Production Maintenance Research Articles

A hybrid deep learning approach to integrate predictive maintenance and production planning for multi-state systems

This paper develops a data-driven approach to dynamically integrate tactical production and predictive maintenance planning for a multi-state system composed of several series-parallel machines. The objective is to determine an integrated lot-sizing and preventive maintenance strategy that will minimize the sum of maintenance and production costs, while satisfying the demand for all products over the entire horizon. A rolling horizon planning strategy is adopted to continuously update the production and maintenance plans based on new data obtained through sensors. Unlike the existing integrated models, we develop a hybrid deep learning (DL) approach to coordinate maintenance and production decisions for a multi-state system composed of multiple machines. To accurately predict the health condition of each machine, the developed hybrid DL method combines the powers of convolutional neural network (CNN), long-short-term memory (LSTM), and attention technique. We use multi-state reliability theory to estimate the production capacity. Furthermore, a genetic algorithm is developed to solve large-scale problems. Benchmarking data are used to compare the results of our data-driven approach with a model-based approach, a pure LSTM, and a CNN-LSTM approach. This comparison is based on prediction accuracy, solution quality, and computational time. The obtained results show the superiority of the suggested CNN-LSTM-attention data-driven framework integrating maintenance and production.

Managing Operations and Supply Chains in Automotive Industry

Profitability, customer satisfaction, and innovation in the cutthroat automobile industry depend on well-managed operations and supply networks. Managing operations and supply chains in the automotive industry is complex, and this paper lays forth a comprehensive framework for doing so. An integral part of effective operations management in the automotive industry is demand forecasting and planning. Using collaborative forecasting methodologies, market trend analysis, and advanced analytics, automotive manufacturers can improve production schedules, minimize inventory costs, and foresee changes in demand. Reducing waste, enhancing process efficiency, and managing low inventory levels are all achieved through the use of lean manufacturing techniques like Just-in-Time (JIT) production and Total Productive Maintenance (TPM). Collaboration with suppliers, uninterrupted material flow, and supply chain innovation can all be achieved through supplier relationship management (SRM). Automakers may enhance product quality, cut costs, and lessen supply chain risks by communicating openly, working together to improve processes, and forming agreements that benefit all parties involved. Automobile companies can't afford to have any product flaws that damage their reputation or the loyalty of their customers, which is why quality management is so important in this industry. Statistical Process Control (SPC), Failure Mode and Effects Analysis (FMEA), and Six Sigma are a few of the rigorous quality control methods that manufacturers use to find and rectify flaws early

Effects of soil erosion–deposition on corn yields in the Chinese Mollisol region

Soil erosion is a major challenge for crop production maintenance and improvement in agricultural regions worldwide. However, quantifying the impacts of soil erosion rate on crop yield has not been carried out often, and there are few reports on impacts of soil deposition crop yields, especially in the Chinese Mollisol Region. Thus, this study quantified soil erosion–deposition rates (SEDRs) at three agricultural catchments in the Chinese Mollisol region using the 137Cs technique and assessed soil erosion–deposition impacts on corn (Zea mays L.) yield. The results showed that SEDRs varied from −5471.7 (deposition) to 9956.0 (erosion) t km−2 yr−1. The distributions of both soil erosion and deposition in the three catchments were in coexistence, but soil erosion was dominant. In addition, above 2500 t km−2 yr−1 of soil erosion rates (larger than slight erosion rates) in the three catchments accounted for 41.0 %, indicating that soil erosion was severe. Moreover, corn yields in the three catchments ranged from 1.9 to 14.6 t ha−1. Compared with deposited sites, corn yields in eroded sites were 19.2 %–40.6 % lower. Furthermore, when soil erosion rates were moderate (2500–5000 t km−2 yr−1), corn yields were 32.4 % lower than those in non-eroded sites. The spatial distribution of corn yield was opposite to that of soil erosion rate at catchment and slope scales. The relationship between corn yields and soil erosion rates had a negative linear relationship (p < 0.01), which was validated with acceptable accuracy. There was a positive linear relationship between corn yields and soil deposition rates without statistical significance (p > 0.05). These findings are valuable for assessing how soil erosion–deposition affects crop yields to implement countermeasures for controlling soil erosion and maintaining sustainable agricultural development.

