Investigation on Creep Deformation and Age Strengthening Behavior of 304 Stainless Steel under High Stress Levels.

The creep deformation behavior and age strengthening behavior of 304 stainless steel under high stress levels were systematically studied by uniaxial creep test, tensile test, XRD diffraction test and transmission electron microscopy. The results show that the total creep strain and the initial creep strain rate increase with the increase in stress level, and the creep strain in the whole aging process is mainly produced in the initial creep stage. The calculated stress exponent shows that the main mechanism of creep deformation of 304 stainless steel at 453 K is dislocation slip. The strength and plasticity of 304 stainless steel after creep aging are improved simultaneously. Microstructural observations indicate an increase in dislocation density and martensite content, as well as austenite and twins, leading to an improvement in strength and plasticity, respectively. In addition, considering the influence of dislocation density on creep behavior, the relative dislocation density increase is introduced into the hyperbolic sine creep model, and a simple mechanism-based creep aging constitutive model is established. The creep strain predicted by the model is in good agreement with the experimental data of 304 stainless steel. The findings can provide theoretical support for the application of creep age forming in 304 stainless steel parts.

Metal-Metal Bonding Process Research Based on Xgboost Machine Learning Algorithm.

Conventionally, the optimization of bonding process parameters requires multi-parameter repetitive experiments, the processing of data, and the characterization of complex relationships between process parameters, and performance must be achieved with the help of new technologies. This work focused on improving metal-metal bonding performance by applying SLJ experiments, finite element models (FEMs), and the Xgboost machine learning (ML) algorithm. The importance ranking of process parameters on tensile-shear strength (TSS) was evaluated with the interpretation toolkit SHAP (Shapley additive explanations) and it optimized reasonable bonding process parameters. The validity of the FEM was verified using SLJ experiments. The Xgboost models with 70 runs can achieve better prediction results. According to the degree of influence, the process parameters affecting the TSS ranked from high to low are roughness, adhesive layer thickness, and lap length, and the corresponding optimized values were 0.89 µm, 0.1 mm, and 27 mm, respectively. The experimentally measured TSS values increased by 14% from the optimized process parameters via the Xgboost model. ML methods provide a more accurate and intuitive understanding of process parameters on TSS.

Enhancing the diversity of self-replicating structures using active self-adapting mechanisms.

Numerous varieties of life forms have filled the earth throughout evolution. Evolution consists of two processes: self-replication and interaction with the physical environment and other living things around it. Initiated by von Neumann et al. studies on self-replication in cellular automata have attracted much attention, which aim to explore the logical mechanism underlying the replication of living things. In nature, competition is a common and spontaneous resource to drive self-replications, whereas most cellular-automaton-based models merely focus on some self-protection mechanisms that may deprive the rights of other artificial life (loops) to live. Especially, Huang et al. designed a self-adaptive, self-replicating model using a greedy selection mechanism, which can increase the ability of loops to survive through an occasionally abandoning part of their own structural information, for the sake of adapting to the restricted environment. Though this passive adaptation can improve diversity, it is always limited by the loop's original structure and is unable to evolve or mutate new genes in a way that is consistent with the adaptive evolution of natural life. Furthermore, it is essential to implement more complex self-adaptive evolutionary mechanisms not at the cost of increasing the complexity of cellular automata. To this end, this article proposes new self-adaptive mechanisms, which can change the information of structural genes and actively adapt to the environment when the arm of a self-replicating loop encounters obstacles, thereby increasing the chance of replication. Meanwhile, our mechanisms can also actively add a proper orientation to the current construction arm for the sake of breaking through the deadlock situation. Our new mechanisms enable active self-adaptations in comparison with the passive mechanism in the work of Huang et al. which is achieved by including a few rules without increasing the number of cell states as compared to the latter. Experiments demonstrate that this active self-adaptability can bring more diversity than the previous mechanism, whereby it may facilitate the emergence of various levels in self-replicating structures.

Incorporation of Efficient Second-Order Solvers Into Latent Factor Models for Accurate Prediction of Missing QoS Data.

Generating highly accurate predictions for missing quality-of-service (QoS) data is an important issue. Latent factor (LF)-based QoS-predictors have proven to be effective in dealing with it. However, they are based on first-order solvers that cannot well address their target problem that is inherently bilinear and nonconvex, thereby leaving a significant opportunity for accuracy improvement. This paper proposes to incorporate an efficient second-order solver into them to raise their accuracy. To do so, we adopt the principle of Hessian-free optimization and successfully avoid the direct manipulation of a Hessian matrix, by employing the efficiently obtainable product between its Gauss-Newton approximation and an arbitrary vector. Thus, the second-order information is innovatively integrated into them. Experimental results on two industrial QoS datasets indicate that compared with the state-of-the-art predictors, the newly proposed one achieves significantly higher prediction accuracy at the expense of affordable computational burden. Hence, it is especially suitable for industrial applications requiring high prediction accuracy of unknown QoS data.

