Saved Queries

by Filippo Luca Gurgoglione, Mattia De Gregorio, Giorgio Benatti, Davide Donelli, Luigi Vignali, Emilia Solinas, Iacopo Tadonio, Andrea Denegri, Marco Covani, Gabriella Dallaglio, Bernardo Cortese and Giampaolo Niccoli

Future Pharmacol. 2024, 4(4), 775-787; https://doi.org/10.3390/futurepharmacol4040041 (registering DOI) - 2 Nov 2024

Abstract

Drug-coated balloons (DCBs) have emerged as an increasingly valuable option for the treatment of coronary artery disease (CAD). Percutaneous coronary intervention (PCI) with DCBs enables the localized delivery of antiproliferative drugs directly to the target coronary lesion, avoiding the need for permanent scaffold implantation. Historically, paclitaxel-coated balloons (PCBs) have been the most used device in this context. Paclitaxel interferes with intracellular microtubule function, leading to cell cycle arrest. However, its cytotoxicity at a higher dosage and narrow therapeutic range has raised some safety concerns. To address these issues, sirolimus-coated balloons (SCBs) have been introduced as an alternative. Sirolimus acts as a cytostatic agent with potent anti-inflammatory and antiproliferative properties and is characterized by a wider therapeutic range, potentially offering a safer profile. Several experimental and clinical studies comparing the safety and efficacy of PCBs versus SCBs have yielded mixed results. Recently, a novel DCB (SirPlux Duo), which simultaneously releases both paclitaxel and sirolimus, has been tested in a porcine coronary model with promising results. In this review, we will elucidate the mechanisms of action of paclitaxel and sirolimus, examine contemporary preclinical and clinical evidence comparing PCB and SCB angioplasty, and discuss novel devices that may enhance the safety and efficacy of PCI with DCBs. Full article

►▼ Show Figures

Figure 1

29 pages, 3537 KiB

Open AccessArticle

Dynamic Integrated Scheduling of Production Equipment and Automated Guided Vehicles in a Flexible Job Shop Based on Deep Reinforcement Learning

by Jingrui Wang, Yi Li, Zhongwei Zhang, Zhaoyun Wu, Lihui Wu, Shun Jia and Tao Peng

Processes 2024, 12(11), 2423; https://doi.org/10.3390/pr12112423 (registering DOI) - 2 Nov 2024

Abstract

The high-quality development of the manufacturing industry necessitates accelerating its transformation towards high-end, intelligent, and green development. Considering logistics resource constraints, the impact of dynamic disturbance events on production, and the need for energy-efficient production, the integrated scheduling of production equipment and automated guided vehicles (AGVs) in a flexible job shop environment is investigated in this study. Firstly, a static model for the integrated scheduling of production equipment and AGVs (ISPEA) is developed based on mixed-integer programming, which aims to optimize the maximum completion time and total production energy consumption (EC). In recent years, reinforcement learning, including deep reinforcement learning (DRL), has demonstrated significant advantages in handling workshop scheduling issues with sequential decision-making characteristics, which can fully utilize the vast quantity of historical data accumulated in the workshop and adjust production plans in a timely manner based on changes in production conditions and demand. Accordingly, a DRL-based approach is introduced to address the common production disturbances in emergency order insertions. Combined with the characteristics of the ISPEA problem and an event-driven strategy for handling dynamic events, four types of agents, namely workpiece selection, machine selection, AGV selection, and target selection agents, are set up, which refine workshop production status characteristics as observation inputs and generate rules for selecting workpieces, machines, AGVs, and targets. These agents are trained offline using the QMIX multi-agent reinforcement learning framework, and the trained agents are utilized to solve the dynamic ISPEA problem. Finally, the effectiveness of the proposed model and method is validated through a comparison of the solution performance with other typical optimization algorithms for various cases. Full article

(This article belongs to the Topic AI and IoT for Promoting Green Operation and Sustainable Environment)

