Industrial Production Processes Research Articles

Data traffic unloading method of internet of things based on mobile edge computing

The Industrial Internet of Things integrates modern technologies such as intelligent terminals, computer technology, and big data, achieving low cost and high applicability in industrial production processes, and improving industrial production efficiency. The offloading of IoT data traffic requires significant energy consumption due to limited mobile terminal device resources. For this reason, the author designs a method of IoT data traffic unloading based on mobile edge computing. The initialization simulation parameters include the number of mobile users, the number of base stations equipped with edge servers, fixed bandwidth, base station height, etc. Calculate the distance and channel power gain from each base station to mobile users, and optimize power allocation through algorithms such as simulated annealing and PSO. The binary PSO algorithm is used to maximize the welfare in edge computing. Finally, by comparing with local offloading, utilizing layered offloading methods, and collaborative computing offloading methods based on fiber wireless networks. Simulation resultsThe energy consumption of SAPA is generally higher than that of PSO, and with the increase of mobile users, the energy consumption of both algorithms shows a significant growth trend. Especially, SAPA's energy consumption is significantly higher than PSO when the number of users is 40 and 60. This indicates that in the mobile network environment, PSO algorithm has more advantages in energy consumption than SAPA, By using particle swarm optimization algorithm to further optimize energy consumption, it greatly saves energy consumption. In comparison to local execution, the proposed offloading method yields substantial energy savings of nearly 62.5 %. The maximum difference in energy consumption between the proposed method and the collaborative computing offloading method based on fiber optic wireless networks is 268 J, while the maximum difference compared to the layered offloading method is 150 J. These results highlight the strategy's ability to enhance the computational efficiency of high-priority tasks on edge servers, concurrently reducing latency and energy consumption for task completion. This underscores the effectiveness of the proposed offloading method in conserving energy and emphasizes its practical significance.

Metabolic Engineering of Bacillus subtilis for the Production of Poly-γ-Glutamic Acid from Glycerol Feedstock

Poly-γ-glutamic acid (γ-PGA) is an attractive biopolymer for medical, agri-food, and environmental applications. Although microbial synthesis by Bacilli fed on waste streams has been widely adopted, the obtainment of efficient sustainable production processes is still under investigation by bioprocess and metabolic engineering approaches. The abundant glycerol-rich waste generated in the biodiesel industry can be used as a carbon source for γ-PGA production. Here, we studied fermentation performance in different engineered Bacillus subtilis strains in glycerol-based media, considering a swrA+ degU32Hy mutant as the initial producer strain and glucose-based media for comparison. Modifications included engineering the biosynthetic pgs operon regulation (replacing its native promoter with Physpank), precursor accumulation (sucCD or odhAB deletion), and enhanced glutamate racemization (racE overexpression), predicted as crucial reactions by genome-scale model simulations. All interventions increased productivity in glucose-based media, with Physpank-pgs ∆sucCD showing the highest γ-PGA titer (52 g/L). Weaker effects were observed in glycerol-based media: ∆sucCD and Physpank-pgs led to slight improvements under low- and high-glutamate conditions, respectively, reaching ~22 g/L γ-PGA (26% increase). No performance decrease was detected by replacing pure glycerol with crude glycerol waste from a biodiesel plant, and by a 30-fold scale-up. These results may be relevant for improving industrial γ-PGA production efficiency and process sustainability using waste feedstock. The performance differences observed between glucose and glycerol media also motivate additional computational and experimental studies to design metabolically optimized strains.

Technoeconomic and environmental impact assessment of industrial scale biodiesel production process from algal oil using a reusable basic ionic liquid magnetic nanocatalyst

A unique magnetically reusable basic ionic liquid nanocatalyst was designed to convert algal oil into biodiesel. The imidazolium-based basic ionic liquid (BIL) was immobilized onto the magnetic nanocomposite (Fe3O4-SiO2), resulting in Fe3O4-SiO2-BIL nanocatalyst with notable properties of large surface area (21.963 m2/g), high saturation magnetization (28.78 emu/g) and high thermal stability. The nanocatalyst effectively facilitated algal oil transesterification with 96.94 % biodiesel yield under methanol: oil ratio of 8.58:1 and a catalyst dosage of 4.59 % at 60.60 °C for 87.42 min. The transesterification reaction proceeded with pseudo-first-order kinetics, featuring a relatively low activation energy. The nanocatalyst showed excellent reusability for eight recycles. A techno-economic analysis demonstrated that industrial-scale biodiesel production from algal feedstock was economically viable with a minimum payback of 2.25 years. The environmental analysis revealed a low carbon footprint with the emission of 0.074 kg CO2 per kg of biodiesel produced. This research presents a sustainable approach for biodiesel production from algal feedstock facilitated by Fe3O4–SiO2–BIL nanocatalyst, offering both environmental and economic benefits.

