Failure Process Research Articles

Penetration test and numerical simulation of scaled earth penetrator for coral aggregate seawater concrete cylindrical target

In order to study the mechanical properties of coral aggregate seawater concrete (CASC) subjected to the penetration of scaled earth penetrator, firstly, the penetration depth and damage of CASC and ordinary sand-gravel concrete under the same conditions were compared by experimental research, and the influence of concrete strength and projectile velocity on penetration performance was analyzed. Then, the three-dimensional mesoscopic model is used to simulate the test conditions, and the failure process and failure mechanism are analyzed. The results show that under the same penetration conditions, as the strength of CASC increases, the crater diameter becomes larger, which is consistent with the conclusion of ordinary concrete (OPC). During the penetration process, the CASC and the mortar are destroyed as a whole. At the same time, as the penetration speed of the projectile increases, the width of the crack on the surface of the target increases. When the projectile velocity is low, the anti-penetration performance of CASC with the same strength is not as good as that of OPC with the same strength. For the target with a thickness of 25 cm, the penetration depth of the concrete target with the same strength will increase with the increase of the velocity of the projectile. When the velocity of the projectile is constant, the penetration depth of CASC will decrease with the increase of the strength. The numerical simulation results obtained by using the K & C mesoscopic model are in good agreement with the experimental results, indicating that the model and its model parameters have high reliability in the analysis of CASC penetration mechanical properties.

Thermophilic and mesophilic anaerobic digestion of soybean molasses: A performance vs. stability trade-off

One of the factors that has a direct impact on anaerobic digestion is the applied organic loading rate (OLRA). Increasing OLRA can boost methane production but can also cause process failure. As a result, establishing the appropriate OLRA for the procedure is critical. This study evaluated the effect of increasing the OLRA using soybean molasses in a thermophilic anaerobic reactor (R-Thermo), as well as the effect of feeding strategy and co-processing with okara. Furthermore, the performance versus stability trade-off between R-Thermo and mesophilic anaerobic digestion (R-Meso) was investigated. The increase of OLRA from 10 to 15 and 20 kg-COD/m³/d led to a decrease in COD removal efficiency (90, 86, and 75%), methane yield (12.0, 11.6, and 9.9 mol-CH4/kg-COD) and an increase in total volatile acids concentration (251, 456, and 1393 mg-HAc/L, respectively). At 15 kg-COD/m³/d, R-Meso performed similarly to R-Thermo, and at 20 kg-COD/m3/d, R-Meso outperformed (81% COD removal efficiency, 9.3 mol-CH4/kg-CODrem and 154.5 mol-CH4/m3/d). Temperature greatly influenced the distribution of metabolic pathways, as shown by thermodynamic and kinetic analyses, thus impacting bacterial diversity. At 55 °C, amongst the bacterial genera, Tepidiphilus stood out (>28.2%), followed by Acetomicrobium, Coprothermobacter and Candidatus_Caldatribacterium. The OLRA clearly impacted the archaeal community; Methanothermobacter (77.4%) was favored over Methanosarcina (14.8%). Under thermophilic temperature, it seems that syntrophic acetate oxidation (SAO) bacteria might have competed for substrate with acetoclastic methanogens, while in R-Meso microorganisms responsible for the initial steps of organic matter breakdown, such as members of the Firmicutes and Proteobacteria phyla (at least 67%), were dominant. In summary, R-Meso, characterized by a more uniform distribution of metabolic pathways, as well as a diverse and well-adapted microbial consortium, have exhibited enhanced stability and outperformed R-Thermo at high-loads.

