Spare Parts Demand Forecasting Research Articles

A Predictive Model with Data Scaling Methodologies for Forecasting Spare Parts Demand in Military Logistics

This study addresses the challenge of accurately forecasting demand for maintenance-related spare parts of the K-X tank, influenced by high uncertainty and external factors. Deep learning models with RobustScaler demonstrate significant improvements, achieving an accuracy of 86.90% compared to previous methods. RobustScaler outperforms other scaling models, enhancing machine learning performance across time series and data mining. By collecting eight years’ worth of demand data and utilising various consumption data items, this study develops accurate forecasting models that contribute to the advancement of spare parts demand forecasting. The results highlight the effectiveness of the proposed approach, showcasing its superiority in accuracy, precision, recall, and F1-Score. RobustScaler particularly excels in time series analysis, further emphasizing its potential for enhancing machine learning performance on diverse datasets. This study provides innovative techniques and insights, demonstrating the effectiveness of deep learning and data scaling methodologies in improving forecasting accuracy for maintenance spare parts demand.

Demand forecasting of spare parts with regression and machine learning methods: Application in a bus fleet

Forecasting the demand of spare parts of vehicles in bus fleets is a vital issue. Vehicles must operate effectively and must have a high availability rate in the fleet. In maintenance operations, faulty parts or parts that complete their lifetime must be replaced with a new one. Spare parts needed must be in inventories with the required amount on time. In this sector, there are thousands of spare parts to manage. The maintenance and repair department must operate effectively. In order to accomplish this, accurate forecast of spare parts is required. In this study, demand forecasting was carried out with regression-based methods (multivariate linear regression, multivariate nonlinear regression, Gaussian process regression, additive regression, regression by discretion, support vector regression), rule-based methods (decision table, M5Rule), tree-based methods (random forest, M5P, Random tree, REPTree) and artificial neural networks. The forecasting model developed in this study includes critical variables such as the number of vehicles in the fleet, the number of breakdowns that cause parts to change, the number of periodic maintenance, mean time between failure and demand quantity in previous years. The application was carried out with real data of eight (2013–2020) years. 2013–2019 data was used for training and 2020 data was used for testing. In forecasts, support vector regression among regression-based methods, decision table among rule-based methods, M5P among tree-based methods gave the best results. It has been observed that the artificial neural network produced more accurate forecasts than all other methods. Artificial neural network forecasts give the highest forecast accuracy rate and the least deviation.

Demand Forecasting of Spare Parts Using Artificial Intelligence: A Case Study of K-X Tanks

The proportion of the inventory range associated with spare parts is often considered in the industrial context. Therefore, even minor improvements in forecasting the demand for spare parts can lead to substantial cost savings. Despite notable research efforts, demand forecasting remains challenging, especially in areas with irregular demand patterns, such as military logistics. Thus, an advanced model for accurately forecasting this demand was developed in this study. The K-X tank is one of the Republic of Korea Army’s third generation main battle tanks. Data about the spare part consumption of 1,053,422 transactional data points stored in a military logistics management system were obtained. Demand forecasting classification models were developed to exploit machine learning, stacked generalization, and time series as baseline methods. Additionally, various stacked generalizations were established in spare part demand forecasting. The results demonstrated that a suitable selection of methods could help enhance the performance of the forecasting models in this domain.

An Improved Stacking Model for Equipment Spare Parts Demand Forecasting Based on Scenario Analysis

The purpose of spare parts management is to maximize the system’s availability and minimize the economic costs. The problem of cost availability trade-off leads to the problem of spare parts demand prediction. Accurate and reasonable spare parts demand forecasting can realize the balance between cost and availability. So, this paper focuses on spare parts management during the equipment normal operation phase and tries to forecast the demand of spare parts in a specific inspection and replacement cycle. Firstly, the equipment operation and support scenarios are analyzed to obtain the supportability data related to spare parts requirements. Then, drawing on the idea of ensemble learning, a new feature selection method has been designed, which can overcome the limitations of a single feature selection method. In addition, an improved stacking model is proposed to predict the demand for spare parts. In the traditional stacking model, there are two levels of learning, base-learning, and meta-learning, in which the outputs of base learners are taken as the input of the meta learner. However, the proposed model brings the initial feature together with the output of the base learner layer as the input of the meta learner layer. And experiments have shown that the performance of the improved stacking model is better than the base learners and the traditional stacking model on the same data set.