A hybrid design for jointly optimizing production scheduling, control chart design and maintenance in continuous flow manufacturing

Integrating the three crucial functions of quality control, economic production quantity (EPQ) and maintenance leads to cost savings and increased efficiency for manufacturing processes. While in the literature, they have typically been studied separately. Moreover, most of the existing integration models are designed for the discrete piece-part manufacturing environment. This study, nevertheless, focuses wholly on continuous flow manufacturing (CFM), which is distinctly different from piece-part manufacturing, as the sampling unit is described in light of laboratory requirements instead of the production unit. Based on this fact, this paper proposes an integrated EPQ scheme jointly designed with control-chart design and maintenance planning for the CFM process. A developed genetic algorithm is employed to minimize the expected total production cost under constraints on the economic-statistical quality. Of the costs considered, quality-related costs are quantified via an approximate formula derived from the quality loss curve depending on Taguchi’s quality loss function. A sensitivity analysis is performed on the expected total production cost and variations in the chosen system parameter values to offer insights into the issue. Finally, a comparative investigation of the suggested model and two similar models that contributed to this field is conducted.

Study on the Alkali-Free Three-Component Flooding System in the Daqing Oilfield.

ASP flooding is an important method to further improve oil recovery by a large margin. At present, it has entered the stage of industrial application, but there are still problems of scaling in the injection production system and high production maintenance costs. Based on the industrialized mature technology of weak alkali ASP flooding, sodium chloride is used to replace sodium carbonate, and the alkali-free three-component flooding (TC) system in the Daqing Oilfield is developed by mixing with petroleum sulfonate and partially hydrolyzed polyacrylamide. Based on the experiments of viscosity increasing, interface performance, stability, adsorption, and oil displacement effect, the differences between the alkali-free TC system and the weak alkali ASP system are compared and analyzed. The laboratory research results show that both systems are basically the same in terms of viscosity, viscoelasticity, shear resistance, interfacial activity, stability, and flowability. Due to the lack of alkaline water, the adsorption, emulsification, and oil displacement performance of the alkali-free TC system is slightly lower than that of the weak alkali ASP system. The recovery factor of core flooding can be increased by 27.31% over water flooding, which is 2.56 percentage points lower than that of the weak alkali ASP system. On the premise of the same 1% EOR effect, the agent cost of the alkali-free system is 17.02% lower than that of the alkali ASP system. This article innovatively verifies the feasibility of using NaCl instead of Na2CO3 and explains the mechanism of significantly improving oil recovery in composite systems under alkali-free conditions from the ion level. However, the emulsification effect of the alkali-free TC system is relatively weak. The next step of research would be to consider adding an E-surfactant to enhance the emulsification performance of the composite system. By improving the system composition, technical references are provided for the efficient development of other terrestrial sandstone oilfields.

A Collaborative Scheduling Algorithm for Real-Time Production and Opportunistic Maintenance Under Cloud Manufacturing Paradigm

A Collaborative Scheduling Algorithm for Real-Time Production and Opportunistic Maintenance Under Cloud Manufacturing Paradigm

UNDERSTANDING GOVERNMENT AGRARIAN PROGRAMS AND SMALLHOLDER PERSPECTIVES ON FOREST COVER DYNAMICS IN MEXICO’S MESOAMERICAN BIOLOGICAL CORRIDOR*

ABSTRACT Agrarian programs implemented since the 1990s in Mexico (for example, PROCAMPO, a cash transfer program to increase production) often promote agricultural intensification, permanent land use, and regulations for shifting agriculture, making broad claims that these practices improved livelihoods and supported forest conservation. Meanwhile, smallholders in Mexico’s Mesoamerican Biological Corridor interpreted and implemented federal program goals based on their own experiences of how local land use supports sustainable production and forest maintenance. This paper examines if one community’s understanding of land use, forest cover dynamics aligns with that of Mexico’s recent federal agroforestry program, Sembrando Vida (“sowing life”). Using in-depth discourse analysis of agrarian program documents and smallholder interviews, we highlight a misalignment between federal agricultural programs and smallholder perspectives over land use and forest cover dynamics. Implications include increased forest fragmentation and loss of access to regions of traditional land use, suggesting a need for meaningful and inclusive smallholder engagement throughout agrarian program development.