In-situ catalytic upgrading of lignin pyrolysis volatiles over red mud

Red mud (RM) is a solid waste of Bayer's alumina industry production process, which comprises a mixture of diverse minerals. After calcination, the minerals in RM are present in the form of oxides, exhibiting remarkable catalytic performance for biomass pyrolysis. It is thought that pyrolysis of lignin generates renewable aromatic chemicals. In this paper, the effect of in-situ catalysis of calcinated RM on the distribution of lignin pyrolysis volatile products is investigated. In addition, upgrading of tar by components in RM, including SiO2, Al2O3, Fe2O3, and Na2O is also discussed. The results show that the addition of RM in lignin pyrolysis leads to lower char yield and higher gas yield. RM catalyzes the breaking and rearrangement of methoxy groups and induces the generation of hydroxyl groups, which leads to an increase from 1.96 to 3.96 wt% in monophenol content of the tar. Furthermore, the activation of C-O bonds by Fe2O3 and the redox properties of Fe2O3 (FeSi) combine to stimulate the production of monophenols and aldehydes by 30.8 % and 148.2 %, while Al2O3 (AlSi) boosts the production of guaiacols by 32.0 % comparing with SiO2 (Si). It is found that synergistic effect between multiple species improves the catalytic performance, the yield of tar reaches 24.5 wt% and the selectivity of oxygenated compounds achieves 94.4 % (FeAlSiNa). The catalytic performances of RM for product yield and tar component distribution are similar to that of FeSi, indicating that Fe2O3 and SiO2 play a main catalytic role in RM.

Real-time concentration detection of Al dust using GRU-based Kalman filtering approach

Kalman filter algorithms have been widely used in dust environment concentration detection systems. However, in industrial environments, methods such as KF and median filtering usually require about 10 s of detection time, which cannot meet the requirements of online real-time detection. For this reason, this present study proposes a framework that combines a gated recirculation unit (GRU) with the KF method to achieve online real-time detection of dust concentration. In this framework, the GRU is mainly responsible for handling dynamic and nonlinear characteristics and capturing instantaneous concentration trends. On the other hand, the Kalman filter utilizes its superior state estimation capability to provide more accurate system state estimation by fusing real-time predictions from GRU and sensor measurements. The results show that the KFGRU method is superior to the conventional linear filtering method with a response time of less than 2 s and can detect dust concentration online in real-time. In terms of prediction accuracy, the deviation value of the curve processed by the KFGRU method is only 0.334, which is a significant breakthrough compared with the Kalman filter algorithm 0.755, the sliding average method 0.843, and the median filter method 0.849 (the smaller the deviation value, the higher the prediction accuracy). This study provides a comprehensive and innovative approach for dust concentration monitoring in dust reduction and explosion suppression systems, which not only meets the real-time requirement but also makes important progress in explosion safety management. This will provide more reliable and advanced technical support for dust control and safety in industrial production processes.

Roadmap of Graphite Moderator and Graphite-Matrix TRISO Fuel Management Options

Most high-temperature reactors use graphite as a moderator and structural material. This includes high-temperature gas-cooled reactors with helium cooling and TRi-structural ISOtropic (TRISO) fuel particles embedded in graphite, as well as fluoride salt–cooled high-temperature reactors with clean salt coolant and TRISO fuel particles embedded in graphite and thermal spectrum molten salt reactors with a graphite moderator and fuel dissolved in the salt. The largest volume radioactive waste stream from these reactors is the irradiated graphite. We describe herein a roadmap for management of these graphite wastes that contain radioactive 14C, tritium, and other radionuclides. There may be some graphite wastes with sufficiently low radioactivity levels that can be treated as nonradioactive waste and managed like other graphite waste. Management options for the graphite include (1) direct disposal, (2) recycled back to the reactor or other nuclear applications, and (3) oxidizing the graphite with release as an effluent or underground sequestration of the carbon dioxide. Cosequestration of this carbon dioxide with carbon dioxide from industrial, biological, and cement production processes can isotopically dilute the 14C before sequestration to eliminate the possibility of exceeding individual radiation exposure limits. We also describe options for processing graphite-matrix TRISO fuel, including separating the bulk graphite to reduce the volumes of used fuel for disposal or processing to recover fissile materials. The inventories of radioactive isotopes in different carbon wastes vary by many orders of magnitude; thus, there is no single economic option for the management of all graphite waste.

