Deterioration Model Research Articles

MACHINE LEARNING MODEL FOR THE PREDICTION OF CONDITION OF MUSEUM OBJECTS

An accurate prediction of the future condition of museum objects is crucial for developing appropriate proactive maintenance and preservation strategies. Despite this, there are very few such damage models that can be used in practice. The main reasons, for this lack of deterioration models, include complexity of deterioration problem and lack of understanding of the degradation mechanisms affecting various materials and objects, and lack of reliable quantitative approaches. In the article, we discuss the machine learning model, which predicts the future condition of museum objects. For this purpose, the model uses the data of MuIS (Estonian Museum Information System). To predict deterioration, we experimented primarily with various tree-based machine learning algorithms, such as the decision tree, the random forest, and XGBoost. The best results were obtained using the decision forest algorithm, which was able to identify 92% of deteriorating museum objects with 50% accuracy. The machine learning model provides a way to model ageing processes of museum objects over the course of time and thus better plan the preservation work of museums.

Accounting for Traffic Dynamics in Pavement Maintenance Scheduling

Effective maintenance, rehabilitation, and reconstruction (MR&R) of road pavements is crucial for ensuring a safe and efficient transportation network. Existing research has proposed various models to aid decision-making in MR&R planning. However, these models often overlook the impact of traffic dynamics, such as shockwaves and queue spillovers caused by reduced capacity during maintenance activities. To bridge this gap, we present a novel methodology that incorporates traffic dynamics into the selection and sequencing of MR&R activities over a planning horizon. Our approach combines numerical evaluation of traffic flow theory using the link transmission model (LTM) with a deterioration model, considering travel time cost, fuel cost, and agency cost, to assess the optimal sequence of MR&R activities. To solve this multi-objective problem, we employ a genetic algorithm (GA) to minimize the objective function. Through a numerical example, we demonstrate the methodology’s effectiveness and sensitivity to pavement deterioration. The results clearly indicate the effectiveness of using the proposed methodology over the widely used Bureau of Public Roads (BPR)-function-based methods for pavement maintenance scheduling problems.

Extrusion 3D printing circular and horseshoe tunnel physical models: A comparative study of deformation and brittle failure

The instability of high-stress hard rock tunnels mainly presented with the deformation and brittle failure, the tunnel brittle failure’s location and range are dissimilar under different stress and shape conditions. In this study, similar 3D printing materials are developed according to the brittleness index of the hard rock in an underground cavern. The physical models of circular and horseshoe tunnel with the equal area are printed, and overloading tests are carried out. The test results reveal that the horseshoe tunnel’s peak strength and residual strength are decreased by 17.2% and 6.6% compared with that of the circular tunnel, the circular tunnel’s vertical displacement is greater than the horseshoe tunnel’s, and the depth and range of brittle failure in the circular tunnel are bigger than the horseshoe tunnel’s. The circular tunnel brittle failure is mainly in the middle of both sides’ walls, while the horseshoe tunnel brittle failure is mainly in the bottom of both sides’ walls. The location and range of the tunnels’ brittle failure can be well simulated by using the rock mass deterioration model (RDM) combined with the rock fracture degree (RFD) index, and the numerical simulation results are consistent with the physical simulation experiment results. According to the results of laboratory physical model experiment and numerical simulation, the brittle failure evolution model of hard rock tunnel is proposed, which can provide a reference for the excavation and support design of hard rock tunnel under high stress.

Investigation of the shared gene signatures and molecular mechanisms between obstructive sleep apnea syndrome and asthma