►▼ Show Figures

Figure 1

22 pages, 2780 KiB

Open AccessArticle

Tracing ALS Degeneration: Insights from Spinal Cord and Cortex Transcriptomes

by Nela Pragathi Sneha, S. Akila Parvathy Dharshini, Y.-h. Taguchi and M. Michael Gromiha

Genes 2024, 15(11), 1431; https://doi.org/10.3390/genes15111431 (registering DOI) - 2 Nov 2024

Abstract

Background/Objectives: Amyotrophic Lateral Sclerosis is a progressive neurodegenerative disorder characterized by the loss of upper and lower motor neurons. Key factors contributing to neuronal death include mitochondrial energy damage, oxidative stress, and excitotoxicity. The frontal cortex is crucial for action initiation, planning, and voluntary movements whereas the spinal cord facilitates communication with the brain, walking, and reflexes. By investigating transcriptome data from the frontal cortex and spinal cord, we aim to elucidate common pathological mechanisms and pathways involved in ALS for understanding the disease progression and identifying potential therapeutic targets. Methods: In this study, we quantified gene and transcript expression patterns, predicted variants, and assessed their functional effects using computational tools. It also includes predicting variant-associated regulatory effects, constructing functional interaction networks, and performing a gene enrichment analysis. Results: We found novel genes for the upregulation of immune response, and the downregulation of metabolic-related and defective degradation processes in both the spinal cord and frontal cortex. Additionally, we observed the dysregulation of histone regulation and blood pressure-related genes specifically in the frontal cortex. Conclusions: These results highlight the distinct and shared molecular disruptions in ALS, emphasizing the critical roles of immune response and metabolic dysfunction in neuronal degeneration. Targeting these pathways may provide new therapeutic avenues to combat neurodegeneration and preserve neuronal health. Full article

(This article belongs to the Section Bioinformatics)

►▼ Show Figures

Figure 1

15 pages, 792 KiB

Open AccessReview

Impact of Reductive Stress on Human Infertility: Underlying Mechanisms and Perspectives

by Efthalia Moustakli, Athanasios Zikopoulos, Charikleia Skentou, Periklis Katopodis, Ekaterini Domali, Anastasios Potiris, Sofoklis Stavros and Athanasios Zachariou

Int. J. Mol. Sci. 2024, 25(21), 11802; https://doi.org/10.3390/ijms252111802 (registering DOI) - 2 Nov 2024

Abstract

Antioxidants have a well-established effect on general health and are essential in preventing oxidative damage to cells by scavenging free radicals. Free radicals are thought to be neutralized by these substances, which include polyphenols, β-carotene, and vitamins C and E, reducing cellular damage. On the other hand, recent data indicates that consuming excessive amounts of antioxidants may have side effects. Apoptosis and cell signaling are two beneficial physiological processes that are affected by excessive supplementation. Other negative effects include paradoxical enhancement of oxidative stress and unbalanced cellular redox potential. Overdosing on particular antioxidants has been associated with increased medication interactions, cancer progression, and fatality risks. Additionally, the complex impacts they may have on fertility might be both useful and adverse, depending on the quantity and duration of usage. This review delves into the dual role of antioxidants and emphasizes the importance of employing antioxidants in moderation. Antioxidant overconsumption may disrupt the oxidative balance necessary for normal sperm and oocyte function, which is one of the potential negative effects of antioxidants on fertility in both males and females that are also investigated. Although modest usage of antioxidants is generally safe and useful, high levels of antioxidants can upset hormonal balance, impair sperm motility, and negatively impact the outcomes of assisted reproductive technologies (ART). The findings emphasize the need to use antioxidant supplements in a balanced way, the importance of further research to optimize their use in fertility treatments, and the importance of supporting reproductive health to avoid adverse effects. Full article

(This article belongs to the Special Issue The Role of Oxidative Stress and Antioxidants in Human Disease)

