Industrial Big Data and Computational Sustainability: Multi-Method Comparison Driven by High-Dimensional Data for Improving Reliability and Sustainability of Complex Systems

Abstract

Sustainable development is of great significance. The emerging research on data-driven computational sustainability has become an effective way to solve this problem. This paper presents a fault diagnosis and prediction framework for complex systems based on multi-dimensional data and multi-method comparison, aimed at improving the reliability and sustainability of the system by selecting methods with relatively superior performance. This study took the avionics system in the industrial field as an example. Based on the literature research on typical fault modes and fault diagnosis requirements of avionics systems, three popular high-dimensional data-driven fault diagnosis methods—support vector machine, convolutional neural network, and long- and short-term memory neural network—were comprehensively analyzed and compared. Finally, the actual bearing failure data were used for programming in order to verify and compare various methods and the process of selecting the superior method driven by high-dimensional data was fully demonstrated. We attempt to provide a sustainable development idea that continuously explores multi-method integration and comparison, aimed at improving the calculation efficiency and accuracy of reliability assessments, optimizing system performance, and ultimately achieving the goal of long-term improvement of system reliability and sustainability.

Super-forecasting the ‘technological singularity’ risks from artificial intelligence

“…To identify training data for the second algorithm we need to expand the search in new and emerging forms of data, e.g., open data -Open Data Institute 1 , Elgin 2 , DataViva 3 ; spatiotemporal data -GeoBrick [12], Urban Flow prediction [13], Air quality [14], GIS platform [15]; high-dimensional data -Industrial big data [16], IGA-ELM [17], MDS [18], TMAP [19]; time-stamped data -Qubit 4 , Edge MWN [20], Mobi-IoST [21], Edge DHT analytics [22]; real-time data -CUSUM [23], and big data [24].…”

New and emerging forms of data and technologies: literature and bibliometric review

“…High-dimensional data is defined as a high number of dimensions, in which the number of features exceeds the number of observations. For example, industrial high-dimensional big data reliability is studied and compared with a multi-method approach [ 52 ]. If we can analyse high-dimensional data, the research potential with is enormous.…”

Review of the state of the art in autonomous artificial intelligence

“…To ensure the success of the autonomous data preparation method, a new scenario is constructed to teach the algorithm how adversarial systems pollute the training data and how to discard such data from the training scenarios. While constructing the scenario, the search for training data expands in new and emerging forms of data (NEFD), e.g., open data-Open Data Institute, 3 Elgin, 4 DataViva 5 ; spatiotemporal data-GeoBrick [5], Urban Flow prediction [6], Air quality [7], GIS platform [8]; high-dimensional data-Industrial big data [9], IGA-ELM [10], MDS [11], TMAP [12]; time-stamped data-Qubit, 6 Edge MWN [13], Mobi-IoST [14], Edge DHT analytics [15]; real-time data-CUSUM [16], and big data [17]. The NEFD are needed to teach the AI how to use Spark to aggregate, process and analyse the OSINT big data and to process data in RAM using Resilient Distributed Data set (RDD).…”

“…The Bayesian optimisation scenarios will be based on Python libraries, e.g., Hyperopt [33] and optimised through experimenting with black box parameter tuning, e.g., Google Vizier [34] and sequential model-based optimisation [32]. Additional sources for building the training scenario include opensource code, such as Spearmint, 9 Hyperas 10 and Talos. 11 The anticipated problems at this stage include challenges caused by configuration space, dimensionality, and the increasing number of data points.…”