Satisfy Customer Demand Research Articles

Leveraging variational autoencoders and recurrent neural networks for demand forecasting in supply chain management: A case study

Accurate demand forecasting is key for companies to optimize inventory management and satisfy customer demand efficiently. This paper aims to Investigate on the application of generative AI models in demand forecasting. Two models were used: Long Short-Term Memory (LSTM) networks and Variational Autoencoder (VAE), and results were compared to select the optimal model in terms of performance and forecasting accuracy. The difference of actual and predicted demand values also ascertain LSTM’s ability to identify latent features and basic trends in the data. Further, some of the research works were focused on computational efficiency and scalability of the proposed methods for providing the guidelines to the companies for the implementation of the complicated techniques in demand forecasting. Based on these results, LSTM networks have a promising application in enhancing the demand forecasting and consequently helpful for the decision-making process regarding inventory control and other resource allocation.

Fuzzy-based thermal management control analysis of vehicle air conditioning system

Automotive air conditioning (ACC) system designers faced unique challenges in satisfying customer demands for efficient and comfortable operation across a broad temperature range. The AAC system's effective or fixed temperature setting makes this possible. Many climate control models, like the state flow switching controller in MATLAB control, must handle heating and cooling due to a single Simulink/environment software and frequently contain steady-state error (SSE). The present research proposes to design an automatic temperature control scheme and fuzzy logic control (FLC) for an automotive air-conditioned (AAC) system. In addition, it employs MATLAB Simulink/environment software to model the fuzzy control technique to analyze the AAC system's response. A simulation has been set up to evaluate the suggested system performance to match a selection of user-specified reference temperatures and compressor speeds. Compared with a PID-controlled AAC system, the proposed FLC-based system reduced the undershoot to only 2.30% from 33.30% respectively, and was robust, quicker, and better at controlling temperature.

The effect of market orientation and technology orientation on industry 4.0 technologies and market performance: Role of innovation capability

Today, businesses are facing increasing demands from the customers and strong competitive pressure. Firms must continuously deliver value and satisfy customer demands to survive and maintain growth in the market. In this regard, organizations are implementing Industry 4.0 (I4) technologies to satisfy customer requirements, deliver value and sustain in the market. This study examines how strategic orientations (market and technology orientation) influence firms to adopt I4 technologies, and how I4 technologies can help to deliver customer value and improve firm performance. To this end, the study posits that adoption of I4 technologies develops innovation capability, which can lead to desired performance outcomes (innovation and market performance). The proposed model is examined using survey responses from 154 US industrial firms. Findings show that market and technology orientation have significant effect on adoption of I4 technologies, and partial mediation effect of technology orientation between market orientation and adoption of I4 technologies. Further, I4 technologies help to build innovation capability, which improves performance outcomes. The study provides implications for managers in industrial firms with regard to understanding the key facets of I4 technologies.

An approach to produce healthier meat products: effect of k-carrageenan and inulin on quality characteristics of bologna-type chicken sausages

In order to satisfy customer demand, healthier meat products must be produced; therefore, reformulating meat products with high dietary fiber is an essential approach. The aim of this study was to evaluate the effects of carrageenan and inulin (1:0%, 0:3%, and 1:3%) (w/w) on the quality properties of chicken bologna sausages (with a high content of mechanically separated chicken meat – MSCM) during 90 days of refrigerated storage. The physicochemical, technological, sensorial, and microstructural characteristics of the sausages were evaluated. Sausages with carrageenan showed better water and fat retention and lower cook loss values. The incorporation of carrageenan (1%) increased the hardness of sausages which reduced the sensory acceptance. Microstructure evaluations showed a more regular structure in the treatments containing inulin. The treatment IN3 (containing %3 inulin) and the control sample had similar overall acceptability scores based on sensory evaluations. Our findings suggest that the combination of carrageenan (<1%) and inulin (3%) may have the potential to develop a healthier and more functional formulation with dietary fiber enrichment, and to also minimize the disadvantages of MSCM in chicken sausages.

