With the widespread use of distributed systems, multi-subspace whole-flow industrial monitoring methods are evolving. However, due to the lack of distinctive features, incipient faults in plant-wide processes are more...
详细信息
ISBN:
(数字)9798350364194
ISBN:
(纸本)9798350364200
With the widespread use of distributed systems, multi-subspace whole-flow industrial monitoring methods are evolving. However, due to the lack of distinctive features, incipient faults in plant-wide processes are more difficult to detect. To improve the detection rate of incipient faults in plant-wide processes while maintaining the generality of the algorithm, a novel double-layer subspace weighted moving window reconstruction independent component analysis (DS-WRICA) method is proposed. In DS-WRICA, process variables are first divided into different subspaces based on process knowledge and data-driven partitioning methods. Secondly, a weighted moving window is used to increase the offset of incipient faults, and monitoring statistics are constructed by combining optimized reconstructed independent component analysis (RICA) and local outlier factor (LOF) in each subspace. Then, the monitoring statistics in each subspace are fused with information by Bayesian inference fusion method to obtain distributed monitoring results. Finally, the effectiveness and superiority of the DS-WRICA method are verified by industrial examples.
A crucial aspect of maintaining a customer-oriented business in the telecommunications sector with machine learning (ML) is understanding the reasons and factors that lead to customer churn. However, the dataset is di...
A crucial aspect of maintaining a customer-oriented business in the telecommunications sector with machine learning (ML) is understanding the reasons and factors that lead to customer churn. However, the dataset is difficult by noise, misclassifications, duplicated data, and imbalanced customer information complicating the process of identifying ways to split the dataset based on events. The under-sampling method address the imbalance data by decreasing the data quantity of majority class, thereby achieving a balanced dataset. This method, utilizing Adaptive k-means clustering, directly determines the reduction based on that data quality in each class. The datasets are combined with class labels to generate a new balanced dataset used for classification in the SVM algorithm, which distinguishes between customer churn and non-churn in the prediction for the telecom sector. The SVM algorithm can perform linear and non-linear classification with a kernel function to control overfitting improve generalization and handle high-dimensional data. The obtained results demonstrate that the proposed method achieves better accuracy of 95.70%, precision of 56.01%, Recall of 55.05%, and F1-score of 96.05% on the telecom churn dataset. These results ensure superior detection and classification performance compared to other existing methods, such as Random Forest (RF), Decision Tree (DT) and K-Nearest Neighbour (KNN).
To develop reliable control systems running on embedded devices, we advice to use domain specified languages. They abstract away the underlying hardware and provide the necessary syntactic sugar to conveniently descri...
To develop reliable control systems running on embedded devices, we advice to use domain specified languages. They abstract away the underlying hardware and provide the necessary syntactic sugar to conveniently describe the most useful control constructs. In addition, such languages can provide toolsets for proving the correctness of programs in them against given formal requirements. In this paper, we consider a partial solution of such a problem related to the formalization of the control code. In our case, syntactic sugar lies in extending the IEC 61131–3 standard for industrial automation languages with explicit statefulness and focusing on logical decomposition of code into processes. The aim of the present paper is to provide approaches and methods for transforming imperative programs in such a promising poST (process-oriented structured text) language into a functional representation for their further proofs using the Isabelle/HOL system. In our solution, we provide insight into three parts of the formalization: (1) the creation of basic data types constituting the original code model, (2) transformation of the poST code model into special representation for execution, and (3) a group of inductive definitions constructing the process of execution. The results represent a complete solution in the form of a formal functional model for the execution of poST programs and then can be used to form and prove theorems based on the model.
With the continuous strengthening of the construction of domestic power grids, in order to efficiently use inspection robots to carry out power inspection work, to meet the needs of the development of the power indust...
详细信息
This paper proposes a distributed computing environment based on data-driven mechanism, which can be deployed on different levels of Industrial Internet, designs and implements an Industrial Internet architecture with...
详细信息
Due to the increasing market share of battery and hybrid electric mobility solutions, there is a high demand for robust manufacturing technologies that enable an efficient high-volume production of powerful electric t...
Due to the increasing market share of battery and hybrid electric mobility solutions, there is a high demand for robust manufacturing technologies that enable an efficient high-volume production of powerful electric traction motors for automotive industry. Within the context of high-quality distributed stator windings, the hairpin technology has become established in automotive production based on advantages regarding the level of automation and productivity in comparison to conventional winding technologies. However, the state-of-the-art industrial process chain, which is based on a sequence of bending, assembly and joining processes, still shows technological weaknesses in terms of process reliability. Besides conventional manufacturing defects caused by misalignment and vibration, the robustness is mainly limited by fluctuating mechanical and geometric properties of the insulated rectangular copper wire which lead to different springback effects within the forming processes: hairpin bending and twisting. Furthermore, geometric defects of hairpin coils also result in a reduced process reliability of the subsequent process steps due to the initial placement of forming in the characteristic sequence of forming operations. Against this background, closed-loop processcontrol concepts for planar bending operations in the context of sequential tool-bound forming of hairpin coils are introduced and validated within this paper.
This paper introduced a method of visual saliency computing with color feature integration based on the psychological experiment. Firstly, based on the results of the psychological experiment of the saliency features,...
详细信息
This paper investigates the finite time stabilization for multi-path cyber physical systems with random denial-of-service (DoS) attacks and time-varying parameters. Unlike previous research, we use auxiliary systems t...
详细信息
ISBN:
(数字)9798331504892
ISBN:
(纸本)9798331504908
This paper investigates the finite time stabilization for multi-path cyber physical systems with random denial-of-service (DoS) attacks and time-varying parameters. Unlike previous research, we use auxiliary systems to establish sufficient conditions for finite time stability in closed-loop multi-path CPSs with various delays and parameters, based on a detailed analysis of the state transition matrix. We also present a condition derived from the Lyapunov function and propose an LMI-based method for designing a non-fragile controller. Finally, we apply these theoretical contributions to a stock investment model to demonstrate their validity.
From the perspective of reducing the configuration complexity of IoT device parameters and improving data security, a lightweight embedded Web server is designed based on the TencentOS tiny operating system to reduce ...
详细信息
In the field of access control locks, conventional methods often require users to download applications with Bluetooth connectivity, and biometric measures such as fingerprints or face recognition that introduce chall...
详细信息
ISBN:
(数字)9798350364507
ISBN:
(纸本)9798350364514
In the field of access control locks, conventional methods often require users to download applications with Bluetooth connectivity, and biometric measures such as fingerprints or face recognition that introduce challenges like access to only authorized parties, limited device accessibility and intricate registration processes. To address these challenges, the research paper presents an innovative IoT-based Smart Door Lock System, aiming to redefine access control. Diverging from traditional approaches, this system eliminates the need for application downloads and simplifies the complexities tied to biometrics. The core innovation lies in the simplicity of a user-friendly 4-digit PIN for primary access, prioritizing ease of use. To overcome real-time access constraints, the system introduces One-time Password (OTP) and One Touch Access (OTA) modes. These modes eliminate the intricacies linked with traditional methods, ensuring immediate and hassle-free access for both authorized and unauthorized users.
暂无评论