Critical Machine Research Articles

Analysis of Molding Defection in IC Packaging and Testing Process

Molding injects a molding compound into a mold to form a protective shell around the wafer. During the injection process, overflow may occur, leading to mold flash, which reduces yield and causes significant manufacturing cost losses. This paper proposes a deep-learning-based method for detecting and predicting the occurrence of mold flash probability to address this issue. First, the paper conducts random forest importance analysis and correlation analysis to identify the key parameters that significantly impact mold flash. This paper uses these key parameters as input signals for the prediction model. The paper introduces an HLGA Transformer to construct an ensemble meta-learning model that predicts the probability of molding defects, achieving a prediction accuracy of 98.16%. The ensemble meta-learning approach proposed in this paper outperforms other methods in terms of performance. The model predictions can be communicated to the system in real time, allowing it to promptly adjust critical machine operation parameters, thereby significantly improving the molding process yield and reducing substantial manufacturing cost losses.

Perturbation defense ultra high-speed weak target recognition

Ultra high-speed target recognition in complex electromagnetic environments is a critical and fundamental machine perception issue. It is difficult to ensure privacy protection and intelligent confrontation with centralized training in many practical situations. In this paper, an efficient ultra high-speed target recognition approach, named InVision, for robot systems is proposed using deep trustworthy federated learning (DTFL). InVision is accurate, safe, fast, and robust. Particularly, geometric component transformer (GCT) is presented to significantly promote neural element's complex representation description ability. And an ambiguity-aware cooperative learning (AACL) scheme is developed to relieve the noisy label problem. Moreover, decentralized federated training (DFT) is designed to mitigate the intractable privacy protection problem, to efficiently search for similarities and reduce the representation redundancy. Furthermore, to promote the running speed of the system in real-world environments, a lightweight deep architecture, called Mobile-XB, is developed. Extensive quantitative and qualitative experiments are carried out, and the results demonstrate that InVision greatly outperforms the outstanding comparison methods, establishing efficient connections and extraction, and providing security guarantees.

Open shop scheduling with group and transportation operations by learning-driven hyper-heuristic algorithms

Open shop scheduling problems (OSSPs) are complex scheduling problems, which have been extensively studied in the literature. Group and transportation activities are two important aspects of OSSPs that still need attention. This work considers an OSSP with group and transportation operations to minimize maximum completion time by solving three key sub-problems: job assignment among groups, job sequence in groups and group sequence on machines. Firstly, an integer programming model is formulized to define the problem. Secondly, a learning-driven hyper-heuristic algorithm is developed by incorporating a Q-learning method and four meta-heuristics, i.e., genetic algorithm, artificial bee colony optimization, variable neighborhood search method and Jaya algorithm. The Q-learning method is devised to select the most promising meta-heuristic for performing at each iteration. Three neighborhood structures are designed by integrating critical machines and critical paths. Finally, the developed model is verified by an exact solver CPLEX, and the comparison results exhibit that CPLEX is effective for instances with ten jobs. For the instances with more than ten jobs, the developed algorithm wins CPLEX in terms of computation accuracy and efficiency, signifying its excellent performance in finding better solutions. Furthermore, four meta-heuristics mentioned above and three state-of-the-art meta-heuristics are employed for comparisons in solving a set of benchmark test instances. The results confirm that the formulated model and algorithm have stronger competitiveness in handling the considered problems.

Design Maintenance System on Mixer Machine to Prevent the Breakdown Using Reliability Centered Maintenance

Equipment, machinery, and labor are fundamental assets of an organization. Therefore, companies must have an appropriate and scheduled maintenance system. However, many manufacturing companies neglect maintenance, leading to frequent machine breakdowns that can result in machine downtime and financial losses. This research aims to determine the machine maintenance interval and the types of actions to be taken. The method employed is Reliability Centered Maintenance with the Failure Mode and Effect Analysis approach to identify failure patterns in a system and formulate the best strategies for designing a maintenance system. The results indicate that the CS-20 Type B mixer is the most critical machine, which can significantly reduce the company's production output due to machine downtime during the repair process. Based on the Reliability Maintenance method, the maintenance interval for components with potential failures is 273.17 hours for the bearing component, experiencing breakdowns three times with the highest damage occurrence within one year.

