Abstract
A maintenance process of internal vehicle transport is important from the production companies and also service providers. Failures of transport vehicles for a production company mean difficulties in the realization of production and auxiliary processes. Failures of transport vehicles for a service organization means those employees of the organization are assigned to carry out service activities for a longer time. This issue can be a particular problem, especially for small service organizations. Hence, in order to plan the maintenance activities, it is appropriate to predict failures to prevent them by undertaking adequate preventive actions. In this work, the failure risk was calculated based on the data from the maintenance processes collected. Additionally, it is proposed the solution, especially for small maintenance service providers, which can be used for maintenance activities taken under consideration the criticality of internal vehicles. The method presented in the article, which supports decision making regarding service planning, can help companies providing maintenance outsourcing services.
Access provided by Autonomous University of Puebla. Download conference paper PDF
Similar content being viewed by others
Keywords
1 Introduction
Companies specializing in technical infrastructure service (machinery and equipment, installations, means of transport) currently operate in almost all possible areas of the market, providing services for both commercial and manufacturing enterprises. Along with the ubiquitous automation and computerization, the demand for services related to, among others, repair, maintenance, and periodic inspection of machines and devices is growing. These needs create a huge field of activity for maintenance companies. Concerning manufacturing enterprises, maintenance service providers support: (i) non-functional areas, such are office heating, air conditioning, lighting; (ii) auxiliary areas to production, such as water treatment for production facilities, air compression, transport vehicles and storage facilities; (iii) production area such as production equipment.
The maintenance tasks realized by service providers are extremely important because the continuity of operation of the processes carried out by the clients of the maintenance company and their success depends on efficiently functioning machines, devices, and means of transport. Also, regular maintenance of devices extends their life cycle and increases the efficiency of their operation and also has a positive effect on production efficiency [1, 2].
Due to the wide spectrum of maintenance services, running a maintenance company is a difficult task. The main problems of managers of such a company include the need to coordinate the dates of planned maintenance activities (e.g., inspections) and unplanned activities related to fixing the failures at customers’ facilities located in different places. On the other hand, service technicians often struggle with maintaining machines from different manufacturers, which forces them to comply with various control procedures and service principles.
Enterprises implementing outsourcing maintenance contracts tend to achieve the “perfect balance” between costs and the availability and technical condition of equipment covered by the service contract. It is mainly done through: adaptation of exploitation strategies to machines depending on their criticality, adjustment of the frequency of preventive works on machines to their criticality, and technical condition.
Machine criticality is a key element for both the company and the maintenance service provider. The same machine can be critical in one enterprise, but not in another. An enterprise providing maintenance services should categorize machines together with client employees to include crucial and specific factors. The results of the categorization will be the basis for determining the scope of maintenance activities that should be taken to keep the risk of failure at the level required by the customer.
Each failure resulting in a stoppage of the machine, production line or even the entire plant may have several consequences, such as costs of removing the failure (e.g., cost of spare parts, cost of work of employees), reduction of product quality or difficulties in the entire supply chain. In addition to purely financial consequences, the occurrence of failure may cause safety risks for machine operators and third parties in the vicinity of the machine; also, it may harm the natural environment [3, 4]. Conducting a criticality analysis enables the selection of an appropriate maintenance strategy [5]. It should be emphasized, however, that selecting the strategy is a complex technical, economic and organizational task, requiring knowledge of market needs (as a recipient of maintenance services), the balance of total costs as well as profits, and the technical capabilities of the used equipment. When selecting the strategy, the specificity of tasks performed by a given company and key problems, that are generated in connection with maintenance processes, are of great importance.
Another element after determining the maintenance strategy, important for the implementation of the service company's activities, is the adjustment of the frequency of preventive work on machines to their criticality and technical condition. Planning and scheduling of maintenance are perceived as the “center” of maintenance management [6]. What and when it is to be performed directly affects production (availability of machinery and equipment), safety (tasks planned are generally safer than unplanned), environment (compliance with legal and sustainable requirements), costs (additional working hours) and indirectly marketing (availability of products for the client) [7]. At the same time, planning and scheduling of maintenance are influenced by the availability of financial resources, human resources (e.g., availability of competences) [8], information (e.g., historical data on operational events) and material and technical resources (internal availability and the possibility of acquiring them from a market environment).
Planning is a decision-making process that deals with the allocation of resources to jobs, in given time intervals, and its task is to optimize one or more goals [9]. Resources and tasks in any organization can take different forms. They can be machines in a repair workshop or people carrying out tasks. The decision to implement many tasks exploiting shared resources (and this situation occurs in enterprises providing services) is very complicated.
