基于虚拟印刷故障培训系统的学习模块研究

为了提供一个基于计算机的虚拟印刷故障学习与培训平台,构建了由学习模块和诊断模块构成的虚拟印刷故障培训系统。其中的学习模块以掌握印刷故障的基本知识和培训基本技能为目标,以数据库为技术支撑,以"故障学习"和"虚拟实践"为子模块。通过研究子模块的基本功能、构建方法和信息检索流程,为虚拟印刷故障培训系统学习模块的开发奠定基础。     

缺省AR－规则在常识推理中的应用

基于模糊逻辑的常识表示与推理是人工智能基础研究的一个新领域，它处理常识的不完全性、不确定性以及例外情形。本文把缺省逻辑的基本思想推广到近似推理理论中，并通过几个实例说明缺省ＡＲ－规则在常识表示与推理中的作用。     

缺省知识与近似推理

基于模糊逻辑的常识表示与推理是人工智能基础研究的一个新领域，它处理常识的不完全性、不确定性，以及例外情形。本文提出一种新的方法，把缺省逻辑的基本思想推广到近似推理理论中，并用缺省ＡＲ－规则来表示缺省知识。     

A Multi-Feature Learning Model with Enhanced Local Attention for Vehicle Re-Identification

Vehicle re-identification (ReID) aims to retrieve the target vehicle in an extensive image gallery through its appearances from various views in the cross-camera scenario. It has gradually become a core technology of intelligent transportation system. Most existing vehicle re-identification models adopt the joint learning of global and local features. However, they directly use the extracted global features, resulting in insufficient feature expression. Moreover, local features are primarily obtained through advanced annotation and complex attention mechanisms, which require additional costs. To solve this issue, a multi-feature learning model with enhanced local attention for vehicle re-identification (MFELA) is proposed in this paper. The model consists of global and local branches. The global branch utilizes both middle and high-level semantic features of ResNet50 to enhance the global representation capability. In addition, multi-scale pooling operations are used to obtain multi-scale information. While the local branch utilizes the proposed Region Batch Dropblock (RBD), which encourages the model to learn discriminative features for different local regions and simultaneously drops corresponding same areas randomly in a batch during training to enhance the attention to local regions. Then features from both branches are combined to provide a more comprehensive and distinctive feature representation. Extensive experiments on VeRi-776 and VehicleID datasets prove that our method has excellent performance.     

A refinement strategy for identification of scientific software from bioinformatics publications

In the field of bioinformatics, a large number of classical software becomes a necessary research tool. To measure the influence of scientific software as one kind of important intellectual products, a few strategies have been proposed to identify the software names from full texts of papers to collect the usage data of packages in bioinformatics research. However, the performance of these strategies is limited because of the highly imbalance of data in the full texts. This study proposes EnsembleSVMs-CRF, a two-step refinement strategy based on ensemble learning that gradually increases the sentences that contain software mentions to improve the performance of named entity recognition. The experiment on the bioinformatics corpus shows that the performance of EnsembleSVMs-CRF, in terms of the local F1 (78.81%) and the global F1-A (73.49%), is superior to the rule-based bootstrapping method and direct CRF. Application of this strategy to the articles published between 2013 and 2017 in 27 bioinformatics journals extracted 8,239 unique packages. The most popular 50 packages thus identified demonstrate that most of them are professional software which generally requires inter-discipline knowledge, rather than programming skill. Meanwhile, we found that researchers in bioinformatics tend to use free scientific software, and the application of general software is increasing compared with professional software.

     

A framework for understanding the emotional impacts in virtual sport training

The efficiency of motor skill acquisition is crucial for sport training. In sport training, virtual reality technology is an implement that could help athletes adjust their movements more precisely in different tasks. However, while training in a simulated environment, an athlete's emotional needs are often overlooked despite the fact that these needs may affect user's physical performance directly and apparently.

In this work, relevant studies in motor skill learning, the formats of feedback and the emotions in virtual training were thoroughly reviewed. Based on the literature reviewed, a framework of a virtual sport training system is proposed. In the proposed framework, elements of the system were illustrated by highlighting the emotional impacts, which were followed by each feedback during training. It appears that virtual sport training is a promising research direction. It is envisaged that the proposed prototype system would be applicable to cater to athlete's overall experiences.     

