Inspection Costs Research Articles

Multi-scale ResNet for real-time underwater object detection

An automatic underwater object recognition system is essential to reduce the costs of underwater inspection. In this study, we propose a novel convolutional neural network architecture that is trained on underwater video frames. This method is based on a modified residual neural network (ResNet) for underwater object detection. Multi-scale ResNet (M-ResNet), the modified method, improves efficiency by utilizing multi-scale operations for the accurate detection of objects of various sizes, especially small objects. The experimental results show that the proposed method yields an accuracy of 96.5% (mAP) in recognition performance. As a consequence, we propose a novel system for automatic object detection as an application for marine environments.

Automatic Crack Segmentation for UAV-Assisted Bridge Inspection

Bridges are a critical piece of infrastructure in the network of road and rail transport system. Many of the bridges in Norway (in Europe) are at the end of their lifespan, therefore regular inspection and maintenance are critical to ensure the safety of their operations. However, the traditional inspection procedures and resources required are so time consuming and costly that there exists a significant maintenance backlog. The central thrust of this paper is to demonstrate the significant benefits of adapting a Unmanned Aerial Vehicle (UAV)-assisted inspection to reduce the time and costs of bridge inspection and established the research needs associated with the processing of the (big) data produced by such autonomous technologies. In this regard, a methodology is proposed for analysing the bridge damage that comprises three key stages, (i) data collection and model training, where one performs experiments and trials to perfect drone flights for inspection using case study bridges to inform and provide necessary (big) data for the second key stage, (ii) 3D construction, where one built 3D models that offer a permanent record of element geometry for each bridge asset, which could be used for navigation and control purposes, (iii) damage identification and analysis, where deep learning-based data analytics and modelling are applied for processing and analysing UAV image data and to perform bridge damage performance assessment. The proposed methodology is exemplified via UAV-assisted inspection of Skodsberg bridge, a 140 m prestressed concrete bridge, in the Viken county in eastern Norway.

Optimal designing of two-level skip-lot sampling reinspection plan

Skip-lot sampling plan is often applied in industries for reducing the cost and effort of the inspection of the product having excellent quality history. Consequence of skip-lot sampling plans is to reduce the cost of inspection so which are more attractive in economical aspect. In this paper, we develop a sampling plan by incorporating the idea of resampling in two-level skip lot sampling plan and the new plan is designated as SkSP-2L.1-R. This paper presents the Markov chain formulation of the proposed plan along with the derivation of performance measures of the plan. We also provide the designing methodology to determine the optimal parameters of the SkSP-2L.1-R plan so as to minimize the average sample number by using two points on the operating characteristic curve approach. By contemplating various combinations of producer and consumer quality levels along with respective risks, a table is constructed to determine the optimal parameters. An industrial application of the proposed SkSP-2L.1-R plan is discussed. The SkSP-2L.1-R with single sampling plan as a reference plan is compared with the conventional single sampling plan, SkSP-2 plan and SkSP-2-R plan and proved that the proposed SkSP-2L.1-R plan outperforms these plans.

Path Planning and Setup Orientation for Automated Dimensional Inspection Using Coordinate Measuring Machines

Inspection planning is considered an essential practice in the manufacturing industries because it ensures enhanced product quality and productivity. A reasonable inspection plan, which can reduce inspection costs and achieve high customer satisfaction, is therefore very important in the production industry. Considerations such as preparations for part inspection, measuring machines, and their setups as well as the measurement path are described in an inspection plan which is subsequently translated into part inspection machine language. Therefore, the measurement of any component using a coordinate measuring machine (CMM) is the final step preceded by several other procedures, such as the preparation of the part setup and the generation of the probe path. Effective measurement of components using CMM can only be done if the preceding steps are properly optimized to automate the whole inspection process. This paper has proposed a method based on artificial intelligence techniques, namely, artificial neural network (ANN) and genetic algorithm (GA), for fine-tuning output from the different steps to achieve an efficient inspection plan. A case study to check and validate the suggested approach for producing effective inspection plans for CMMs is presented. A decrease of nearly 50% was observed in the travel path of the probe, whereas the CMM measurement time was reduced by almost 25% during the actual component measurement. The proposed method yielded the optimum part setup and the most appropriate measuring sequence for the part considered.

