Search

Nonlinear process modeling is a primary task in intelligent manufacturing, aiming at extracting high-value features from massive process data for further process analysis like process monitoring. However, it is still a challenge to develop nonlinear process models with robust representation capability for diverse process faults. From the new perspective of the correlation between process variables, this paper develops a nonlinear process modeling algorithm to adaptively preserve the features of both global and local inter-variable structures, in order to fully exploit inter-variable features for enhancing the nonlinear representation of process operating conditions. Specifically, a unidimensional convolutional operation with a self-attention mechanism is proposed to simultaneously extract global and local inter-variable structures, wherein different attentions can be adaptively adjusted to these two structures for the final aggregation of them. Besides, cooperating with a two-dimensional dynamic data extension, the unidimensional convolutional operation can represent the overall temporal relationship between process samples. Through stacking a collection of these convolutional operations, a ResNet-style convolutional neural network then is constructed to extract high-order nonlinear features. Experiments on the Tennessee Eastman process validate the effectiveness of the proposed algorithm for two vital process monitoring problems—fault detection and fault identification. • A 1D CNN with a self-attention is proposed for fault detection and diagnosis. • The self-attention adaptively preserves global and local inter-variable structures. • 1D convolutions with dynamic data extension captures overall temporal relationships. [ABSTRACT FROM AUTHOR]

• Low salinity is new used in mud crab culture to expand the inland saline aquaculture. • Dietary lipid source, but not salinity, influenced nutritional values of flesh of mud crab. • Low salinity changed the myofiber structure and provided new texture for consumers. • Low salinity and dietary soybean oil weakened the umami taste and aroma of crab flesh. The quality of crustaceans' flesh has direct impact on consumers' purchase choices, with water environment and dietary nutrition being effective ways to regulate flesh quality. The aim of present study was to investigate the impacts of water salinity (low, 4 and medium, 23) and dietary lipid source (fish oil and soybean oil) on nutritional values, texture, taste and odor of flesh of mud crab. While water salinity had no significant influence on nutritional values of crab flesh, crabs fed soybean oil displayed significantly lower contents of amino acids and n-3 PUFAs in muscle. However, crabs reared at low salinity showed reduced flesh hardness, chewiness and gumminess likely related to altered myofiber structure, that impacted muscle texture. Furthermore, low salinity and dietary soybean oil weakened umami taste and aroma characteristics of crab flesh associated with decreased contents of free amino acids, flavor nucleotides, inorganic ions and odor active compounds in flesh. [ABSTRACT FROM AUTHOR]

• Surface residual stress is measured by XRD using symmetrical inclining method. • A novel optimization strategy is proposed to minimize surface residual stress. • Effects of turning parameters on surface residual stress are investigated. • The improved PSO algorithm shows a better performance in convergence efficiency. • Model for process parameter optimization is validated by the experimental results. Surface residual stress, induced by process parameters, has a significant effect on the performance of workpiece. Focusing on the minimization of surface residual stress in turning DT4E pure iron, the influence of cutting speed (v c , 80–240 m/min), feed rate (f , 0.04–0.20 mm/rev) and depth of cut (a p , 0.05–0.25 mm) on surface tensile residual stress (σ τ in cutting direction, σ r in feeding direction) is analyzed, and the optimal combination of process parameters is found. Central composite design (CCD) method is first used to design the turning experiments of pure iron material. By means of range analysis and the main effect plot, the relations between the process parameters and responses are discussed in detail. Subsequently, the non-linear mapping models of σ τ and σ r with regard to turning parameters are established respectively using support vector regression (SVR) method. The experimental database is utilized to validate the effectiveness of SVR models. Taking the total stress σ as the optimization objective of process parameters, the optimal combination of turning parameters within given parameter ranges is finally obtained by combining SVR models with improved particle swarm optimization (PSO) algorithm. Further, the comparisons between genetic algorithm (GA), traditional and improved PSO algorithms are conducted, which indicate that the improved PSO algorithm has an advantage in convergence efficiency. Finally, verification experiments are performed to confirm the minimization of surface residual stress. The results show that the proposed optimization strategy of process parameters is effective and reliable, while at the same time providing a good prediction accuracy. [ABSTRACT FROM AUTHOR]