►▼ Show Figures

Figure 1

14 pages, 2862 KiB

Open AccessArticle

Immune Suppression and Rapid Invasion of Nile Tilapia Gills Following an Acute Challenge by Flavobacterium Davisii

by Yingxuan Xu, Shifeng Wang, Yongcan Zhou, Zhenyu Xie, Bei Wang, Zhangding Zhao, Wenlong Cai, Peibo Wang, Weiliang Guo, Dongdong Zhang and Zhi Ye

Biology 2024, 13(11), 894; https://doi.org/10.3390/biology13110894 (registering DOI) - 2 Nov 2024

Abstract

Flavobacterium davisii is one of the causative agents of columnaris disease, significantly impacting Nile tilapia aquaculture. This study examines the invasion and immune evasion mechanisms of a highly virulent F. davisii strain through transcriptomic profiling of tilapia gills following acute immersion. We identified 8192 differentially expressed genes (DEGs) at 2 h, 6 h, and 12 h post-infection. They are enriched in pathways related to oxidative stress, immune suppression, tissue necrosis, and bacterial infection. Notably, early overexpression of rhamnose-binding lectin and mucin genes facilitated bacterial adhesion. Key immune genes, including those encoding major histocompatibility complex (MHC), immunoglobulins (Ig), Toll-like receptors (TLRs), and chemokines, were downregulated, indicating immune suppression. Conversely, immune evasion genes such as Fc receptor-like (FcRL) and programmed death-ligand 1 (PDL1) were upregulated, along with genes associated with reactive oxygen species (ROS) production, leading to increased tissue damage. Additionally, the upregulation of fibroblast growth factor and collagen genes suggested active tissue repair. In conclusion, F. davisii rapidly invades its host by enhancing adhesion to gill tissues, suppressing immune function, and inducing tissue damage. These findings enhance our understanding of F. davisii infection mechanisms and support the future breeding of disease-resistant tilapia and the development of sustainable control strategies. Full article

(This article belongs to the Special Issue Mechanisms of Immunity and Disease Resistance in Aquatic Animals)

►▼ Show Figures

Figure 1

20 pages, 8818 KiB

Open AccessArticle

“Re-Think” Sulfur Curing

by Anke Blume, Frances van Elburg, Fabian Grunert and Auke Talma

Molecules 2024, 29(21), 5198; https://doi.org/10.3390/molecules29215198 (registering DOI) - 2 Nov 2024

Abstract

Since Charles Goodyear discovered the method of sulfur curing Natural Rubber in 1839, many studies have been carried out to understand its mechanism. Currently, the broadly accepted mechanism includes an activated accelerator complex formed by Zinc oxide, stearic acid, accelerators and sulfur. Furthermore, it is also broadly accepted that the coupling of the sulfur to the polymer takes place in the allylic position to the double bond. Modern passenger car tire treads no longer contain Natural Rubber but instead a blend of Solution Styrene Butadiene Rubber and Butadiene Rubber, filled with a silica/silane system. Is it possible to transfer all the gained knowledge from the Natural Rubber crosslink reaction to such modern passenger car tire tread formulations, or is it required to “re-think” sulfur curing? Full article

►▼ Show Figures

Figure 1

15 pages, 3989 KiB

Open AccessArticle

Research on Ozone Pollution Characteristics and Source Apportionment During the COVID-19 Lockdown in Jilin City in 2022

by Chunsheng Fang, Sainan Zou, Xiaowei Zhou and Ju Wang

Atmosphere 2024, 15(11), 1324; https://doi.org/10.3390/atmos15111324 (registering DOI) - 2 Nov 2024

