A Hybrid Ensemble Deep Learning Approach for Early Prediction of Battery Remaining Useful Life

Accurate estimation of the remaining useful life(RUL)of lithium-ion batteries is critical for their large-scale deployment as energy storage devices in electric vehicles and stationary storage.A fundamental understanding of the factors affecting RUL is crucial for accelerating battery technology development.However,it is very challenging to predict RUL accurately because of complex degradation mechanisms occurring within the batteries,as well as dynamic operating conditions in practical applications.Moreover,due to insignificant capacity degradation in early stages,early prediction of battery life with early cycle data can be more difficult.In this paper,we propose a hybrid deep learning model for early prediction of battery RUL.The proposed method can effectively combine handcrafted features with domain knowledge and latent features learned by deep networks to boost the performance of RUL early prediction.We also design a non-linear correlation-based method to select effective domain knowledge-based features.Moreover,a novel snapshot ensemble learning strategy is proposed to further enhance model generalization ability without increasing any additional training cost.Our experimental results show that the proposed method not only outperforms other approaches in the primary test set having a similar distribution as the training set,but also generalizes well to the secondary test set having a clearly different distribution with the training set.The PyTorch implementation of our proposed approach is available at https://github.com/batteryrul/battery_rul_early_prediction.

A Review on Swarm Intelligence and Evolutionary Algorithms for Solving Flexible Job Shop Scheduling Problems

Flexible job shop scheduling problems(FJSP)have received much attention from academia and industry for many years.Due to their exponential complexity,swarm intelligence(SI)and evolutionary algorithms(EA)are developed,employed and improved for solving them.More than 60%of the publications are related to SI and EA.This paper intents to give a comprehensive literature review of SI and EA for solving FJSP.First,the mathematical model of FJSP is presented and the constraints in applications are summarized.Then,the encoding and decoding strategies for connecting the problem and algorithms are reviewed.The strategies for initializing algorithms?population and local search operators for improving convergence performance are summarized.Next,one classical hybrid genetic algorithm(GA)and one newest imperialist competitive algorithm(ICA)with variables neighborhood search(VNS)for solving FJSP are presented.Finally,we summarize,discus and analyze the status of SI and EA for solving FJSP and give insight into future research directions.

Position Encoding Based Convolutional Neural Networks for Machine Remaining Useful Life Prediction

Accurate remaining useful life(RUL)prediction is important in industrial systems.It prevents machines from working under failure conditions,and ensures that the industrial system works reliably and efficiently.Recently,many deep learning based methods have been proposed to predict RUL.Among these methods,recurrent neural network(RNN)based approaches show a strong capability of capturing sequential information.This allows RNN based methods to perform better than convolutional neural network(CNN)based approaches on the RUL prediction task.In this paper,we question this common paradigm and argue that existing CNN based approaches are not designed according to the classic principles of CNN,which reduces their performances.Additionally,the capacity of capturing sequential information is highly affected by the receptive field of CNN,which is neglected by existing CNN based methods.To solve these problems,we propose a series of new CNNs,which show competitive results to RNN based methods.Compared with RNN,CNN processes the input signals in parallel so that the temporal sequence is not easily determined.To alleviate this issue,a position encoding scheme is developed to enhance the sequential information encoded by a CNN.Hence,our proposed position encoding based CNN called PE-Net is further improved and even performs better than RNN based methods.Extensive experiments are conducted on the C-MAPSS dataset,where our PE-Net shows state-of-the-art performance.

Short-term Ocular Toxicity and Eye Irritation Tests Following Application of Sufentanil in Rabbits

Purpose:.To test the safe clinical application of sufentanil as topical ophthalmic drops by examining treated rabbit eyes for ophthalmic irritation signs or short-time toxic reactions.Methods:.Twenty-four rabbits were randomly divided into 8groups(n=3): The ocular toxicity at 14 d after eye drop administration was evaluated in groups 1 to 4, and at 30 d postadministration in groups 5 to 8..Groups 1 and 5 were treated with blank vehicle and served as normal controls..The left eyes of rabbits in groups 2 and 6 were exposed to low-dose sufentanil(5 μg, 2 drops within 5 min), groups 3 and 7 received moderate-dose sufentanil.(7.5 μg, 3 drops within 10 min),and groups 4 and 8 received high-dose sufentanil(10 μg,.4drops within 15 min). As self-controls, the right eyes of each rabbit were administered an equivalent amount of sodium chloride(9 g / L) at the same drop intervals. At 14 and 30 d after exposure to sufentanil,.ophthalmic irritation signs were evaluated and corneas were stained with fluorescein and observed by slit-lamp microscopy..Corneal endothelial counts were performed and toxic reactions were evaluated.Results: Multiple parameters were compared in the control and experimental groups by visual inspection and slit-lamp examination at 14 and 30 d after sufentanil administration..No evidence of irritation signs(including corneal opacity,.conjunctival congestion, or edema), eye secretions, iris abnormalities,.or temporal eye closure were noted..Corneal endothelial cell counts did not significantly differ between the control and experimental groups..Light microscopy revealed no pathological or morphological injury to the cornea, conjunctiva, iris, ciliary body, retina, or optic nerve in either group.The same observation outcomes were noted at 14 and 30 d after administration.Conclusion:.Single ocular administration of sufentanil at a dose of 5-10 μg in rabbits yields no ocular irritation or toxic responses at 14 or 30 d following eye drop delivery.