Low-carbon UHPC with glass powder and shell powder: Deformation, compressive strength, microstructure and ecological evaluation

Waste glass and shells are by-products generated in the production process of the construction industry and aquaculture respectively. The high-value treatment of these materials presents a global challenge. Converting waste glass and shells into solid waste-based ultra-high performance concrete (UHPC) mixtures is an eco-friendly strategy. In this study, glass powder (GP) and oyster shell powder (OSP) were mixed to prepare composite supplementary cementitious materials (GOS) and partially replace cement. The compressive strength, drying shrinkage, microstructure, and environmental impact of GOS-containing UHPC were investigated. Results indicate that adding GOS reduces the fluidity of UHPC mixtures, with further decreases as GOS content increases. Replacing cement with an appropriate amount of GOS (10 wt%-20 wt%) enhances the compressive strength of UHPC, though higher GOS levels reduce its strength. Meanwhile, the drying shrinkage deformation of UHPC decreases significantly as the GOS substitution level increases. The 28-d drying shrinkage deformation of the specimen added with 20 wt% GOS is 574 μm/m, which is 61.96 % lower than the control group. Additionally, the specimen added with 20 wt% GOS shows significantly improved compactness and enhanced bonding at the interfacial transition zone. Compared with traditional UHPC, GOS-containing UHPC has lower carbon emissions and costs, effectively utilizes waste, and promotes sustainable development.

HLG-YOLOv7: small object detection in conveyor belt damage based on leveraging hybrid local and global features

In the industrial production process, the detection of conveyor belt damage plays a crucial role in ensuring the stable operation of the transportation system. To tackle the issues of significant changes in damage size, missed detections, and poor detection ability of small-size objects in conveyor belt surface damage detection, an improved HLG-YOLOv7 (Hybrid Local and Global Features Network) conveyor belt surface defect detection algorithm is proposed. Firstly, Next-VIT is employed as the backbone network to fully extract local and global features of the damage, enhancing the model’s ability to extract features of different-sized damages. Additionally, to deeply utilize the extracted local and global features, the Explicit Visual Center (EVC) feature fusion module is introduced to obtain comprehensive and discriminative feature representations, further enhancing the detection capability of small objects. Lastly, a lightweight neck structure is designed using GSConv to reduce the complexity of the model. Experimental results demonstrate that the proposed method has better small object detection performance compared to existing methods. The improved algorithm achieves mAP and F1 scores of 96.24% and 97.15%, respectively, with an FPS of 28.2.

Optimizing the production process of biscuit industry as an approach to strengthening the local agricultural sector which reduce vulnerability of the global food crisis case study: analysis of waste in coconut biscuit industry with the DMAIC method

Abstract The local biscuit industry as a potential partner in the agricultural sector continues to grow rapidly. The development of local industries, including the coconut biscuit industry, must be continuouslyoptimized as an approach to empowering local agricultural sector that indirectly play a role in reduce vulnerability of the global food crisis. This makes the industry continue to try to find and adopt efficient and effective ways to increase product value and expand market share, one of the ways is the application of lean manufacturing. In this article, a case study is used in the coconut biscuit industry using the DMAIC analysis method and several tools such as VALSAT, fishbone diagrams and FMEA. Based on the analysis conducted, it is known that in the coconut industry there are several wastes such as unnecessary motion, defects and rework, and waiting with non-value added (NVA) activities for 784s. Therefore, further analysis is carried out regarding the proposed improvements that might be implemented. Some of the suggestions for improvement that can be given are the preparation of a buffer tank that is integrated with aload cell and transfer using a piping system, determine standardization of temperature and treatment of ovens as well as stipulation of work instructions and briefings during the initial process of the production line, analysis and evaluation of capacity, line layout, and lifetime on sugar water silo pumps and adjustments size and maintenance of dough tubs so as to reduce waste and NVA in the production process area.