Abstract

The increasing Ozone (O₃) concentration in various regions of China has garnered significant attention, highlighting the need to understand the mechanisms of O₃ formation. This study focuses on the source apportionment of O₃ in Jilin City during and after the COVID-19 lockdown countermeasure, and also the influence of anthropogenic emissions on O₃ concentration. The contributions of different O₃ emission sources were quantified using the Weather Research and Forecasting Community Multi-Scale Air Quality (WRF-CMAQ) model in conjunction with the Integrated Source Apportionment Method (ISAM). The results indicate a significant increase in O₃ concentrations during the lockdown in Jilin City, which were particularly characterized by long-distance transportation. Transportation is identified as the primary direct source of O₃ in Jilin City, with Yongji County contributing the most among the six designated regions. This study highlights variations in the causes and sources of O₃ pollution among the different regions of Jilin City. Simply controlling anthropogenic emissions is inadequate for effectively managing O₃ pollution and may even worsen the situation. It is more effective to focus on controlling O₃’s precursors. These findings improve the understanding of O₃ pollution in Jilin City and provide valuable insights for developing O₃ control policies. Similarly, this research is applicable to other countries and regions. Full article

(This article belongs to the Section Air Quality)

►▼ Show Figures

Figure 1

16 pages, 3410 KiB

Open AccessArticle

Synthesis and Characterization of Mesoporous Materials Functionalized with Phosphinic Acid Ligand and Their Capability to Remove Cd(II)

by Khayra Mersellem, Djamila Bouazza, Irene Malpartida, Pedro Maireles-Torres, Anne Boos, Hary Demey and Hafida Miloudi

Molecules 2024, 29(21), 5199; https://doi.org/10.3390/molecules29215199 (registering DOI) - 2 Nov 2024

Abstract

This article presents a study of cadmium removal from nitrate medium using adsorption in calcined mesoporous silica (MCM-C), mesoporous silica doped (MCM_DIOPA), and calcined and impregnated mesoporous silica (MCM@DIOPA), with diisooctylphosphinic acid (DIOPA). The sorbents were synthesized via a sol–gel method. Several characterization techniques, such as XRD, FTIR spectroscopy, N₂ sorption and elemental analysis, have been used to determine the main structural, textural, and chemical properties of prepared sorbents. Batch adsorption and kinetics tests were carried out, where the influence of pH and contact time of the sorbents and their role in cation removal were studied. Experimental results show poor sorption efficiencies with MCM-C and MCM_DIOPA at pH 5.85. At the same pH, better cadmium extraction was attained by MCM@DIOPA and was achieved within 30 min. The pseudo-second-order model is the most appropriate model to describe the elimination mechanism of Cd(II) ions. The Langmuir equation was used to model the sorption isotherm and the maximum sorption capacity of Cd(II) is 22.16 mg/g (200 mmol/kg). The complex type of the probable extracted species isCdL2-HL. Full article

(This article belongs to the Special Issue Organic and Inorganic Pollutant Removal from Waters by Physicochemical, Electrochemical and Thermochemical Processes)

►▼ Show Figures

Figure 1

16 pages, 3022 KiB

Open AccessArticle

An Enhanced Deep Learning Model for Effective Crop Pest and Disease Detection

by Yongqi Yuan, Jinhua Sun and Qian Zhang

J. Imaging 2024, 10(11), 279; https://doi.org/10.3390/jimaging10110279 (registering DOI) - 2 Nov 2024

Abstract

Traditional machine learning methods struggle with plant pest and disease image recognition, particularly when dealing with small sample sizes, indistinct features, and numerous categories. This paper proposes an improved ResNet34 model (ESA-ResNet34) for crop pest and disease detection. The model employs ResNet34 as its backbone and introduces an efficient spatial attention mechanism (effective spatial attention, ESA) to focus on key regions of the images. By replacing the standard convolutions in ResNet34 with depthwise separable convolutions, the model reduces its parameter count by 85.37% and its computational load by 84.51%. Additionally, Dropout is used to mitigate overfitting, and data augmentation techniques such as center cropping and horizontal flipping are employed to enhance the model’s robustness. The experimental results show that the improved algorithm achieves an accuracy, precision, and F1 score of 87.09%, 87.14%, and 86.91%, respectively, outperforming several benchmark models (including AlexNet, VGG16, MobileNet, DenseNet, and various ResNet variants). These findings demonstrate that the proposed ESA-ResNet34 model significantly enhances crop pest and disease detection. Full article