Optimal inspection and mission abort policies for systems subject to degradation

Safety-critical systems are commonly required to perform missions in various engineering fields. Failures of safety-critical systems may result in irretrievable economic losses and significant damages. To enhance the system survivability, mission abort is usually conducted if the failure risk becomes too high. This paper investigates the joint optimization of inspection and condition based mission abort policies for systems subject to continuous degradation. Dynamic mission abort decisions are considered based on the degradation level together with the time in mission. The problem is formulated within the framework of Markov decision process to minimize the expected costs of inspection, mission failure and system failure. In addition to deriving some structural properties, we also numerically evaluate several heuristic policies where mission reliability and system survivability are derived. Numerical studies are presented to validate the obtained results.

Evaluation of Corrosion Resistance of Steel Materials By Hyperspectral Analysis of Corrosion Products

Direct visual inspection at short range and hammering test every five years are obligatory for inspection and evaluation of bridges in Japan. However, simple and quantitative inspection techniques are required due to issues such as a shortage of bridge inspectors and a lack of inspection cost. We focused on the spectrum analysis by a hyperspectral camera as a new tool to evaluate corrosion resistance. The purpose of this study is to investigate the feasibility of evaluating the corrosion resistance of steel materials by hyperspectral analysis of corrosion products.α-FeOOH, β-FeOOH, γ-FeOOH and Fe3O4 were used as the samples of standard iron corrosion products. These corrosion products were set on the sample holder, and the spectra were taken by a hyperspectral camera using halogen lamps as a source of irradiation light. The average spectrum obtained at almost the center of the sample was analyzed.The reflection spectra were observed at 595 nm and 770 nm for α-FeOOH, 745 nm for β-FeOOH, and 790 nm for γ-FeOOH, respectively, and Fe3O4 showed a low reflection spectrum. This means that different corrosion products can be identified from the reflection spectrum. In addition, the spectrum analysis was conducted for the corrosion products formed on the sample exposed in coastal area for six months. The peaks in the spectrum were correspondent with them observed in the spectra of the standard iron corrosion products. The spectrum analysis by a hyperspectral camera can be powerful tool to evaluate the corrosion performance of steel materials.

AQUADA: Automated quantification of damages in composite wind turbine blades for LCOE reduction

AbstractReliability and cost are two important driving factors in the development of wind energy. Automation and digitalization of operation and maintenance (O&M) procedures help to increase turbine reliability and reduce the levelized cost of energy (LCOE). Here, we demonstrate a novel method, coined as AQUADA, which may change the current labor‐intensive and operation‐interfering blade inspection by using thermography and computer vision. We experimentally show that structural damages below the surfaces can be detected and quantified remotely when wind turbine blades are subject to fatigue loads. The data acquisition and analysis are automatically done in one single step, which may shift the current inspection paradigm through more automated O&M procedures. The cost analysis shows that the AQUADA method has a potential to at least half the total inspection cost and reduce the LCOE by 1%–2% when applied to a baseline land‐based wind farm consisting of twenty 2.45‐MW turbines. All data and source codes are published for researchers to reproduce our results and facilitate further development of AQUADA towards more mature industrial applications.

