High-value Assets Research Articles

Remaining Useful Life Prediction Method Based on Dual-Path Interaction Network with Multiscale Feature Fusion and Dynamic Weight Adaptation

In fields such as manufacturing and aerospace, remaining useful life (RUL) prediction estimates the failure time of high-value assets like industrial equipment and aircraft engines by analyzing time series data collected from various sensors, enabling more effective predictive maintenance. However, significant temporal diversity and operational complexity during equipment operation make it difficult for traditional single-scale, single-dimensional feature extraction methods to effectively capture complex temporal dependencies and multi-dimensional feature interactions. To address this issue, we propose a Dual-Path Interaction Network, integrating the Multiscale Temporal-Feature Convolution Fusion Module (MTF-CFM) and the Dynamic Weight Adaptation Module (DWAM). This approach adaptively extracts information across different temporal and feature scales, enabling effective interaction of multi-dimensional information. Using the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset for comprehensive performance evaluation, our method achieved RMSE values of 0.0969, 0.1316, 0.086, and 0.1148; MAPE values of 9.72%, 14.51%, 8.04%, and 11.27%; and Score results of 59.93, 209.39, 67.56, and 215.35 across four different data categories. Furthermore, the MTF-CFM module demonstrated an average improvement of 7.12%, 10.62%, and 7.21% in RMSE, MAPE, and Score across multiple baseline models. These results validate the effectiveness and potential of the proposed model in improving the accuracy and robustness of RUL prediction.

Analysing cross-border logistics operations for performance improvement: development and validation of a reference model

AbstractThe critical role played by cross-border logistics (CBL) systems in sustaining fast, efficient and responsive global supply chains is widely recognised. However, scholarly research focusing on CBL systems is limited, which means that theoretical frameworks and methodological approaches available for analysing and improving CBL operations are underdeveloped. As such, coordination among diverse stakeholders, meeting regulatory requirements, adapting to a rapidly evolving technological environment, and limited capacity for investing in high-value assets, all remain ongoing challenges hindering the smooth and swift flow of cargo across borders. With a view to addressing these challenges and research gaps, this paper develops a reference model for analysing and improving CBL-specific processes. Seven underlying process dimensions have been identified following a rigorous methodological approach for the modelling, analysis and improvement of CBL operations. The efficacy of the reference model is demonstrated using two purposive case applications. The reference model also helps identify potential technological interventions to improve operations and benchmark CBL systems, operations and processes.

Optimisation and Calibration of Bayesian Neural Network for Probabilistic Prediction of Biogas Performance in an Anaerobic Lagoon.

This study aims to enhance diagnostic capabilities for optimising the performance of the anaerobic sewage treatment lagoon at Melbourne Water's Western Treatment Plant (WTP) through a novel machine learning (ML)-based monitoring strategy. This strategy employs ML to make accurate probabilistic predictions of biogas performance by leveraging diverse real-life operational and inspection sensor and other measurement data for asset management, decision making, and structural health monitoring (SHM). The paper commences with data analysis and preprocessing of complex irregular datasets to facilitate efficient learning in an artificial neural network. Subsequently, a Bayesian mixture density neural network model incorporating an attention-based mechanism in bidirectional long short-term memory (BiLSTM) was developed. This probabilistic approach uses a distribution output layer based on the Gaussian mixture model and Monte Carlo (MC) dropout technique in estimating data and model uncertainties, respectively. Furthermore, systematic hyperparameter optimisation revealed that the optimised model achieved a negative log-likelihood (NLL) of 0.074, significantly outperforming other configurations. It achieved an accuracy approximately 9 times greater than the average model performance (NLL = 0.753) and 22 times greater than the worst performing model (NLL = 1.677). Key factors influencing the model's accuracy, such as the input window size and the number of hidden units in the BiLSTM layer, were identified, while the number of neurons in the fully connected layer was found to have no significant impact on accuracy. Moreover, model calibration using the expected calibration error was performed to correct the model's predictive uncertainty. The findings suggest that the inherent data significantly contribute to the overall uncertainty of the model, highlighting the need for more high-quality data to enhance learning. This study lays the groundwork for applying ML in transforming high-value assets into intelligent structures and has broader implications for ML in asset management, SHM applications, and renewable energy sectors.