Spare parts demand forecasting method of modern enterprises based on digital twin model

Accurate forecast of spare parts demand is of great significance for modern enterprises to provide accurate support and improve market competitiveness. In most studies, mathematical laws are used to forecast, without enough consideration of the actual operation of equipment and the fact that the accuracy of spare parts demand forecasting is not high, which cannot adapt to the new characteristics of complex equipment use environment and fierce market competition in modern enterprises. The digital twin model can be used to forecast the demand for spare parts more accurately and guide modern enterprises to carry out accurate support. By analyzing the current spare parts demand of modern enterprises, the paper puts forward the forecasting ideas of spare parts demand based on the digital twin model by using the digital twin model of equipment maintenance management in modern enterprises. In the digital twin model, the theoretical demand forecasting model of spare parts based on life distribution of replaceable units is introduced, and the sensitivity coefficient system of spare parts demand of replaceable units to operation and environment is constructed. The digital twin model is used to feedback train the sensitivity coefficient to obtain the reliable spare parts demand rules. Based on the theoretical demand and sensitivity coefficient of spare parts, the forecasting method of spare parts demand is given, and the spare parts demand forecasting model is established. Through case analysis, the feasibility and accuracy of the forecasting model are verified.

Spare Parts Demand Forecasting During Covid 19 pandemic

The research was conducted to analyze the calculation of demand forecasting and inventory of spare parts . The data collection method uses descriptive quantitative by conducting literature studies, interviews, and collecting sample data of 140 spare parts from June 2019 to June 2020. The data classification process with FSN method, obtained 13 fast moving spare parts use for calculating demand forecasting based on the Triple Exponential Smoothing method. The results from the trial error to get the smoothing value of alpha, beta and gamma errors prioritize to best MAPE <5%. Some MAPE errors above 5% are X000000 000254 MAPE = 5.68% , X000000 005566 MAPE = 21.12, X400 401 10 72 MAPE = 13.14, and X400 401 26 71 MAPE = 16.70. The calculation result of safety stock and reorder point find 4 spare parts have low level inventory have to reorder.

RNN / LSTM with modified Adam optimizer in deep learning approach for automobile spare parts demand forecasting

The spare parts demand forecasting is very much essential for the organizations to minimize the cost and prevent the stock outs. The demand of spare parts/ car sales distribution is an important factor in inventory control. The valuation of the demand is challenging as the automobile spare parts/car sales demand are often recurrent. The renowned empirical method adopts historical demand data to create the distribution of lead time demand. Although it works reasonably well when service requirements are relatively low, it has difficulty reaching high target service levels. In this paper, we proposed Recurrent Neural Networks/ Long-Short Term Memory (RNN / LSTM) with modified Adam optimizer to predict the demand for spare parts. In this LSTM, weight vectors are generated respectively. These weights are optimized using the Modified-Adam algorithm. The accuracy of the forecast and the performance of the inventory are considered in the experimental result. Experimental results confirm that RNN / LSTM with a Modified-Adam works well with minimal error compared to other existing methods. We conclude that the proposed RNN/LSTM with Modified-Adam algorithm is well suited for the prediction of automobile spare parts.

Intermittent demand forecasting for spare parts in the heavy-duty vehicle industry: a support vector machine model

Intermittent demand occurs commonly for spare parts in the heavy-duty vehicle industry. Demand uncertainty and intermittency pose challenges to demand forecasting by conventional models. Support vector machine (SVM) models have been observed to yield competitive accuracy with existing models. However, there are still limitations for basic SVM models. First, the time-consuming computation does not bring a statistically significant accuracy improvement. Second, the forecasting-based inventory performance has not been sufficiently explored. Third, scarce explanations of model robustness are offered for demand forecasting. We build an adaptive univariate SVM (AUSVM) model to forecast intermittent demand. Its effectiveness, compared to 12 existing models and an improved neural-network, is demonstrated by real-world data from a heavy-duty vehicle spare-part company. AUSVM has an apparent advantage in computation time over basic SVM and neural networks. The computational results of the heavy-duty vehicle case indicate that, compared to well-known parametric models, AUSVM achieves a statistically significant accuracy improvement and better inventory performance for the group of non-smooth demand series. Discussions are presented on why AUSVM works for demand forecasting and inventory control of heavy-duty vehicle spare parts. Several insights are revealed for practitioners in the heavy-duty vehicle industry.