Improving the efficiency of liquid fuel boiler plants

The issues of saving fuel and energy resources, as well as improving the equipment efficiency, are of great importancei n all sectors and especially in the energy sector, the main fuelconsuming industry. Improving of the boiler plants efficiency and is currently an urgent issue. Organizational and technical measures to improve technological processes are being developed at each station. The article discusses several ways to improve the boiler plants efficiency using liquid fuel. Industrial tests of the diesel nozzle cleaner in the boiler plant were carried out, which led to the following results: - received fuel consumption savings of 8.67%. At the same time, the amount of heat transferred to the LTC-4 network increased by 5.86%. - the specific indicator of fuel consumption (the ratio of diesel fuel consumption to the amount of heat transferred, kg / Gcal) decreased by 12.57%, and also at the same time as the efficiency of the boilers, the resource indicators of the boiler nozzles will increase, the time and the costs for the nozzles technical inspection will decrease.

Prognosis and Multiobjective Optimization of the Sampling Plan for Cylindricity Evaluation

The actualization of the befitting sampling strategy and the application of an appropriate evaluation algorithm have been elementary issues in the coordinate metrology. The decisions regarding their choice for a given geometrical feature customarily rely upon the user’s instinct or experience. As a consequence, the measurement results have to be accommodated between the accuracy and the inspection time. Certainly, a reliable and efficient sampling plan is imperative to accomplish a dependable inspection in minimal time, effort, and cost. This paper deals with the determination of an optimal sampling plan that minimizes the inspection cost, while still promising a measurement quality. A cylindrical-shaped component has been utilized in this work to achieve the desired objective. The inspection quality of the cylinder using a coordinate measuring machine (CMM) can be enhanced by controlling the three main parameters, which are used as input variables in the data file, namely, point distribution schemes, total number of points, and form evaluation algorithms. These factors affect the inspection output, in terms of cylindricity and measurement time, which are considered as target variables. The dataset, which comprises input and intended parameters, has been acquired through experimentation on the CMM machine. This work has utilized state-of-the-art machine learning algorithms to establish predictive models, which can predict the inspection output. The different algorithms have been examined and compared to seek for the most relevant machine learning regression method. The best performance has been observed using the support vector regression for cylindricity, with a mean absolute error of 0.000508 mm and a root-mean-squared error of 0.000885 mm. Likewise, the best prediction performance for measuring time has been demonstrated by the decision trees. Finally, the optimal parameters are estimated by employing the grey relational analysis (GRA) and the fuzzy technique for order performance by similarity to ideal solution (FTOPSIS). It has been approved that the values obtained from GRA are comparable with those of the FTOPSIS. Moreover, the quality of the optimal results is bettered by incorporating the measurement uncertainty in the outcome.

Studies on application of image processing in various fields: An overview

Quality inspection and evaluation is a vital role in producing quality products in a shorter span. Computer-aided estimation of quality products in different fields of engineering is a constructive advancement happening. Image processing is one of the most promising areas, which is applied for quality inspection of products where the challenging task lies in recognition of the object and feature extraction. This paper made attempt to provide an overview of the application of image processing and their methodology with few algorithms that have been used in different fields of engineering which falls under three important phases: acquisition of images, the region of interest and identification of defects. This paper concentrates on applications like construction, fluid flow, thermal imaging, medical industries, fruit and vegetable industry, rock carvings, and other applications. Applying image processing different fields leads to quality products by a qualitative process which leads to a reduction in inspection time and cost involved.

Challenges for On-Site Automated Ultrasonic Phased Array Inspection of Composite Aircraft