Critical Climate Machine: A Visual and Musical Exploration of Climate Misinformation through Machine Learning

Critical Climate Machine: A Visual and Musical Exploration of Climate Misinformation through Machine Learning

Accelerated evaluation of blocking flowshop scheduling with total flow time criteria using a generalized critical machine-based approach

Despite the considerable advances in the research of the blocking flowshop scheduling problem (BFSP), several unresolved challenges persist. Algorithmic complexity presents hurdles. Although the insertion-based method is considered to generate superior solutions, its high computational demand diminishes the efficiency of algorithms, especially within large-scale sequences. The existing accelerated evaluation methods cannot utilize the existing information to quickly calculate the total flow time or the total tardiness time of the changed sequence after the job insertion, but recalculates it from scratch. This does not significantly reduce computational effort and needs to be further improved.In this paper, we delve into the intrinsic features of these challenges, proposing a generalized accelerated critical machine-based evaluation tailored for the total flow time and tardiness criteria of the BFSP with and without sequence-dependent setup times. First, we propose three theorems, one corollary, and their proofs based on the critical machine. Second, we propose the accelerated evaluation procedure based on these theorems to calculate the objectives related to the total flow time. Third, we also extend the proposed accelerated evaluation method to the BFSP with sequence-dependent setup times, aiming to significantly reduce the time complexity. Finally, we conduct four experiments on five well-known benchmarks (a total of 3540 test instances). Through statistical analysis, it becomes evident that our computational efforts have significantly decreased in computing both the total flow time and the total tardiness time. This performance enhancement is superior to the effectiveness of existing acceleration techniques.

Theoretical analysis and methods of rapid evaluation: Solving the blocking flowshop group scheduling problem with the total flow time and total tardiness time criteria

For the blocking flowshop group scheduling problem (BFGSP), this study addresses its high computational burden associated with insertion operations due to over-much objective function calculations as the number of groups and jobs increases. Unfortunately, the existing rapid evaluation methods exhibit limitations when handling group-based insertion, blocking constraint, total flow time, and total tardiness time criteria. We emphasize the need for improved rapid evaluation techniques tailored to these limitations and propose the theoretical analysis and methods of a critical machine-based rapid evaluation for total flow time and tardiness criteria of BFGSP. More specifically, first, under the two scenarios of the group and job scheduling, we propose the concept of the critical machines, three theorems, one corollary, and their corresponding proofs, respectively. Secondly, we present rapid evaluation methods for group insertion and job insertion, respectively, namely Rapid_group and Rapid_job based on the above theorems and corollary. We find that it is unnecessary to start the computation from the first machine when scheduling the changed groups or jobs, and it suffices to begin the computation from the critical machine, thus reducing the computational cost. Finally, we conduct five experiments on four well-known benchmarks (a total of 6000 instances). Through statistical analysis, it becomes evident that our computational efforts have decreased significantly in computing both the total flow time and the total tardiness time for group-based and jobs-based insertion operations. The development of rapid evaluation mechanisms is a promising approach to mitigate the time complexity by reducing the number of machines involved in the evaluation, and makes up for gaps in existing accelerated evaluation methods for BFGSP.

Lumen Prize

Abstract The Lumen prize BCS Futures award 2023 went to Gaëtan Robillard's for his Critical Climate Machine. Here we explore the project and its inspiration.

Optimization of preventive maintenance on critical machines at the Sabiz 1 plant using Reliability-Centered Maintenance method

Maintenance planning is the first step in an industry, especially when it comes to the trade-off between cost and reliability, which is the reason for this research's aim. The Reliability Centered Maintenance (RCM) method will be used in this research to optimize maintenance activity in critical machines at the Sabiz 1 plant to minimize downtime, costs incurred for machine repairs, and production losses. The tools of RCM that will be used such as FMEA to determine critical machines as the focus of analysis, a Fishbone Diagram to determine the causes of failure, an RCM worksheet to get preventive activities, and a statistical distribution approach to obtain appropriate preventive activity intervals. The result of data processing shows that all data has a lognormal distribution and can be continued using the lognormal distribution method. The results of this analysis are the preventive maintenance activities proposal and their intervals as a reference for Sabiz 1 plant maintenance planning. The preventive maintenance plan for three critical machines is the high-pressure pump is four days of inspection activities and two days for replacement activities; for the powder, base conveyor is four days of checking activities and 17 days for replacement activities; and for the extraction tower fan for inspection, activities is seven days. The prediction of the implementation impact of this maintenance planning will save maintenance costs around 70% compared to historical costs.

