Applying Job Shop Scheduling to SMEs Manufacturing Platform to Revitalize B2B Relationship

A small and medium enterprises(SMEs)manufacturing platform aims to perform as a significant revenue to SMEs and vendors by providing scheduling and monitoring capabilities.The optimal job shop scheduling is generated by utilizing the scheduling system of the platform,and a minimum production time,i.e.,makespan decides whether the scheduling is optimal or not.This scheduling result allows manufacturers to achieve high productivity,energy savings,and customer satisfaction.Manufacturing in Industry 4.0 requires dynamic,uncertain,complex production environments,and customer-centered services.This paper proposes a novel method for solving the difficulties of the SMEs manufacturing by applying and implementing the job shop scheduling system on a SMEs manufacturing platform.The primary purpose of the SMEs manufacturing platform is to improve the B2B relationship between manufacturing companies and vendors.The platform also serves qualified and satisfactory production opportunities for buyers and producers by meeting two key factors:early delivery date and fulfillment of processing as many orders as possible.The genetic algorithm(GA)-based scheduling method results indicated that the proposed platform enables SME manufacturers to obtain optimized schedules by solving the job shop scheduling problem(JSSP)by comparing with the real-world data from a textile weaving factory in South Korea.The proposed platform will provide producers with an optimal production schedule,introduce new producers to buyers,and eventually foster relationships and mutual economic interests.

Accurate Multi-Scale Feature Fusion CNN for Time Series Classification in Smart Factory

Time series classification(TSC)has attracted various attention in the community of machine learning and data mining and has many successful applications such as fault detection and product identification in the process of building a smart factory.However,it is still challenging for the efficiency and accuracy of classification due to complexity,multi-dimension of time series.This paper presents a new approach for time series classification based on convolutional neural networks(CNN).The proposed method contains three parts:short-time gap feature extraction,multi-scale local feature learning,and global feature learning.In the process of short-time gap feature extraction,large kernel filters are employed to extract the features within the short-time gap from the raw time series.Then,a multi-scale feature extraction technique is applied in the process of multi-scale local feature learning to obtain detailed representations.The global convolution operation with giant stride is to obtain a robust and global feature representation.The comprehension features used for classifying are a fusion of short time gap feature representations,local multi-scale feature representations,and global feature representations.To test the efficiency of the proposed method named multi-scale feature fusion convolutional neural networks(MSFFCNN),we designed,trained MSFFCNN on some public sensors,device,and simulated control time series data sets.The comparative studies indicate our proposed MSFFCNN outperforms other alternatives,and we also provided a detailed analysis of the proposed MSFFCNN.

Accurate Multi-Site Daily-Ahead Multi-Step PM_(2.5)Concentrations Forecasting Using Space-Shared CNN-LSTM

Accurate multi-step PM_(2.5)(particulate matter with diameters≤2.5 um)concentration prediction is critical for humankinds’health and air populationmanagement because it could provide strong evidence for decisionmaking.However,it is very challenging due to its randomness and variability.This paper proposed a novel method based on convolutional neural network(CNN)and long-short-term memory(LSTM)with a space-shared mechanism,named space-shared CNN-LSTM(SCNN-LSTM)for multi-site dailyahead multi-step PM_(2.5)forecasting with self-historical series.The proposed SCNN-LSTM contains multi-channel inputs,each channel corresponding to one-site historical PM_(2.5)concentration series.In which,CNN and LSTM are used to extract each site’s rich hidden feature representations in a stack mode.Especially,CNN is to extract the hidden short-time gap PM_(2.5)concentration patterns;LSTM is to mine the hidden features with long-time dependency.Each channel extracted features aremerged as the comprehensive features for future multi-step PM_(2.5)concentration forecasting.Besides,the space-shared mechanism is implemented by multi-loss functions to achieve space information sharing.Therefore,the final features are the fusion of short-time gap,long-time dependency,and space information,which enables forecasting more accurately.To validate the proposed method’s effectiveness,the authors designed,trained,and compared it with various leading methods in terms of RMSE,MAE,MAPE,and R^(2)on four real-word PM_(2.5)data sets in Seoul,South Korea.The massive experiments proved that the proposed method could accurately forecast multi-site multi-step PM_(2.5)concentration only using self-historical PM_(2.5)concentration time series and running once.Specifically,the proposed method obtained averaged RMSE of 8.05,MAE of 5.04,MAPE of 23.96%,and R^(2)of 0.7 for four-site daily ahead 10-hourPM_(2.5)concentration forecasting.

Dynamic PIV Measurement of a Compressible Flow Issuing from an Airbag Inflator Nozzle

Among many equipment for passenger safety, the air bag system is the most fundamental and effective device for an automobile. The inflator housing is a main part of the curtain-type air bag system, which supplies high-pressure gases in pumping up the air bag-curtain which is increasingly being adapted in deluxe cars for protecting passengers from the danger of side clash. However, flow information on the inflator housing is very limited. In this study, we measure the instantaneous velocity fields of a high-speed compressible flow issuing from the exit nozzle of an inflator housing using a dynamic PIV system. From the velocity field data measured at a high frame-rate, we evaluate the variation of the mass flow rate with time. The dynamic PIV system consists of a high-repetition Nd：YLF laser, a high-speed CMOS camera, and a delay generator. The flow images are taken at 4000 fps with synchronization of the trigger signal for inflator ignition. From the instantaneous velocity field data of flow ejecting from the airbag inflator housing at the initial stage, we can see a flow pattern of broken shock wave front and its downward propagation. The flow ejecting from the inflator housing is found to have very high velocity fluctuations, with the maximum velocity at about 700 m/s. The time duration of the high-speed flow is very short, and there is no perceptible flow after 100 ms.