BackgroundObstructive sleep apnea syndrome (OSAS) is highly related with asthma from the epidemiology to pathogenesis, while the underlying mechanism is still unclear. Herein, we aimed to reveal the shared gene signatures and molecular mechanisms underlying the coexistence of OSAS and asthma and verified relating pathway in mouse models. We downloaded GSE75097 of OSAS and GSE165934 of asthma from GEO database and performed differential expression analysis and functional enrichment analysis to screen differentially expressed genes (DEGs) and potential pathogenic pathway. PPI network was constructed with the STRING database. Hub genes were identified with cytoHubba and immune infiltration analysis was performed with cibersort for further verification. Potential drugs were screened with Comparative Toxicogenomics Database and miRNA-gene network was constructed. Besides, to test the pulmonary function and inflammatory cytokine, mouse models with OSAS and asthma were constructed, followed by validating the involvement of NOD1/NOD2-RIPK2-NF-κB-MCPIP-1 pathway in associated diseases. ResultsIn total, 104 DEGs were identified, in which PLAUR, RIPK2, PELI1, ZC3H12A, and TNFAIP8 are the hub genes, while NOD-like receptor signaling pathway and apoptosis signaling pathway were the potential influential pathways. Increased γδT cells and neutrophils were detected in asthma patients through immune infiltration analysis. Significant difference was detected among genders in OSAS, and acetaminophen is a potential drug in the comorbidity by screening the drugs in the Comparative Toxicogenomics Database. Mice with OSAS and asthma presented with worse pulmonary function and higher levels of inflammatory cytokines. The relative proteins, including NOD1, NOD2, RIPK2, NF-κB, and MCPIP-1, were up-regulated in mice with the OSAS and asthma. ConclusionsThis research firstly elucidates NOD1/NOD2-RIPK2-NF-κB-MCPIP-1 pathway as the shared pathway in the development of OSAS and asthma through bioinformatics and experimental methods. There is an interactive deterioration model between OSAS and asthma. This study may provide some potential biomarkers in the future research of the underlying pathogenesis and treatment of comorbidity of OSAS and asthma.

Gene Duplication, Shifting Selection, and Dosage Balance of Silicon Transporter Proteins in Marine and Freshwater Diatoms.

Numerous factors shape the evolution of protein-coding genes, including shifts in the strength or type of selection following gene duplications or changes in the environment. Diatoms and other silicifying organisms use a family of silicon transporters (SITs) to import dissolved silicon from the environment. Freshwaters contain higher silicon levels than oceans, and marine diatoms have more efficient uptake kinetics and less silicon in their cell walls, making them better competitors for a scarce resource. We compiled SITs from 37 diatom genomes to characterize shifts in selection following gene duplications and marine-freshwater transitions. A deep gene duplication, which coincided with a whole-genome duplication, gave rise to two gene lineages. One of them (SIT1-2) is present in multiple copies in most species and is known to actively import silicon. These SITs have evolved under strong purifying selection that was relaxed in freshwater taxa. Episodic diversifying selection was detected but not associated with gene duplications or habitat shifts. In contrast, genes in the second SIT lineage (SIT3) were present in just half the species, the result of multiple losses. Despite conservation of SIT3 in some lineages for the past 90-100 million years, repeated losses, relaxed selection, and low expression highlighted the dispensability of SIT3, consistent with a model of deterioration and eventual loss due to relaxed selection on SIT3 expression. The extensive but relatively balanced history of duplications and losses, together with paralog-specific expression patterns, suggest diatoms continuously balance gene dosage and expression dynamics to optimize silicon transport across major environmental gradients.

A surrogate deterioration model of debris retention systems towards cost-effective maintenance strategies and increased protection efficacy

Protection systems are usually implemented in mountains aiming to resist natural dangerous phenomena. As any other critical infrastructure, protection systems should always withstand and operate efficiently as they guarantee the safety of people and protect socio-economic assets. However, the efficacy of these systems decreases with the increase of the deterioration level of the interdependent components, which constitute them. To provide desirable operation over their lifetime, the management of protection systems is of paramount importance. A major key issue in such critical infrastructure management is to optimize the cost effectiveness of maintenance actions while maintaining a sufficient protection efficacy. This study proposes a decision-aiding model to assess different maintenance strategies applied to a protection system against debris flows. The model is constructed using physics-based stochastic Petri nets. It incorporates (1) a stochastic deterioration model, which is a surrogate model of a physics-based model developed for building deterioration trajectories of the system and (2) maintenance model that permits assessing the cost and efficiency of maintenance strategies. This study addresses the case of a debris retention system, in which the progressive filling of its basin by debris materials is modeled. This is followed by assessing several maintenance strategies concerning the cleaning of the basin. A simple sensitivity analysis is also carried out in order to check the effect of the uncertainty that invades the model’s inputs on maintenance decisions. A numerical analysis is performed using real data of the retention system located in the Claret torrent in France and subjected to debris flows over a period of 50 years.