Advanced diagnostic techniques for turbo compressors: A spectral analysis approach for preventive maintenance

This paper introduces an innovative spectral analysis control approach aimed at monitoring and diagnosing machine malfunctions to prevent potential failures. The research was conducted on a critical machine in a major industrial enterprise. The proposed method involves the use of a new indicator, called Overall Level (OL), that evaluates the machine’s condition before any operation. This study showcases practical methodologies for transitioning from time-based maintenance to predictive strategies, furnishing actionable insights into machine condition. This yields tangible advantages for the industry in terms of optimizing maintenance practices and enhancing asset productivity. Additionally, various methods, including vibration analysis, performance monitoring, and data analysis, are employed to identify the causes of issues and recommend solutions to enhance the reliability of the turbo compressor. The results provide a clear representation of the machine’s vibration state for diagnostic purposes. This noteworthy intervention underscores the potential of incorporating the measured and calculated values of the OL indicator across three specifically chosen frequency bands. To achieve this objective, the average value is employed as an indicator, contributing to the enhancement of reliability and longevity of critical industrial machinery. In this context, the novelty of the findings resides in the advanced diagnostic capabilities of the turbocompressor, thereby augmenting the efficacy of condition-based preventive maintenance for the BP 103 J turbine. The ultimate goal is to extend the equipment’s lifespan, improve the efficiency of the rotating machinery fleet, reduce maintenance costs, and enhance parameters such as availability and reliability through the support of an electronic maintenance system.

Optimizing Stainless Steel Bearings: Enhancement of Stainless Steel Bearing Fatigue Life by Low-Temperature Forming

A proposed low-temperature forging method is presented to enhance stainless steel bearings by creating a martensitic subsurface layer, significantly boosting bearing fatigue life due to increased surface hardness. This technique induces beneficial residual stresses, particularly in axial bearings, streamlining their construction and improving machine elements. Challenges persist, especially with radial bearings, but simplicity in axial bearing forging promotes compact, resource-efficient facility construction. Future research will focus on applying this technique to axial bearing washers, potentially replicating success in other bearing components. Despite the energy expenditure on cooling during forging, the substantial increase in bearing fatigue life offsets this, enhancing overall durability and reliability of critical machine components. Integration of this forging technique into bearing fabrication appears seamless, offering a promising trade-off between energy use and enhanced performance.

Implementing Industry 4.0: An In-Depth Case Study Integrating Digitalisation and Modelling for Decision Support System Applications

The scientific community has shown considerable interest in Industry 4.0 due to its capacity to revolutionise the manufacturing sector through digitalisation and data-driven decision-making. However, the actual implementation of Industry 4.0 within complex industrial settings presents obstacles that are typically beyond the scope of mainstream research articles. In this paper, a comprehensive case-study detailing our collaborative partnership with a leading medical device manufacturer is presented. The study traces its evolution from a state of limited digitalisation to the development of a digital intelligence platform that leverages data and machine learning models to enhance operations across a wide range of critical machines and assets. The main business objective was to enhance the energy efficiency of the manufacturing process, thereby improving its sustainability measures while also saving costs. The project encompasses energy modelling and analytics, Fault Detection and Diagnostics (FDD), renewable energy integration and advanced visualisation tools. Together, these components enable informed decision making in the context of energy efficiency.

Machinery health prognostic with uncertainty for mineral processing using TSC-TimeGAN

Deploying health state (HS) assessment and remaining useful life (RUL) prognostic on the industrial equipment can effectively avoid shutdown and reduce productivity losses. This paper proposes a temporal self-clustering (TSC) and time-series generative adversarial network (TimeGAN) based uncertainty-aware health prognostic algorithm for the hydrocyclone, a critical machine in the mineral processing. To label the HS of degradation data, an autoencoder based TSC algorithm is proposed. It integrates the extraction and clustering of health indicators into a unified framework, so that the correlation information between feature extraction and clustering can be captured for cluster analysis. A Benders decomposition based optimization approach is designed to synthetically optimize network weights and clustering centers, thereby extracting and labeling data features more reasonably. For quantifying prediction uncertainty, an uncertainty-aware prognostic algorithm is proposed to predict the RUL distribution, and the uncertainty can be quantified as the standard deviation (Std) of the distribution. Furthermore, a mechanism and TimeGAN fusion temporal sequence generation algorithm is proposed to augment the degradation process sequences of the equipment. Verification experiments using the actual data show that the proposed algorithm can effectively evaluate the HS of the equipment and provide a sensible and convincing RUL prediction.