Digital Twin of a Water Supply System Using the Asset Administration Shell.

The concept of digital twins is one of the fundamental pillars of Industry 4.0. Digital twin allows the realization of a virtual model of a real system, enhancing the relevant performance (e.g., in terms of production rate, risk prevention, energy saving, and maintenance operation). Current literature presents many contributions pointing out the advantages that may be achieved by the definition of a digital twin of a water supply system. The Reference Architecture Model for Industry 4.0 introduces the concept of the Asset Administration Shell for the digital representation of components within the Industry 4.0 ecosystem. Several proposals are currently available in the literature considering the Asset Administration Shell for the realization of a digital twin of real systems. To the best of the authors' knowledge, at the moment, the adoption of Asset Administration Shell for the digital representation of a water supply system is not present in the current literature. For this reason, the aim of this paper is to present a methodological approach for developing a digital twin of a water supply system using the Asset Administration Shell metamodel. The paper will describe the approach proposed by the author and the relevant model based on Asset Administration Shell, pointing out that its implementation is freely available on the GitHub platform.

Utilization of Augmented Reality Technology in Independent Speech Therapy Applications

One of the uses of information technology is augmented reality technology in the health sector. Augmented reality is used in the development of applications that are used for speech therapy for children with autism or children with speech delays. The method used for the development of speech therapy applications is the extreme programming method. This method can adapt to the development of an application in a short time and quite a lot of changes. The stages in the extreme programming method include identifying system requirements, planning activities during system/application development, system development process, iteration for system improvement until the final iteration, and no more user feedback, system/application production, and system maintenance with data backup and system recovery. After testing the system, it was concluded that three iterations occurred during the development of the speech therapy application. The last test showed that the user accepted the speech therapy application with a percentage of 77,14%. The output of this research is an augmented reality-based speech therapy application that is useful for independent speech therapy for children with speech delays.

Standardization of the preparation of a herbo-mineral formulation Shwasakasari Rasa

Shwasakasari Rasa is mentioned in Rasa Yoga Sagar,[1] (part 2) as a remedy of Shwasa &amp; Kaasa Roga. This type of Rasa Aushadhi are more effective against bacteria. These drugs have a multi dimension effect like Broad-spectrum antibiotics. In this study an endeavor has been made to determine standard procedure for preparation of the research formulation i.e. Shwasakasari Rasa. SOPs (Standard Operating Procedure) for pharmaceuticals are associated with quality assurance, internal control, production maintenance, utility and human resources or also defined as established or prescribed methods to be strictly followed for the preparation of particular formulations by a selected method. In this section of the research study all the processes adapted for the preparation of Shwasakasari Rasa are well elaborated with explicit detail of quantity, duration, heating pattern, temperature, material &amp; methods together with timely observed and recorded values. Therefore, Shwasakasari Rasa was prepared in the department &amp; analyse all contents present in Rasa Aushadhi for the establishment of drug for the benefit of society and mankind.

Different Induction Motor Faults by New Proposed Random Forest Method

Induction motors (IM) are widely used in industry. Failures in asynchronous motors cause disruptions and interruptions in production processes. Due to this situation, economic losses are experienced. Monitoring the induction motor status and monitoring the symptoms before the failure occurs is a matter of great importance in the industry. In this study, 8 different situations that may occur in the motor were monitored through the acceleration and sound data obtained from the induction motor. The feature vector was created with the Short-Term Fourier Transform (STFT) method on the acceleration and sound data obtained from the engine. The feature vectors were classified using the Random Forest (RF) method. The feature vectors created from the acceleration and sound data were also analyzed separately and the classification performance was examined. In addition, a new RF algorithm based on weight values using the Gini algorithm has been proposed. With this algorithm, the traditional RF algorithm has been developed and the success rates have been increased. In classical RF classification based on acceleration and sound data, 89.9% accuracy was achieved. The success rate of the proposed model was 95.7%. This shows that the proposed model successfully detects all types of faults in asynchronous motors. In addition, when we compared in terms of time, it was observed that the proposed model produced faster and more accurate results both in fault detection and in the production maintenance phase.