Different types of machines are assigned to different periods of service, depending on the frequency of failures and their criticality. One of the challenges is to determine the right time interval between services and their ranges. It is necessary to ensure that:
-
costly and unnecessary maintenance activities were not performed long before the actual occurrence of the failure;
-
costly activities caused by the failure as a consequence of too long time intervals between planned preventive actions were not necessary.
The need to plan maintenance and repair activities, the variety of planning methods used, and the resulting benefits are the subject of many publications [10,11,12,13,14].
2 Literature Review
The review presents some solutions supporting maintenance transport. In research [15], the case study takes its starting point in the perspective of an actor considering how to develop vehicle maintenance services for its customers and points at the need to enable understanding of the conditions for vehicle maintenance, which necessitates identification and analysis of the variety across transport service settings. The main objective of the work [16] is to design a system for diagnosis, measurement, and improvement of productivity aimed at quality of service. The result in the study [17] is researched on how to achieve an effective fleet maintenance planning in transport companies, which contributes to increasing the fleet energy efficiency and in achieving the companies' goal. Some decision systems are also presented in the works [18,19,20].
Although the literature on the subject presents some solutions to decision support systems, in the field of vehicle transport maintenance, there is still a lack of dedicated, simple, low-cost, and intelligent solutions, especially for small service providers. That is why the main research problem in this paper is: How to support maintenance service providers in planning their maintenances tasks based on the criticality of vehicles and predict adequate maintenance activities, especially in a small service provider?
This paper is organized as follows. First, a short literature review related to maintenance service providers is presented. Moreover, the research problem is posed. Next, the analysis of maintenance activities frequency based on case study service provider is introduced. In the third chapter, the intelligent predictive decision support system for the services provider is presented. Finally, the main conclusion and added value of this work are discussed.
3 Research Methodology
3.1 Structure of Internal Vehicle Transport Classification
The paper presents a practical analysis of the process of maintaining internal transport, the main purpose of which is to keep vehicles in readiness for work. The analysis was carried out based on the principles of organization and implementation of machine maintenance activities for various vehicles and used in various locations. The planning of maintenance activities of the service provider must anticipate failures to take them and take appropriate preventive action. In this analysis, the data is based on data collected in maintenance processes performed by the service provider.
The subject of the following analyses is Internal Vehicle Transport (IVT). Different criteria were used to classify IVT, such: type of IVT (internal combustion vehicle, electric), a model (m1, m2,…,mn), age, and working time (WT) (Table 1). Ranges for criteria were identified during the data analysis from the case company and concerning requirements from internal vehicle producers. For analysis, the data delivered by the service provider were used. The boxplot in Fig. 1 shows the value distribution of Age (A) and working time (WT). Only the boxplot of working time shows the outliers, which do not influence further analyses.
3.2 Maintenance Activities Analyses
The first of the study was to identify the type and the frequency of maintenance activities (MA). Mainly the type of maintenance activities was divided into two types planned and unplanned activities. To identify the frequency of maintenance activities to criteria were analyzed: age (A) and Working Time (WT). The analysis showed that the age of IVT is in the range of 7–22 years, and the maximum value of the working time of IVT is almost 30000 h. Three categories of analyzed criteria have been established: High (H), Medium (M)) and Low (L) (Table 1). The criteria categories have been established based on authors and service organization experience.
To analyze the frequency of maintenance activities of each IVT category, the maintenance activities frequency (MAF) indicator, according to Eq. (1), was calculated.
where: MAF – the maintenance activities frequency, NoMAc – many maintenance activities in every category (considering A and WT),
\(\sum NoMAF \)– the total number of maintenance activities in the analyzed time.
Table 2 shows the obtained results, the value of the MAF indicator in each category.
The experience of authors and personnel of service organizations let to identify the risk level of the MAF indicator. The level of risk of the MAF indicator was divided into three categories: Low, when the value of MAF is less than 0.10, Medium when the value of MAF is in the range 0.10 to 0.20, High when the value of the MAF indicator is more than 0.20 (Table 3). According to these assumptions, the risk level of MAF for every category was specified and presented in Table 4.
The possible use of the presented matrix of risk has been proved with workers in the analyzed service organization. In order to provide any circumstances (especially if the values of criteria are near to the border of the ranges), it is important to use an approach based on fuzzy logic to support the MAF indicator.
4 Results
4.1 Process of Fuzzy Interference
The shown case study described in the paper, a Mamdani-type process of fuzzy inference is utilized. The membership functions were formulated, taking into account the values of the A and WT. However, it might be changed membership functions according to maintenance experts. Figure 2 presents the total view of the suggested fuzzy system of risk importance assessment. To calculate the risk rank, there is the option to choose A and WT, as the inputs to the fuzzy system. Because the Mamdani type fuzzy inference process is easy to understand and the most intuitive, so it was used to present that analyzed case study.
