Data-Based Design of Multi-Model Inferential Sensors
- URL: http://arxiv.org/abs/2308.02872v1
- Date: Sat, 5 Aug 2023 12:55:15 GMT
- Title: Data-Based Design of Multi-Model Inferential Sensors
- Authors: Martin Mojto, Karol Lubu\v{s}k\'y, Miroslav Fikar, Radoslav Paulen
- Abstract summary: The nonlinear character of industrial processes is usually the main limitation to designing simple linear inferential sensors.
We propose two novel approaches for the design of multi-model inferential sensors.
The results show substantial improvements over the state-of-the-art design techniques for single-/multi-model inferential sensors.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper deals with the problem of inferential (soft) sensor design. The
nonlinear character of industrial processes is usually the main limitation to
designing simple linear inferential sensors with sufficient accuracy. In order
to increase the inferential sensor predictive performance and yet to maintain
its linear structure, multi-model inferential sensors represent a
straightforward option. In this contribution, we propose two novel approaches
for the design of multi-model inferential sensors aiming to mitigate some
drawbacks of the state-of-the-art approaches. For a demonstration of the
developed techniques, we design inferential sensors for a Vacuum Gasoil
Hydrogenation unit, which is a real-world petrochemical refinery unit. The
performance of the multi-model inferential sensor is compared against various
single-model inferential sensors and the current (referential) inferential
sensor used in the refinery. The results show substantial improvements over the
state-of-the-art design techniques for single-/multi-model inferential sensors.
Related papers
- Condition-Aware Multimodal Fusion for Robust Semantic Perception of Driving Scenes [56.52618054240197]
We propose a novel, condition-aware multimodal fusion approach for robust semantic perception of driving scenes.
Our method, CAFuser, uses an RGB camera input to classify environmental conditions and generate a Condition Token that guides the fusion of multiple sensor modalities.
We set the new state of the art with CAFuser on the MUSES dataset with 59.7 PQ for multimodal panoptic segmentation and 78.2 mIoU for semantic segmentation, ranking first on the public benchmarks.
arXiv Detail & Related papers (2024-10-14T17:56:20Z) - One Masked Model is All You Need for Sensor Fault Detection, Isolation and Accommodation [1.0359008237358598]
We propose a novel framework for sensor fault detection using masked models and self-supervised learning.
We validate our proposed technique on both a public dataset and a real-world dataset from offshore GE wind turbines.
Our proposed technique has the potential to significantly improve the accuracy and reliability of sensor measurements in real-time.
arXiv Detail & Related papers (2024-03-24T13:44:57Z) - Complexity Matters: Rethinking the Latent Space for Generative Modeling [65.64763873078114]
In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion.
In this study, we aim to shed light on this under-explored topic by rethinking the latent space from the perspective of model complexity.
arXiv Detail & Related papers (2023-07-17T07:12:29Z) - Constrained optimization of sensor placement for nuclear digital twins [1.7247618645684337]
We develop a data-driven technique that incorporates constraints into an optimization framework for sensor placement.
We demonstrate the efficacy of sensors optimized by exhaustively computing all feasible configurations for a low-dimensional dynamical system.
arXiv Detail & Related papers (2023-06-23T17:47:06Z) - SensiX++: Bringing MLOPs and Multi-tenant Model Serving to Sensory Edge
Devices [69.1412199244903]
We present a multi-tenant runtime for adaptive model execution with integrated MLOps on edge devices, e.g., a camera, a microphone, or IoT sensors.
S SensiX++ operates on two fundamental principles - highly modular componentisation to externalise data operations with clear abstractions and document-centric manifestation for system-wide orchestration.
We report on the overall throughput and quantified benefits of various automation components of SensiX++ and demonstrate its efficacy to significantly reduce operational complexity and lower the effort to deploy, upgrade, reconfigure and serve embedded models on edge devices.
arXiv Detail & Related papers (2021-09-08T22:06:16Z) - Data-based Design of Inferential Sensors for Petrochemical Industry [0.0]
Inferential (or soft) sensors are used in industry to infer the values of imprecisely and rarely measured (or completely unmeasured) variables from variables measured online.
This work is focused on the design of inferential sensors for product composition of an industrial distillation column in two oil refinery units.
arXiv Detail & Related papers (2021-06-25T08:48:50Z) - Perception Entropy: A Metric for Multiple Sensors Configuration
Evaluation and Design [17.979248163548288]
A well-designed sensor configuration significantly improves the performance upper bound of the perception system.
We propose a novel method based on conditional entropy in Bayesian theory to evaluate the sensor configurations containing both cameras and LiDARs.
To the best of our knowledge, this is the first method to tackle the multi-sensor configuration problem for autonomous vehicles.
arXiv Detail & Related papers (2021-04-14T03:52:57Z) - Real-time detection of uncalibrated sensors using Neural Networks [62.997667081978825]
An online machine-learning based uncalibration detector for temperature, humidity and pressure sensors was developed.
The solution integrates an Artificial Neural Network as main component which learns from the behavior of the sensors under calibrated conditions.
The obtained results show that the proposed solution is able to detect uncalibrations for deviation values of 0.25 degrees, 1% RH and 1.5 Pa, respectively.
arXiv Detail & Related papers (2021-02-02T15:44:39Z) - Investigating the Effect of Sensor Modalities in Multi-Sensor
Detection-Prediction Models [8.354898936252516]
We focus on the contribution of sensor modalities towards the model performance.
In addition, we investigate the use of sensor dropout to mitigate the above-mentioned issues.
arXiv Detail & Related papers (2021-01-09T03:21:36Z) - SensiX: A Platform for Collaborative Machine Learning on the Edge [69.1412199244903]
We present SensiX, a personal edge platform that stays between sensor data and sensing models.
We demonstrate its efficacy in developing motion and audio-based multi-device sensing systems.
Our evaluation shows that SensiX offers a 7-13% increase in overall accuracy and up to 30% increase across different environment dynamics at the expense of 3mW power overhead.
arXiv Detail & Related papers (2020-12-04T23:06:56Z) - Deep Soft Procrustes for Markerless Volumetric Sensor Alignment [81.13055566952221]
In this work, we improve markerless data-driven correspondence estimation to achieve more robust multi-sensor spatial alignment.
We incorporate geometric constraints in an end-to-end manner into a typical segmentation based model and bridge the intermediate dense classification task with the targeted pose estimation one.
Our model is experimentally shown to achieve similar results with marker-based methods and outperform the markerless ones, while also being robust to the pose variations of the calibration structure.
arXiv Detail & Related papers (2020-03-23T10:51:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.