower disassembly samples, proving it can generalize to industrial environments.

Limitations and Future Work

While powerful, the authors note a few hurdles:

  • Data Hunger: The models currently require about 50 labeled samples per class to perform well, which can be difficult to collect in some industrial settings.
  • Transferability: Differences in sensors or recording hardware between different factories might limit how easily a model trained in one location can be used in another.
  • Next Steps: The team plans to explore synthetic data generation to reduce the need for manual labeling and foundation models (like TOTEM) to improve cross-system generalization. They also aim to move toward real-time, sequential processing to catch errors while the screw is still turning.

Summary updated

Abstract

The growing volume of process data generated by screwdriving systems, combined with advancements in computing power, data storage, and algorithms, is facilitating the application of artificial intelligence in this field. Accurately detecting and classifying screwdriving errors is crucial for ensuring product quality, avoiding costly rework in manufacturing, and supporting sustainability by facilitating the maintenance, reuse, and recycling of screw-connected products. In this context, machine learning approaches offer a promising alternative to traditional monitoring techniques, such as window-based methods or envelope curves. This study examines the use of deep learning techniques for anomaly detection and error classification in screwdriving processes. The data corpus consists of multivariate time series capturing process parameters, such as torque and rotation angle. For anomaly detection, the embedding space of a vector quantized variational autoencoder was analyzed. In terms of error classification, four different model architectures were evaluated. The results demonstrate the effectiveness of anomaly detection and confirm that deep learning models can distinguish between multiple error categories beyond traditional binary classification. This extends the capabilities of conventional monitoring approaches, achieving accuracies of up to 100%. Additionally, real-world data material was examined in order to further demonstrate model robustness. Overall the results indicate strong generalization capability and highlight the practical potential of the developed models for use in industrial screwdriving processes, eliminating the need for expert knowledge in error identification and significantly reducing manual effort and analysis time.
BibTeX
@misc{lettner2026screwsense,
  author = {Tobias Lettner and Tatyana Ivanovska and Anwar Al Assadi and Christian Bergler},
  title = {{ScrewSense: Mapping the Invisible - Anomaly Detection and Error Classification in Screwdriving Processes}},
  year = {2026},
  eprint = {2611.16789},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.16789},
}
Figure