A CONSUMER SENTIMENT ANALYSIS METHOD BASED ON EEG SIGNALS AND A RESNEXT MODEL

E-commerce is becoming increasingly dependent on technologies such as consumer sentiment research at an ever-increasing rate. Its purpose is to recognize and comprehend the feelings and dispositions of customers by analyzing customer language and behavior as expressed in social media, online reviews, and other forms of digital communication. The proliferation of digital technology has resulted in an increase in the number and variety of channels through which customers can communicate their feelings. Gaining a comprehensive understanding of consumer sentiment may be of great use to businesses, as it enables them to better satisfy customer demands, enhance their products and services, improve their brand reputation, and ultimately increase their level of competitiveness. As a result, consumer sentiment research has evolved into a tool that is essential for the decision-making process in e-commerce as well as the management of customer relationships. Within the scope of this discussion, this study uses deep learning models to improve consumer sentiment research precision. The following is the list of the primary contributions that this paper makes. (1) Advancing the use of EEG signals as a basis for a method for analyzing customer feelings. This technique measures brain activity directly, thus avoiding the restrictions and ambiguities that come with relying on verbal expression. (2) The purpose of this study is to improve the overall performance of the model for analyzing sentiment by incorporating an attention mechanism into the ResNeXt model. This attention mechanism is intended to augment the model’s capacity to extract subtle characteristics. (3) The results of the experiments show that the strategy described in this study is effective in improving EEG-based sentiment analysis performance. When compared to standard text-based sentiment analysis approaches, this sentiment analysis model demonstrates greater objectivity, real-time capabilities, and multidimensionality when applied to consumer sentiment analysis in e-commerce.

Multi-objective continuous review inventory policy using MOPSO and TOPSIS methods

In the dynamic business environment of today, decision-making involves considering various conflicting aspects. Inventory planning problems aim to determine how much and when to order products to satisfy customer demand at the lowest possible cost while maintaining a desirable service level. These problems can be formulated as a MOPSO algorithm, which is used to handle multiple objectives in a continuous review stochastic inventory control system (r, Q). Unfortunately, most multi-objective inventory models have been solved by aggregating objectives using specific weights or by optimizing only one objective and treating the others as constraints. Considering the complexity of real-world inventory control problems, which involves conflicting objectives such as minimizing cost and maximizing service level, the need arises to employ more precise optimizers that can generate better and more diverse non-dominated solutions of reorder point and order size system. In this paper multi-criteria decision-making framework that combines MOPSO algorithm and TOPSIS method to generate a Pareto front of non-dominated solutions and rank them based on decision makers' preferences. Initially, the original MOPSO is applied to the multi-objective inventory control problem, and then the mutation operator is integrated into the MOPSO to maintain diversity in the swarm and explore the entire search space. Next, the leader selection strategy called the geographically-based system (Grids) is replaced by the crowding distance factor to choose the global optimal particle as a leader. Additionally, the ε-dominance concept is employed to limit the archive size and maintain more diversity and convergence in the MOPSO for optimizing the inventory control problem. In conclusion, this work not only pioneers a cutting-edge approach to multi objective inventory control but also underscores its practical value. By facilitating the generation of superior solutions that cater to diverse decision-maker preferences, our methodology resonates deeply with real-world challenges and sets a new benchmark for effective inventory planning.