Mesoscopic analysis on the coral aggregate reinforced concrete column under axial and eccentric compression

Coral aggregate concrete (CAC) has been identified as a promising building material for reef engineering construction, yet its practical application remains challenging due to incomplete research on the mechanical behaviors of the CAC beam and column components. In this study, a 3D mesoscale modeling approach considering the heterogeneity of CAC was utilized to investigate the mechanical performance of coral aggregate reinforced concrete columns (CARCCs) under axial and eccentric compression. Through numerical delineation of failure processes and damage mechanisms at the mesoscale, comprehensive parametric analysis integrating both numerical simulations and experimental validations were executed to assess the load-bearing capacity of CARCC. Results indicate that the mesoscale model has significant reliability in simulating the deformation and cracking failure behaviors and analyzing the load-displacement relationships of CARCC under axial and eccentric compression loads. When under axial loads, macroscopic cracks in CARCC primarily develop in an oblique manner, precipitating significant concrete spalling and extensive cracking failure along the longitudinal axis. Under eccentric loads, failure advances from crack initiation at load points to abrupt vertical fractures in stressed zones, manifesting a decrement in the load-bearing capacity with escalating eccentricity. Furthermore, the strength grade and reinforcement ratio exert a profound influence on the load-bearing capacity, with disparate impacts under varied loading conditions. It is concluded that reinforcement strategies tailored to specific loading conditions have significant implications for the design and safety of reinforced concrete structures in reef engineering projects.

Interfacial interaction mechanism and theoretical bond strength model between UHPC-CA and steel bar

The bond property is the basis of the bear collectively load between the steel bar and Ultra-High Performance Concrete with Coarse Aggregate (UHPC-CA). In this paper, the theoretical calculation method of bond strength between UHPC-CA and high-strength steel bar is studied. The chemical adhesion strength, friction coefficient, and mechanical interlock process of the two were investigated respectively through the refined bond property tests. The failure model is established from the interlock failure characteristics, and the bond strength is obtained theoretically. Results show that the chemical adhesion strength and friction coefficient between UHPC-CA and steel bars are 0.07MPa and 0.5, respectively. The friction coefficient between UHPC-CA is 1.15. The interlock failure process of UHPC-CA and steel bars can be divided into three stages: uncracked stage, crack development stage, and split stage. The crack develops at an angle of 52° to the steel bar's axis and tends to stagnate at a height of 4.5 times the rib. A theoretical bond strength model is established and it is proved that the model is applicable not only to UHPC-CA but also to UHPC. This study can provide a theoretical basis for determining the anchorage length of steel bars in the design of UHPC-CA/UHPC structure, and can also provide a reference for the formulation of relevant standards.

Motion process and failure mode of Pusa landslide, China based on dense optical flow method

ABSTRACT Unmanned aerial vehicle (UAV) is widely applied in geohazard monitoring with its high resolution and feasibility features, where UAV videos can record the whole landslide failure process. Previous studies can only provide the qualitative depiction of the landslide failure process, rather than the quantitative motion process, which makes it difficult to analyse the landslide dynamic characteristics and failure mode. In this letter, we take UAV video of Pusa landslide, China obtained on 28 August 2017 to retrieve the landslide motion process by using the dense optical flow method. Firstly, the landslide boundary can be clearly depicted by the cumulative landslide motion time series maps. Secondly, the maximum cumulative motion distance of the Pusa landslide was located in the middle of the slope body, with the maximum distance as 79 m, while the maximum instantaneous motion rate was around 42 m/s in the middle and lower part of the slope body. Finally, the failure mode of Pusa landslide can be characterized as ‘fissure zone in the middle, fissure extension to the top, rock bulges outward in the middle and landslide failure to high-speed runout debris flow’.