Resource Efficient Deep Learning Hardware Watermarks with Signature Alignment

Deep learning intellectual properties (IPs) are high-value assets that are frequently susceptible to theft. This vulnerability has led to significant interest in defending the field's intellectual properties from theft. Recently, watermarking techniques have been extended to protect deep learning hardware from privacy. These technique embed modifications that change the hardware's behavior when activated. In this work, we propose the first method for embedding watermarks in deep learning hardware that incorporates the owner's key samples into the embedding methodology. This improves our watermarks' reliability and efficiency in identifying the hardware over those generated using randomly selected key samples. Our experimental results demonstrate that by considering the target key samples when generating the hardware modifications, we can significantly increase the embedding success rate while targeting fewer functional blocks, decreasing the required hardware overhead needed to defend it.

Detecting lateral movement: A systematic survey

Within both the cyber kill chain and MITRE ATT&CK frameworks, Lateral Movement (LM) is defined as any activity that allows adversaries to progressively move deeper into a system in seek of high-value assets. Although this timely subject has been studied in the cybersecurity literature to a significant degree, so far, no work provides a comprehensive survey regarding the identification of LM from mainly an Intrusion Detection System (IDS) viewpoint. To cover this noticeable gap, this work provides a systematic, holistic overview of the topic, not neglecting new communication paradigms, such as the Internet of Things (IoT). The survey part, spanning a time window of eight years and 53 articles, is split into three focus areas, namely, Endpoint Detection and Response (EDR) schemes, machine learning oriented solutions, and graph-based strategies. On top of that, we bring to light interrelations, mapping the progress in this field over time, and offer key observations that may propel LM research forward.

Predicting Defect Rates of Printed Circuit Board Assemblies: Towards Zero Defect Manufacturing and Zero-Maintenance Strategies

Printed Circuit Boards (PCB) manufacturing is a critical part of volatile supply chains for a wide variety of products and high value assets. PCBs are expected to exhibit zero defects and be subject to zero-maintenance. However low the defect rates, defects are highly disruptive and costly. Such defects can be introduced by a multitude of reasons, including faulty parts or sub-standard manufacturing processes. While sophisticated and dedicated quality inspection systems are typically in place in production environments, they still leave room for erroneous quality control outcomes. Besides in-line or post-production quality inspection, manufacturers can exploit experience gained from historical records of past inspections to predict future defect rates. This paper presents the development of a predictive quality modelling approach, which capitalises on such historical data and domain knowledge, to predict defect rates in new production orders. Employing appropriate encoding of knowledge through data pre-processing and applying regression type of machine learning, the proposed approach is validated on a real case study from an electronics manufacturing company. The developed approach can positively contribute towards optimising consequent maintenance and warranty services and become part of a zero-defect production strategy.

Intellectual Capital and the perception about self

The value of a company is not only measured by the value of its shares in the financial market, but also by its influence in the media and by how it impacts people's lives. Therefore, you have the value of that brand, its name, and its owner. Although this value speaks very loudly in a society, capitalist or not, there is another value that is not measurable and has a high impact on the external value of a company. It is the value that a company has for its employees and aggregate workers. This is a value that can be measured in the evasion of its staff. However, there is still one more value. Having valuable employees is not a gift; it's an achievement. Getting employees who work for years in the company and have high performance, engagement, and motivation, is more than professionalism. It's affection. And work with affection is not a characteristic of all people. This employee-company relationship requires commitment from both parties. A company, like a tree, is more than it appears to be. Likewise, a person is also more than appears to be. In this context, this article aims to address these intricacies of business-employee relationships, so that self-perception is the basis of a lasting and healthy relationship. The methodology of this work, in addition to long bibliographical research, is research that addresses several issues related to this context and the results are surprising. Thus, more so than professional development, it is necessary to invest in a high-value asset: awareness of yourself. Searching for your value within yourself is a great journey, which must be carefully instigated, in order to promote evolution and well-being within the company. More than professionals, people of character and commitment are needed, and these are also characteristics that must be sought in its employees. This is so the company has a long and healthy life, and the employee feels motivated to grow as a person and as a professional.