Upcycling agricultural byproducts into eco-friendly food packaging

This investigation looks at the transformative potential of upcycling agricultural waste to make ecologically friendly food packaging. Agricultural wastes, which are frequently ignored, might be valuable resources in reversing the sustainable destiny of the packaging sector. We review recent research on plant-based byproducts, including proteins, polysaccharides, lipids, pigments, and minerals, that are isolated from agricultural waste. Creating edible and (bio)degradable packaging solutions that can include biobased active components, including flavorings, antioxidants, and antimicrobials, can begin with these compounds. Utilizing plant fibers from agricultural waste reduces environmental contamination while increasing packing efficiency. The review concentrates on packaging solutions that are good for the environment, like edible coatings and films with antioxidant and antibacterial qualities and active packaging made of phenolic chemicals. These innovations, derived from various foods and agricultural waste, satisfy customer demand for premium foods with longer shelf lives. A practical way to lessen the excessive use of non-biodegradable plastics is to create edible materials, especially in light of the global push for sustainability. These formulations can enhance food packaging performance since they are made from biowastes and biopolymers. Our comprehensive research synthesizes existing knowledge to shed light on the extraction, processing, and application of agricultural byproducts in packaging materials. The broad spectrum includes regulatory systems, processing techniques, biodegradability parameters, and the properties of various byproducts. By providing an all-encompassing viewpoint, this evaluation draws attention to current achievements and indicates avenues for more research and development. It provides a roadmap for the ecologically friendly upcycling of agricultural waste into sustainable food packaging, which helps to shift the packaging industry's paradigm continuously.

Economic growing quantity: Broiler chicken in Morocco

In this work, we introduce an innovative mathematical model for growing items, with a particular emphasis on broiler chicken production within the context of Moroccan agriculture. The main goal of this study is to determine the optimal order quantity of items that the inventory should purchase to satisfy customer demand and the corresponding cycle duration. For the first time, a staircase function is used to depict the gradual reduction in item quantities over time due to the mortality during the rearing period. Furthermore, and for the first time, our model incorporates three distinct feeding types—Starter Feed, Grower Feed, and Finisher Feed-bringing it in line with real-world agricultural practices. A numerical example is provided, based on data extended from a Moroccan farm project, along with an analytic solution.

Production Activity Control Framework for the Make-To-Order Industry Utilizing Cyber-Physical Production System

The make-to-order industry has complex production activities due to the varying nature of customer orders. The ability to meet production specifications within agreed time and cost constraints is crucial in satisfying customer demands. Therefore, effective monitoring of production activities is essential. In order to track production activities, this research proposes a Production Activity Control Framework using the Cyber-Physical Production System. The proposed framework enables precise monitoring of 1) machine activities, which include idle, setup, and processing times, and 2) operator activities, such as productive and idle times. The effectiveness of the proposed framework was tested and validated in the make-to-order industry. Its implementation demonstrates the ability to enhance control over the production schedule and direct manufacturing costs. With the proposed framework, the evaluation of operator and machining costs can be performed accurately, as opposed to the traditional production activity control activities in the make-to-order, which relies on estimates or an aggregate approach.

CONTEMPORARY CASES OF DIGITAL PRODUCT ASSORTMENT MANAGEMENT IN AN INTERNET SHOP

Within the outlined research, the main focus is on economic entities that operate not just as retail merchants but conduct their activities through various types of Іnternet-shops. It has been proven that effective management of their product assortment is crucial. While this process is characterized by the ability of the curated set of products or services to meet customer demand over an extended period, what is critically important is precisely the effective management of their product assortment, which distinguishes the ability of the curated set of products or services to satisfy customer demand over an extended period. According to the above, the purpose of the article is to specify and analyze contemporary cases of digital assortment management across basic types of Internet shops. Within the study, attention is drawn to the fact that digital technologies are significantly changing the paradigm of product assortment management in Internet shops and are providing new opportunities that open up a wide range of strategies and approaches in this area.