Emulating long-term weather-driven transportation earthworks deterioration models to support asset management

The deterioration of transport infrastructure earthworks is a global problem, with negative impacts for infrastructure resilience, becoming of increasing significance as existing infrastructure ages. Key mechanisms which affect this deterioration include seasonal pore pressure cycling driven by changing weather and climate, and the long-term dissipation of construction induced excess pore pressures. These complex processes lead to significant uncertainty in rates of deterioration and the current state of existing earthworks assets. The objective in this work was to establish a framework to emulate deterministic numerical models of slope deterioration over time using statistical (Gaussian process) emulation. A validated, physically based, deterministic modeling capability has been developed that can replicate the hydro-mechanically coupled behavior of cut and embankment slopes and their deterioration as driven by weather and climate. In parallel, a statistical (Gaussian process) emulator model was developed, and then trained with data from a deterministic modeling parametric study, using a formal experimental design approach, making use of Latin hypercube sampling. Exemplar forecasting outputs are presented to demonstrate application of the approach for use in decision-making. This information can be used in the design of new earthworks and the management of existing earthwork portfolios.

Interval valued inventory model for deterioration, carbon emissions and selling price dependent demand considering buy now and pay later facility

Uncertainty refers to a lack of precise knowledge or information about a particular event, situation, or outcome. It is an inherent characteristic of many real-world phenomena and is often associated with the presence of risk or ambiguity. Uncertainty can arise due to various factors, such as incomplete information, unpredictability, complexity, or variability of a system or process. In many cases, uncertainty can lead to difficulties in decision-making and pose challenges in planning, forecasting, and managing risks. There are different types of uncertainty, including epistemic uncertainty, which arises from the inherent randomness or variability of a system or process. This study encompasses the inclusion of all inventory parameters as uncertainty parameters, which are expressed in the form of intervals. Furthermore, demand for the product is taken into account in interval form. The conversion of the differential equation into an interval differential equation is carried out in order to account for the variability in demand within a certain interval. The utilisation of the centre-radius technique leads to the derivation of the related optimisation problem under a ‘buy now, pay later’ (BNPL) payment scheme. In order to demonstrate the concept, a numerical case is selected and solved with the MATHEMATICA software and interval order relations. In the end, a comprehensive sensitivity analysis has been conducted to derive insightful conclusions pertaining to this study.

Study on mechanical characteristics and energy accumulation and release law of coal samples with different saturation and creep damage

ABSTRACT Under the long-term influence of overburden load and water infiltration, coal undergoes creep damage, and the disturbance caused by mining activities can lead to sudden instability, triggering geological disasters such as mine flooding. Therefore, this study prepared four types of coal samples with different saturations under creep damage conditions and conventional coal samples. A comparative study was conducted using uniaxial compression tests to examine the deterioration characteristics of physical and mechanical parameters, failure modes, and energy evolution patterns in these two types of coal samples. Additionally, a microscopic deterioration model of coal samples under the combined influence of water and creep damage was constructed to elucidate the mechanism of creep damage on the deterioration of mechanical properties in water-containing coal samples. The research findings indicate that coal samples affected by creep damage and conventional coal samples exhibit significant consistency in mechanical parameters and energy evolution patterns. Specifically, an increase in saturation is positively correlated with peak stress, elastic modulus, and dissipated energy. Conversely, peak strain, total input energy, and elastic strain energy are negatively correlated with rising saturation levels. Under the same saturation conditions, the change in mechanical parameters and energy characteristics is more pronounced in creep-damaged coal samples. Furthermore, the stress-strain curves of both coal sample types exhibit prolonged compaction stages, shortened elastic stages, and more significant yield stages. Under equivalent saturation levels, the stress-strain trends in creep-damaged coal samples show more substantial variations. Upon loading and failure, the conventional coal sample transitions from single inclined plane shear failure to tension-shear mixed failure as the saturation increases. Conversely, the creep-damaged coal sample shifts from “X”-type conjugate shear failure and tension-shear mixed failure to tension failure, signifying a tendency toward more complex failure modes. In cases where the coal sample has a water saturation of 41%, the deterioration of its mechanical parameters is primarily attributed to creep damage. However, when the water saturation reaches 41–100%, water plays a dominant role in the deterioration of the coal sample’s mechanical parameters. After experiencing creep damage, the internal micro-cracks of the coal sample are extensively developed, which is also the primary factor contributing to the deterioration of the coal sample’s mechanical properties and an increased proportion of dissipated energy.