Product–machine qualification using a process flexibility strategy considering capacity loss

Due to uncertainties in future demands regarding product variety, manufacturers must maintain a balance between capacity investment costs and future demand satisfaction levels, which makes capacity management challenging for a high-value asset industry. Product–machine qualification, which is an essential process in configuring machines to produce new products, plays an important role in allocating appropriate capacity to different products. Motivated by the challenges presented by this real-world trade-off problem, this article develops effective “product–machine” production structures by introducing new process flexibility strategies. The product–machine qualification process is complex and very time-consuming, which generally causes processing machines to experience massive capacity loss. The more flexible a machine is, the more product–machine qualification steps are required and the more capacity will be lost. Traditional process flexibility strategies, such as the long chain strategy, cannot be used directly for product–machine qualification decisions because they all assume that the capacities of machines are constant and that only product demands vary. This article promotes the traditional process flexibility theory by introducing capacity loss into the model. The proposed strategies for balancing process flexibility and capacity loss have proven effective in satisfying uncertain demands by cost-effective capacity-demand matching structures.

Exhaust-gas temperature model and prognostic feature for diesel engines

Prognostics is an enabler of predictive maintenance, which can improve reliability, availability, and reduce the maintenance cost of high value assets. A novel prognostic feature was developed that tracks diesel fuel injector damage based upon measured exhaust gas temperature for each cylinder, where prior work was limited to fault detection. The feature value is computed using a simple and accurate two-stage hybrid linear regression model for exhaust gas temperature that is based on engine thermodynamics and data from the engine controller. The model is shown to be accurate to within 10 percent at low exhaust temperature and within 5 percent at high exhaust temperature. The study showed that the feature has a strong correlation to injector leakage over the leakage range of 0–100 mm3 per cylinder stroke. The feature was developed from steady-state operating conditions and is shown to generalize to operating conditions outside of the development set. It was also shown to work on short stable data segments (3 s and longer) extracted from transient operating conditions.

Comparison of Selection for Employee Position Recommended MCDM-AHP, SMART and MAUT Method

In a company, employees are high-value assets, therefore it is necessary to select employees for the continuity of the company, of course, by getting quality human resources. The purpose of this paper is to refute the difference in the number of rankings in selecting the best employees through a comparison of the SMART and MAUT methods. Many methods can be used in the selection process. This article describes in detail about the selection of employee promotions using the MCDM-AHP collaboration method which is used to provide an assessment of the main criteria through eigenvector values ​​based on joint decisions by company leaders based on consistent and optimal questionnaire instrumentation which is not set based on percentages manually based on wishes leader. The SMART method is used to provide a sub-criteria assessment based on a balanced weighting utility according to the number of criteria used, with an assessment weight starting from zero as the lowest value and one as the highest value. The MAUT method will be used as a comparison against the results of the SMART method, where the MAUT method has differences in determining the weights on the sub-criteria based on the perception of understanding the criteria, so that they are arranged in an orderly manner and then determine the utility value of the criteria, so that there are similarities between the two methods. The ranking results obtained from the comparison of the two methods are that they have the same rating, so that the decision support taken also has similarities between the two SMART methods and the MAUT method. This can happen if the standard of measurement is carried out consistently through the MCDM-AHP method by not changing the assessment range in determining the interval range of each criterion.