A learning-based methodology for dynamic scheduling in distributed manufacturing systems

To enhance productivity in a distributed manufacturing system under hierarchical control, we develop a framework of dynamic scheduling scheme that explores routeing flexibility and handles uncertainties. We propose a learning-based methodology to extract scheduling knowledge for dispatching parts to machines. The proposed methodology includes three modules: discrete-event simulation, instance generation, and incremental induction. First, a sophisticated simulation module is developed to implement a dynamic scheduling scheme, to generate training examples, and to evaluate the methodology. Second, the search for training examples (good schedules) is successfully fulfilled by the genetic algorithm. Finally, we propose a tolerance-based learning algorithm that does not only acquire general scheduling rules from the training examples, but also adapts to any newly observed examples and thus facilitates knowledge modification. The experimental results show that the dynamic scheduling scheme significantly outperforms the static scheduling scheme with a single dispatching rule in a distributed manufacturing system.     

Learning beyond ‘hands and feet’ in offshore helicopter operations: integrating the individual with the social in CRM and SA

Abstract

This article makes situated learning theories central to an analysis of offshore helicopter in-flight emergency response, where rule following is mandatory for safety reasons. We examine the ways in which individual learning is connected to situated learning, particularly as relates to multiple forms of knowledge and directive documentation such as standard operating procedures and emergency checklists. The analysis connects to sociotechnical skills, contextual factors, and organizational culture; details five generations of crew resource management (CRM) training, positioning this research within the fifth generation and in relation to situation awareness (SA). It describes and provides guidance on how training, which is focused on error recognition, management, and mitigation, as well as communication, understanding, and innovation, can improve CRM performance. Finally, we make recommendations for future research based on our analysis for combining CRM and SA in ways that enable the sharing of tacit knowledge to increase pilots’ understanding of their work through legitimate peripheral participation.     

堆叠自编码器在样本不充足下的轴承故障诊断方法

深度学习作为一种实用的大数据处理工具,在机械智能故障诊断领域也受到广泛关注,许多研究者已经成功地将深度学习模型应用于故障诊断领域.但这些研究往往忽略了两个重要的问题:(1)当原始训练数据集不足时,模型训练过程不理想;(2)网络模型的学习内容不明确.为了克服上述不足,提出一种新的数据增强的堆叠自编码器(DESAE)框架,...     

基于概念漂移检测的制冷系统故障诊断模型自适应

制冷系统实际运行中,故障诊断模型可能出现诊断性能波动或下降等情况,需具备再学习能力以适应现场数据。本文设计了一种基于正确率阈值的概念漂移检测机制及支持向量机增量学习的故障诊断自适应模型,并将其应用于制冷剂过量故障的再学习。该算法通过两次优化选择、过滤数据信息,保留原有诊断知识,仅学习未知样本信息,可极大地节约模型学习时间,快速适应新环境。结果表明,新的故障种类出现时,诊断模型检测到概念漂移,进而通过增量学习进行自我更新,实现对新故障的学习与诊断。1 400个过量故障样本中诊断模型只需要学习600个,且保证最终模型对后续数据流具有较佳诊断性能,正确率高达99%。在现场制冷系统故障诊断应用中,诊断模型的再学习和自适应体现出良好的应用前景。     

A generalized finite element method with global-local enrichment functions for confined plasticity problems

The main feature of partition of unity methods such as the generalized or extended finite element method is their ability of utilizing a priori knowledge about the solution of a problem in the form of enrichment functions. However, analytical derivation of enrichment functions with good approximation properties is mostly limited to two-dimensional linear problems. This paper presents a procedure to numerically generate proper enrichment functions for three-dimensional problems with confined plasticity where plastic evolution is gradual. This procedure involves the solution of boundary value problems around local regions exhibiting nonlinear behavior and the enrichment of the global solution space with the local solutions through the partition of unity method framework. This approach can produce accurate nonlinear solutions with a reduced computational cost compared to standard finite element methods since computationally intensive nonlinear iterations can be performed on coarse global meshes after the creation of enrichment functions properly describing localized nonlinear behavior. Several three-dimensional nonlinear problems based on the rate-independent J ₂ plasticity theory with isotropic hardening are solved using the proposed procedure to demonstrate its robustness, accuracy and computational efficiency.     