In the structural fatigue fields, such as aerospace, maritime, and civil engineering, the accurate construction of the Probability-Stress-Life (P-S-N) curve is crucial for preventing unexpected structural failures and is fundamental to the engineering design process. Conventional methods usually assume that the fatigue life distribution follows a normal or weibull distribution, which overlooks the differences of life distribution at different stress levels and introduces subjective errors. To address this issue, this paper proposes a new approach based a multi-layer perceptron model with maximum entropy algorithm (MPME) for probabilistic fatigue life prediction. During the derivation of life probability distribution function in this approach, the type not require any pre-assumption, thus effectively avoiding the introduction of subjective errors. Specifically, the dispersed information of fatigue life is quantified as various life distribution statistical features such as mean, variance, skewness, and kurtosis. Next, learn the continuous functional relationship between stress and these features using a multi-layer perceptron (MLP). Finally, the target probability distribution is derived using the maximum entropy algorithm, with the predicted distribution features obtained from the MLP serving as constraints for it. In addition, to ensure the consistency between the prediction of MLP and physical laws, we encode physical knowledge into the network loss to guide the updating of network parameters. Experimental results of two different material fatigue data demonstrate that, compared to traditional deterministic model-based methods and machine learning methods, the MPME in this paper can more accurately predict the probabilistic fatigue life. • A multi-layer perceptron with maximum entropy algorithm for probabilistic fatigue life prediction is proposed. • The paradigm of learning distribution models parameter in machine learning-based methods had been revolutionized. • A hybrid Loss function is constructed to guide the parameter updating of network. • The performance of the model was evaluated using three metrics on two datasets. [ABSTRACT FROM AUTHOR]

• The dynamic data representation method is applied to semi-supervised fault classification and the differences between it with supervised fault detection are emphasized. • A semi-supervised form of CNN, i.e., SS-LGF-CLN, is proposed for fault classification, which can jointly capture latent manifold features of unlabeled samples and extract discriminative features of labeled samples. • The usefulness of global inter-variable correction features in representing incipient faults is discussed for the first time, while other CNN based fault classification methods focused on local inter-variable correction features. • An overall fault classification accuracy of 91.29% including incipient faults is achieved on the benchmark process. Effective fault classification is of great significance to isolate and eliminate faults in the smart manufacturing process, especially for chemical industry. However, incipient faults and limited labeled samples make it hard to classify faults accurately. This motivates the formulation of a semi-supervised convolutional ladder network with local and global feature fusion. In the algorithm, a convolutional ladder network is developed to capture higher-order correlations from both labeled and unlabeled samples simultaneously to overcome the problem caused by limited labeled samples, skipped connections are embedded within which to make a balance between supervised and unsupervised feature learning for further identifying faults. To improve the classification performance on incipient faults, a local and global feature fusion strategy is proposed to enhance the representation of incipient faults. Furthermore, a semi-supervised dynamic data representation strategy is introduced to jointly deal with labeled and unlabeled process samples, which enables the proposed method to handle process dynamics by characterizing temporal information of process variables. Experiments on the Tennessee Eastman process show that the proposed method is effective for process fault classification when labeled samples are limited compared to the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