Fatigue crack detection in edges of thin-walled structures with corners using the fundamental mode of edge waves

Non-destructive detection and evaluation of fatigue cracks is critical to maintain safety and effective operation of high-value assets working under cyclic loading. However, this can be difficult in the case of the corners of the structural elements, especially at inaccessible locations. In this article, the propagation of the fundamental symmetric mode of edge wave (ES0) along structural features such as sharp and rounded corners are investigated using experimental and numerical methods. The ultimate aim of this study is to demonstrate that the ES0 is a promising for defect detection in geometries with corners. The outcomes of this study show that ES0 wave is able to propagate through sharp and rounded corners and provides a way to inspect difficult-to-reach locations. Further, the numerical simulations indicate that the radius-to-wavelength ratio above 3 has no significant impact on the wave amplitude when the ES0 propagates through the rounded corner. The results also demonstrate that the presence of fatigue crack leads to generation of the second harmonic of the ES0 wave mode, and this phenomenon can be utilised in the development of fatigue crack detection and characterization procedures.

The crazy rich phenomenon in the airline industry: The accountant’s perspective based on IFRS 16

This study aims to find out how the perspective of accountants in Indonesia on their knowledge of the International Financial Reporting Standards (IFRS) 16 which related to the recognition of ownership of private jets rented by Indonesian “crazy rich”. The respondents of this study were accountants in Indonesia with a total of 222 people consisting of 84 registered accountants who were members of professional accounting bodies such as the Indonesian Accountant Association, Institute of Indonesian Public Accountants, and Institute of Indonesia Management Accountants, and 138 accountants who were not registered. The data analysis method is using a different test (t-test) using the assumption of equal variance assumed and not assumed to see significant differences between the two categories of accountants regarding the perspective of recognizing leased assets. The results show that both categories of accountants have the same perspective for approving the recognition of private jets as assets because they are high-value assets even though the lease period is less than or equal to 12 months and agreeing to be part of business operations that increase revenue. Accounting standards for leases guide lessees to categorize them as finance leases that recognize right-of-use assets, lease liabilities, interest, and depreciation costs. Reports that use finance leases will change profitability and debt-to-equity ratios. By understanding the latest standards, accountants will react appropriately in relation to the existing phenomena. This research provides added value and general lessons for parties with an interest in business and especially for accountants that learning the latest standards is very important in order to be able to scientifically respond to social phenomena that occur around us.

Asset Waqf Management Model in the Health Sector LAZNAS Daarut Tauhiid Peduli Surabaya

Purpose: Modernization has brought the application of waqf to develop in various parts of the country. The reason is, not only in terms of Islam and worship,waqf has close links with legal, social and economic aspects that are highlighted because waqf assets can produce high-value assets whose results can be used for the welfare of the people.Design/Mothod/Approach : Using a qualitative method with a descriptive approach, this study explains how the pattern of asset waqf management in the form of medical devices was launched in a health program by LAZNAS DT Peduli with program partners, starting from planning activities to the realization steps. The main data were obtained through moderate participation observation techniques and semi-structured interview techniques along with the research sample. The data analysis technique includes three activities; data reduction on the main and important things from the results of observations and interviews, followed by data presentation in the form of narrative descriptions, to drawing conclusions to answer the formulation of the problem.Findings: The results of the study explain that management requires continuity of the process. The dynamics obtained from the beginning to the end must be consistent and consistent with the design they have. LAZNAS DT Peduli as a philanthropic institution in waqf management with an innovation model makes initial planning the decisive stage.Originality/Values: Followed by structuring action steps that are packaged in the organizing stage, followed by action steps or realization in order to get results to support the medical device waqf program until supervision of sterilizers has been carried out at the same time to ensure the benefits of medical device waqf are well conveyed.

Design engineering a walking robotic manipulator for in-space assembly missions.

