Business processes require continuous changes or interventions to remain efficient and competitive over time. However, implementing these changes-such as reordering or adding new tasks- can negatively affect the overa...
详细信息
ISBN:
(纸本)9783031790584;9783031790591
Business processes require continuous changes or interventions to remain efficient and competitive over time. However, implementing these changes-such as reordering or adding new tasks- can negatively affect the overall process performance. A longstanding problem in Business process Management is that of forecasting ex-ante the values that process performance measures will assume after implementing changes. To achieve this, the concept of Digital process Twins, which extends the well-established Digital Twin paradigm, paves the way for new interesting opportunities. Digital process Twins enable enhanced what-if analysis by virtually predicting process performance under various changes, thus allowing for informed decision-making before actuating process changes in the real world. However, despite recognition as one of the new key enablers of modern process re-engineerization, a comprehensive approach to implementing Digital process Twins is still lacking. This paper proposes a novel conceptual architecture for deploying Digital process Twins to address this gap. Additionally, we introduce Dolly, a framework that implements such conceptual architecture using a multi-modeling approach combining domain data and processmodeling along with a data-driven process simulation technique.
Peach body resection is a common treatment in clinical practice, especially for patients with recurrent tonsillitis. However, the effect of tonsillectomy on the risk of sinusitis in adults has not been fully studied. ...
详细信息
Peach body resection is a common treatment in clinical practice, especially for patients with recurrent tonsillitis. However, the effect of tonsillectomy on the risk of sinusitis in adults has not been fully studied. In recent years, the application of medical thermal modeling technology provides a new perspective to explore the relationship between surgery and disease. The aim of this study was to assess whether tonsillectomy is a risk factor for sinusitis in adults and to analyze its underlying mechanisms through medical thermal modeling techniques. Participants' medical history, tonsillectomy records, and sinusitis status were analyzed cross-sectional. The use of medical thermal modeling aims to simulate and analyze the process of heat transfer within organisms to help understand thermodynamic changes during the onset, development and treatment of diseases. The heat transfer equation describes the law of internal heat transfer of an object. The heat generated in an organism comes from metabolism and muscle activity, etc., while the heat input from the external environment is related to body temperature regulation. Multivariate regression analysis of the data was performed to control for confounding factors such as age, sex, allergy and smoking history. Medical thermal modeling revealed that tonsillectomy increases the risk of sinusitis by altering the anatomy and immune function of the upper respiratory tract. Postoperative nasal ventilation and drainage were affected, leading to chronic inflammation.
The aim of this research is to present the optimal pattern structure of double-layer woven heating fabrics, to deliberately increase the heating efficiency of the fabric on one side and reduction of heating energy los...
详细信息
The aim of this research is to present the optimal pattern structure of double-layer woven heating fabrics, to deliberately increase the heating efficiency of the fabric on one side and reduction of heating energy loss on the other side of the fabric. Besides, analysis was carried out to provide a thermal model for a more detailed examination of the performance of these textiles in terms of thermal characteristics. Moreover, implementation of an intelligent temperature control system was performed to steadily regulate the temperature, at a predetermined temperature, in various external environmental temperature conditions. To achieve this purpose, nine samples of double-layer woven fabrics made of polyester yarns, consisting of nickel-chromium element as a proportion of weft yarns, were designed and produced. The mentioned fabrics were different in terms of weave pattern, connecting stitch type, and element-thread ratio. Finally, the effect of various structural factors of these fabrics in terms of thermal insulation properties, the heat production, and also the transfer process, has been investigated and a thermal model is introduced and described. Also, an intelligent control system based on Arduino microcontroller was designed and optimized based on PID control logic, and the ability of the control system to adjust the temperature was examined. Finally, according to the analysis of the results, it was determined that the double-layer tubular fabric is the most appropriate sample to achieve the goals of this research. The finding is due to the complete separation of the two layers of fabric from each other, and as a result, significant air is trapped between the two layers of the fabric creating an insulation layer in between. Also, the presented thermal model had acceptable results compared to the experimental data, and the control system was successful in controlling the textile temperature in different conditions.
Offshore wind turbines face substantial challenges in operation and maintenance due to the harsh marine environment and remote locations. Predictive maintenance, encompassing fault diagnostics and failure prognostics,...
