Industrial time series determinative anomaly detection based on constraint hypergraph

Liang, Zheng; Wang, Hongzhi; Ding, Xiaoou; Mu, Tianyu

doi:10.1016/j.knosys.2021.107548

Cited by 11 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They can be used not only for data smoothing but also for data prediction. Constraint based methods use dependency between data to check and remedy error [26]. Statistics based algorithms use probabilistic models to learn data statistical characteristics and make inference to data.…”

Section: B Time Series Data Cleaningmentioning

confidence: 99%

Finding the Truth From Uncertain Time Series by Differencing

Sun,

Zhou,

Jiang

2023

IEEE Open J. Comput. Soc.

View full text Add to dashboard Cite

Time series data is ubiquitous and of great importance in real applications. But due to poor qualities and bad working conditions of sensors, time series reported by them contain more or less noises. To reduce noise, multiple sensors are usually deployed to measure an identical time series and from these observations the truth can be estimated, which derives the problem of truth discovery for uncertain time series data. Several algorithms have been proposed, but they mainly focus on minimizing the error between the estimated truth and the observations. In our study, we aim at minimizing the noise in the estimated truth. To solve this optimization problem, we first find out the level of noise produced by each sensor based on differenced time series, which can help estimating the truth wisely. Then, we propose a quadratic optimization model to minimize the noise of the estimated truth. Further, a post process is introduced to refine the result by iteration. Experimental results on both real world and synthetic data sets verify the effectiveness and efficiency of our proposed methods respectively.

show abstract

Section: B Time Series Data Cleaningmentioning

confidence: 99%

Finding the Truth From Uncertain Time Series by Differencing

Sun,

Zhou,

Jiang

2023

IEEE Open J. Comput. Soc.

View full text Add to dashboard Cite

show abstract

“…[76] and used to solve the vacancy value filling problem for time series data. Ding et al [77,78] proposed a correlation-based error detection method for multidimensional time series data, a framework for a multi-role error identification and diagnosis method for four types of data quality rule types, and a solution method based on a weighted set coverage. On this basis, in 2021, Liang et al [79] conducted an example study on power plant IoT timing data to solve the key feature calculation problem of time series data errors using variance constraints, velocity constraints, and similarity rules.…”

Section: Rule-based Error Repairmentioning

confidence: 99%

“…Solving vacancy value filling problems using similarity rules [76] ; correlation-based methods for repairing multidimensional time series data [77,78] ; solving key feature calculation problems for time series data errors using variance constraints, velocity constraints, and similarity rules, etc. [79] repair, and approximate calculation of poor quality tolerance as the main lines.…”

Section: Multi-entity Multiattributementioning

confidence: 99%

IoT data cleaning techniques: A survey

Ding

Wang

et al. 2022

Intell. and Converged Netw.

Self Cite

View full text Add to dashboard Cite

Data cleaning is considered as an effective approach of improving data quality in order to help practitioners and researchers be devoted to downstream analysis and decision-making without worrying about data trustworthiness. This paper provides a systematic summary of the two main stages of data cleaning for Internet of Things (IoT) data with time series characteristics, including error data detection and data repairing. In respect to error data detection techniques, it categorizes an overview of quantitative data error detection methods for detecting single-point errors, continuous errors, and multidimensional time series data errors and qualitative data error detection methods for detecting rule-violating errors. Besides, it provides a detailed description of error data repairing techniques, involving statistics-based repairing, rule-based repairing, and human-involved repairing. We review the strengths and the limitations of the current data cleaning techniques under IoT data applications and conclude with an outlook on the future of IoT data cleaning.

show abstract

“…The LSTM model uses the gradient descent method of backpropagation for optimization. Only the gradient calculation formula of W fx is given here, as shown in Equation (7). Other parameters such as…”

Section: Source Domain Base Models Learningmentioning

confidence: 99%

“…Time-series prediction is an important direction of dynamic data analysis and processing, [1][2][3] and it has important application value in equipment health management, fault prediction, and system twinning in the engineering field. [4][5][6] In practice, the health status of the system is often evaluated based on higher-dimensional time-series data characteristics, [7][8][9] so as to realize the health management of the system. However, the current time-series prediction research is often based on a piece of existing data, which does not have much application value for observing the future health status of the system.…”

Section: Introductionmentioning

confidence: 99%

Multihorizons transfer strategy for continuous online prediction of time‐series data in complex systems

Zhou

Wang

2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

The sustainability online prediction is of great significance for higher horizon time-series prediction in the future, and it embodies higher application value in equipment fault prediction and health management. However, compared with one-step time-series prediction, continuous online prediction faces many uncertainties, including error accumulation and lack of information. To realize continuous online prediction of time-series data in complex systems, this paper proposes a continuous online prediction strategy based on multihorizons transfer (OnMultiHorTS), which is used for continuous online prediction tasks of timeseries data. The algorithm aims to use source domain data to provide more effective information for target prediction tasks. However, the time-varying characteristics of time-series data often lead to large differences in data distribution over a long time span, which is difficult to guarantee the assumption that the data are the same distribution. How to construct more effective source domain information based on historical data and existing data, and apply it to the target domain prediction tasks, is one of the focuses of our OnMultiHorTS algorithm. In addition, different from the typical iterative and multistep advance prediction methods, the proposed algorithm regards different prediction tasks as different horizons, which are

show abstract

Industrial time series determinative anomaly detection based on constraint hypergraph

Cited by 11 publications

References 17 publications

Finding the Truth From Uncertain Time Series by Differencing

Finding the Truth From Uncertain Time Series by Differencing

IoT data cleaning techniques: A survey

Multihorizons transfer strategy for continuous online prediction of time‐series data in complex systems

Contact Info

Product

Resources

About