Aircraft maintenance represents 10-20% of the overall operating cost, and heavy C-check and D-check maintenance demands NDT inspection of 100% skin area of composite material fuselages. Delamination and low velocity Barely Visible Impact Damages (BVID) are typical in-service damages found in skin causing small to large sub-surface damages with little or no surface indication. These damages are difficult to detect during manual visual inspection. Conventional manual ultrasonic and advanced Phased Array (PA) scanning of skin followed by data interpretation and analysis for damage sizing is time consuming and cost-inefficient for on-site application; hence a potential task to be automated or robotized. Automated PA inspection by magnetic-adhesion based manipulators, crawlers and scanners have led to rapid inspection rates and lowering the cost of inspection in oil and gas sectors. The composite skin surfaces are painted, smooth and non-magnetic, which invalidates the use of current magnetic adhesion based crawlers for inspection. Despite some previous efforts, the development of automated PA inspection of skin surfaces using a mobile robot is still an unsolved problem. This work is a part of ongoing EU-H2020 project ‘CompInnova’ which aims to develop an integrated NDT approach using combined PA and Infrared Thermography inspection of the fuselage-skin through separate inspection modules mounted on a mobile robot, that will lead to cost-effective combination for on-site automated inspection. A novel vortex based wheeled mobile robot was developed for traversing over the fuselage using adhesion forces generated by means of Electric Ducted Fan (EDF) motors [4]. This robot was designed to carry a PA NDT module [4], but with restrictions on payload (1 Kg.) and minimum water couplant usage requirements. Thus this work presents the development challenges of the PA module for automated PA inspection and to meet the requirements for its integration with robot. PA inspection results obtained by robotic scanning of laminates with impact damages, are evaluated for assessing the functionality and performance of the PA module.

A new method for determining the denaturation temperature of collagen

The denaturation temperature of collagen has been determined using several methods, such as circular dichroism, fourier transform infrared spectroscopy, and differential scanning calorimetry, etc. Such methods need specific equipment or mass samples (more than 75 mg samples), which means higher inspection costs. In this study, Sirius red was employed to determine the Tds of collagen from calf tendon, silver carp skin, frog and salmon skins (38.2 °C, 32.6 °C, 33.8 °C, and 15.6 °C, respectively) to explore a new method that does not require special equipment and only needs 2–3 mg sample for one measurement. This method was suitable for the determination of the denaturation temperature of collagen from terrestrial, aquatic and amphibian animals. Analysis of variance and t-test revealed that no significant difference was found between Sirius Red and viscosity methods. However, the Sirius Red method needs simpler equipment and less sample than viscosity and other methods. So it could be used as a convenient approach to determine the denaturation temperature of collagen instead of the viscosity method.

Analysis of screening decisions in inventory models with imperfect quality items

We consider an Economic Order Quantity (EOQ) model with imperfect quality items. All the items undergo a quality screening process for which both the cost and the defect detection rate depend on the time devoted to this operation. Contrary to most previous research in the field, the speed of screening is taken as a decision variable in the presented model jointly with the order quantity. Additionally, we introduce various functional forms for the screening cost and defect detection functions. In particular, nonlinear forms lead to nonconvexities in the total cost function consisting of multiple cost components, e.g. inspection cost, penalty costs, etc. We solve the model analytically for a selected set of assumptions and provide numerical examples and sensitivity analysis. The results provide interesting insights. While lower screening costs motivate longer screening times, the effectiveness of this operation is only obtained in combination with the reliability of the defect detection method. It is also observed that reducing return rates and improving customer satisfaction can be achieved by adjusting the operational parameters, without a significant increase in system cost or new investments.

Maintenance Modelling of Ceramic Claddings in Pitched Roofs Based on the Evaluation of Their In Situ Degradation Condition

Existing maintenance policies have several limitations, mainly due to the lack of knowledge regarding the durability and performance of buildings. Usually, the maintenance policies are insufficiently accurate, neglecting the risk of failure over time and the global costs associated with repairs. In this study, a condition-based maintenance model, based on Petri nets, is proposed to evaluate the impact of three maintenance strategies of ceramic claddings in pitched roofs (CCPR): MS1—only total replacement; MS2—composed of total replacement and minor intervention and MS3—composed of total replacement, minor intervention and cleaning operations. In this study, 146 CCPR were inspected in situ, with a total area of 43,991.6 m2. The remaining service life of the CCPR; the global costs over the claddings’ lifetime (considering inspection, maintenance, replacement and disposal costs); the claddings’ degradation condition and the number of replacements during the time horizon are used to evaluate the performance of the different maintenance strategies through a simplified multi-criteria analysis. The results show that the gains in performance, in terms of expected service life and durability, of the consideration of preventive maintenance actions (minor interventions or cleaning operations) outweigh the increase of the operation costs.