Intelligent Robotic Arm-Assisted Electrical Furnace for Efficient Metal Casting

Abstract: This project proposes the development of an intelligent robotic arm-assisted electrical furnace system for efficient and precise metal casting. Electric furnace is used for heating purpose in various industrial production processes. Electric furnaces are used where more accurate temperature control is required. By combining the strengths of robotic automation with the clean and controllable environment of an electric furnace, the system aims to achieve Enhanced quality and reduced waste, Improved safety and reduced hazards, increased efficiency and productivity, Greater flexibility, and versatility, Reduced environmental impact. The project will explore the integration of sensors enhancing efficiency and quality control. The integration of these technologies aims to enhance productivity, precision, and safety while reducing operational costs. The robotic arm is designed to perform loading and unloading tasks, handling raw materials and moulds with exceptional accuracy and repeatability. The robotic arm can be attached to the electrical furnace. With the help of sensors, robots can manage to avoid obstacles on their paths and achieve their goals with or without prior planning, depending on the complexity of their implemented program.

Structural Insights of a cis-Epoxysuccinate Hydrolase Facilitate the Development of Robust Biocatalysts for the Production of l-(+)-Tartrate.

l-(+)-Tartaric acid plays important roles in various industries, including pharmaceuticals, foods, and chemicals. cis-Epoxysuccinate hydrolases (CESHs) are crucial for converting cis-epoxysuccinate to l-(+)-tartrate in the industrial production process. There is, however, a lack of detailed structural and mechanistic information on CESHs, limiting the discovery and engineering of these industrially relevant enzymes. In this study, we report the crystal structures of RoCESH and KoCESH-l-(+)-tartrate complex. These structures reveal the key amino acids of the active pocket and the catalytic triad residues and elucidate a dynamic catalytic process involving conformational changes of the active site. Leveraging the structural insights, we identified a robust BmCESH (550 ± 20 U·mg-1) with sustained catalytic activity even at a 3 M substrate concentration. After six batches of transformation, immobilized cells with overexpressed BmCESH maintained 69% of their initial activity, affording an overall productivity of 200 g/L/h. These results provide valuable insights into the development of high-efficiency CESHs and the optimization of biotransformation processes for industrial uses.

Improving Ammonia Emission Model of Urea Fertilizer Fluidized Bed Granulation System Using Particle Swarm Optimization for Sustainable Fertilizer Manufacturing Practice

Granulation is an important class of production processes in food, chemical and pharmaceutical manufacturing industries. In urea fertilizer manufacturing, fluidized beds are often used for the granulation system. However, the granulation processes release ammonia to the environment. Ammonia gas can contribute to eutrophication, which is an oversupply of nitrogen and acidification to the ecosystems. Eutrophication may cause major disruptions of aquatic ecosystems. It is estimated that global ammonia emissions from urea fertilizer processes are approximately at 10 to 12 Tg N/year, which represents 23% of overall ammonia released globally. Therefore, accurate modeling of the ammonia emission by the urea fertilizer fluidized bed granulation system is important. It allows for the system to be operated efficiently and within sustainable condition. This research attempts to optimize the model of the system using the particle swarm optimization (PSO) algorithm. The model takes pressure (Mpa), binder feed rate (rpm) and inlet temperature (°C) as the manipulated variables. The PSO searches for the model’s optimal coefficients. The accuracy of the model is measured using mean square error (MSE) between the model’s simulated value and the actual data of ammonia released which is collected from an experiment. The proposed method reduces the MSE to 0.09727, indicating that the model can accurately simulate the actual system.

Study on the gelling properties of egg white/surfactant system by different heating intensities