In the proposed Mamdani Fuzzy Interference System, two quantitative inputs were used (A) and (WT), and output is the MAF indicator. The MATLAB (R2019b) was used to implement the proposed fuzzy inference process [21] (Fig. 3).
4.2 Parameters of Fuzzy Interference System
For the inputs (A, WT) and output (MAF), the membership functions MFs were specified. In this paper, the functions of Gaussian membership available in MATLAB (R2019b) were incorporated by the authors for input A and WT, were used [21, 22] The curve of Gaussian membership function is described by the Eq. (2):
where σ is the standard deviation, and c is the mean. Figure 4 presents the Gaussian membership function (GMF) for inputs A and WT.
Based on the work [23], the authors’ and service organization experience, and in order to reduce the difference regarding the mathematical modeling and the practical implementation, the triangular membership functions for output MAF were used (3).
The curve of the triangular membership function is a vector x, and it depends on three parameters a, b, and c. The b parameter is the triangle peak, and the a and c parameters determine the “feet”. The membership functions for output MAF was determined based on the ranges presented in Table 3 (see Fig. 5). Based on Table 4, the fuzzy rule base was established (see Fig. 6).
4.3 Analysis of the Results and Discussion
Figure 7 and Fig. 8 present the calculation value of MAF (3D) three-dimensional risk (MAT) profiles relative to A and WT. The calculation was made for the A = 7 and WT = 7.000 h. The value of the MAF indicator estimated by the FIS is 0.396. According to the corresponding linguistic value presented in Table 3 is H. This linguistic value H means that for this IVT group means a high frequency of performing maintenance activities. It is very important information from the service company's point of view. In the next step, the service company should analyze the type of maintenance activities performed for this IVT group (Age – Medium and Working Time - Low). In the analyzed group of IVT, a significant part of 80% was corrective maintenance, and preventive maintenance constituted only 20%. It means that the failure rate for the analyzed transport vehicles was high. Failure of transport vehicles for a production company means difficulties in the realization of processes such as the transport of materials for production, transport of finished products, and warehouse service. Failure of transport vehicles for a service organization means that employees of the organization are assigned to carry out service activities for a longer period of time. It can be a particular problem especially for small service organizations.
Figure 9 shows the type of maintenance activities implemented for the IVT group (percentage of Preventive Maintenance (PM) and Corrective Maintenance (CM)).
The proposed solution to this situation is to increase the number of preventive maintenance activities. For a production company, this would mean increasing the availability and reliability of transport vehicles, while for a servicing organization, it would help to plan the maintenance activities.
5 Conclusions
The method presented in the article, which supports decision making regarding service planning, can help companies providing maintenance outsourcing services. However, recently, along with new technologies such as RFID, various sensors, and wireless telecommunications as well as data control and acquisition, both the quantity and quality of IVT data during the period of their use is very high. Modern IVT with installed sensors and connected thanks to IoT technology can provide a very large amount of data describing their work and technical condition. It will enable companies that provide maintenance services to better plan their work, and thus to better manage human resources. The use of new technologies for planning service work seems to be an excellent strategy for any company providing maintenance services, looking for ways to perform services at the level of satisfying customers while effectively using their resources. It is also the direction of future research of the authors of this work.