Biofilm mass transfer and thermodynamic constraints shape biofilm in trickle bed reactor syngas biomethanation

Syngas (H2, CO2, CO) produced thermochemically from lignocellulosic biomass is an underexploited source for resource recovery and valorisation through its biological conversion for the production of a wide range of chemicals and fuels. Syngas biomethanation is one such promising bioconversion pathway, displaying interesting features such as high conversion efficiency and product selectivity, as methane is the sole product of the process. The biological conversion of syngas to high purity biomethane is still typically associated with a number of challenges related to the syngas composition, CO toxicity, and gas–liquid mass transfer limitations. In this work, the syngas biomethanation process carried out in trickle bed reactors was investigated at its boundary conditions to explore the limits of the process, focusing on syngas composition and mass-transfer conditions potentially limiting process performance. The process was found to be robust when exposed to CO excess, but highly sensitive to H2 excess, which caused severe inhibition even under small amounts of excess H2. This implies that biomethane purity comparable to natural gas can be achieved by addition of renewable H2, but this requires precise control to avoid process failure. Modulating the liquid recirculation rate and gas residence time allowed for a maximum methane productivity of 9.8 ± 0.5 mmol CH4 h−1 Lreactor−1 with full conversion of H2 and CO at a gas residence time of 1 h. Nevertheless, increasing the gas–liquid mass transfer with increasing liquid recirculation rate did not lead to increased methane productivity, which suggested additional rate-limiting bottlenecks in the process. Careful investigation of other factors potentially limiting the process led to the conclusion that diffusive transport of syngas components in the biofilm was the main bottleneck of the process. This diffusive limitation leads to a scenario of severe substrate scarcity in the biofilm phase that conditions the thermodynamic feasibility of the different biochemical reactions involved in syngas biomethanation. In turn, these thermodynamic constraints were found to drive the stratification of microbial groups and sequential consumption of syngas components along the height of the reactor

Overload cascading failure detection algorithm for multi-layer supply chain network considering delay probability factor

At present, the supply chain is multi-layered and complicated, and its failure detection is based solely on the characteristic threshold, which does not lack the ability to describe the complex supply chain. An overload cascading failure detection algorithm for multi-layer supply chain network considering delay probability is proposed. Based on the multi-layer supply chain network including raw material suppliers, manufacturers, distributors and retailers, the overload cascading failure model of the multi-layer supply chain network is constructed through networking, and the overload cascading failure process of the multi-layer supply chain network is described through three aspects: initial load, node capacity and overload node load distribution. By monitoring and analyzing the status update messages of each node in the supply chain network, and considering the delay probability factor, the node and path that may lead to cascading failure are identified by predicting the delay probability of the next message through the historical message delay probability, and the overload cascading failure detection of the multi-layer supply chain network is realized. The experimental results show that the algorithm can effectively detect the failure of each overloaded enterprise node in the multi-layer supply chain network, which is helpful to enhance the early warning and response ability of the cascade failure of the supply chain network. The algorithm can realize the failure detection of supply chain network under different attack conditions and initial failure ratio of nodes, and measure the anti-risk ability of supply chain network. Under deliberate attack and when the initial attack node is a supplier network layer node, it has a greater impact on the multi-layer supply chain network.

Study on the characteristics of acoustic-thermal precursors of destabilization damage in coal-rock combination bodies with different proportions

The instability and failure processes of coal-rock combinations are accompanied by the release of acoustic emission (AE) and infrared radiation (IR) signals. To investigate the characteristics of AE and IR signals during the failure process in coal-rock combinations with different ratios, and to analyze the effectiveness and applicability of the monitoring methods for these two signals in various specimen ratios. In this paper, the uniaxial compression tests were conducted on seven coal-rock combinations with different ratios by using the rock mechanics loading system and the cooperative monitoring platform of infrared and acoustic emission. The results show that (1) the AE counts for failure precursors in coal-rock combinations are positively correlated with the coal-rock ratio, whereas the AE peak counts are negatively correlated. Moreover, as the coal-rock ratio decreases, the slope of the cumulative AE count curve during the peak failure stage approaches 1. (2) During the elastic and yield stages, the maximum infrared radiation temperature (MIRT) curve fluctuates, and just before peak failure, the curve displays a distinctive “V” shape. This “V” shape becomes more pronounced as the coal-rock ratio decreases. (3) In the monitoring of damage precursors of coal-rock combinations, when the ratio of coal to rock is 1:3 or less, IR monitoring is better than AE monitoring. Conversely, when the ratio of coal to rock is greater than 1:3, AE monitoring is more suitable. Consequently, the combined monitoring of AE and IR signals can increase the reliability and precision of early warning signals for coal-rock assemblage damage precursors.