Synaptic Resistors for Concurrent Inference and Learning with High Energy Efficiency

The fastest supercomputer, Summit, has a speed comparable to the human brain, but is much less energy‐efficient (≈10¹⁰ FLOPS W^?1, floating point operations per second per watt) than the brain (≈10¹⁵ FLOPS W^?1). The brain processes and learns from “big data” concurrently via trillions of synapses in parallel analog mode. By contrast, computers execute algorithms on physically separated logic and memory transistors in serial digital mode, which fundamentally restrains computers from handling “big data” efficiently. The existing electronic devices can perform inference with high speeds and energy efficiencies, but they still lack the synaptic functions to facilitate concurrent convolutional inference and correlative learning efficiently like the brain. In this work, synaptic resistors are reported to emulate the analog convolutional signal processing, correlative learning, and nonvolatile memory functions of synapses. By circumventing the fundamental limitations of computers, a synaptic resistor circuit performs speech inference and learning concurrently in parallel analog mode with an energy efficiency of ≈1.6 × 10¹⁷ FLOPS W^?1, which is about seven orders of magnitudes higher than that of the Summit supercomputer. Scaled‐up synstor circuits could circumvent the fundamental limitations in computers, and facilitate real‐time inference and learning from “big data” with high efficiency and speed in intelligent systems.     

A hybrid SVM and supervised learning approach to fuzzy min‐max hyperbox classifiers

Abstract

In this paper, a fuzzy min‐max hyperbox classifier is designed to solve M‐class classification problems using a hybrid SVM and supervised learning approach. In order to solve a classification problem, a set of training patterns is gathered from a considered classification problem. However, the training set may include several noisy patterns. In order to delete the noisy patterns from the training set, the support vector machine is applied to find the noisy patterns so that the remaining training patterns can describe the behavior of the considered classification system well. Subsequently, a supervised learning method is proposed to generate fuzzy min‐max hyperboxes for the remaining training patterns so that the generated fuzzy min‐max hyperbox classifier has good generalization performance. Finally, the Iris data set is considered to demonstrate the good performance of the proposed approach for solving this classification problem.     

A genetic algorithm with domain knowledge for weapon‐target assignment problems

Abstract

In this paper, a novel genetic algorithm, including domain specific knowledge into the crossover operator and the local search mechanism for solving weapon‐target assignment (WTA) problems is proposed. The WTA problem is a full assignment of weapons to hostile targets with the objective of minimizing the expected damage value to own‐force assets. It is an NP‐complete problem. In our study, a greedy reformation and a new crossover operator are proposed to improve the search efficiency. The proposed algorithm outperforms its competitors on all test problems.     

A Robust Transfer Dictionary Learning Algorithm for Industrial Process Monitoring

Data-driven process-monitoring methods have been the mainstream for complex industrial systems due to their universality and the reduced need for reaction mechanisms and first-principles knowledge. However, most data-driven process-monitoring methods assume that historical training data and online testing data follow the same distribution. In fact, due to the harsh environment of industrial systems, the collected data from real industrial processes are always affected by many factors, such as the changeable operating environment, variation in the raw materials, and production indexes. These factors often cause the distributions of online monitoring data and historical training data to differ, which induces a model mismatch in the process-monitoring task. Thus, it is difficult to achieve accurate process monitoring when a model learned from training data is applied to actual online monitoring. In order to resolve the problem of the distribution divergence between historical training data and online testing data that is induced by changeable operation environments, a robust transfer dictionary learning (RTDL) algorithm is proposed in this paper for industrial process monitoring. The RTDL is a synergy of representative learning and domain adaptive transfer learning. The proposed method regards historical training data and online testing data as the source domain and the target domain, respectively, in the transfer learning problem. Maximum mean discrepancy regularization and linear discriminant analysis-like regularization are then incorporated into the dictionary learning framework, which can reduce the distribution divergence between the source domain and target domain. In this way, a robust dictionary can be learned even if the characteristics of the source domain and target domain are evidently different under the interference of a realistic and changeable operation environment. Such a dictionary can effectively improve the performance of process monitoring and mode classification. Extensive experiments including a numerical simulation and two industrial systems are conducted to verify the efficiency and superiority of the proposed method.     