Identifying the Factors Impacting Bridge Deterioration in the Gulf Cooperation Council

The deterioration module (DM) is one of the four major modules necessary for any bridge management system (BMS). Environmental conditions, structural systems, bridge configuration, geographic location, and traffic data are some of the major factors that affect the development of deterioration modules. This emphasizes the need for the development of deterioration models that reflect the local conditions. In this article, some of the most important factors that could help in developing deterioration models in the Gulf Cooperation Council (GCC) were identified. The research was conducted in three phases; in the first phase, an extensive literature search was conducted to identify factors adopted in different deterioration models, and in phase two, the most relevant factors to the GCC environment were selected and these factors were further reduced based on input from local bridge experts. The result from the second phase is a list of factors identified by the experts. The identified list was utilized in phase three, which was focused on conducting a survey targeting bridge engineers to help identify the final selection and rank the factors according to their importance level. The results indicate that steel reinforcement protection, design load, chloride attack, type of defect, and age are the most important factors impacting bridge deterioration in the GCC. In addition, the time of rehabilitation; average daily truck traffic, ADTT; and average daily traffic, ADT, are the second most important factors. Factors with medium importance level are deck protection, services under the bridge, and inspection gap. The least important set of factors include temperature and wind load.

Study on the freeze–thaw effect on concrete arch dam using an improved response surface method

The damming materials will be deteriorated during the long-term service of concrete arch dam by weathering, seepage dissolution, freeze–thaw and other factors which will put dams at potential risk. However, there are few researches on the reliability assessment of arch dams considering the effect of material deterioration. In this paper, a prediction model of concrete mechanical properties under freeze–thaw cycles is established using regression analysis. Considering various uncertain factors, a time-varying structural reliability analysis model is established using finite element equivalent stress method and an optimized response surface method with improved sampling strategy and convergence criterion. A case study is later carried out. The results show that, at the early stage of freeze–thaw, the structural failure probability will increase steadily in a small range. However, as the tensile strength of concrete continues to decrease under long-time freeze–thaw action, the reliability of the arch dam structure will suddenly fall off a cliff. The proposed deterioration model and reliability analysis probability model are reasonable and practical and could be serve as a technical support for similar engineering projects.

Poster] Fusing Mode S and Earth observation data for ML-driven engine performance deterioration modeling

In the following, an approach currently being researched, is presented. The objective of this approachis to more precisely model engine performance and condition deterioration with the help of Mode S andEarth observation data. The fusion of Mode S with Earth observation data is described with a focus onthe contributions of Mode S data. Also, the Earth observation data contained in Mode S data is pointedto. Research in progress is presented and user needs are highlighted.From the preliminary findings, one can conclude that the usage of Mode S data is essential to engineperformance and condition deterioration modeling in situations in which no aircraft position data can beobtained. ADS-B data provides the means to achieve a mapping of the aircraft location to outputs fromaerosol models, such as the Copernicus Atmospheric Modelling Service’s global reanalysis, and otherambient condition data from in-situ sources or satellites.Aero engine condition and hence, engine performance deterioration is a function of the severity of theoperational environment. Exposure of aero engines to contaminants leads to fouling, erosion, and corrosion.Additional maintenance, repair, and overhaul costs, and excess emissions result from exposingaircraft engines to harsh operating environments. ADS-B and Enhanced Surveillance (EHS) data bear theopportunity to better determine the exposure to and the impact of contamination on aero engine conditionand performance. Subsequent data analysis and generation of decision-critical information willideally decrease operational costs and the environmental footprint.

A simple method to determine soil–water retention curves of compacted active clays

Determining the Soil Water Retention Curve (SWRC) of an active clay constitutes a challenge due to the significant, and sometimes irreversible, volume changes that occur during wetting and drying cycles. A novel yet simple method of experimentally determining the evolution of the SWRCs with moisture cycles is presented based on the results of a rigorous experimental study. Its purpose is to support the modelling of water flux in earthworks exposed to weather cycles that cause deterioration. Firstly, three SWRC branches (the primary drying, a scanning drying, and a scanning wetting branch) are measured and used to fit the proposed generic SWRC semi-empirical model in terms of water ratio, that, in the adsorptive region, is independent of the compaction conditions (void ratio and water content at compaction). Soil Shrink-Swell Curves (SSSCs) in terms of water ratio versus void ratio, that are easy to measure, can be determined for different compaction conditions over several drying and wetting cycles. Finally, the SSSCs are combined with the generic SWRC model to determine the evolution of the SWRCs with moisture cycles for the compaction conditions of interest. This method is demonstrated for two London clays of high and very high plasticity. Samples were compacted in five different conditions, varying in gravimetric water content and dry density, and were cycled six times between 1 and 80 MPa of total suction. The generic SWRC model was fitted to the experimental data. The model was able to estimate the SWRC in terms of degree of saturation over the six drying-wetting cycles without propagation of error. The significance of the research is that SWRC can now be determined over a range of wetting and drying cycles quickly and simply and enable modelling of deterioration of clays fills due to the action of weather to be accurate.