Generating Highly Accurate Predictions for Missing QoS Data via Aggregating Nonnegative Latent Factor Models.

Automatic Web-service selection is an important research topic in the domain of service computing. During this process, reliable predictions for quality of service (QoS) based on historical service invocations are vital to users. This work aims at making highly accurate predictions for missing QoS data via building an ensemble of nonnegative latent factor (NLF) models. Its motivations are: 1) the fulfillment of nonnegativity constraints can better represent the positive value nature of QoS data, thereby boosting the prediction accuracy and 2) since QoS prediction is a learning task, it is promising to further improve the prediction accuracy with a carefully designed ensemble model. To achieve this, we first implement an NLF model for QoS prediction. This model is then diversified through feature sampling and randomness injection to form a diversified NLF model, based on which an ensemble is built. Comparison results between the proposed ensemble and several widely employed and state-of-the-art QoS predictors on two large, real data sets demonstrate that the former can outperform the latter well in terms of prediction accuracy.

A Nonnegative Latent Factor Model for Large-Scale Sparse Matrices in Recommender Systems via Alternating Direction Method.

Nonnegative matrix factorization (NMF)-based models possess fine representativeness of a target matrix, which is critically important in collaborative filtering (CF)-based recommender systems. However, current NMF-based CF recommenders suffer from the problem of high computational and storage complexity, as well as slow convergence rate, which prevents them from industrial usage in context of big data. To address these issues, this paper proposes an alternating direction method (ADM)-based nonnegative latent factor (ANLF) model. The main idea is to implement the ADM-based optimization with regard to each single feature, to obtain high convergence rate as well as low complexity. Both computational and storage costs of ANLF are linear with the size of given data in the target matrix, which ensures high efficiency when dealing with extremely sparse matrices usually seen in CF problems. As demonstrated by the experiments on large, real data sets, ANLF also ensures fast convergence and high prediction accuracy, as well as the maintenance of nonnegativity constraints. Moreover, it is simple and easy to implement for real applications of learning systems.

A highly efficient approach to protein interactome mapping based on collaborative filtering framework.

The comprehensive mapping of protein-protein interactions (PPIs) is highly desired for one to gain deep insights into both fundamental cell biology processes and the pathology of diseases. Finely-set small-scale experiments are not only very expensive but also inefficient to identify numerous interactomes despite their high accuracy. High-throughput screening techniques enable efficient identification of PPIs; yet the desire to further extract useful knowledge from these data leads to the problem of binary interactome mapping. Network topology-based approaches prove to be highly efficient in addressing this problem; however, their performance deteriorates significantly on sparse putative PPI networks. Motivated by the success of collaborative filtering (CF)-based approaches to the problem of personalized-recommendation on large, sparse rating matrices, this work aims at implementing a highly efficient CF-based approach to binary interactome mapping. To achieve this, we first propose a CF framework for it. Under this framework, we model the given data into an interactome weight matrix, where the feature-vectors of involved proteins are extracted. With them, we design the rescaled cosine coefficient to model the inter-neighborhood similarity among involved proteins, for taking the mapping process. Experimental results on three large, sparse datasets demonstrate that the proposed approach outperforms several sophisticated topology-based approaches significantly.

Reliability prediction of ontology-based service compositions using Petri net and time series models.

OWL-S, one of the most important Semantic Web service ontologies proposed to date, provides a core ontological framework and guidelines for describing the properties and capabilities of their web services in an unambiguous, computer interpretable form. Predicting the reliability of composite service processes specified in OWL-S allows service users to decide whether the process meets the quantitative quality requirement. In this study, we consider the runtime quality of services to be fluctuating and introduce a dynamic framework to predict the runtime reliability of services specified in OWL-S, employing the Non-Markovian stochastic Petri net (NMSPN) and the time series model. The framework includes the following steps: obtaining the historical response times series of individual service components; fitting these series with a autoregressive-moving-average-model (ARMA for short) and predicting the future firing rates of service components; mapping the OWL-S process into a NMSPN model; employing the predicted firing rates as the model input of NMSPN and calculating the normal completion probability as the reliability estimate. In the case study, a comparison between the static model and our approach based on experimental data is presented and it is shown that our approach achieves higher prediction accuracy.