Selection processes, transportability, and failure time analysis in life history studies.

In life history analysis of data from cohort studies, it is important to address the process by which participants are identified and selected. Many health studies select or enrol individuals based on whether they have experienced certain health related events, for example, disease diagnosis or some complication from disease. Standard methods of analysis rely on assumptions concerning the independence of selection and a person's prospective life history process, given their prior history. Violations of such assumptions are common, however, and can bias estimation of process features. This has implications for the internal and external validity of cohort studies, and for the transportabilty of results to a population. In this paper, we study failure time analysis by proposing a joint model for the cohort selection process and the failure process of interest. This allows us to address both independence assumptions and the transportability of study results. It is shown that transportability cannot be guaranteed in the absence of auxiliary information on the population. Conditions that produce dependent selection and types of auxiliary data are discussed and illustrated in numerical studies. The proposed framework is applied to a study of the risk of psoriatic arthritis in persons with psoriasis.

Design an Agricultural Soil and Environment Monitoring System Based on IoT

One of the problems farmers face is the inability to make complete, real-time, and accurate observations of their farmland. The system proposed in this paper helps farmers to know the condition of farmland from anywhere and anytime by using a web-based application. The main objective of this prototype is to reduce the failure of the growth process of farming commodities by knowing the conditions inside and outside the soil with a total of 14 parameters. Internet of Things (IoT) technology is used to implement the prototype, which consists of Sensor Panels, Controllers, Message Broker, and Backend Service. All obtained data, created and tested in real-time, are displayed on the application. In addition to real-time data display, the system also includes monitoring history, alerts, and site location management.

Determination of the REV size for heterogeneous rocks with different grain sizes: Deep learning and numerical approaches

Accurate determination of the representative elementary volume (REV) size plays a pivotal role in analysing the mechanical properties and failure processes of heterogeneous rocks in complex engineering environments. In this study, a novel microstructure modelling strategy (NMMS) for determining the REV size is proposed by combining deep learning and an improved phase-field method (PFM). Micro- and macroscale experiments are systematically conducted to determine the real microstructural characteristics and mechanical properties of heterogeneous rocks with different grain sizes. On the basis of this experimental evidence, geometric models of different sizes were reconstructed through deep learning to avoid the limitations of human-based methods, and an improved PFM was used for numerical calculations. These models were then employed to perform numerical tests under uniaxial loading conditions, and the coefficient of variation was introduced to determine the REV size of heterogeneous rocks with different grain sizes. The research findings indicate that the final REV size is the maximum value of the REVs defined by the evaluation properties within an acceptable coefficient of variation. At a criterion of 5% for the coefficient of variation, the REV sizes are 60 mm×60 mm, 70 mm×70 mm, and 90 mm×90 mm for fine-medium-grained (FMG), medium-grained (MG), and coarse-grained (CG) rocks, respectively. Furthermore, the REV determined by the NMMS was applied to investigate the effects of microstructure on macromechanical properties and damage evolution under triaxial loading conditions. The numerical results show that the NMMS can accurately predict the macromechanical properties and microcracking patterns of heterogeneous rocks, especially the intracrystalline cracks in feldspar, the interfacial cracks in gravel, and the “voids” of cracks in biotite. This research can provide some basic references for the optimal choice of the REV size of heterogeneous rocks.

Evaluating overhanging slope failure mechanisms and rockfall trajectories through integrated UAV imagery and discrete element modeling

AbstractTo evaluate the threat of rockfall from an overhanging slope above a bridge, this study proposes a comprehensive analysis procedure to assess the failure mechanisms of the slope and the associated rockfall trajectories. The analysis utilizes high-resolution point cloud data obtained through integrated UAV-based imagery technology, enabling a detailed evaluation of joint configurations and slope stability. The geometric reconstruction of unstable rock blocks, combined with stereographic projections, provides an in-depth analysis of potential failure modes. Discrete element modeling (DEM) is employed to simulate the failure processes and predict rockfall trajectories, with particular emphasis on the potential risks to the underlying bridge. The results indicate that rockfall events near the bridge are primarily driven by wedge-shaped failures, a finding confirmed by both the proposed inverted three-dimensional projection method and DEM simulations. The analysis identifies critical rock blocks near the bridge, underscoring the need for targeted mitigation strategies. This case study demonstrates the effectiveness of integrating UAV-derived data with DEM for assessing overhanging slope failures and managing rockfall risks in similar geological settings.

Experimental study on the compression and shear deformation evolution of coal pillar dam samples

To understand the mechanical properties and deformation failure patterns of coal pillar dams in gently inclined coal seam mine underground reservoirs, compression-shear coupling tests with variable angles were conducted on coal pillar dam samples under different saturation states. The digital image correlation (DIC) technique was utilized to obtain the deformation patterns of the displacement field throughout the compression-shear failure process of the samples. Numerical simulations were used to perform a comparative analysis and validation of the experimental results. The results indicated that the load-bearing capacity of the coal pillar dam samples decreased by 12.8–17.4% under water-saturated conditions. For every 5° increase in the inclination angle, the load-bearing capacity of the coal pillar dam samples decreased by an average of 3.53%. The normal stress and shear stress on the shear surface of the saturated samples were both lower than those of the natural samples, and both exhibited a linear variation with increasing inclination angle. The deformation evolution of the coal pillar dam samples under different test conditions exhibited similarity. The initial positive and negative displacement extremities in the horizontal direction were located at the lower right and upper left corners of the samples, respectively. Ultimately, the displacement field of the samples showed a pattern of smaller displacements at the top and larger displacements at the bottom, with negative values at the top and positive values at the bottom, distributed along the direction of the sample’s bedding. The saturated state and the increase in inclination both had a weakening effect on the load-bearing performance of the samples but had a relatively small impact on the differences in the displacement field deformation patterns. The research results can provide a reference for the study of the stability of coal pillar dams under similar conditions.

Rock Slope Instability Mechanism Induced by Repeated Mining in Mountain Mining Areas

When mineral resources are extracted using underground mining methods in hilly regions, landslides or slope failures can be induced frequently. In this study, slope collapse disasters in mountain mining areas were analyzed. The model test and numerical simulation of the slope impacted by repeated mining were carried out. The crack evolution and failure process were analyzed to reveal the instability mechanism. The results show that the rock mass would topple to the inside of the slope first, when the subsidence of overlying rock was induced by the mining of the upper coal seam. When repeated mining was performed in the lower coal seam, the mining induced macro-cracks that could connect with natural fissures, inducing the outward displacement of the slope. Then, the rock mass at the foot of the slope has to bear the upper load, which is also squeezed out by the collapsed rock mass, forming the potential slip zone. Finally, the instability is caused by the shear slip of the slope toe rock mass. Therefore, the instability evolution of the slope under underground repeated mining disturbance can be divided into four stages as follows: roof caving and overlaying rock subsidence, joint rock toppling, fracture penetration, and slope toe shearing and slope slipping.

Dynamics of real-time forecasting failure and recovery due to data gaps: A study using EnKF-based assimilation with the Lorenz model

Data assimilation-based real-time forecasting is widely used in meteorological and hydrological applications, where continuous data streams are employed to update forecasts and maintain accuracy. However, the reliability of the data source can be compromised due to sensor and communication failures or physical or cyber-attacks, and the impact of data stream failures on the accuracy of the forecasting system is not well understood. This study aims to systematically investigate the process of data stream failure and recovery for the first time. To achieve this, data gaps with varying lengths and timings are introduced to EnKF-based data assimilation system on the Lorenz model operating in both chaotic and periodic modes. Results show that the forecasting error grows exponentially in the chaotic mode but was limited in the periodic mode from the start of the data gap. For chaotic mode, the recovery of the system depends on the length of the data gap if the model error is not saturated; after saturation, the timing of the data stream recovery is important. Moreover, even long after restarting the data assimilation in the chaotic mode, the forecasting system cannot fully restore the original accuracy, while the periodic mode is generally resilient to disruption. This research introduces new metrics for quantifying system resilience and provides crucial insights into the long-term implications of data gaps, advancing our understanding of forecasting system behavior and reliability.

Numerical and experimental study on corrosion mechanism of the water-oil two-phase flow in the atmospheric tower top system

The atmospheric tower is the main component of the crude oil refining units and is a critical area of concern due to the risk of corrosion failure. Research on the corrosion mechanism and risk protection of atmospheric tower top systems plays a vital role in the safe operation of refineries. In this paper, the water-oil two phase process flow of the atmospheric tower top system was simulated by Aspen software. A corresponding flow corrosion simulation experiment was designed according to the main characteristic parameters of the simulated stream. The experimental results under varying temperature and impact angle conditions were analyzed by using microanalysis technology and CFD simulation methods. The process and mechanism of corrosion failure of tower top system under ammonia salt and dew point corrosion environment are revealed in physicochemical aspects. The results show that the corrosion rate was highest at the dew point temperature, but as the temperature decreases, the corrosion products adsorbed and accumulated on the surface are more difficult to remove from the surface, which slows down the corrosion rate. When the impact angle increased from 0° to 60°, the increment of the surface fluid impact force and turbulence intensity makes the corrosion products easier to be stripped off, which enhances the mass transfer efficiency between the corrosive medium and the surface to accelerate the corrosion rate. Different phase states and flow modes affected the morphology of corrosion pits on the surface. The depth and size of the pits in only water phase corrosion were larger than those in the two-phase flow corrosion, Additionally, as the impact angle increased from 0°, the morphology of pits changes from a relatively flat pattern to a more undulating shape. The research results reveal the characteristics of the main corrosion types occurring in the atmospheric tower top system of the oil refining industry, and provide a reference for corrosion risk protection methods.

Simulation of the failure and run-out processes of rotational–translational loess landslides using an SPH model considering strain softening

Simulation of the failure and run-out processes of rotational–translational loess landslides using an SPH model considering strain softening

Model test study on the dynamic failure process of tunnel surrounding rocks in jointed rock mass under explosive load

The presence of joints can significantly reduce the integrity and stability of an engineering rock mass. Under dynamic loads, such as from blasting excavation, the key blocks divided by joints may be destabilized and prone to sliding, potentially leading to engineering geological disasters like rockbursts. To study the dynamic instability process, similar materials for the rock mass and joints were developed based on the similarity theory, and a tunnel model in the jointed rock mass was constructed. Subsequently, a detonating fuse was used to generate a dynamic load, and the dynamic instability process of the tunnel surrounding rock in the jointed rock mass under explosive load was studied using the geotechnical multifunctional testing device. The deformation characteristics and dynamic instability process of the tunnel surrounding rock were analyzed using acceleration sensors, resistance strain gages, linear variable displacement transducers and motion camera. The study shows that the acceleration at the tunnel vault is significantly greater than at the straight wall and floor under blast loads, with differences reaching an order of magnitude. Acceleration waveforms were classified into three categories based on peak characteristics, explained through the propagation of explosive stress waves. Additionally, strain and displacement at the tunnel arch were also significantly greater than in other areas, indicating more severe stress concentration and dynamic damage at the arch, necessitating reinforced support in tunnel excavation. The entire dynamic instability process of the tunnel surrounding rock was successfully recorded using a motion camera. The dynamic failure process was divided into several phases, the appearance of cracks on the joint surface, particle ejection accompanied by the dropping of jointed blocks, a significant drop of the jointed blocks, and return to calm. The dynamic failure modes include the dropping and rotation of jointed blocks, local particle ejection, and shear cracks on jointed block.