Calibration of Effective Structural Number and Tensile Strain Models Using Traffic Speed Deflectometer (TSD) Data for Enhanced Project-Level Assessment on Flexible and Composite Pavements

Pavement deterioration models provide the basis for predicting future changes in network conditions, estimating future funding needs, and determining the effectiveness and timing of maintenance and rehabilitation activities. Determining the accurate structural condition of pavements helps identify effective maintenance strategies which enhance the sustainability and service life of pavements. This study aimed to use the Traffic Speed Deflectometer (TSD) and Fast Falling Weight Deflectometer (FFWD) for project-level evaluation of pavements and use pavement properties to calibrate current models that help to predict the structural condition of pavements. Model parameters were calibrated to determine the effective structural number and tensile strains at the bottom of asphalt concrete for asphalt and composite pavements from TSD deflections. Tensile strains from the KENLAYER highlighted varied behaviors for composite pavements. A significant improvement in the calibration was observed for asphalt concrete pavements. While the TSD has higher daily operational costs than FWD, its per-mile cost is significantly lower, making it a viable choice for extensive coverage, even though the quantitative results might differ between the two devices.

Exploring strength deterioration mechanism of soil-rock mixture based on pore structure characteristics under freeze–thaw cycles

The strength deterioration of soil-rock mixtures (SRM) subjected to freeze–thaw (F–T) cycles leads to instability and failure of upper engineering structures in cold regions. However, the mutual feedback response mechanism pertaining to the changes of pore and strength in SRM under F–T cycles are rarely addressed. Nuclear magnetic resonance and triaxial tests were carried out to study the pore structure characteristics and strength response patterns of samples. A correlation model of SRM porosity and strength deterioration was first proposed under F–T cycles, and the model rationality was verified by test data. The results demonstrated that the pore connectivity and porosity increased throughout the F–T process, with the T2 spectral distribution curves exhibiting three peaks. Among these peaks, the main peaks underwent slight changes, while the secondary and micro peaks presented significant changes. Before 3 F–T cycles, the pore distribution evolved to small pores uniformly, followed with the large pores increasing and the micropores disappearing. With increasing of F–T times, the strength and cohesion of SRM experienced a drastic decline, while the internal friction angle demonstrated a slight decrease accompanied by fluctuations. Based on the analysis of test results, a correlation model regarding the porosity and strength deterioration was proposed through the relationship between the micro-structure evolution and the macro–mechanical response during F–T cycles. Furthermore, intrinsic mechanism of SRM strength deterioration under F–T cycles was revealed by considering the pore structure characteristics. The results can provide theoretical insights for the analysis of F–T disaster mechanism and prevention of SRM in cold regions.

Structural reliability assessment of steel bridges using OSIM visual inspection data and Bayesian updating

Structural reliability theories are used in the calibration of load and resistance factor design (LRFD) in the Canadian Highway Bridge Design Code (CHBDC). The LRFD approach contains certain assumptions about uncertainties in the load and capacity estimation that prevent it from fully exploiting the information gathered during visual inspections. This paper presents a reliability-based framework for analyzing the visual inspection data obtained according to the Ontario structure inspection manual (OSIM). Existing deterioration models are adapted. The Bayesian interference is utilized to estimate the updated structural properties according to the prior information from the bridge maintenance and deterioration models and the new information collected from visual inspections. The criteria set by the CHBDC are used to analyze components and systems reliability. The value of the proposed framework for bridge evaluation and optimizing maintenance is demonstrated through the full implementation of a case-study bridge in the Canadian Province of NB.