详细信息
Offshore wind turbines face substantial challenges in operation and maintenance due to the harsh marine environment and remote locations. Predictive maintenance, encompassing fault diagnostics and failure prognostics, is a promising maintenance strategy to address these challenges. To contribute to this strategy, an integrated data-driven model is developed for probabilistic failure prognostics at the component level. The remaining useful life of a gearbox pump in an offshore wind turbine is predicted accurately based on supervisory control and data acquisition data. In this approach, light gradient boosting machines are tuned to model normal temperatures. The gated recurrent unit outperforms other neural networks and is selected to process temperature residuals with a Bayesian neural network. Results show that the prediction at the 50% percentile precedes the true failure time by 3.83 h. Moreover, there is 97.5% confidence that the true failure time falls within around +/- 5.3 h of the predicted time. Furthermore, the earliest alarm is issued at the 2.5% percentile, precisely 9.17 h prior to the true failure time. This study demonstrates the effectiveness of supervised learning and normal behavior modeling for probabilistic failure prognostics of offshore wind turbine components.
In complex industrial processes, distributed control systems (DCSs) are currently operated to prevent unplanned shutdowns and major accidents. However, DCSs not only have the advantages of collecting large amounts of ...
详细信息
In complex industrial processes, distributed control systems (DCSs) are currently operated to prevent unplanned shutdowns and major accidents. However, DCSs not only have the advantages of collecting large amounts of operational history data, but they also have the shortcoming of limited monitoring capabilities, such as early detection, due to their reliance on generating fault alarms based on simple threshold values. To improve the stability and reliability of industrial processes, it is essential to operate DCS in conjunction with data-driven process monitoring technologies. In this paper, we propose a novel hybrid model combining independent component analysis (ICA) and auto-associative kernel regression (AAKR) to address the limitations of both models. The proposed model (ICA+AAKR) introduces a new method, cumulative percentage distance (CPD), which can determine the appropriate number of independent components (ICs) for dimensionality reduction in ICA. By inputting the dimension-reduced IC matrix into AAKR, the issue of excessive computation time caused by lazy learning in AAKR is effectively mitigated. We applied the proposed fault detection method to two well-known benchmarks (multivariate dynamic process and Tennessee Eastman process) and a real-world application (actual tube leakage in power plant) to verify its monitoring performance. The experimental results validated superior detection performance compared to existing methods for the two benchmark problems. In addition, the method demonstrated the potential to enhance process stability and reliability by enabling remarkable early detection of tube leakage in a circulating fluidized bed boiler at the power plant.
The autopilot design for the full flight envelope, starting from take-off to landing, is presented in this paper. The navigation, guidance, and flight control law models that make up the autopilot have been designed f...
详细信息
The autopilot design for the full flight envelope, starting from take-off to landing, is presented in this paper. The navigation, guidance, and flight control law models that make up the autopilot have been designed for use in unmanned aircraft. Through processor-in-loop simulation, the designed autopilot is put into action. Medium-altitude long-endurance unmanned aircraft (MALE) is being examined to demonstrate the proposed autopilot. The controller is put through a test against the wind. The flight control law in which the systematic and generalized autopilot design procedure is established with a hardware-lumped model. The design process comprises the assessment of the aircraft's linear and nonlinear responses, open-loop characteristics, transfer function design, root locus analysis with delay, control bandwidth analysis, time-domain analysis, control law implementation, and testing for the nonlinear model. The said procedure is repeated for other trim flight conditions. A novel Cubature Kalman filter (CKF)-based navigation algorithm has been proposed to process attitude heading reference systems (AHRS) solution information, primarily rates, attitudes, heading, geodetic position, and velocity data. The first filter, named complementary CKF is used to re-estimate aircraft attitudes and the second filter, named integrated CKF (I-CKF) is used to estimate aircraft position and velocities. Thus, the complete stages of a practical flight control system, starting from the aircraft model, total loop delay characterization, sensor and actuator modeling, controller design using successive loop closure method for navigation and landing flights, guidance, and navigation filters, are clearly explained in this paper.
Knowledge management has emerged as a key enabler of organisational learning and innovation in the digital era. Over data helps organizations to collect, transform and act upon these insights towards process innovatio...