References
Araújo, A.F., Varela, M.L.R., Gomes, M.S., Barreto, R.C.C., Trojanowska, J.: Development of an intelligent and automated system for lean industrial production adding maximum productivity and efficiency in the production process. In: Hamrol, A., Ciszak, O., Legutko, S., Jurczyk, M. (eds.) Advances in Manufacturing. LNME, pp.131‒140 (2018)
Jasiulewicz-Kaczmarek, M.: Practical aspects of the application of RCM to select optimal maintenance policy of the production line. In: Nowakowski, T., et al. (eds.) Safety and Reliability: Methodology and Applications - Proceedings of the European Safety and Reliability Conference, ESREL 2014, pp. 1187‒1195. Taylor & Francis Group, London (2015)
Burduk, A.: An attempt to adapt serial reliability structures for the needs of analyses and assessments of the risk in production systems. Eksploatacja i Niezawodnosc-Maintenance Reliab. 3, 85–96 (2010)
Garg, A., Deshmukh, S.: Maintenance management: literature review and directions. J. Qual. Maintenance Eng. 12(3), 205–238 (2006)
Jasiulewicz-Kaczmarek, M., Żywica, P.: The concept of maintenance sustainability performance assessment by integrating balanced scorecard with non-additive fuzzy integral. Eksploatacja i Niezawodnosc – Maintenance Reliab. 20(4), 650–661 (2018)
Gopalakrishnan, M., Skoogh, A.: Machine criticality based maintenance prioritization: identifying productivity improvement potential. Int. J. Prod. Perform. Manag. 67(4), 654–672 (2018)
Koochaki, J., Bokhorst, J.A.C., Wortmann, H., Klingenberg, W.: The influence of condition-based maintenance on workforce planning and maintenance scheduling. Int. J. Prod. Res. 51(8), 2339–2351 (2013)
Allahverdi, A.: The third comprehensive survey on scheduling problems with setup times/costs. Eur. J. Oper. Res. 246(2), 345–378 (2015)
Basri, E., Abdul Razak, I., Ab-Samat, H., Kamaruddin, S.: Preventive maintenance (PM) planning: a review. J. Qual. Maintenance Eng. 23(2), 114–143 (2017)
Baptista, M., Sankararaman, S., Medeiros, I.P., Nascimento, C., Jr., Prendinger, H., Henriques, E.M.P.: Forecasting fault events for predictive maintenance using data-driven techniques and ARMA modeling. Comput. Ind. Eng. 115, 41–53 (2018)
Gopalakrishnan, M., Skoogh, A., Laroque, C.: Simulation-based planning of maintenance activities in the automotive industry. In: Proceedings of the 2013 Winter Simulation Conference (2013)
Kujawińska, A., Diering, M., Żywicki, K., Rogalewicz, M., Hamrol, A., Hoffmann, P., Konstańczak, M.: Methodology supporting the planning of machining allowances in the wood industry. In: International Joint Conference SOCO 2017-CISIS 2017-ICEUTE 2017, León, Spain, 6–8 September 2017. Advances in Intelligent Systems and Computing, pp. 338‒347. Springer (2018)
Hedvall, K., Lind, F.: Analysing an activity in context: a case study of the conditions for vehicle maintenance. Ind. Mark. Manag. 58, 69–82 (2016)
Kujawińska, A., Diering, M., Rogalewicz, M., Żywicki, K., Hetman Ł.: Soft modelling-based methodology of raw material waste estimation. In: Intelligent Systems in Production Engineering and Maintenance – ISPEM 2017. Advances in Intelligent Systems and Computing, vol. 637, pp. 407‒417 (2017)
Parada, M., Madriz-Rodriguez, M.D., Castillo-Pedraza, M.: Productivity management system for the service sector in the San Cristobal municipality of Tachira state, Venezuela. Ciencia Unemi 11(26), 63–78 (2018)
Moyseenko, S.S., Moroz, E.O.: Optimization of the transport service system of fishing vessels. Mar. Intellect. Technol. 3(4), 168–176 (2018)
Vujanovic, D.B., Momcilovic, V.M.: A hybrid multi-criteria decision making model for the vehicle service center selection with the aim to increase the vehicle fleet energy efficiency. Therm. Sci. 22(3), 1549–1561 (2018)
Ratnayake, R.M.C., Antosz, K.: Risk based maintenance assessment in the manufacturing industry: minimization of suboptimal prioritization. Manag. Prod. Eng. Rev. 8(1), 38–45 (2017)
Burduk, A., Grzybowska, K., Safonyk, A.: The use of a hybrid model of the expert system for assessing the potentiality manufacturing the assumed quantity of wire harnesses. LogForum 15(4), 459–473 (2019)
Antosz, K., Stadnicka, D.: An intelligent system supporting a forklifts maintenance process. Advances in Intelligent Systems and Computing, vol. 637, pp. 13‒22 (2018)
Matlab, MATLAB 7.12.0 (R2019b): Fuzzy logic Toolbox, 1984–2019. The MathWorks, Inc. (2019)
Mathworks, Fuzzy inference system modelling: Gaussian combination membership function. www.mathworks.se/help/fuzzy/gauss2mf.html. Accessed 10 Oct 2019
Ross, T.: Fuzzy Logic in Engineering Applications, 3rd edn. Wiley, Singapore (2010)
Acknowledgements
The authors would like to acknowledge the employees of the service provider for delivered data and participation in this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Antosz, K., Jasiulewicz-Kaczmarek, M. (2021). Intelligent Predictive Decision Support System for the Maintenance Service Provider. In: Tonkonogyi, V., et al. Advanced Manufacturing Processes II . InterPartner 2020. Lecture Notes in Mechanical Engineering. Springer, Cham. https://doi.org/10.1007/978-3-030-68014-5_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-68014-5_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-68013-8
Online ISBN: 978-3-030-68014-5
eBook Packages: EngineeringEngineering (R0)