A novel collaborative electric vehicle routing problem with multiple prioritized time windows and time-dependent hybrid recharging

Due to global warming and environmental deterioration, the development of electric vehicles (EVs) is seen as a key measure to promote energy saving and emission reduction in logistics industries. However, EVs’ limited driving range and long recharging time make them unable to be widely applied in logistics distribution activities. Thus, this study establishes a model for a novel collaborative electric vehicle routing problem with multiple prioritized time windows and time-dependent hybrid recharging to address the above difficulties. The model quantifies and incorporates the priority of different time windows into costs to better satisfy customer demands while minimizing the total costs. A time-dependent hybrid recharging strategy that integrates three modes of in-station fast, in-station normal, and en-route battery swapping with collaborative mobile battery swapping vans (BSVs) is presented to reduce the impact of recharging time on route decision-making. The possible queuing time due to the limited capacity of recharging stations is considered to simulate the practical application scenarios. To effectively solve the complex model of synchronous optimization of EV and BSV routes, an extended adaptive large neighborhood search algorithm with two-dimensional coding scheme is proposed. In the proposed algorithm, several removal and insertion operators are integrated to effectively evolve the solutions, and the variable neighborhood descent algorithm is combined with local search operators to further improve the algorithmic performance. Comparison experiments were conducted to verify the effectiveness of the proposed algorithm by comparing with the other baseline algorithms.

Exploratory and co-exploratory innovation. The mediating role of digitalization on competitiveness in the hotel industry

Tourism plays a fundamental role in the economy of many countries and its growth is driven by the capacity of the tourism industry to offer new products and experiences. To compete efficiently, tourism firms need to be innovative, either through increasing their efficiency or by offering new high-quality products capable of satisfying customer demands. The complexity of the tourism environment highlights the need to understand innovation patterns that contribute to improving competitiveness in tourism firms, especially in the hotel industry. Therefore, the objective of this study is twofold. First, analyze the relationship between innovation processes and competitiveness in the hotel industry. Second, study whether digitalization in the hotel industry influences the innovation-competitiveness relationship. Following an exhaustive literature review, we develop a research model with four hypotheses, which are tested through PLS on a population of 322 Spanish hotels with at least 3 stars. The results show that innovation activities alone do not increase hotel competitiveness and that hotels should digitalize their activities in order to capitalize on innovation efforts towards efficient processes and differentiated services.

Waste printer ink as modifier for natural rubber/carbon black composites: No haste, use waste

From a sustainability perspective, achieving a greener future with a minimal carbon footprint requires maximizing waste materials' reuse. Typically, processing, price, properties, and performance are the four pillars of satisfying customer demands. Armed with this vision, the present work seeks to utilize waste printer ink (WPI) as a source of carbon in combination with low- and high-surface carbon black (LCB and HCB, respectively) additives to enhance the properties and performance of natural rubber (NR). Using WPI-modified CB together with NR underlines the importance of this work from a sustainability angle. By altering the type and amount of CB and WPI content, a broad properties window was unraveled, such that a very high elongation at break of ∼970% and elasticity of 53% were achieved under optimized conditions and formulation, when compared with 385% and 27.5% values of the reference blank NR sample, respectively. Thermal stability was also changed quite broadly, depending on the formulation. The analysis of volatile organic compounds (VOCs) revealed that propanol and its derivatives were the most abundant volatiles detected, accounting for more than 85% of the total emission. Analyzing environmental contamination and properties investigations opened avenues to propose practical ideas and strategies in order to standardize the usage of WPI and CB additives in NR compounding.

Optimal Lot-Sizing Decisions for a Remanufacturing Production System under Spare Parts Supply Disruption

Remanufacturing is one of the ways forward for product recovery initiatives and for maintaining sufficient production flow to satisfy customer demand by providing high-quality goods with a combination of new and return parts through a circular economy. Recently, manufacturers have been progressively incorporating remanufacturing processes, making their supply chains vulnerable to disruptions. One of the main disruptions that occurs in remanufacturing systems is the shortage of spare parts supply, which results in unexpected delays in the remanufacturing process and could eventually result in a possible loss of sales. In the event of such potential disruptions, remanufacturing facilities must manage their supply chains in an effective and optimal manner such that the negative impact of disruptions to their business can be minimised. In this study, a two-stage production–inventory system was analysed by developing a cost-minimisation model that focuses on the recovery schedule after the occurrence of a disruption in sourcing spare parts for a remanufacturer’s production cycle. The developed model was solved using the branch-and-bound algorithm, where the experimental results demonstrated that the model provides effective solutions. Through numerical experiments, results indicated that the optimal recovery schedule and the number of recovery cycles are considerably dependent on the disruption time, lost sales and backorder costs. A sensitivity analysis showed that the lost sales option seems to be more effective than the backorder sales option in optimising the system’s overall cost due to unmet demand, which becomes lost sales when serviceable items are reduced, thereby shortening recovery time. Furthermore, a case study revealed that a manufacturer’s response to disruption is highly influenced by the spare part costs and overall recovery costs as well as the supplier’s readiness level. The proposed model could assist managers in deciding the optimal production strategy whilst providing interesting managerial insights into vital spare parts recovery issues when disruption strikes.