The aim of this study was to elucidate the different effects and difference mechanism of gelling properties among egg white (EW) treated with different heating intensities and the composite addition of rhamnolipid and soybean lecithin. Particle size analyzer, potentiometric analyzer, surface hydrophobicity method, and Fourier transform infrared spectroscopy techniques were used to determine the physicochemical properties and molecular structure, respectively. Low-field nuclear magnetic resonance, magnetic resonance imaging, texture profile analysis, and scanning electron microscopy techniques were used to analyze the gelling properties and gel structure, respectively. And we illuminate the different mechanisms in the gelling properties of the EW with various treatments and key internal factors that play important roles in improving gelling properties by establishing the link between the gelling properties and relevant characteristics by mixed effects model and visual network analysis. The results indicate raising the content of rhamnolipid decreased the migration of immobilized water in the EW gel and the free water content. At the heating intensities of 55 °C/3.5, 65 °C/2.5, and 67 °C/1.5 min, with an increase in rhamnolipid, the gel's cohesiveness, gumminess, and chewiness gradually increased. The mixed effects model indicated that heating intensities and composite ratios have a 2-way interaction on zeta potential, the relaxation time of bound water (T21), the content of bound water (P21), the content of immobilized water (P22), and fractal dimension (df) attributes (P < 0.05). The visual network analysis showed that the protein solubility, the relaxation time of immobilized water (T22), surface hydrophobicity, zeta potential, average particle size (d43) and the relaxation time of free water (T23) are critical contributors to the different gelling properties of EW subjected to various treatments and the improvement of gelling properties. This study will provide theoretical guidance for the development of egg white products and the expansion of egg white's application scope in the egg product processing industry.

Research on the impact of innovation investment on operating efficiency of listed forest product processing companies

PurposeThe forest products processing industry is a key component of the forestry economy, and the level of companies’ operating efficiency directly affects its profitability and market competitiveness.Design/methodology/approachIn order to deeply study the operation status of forest product processing industry, this paper takes the panel data of 70 listed forest product processing companies from 2015 to 2022 as the basis, and adopts BBC, CCR and DEA-Malmquist models to measure the operating efficiency of these companies. Meanwhile, the Tobit model is applied to deeply explore the impact of innovation input on operating efficiency.FindingsThe results of the paper show that: (1) the overall operating efficiency of listed forest product processing companies performs well, and the improvement of technology level promotes the growth of total factor productivity; (2) innovation input plays a significant positive role in listed forest product processing companies, which positively affects the operating efficiency.Practical implicationsA scientific and reasonable evaluation of the operating efficiency of listed forest product companies is of great practical significance to the development of the forestry industry The study of forest product processing industry is of key significance to the social economy.Originality/valueThis paper explores the improvement of production and operation efficiency of forest products processing enterprises for the purpose of in-depth analysis of the current situation of China's forest products processing enterprises, which is conducive to improving the innovation and operation efficiency of China's forest products processing enterprises, and realizing the high-quality development of China's forest products processing industry.

Using the Lean and Green Six Sigma Method at PT. XYZ, this Painting Process aims to Reduce Tosou Butsu Alloy Wheel Defects

Aluminium wheels are a significant component of the automotive industry, but opinions about their quality are primarily based on how they look. As a result, finishing is crucial to the production process in the wheel industry. Efforts must be made to reduce the frequency of Tosou Butsu flaws in the painting process, which most frequently occur in the paint section, even though there are still a lot of errors in the wheel production process. Therefore, to lessen the chance of Tosou Butsu faults developing during the wheel finishing process, the Lean &amp; Green Six Sigma technique is applied. Measure, Analyze, Improve, Control, and Define are the five stages of the Six Sigma methodology (DMAIC). Conversely, the Six Sigma level has grown from 3,417?, which was the level before the Sigma was repaired, to 3,750? in Sigma level 3 conditions, or level 4 conditions, with the potential for Tosou Butsu defects to occur at 12104 for a million production processes. Six Sigma is then applied to In this investigation, the painting procedure was able to lower the percentage of Tosou Butsu faults from 0.0276 to 0.0121. In order to optimize efficiency and focus on system mechanisms that align with standard operating procedures and human resource development, the Six Sigma process needs to be applied regularly and refined until the Sigma level reaches 6?.

Preliminary Purification and Partial Characterization of a Functional Bacteriocin of Lacticaseibacillus paracasei Zhang and Mining for its Gene Cluster.