(This article belongs to the Special Issue Imaging Applications in Agriculture)

16 pages, 1063 KiB

Open AccessReview

Epigenetic Mechanisms Induced by Mycobacterium tuberculosis to Promote Its Survival in the Host

by Shwetha Susan Thomas, Kuniyil Abhinand, Arjun M. Menon, Bipin G. Nair, Geetha B. Kumar, K. B. Arun, Lekshmi K. Edison and Aravind Madhavan

Int. J. Mol. Sci. 2024, 25(21), 11801; https://doi.org/10.3390/ijms252111801 (registering DOI) - 2 Nov 2024

Abstract

Tuberculosis caused by the obligate intracellular pathogen, Mycobacterium tuberculosis, is one among the prime causes of death worldwide. An urgent remedy against tuberculosis is of paramount importance in the current scenario. However, the complex nature of this appalling disease contributes to the limitations of existing medications. The quest for better treatment approaches is driving the research in the field of host epigenomics forward in context with tuberculosis. The interplay between various host epigenetic factors and the pathogen is under investigation. A comprehensive understanding of how Mycobacterium tuberculosis orchestrates such epigenetic factors and favors its survival within the host is in increasing demand. The modifications beneficial to the pathogen are reversible and possess the potential to be better targets for various therapeutic approaches. The mechanisms, including histone modifications, DNA methylation, and miRNA modification, are being explored for their impact on pathogenesis. In this article, we are deciphering the role of mycobacterial epigenetic regulators on various strategies like cytokine expression, macrophage polarization, autophagy, and apoptosis, along with a glimpse of the potential of host-directed therapies. Full article

(This article belongs to the Special Issue Host-Pathogen Interaction, 6th Edition)

►▼ Show Figures

Figure 1

12 pages, 2924 KiB

Open AccessArticle

Detection of Silver and Mercury Ions Using Naphthalimide-Based Fluorescent Probe

by Chunwei Yu, Xiangxiang Li, Mei Yang, Yinghao Xie and Jun Zhang

Molecules 2024, 29(21), 5196; https://doi.org/10.3390/molecules29215196 (registering DOI) - 2 Nov 2024

Abstract

A multifunctional fluorescent probe P based on a naphthalimide derivative for the detection of Ag⁺ and Hg²⁺ through a dual-signal was designed and characterized. P exhibited a large Stokes shift (107 nm), high selectivity, good sensitivity, and fast response time. By adjusting the testing medium and the order of reagent addition, multifunctional detection with P was achieved. The addition of Ag⁺ or Hg²⁺ to P solution in either ethanol or an ethanol–water mixture resulted in a significant quenching of fluorescence emission at 537 nm and caused a decrease in the absorbance at 440 nm accompanied by the appearance of a new absorption peak at around 340 nm, and there was an obvious color change from yellow to colorless. In contrast, the addition of other common metal ions and anions did not produce substantial spectral or color changes. The detection limit of probe P for Ag⁺ and Hg²⁺ was calculated to be 0.33 μM. The sensing mechanism was proposed and validated through MS and ¹H NMR spectrometry methods. Additionally, P demonstrated the capability to recognize Ag⁺ and Hg²⁺ in living cells with satisfactory results. Full article

(This article belongs to the Special Issue Research Progress of Fluorescent Probes)

►▼ Show Figures

Figure 1

17 pages, 6728 KiB

Open AccessArticle

Transcriptome Profiling of Two Camellia japonica Cultivars with Different Heat Tolerance Reveals Heat Stress Response Mechanisms

by Yue Tan, Yinzhu Cao, Fenglian Mou, Bin Liu, Huafeng Wu, Shihui Zou, Lijiao Ai and Shunzhao Sui

Plants 2024, 13(21), 3089; https://doi.org/10.3390/plants13213089 (registering DOI) - 2 Nov 2024