Multi-period facility location and capacity expansion with modular capacities and convex short-term costs

In this paper, we consider a multi-period facility location problem with capacity expansion motivated by the real-world problem of establishing hydrogen production infrastructure in Norway. The problem is formulated using modular capacities that capture economies of scale in production costs. The costs of opening a facility are represented by concave long-term costs, while the production costs of each capacity level are given by convex short-term costs. In our model, we allow only one expansion during the planning horizon, and have to observe limits on minimum production quantities. The objective is to minimize the sum of investment, expansion, production, and distribution costs while satisfying customer demand. To solve the problem we implement a solution method based on Lagrangian relaxation. The lower bound is calculated using a dynamic programming approach. To obtain an upper bound solution, we develop a greedy heuristic that converts the solution to the Lagrangian dual into a feasible solution. The approach is tested on different problem instances based on real-world data. The results show that our solution method based on Lagrangian relaxation outperforms Gurobi in terms of run time for all tested instances. Our Lagrangian based approach also always finds good or even near-optimal solutions, whereas Gurobi fails to find feasible solutions for some of the larger instances.

When core sorting and quality grading is beneficial to remanufacturers: Insights from analytical models

In this paper, we study the core acquisition and remanufacturing problem in which the remanufactured products are produced from acquired cores with uncertain quality condition, and are used to satisfy customer demand. Decision-making models are developed to examine the potential value of core sorting and quality grading in the remanufacturing system: a single-period model with deterministic demand, and a single-period model with stochastic demand (i.e., a newsvendor-type model). In each model, both the sorting strategy and the non-sorting strategy are discussed and compared. Our theoretical and numerical results show that: (1) In the deterministic demand case, core sorting is cost-effective only when the unit sorting cost is below a threshold value and the unit acquisition cost falls into a specific interval. Furthermore, in the case with two quality grades the adoption of sorting strategy with respect to the expected fraction of high-quality cores may be non-monotone: an initial increase in the expected fraction of high-quality cores may motivate a switch to core sorting, however, further increase in the expected fraction may motivate a reverse switch; (2) Similarly, in the stochastic demand case, the sorting strategy also becomes unattractive when the unit sorting cost is sufficiently high. In addition, the value of core sorting will be better off under more fluctuating demand for remanufactured products if the sorting strategy is the dominant strategy. Otherwise, it will be worse off.

Modeling and Forecasting of Milk Production in the Western Zone of Tamil Nadu

Background: In India, the dairy business is expanding dramatically. Tamil Nadu milk cooperatives significantly contribute to the growth of the dairy sector in the state. In terms of delivering economic income for dairy smallholders and satisfying customer demand, the identification of milk production is one of the primary financial operations made in India. Considering this, it is crucial to understand future production to enhance and sustain the sector’s growth and development. Methods: The present investigation attempts to predict and forecast milk production in Tamil Nadu using time series models. Yearly milk data from 1976 to 2020 was taken. The study considered Auto-Regressive Integrated Moving Average (ARIMA) and Artificial Neural Network (ANN) to select the appropriate stochastic model for forecasting milk production in Tamil Nadu. Further statistical modeling procedures employed for milk production reveal that the selection of a suitable time series model will always depend on the nature of the data. Result: Results revealed that the ARIMA model is selected as the best model despite ANN, even if it is considered the most powerful model. The CAGR for forecasted milk production from 2020-2025 was 0.02%. Model adequacy criteria like RMSE, MAPE and MAE are used. Based on observation ARIMA model (1, 1, 2) is chosen as the best model over the ANN model.