In-Space Services aim to introduce sustainable futuristic technology to support the current and growing orbital ecosystem. As the scale of space missions grows, there is a need for more extensive infrastructures in orbit. In-Space Assembly missions would hold one of the key responsibilities in meeting the increasing demand. In the forthcoming decades, newer infrastructures in the Earth’s orbits, which are much more advanced than the International Space Station are needed for in-situ manufacturing, servicing, and astronomical and observational stations. The prospect of in-orbit commissioning a Large Aperture Space Telescope (LAST) has fuelled scientific and commercial interests in deep-space astronomy and Earth Observation. However, the in-situ assembly of such large-scale, high-value assets in extreme environments, like space, is highly challenging and requires advanced robotic solutions. This paper introduces an innovative dexterous walking robotic system for in-orbit assembly missions and considers the Large Aperture Space Telescope system with an aperture of 25 m as the use case. The top-level assembly requirements are identified with a deep insight into the critical functionalities and challenges to overcome while assembling the modular LAST. The design and sizing of an End-over-end Walking Robot (E-Walker) are discussed based on the design of the LAST and the specifications of the spacecraft platform. The E-Walker’s detailed design engineering includes the structural finite element analysis results for space and earth-analogue design and the corresponding actuator selection methods. Results of the modal analysis demonstrate the deflections in the E-Walker links and end-effector in the open-loop due to the extremities present in the space environment. The design and structural analysis of E-Walker’s scaled-down prototype is also presented to showcase its feasibility in supporting both in-orbit and terrestrial activities requiring robotic capabilities over an enhanced workspace. Further, the mission concept of operations is presented based on two E-Walkers that carry out the assembly of the mirror modules. The mission discussed was shortlisted after conducting an extensive trade-off study in the literature. Simulated results prove the dual E-Walker robotic system’s efficacy for accomplishing complex in-situ assembly operations through task-sharing.

Security and Safety Concerns in Air Taxis: A Systematic Literature Review.

Different from traditional transport systems, such as cars or trains, which are limited by land transit space, flying cars (such as UAS, drones, and air taxis) do not occupy space with traffic. They have a degree of freedom in space and time, smaller displacement, and consequently, less stress for their users. Large companies and researchers around the world are working with different architectures, algorithms, and techniques to test air taxi transport to serve a significant proportion of people safely and autonomously. One of the main issues surrounding the diffusion of air taxis is safety and security, since a simple failure can lead to the loss of high-value assets, loss of the vehicle, and/or injuries to human lives, including fatalities. In this sense, despite significant efforts, the literature is still specific and limited regarding air taxi safety and security. Therefore, this study aimed to carry out an extensive systematic literature review of the main modern advances in techniques, architectures, and research carried out around the world focused on these types of vehicles. More than 210 articles from between 2015 and January 2022 were individually reviewed. In addition, this study also presents gaps that could serve as a direction for future research. As far as the authors are aware, no other study performs this type of review focused on air taxi safety.

Enhancement of solubility of recombinant alcohol dehydrogenase from Rhodococcus ruber using predictive tool.

Solubility is one of key factors influencing the heterologous production of recombinant proteins in biotechnology. Among many aggregation-prone proteins, alcohol dehydrogenase (ADH-A) from Rhodococcus ruber (in this work abbreviated RrADH) shows a great potential in processes involved in the biotransformation of natural compounds. As ADH-A is a potentially high value asset in industrial biotransformation processes, improvement of its solubility would be of major commercial benefit. Predictive tools and in silico analysis provide a fast means for improving protein properties, for selecting appropriate changes, and ultimately for saving costs. We have therefore focused on enhancement of the solubility of RrADH using an online accesible predictive tool Aggrescan 3D 2.0. Selected mutations were introduced into the protein amino acid sequence by using site-directed PCR. This led to a 17% increase in the protein solubility of RrADHmut1 and a 98% increase for RrADHmut2. Moreover, the basic kinetics of the enzyme reaction were positively affected, further optimizing the overall performance of the production process.

Squat Detection of Railway Switches and Crossings Using Wavelets and Isolation Forest.