Abstract

Camellia (Camellia japonica) is a semi-shaded plant that is highly vulnerable to heat stress. To investigate the mechanisms underlying heat stress in C. japonica, two C. japonica cultivars, “Xiaotaohong” and “Zhuapolian”, which exhibit significant differences in heat tolerance, were selected from four common cultivars. The selection methods included phenotypic observations and physiological index detection, including relative electric conductivity (REC), malondialdehyde (MDA) content, superoxide dismutase (SOD) enzyme activity, relative water content (RWC), and chlorophyll content. RNA-seq analysis yielded 980 million reads and identified 68,455 differentially expressed genes (DEGs) in the two C. japonica cultivars during heat stress compared to the control samples. Totals of 12,565 and 16,046 DEGs were differentially expressed at 16 h and 32 h, respectively, in “Xiaotaohong” during heat stress. In “Zhuapolian”, 40,280 and 37,539 DEGs were found at 16 h and 32 h, respectively. KEGG enrichment analysis revealed that both cultivars were enriched in the “plant hormone signal transduction” and “circadian rhythm” pathways at two stages, indicating the critical role these pathways play in the heat stress response. The differences in the tolerance between the two cultivars are likely linked to pathways such as “plant hormone signal transduction”, “photosynthesis”, and “circadian rhythm”. Some members of heat shock proteins (HSPs) are associated with the heat stress response. It is speculated that transcription factor families contributing to the tolerance differences include AP2/ERF, C3H, bHLH, bZIP, and MYB-related with a small number of heat shock factors (HSFs) also induced by the stress. In conclusion, these results reveal the changes in the physiological indices and molecular networks of two C. japonica cultivars under heat stress. This study lays the foundation for the breeding of superior heat-resistant C. japonica cultivars and for further molecular research. Full article

(This article belongs to the Section Plant Response to Abiotic Stress and Climate Change)

►▼ Show Figures

Figure 1

24 pages, 5987 KiB

Open AccessArticle

Expression Profiling Analysis of the SWEET Gene Family in In Vitro Pitaya Under Low-Temperature Stress and Study of Its Cold Resistance Mechanism

by Youjie Liu, Hanyao Zhang, Ke Zhao, Xiuqing Wei, Liang Li, Yajun Tang, Yueming Xiong and Jiahui Xu

Plants 2024, 13(21), 3092; https://doi.org/10.3390/plants13213092 (registering DOI) - 2 Nov 2024

Abstract

Pitaya (Hylocereus undatus) fruit is an attractive, nutrient-rich tropical fruit with commercial value. However, low-temperature stress severely affects the yield and quality of pitaya. The relevant mechanisms involved in the response of pitaya to low-temperature stress remain unclear. To study whether the SWEET gene family mediates the response of H. undatus to low-temperature stress and the related mechanisms, we performed genome-wide identification of the SWEET gene family in pitaya, and we used ‘Baiyulong’ tissue-cultured plantlets as material in the present study. We identified 28 members of the SWEET gene family from the H. undatus genome and divided these family members into four groups. Members of this gene family presented some differences in the sequences of introns and exons, but the gene structure, especially the motifs, presented relatively conserved characteristics. The promoter regions of most HuSWEETs have multiple stress- or hormone-related cis-elements. Three duplicated gene pairs were identified, including one tandem duplication gene and two fragment duplication gene pairs. The results revealed that the SWEET genes may regulate the transport and distribution of soluble sugars in plants; indirectly regulate the enzyme activities of CAT, POD, and T-SOD through its expression products; and are involved in the response of pitaya to low-temperature stress and play vital roles in this process. After ABA and MeJA treatment, the expression of HuSWEETs changed significantly, and the cold stress was also alleviated. This study elucidated the molecular mechanism and physiological changes in the SWEET gene in sugar metabolism and distribution of pitaya when it experiences low-temperature stress and provided a theoretical basis for cold-resistant pitaya variety breeding. Full article