Minimization of Root Causes of Declining Productivity in a Manufacturing Company: A Case Study of Jocalis Company

This presents a comprehensive methodology employed to identify and address declining productivity issues within the JOCALIS Aluminium Roofing Sheet Manufacturing Company Limited, situated in Onitsha, Nigeria. The study encompasses various manufacturing divisions, with a primary focus on aluminium roofing sheet production of three lines involve in production of red, black, and milk colour coated roofing sheet. The research aims to uncover the root causes of defects in the manufacturing process and develop effective strategies for improvement. Key methods include data collection through interviews, company records, library research, and internet sources, followed by data analysis and root cause identification. From the result obtained, the average availability of critical machine like the roller machine after root cause analysis is increased by 10.62%. Also, the average MTBF (mean time between failure) of the critical machine after root cause analysis is increased by 13.66% and MTTR (mean time to repair) is decreased to 46.42% respectively. The applications and general impact of this study includes enhancing machine availability, reducing downtime, increasing efficiency, optimizing maintenance practices, implementing preventive maintenance schedules, improving equipment diagnostics, and prioritizing root cause analysis to reduce breakdowns.

Shifting roles and slow research: children’s roles in participatory co-design of critical machine learning activities and technologies

ABSTRACT Including children’s voices in the design of learning activities and technologies has increasingly become a subject of conversation among researchers and learning designers. Research suggests children have lived experiences that position them as useful contributors in co-designing curricula activities or technologies they will use. However, one significant challenge in participatory co-design is engaging children in the co-design of curricula when they have not yet learned the disciplinary content within the curricula. We present our two-year participatory design-based research study in which we co-designed a Critical Machine Learning educational programme with different groups of children at two after-school centres over two consecutive years. In this paper, we characterize the roles children embodied in two cycles of participatory co-design and how the program's activities impacted these roles. Findings in this study suggest that in two participatory design-based research cycles, children embodied different roles of tester, informant, or designer of both AI learning activities and AI technologies. Based on this design-based research study, we propose that a ‘slow research’ approach that emphasises trust-building and a deep understanding of children's perspectives can be instrumental in achieving meaningful co-design outcomes.

Optimizing Footwear Manufacturing Through Defect Analysis and Spare Parts Optimization

This study investigates the causes of defects in the production line of inlay soles in footwear manufacturing, focusing on the impact of malfunctioning machine spare parts. Using Failure Mode and Effects Analysis (FMEA), critical machines—splitting, cutting, and moulding—are identified, along with their associated spare parts influencing defect occurrence. Process FMEA (PFMEA) prioritizes actions based on discussions with maintenance managers and quality staff. Results highlight top spare parts affecting defects, such as Fertinak, grinding stone, and V-belt for the splitting machine; hydraulic motor, hydraulic seal, and hydraulic filter for the cutting machine; and Solid State Relay, Thermocouple, and Heater for the moulding machine. These findings underscore the importance of maintaining machine performance and addressing spare part malfunctions to enhance product quality and operational efficiency in footwear manufacturing, providing actionable insights for industry practitioners. Hightligh: Critical Machines Identified: Splitting, cutting, and moulding machines analyzed for defect occurrence. Spare Parts Influence: Fertinak, Solid State Relay impact defect occurrence. Practical Industry Insights: Strategies for improving product quality and efficiency highlighted. Keywords: Defect analysis, Footwear manufacturing, Spare parts, Failure Mode and Effects Analysis (FMEA), Product quality.

Structural basis of the human NAIP/NLRC4 inflammasome assembly and pathogen sensing.