详细信息
ISBN:
(纸本)9798331527495
Knowledge management has emerged as a key enabler of organisational learning and innovation in the digital era. Over data helps organizations to collect, transform and act upon these insights towards process innovation and decision victory. Rooted in a dynamic capability lens of organizational learning, this study extends theory and practice by illustrating how knowledge management systems, powered by NLP, can provide transformational impact in terms of guiding organizational learning to achieve competitive advantage in the midst of evolving business scopes. Failure to capture, share and innovate organizational learning allows an organisation to learn from its best practices and adequately adapt to change. Traditional KM approaches have been biased to the codification of explicit knowledge which, by and large, have focused on the codification of explicit knowledge, in general, they did not pay much attention to tacit knowledge embedded in extracted information from the organization communication, documents, and external data stores. NLP technologies help fill this vacuum by enabling organizations to work with both structured and unstructured data in a manner capable of uncovering previously opaque patterns, insights and knowledge. Leveraging essential NLP techniques such as sentiment analysis, topic modeling, entity recognition, and text summarization, organizations can generate insights from vast datasets. As a few examples, qualitative analysis can be used to to measure employee satisfaction or customer feedback using sentiment analysis etc. or topic modeling can work to surface new trends or areas of knowledge that are critical for strategic initiatives. Entity recognition also facilitates the identification of key players, relations and resources, which streamlines the decision-making process. When paired with machine learning algorithms, this kind of NLP tooling provides insight into key topics in real time, automating repetitive tasks and enabling adaptive lea
Industrial data often consist of continuous variables (CVs) and binary variables (BVs), both of which provide crucial information about process operating conditions. Due to the coupling between industrial systems or e...
详细信息
Industrial data often consist of continuous variables (CVs) and binary variables (BVs), both of which provide crucial information about process operating conditions. Due to the coupling between industrial systems or equipment, these hybrid variables are usually high-dimensional and highly correlated. However, existing methods generally model hybrid variables directly in the observation space and assume independence between the variables to overcome the curse of dimensionality. Thus, they are ineffective at capturing dependencies among hybrid variables, and the effectiveness of process monitoring will be compromised. To overcome the limitations, this study proposes to seek a unified subspace for hybrid variables using the probabilistic latent variable (LV) model. By introducing a low-dimensional continuous LV, the proposed method can avoid the curse of dimensionality while capturing the dependencies between hybrid variables. Nevertheless, the inference of LV is analytically intractable and thus time-consuming due to the heterogeneity of CVs and BVs. To accelerate offline learning and online inference procedures, this study originally derives an analytical Gaussian distribution to approximate the true posterior distribution of the LV, based on which an efficient expectation-maximization algorithm is developed for parameter estimation. The Gaussian approximation is simultaneously optimized with the latest parameters to achieve a high approximation accuracy. The LV is then estimated by the posterior mean of the Gaussian approximation. By mapping the heterogeneous variables into a unified subspace, the proposed method defines three monitoring statistics, which are physically interpretable and thoroughly evaluate the probability of hybrid variables being normal. The effectiveness of the proposed method in detecting anomalies in CVs and BVs is shown through a numerically simulated case and a real industrial case.
The cause of the accident comes from the unsafe state of the system, and the development process of the accident reflects the dynamic change of the system state in the process. Aiming at the problem of complex system ...
详细信息
Fine-grained urban flow inference is pivotal in alleviating traffic congestion and reducing detector deployment costs. It aims to infer fine-grained flow maps from coarse-grained traffic data. However, existing method...
详细信息
Fine-grained urban flow inference is pivotal in alleviating traffic congestion and reducing detector deployment costs. It aims to infer fine-grained flow maps from coarse-grained traffic data. However, existing methods face challenges due to the highly complex nature of spatial modeling for urban flow patterns and the distinctive impact of external factors such as temperature and weather. To address these issues, this paper proposes a Simplified Multi-Factor spatial modeling framework (SimMF) to enhance the accuracy of fine-grained flow inference while optimizing inference complexity. SimMF incorporates a dual-path architecture for short-range modeling, combining multi-scale convolutions and frequency-domain processing via FFT to capture cross-scale spatial correlations and heterogeneity. For long-range dependencies, SimMF employs enhanced bottleneck attention with linear complexity, effectively modeling intricate spatial relationships. Additionally, SimMF adopts a view-aware learnable approach to represent external factors, enabling each factor to generate distinctive feature maps and capture its unique characteristics. Experimental results on two urban datasets demonstrate that SimMF outperforms existing methods, achieving superior inference accuracy while maintaining computational efficiency with significantly improved computational efficiency.
暂无评论