Proposal of a Framework for Evaluating the Importance of Production and Maintenance Integration Supported by the Use of Ordinal Linguistic Fuzzy Modeling

Over the years, the integration of Production Management and Maintenance Management has gained significant attention from the scientific community due to its benefits for the company. When searching through the states of the art and practice, it is possible to understand that one of the main challenges for the integration is the lack of systematic, methodological, and scientific approaches and evaluation systems that lead companies into a successful implementation and a clear understanding of the benefits and drawbacks of the process. This paper introduces an original framework that conducts the processes of evaluation, weighting, and aggregation of set of novel indicators proposed by the authors. The main output of the proposal is an integral index that allows us to qualify, in a linguistic domain, the importance of the Production and Maintenance Management integration. At the same time, the proposed framework includes a methodology to evaluate the consensus of the experts, based on the use of linguistic terms with a membership function of the triangular type, which attempts to overcome some deficiencies of previous models identified by the authors in a detailed and complex analysis of the scientific literature. The proposed framework is applied in a plant of the Cuban mechanical industry. The results of this application are clearly presented and discussed, allowing us to verify and validate the proposal while also contributing to its ease of understanding and ultimately to the successful integration of the production and maintenance tasks in the given company.

Bi-objective flexible job shop scheduling on machines considering condition-based maintenance activities

This paper investigates multi-objective flexible job shop scheduling considering maintenance activities. The condition-based maintenance strategy is used to reduce machines breakdown. After maintenance activities are completed, the machine degradation model’s parameters are updated using Bayesian inference to make it more realistic. A novel multi-objective evolutionary algorithm is designed to address the multi-criteria scheduling problem. An innovative insertion algorithm is proposed in this paper to balance production plan and maintenance activities. According to the experimental results, the designed evolutionary algorithm performs better than the other two traditional algorithms, and the insertion approach can reduce the impact of maintenance activities on production plan by up to 200%.

Simultaneous Production Scheduling and Maintenance in Multi-Stage Production Systems: A Synergic Approach

Simultaneous Production Scheduling and Maintenance in Multi-Stage Production Systems: A Synergic Approach

Exploring the Importance of Trace Elements in Nutrition: Understanding Their Vital Role in Health and Well-being

Trace elements despite being needed in extremely small amounts, trace elements are essential for many body’s physiological processes. The relevance of trace elements in human nutrition is examined in this abstract, which also conclude their functions in immunological response, hormone production, enzyme activity, and tissue structure maintenance. It is crucial to maintain a balanced intake of these nutrients since deficiencies or excesses of them might have negative effects on one's health. People can get these trace elements—which are necessary for general health—by eating a varied and nourishing diet. The complex functions that trace elements play in human health are still being uncovered by ongoing research, which emphasises how important it is to comprehend and maximise their presence in our diets. To provide accessibility to essential micronutrients and to promote optimal health, trace elements must be included in dietary recommendations.

Integrating production and maintenance planning in process industries using Digital Twin: A literature review

Among the Industry 4.0 technologies transforming manufacturing environments, the Digital Twin (DT) technology is gaining attention as a driver for improving manufacturing performance and a platform to enhance collaboration. While the advantages of leveraging DT for supporting decision-making in production planning and maintenance planning are recognized, research taking an integrated perspective is scarce. In addition, besides the growing trend, recent studies highlight the limited adoption of DTs in process industries, emphasizing the necessity to address the unique features of their production processes. Through a literature review, this paper points out the main obstacles encountered during the implementation of DT in process manufacturing industries, as well as shows the research gap in exploiting DT to support the integration of decisions concerning production and maintenance and underscores the need for further investigation in this direction to discover its full potential.