The NLR family caspase activation and recruitment domain-containing 4 (NLRC4) inflammasome is a critical cytosolic innate immune machine formed upon the direct sensing of bacterial infection and in response to cell stress during sterile chronic inflammation. Despite its major role in instigating the subsequent host immune response, a more complete understanding of the molecular events in the formation of the NLRC4 inflammasome in humans is lacking. Here we identify Bacillus thailandensis type III secretion system needle protein (Needle) as a potent trigger of the human NLR family apoptosis inhibitory protein (NAIP)/NLRC4 inflammasome complex formation and determine its structural features by cryogenic electron microscopy. We also provide a detailed understanding of how type III secretion system pathogen components are sensed by human NAIP to form a cascade of NLRC4 protomer through a critical lasso-like motif, a 'lock-key' activation model and large structural rearrangement, ultimately forming the full human NLRC4 inflammasome. These results shed light on key regulatory mechanisms specific to the NLRC4 inflammasome assembly, and the innate immune modalities of pathogen sensing in humans.

The impact of technological parameters of electrolytic-plasma treatment on the changes in the mechano-tribological properties of steel 45

<p>This article presents the results of research on the effects of electrolyte plasma hardening on the structure, phase composition, tribological, and mechanical properties of medium-carbon structural steel 45, which is widely used in the manufacturing of tools and machine parts. Hardening experiments were conducted using an electrolyte plasma hardening setup with electrolytes varying in sodium carbonate (Na<sub>2</sub>CO<sub>3</sub>) concentration in distilled water (15%, 20%, and 25%). With a consistent heating duration of 4 s during quenching, significant phase changes in the steel's microstructure were observed, enhancing hardness and wear resistance. The transformation of the initial structure of steel 45, which consists of ferrite and pearlite into martensite on the surface of the samples, led to an increase in microhardness up to 506–690 HV<sub>01</sub>. This value is 2.5–3.5 times higher compared to the untreated sample, and the thickness of the hardened layer reached up to 3.2 mm. Additionally, wear volume measurements showed that after electrolyte plasma hardening, the wear resistance of the samples increased by 1.3–1.5 times (2.01 × 10<sup>−4</sup>, 2.26 × 10<sup>−4</sup> m<sup>3</sup>). The obtained results on the changes in microstructure and mechano-tribological properties of steel 45 confirm the potential of electrolyte plasma hardening technology for improving operational characteristics and extending the service life of heavily loaded and critical machine parts.</p>

Attribute Subspace Partitioning with Neural Regression for Contextual Outlier Detection

Outlier detection is a critical machine learning task, especially when dealing with context-driven outliers. Such outliers usually remain undetected by conventional detection methods. Detecting these specific outliers requires deep domain knowledge. This paper introduces an innovative approach to contextual outlier detection, leveraging a hybrid method that combines a neural network-based regression model with traditional techniques. The proposed method enables precisely distinguishing contextual outliers by employing attribute subspace partitioning. The proposed algorithm effectively separates anomalous data points by integrating domain knowledge on attribute-specific contextual behavioral deviations with standard outlier detection methods. This experiment exhibits the effectiveness of the proposed method across five real-world datasets, yielding a notable enhancement in the range of 22% to 45% in the AUC score.

Technical Evaluation and Financial Analysis of a Retrofitting Investment Project for Production Machinery in a Cement Plant

In today's rapidly evolving industrial landscape, businesses are increasingly challenged to strike a balance between enhancing productivity and maintaining product quality. Company X, a renowned cement manufacturer in Indonesia, relies heavily on four key raw materials, among which clay is particularly crucial for the raw mix. Recent trends have shown a decrease in the Al2O3 composition of clay, necessitating adjustments in clay capacity to uphold quality standards. A thorough technical evaluation of the plant highlighted that a significant number of critical machines, totaling 17, were operating with mechanical availability below the desired threshold. Additionally, a utility analysis pinpointed a shortfall in meeting the required clay tonnage, leading to the identification of machines that would benefit from retrofitting. The financial implications of this initiative were substantial, with the initial investment for the upgrades and subsequent operational costs in the first year being considerable. Yet, this expenditure was offset by a notable profit in the first year post-retrofitting. Key financial metrics further underscored the project's viability: a highly favorable Net Present Value (NPV), an impressive Internal Rate of Return (IRR), a rapid Payback Period (PP), and a significant Profitability Index (PI). These parameters, derived from an exhaustive analysis, clearly support the strategic decision to invest in retrofitting the production machinery at Company X's cement plant, illustrating the project's feasibility and the prospective benefits of this investment.