Statistical transfer learning: A review and some extensions to statistical process control

ABSTRACT

The rapid development of information technology, together with advances in sensory and data acquisition techniques, has led to the increasing necessity of handling datasets from multiple domains. In recent years, transfer learning has emerged as an effective framework for tackling related tasks in target domains by transferring previously-acquired knowledge from source domains. Statistical models and methodologies are widely involved in transfer learning and play a critical role, which, however, has not been emphasized in most surveys of transfer learning. In this article, we conduct a comprehensive literature review on statistical transfer learning, i.e., transfer learning techniques with a focus on statistical models and statistical methodologies, demonstrating how statistics can be used in transfer learning. In addition, we highlight opportunities for the use of statistical transfer learning to improve statistical process control and quality control. Several potential future issues in statistical transfer learning are discussed.     

A Global Training Model for Beat Classification Using Basic Electrocardiogram Morphological Features

Clinical Study and automatic diagnosis of electrocardiogram (ECG) data always remain a challenge in diagnosing cardiovascular activities. The analysis of ECG data relies on various factors like morphological features, classification techniques, methods or models used to diagnose and its performance improvement. Another crucial factor in the methodology is how to train the model for each patient. Existing approaches use standard training model which faces challenges when training data has variation due to individual patient characteristics resulting in a lower detection accuracy. This paper proposes an adaptive approach to identify performance improvement in building a training model that analyze global training methodology against an individual training methodology and identifying a gap between them. We provide our investigation and comparative study on these methods and model with standard classification techniques with basic morphological features and Heart Rate Variability (HRV) that may aid real time application. This approach helps in analyzing and evaluating the performance of different techniques and can suggests adoption of a best model identification with efficient technique and efficient attribute set for real-time systems.

     

A fuzzy lot-sizing problem with two-stage composite human learning

Due to the repetitive nature of inventory planning over the planning horizon, the operator in charge has to perform planning tasks repetitively, and consequently s/he becomes more familiar with the tasks over time. Familiarity with the tasks suggests that learning takes place in inventory planning. Even though the operator’s learning over time might improve his/her efficiency, prior research on fuzzy lot-sizing problems mostly overlooked the effect of human learning in their models and its impact on the operator’s performance. To close the research gap in this area, this paper models the operator's learning in a fuzzy economic order quantity model with backorders. The paper models a situation where the operator applies the acquired knowledge over the cycles in setting the fuzzy parameters at the beginning of every planning cycle, where his/her learning ability includes the cognitive and motor capabilities of a human being. Subsequently, a mathematical model which takes account of a two-stage human learning over the planning cycles is developed, which is then analytically investigated using sample data-sets. The results indicate that both operator’s capabilities, cognitive and motor, affect the efficiency of the fuzzy lot-sizing inventory model, but the influence of the cognitive capability is more profound, which in turn suggests the importance of training programmes for the workforces. The results of the sensitivity analysis also draw some managerial insights for the case that some model parameters vary over the planning horizon.     

Accurate Multi-Scale Feature Fusion CNN for Time Series Classification in Smart Factory

Time series classification (TSC) has attracted various attention in the community of machine learning and data mining and has many successful applications such as fault detection and product identification in the process of building a smart factory. However, it is still challenging for the efficiency and accuracy of classification due to complexity, multi-dimension of time series. This paper presents a new approach for time series classification based on convolutional neural networks (CNN). The proposed method contains three parts: short-time gap feature extraction, multi-scale local feature learning, and global feature learning. In the process of short-time gap feature extraction, large kernel filters are employed to extract the features within the short-time gap from the raw time series. Then, a multi-scale feature extraction technique is applied in the process of multi-scale local feature learning to obtain detailed representations. The global convolution operation with giant stride is to obtain a robust and global feature representation. The comprehension features used for classifying are a fusion of short time gap feature representations, local multi-scale feature representations, and global feature representations. To test the efficiency of the proposed method named multi-scale feature fusion convolutional neural networks (MSFFCNN), we designed, trained MSFFCNN on some public sensors, device, and simulated control time series data sets. The comparative studies indicate our proposed MSFFCNN outperforms other alternatives, and we also provided a detailed analysis of the proposed MSFFCNN.