Robust possibilistic programming-based three-way decision approach to product inspection strategy

During product inspection, Type I and Type II errors, widely considered to assess product quality, are represented by erroneously rejecting non-defective products and erroneously accepting defective products, respectively. Meanwhile, the formulation of product inspection strategy is oftentimes deemed as an interdependent process influenced by multiple factors (e.g., production technology and customer demand) from both upstream (e.g., production process) and downstream (e.g., customer zone). Due to the limited understanding and knowledge of decision-makers on imprecise parameters of these factors, it is challenging for decision-makers to formulate an appropriate product inspection strategy. To address the aforementioned challenges, an improved three-way decision (3WD), known as robust possibilistic programming (RPP)-based 3WD is put forth. Such an improvement for 3WD is evident in two aspects (1) the RPP model endows 3WD to address imprecise parameters and chance constraints using flexible attitudes, and (2) the RPP model ensures the formulation of the product inspection strategy of 3WD is robust. Additionally, with the aid of 3WD, an intermediate/uncertain decision, is introduced to simultaneously reduce the aforementioned two types of errors. A case study of a semiconductor manufacturing system, along with discussions and two comparative studies, is presented to demonstrate the effectiveness and performance of this approach. As shown in this study, the proposed approach (1) effectively prevents decision-makers from making an over-conservative attitude in the formulation of the product inspection strategy, (2) has better performance in satisfying customer demand, and (3) has significant advantages in terms of cost and computational time.

Proposal of a New Tool for Pre-Straining Operations of Sheet Metals and an Initial Investigation of CR4 Mild Steel Formability

With the increased focus on reducing carbon emissions in the automotive industry, more advanced materials are introduced to reduce the vehicle weight, and more complex component geometries are designed to both satisfy customer demands and to optimize the vehicle aerodynamically. With the increase in component complexity, the strain paths produced during the forming operation of car body components often display a highly non-linear behavior which makes the task of failure prediction during the manufacturing feasibility studies more difficult. Therefore, CAE engineers need better capabilities to predict failure induced by strain path nonlinearity. This study proposes a new tool designed for creating bi-linear strain paths, by performing a pre-strain of a sheet large enough to cut out Nakajima specimens to perform the post-straining in any direction. From five pre-straining tests the tool present a stable pre-straining operation with a uniform strain field in a radius of 100 [mm] from the centre, corresponding to the region of interest of a Nakajima specimen. From the five pre-strained samples, different Nakajima specimens are cut transverse and longitudinal to the rolling direction and a failure prediction approach in an alternative, path independent evaluation space was used to predict the onset of necking with promising results.

Risk-based inventory scheduling framework to fulfill multi-product orders within a production network

Production facilities are critical components of the global economy and supply chain. Firms are forced to balance several competing objectives—from reducing operating costs by managing inventory to increasing profits by satisfying customer demand. The act of scheduling material through an interconnected production network is analytically challenging; therefore, stakeholders require statistical insights to strengthen the decision-making process. This inventory scheduling application allows decision-makers to monitor the status and impact of numerous production parameters while aiming to mitigate the propagation of schedule risk through the system. This work presents a material planning framework that (i) jointly represents work center and material relationships and (ii) integrates stochastic methods to assess potential risk. Using network flow optimization and Monte Carlo simulation, this work accommodates three primary considerations: (i) safety stock, and other inventory restrictions, (ii) multi-product order satisfaction, and (iii) costs derived from holding inventory and delaying orders. An illustrative example examines the impact of twelve experimental scenarios on order fulfillment, work center utilization, and material inventory and production.