Forecasting Spare Parts Demand of Military Aircraft: Comparisons of Data Mining Techniques and Managerial Features from the Case of South Korea

In a weapon system, the accurate forecasting of the spare parts demand can help avoid the excess inventory, leading to the efficient use of budget. It can also help develop the combat readiness of the weapon system by improving weapon system utilization. Moreover, as performance-based logistics (PBL) projects have recently emerged, the accurate demand forecasting of spare parts has become an important issue for the PBL contractors as well. However, for the demand forecasting of spare parts, the time series methods, typically used in the military sector, have low prediction accuracies and the PBL contractors are mostly based on the judgment of practitioners. Meanwhile, most of the previous studies in the military sector have not considered the managerial characteristics of spare parts (e.g., reparability and the irregularity of maintenance). No previous work has considered any such features, which can indicate the reliability of spare parts (e.g., mean time between failures (MTBF)), although they can affect the spare parts demand. Therefore, to develop a more accurate forecasting of the spare parts demand of military aircraft, we designed and examined a systematic approach that uses data mining techniques. To fill up the research gaps of related works, our approach also considered the managerial characteristics of spare parts and included the new features that represent the reliability of spare parts. Consequently, given the case of South Korea and the full feature set, we found random forest gave better results than the other data mining techniques and the conventional time series methods. Using the best technique Random Forest, we identified the contribution of each managerial feature set to improving the prediction accuracy, and we found the reliability and operation environment are valuable feature sets in a significant way, so they should be collected, managed more carefully, and included for better prediction of spare parts demand of military aircraft.

머신러닝 기반 Lumpy 수요형태의 항공기 수리부속 수요예측 정확도 개선 연구

For the spare parts of aircraft "A" operated by ROKAF(Republic of Korea Air Force), this research suggests the application of machine learning technique rather than that of time series technique in order to improve demand forecast accuracy of spare parts whose demand pattern is lumpy. Demand patterns are divided into four categories by applying Average Inter-Demand Interval(ADI) and Coefficient of Variation(CV). Only for the lumpy parts, this study applies various analysis models selected from demand history, and the probability of demand occurrence for each period for lumpy parts is predicted by applying machine learning techniques. As a result of the experiment, lumpy or erratic pattern appeared to be higher in aircraft spare parts, and smooth parts with stable demand appeared relatively lower. In addition, logistics regression, linear discriminant analysis, and decision tree technique showed a relatively better accuracy, and machine learning technique improved prediction accuracy about 5% higher than time series technique, thus proving that machine learning technique is an effective technique to for lumpy spare parts demand forecast.

Maintenance Spare Parts Demand Forecasting for Automobile 4S Shop Considering Weather Data

Maintenance spare parts demand forecasting is an important foundation of maintenance spare parts inventory control, which is an essential responsibility for managers of an automobile 4S shop. Although the existence of the effect of weather conditions on maintenance spare parts demand has been verified, the study on maintenance spare parts demand forecasting for an automobile 4S shop considering weather data has not been found. In this paper, a novel method is proposed for maintenance spare parts demand forecasting for an automobile 4S shop considering weather data. By taking into account three dimensions of weather data (i.e., temperature, visibility, and slipperiness) and delayed effects of weather conditions on maintenance spare parts demand, a vector of numerical weather data with 30 weather factors is constructed to represent the related weather conditions of a given day. Then, a back propagation (BP) neural network is trained and the weights of the 30 weather factors are determined. Similar historical cases of the target case are extracted, and two forecasting models are respectively trained based on extreme learning machine (ELM) and support vector machines (SVM) using the similar historical cases. The final forecasting model is determined by comparing the fitting precisions of the two forecasting models. The experimental study is conducted based on the real data of an automobile 4S shop. The results show that weather data is critical to maintenance spare parts demand forecasting for an automobile 4S shop, and the extraction of similar historical cases is an effective approach to capture the complex effect mechanism of weather data on maintenance spare parts demand.