(This article belongs to the Special Issue Horticultural Plant Physiology and Molecular Biology)

►▼ Show Figures

Figure 1

16 pages, 10303 KiB

Open AccessArticle

Deep Learning-Based Automatic Estimation of Live Coral Cover from Underwater Video for Coral Reef Health Monitoring

by Zechen Li, Shuqi Zhao, Yuxian Lu, Cheng Song, Rongyong Huang and Kefu Yu

J. Mar. Sci. Eng. 2024, 12(11), 1980; https://doi.org/10.3390/jmse12111980 (registering DOI) - 2 Nov 2024

Abstract

Coral reefs are vital to marine biodiversity but are increasingly threatened by global climate change and human activities, leading to significant declines in live coral cover (LCC). Monitoring LCC is crucial for assessing the health of coral reef ecosystems and understanding their degradation and recovery. Traditional methods for estimating LCC, such as the manual interpretation of underwater survey videos, are labor-intensive and time-consuming, limiting their scalability for large-scale ecological monitoring. To overcome these challenges, this study introduces an innovative deep learning-based approach that utilizes semantic segmentation to automatically interpret LCC from underwater videos. That is, we enhanced PSPNet for live coral segmentation by incorporating channel and spatial attention mechanisms, along with pixel shuffle modules. Experimental results demonstrated that the proposed model achieved a mean Intersection over Union (mIoU) of 89.51% and a mean Pixel Accuracy (mPA) of 94.47%, showcasing superior accuracy in estimating LCC compared to traditional methods. Moreover, comparisons indicated that the proposed model aligns more closely with manual interpretations than other models, with an mean absolute error of 4.17%, compared to 5.89% for the original PSPNet, 6.03% for Deeplab v3+, 7.12% for U-Net, and 6.45% for HRNet, suggesting higher precision in LCC estimation. By automating the estimation of LCC, this deep learning-based approach can greatly enhance efficiency, thereby contributing significantly to global conservation efforts by enabling more scalable and efficient monitoring and management of coral reef ecosystems. Full article

(This article belongs to the Topic Conservation and Management of Marine Ecosystems)

►▼ Show Figures

Figure 1

19 pages, 2710 KiB

Open AccessArticle

Energy Consumption Prediction of Injection Molding Process Based on Rolling Learning Informer Model

by Jianfeng Huang, Yi Li, Xinyuan Li, Yucheng Ding, Fenglian Hong and Shitong Peng

Polymers 2024, 16(21), 3097; https://doi.org/10.3390/polym16213097 (registering DOI) - 2 Nov 2024

Abstract

Accurate energy consumption prediction in the injection molding process is crucial for optimizing energy efficiency in polymer processing. Traditional parameter optimization methods face challenges in achieving optimal energy prediction due to complex energy transmission. In this study, a data-driven approach based on the Rolling Learning Informer model is proposed to enhance the accuracy and adaptability of energy consumption forecasting. The Informer model addresses the limitations of long-sequence prediction with sparse attention mechanisms, self-attention distillation, and generative decoder techniques. Rolling learning prediction is incorporated to enable continuous updating of the model to reflect new data trends. Experimental results demonstrate that the RL-Informer model achieves a normalized root mean square error of 0.1301, a root mean square error of 0.0758, a mean absolute error of 0.0562, and a coefficient of determination of 0.9831 in energy consumption forecasting, outperforming other counterpart models like Gated Recurrent Unit, Temporal Convolutional Networks, Long Short-Term Memory, and two variants of the pure Informer models without Rolling Learning. It is of great potential for practical engineering applications. Full article

(This article belongs to the Special Issue Machine Learning and Artificial Intelligence for Polymer Injection Molding Design and Processing)

Show export options Show export options

Select all

Export citation of selected articles as:

Error

Oops... you haven't selected anything for export.

Displaying article 1-50 on page 1 of 2000.

Go to page 1 2 3 4 5

Search Results (299,163)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI