Large Mesh Research Articles

Memory-efficient boundary-preserving tetrahedralization of large three-dimensional meshes

Memory-efficient boundary-preserving tetrahedralization of large three-dimensional meshes

OC-029 E- MILOS EXTRAPERITONEAL MESH REPAIR OF UMBILICAL HERNIAS WITH COMBINED RECTUSDIASTASIS

Abstract Aim Umbilical hernias with combined rectusdiastasis have a higher risk für recurrence after single repair of the umbilical hernia. The E- MILOS concept enables the minimal invasive sublay mesh repair realizing the benefits of minimally invasive surgery and placing the mesh in the retromuscular position. Materials & Methods All E- MILOS operations were documented prospectively. For 1 year follow-up all patients received a questionnaire. Results From January 2019 to December 2022, 89 patients (24 female/65 male) with umbilical hernia and a coexisting rectus diastasis (median hernia size 2 cm/diastasis recti 5,5 cm) and median age of 61 yrs were operated by 3 experienced surgeons. In all cases a polypropylene mesh (median size 40×12 cm) was implanted in the retromuscular space without any fixation and continuous suture (V-Loc 2–0) of the anterior and posterior rectus sheet was achieved for reconstructing the midline. The average skin incision was 4,5 cm; median operation time was 125 min. The median hospital stay was 5 days, the postoperative median pain score (VAS) was 2. Two patients needed reoperation due to a retromuscular haematoma. Chronic pain was reported by 13 patients, no postoperative infection and 4 recurrences were observed. Not satisfied with the cosmetic result (subcutaneous bulging) were 4 female patients. Conclusions The E- MILOS technique allows minimally invasive transhernial repair of umbilical hernias with combined rectusdiastasis using large retromuscular meshes with low morbidity. The technique is reliable and easy to standardize and shows mostly good cosmetic results.

V-021 MIDLINE RESTORATION VIA EMILOS TECHNIQUE

Abstract Aim In recent years, numerous minimally invasive techniques have been developed for the repair of midline hernias associated with diastasis recti. The eMILOS technique (Endoscopic mini/less open sublay technique) allows midline repair with mesh placement in the retromuscular space through a small trans-hernial incision without entering the abdominal cavity. Material & Methods We present a case of a 45 year-old male who complained of umbilical bulge and pain. On physical exam, an umbilical hernia measuring 2cm was observed, associated with 5cm diastasis recti. Midline restoration via eMILOS approach was decided. In this technique, a transhernial endoscopic approach is performed with two 5mm ports on both flanks, allowing a complete dissection of the retromuscular space. First, a sublay approach of the umbilical hernia is performed. The hernial content is reduced and the posterior sheath is closed. Then, we place a homemade device (consisting of a wound protector, a surgical glove and a port) to perform the endoscopic approach. When the retromuscular space is completely dissected, both anterior and posterior sheaths are closed with barbed sutures. A large heavy polypropylene mesh is placed and fixed with absorvable tackers and glue. Afterwards, the endoscopic step is over and the ports are taked out, the umbilical fascia is closed with a running suture and the umbilicus scar is fixed. Results The patient presented a favorable evolution, with no recurrence a year postoperatively. Conclusions The eMILOS technique is a safe and effective alternative for the treatment of diastasis recti associated with midline defects.

OC-089 A CHALLENGING REPAIR OF RECURRENT VENTRAL HERNIA IN A PATIENT WITH A PREVIOUS INTRAPERITONEAL MESH AND ABDOMINOPLASTY

Abstract Aim To understand the challenges faced in repair of recurrent ventral hernia in a patient with a previous intraperitoneal mesh and abdominoplasty. Introduction Ventral hernias still represent a great challenge for surgeons, especially if they are recurrent. We present a 54-year-old overweight female with complex surgical history and a recurrent incisional hernia. She had a laparoscopic cholecystectomy and port site hernia which was repaired without a mesh. She later underwent a Roux-en-Y Gastric bypass for obesity and developed another port site hernia in lower epigastrium. The incisional hernia was repaired with an intraperitoneal mesh. Finally, she had an abdominoplasty for cosmetic reasons. She presented to our surgical clinic with a clinically palpable recurrent large incisional hernia. Methods The repair was carefully planned with a CT abdomen confirming a 6 cm defect in the upper midline and a large intraperitoneal mesh with multiple metallic tacks. The surgical procedure was as follows: Midline incision and careful dissection of the sac. The intraperitoneal mesh was identified and removed carefully keeping the posterior rectus sheath and peritoneum intact. A posterior component separation technique was performed. Posterior rectus sheath was closed with interrupted absorbable sutures. A tailored polypropylene mesh was placed in retro-rectus space. The anterior rectus sheath was closed with non-absorbable interrupted sutures. Patient had an uneventful postoperative period and was discharged on the third postoperative day. Conclusion Careful patient selection, detailed preoperative planning and expertise in abdominal wall reconstruction result in a successful repair of complex ventral hernias.

P-006 OUR EXPERIENCE WITH TAR FOR COMPLEX INCISIONAL HERNIA REPAIR

Abstract Aim Transverse abdominis muscle release (TAR) enables dissection of the preperitoneal space and the placement of large meshes. We present our experience with TAR in the treatment of complex incisional hernias (IH). Material and Methods Retrospective, descriptive study of patients operated with the TAR technique (October 2019-July 2022). Epidemiological characteristics, comorbidity, prehabilitation, type of IH, bridging, surgical time, hospital stay, morbidity, mortality and recurrence were studied. Results 69 TAR (30 females/39 males); age 64.9 years (24–85), body mass index 31 (19–49), CeDAR 35% (4–92). 66 cases (96%) treated preoperatively with Botulinum Toxin A, 31 (45%), with preoperative progressive pneumoperitoneum and 29 (42%) with both. Classification (EHS): M 52 (46%), L 7 (10%), ML 9 (13%), parastomal 1 (1%), tumour 1 (1%). 36 cases R0 (52%), R1 22 (32%), R2 4 (10%) and R3 6 (9%). Median size 17.8 cm(3–30) x13.7 cm (6–25), area 694.3 cm2. Primary fascial closure was achieved in 26 cases (38%), remaining 43 (62%) with bridging (8.7 cm (2–19)x5 cm (1–16)), postoperative area 125.6 cm2 (82% reduction). Surgical time was 242 minutes (140–450). Hospital stay 9 days (3–45). Wound-related complications 35 (50%): infection 15 (21%), seroma 17 (24%), haematoma 15 (7%), skin necrosis 1 (1%). General complications 7 (10%): 2 urinary tract infection, 1 intestinal perforation, 1 pneumonia, 1 haematoma, 1 haemorrhagic shock, 1 heart failure. Mortality 2 (3%). Recurrences 0 (0%). Conclusions TAR is a very useful and effective technique for resolving complex eventrations. It is not exempt from morbidity, therefore adequate patient selection is recommended.

A Model for the Fate of a Gas Bubble Interacting with a Wire Mesh.

In the concept of a microstructured bubble column reactor, microstructuring of the catalyst carrier is realized by introducing a static mesh of thin wires coated with catalyst inside the column. Meanwhile, the wires also serve the purpose of cutting the bubbles, which in turn results in high interfacial area and enhanced interface hydrodynamics. However, there are no models that can predict the fate of bubbles (cut/stuck) passing through these wires, thus making the reactor optimization difficult. In this work, based on several typical bubble-wire interacting configurations, we analyze the outcomes by applying the energy balance of the bubble focusing on buoyancy and surface tension. Two limiting cases of viscosity, corresponding to the ability of the bubble to reconfigure into the lowest energy state, are investigated. Upon analysis, it is observed that a narrow mesh spacing and a smaller bubble Eötvös number generally result in bubbles getting stuck underneath the wire. We have obtained the threshold grid spacing and the critical Eötvös number for bubble passage and bubble cutting, which are verified by the direct numerical simulation results of bubble passing through a single mesh opening. The derived energy balance is generalized to large meshes with multiple openings and different configurations. Finally, a closure model based on the outcomes of energy-balance analysis is proposed for Euler-Lagrange simulations of microstructured bubble columns.

Hydration-induced Void-containing Hydrogels for Encapsulation and Sustained Release of Small Hydrophilic Molecules.

Efficient encapsulation and sustained release of small hydrophilic molecules from traditional hydrogel systems have been challenging due to the large mesh size of 3D networks and high water content. Furthermore, the encapsulated molecules are prone to early release from the hydrogel prior to use, resulting in a short shelf life of the formulation. Here, we present a hydration-induced void-containing hydrogel (HVH) based on hyperbranched polyglycerol-poly(propylene oxide)-hyperbranched polyglycerol (HPG-PPG-HPG) as a robust and efficient delivery system for small hydrophilic molecules. Specifically, after the HPG-PPG-HPG is incubated overnight at 4 °C in the drug solution, it is hydrated into a hydrogel containing micron-sized voids, which could encapsulate hydrophilic drugs and achieve 100% drug encapsulation efficiency. In addition, the voids are surrounded by a densely packed polymer matrix, which restricts drug transport to achieve sustained drug release. The hydrogel/drug formulation can be stored for several months without changing the drug encapsulation and release properties. HVH hydrogels are injectable due to shear thinning properties. In rats, a single injection of the HPG-PPG-HPG hydrogel containing 8 μg of tetrodotoxin (TTX) produced sciatic nerve block lasting up to 10 hours without any TTX-related systemic toxicity nor local toxicity to nerves and muscles.

103 Chew frequency and duration in horses consuming bermudagrass hay in slow feeders as compared to loose hay

Stabled horses are predisposed to gastrointestinal disorders related to hay consumption. Horses produce saliva when chewing which contains sodium bicarbonate to buffer stomach acid, lubricate a food bolus, and aid in digestion. Chewing hay over a prolonged period allows for buffering of stomach acid to aid in prevention of gastric ulcers. Additionally, increased chewing results in food particle size reduction and improves lubrication to potentially decrease the incidence of impaction colic. Hay nets have been promoted to slow the rate of hay consumption, with many styles of nets and slow feeders currently marketed for horses. No research has yet demonstrated whether hay nets cause the horse to increase their chewing frequency and chewing duration, or whether the slowing effect is simply due to restriction in the amount of forage they can ingest per bite. The objective of this study was to compare chew frequency (CF, total number of chews/kg consumed) and chew duration (CD, total minutes chewed/kg consumed) of horses eating bermudagrass hay in 3 styles of hay nets [large mesh (LM), small mesh (SM), bottom hole (BH)] as compared with a control of loose hay (CTL). Before initiating this project, trial data was collected from 2 horses over 4 d and demonstrated that horses acclimate quickly to hay nets. No differences were seen in CF from day one through d 4 (P = 0.49). Eight horses were then divided into 2 trials, with the4 horses in each trial rotating through treatments in a Latin square design.Each horse was given a 24-h acclimation period to a treatment, and then their chewing patterns were recorded for the following 24 h using an automated halter fit with a pressure-sensor noseband (EquiwatchTM, Liestal, Switzerland). Refused hay was weighed back, and CF and CD were calculated per kg of hay consumed. Data were analyzed using Minitab v.21 (State College, PA, USA) as a mixed model ANOVA with net type as the fixed effect and a post hoc Tukey's test to compare treatments. Data with P < 0.05 were considered statistically different. No treatment difference was noted in amount of hay consumed, with horses chewing an average of 6.8 ± 0.3 kg per treatment. Results indicate no difference between treatments in CF (P = 0.72). CD showed no overall treatment effect (P = 0.27), however, when individual treatments were compared, a statistical difference between SM and CTL was noted (262 vs 189 min respectively, P = 0.001). Results of this study indicate that slow feeders do not influence the number of chews a horse performs while masticating hay, but small mesh feeders do increase the amount of time spent chewing as compared with loose hay.

Body size in relation to rotifer abundance underestimation using a net of large mesh size in a tropical reservoir

Body size in relation to rotifer abundance underestimation using a net of large mesh size in a tropical reservoir

Spatio-temporal patterns of human-wildlife conflicts and effectiveness of mitigation in Shuklaphanta National Park, Nepal.

Human-wildlife interactions occur where human and wildlife coexist and share common resources including food or shelter. Increasing wildlife populations within protected areas also can increase interactions with humans living adjacent to these areas, resulting in conflicts including human casualty, livestock depredation, crop damage, and property loss. We analyzed six years human-wildlife conflict data from 2016-2021 in the buffer zone of Shuklaphanta National Park and conducted questionnaire survey to investigate factors influencing human-wildlife conflicts. Nineteen people were attacked by wildlife, primarily wild boar (Sus scrofa). Ninety-two livestock were killed by leopard (Panthera pardus), and among these most were sheep or goats killed near ShNP during summer. Crops were most frequently damaged by Asian elephants (Elephas maximus), followed by wild boar. Greatest economic losses were from damage to rice, followed by sugarcane and wheat. Asian elephant was the only reported species to cause structural damage to property (e.g., homes). Majority of respondents (83%) considered that the mitigation techniques that are currently in practice are effective to reduce the conflicts. However, the effectiveness of the mitigation techniques are the species specific, we recommend use of more efficacious deterrents (e.g., electric fencing) for large herbivores and mesh wire fencing with partially buried in the ground. Effective collaboration among different tiers of government, non-governmental organizations, civil societies and affected communities are important to share the best practices and continue to apply innovative methods for impactful mitigation of human-wildlife conflicts in the region.

A robust numerical scheme for singularly perturbed differential equations with spatio-temporal delays

In this article, we proposed and analyzed a numerical scheme for singularly perturbed differential equations with both spatial and temporal delays. The presence of the perturbation parameter exhibits strong boundary layers, and the large negative shift gives rise to a strong interior layer in the solution. The abruptly changing behaviors of the solution in the layers make it difficult to solve the problem analytically. Standard numerical methods do not give satisfactory results, unless a large mesh number is considered, which needs a massive computational cost. We treated such problem by proposing a numerical scheme using the implicit Euler method in the temporal variable and the nonstandard finite difference method in the spatial variable on uniform meshes. The stability and uniform convergence of the proposed scheme have been investigated and proved. To demonstrate the theoretical results, numerical experiments are carried out. From the theoretical and numerical results, we observed that the method is uniformly convergent of order one in time and of order two in space.

Testing of a helix twine off-bottom trawl on Georges Bank

The massive biomass of Eastern Georges Bank haddock (Melanogrammus aeglefinus) is difficult to harvest without capturing less robust, but still valuable groundfish stocks like Atlantic cod (Gadus morhua) and some flatfish species. Specialized haddock trawls that raise the mouth of the nets off-bottom have reduced bycatch but the very poor status of Atlantic cod prioritizes even greater reduction to prevent exceeding regulatory fishing quotas. Raising the entire fishing gear off-bottom may further reduce bycatch while eliminating benthic impacts, expanding access to grounds previously off-limits to bottom-tending trawls. We evaluated an off-bottom trawl (OBT) to harvest Eastern Georges Bank haddock while reducing catches of overexploited stocks. The OBT net has very large meshes at the front end, made with innovative “helix” twine that produces lateral hydraulic forces while towing, resulting in self-spreading of the meshes. We established optimal gear configurations to achieve the target OBT net shape and distance to the seafloor by using an assortment of mensuration sensors/loggers and cameras. The OBT caught similar amounts of haddock and reduced some bycatch more than a standard bottom “Ruhle trawl”, but also caught fish of the same lengths despite the OBT using a smaller mesh-sized codend. The OBT also demonstrated similar requirements in vessel RPMs as the Ruhle trawl, despite having a larger swept area.

Clinical effect of limited posterior decompression and 13-mm titanium mesh implantation onsevere thoracolumbar burst fractures: A case series.

Posterior incision with 270° spinal canal decompression and reconstruction surgery is a treatment option for thoracolumbar burst fractures (TLBF), but the large diameter titanium mesh placement is difficult. This study evaluated the characteristics and clinical effects of limited posterior decompression and 13-mm titanium mesh implantation to treat TLBF. 13-mm titanium meshes could be used to fix thoracolumbar burst fractures. This case series included patients who underwent limited posterior decompression and 13-mm titanium mesh implantation at China Medical University Shaoxing Hospital (01/2015-12/2019). The Cobb angle, injury vertebral anterior edge height loss percentage, and spinal canal occupancy rate were analyzed. The degree of spinal cord injury was evaluated according to the ASIA grade. Fifteen patients were included (eight males and seven females). The patients were 32.2 ± 4.6 years of age. The American Association of Spinal Injury improved after surgery (A/B/C/D/E: from 2/6/5/2/0 to 0/0/2/8/5, P < 0.001). The Cobb angle decreased after surgery (from 20.1 ± 4.8° to 7.1 ± 1.4°, P < 0.001) but increased to 8.2 ± 0.9° at 1 year (P = 0.003). The percentage of loss of the anterior edge height of the injured vertebrae decreased after surgery (from 40.9% ± 6.1% to 7.5% ± 1.8%, P < 0.001) and decreased at 1 year (7.0% ± 1.5%, P = 0.044). The spinal canal occupancy rate decreased after surgery (from 64.8% ± 7.8% to 20.1% ± 4.2%, P < 0.001) but did not decrease further at 1 year (19.4% ± 3.4%, P = 0.166). Spinal canal limited posterior decompression, and 13-mm titanium mesh implantation in the treatment of TLBF can achieve one-stage spinal canal decompression and three-column reconstruction. The curative effect was satisfying. Level IV; case series.

Prediction of buffeting responses of the thin plate under joint action of wave and wind using LSTM and transfer learning

To predicate the buffeting responses of long-span sea-crossing bridges under joint action of wave and wind, a thin plate was taken as the example, and a piston-type wave maker was adopted to simulate the second order Stokes wave in a computational domain. Through the large eddy simulation (LES) and dynamic mesh methods, time-histories of wind field and buffeting response of the thin plate under joint action of wave and wind were obtained. Then, the buffeting responses of the thin plate were predicted using the conventional long short-term memory (LSTM), convolutional LSTM (Conv LSTM) and LSTM with attention mechanism (LSTM-AM) neural network models, respectively. Furthermore, the transfer learning (TL) method was introduced, the method to solve a large amount of source task data was established, and a combined neural network model of TL-Conv LSTM-AM was proposed to predict the buffeting responses of the thin plate. The results show that the prediction accuracies of Conv LSTM and LSTM-AM models are both higher than the conventional LSTM model based on the evaluation indexes of determination coefficient (R2) and root mean square error (RMSE). The prediction accuracies of the buffeting responses can be improved significantly when the above LSTM neural network models are combined with the TL method. Also, there are still some deviations between the predicated time-histories and target ones. For the proposed combined model of TL-Conv LSTM-AM, the values of R2 in three directions of the buffering responses are all larger than 0.996 and 0.983 in the high and low turbulent flow fields, respectively. Therefore, the proposed TL-Conv LSTM-AM combined model has the highest prediction accuracy among them. Similar prediction accuracy can be achieved for longer time duration of the testing data set using the proposed combined model of TL-Conv LSTM-AM. The above phenomenon proves that the effectiveness of this proposed combined model in predicting the buffeting responses of the thin plate under joint action of wave and wind.

Adenylate Kinase Fused to Spidroin as a Catalyst for Decreasing Leakage out of 3D-Bioprinted Hydrogels and for ATP Regeneration.

Numerous metabolic reactions and pathways use adenosine 5'-triphosphate (ATP) as an energy source and as a phosphorous or pyrophosphorous donor. Based on three-dimensional (3D)-printing, enzyme immobilization can be used to improve ATP regeneration and operability and reduce cost. However, due to the relatively large mesh size of 3D-bioprinted hydrogels soaked in a reaction solution, the lower-molecular-weight enzymes cannot avoid leaking out of the hydrogels readily. Here, a chimeric adenylate-kinase-spidroin (ADK-RC) is created, with ADK serving as the N-terminal domain. The chimera is capable of self-assembling to form micellar nanoparticles at a higher molecular scale. Although fused to spidroin (RC), ADK-RC remains relatively consistent and exhibits high activity, thermostability, pH stability, and organic solvent tolerance. Considering different surface-to-volume ratios, three shapes of enzyme hydrogels are designed, 3D bioprinted, and measured. In addition, a continuous enzymatic reaction demonstrates that ADK-RC hydrogels have higher specific activity and substrate affinity but a lower reaction rate and catalytic power compared to free enzymes in solution. With ATP regeneration, the ADK and ADK-RC hydrogels significantly increase the production of d-glucose-6-phosphate and obtain an efficient usage frequency. In conclusion, enzymes fused to spidroin might be an efficient strategy for maintaining activity and reducing leakage in 3D-bioprinted hydrogels under mild conditions.

The effect of a local mesh refinement on hydraulic modelling of river meanders

AbstractLarge‐scale river models are generally discretized by relatively large mesh cells resulting in bathymetry discretization errors and numerical effects. These hydraulic models are generally calibrated by altering the bed roughness to compensate for these errors and effects. Consequently, the calibrated roughness values are mesh‐dependent while generally local mesh refinements are executed after model calibration to study the effects of river interventions. This study shows both the errors caused by bathymetry discretization and numerical effects for locally refined meshes. First, schematised river meanders with a flat bed in the transverse flow direction are analysed to isolate the induced numerical effects by the mesh. Afterwards, a case study is considered to verify if similar mesh influences are found in natural river meanders. Curvilinear, triangular and hybrid (combination of curvilinear and triangular cells) meshes are used with different resolutions. The analysis shows that in the schematised river meanders lower depth‐averaged flow velocities and larger water depths are simulated with coarser meshes. In the case study, substantial differences in hydrodynamics between the meshes are obtained suggesting that the bathymetry discretization is more influential than the numerical effects. Finally, it was found that triangular meshes, and rivers with narrow meander bends, are most sensitive to mesh resolution. Especially in these cases, it is desirable to refine the mesh at the desired locations before model calibration.

Confinement of concrete with FRCM: Influence of bond aspects under cyclic axial loading

Bond aspects may significantly influence the effectiveness of Fiber Reinforced Cementitious Matrix (FRCM) jackets as confining system. Among them, this paper focuses on the following variables: the overlapping length, the equivalent thickness of the fibers (directly related with the fabric weight), fibers coating presence (pre-impregnated with epoxy resin or fluid cement paste), and lastly, the reinforcement configuration (continuous or discontinuous layers). For this scope, an experimental campaign was carried out on cylindric specimens, subject to cyclic axial loading, strengthened with two layers of carbon-based FRCM (CFRCM). Failure modes, axial stress–strain curve, strength and stiffness deterioration and, lastly, plastic strains were analyzed. Experimental results indicate a clear effect of the investigated parameters on the overall effectiveness of the confining jackets: the best results were obtained when carbon fibers are epoxy-coated, recalling that for making the application feasible, a relatively large mesh size and a low degree of coating impregnation should be used for the textiles. Lastly, new relationships to predict the main parameters that define the cyclic behavior of confined concrete are proposed and compared with those found in literature for other confining systems (based on fiber-reinforced polymer FRP and transverse steel).

Evaluation of light weight large pore mesh versus heavy weight small pore mesh in total extraperitoneal repair of inguinal hernia: A prospective randomized study

Evaluation of light weight large pore mesh versus heavy weight small pore mesh in total extraperitoneal repair of inguinal hernia: A prospective randomized study

Theoretical prediction on net boroxene as a promising Li/Na-ion batteries anode.

Novel two-dimensional (2D) electrode materials have become a new frontier for mining electrode materials for Li-ion batteries (LIBs) and Na-ion batteries (NIBs). Herein, based on first-principles calculations, we present a systematic study on the Li and Na storage behaviors in Calypso-predicted completely flat 2D boron oxide (l-B2O) with large mesh pores. We start our calculations from geometrical optimization, followed by a performance evaluation of Li/Na adsorption and migration processes. Finally, the specific capacity and average open-circuit voltage are evaluated. Our study reveals that l-B2O has good electrical conductivity before and after Li/Na adsorption and the Li/Na diffusion barrier height and average open-circuit voltage are both low, which is beneficial to the rate performance and full-cell operation voltage, respectively. Furthermore, it suffers a small lattice change (<1.7%), ensuring good cycling performance. In particular, we find that the Li and Na theoretical specific capacities of l-B2O can reach up to 1068.5 mA h g-1 and 712.3 mA h g-1, respectively, which are almost 2-3 times higher than graphite (372 mA h g-1). All the above outcomes indicate that 2D l-B2O is a promising anode material for LIBs and NIBs.

A Study on Structural Health Monitoring of a Large Space Antenna via Distributed Sensors and Deep Learning

Most modern Earth and Universe observation spacecraft are now equipped with large lightweight and flexible structures, such as antennas, telescopes, and extendable elements. The trend of hosting more complex and bigger appendages, essential for high-precision scientific applications, made orbiting satellites more susceptible to performance loss or degradation due to structural damages. In this scenario, Structural Health Monitoring strategies can be used to evaluate the health status of satellite substructures. However, in particular when analysing large appendages, traditional approaches may not be sufficient to identify local damages, as they will generally induce less observable changes in the system dynamics yet cause a relevant loss of payload data and information. This paper proposes a deep neural network to detect failures and investigate sensor sensitivity to damage classification for an orbiting satellite hosting a distributed network of accelerometers on a large mesh reflector antenna. The sensors-acquired time series are generated by using a fully coupled 3D simulator of the in-orbit attitude behaviour of a flexible satellite, whose appendages are modelled by using finite element techniques. The machine learning architecture is then trained and tested by using the sensors' responses gathered in a composite scenario, including not only the complete failure of a structural element (structural break) but also an intermediate level of structural damage. The proposed deep learning framework and sensors configuration proved to accurately detect failures in the most critical area or the structure while opening new investigation possibilities regarding geometrical properties and sensor distribution.