Road Pavement Condition Index Deterioration Model for Network-Level Analysis of National Road Network Based on Pavement Condition Scanning Data

Surveying the condition of the pavement is one of the most important processes in managing the road network. The information collected during these surveys allows for the calculation of the Pavement Condition Index, which is a derivative cumulative qualitative indicator that evaluates various pavement characteristics and defects. Deterioration modelling of these measured indicators and calculated indices is a critical element and its most accurate prediction brings the process of pavement management closer to a higher quality process by more efficiently allocating funds and repair work. Many different models – both extremely complex and simple – are used in the world to simulate the condition of individual pavement indicators. However, these models are developed based on the data of a certain country or region and are not suitable in another country due to different requirements for pavement structures and other reasons. In Lithuania, measurements of the quality indicators of road surfaces with new generation survey equipment have been carried out recently but the information stored in the databases about road sections is minimal, and it becomes difficult to adapt the models applied abroad due to the missing information. The aim of this study is to create pavement condition index prediction models by evaluating such quantitative and qualitative indicators as traffic loads, road surface unevenness, type of repair, pavement age, climatic zones, and pavement construction classes.

Predictive Modeling for Highway Pavement Rutting: A Comparative Analysis of Auto-Machine Learning and Structural Equation Models

Highway pavements deteriorate over time as successive wheel loads cause rutting, cracking, texture loss, and so forth. Design standards and pavement performance models account for some of the known contributory factors, such as levels of traffic and vehicle composition. However, such models are limited in their predictive power, and highway authorities must conduct regular pavement condition surveys rather than relying on the standard deterioration models alone. The ways in which multiple factors affect pavement deterioration, including rutting, are complex and are believed to include feedback loops where rutting then influences driving position, exacerbating the rutting levels. Standard regression models are not well suited to representing such complex causal mechanisms. This paper compares two alternative modeling approaches, structural equation models and auto-machine learning, and evaluates the predictive ability and practicalities of each. The findings indicate that auto-machine learning (AutoML) may be superior in its predictive ability. However, the “black box” nature of AutoML results makes them potentially less useful to practitioners. A process of using machine learning to help inform a structural equation model is proposed.

Dynamic characteristics and deterioration mechanism of coal under distinct initial gas pressure

Additional to dynamic and static superimposed loads, gas effects frequently affect coal seams throughout the coal mining process. It is crucial to comprehend coal samples’ mechanical properties and deterioration mechanisms under distinct initial gas pressure conditions. Consequently, the dynamic compression experiment of coal samples was conducted utilizing a self-developed observable combined dynamic and static loading test system of gas-bearing coal (GAS). The mechanical characteristics including failure mode in coal samples under distinct initial gas pressures were studied. Furthermore, the mechanism of gas deteriorated mechanical parameters and aggravated the propagation of cracks when combined with dynamic and static loads was revealed. The conclusions are drawn as follows: The GAS can go through four stages of deformation: elastic stage, elastoplastic stage, plastic stage, and failure stage. Furthermore, the dynamic strength and failure strain deteriorated with increasing gas pressure. Based on computed tomography (CT) technology, it is found that the splitting-spallation composite cracks of impacted samples become more noticeable with rising initial gas pressure, and finally, the two kinds of cracks create a complex reticular crack system. Meanwhile, the crack volume and fractal dimension increase with rising gas pressure, indicating that gas can aggravate the coal’s failure degree. Under combined dynamic and static loads, the deterioration model of mechanical parameters of GAS is obtained, that is, with rising initial gas pressure, the dynamic strength of coal samples reduces and the failure strain rises synchronously. The main reason for the aggravation of compound failure in impacted samples is that the stress intensity factor rises with the rise of gas pressure. These conclusions enrich the basic theories such as the inducing mechanism of dynamic disasters caused by coal-rock-gas compounds and can offer a theoretical foundation for the technology employed in monitoring, early warning, and prevention of dynamic disasters in compounds.

Scrutinizing the Performances of Hybrid ANN Models for Forecasting Condition of Bridges

AbstractBridges all over the world are vulnerable to severe deterioration agents meanwhile their maintenance budgets are being tightened. This state of affairs necessitates the establishment of an autonomous deterioration model to predict the performance condition of bridges. This research paper explores the implementation of a set of intelligent data driven models to analyze the future condition ratings of bridge decks. These models comprise support vector machines, Gaussian process regression, regression tree, back propagation artificial neural network, Elman recurrent neural network, cascade forward neural network, long short‐term memory network and deep convolutional neural network. The performance comparison is carried out using five evaluation metrics of root mean squared percentage error, mean absolute percentage error, root mean squared error mean absolute error and relative absolute error. The models herein are developed and validated using the structural deterioration information retrieved from the National Bridge Inventory (NBI). It can be argued that the developed deterioration model could be implemented by departments of transportation to analyze and monitor the performance condition behavior of bridge components over their useful lifetime.