A novel framework for predicting non-stationary production time series of shale gas based on BiLSTM-RF-MPA deep fusion model

Shale gas, as an environmentally friendly fossil energy resource, has gained significant commercial development and shows immense potential. However, accurately predicting shale gas production faces substantial challenges due to the complex law of decline, nonlinear and non-stationary features in production data, which greatly repair the robustness of current models in predicting shale gas production time series. To address these challenges and improve accuracy in production forecasting, this paper introduces a novel and innovative approach: a hybrid proxy model that combines the bidirectional long short-term memory(BiLSTM) neural network and random forest(RF) through deep learning. The BiLSTM neural network is adept at capturing long-term dependencies, making it suitable for understanding the intricate relationships between input and output variables in shale gas production.On the other hand, RF serves a dual purpose: reducing model variance and addressing the concept drift problem that arises in non-stationary time series predictions made by BiLSTM. By integrating these two models, the hybrid approach effectively captures the inherent dependencies present in long and nonstationary production time series, thereby reducing model uncertainty. Furthermore, the combination of BiLSTM and RF is optimized using the recently-proposed marine predators algorithm(MPA) to fine-tune hyperparameters and enhance the overall performance of the proxy model. The results demonstrate that the proposed BiLSTM-RF-MPA model achieves higher prediction accuracy and demonstrates stronger generalization capabilities by effectively handling the complex nonlinear and non-stationary characteristics of shale gas production time series. Compared to other models such as LSTM, BiLSTM, and RF, the proposed model exhibits superior fitting and prediction performance, with an average improvement in performance indicators exceeding 20%. This innovative framework provides valuable insights for forecasting the complex production performance of unconventional oil and gas reservoirs, which sheds light on the development of data-driven proxy models in the field of subsurface energy utilization.

RECONFIGURABLE PRODUCTION LINE MODELING AND SCHEDULING USING PETRI NETS AND GENETIC ALGORITHM

In response to the production capacity and functionality variations, a genetic algorithm （GA） embedded with deterministic timed Petri nets（DTPN） for reconfigurable production line（RPL） is proposed to solve its scheduling problem. The basic DTPN modules are presented to model the corresponding variable structures in RPL, and then the scheduling model of the whole RPL is constructed. And in the scheduling algorithm, firing sequences of the Petri nets model are used as chromosomes, thus the selection, crossover, and mutation operator do not deal with the elements in the problem space, but the elements of Petri nets model. Accordingly, all the algorithms for GA operations embedded with Petri nets model are proposed. Moreover, the new weighted single-objective optimization based on reconfiguration cost and E/T is used. The results of a DC motor RPL scheduling suggest that the presented DTPN-GA scheduling algorithm has a significant impact on RPL scheduling, and provide obvious improvements over the conventional scheduling method in practice that meets duedate, minimizes reconfiguration cost, and enhances cost effectivity.

ANALYSIS AND IMPROVEMENT OF LEAD TIME FOR JOB SHOP UNDER MIXED PRODUCTION SYSTEM

Firstly an overview of the potential impact on work-in-process （WIP） and lead time is provided when transfer lot sizes are undifferentiated from processing lot sizes. Simple performance examples are compared to those from a shop with one-piece transfer lots. Next, a mathematical programming model for minimizing lead time in the mixed-model job shop is presented, in which one-piece transfer lots are used. Key factors affecting lead time are found by analyzing the sum of the longest setup time of individual items among the shared processes （SLST） and the longest processing time of individual items among processes （LPT）. And lead time can be minimized by cutting down the SLST and LPT. Reduction of the SLST is described as a traveling salesman problem （TSP）, and the minimum of the SLST is solved through job shop scheduling. Removing the bottleneck and leveling the production line optimize the LPT. If the number of items produced is small, the routings are relatively short, and items and facilities are changed infrequently, the optimal schedule will remain valid. Finally a brief example serves to illustrate the method.