A hybrid CNN-LSTM model for joint optimization of production and imperfect predictive maintenance planning

A hybrid CNN-LSTM model for joint optimization of production and imperfect predictive maintenance planning

An interpretable horizontal federated deep learning approach to improve short-term solar irradiance forecasting

Solar irradiance forecasting is critical in the planning and operation of solar power plants for production scheduling, energy trading, and maintenance planning. Accurate solar irradiance forecasting is crucial for efficient and stable power systems. Various deep learning (DL) methods have been researched in solar irradiance forecasting because of their powerful capabilities of nonlinear mapping. However, traditional DL models face challenges with small sample sizes, irradiance fluctuations, and data privacy concerns. On this foundation, it is also critical to ensure the interpretability of artificial intelligence (AI) models, as interpretable and trustworthy predictive models can help operators make effective decisions. Focusing on the above-mentioned issues, a privacy-preserving, interpretable, and DL-based model is proposed to improve the forecast accuracy of solar irradiance while ensuring the data available but not visible to each participant and prediction comprehensibility. This model is constructed by horizontal federated framework (HFF), self-attention (SA) mechanism, convolutional neural network (CNN), and long short-term memory (LSTM) network, named HFF-based SA-CNN-LSTM. A series of comprehensive experiments spanning various climate regions are designed to assess model performance under different federated conditions. The experiments show that this method significantly improves forecasting accuracy, especially in scenarios with incomplete data and highly fluctuating irradiance when federated with other datasets, and the model exhibits interpretability, adjusting attention for precise predictions at different time points. Moreover, the effects of different federated scales on the predictive performance of the target model are fully discussed for future practical applications. These findings hold significant promise for enhancing the accuracy of irradiance forecasting, contributing to energy efficiency, grid stability, and data privacy.

Smart manufacturing system based on industrial internet of things

The primary challenge in the manufacturing industry today is the subpar productivity and efficiency in production processes. This predicament can be attributed to the widespread utilization of suboptimal production systems and the underutilization of advanced technology in manufacturing. Furthermore, the lack of accurate production data, limited employee involvement in production processes, and the high costs associated with production and machine maintenance have emerged as significant concerns in the contemporary manufacturing landscape. In response to these challenges, the adoption of Smart Manufacturing Systems (SMS) based on the Industrial Internet of Things (IIoT) has become crucial to address these issues andenhance overall production quality and efficiency. The SMS IIoT system empowers companies to gather real-time data from various industrial devices and machines. This data is subsequently analyzed to optimize production processes, resulting in increased efficiency and productivity. With this system in place, companies can closely monitor production processes in real-time and promptly detect and address defective or non-compliant products at the onset of production. The research results show an availability value of 88%, indicating that the machine operates 88% of the scheduled time. A Performance value of 100% indicates that the engine is operating at the desired maximum speed. OEE is calculated as the product of Availability, Performance, and Quality of Rate. With a value of 88%, OEE reflects the overall level of effectiveness of the machine in the production process. This paper highlights the significance of IIoT-based Smart Manufacturing Systems in addressing the prevailing challenges encountered by the manufacturing industry.

Integration of production–maintenance planning and monitoring simple linear profiles via Hotelling's T2 control chart and particle swarm optimization

This paper introduces an integrated model that merges three key concepts: quality control through linear profile monitoring using Hotelling's T2 control chart, production cost evaluation, and maintenance policies. The objective function of the integrated model is to minimize total costs. This study is the first to jointly consider production and maintenance costs in the framework of profile monitoring using Hotelling’s T2 control chart for linear profiles without compromising on the versatility of simple linear profiles as a modeling tool, particularly in calibration applications. Appropriate assumptions are made for the proposed integrated model and the particle swarm optimization algorithm is implemented to determine decision variables. To evaluate the effectiveness of the integrated model, a numerical example and a comprehensive comparative analysis are conducted. Moreover, a sensitivity analysis to study the effects of various input parameters on the optimal solutions is performed. The findings suggest that adopting the integrated model with specific decision variables results in lower expected total costs when compared to the joint model and fixed parameter schemes.