Bacteriocins produced by lactic acid bacteria (LAB) have good potential for use as food biopreservatives. Lacticaseibacillus paracasei Zhang (L. paracasei Zhang) is both a food use and a probiotic bacterium. This study aimed to purify and preliminary characterize the active antibacterial metabolite of L. paracasei Zhang. The cell-free supernatant of L. paracasei Zhang was collected and purified by ultrafiltration and gel filtration chromatography. The 1-3kDa active fraction could inhibit the growth of Staphylococcus aureus but not Escherichia coli. Further antibacterial activity assays revealed its capacity to suppress various foodborne and human opportunistic pathogens (including Staphylococcus aureus, Pseudomonas fluorescens, Pseudomonas aeruginosa, Listeria monocytogenes, and Bacillus cereus), but not fungi. The antibacterial activity showed good tolerance to heat (40 to 100°C), acid-base (pH 2-3 and pH 6-10), and digestions by a number of industrial and animal/human enzymes (such as trypsin, pepsin, α-amylase, and protease K, except papain); these desired properties make it a suitable biopreservative to be used in harsh and complex industrial production processes. The high papain sensitivity suggested a proteinaceous/peptide nature of the bioactivity. Moreover, our genomic data mining for bacteriocin through BAGEL4 revealed an area of interest encoding a complete set of putative genes required for bacteriocin production. In conclusion, our study showed that L. paracasei Zhang can produce extracellular functional antibacterial metabolite, likely a class II bacteriocin. Our preliminary extraction and characterization of the active metabolite demonstrated that it has good potential to be used as a biopreservative or an agent for suppressing gastrointestinal infections.

A Novel Fault Diagnosis Framework for Industrial Production Processes Based on Causal Network Inference

A Novel Fault Diagnosis Framework for Industrial Production Processes Based on Causal Network Inference

Directional hydrothermal hydrogenation of palmitic acid to alcohol over carbon-encapsulated highly dispersed Co catalyst

The directed conversion of fatty acids into fatty alcohols in water medium has recent received increasing attention. Here, a carbon-encapsulated catalyst (Co@C) is designed and used for the hydrothermal hydrogenation of palmitic acid (a model compound of microalgae-based bio-oils) to produce 1-hexadecanol, exhibiting ultra-high catalytic activity. The yield of 1-hexadecanol is as high as 95.1 % at 200 °C within 60 min. The characterization results indicate that a large number of highly dispersed CoO nanoparticles (CoO NPs) provide sufficient hydrogenation active centers for the Co@C catalyst. More importantly, under the protection of the carbon layer, the Co@C catalyst exhibits high hydrothermal stability, far superior to the conventional supported Co/AC catalyst. The catalyst uses inexpensive glucose and cobalt nitrate as raw materials, with a simple synthesis process, low cost, and easy large-scale industrial production. This work provides a new strategy for obtaining catalysts with hydrothermal stability and activity for production of alcohols.

Agri-food supply chain optimization through a decentralized production process in the olive oil industry

A tactical/operational model is proposed to assist decision-making in harvest planning and olive oil production planning of the different producers in the rural sector, considering allocation and transportation decisions of the kilograms of olives to the production plant with temporary relocation decisions of the mobile olive oil mills through decentralized production activities in the agri-food supply chain. A Mixed Integer Linear Programming model is presented that maximizes the profit of small farmers in the production process of single-varietal extra virgin olive oil. The decisions are based on the geographical dispersion of the different olive growers and the oil concentration of the olive varieties in a certain period, which depends on the climatic conditions of each sector where the olives are cultivated. The mathematical programming model is applied in Coquimbo, Chile, using actual data collected from previous harvest seasons. The computational results of the optimization model indicate that transportation decisions impact olive harvesting and oil production decisions. It is concluded that cooperatives of small producers in the rural sector increase overall profits and reduce transportation costs and the number of kilometers traveled by at least 41% through a decentralized production process with mobile production plants.

Dynamic fault detection and diagnosis of industrial alkaline water electrolyzer process with variational Bayesian dictionary learning

Alkaline Water Electrolysis (AWE) is one of the simplest green hydrogen production method using renewable energy. AWE system typically yields process variables that are serially correlated and contaminated by measurement uncertainty. A novel robust dynamic variational Bayesian dictionary learning (RDVDL) monitoring approach is proposed to improve the reliability and safety of AWE operation. RDVDL employs a sparse Bayesian dictionary learning to preserve the dynamic mechanism information of AWE process which allows the easy interpretation of fault detection results. To improve the robustness to measurement uncertainty, a low-rank vector autoregressive (VAR) method is derived to reliably extract the serial correlation from process variables. The effectiveness of the proposed approach is demonstrated with an industrial hydrogen production process, and RDVDL can efficiently detect and diagnose critical AWE faults.