Reliability-based life-cycle cost design of asphalt pavement using artificial neural networks

It is widely recognized that reliability-based optimization methodologies are rational and promising tools to perform the life-cycle management (LCM) of civil engineering structures. In order to realize the optimal design and maintenance of asphalt pavement, a comprehensive reliability-based optimization methodology considering the life-cycle cost (LCC) is proposed in this paper. Considering the powerful ability of Artificial Neural Networks (ANNs) to solve complex and nonlinear problems, ANNs are implemented to predict the performance of asphalt pavement based on the training data (i.e. structural, traffic, climatic, and performance parameters) selected from the Long-Term Pavement Performance (LTPP) program. Monte Carlo simulation (MCS) with Importance Sampling (IS) is conducted based on the obtained ANNs model to calculate the life-cycle reliability of asphalt pavement. Finally, the expected LCC including the initial construction cost, the preventive maintenance cost, inspection cost, users cost, and salvage value is minimized while maintaining a prescribed life-cycle reliability level for asphalt pavement. Several applications are presented to investigate the effects of traffic and climatic parameters on reliability-based optimum cost solution.

Lifetime estimation of a BWR core shroud in terms of IGSCC

The continued operation of aging Boiling Water Reactors (BWRs) worldwide requires gradually increasing cost of inspection, maintenance, and repair. Intergranular Stress Corrosion Cracking (IGSCC) in sensitized austenitic stainless steel piping first became a major issue for BWRs in the 1980s, resulting in recognition of the susceptibility of reactor internals to IGSCC. Shroud cracking identified in 1993–1994 confirmed that IGSCC of internals is a significant issue for BWRs. IGSCC is a time-dependent, material degradation process, which is caused and accelerated by the presence of residual stresses, material sensitization, irradiation, cold work, elevated temperature, and corrosive environments. This paper emphasizes the importance of accounting for corrosive environments, or more exactly, electrochemical phenomena in modelling IGSCC and predicting the service life of BWR in-vessel components, and stresses the necessity of performing such modeling not just for a single state point under full power conditions, but for the whole operating history of the reactor, including startups and shutdowns. This paper demonstrates that ignoring electrochemical considerations may result in underestimating component lifetime and lead to unnecessary expenses for inspection and repair.

Modified Average Sample Number for Improved Double Sampling Plan Based on Truncated Life Test Using Exponentiated Distributions

The reliability of the product has developed a dynamic issue in a worldwide business market. Generally acceptance sampling guarantees the superiority of the product. In acceptance sampling plan, increasing the sample size may lead to minimization of customers' risk of accepting bad lots and producers' risk of rejecting good lots to a certain level but will increase the cost of inspection. Hence truncation of life test time may be introduced to reduce the cost of inspection. Modified Average Sample Number (MASN) for Improved Double Sampling Plan (IDSP) based on truncated life test for popular exponentiated family such as exponentiated gamma, exponentiated lomax and exonentiated Weibull distribution are considered. The modified ASN creates a band width for average sample number which is much useful for the consumer and producer. The interval for average sample number makes the choice of consumer with a maximum and minimum sample size which is of much benefit without any loss for the producer. The probability of acceptance and average sample number based on modified double sampling plan for lower and upper limit is computed for the exponentiated family. Optimal parameters of IDSP under various exponentiated families with different shape parameters were computed. The proposed plan is compared over traditional double sampling and modified double sampling using Gamma distribution, Weibull distribution and Birnbaum-Saunders distribution and shows that the proposed plan with respect to exponentiated family performs better than all other plans. The tables were provided for all distributions. Comparative study of tables based on proposed exponentiated family and earlier existing plan are also done.