A double-level combination approach for demand forecasting of repairable airplane spare parts based on turnover data

To address the problem that the demand forecasting methods for repairable airplane spare parts are not advanced, and that the basic forecasting data are not consistent with actual consumption, this paper proposes a double-level combination forecasting approach for repairable spare parts based on relevant data. First, we conduct an analysis for the factors that influence the demand of repairable spare parts. Second, five types of individual direct forecasting models are combined to establish a double-level combination forecast model, which is superior to both individual combination forecasting models and individual direct forecasting models. Finally, we evaluate the forecasting performance by utilizing consumption data for an aircraft fleet and turnover data for an aircraft. The forecasting results provide strong evidence that that the double-level combination forecast model is more accurate and consistent with actual demand.

Models of spare parts inventories' optimisation: a literature review

In recent decades, several models had been developed to optimise inventory of spares parts. It is a major challenge for many organisations because the spares parts include features that differentiate them from other products. Due to the huge amount of models made by researchers for the optimisation of spares parts inventories, it is important to collect all the information concerning these models, and present them in a research paper. This research paper provides a critical literature review on spare parts inventories. The first and second part is dedicated to the examination of the methods and the modifications proposed by the researchers for classification and demand forecasting of spare parts. The third part focuses on the common optimisation models of maintenance policies, replenishment policies of spares parts, and repair capacity.

Models of spare parts inventories' optimisation: a literature review

In recent decades, several models had been developed to optimise inventory of spares parts. It is a major challenge for many organisations because the spares parts include features that differentiate them from other products. Due to the huge amount of models made by researchers for the optimisation of spares parts inventories, it is important to collect all the information concerning these models, and present them in a research paper. This research paper provides a critical literature review on spare parts inventories. The first and second part is dedicated to the examination of the methods and the modifications proposed by the researchers for classification and demand forecasting of spare parts. The third part focuses on the common optimisation models of maintenance policies, replenishment policies of spares parts, and repair capacity.

The Research and Analysis on Failure Distribution Model of Diesel Engine Component Parts

Reliability research not only provides the direction of quality improvement for new product research and development, but also helps to get the product failure distribution model, so as to ensure the logistics organization to improve the service level. According to the reliability data from the database of research group, we analyzed the rule of failure distribution of high frequency fault component (fuel injection pump) and built a Weibull model. The parameters of the model are estimated and solved by using the uniform linear method and the least square method. After solving the model, the density function curves and the failure rate curves are drawn, and then the model of the demand forecasting of spare parts based on the failure distribution is obtained.

Cost-optimal spare parts inventory planning for wind energy systems

For safe and reliable machine operation, maintenance, repair and overhaul (MRO) activities are required. Spare parts demand forecasting and inventory planning, which is an important part of MRO activities, must be accurate to avoid costs because of surplus spare parts or machine downtimes. The restriction of reduced accessibility to wind turbines during the winter months also has to be taken into account when planning maintenance activities and spare part inventories for wind farms. The presented model provides the most economic stock quantity under given environmental conditions. It is based on the proportional hazards model, which is extended to calculate the remaining useful component life time and derive required spare parts inventory levels. The presented model is validated, using condition monitoring data and environmental data of an onshore wind farm. Comparison of the spare part inventory prediction to wind farm’s failure data proves the model’s accuracy. Parameter analyses show that the model can be applied for spare parts inventory planning under consideration of environmental conditions.

An integrated approach for demand forecasting and inventory management optimisation of spare parts

In this paper, we develop and test an advanced model, based on discrete-event simulation, whose purpose is to forecast the demand of spare parts during the whole lifetime of a complex product, such as, for instance, an industrial machine. To run the model, the relevant data of the product manufactured by a targeted company should be collected. With those data, the model provides an estimate of the optimal level of spare parts inventory the company should keep available. The data provided by the model are subsequently applied to a case example, referring to a hypothesised company, manufacturing industrial plants. The application is carried out considering two scenarios, i.e., a 'traditional' and an 'advanced' approach for demand forecasting, this latter reflecting the circumstance where the company makes use of the proposed forecasting method. The comparison of the outcomes obtained in the two scenarios highlights the efficiency and resolution capacity of the model developed.