Modeling dynamic assessment of ecosystem services based on remote sensing technology:A sampling of the Gansu grassland ecosystem

The ecosystem is important because it is the life sustaining system for human survival.Three ecosystem characteristics are:regional particularities,ecosystem complexity and conventional cultural particularities.This paper develops a remote sensing based dynamic model to assess grassland ecosystem service values involving multidisciplinary knowledge.The ecological value of grassland ecosystems is focused on using a remote sensing technique in the model,and setting up the framework for a dynamic assessing model.The grassland ecological services condition and value in 1985 is used as the benchmark.The dynamic model has two adjusting indicators:biomass and price index.The biomass is simulated using the CASA(Carnegie-Ames-Stanford Approach) model.The price index was obtained from statistics data published by the statistical bureau.Results show that the grassland ecosystem value in Gansu Province was 28.36 billion Chinese Yuan in 1985,140.37 billion in 1999 and 130.86 billion in 2002.

Differentiation of human epidermis-derived mesenchymal stem cell-like pluripotent cells into neural-like cells in culture and after transplantation

Skin is the largest organ of the human body and a possible source of stem cells for research and cell-based therapy. We have isolated a population of mesenchymal stem cell-like pluripotent cells from human epidermis, termed human (h) EMSCPCs. This preliminary study tested if these hEMSCPCs can be induced to differentiate into neural-like cells. Human EMSCPCs were first cultured for four to seven days in a serum-free neural stem cell (NSC) medium for pre-induction. During pre-induction, hEMSCPCs coalesced into dense spheres that resembled neural rosettes. In the presence of a conditioned differentiation medium, pre-induced cells took on the morphological characteristics of neural cells, including slender projections with inflated or claw-like ends that contacted the soma or projections of other cells as revealed by confocal microscopy. Moreover, these differentiating cells expressed the neural-specific markers β-III tubulin, MAP2, GFAP, and synapsin I as evidenced by immunocytochemistry. Both pre-induced hEMSCPCs and uninduced hEMSCPCs were labeled with CM-DiI and transplanted into the vitreous cavities of nude mice. Transplanted cells were examined four weeks later in frozen eyeball sections by immunofluorescence staining, which demonstrated superior retinal migration and neural differentiation of pre-induced cells. Our study is the first to demonstrate that hEMSCPCs possess the capacity to differentiate into neural-like cells, suggesting potential uses for the treatment of retinal diseases such as age-related macular degeneration.

DDUC:an erasure-coded system with decoupled data updating and coding

In distributed storage systems,replication and erasure code(EC)are common methods for data redundancy.Compared with replication,EC has better storage efficiency,but suffers higher overhead in update.Moreover,consistency and reliability problems caused by concurrent updates bring new challenges to applications of EC.Many works focus on optimizing the EC solution,including algorithm optimization,novel data update method,and so on,but lack the solutions for consistency and reliability problems.In this paper,we introduce a storage system that decouples data updating and EC encoding,namely,decoupled data updating and coding(DDUC),and propose a data placement policy that combines replication and parity blocks.For the(N,M)EC system,the data are placed as N groups of M+1 replicas,and redundant data blocks of the same stripe are placed in the parity nodes,so that the parity nodes can autonomously perform local EC encoding.Based on the above policy,a two-phase data update method is implemented in which data are updated in replica mode in phase 1,and the EC encoding is done independently by parity nodes in phase 2.This solves the problem of data reliability degradation caused by concurrent updates while ensuring high concurrency performance.It also uses persistent memory(PMem)hardware features of the byte addressing and eight-byte atomic write to implement a lightweight logging mechanism that improves performance while ensuring data consistency.Experimental results show that the concurrent access performance of the proposed storage system is 1.70–3.73 times that of the state-of-the-art storage system Ceph,and the latency is only 3.4%–5.9%that of Ceph.

Construction of single-chromosome DNA library from Lilium regale Wilson

A protocol of simple rapid microdissection of single-chromosome, amplification and cloning of its DNA from Lilium regale Wilson is described. Single-chromosome, microdissected by micromanipulator, was put into a 0 5 mL Eppendorf tube and digested with Sau3A, and then the Sau3A linker adaptors were ligated to the ends of DNA fragments. After 2 rounds of PCR amplification with one chain of linker adaptor as primer, the PCR products thus obtained have a length of 300-2 500 base pairs (bp) with predominant fragments at about 1 000 bp. Southern blot analysis confirmed that the PCR products originated from the genome of Lilium regale Wilson. By cloning the amplification products from the second round of PCR, single-chromosome DNA library was constructed, in which about as many as 100 000 recombinant clones were produced. A total number of 84 clones were analysed, and it was revealed that the inserts ranged in size from 300 to 1 800 bp, with an average of 780 bp. Compared with the methods described in other literature, this protocol, eliminating the need for enzymatic digestion and ligating micromanipulation of chromosomal DNA in nanoliter volumes, permits the efficient amplification of single chromosome (not tens of chromosomes as reported before) and the fragments (780 bp in average) cloned in this study are longer than those reported before (650 bp in average).

Chromosome microdissection by laser microbeam, chromosomal fragment isolation and amplification in vitro in barley (Hordeum vulgare L.)

A method for microdissection, isolation and amplification of plant chromosomal fragments using laser microbeam and a glass microneedle was established. Firstly, 7H chromosome of barley (Hordeum vulgare L.) was dissected by Nd: YAG laserbeam with suitable parameters and the fragment comprising a satellite was isolated with a glass microneedle which was fixed on a micromanipulator. Then, the chromosomal fragment DNA was amplified by LA_PCR (linker adaptor PCR) for two rounds. The size of the DNA fragments of PCR products varied from 500-3 000 bp and the PCR products originated from the genome of barley were verified by Southern hybridization. Compared with previous reports, there are some advantages in this research. The performance is easier, the dissection is more precise and the cost is low. It also permits efficient amplification with only one single chromosome fragment. Laser microbeam_glass microneedle method may be useful in the microdissection of special chromosome regions, especially in plants with middle or small chromosomes.