Developing a model of the dynamics of states of a recommendation system under conditions of profile injection attacks

The recommendation systems used to form a news feed in social networks or to create recommendation lists on content websites or Internet stores are often exposed to information profile injection attacks. These attacks are aimed at changing ratings, and thus at changing the frequency of appearing in recommendations, certain objects of a system. This can lead to threats to users’ information security and losses of the system owners. There are methods to detect attacks in recommendation systems, but they require permanent repetitive checks of all users’ profiles, which is a rather resource-intensive operation. At the same time, these methods do not contain any proposals as for determining the optimal frequency of attack checks. However, a properly chosen frequency of such checks will not overload a system too much and, at the same time, will provide an adequate level of its operational security. A mathematical model of the dynamics of states of a recommendation system under conditions of an information attack with the use of the mathematical apparatus of Markovian and semi-Markovian processes was developed. The developed model makes it possible to study the influence of profile injection attacks on recommendation systems, in particular, on their operation efficiency and amount of costs to ensure their information security. The practical application of the developed model enables calculating for recommendation systems the optimum frequency of information attack check, taking into consideration the damage from such attacks and costs of permanent inspections. Based on the developed mathematical model, the method for determining total costs of a recommendation system as a result of monitoring its own information security, neutralization of bot-networks activity and as a result of information attacks was proposed. A method for determining the optimal frequency of checking a recommendation system for information attacks to optimize the overall costs of a system was developed. The application of this method will enable the owners of websites with recommendation systems to minimize their financial costs to provide their information security

Process‐capability‐qualified adjustable multiple‐dependent‐state sampling plan for a long‐term supplier–buyer relationship

AbstractAcceptance sampling plan is widely used for the inspections of incoming or outgoing products to provide the producer and the consumer a general benchmark for lot sentencing. To reduce the inspection cost, the multiple‐dependent‐state (MDS) plan that takes account of the preceding lots' quality history into the current lot disposition has been proposed. However, recent studies overlook the fact that the MDS plan's performance needed to reach target compliance decreases with an increase in the number of preceding lots considered. This unawareness makes the MDS plan fall into a conflictive situation. To overcome the drawback of the MDS plan, in this paper, we introduce a modified MDS plan to accommodate an adjustable mechanism, called adjustable MDS (AMDS) sampling plans. The presented AMDS plans are designed on the basis of the advanced process capability index, which is cognizant of both the process yield and the process loss. This established process‐capability‐qualified AMDS plan efficiently solves the conflictive situation of the MDS plan when encompassing more preceding lots in the lot‐disposition decision. Notably, its efficacy has been shown on high improvements in terms of the required sample size for the inspection, the discriminatory power, and the average run length for lot sentencing.

A Semi-quantitative Approach Development for Risk-based Inspection in a Petrochemical Plant

BACKGROUND: Recently, oil and gas industries have focused on risk-based methods to specifically compile inspection, maintenance, and management strategies worldwide.
 AIM: The provided method in this study is a management tool to recognize and then prioritize the equipment’s risks and, consequently, propose an inspection plan based on these risks. In fact, it is a risk analysis aspect of an inspection plan for industrial equipment.
 MATERIALS AND METHODS: The study is performed on de-ethanizer unit, considering variety of process equipment including distillation tower, exchanger, pressure vessel, drum, and related piping. To initiate the study, first, the risk-based inspection (RBI) team formed, then all required data were gathered and 22 equipment were identified based on the method.
 RESULTS: After RBI be performed and risks are estimated, 13.6% of equipment rated on high risk, 63.63% rated on medium risk, and 22.72% rated on low-risk classification. Based on specific risk criteria for equipment, we determined new parameters as inspection level and type of inspection and finally integrated them. As one of the obtained results, the overhaul maintenance of the unit was postponed to a later time and for equipment that should inspect before this year, reduction risk strategy and advance none distractive test defined, and their inspection time also postpone to 2015 from 2012 to 2013.
 CONCLUSION: This decision results in saving a shutdown cost, inspection cost, reduction of failure, and increasing of equipment reliability factor. The result of this study will be helpful to assist similar industries improving their risk management plans.