Electrical Spare Parts Demand Forecasting

In this paper is presented a research of electrical spare parts demand forecasting through application of conventional (moving average, exponential smoothing and naive theory), more sophisticated forecasting techniques (support vector regression, feed-forward neural networks) and adaptive model selection methodologies. Electrical spare parts demand forecasting is a fundamental task that should be performed in order to improve SCM (supply chain management). If it would be possible to know what the demand for electrical parts will be in the future, the logistics of the companies that manufacture electrical parts or retailers could be managed more accurately: selection of appropriate warehouse safety limits for each part and ability to plan the resources more precisely. Customer sales and marketing departments always perform formal forecasts, this is usually done through application of conventional methods in order to prepare future plans. Experimental results reveal that application of SVR technique guarantees the best and precise results of forecasting of weekly and daily demand of electrical parts. Furthermore, application of adaptive methodology in order to select adaptive model allowed substantially to increase forecasting accuracy. DOI: http://dx.doi.org/10.5755/j01.eee.20.10.8870

Demand forecasting and inventory control: A simulation study on automotive spare parts

This paper presents results of a large-scale simulation study on spare parts demand forecasting and inventory control to select best policies within each SKU category. Simulations were conducted over 10,032 SKUs of an automaker that operates in Brazil, considering six years of demand data. Literature review drove the selection of different models simulated. The study included three alternatives to record demand data (individual orders data, weekly and monthly time buckets), three demand forecasting models (SMA – Simple Moving Average, SBA – Syntetos–Boylan Approximation and Bootstrapping) and six models for demand distribution during lead-time (Normal, Gamma, NBD-Negative Binomial Distribution, compound Poisson-Normal, compound Poisson-Gamma and Bootstrapping) resulting in 17 “combined” policies. These policies were applied under (s, nQ) inventory control (reorder point, multiples of fixed order quantity), considering two alternative frequencies for model parameters revision (monthly and semi-annually) and four Target-Fill-Rates (TFR=80%, 90%, 95% and 99%), totalizing 136 simulation runs over each SKU. Parameter values (s, Q) were calculated towards TFR using methods from literature. Performance of each combined policy was measured by total costs and RFR – Realized-Fill-Rate. Major contributions of the research are the policy recommendations within each SKU category, a new Bootstrapping procedure and the highlight of Single Demand Approach (SDA) as a promising area for future theoretical and empirical studies. Results shall be used as guideline for practitioners under similar operations.

A risk‐based approach to manage non‐repairable spare parts inventory

Purpose – The purpose of this paper is to propose a risk‐based approach for spare parts demand forecast and spare parts inventory management for effective allocation of limited resources. Design/methodology/approach – To meet the availability target and to reduce downtime, process facilities usually maintain inventory of spare parts. The maintaining of non‐optimized spare parts inventory claims more idle investment. Even if it is optimized, lack of attention towards the critical equipment spares could threaten the availability of the plant. This paper deals with the various facets of spare parts inventory management, mainly risk‐based spare parts criticality ranking, forecasting, and effective risk reduction through strategic procurement policy to ensure spare parts availability. A risk‐based approach is presented that helps managing spare parts requirement effectively considering the criticality of the components. It also helps ensuring the adequacy of spare parts inventory on the basis of equipment criticality and dormant failure without compromising the overall availability of the plant. Findings – The paper proposes a risk‐based approach that used conjugate distribution technique with the capability to incorporate historical failure rate as well as expert judgment to estimate the future spare demand through posterior demand distribution. The approach continuously updates the prior distribution with most recent observation to give posterior demand distribution. Hence the approach is unique in its kind. Practical implications – Appropriate spare parts unavailability could have great impact on process operation and result in costly downtime of the plant. Following proposed approach the availability target can be achieved in process industry having limited maintenance resources, by forecasting spare parts demand precisely and maintaining inventory in good condition. Originality/value – Adopting the approach proposed in the paper, risk level can be minimized and plant availability can be maximized within the financial constraint. The resources are allocated to the most critical components and thereby increased availability, and reduce risk.