Railway switches and crossings (S&Cs) are critical, high-value assets in railway networks. A single failure of such an asset could result in severe network disturbance and considerable economical losses. Squats are common rail surface defects of S&Cs and need to be detected and estimated at an early stage to minimise maintenance costs and increase the reliability of S&Cs. For practicality, installation of wired or wireless sensors along the S&C may not be reliable due to the risk of damages of power and signal cables or sensors. To cope with these issues, this study presents a method for collecting and processing vibration data from an accelerometer installed at the point machine to extract features related to the squat defects of the S&C. An unsupervised anomaly-detection method using the isolation forest algorithm is applied to generate anomaly scores from the features. Important features are ranked and selected. This paper describes the procedure of parameter tuning and presents the achieved anomaly scores. The results show that the proposed method is effective and that the generated anomaly scores indicate the health status of an S&C regarding squat defects.

An RUL-informed approach for life extension of high-value assets

The conventional approaches for life-extension (LE) of industrial assets are largely qualitative and focus only on a few indicators at the end of an asset’s design life. However, an asset may consist of numerous individual components with different useful lives and therefore applying a single LE strategy to every component will not result in an efficient outcome. In recent years, many advanced analytics techniques have been proposed to estimate the remaining useful life (RUL) of the assets equipped with sensor technology. This paper proposes a data-driven model for LE decision-making based on RUL values predicted on a real-time basis during the asset’s operational life. Our proposed LE model is conceptually targeted at the component, unit, or subsystem level; however, an asset-level decision is made by aggregating information across all components. Consequently, LE is viewed and assessed as a series of ongoing activities, albeit carefully orchestrated in a manner similar to operation and maintenance (O&M). The application of the model is demonstrated using the publicly available NASA C-MAPSS dataset for large commercial turbofan engines. This approach will be very beneficial to asset owners and maintenance engineers as it seamlessly weaves LE strategies into O&M activities, thus optimizing resources.

Autonomous Unmanned Heterogeneous Vehicles for Persistent Monitoring

Swarms of unmanned vehicles (air and ground) can increase the efficiency and effectiveness of military and law enforcement operations by enhancing situational awareness and allowing the persistent monitoring of multiple hostile targets. The key focus in the development of the enabling technologies for swarm systems is the minimisation of uncertainties in situational awareness information for surveillance operations supported by ‘system of systems’ composed of static and mobile heterogeneous sensors. The identified critical enabling techniques and technologies for adaptive, informative and reconfigurable operations of unmanned swarm systems are robust static sensor network design, mobile sensor tasking (including re-allocation), sensor fusion and information fusion, including behaviour monitoring. The work presented in this paper describes one of the first attempts to integrate all swarm-related technologies into a prototype, demonstrating the benefits of swarms of heterogeneous vehicles for defence applications used for the persistent monitoring of high-value assets, such as military installations and camps. The key enabling swarm system technologies are analysed here, and novel algorithms are presented that can be implemented in available COTS-based unmanned vehicles. The algorithms have been designed and optimised to require small computational power, be flexible, be reconfigurable and be implemented in a large range of commercially available unmanned vehicles (air and ground).

Human ignitions on private lands drive USFS cross-boundary wildfire transmission and community impacts in the western US

Wildfires in the western United States (US) are increasingly expensive, destructive, and deadly. Reducing wildfire losses is particularly challenging when fires frequently start on one land tenure and damage natural or developed assets on other ownerships. Managing wildfire risk in multijurisdictional landscapes has recently become a centerpiece of wildfire strategic planning, legislation, and risk research. However, important empirical knowledge gaps remain regarding cross-boundary fire activity in the western US. Here, we use lands administered by the US Forest Service as a study system to assess the causes, ignition locations, structure loss, and social and biophysical factors associated with cross-boundary fire activity over the past three decades. Results show that cross-boundary fires were primarily caused by humans on private lands. Cross-boundary ignitions, area burned, and structure losses were concentrated in California. Public lands managed by the US Forest Service were not the primary source of fires that destroyed the most structures. Cross-boundary fire activity peaked in moderately populated landscapes with dense road and jurisdictional boundary networks. Fire transmission is increasing, and evidence suggests it will continue to do so in the future. Effective cross-boundary fire risk management will require cross-scale risk co-governance. Focusing on minimizing damages to high-value assets may be more effective than excluding fire from multijurisdictional landscapes.