Uncovering the Fracturing Mechanism of Granite Under Compressive–Shear Loads for Sustainable Hot Dry Rock Geothermal Exploitation

Shear-dominated hazards, such as induced earthquakes, pose an escalating threat to the sustainability and safety of the geothermal exploitation. Variations in fault orientations and compression–shear stress ratios exert a profound influence on the failure processes underlying these disasters. To better understand these effects on the shear failure mechanisms of hot dry rocks, mode-II fracturing tests on granites were conducted at varying loading angles (specifically, 55°, 60°, 65°, and 70°). These tests were accompanied by a comprehensive analysis of the mechanical properties, energy dissipation behavior, acoustic emission (AE) responses, and digital image correlation (DIC)-extracted displacement fields. The tensile–shear properties of stress-induced microcracks were discerned via AE characteristic parameter analysis and DIC displacement decomposition, and the mode-II fracture energy release rate was quantitatively characterized. The results reveal that with increasing compression–shear loading angles, the mechanical properties of granites are weakened, and the elastic strain energy at peak stress gradually decreases, while the slip-related dissipated energy increases. Throughout the fracturing process, the AE count progressively climbs and reaches a peak near catastrophic failure, with an upsurge in low-frequency and high-amplitude AE events. Microcrack distribution concentrates aggregation along the shear plane, reflecting the emergent displacement discontinuities evident in DIC contours. Both the AE characteristic parameter analysis and DIC displacement decomposition demonstrate that shear-sliding constitutes the paramount mechanism, and the fraction of shear-oriented microcracks and the ratio of tangential versus normal displacement escalate with increases in shear stress. This analysis is supported by the heightened propensity for transgranular microcracking events observed through scanning electron microscopy. As the shear-to-compression stress increases, the energy concentration along the shear band intensifies, with the gradient of the fitting line between cumulative AE energy and slip displacement steepening, indicative of a heightened mode-II energy release rate. These results contribute to a deeper understanding of the mode-II fracture mechanism of rocks, thereby providing a foundational basis for early warnings of shear-dominant geomechanical disasters, and improving the safety and sustainability of subsurface rock engineering.

Advance industrial monitoring of physio-chemical processes using novel integrated machine learning approach

With the rapid transition of Industry 4.0 to 5.0, modern industrial physio-chemical processes are characterized by two critical challenges: process safety and the quality of the final product. Traditional industrial monitoring methods have low reliability in accuracy and robustness, and they are inefficiently providing satisfactory results. This paper introduces a novel integration technique that employs machine learning (ML) to tackle the challenges associated with real industrial monitoring in physical and industrial processes. The proposed framework integrates distributed canonical correlation analysis - R-vine copula (DCCA-RVC), global local preserving projection (GLPP), and 2-Dimensional Deng information entropy (2-DDE). The framework's ability and productivity are assessed utilizing existing approaches such as wavelet-PCA, MRSAE, and DALSTM-AE and the new proposed novel integrated machine learning-based (DCCA-RVC) approach as benchmarks for model performance. The proposed novel approach has been validated by testing it on the ethanol-water system distillation column (DC) and Tennessee Eastman Process (TEP), utilizing it as actual industrial benchmarks. The results demonstrate that the novel integration ML-technique (DCCA-RVC) T22 – GLP monitoring graphs for the fault class type 1 in the distillation column showed a (FAR) of 0 %, a (FDR) of 100 %, a precision of 100 %, F1-score of 100 % and an accuracy of 100 %. However, for the TEP process failure event 13, the (FAR) was 0 %, the (FDR) was 99 %, the accuracy was 100 %, the F1-score was 99.5 %, and the accuracy was 99.5 %.