The eggshell color of avian species is an important trait that is predominantly determined by the pigments biliverdin and protoporphyrin. Various factors affect eggshell pigment deposition and coloration; however, the underlying mechanisms remain unclear. We analyzed the hepatic transcriptomes and metabolomes of Changshun green-shell hens laying dark green and light green eggs to investigate the potential role of the liver in regulating the intensity of the green eggshell color. In total, 350 differentially expressed genes and 211 differentially altered metabolites were identified. Gene set enrichment analysis revealed that the enriched pathways and Gene Ontology (GO) terms were mainly associated with energy, immunity, and nutrient metabolism. Metabolite set enrichment analysis revealed that the enriched pathways were mainly associated with amino acid, vitamin, bile acid, and lipid metabolism. Moreover, gene–metabolite interaction network analysis revealed 1 subnetwork. Most genes and metabolites in this subnetwork were determined to be related to melanin metabolism and transport. In conclusion, our results suggest that hepatic melanin metabolism and transport are critical for eggshell coloration. Six candidate genes (CDKN2B, DDC, PYCR1, ABCG5, SLC3A1 , and P2RX2) and 7 candidate metabolites (serotonin, 5-hydroxyindoleacetic acid, ornithine, acetylcholine, L -tryptophan, D -ornithine, and ADP) were suggested to play important roles in this process. Meanwhile, this study suggests that changes in hepatic energy metabolism, immune status, antioxidation activity, nutrient availability, and bile acid synthesis can impair eggshell coloration. [ABSTRACT FROM AUTHOR]

• Faba bean changed fatty acids composition in white muscle of carps. • Faba bean changed oxidation state in white muscle and hepatopancreas of carps. • Faba bean caused myofiber atrophy and collagen turnover interruption in carps. In order to further explain the fillet texture improvement of Yellow River carp (Cyprinus carpio) fed with faba bean (Vicia faba L.), a three-month rearing trial was conducted to investigate fatty acid composition, antioxidant capacity, myofiber development, collagen deposition and transcriptome in white muscle of two farmed carp groups (One was fed only faba bean, the other was fed commercial diet). As a strong oxidant, faba bean changed fatty acids composition in white muscle, especially DHA and EPA, up-regulated the levels of reactive oxygen species (ROS) and down-regulated major antioxidant enzyme activities in the hepatopancreas and white muscle. Through the analysis of transcriptome and subsequent verification analysis, we speculated that the increase of ROS led to the decrease of myofiber diameter and collagen metabolism. This study provides a theoretical basis for further understanding the regulation of faba bean on fillet texture characteristic of Yellow River carp. [ABSTRACT FROM AUTHOR]

• Dietary oils affect the composition of lipid molecules in hepatopancreas of crab. • Dietary oils affect stereospecific position of fatty acids in glycerolipids in crab. • Dietary krill oil raises deposition of 20:5n-3 and 22:6n-3 at sn-2 in phospholipids. • Fish oil intake promotes deposition of EPA and DHA at sn-1,2,3 in triglyceride. • LC-PUFA biosynthesis and dietary oils could affect the distribution of fatty acids. While tissue fatty acid compositions reflect that of the dietary lipid source, little information is available on how dietary oils modify lipid class and molecular species profiles in hepatopancreas of crustacean. Herein, an 8-week nutritional trial and untargeted lipidomic analysis were used to investigate the impacts of dietary n-3 PUFA lipid sources including fish oil, krill oil and linseed oil on the lipidomic characteristics of hepatopancreas of swimming crab (Portunus trituberculatus). Dietary krill oil significantly increased distribution of 20:5n-3 and 22:6n-3 at sn-2 in phosphatidylcholine and phosphatidylethanolamine compared to fish oil. Fish oil intake promoted the deposition of 20:5n-3 and 22:6n-3 at sn-1,2,3 in triglyceride compared to linseed oil, which significantly increased the specific accumulation of 18:3n-3 at sn-1,3 in triglyceride and sn-2 in phosphatidylcholine and phosphatidylethanolamine. The study revealed metabolic responses to different dietary n-3 PUFA in swimming crab, which provided novel insight into the lipid nutrition of crustacean. [ABSTRACT FROM AUTHOR]

An 8-week feeding trial was conducted to evaluate the effects of replacement of fish meal (FM) with poultry by-product meal (PBM) on growth performance, feed utilization and expression of genes involved in protein metabolism in juvenile black sea bream (Acanthoparus schlegelii). Six isonitrogenous (42%) and isolipidic (11%) experimental diets were formulated to replace 0% (control diet), 10%, 20%, 30%, 40% and 60% protein from FM with PBM. All the diets except the control diet were supplemented with lysine and methionine to keep same lysine and methionine levels among all diets. A total of 360 fish (approximately initial weight, 0.46 ± 0.02 g) were randomly stocked and sorted in 18,300-L cylindrical fiberglass tanks, each diet was randomly assigned to triplicate groups of 20 juvenile black sea bream and fed twice each day to apparent satiation. The results showed that survival ranged from 88.33 to 93.33%, and there were no significant differences among all treatments (p >.05). Final body weight (FBW) and percent weight gain (PWG) significantly increased with dietary replacement levels of FM with PBM increasing from 0% to 30%, and significantly decreased when replacement of FM with PBM further increased from 30% to 60% (p <.05) , fish fed the 30% replacement of FM with PBM diet had higher FBW and PWG than those fed the other diets. Based on PWG against replacement levels of FM with PBM, A two-slope broken-line model analysis indicated that the optimal replacement of FM with FBM is to be 28.30%. Proximate composition in whole body did not show significant differences among all dietary treatments (p >.05). Higher hepatosomatic index (HSI) was observed in fish fed the 30% replacement of FM with PBM compared to the control and other diets, however, viscerosomatic index (VSI) and condition factor (CF) were not significantly influenced by the replacement of FM with PBM (p >.05). Fish fed the diet containing 30% replacement of FM with PBM had higher lysine and methionine concentration in muscles than those fed the other diets, however, other essential or non-essential amino acids in muscle were not significantly affected by dietary replacement of FM with PBM. The relative expressions of igf1 , tor , s6k1 , pi3k and akt were significantly up-regulated when replacement levels of FM with PBM increased from 0% to 30%, however, the expression levels of these genes significantly down-regulated with the further increase of replacement level of FM by PBM (p <.05). Moreover, the lowest expression of 4e-bp2 was occurred at fish fed the 30% replacement of FM with PBM among all treatments. In summary, the results of present study indicated that dietary PBM supplementation could be an alternative protein source for black sea bream, and 30% replacement of FM with PBM could improve growth and up-regulate the relative expression of genes involved in protein metabolism. • PBM significantly improved the growth performance and feed utilization of black sea bream. • The optimum substitution level of dietary PBM for maximum weight gain was 28.30%. • Dietary PBM significantly influenced the protein metabolism in relation to gene expression. [ABSTRACT FROM AUTHOR]

An 8-week feeding trail was conducted in Acanthopagrus schlegelii with an initial body weight of 8.34 ± 0.01g. Three isonitrogenous diets were formulated, (1) Control: medium-fat diet (12%); (2) HFD: high-fat diet (18%); (3) HFD + FF: high-fat diet with fenofibrate (0.15%). Liver histological analysis revealed that, compared to HFD, vacuolar fat drops were smaller and fewer in fish fed fenofibrate. Expression of lipid catabolism regulator peroxisome proliferator-activated receptor alpha (pparα) was up-regulated by fenofibrate compared with HFD. In addition, fenofibrate significantly increased the expression level of silent information regulator 1 (sirt1). Meanwhile, the expression level of anti-inflammatory cytokine interleukin 10 (il-10) in intestine was up-regulated, while pro-inflammatory cytokine interleukin 1β (il-1β) in liver and intestine were down-regulated by dietary fenofibrate supplementation. Overall, the present study indicated that fenofibrate reduced fat deposition and attenuated inflammation response caused by HFD partly through a pathway involving regulation of pparα and sirt1. • Explored how dietary fenofibrate impacts lipid metabolism and inflammatory responses in fish. • Fenofibrate significantly increased the expression level of sirt1 and pparɑ compared with HFD. • Fenofibrate up-regulated the il-10 , while il-1β were down-regulated. • Compared to HFD, vacuolar fat drops were smaller and fewer in fish fed fenofibrate. [ABSTRACT FROM AUTHOR]