MIP Formulations and Metaheuristics for Multi-Item Capacitated Lot-Sizing Problem with Non-Customer Specific Production Time Windows and Setup Times

Our research focuses on the development of two cooperative approaches for resolution of the multi-item capacitated lot-sizing problems with time windows and setup times (MICLSP-TW-ST). In this paper we combine variable neighborhood search and accurate mixed integer programming (VNS-MIP) to solve MICLSP-TW-ST. It concerns so a particularly important and difficult problem in production planning. This problem is NP-hard in the strong sense. Moreover, it is very difficult to solve with an exact method;it is for that reason we have made use of the approximate methods. We improved the variable neighborhood search (VNS) algorithm, which is efficient for solving hard combinatorial optimization problems. This problem can be viewed as an optimization problem with mixed variables (binary variables and real variables). The new VNS algorithm was tested against 540 benchmark problems. The performance of most of our approaches was satisfactory and performed better than the algorithms already proposed in the literature.

A Roadmap to Lean Production Implementation for Small Scale Nigerian Wire and Cable Companies

The increasing customers＇ demands in terms of speed of service and reduced cost at higher quality has generated a new platform on which manufacturing companies compete. This heightened challenge is virtually driving all manufacturing companies to introducing lean manufacturing principles into their production systems. This paper focuses on the analysis of the current state mapping of a case study and then proposes a future state mapping to the company. The extruder 60 production line of Denki wires and cables limited, Akure, Nigeria was carefully evaluated. Data were collected from actual operators on the shop floor and feedbacks from the customers at the Gemba. Denki＇s extruder 60 production line production lead time was massively reduced from 38.42 days to 5.16 days with a 12.86% waste reduction. At the end, a practical way of implementing this aspect of lean manufacturing was suggested.

National Plan for Non-ferrous Metals Production Fulfilled ahead of Time

Vice president of China National Nonferrous Metals Industries Corporation Mr. WoTingshu said:"The output of 10 kinds of nonferrous metals amounted to 2.45 Mt." This factmean1s that the national plan for nonferrous metals production fulfiled earlier. The 10 kinds ofnonferrous metals are aluminium, magnesium, lead, zinc, copper, tin, nickel, antimony mercuryand titanium.

Data-driven approaches for time series prediction of daily production in the Sulige tight gas field, China

The Sulige tight gas field is presently the largest gas field in China.Owing to the ultralow permeability and strong heterogeneity of the reservoirs in Sulige,the number of production wells has exceeded 3,000,keeping the stable gas supply in the decade.Thus,the daily production prediction of gas wells is significant for monitoring production and for implementing and evaluating stimulation measures.Therefore,on the basis of the three datadriven time series approaches,the daily production of 1692 wells over 10 years was mining for the daily production prediction of wells in Sulige.The jointed deep long short-term memory and fully connected neural network(DLSTM-FNN)model was proposed by introducing the recurrent neural network's sequential expression ability and was compared with random forest(RF)and support vector regression(SVR).After the daily production predictions of thousands of wells in Sulige,the proposed DLSTM-FNN model significantly improved the time series prediction accuracy and efficiency in the short training samples and had strong availability and practicability in the Sulige tight gas field.

The optimal fractional Gabor transform based on the adaptive window function and its application

We designed the window function of the optimal Gabor transform based on the time-frequency rotation property of the fractional Fourier transform. Thus, we obtained the adaptive optimal Gabor transform in the fractional domain and improved the time-frequency concentration of the Gabor transform. The algorithm first searches for the optimal rotation factor, then performs the p-th FrFT of the signal and, finally, performs time and frequency analysis of the FrFT result. Finally, the algorithm rotates the plane in the fractional domain back to the normal time-frequency plane. This promotes the application of FrFT in the field of high-resolution reservoir prediction. Additionally, we proposed an adaptive search method for the optimal rotation factor using the Parseval principle in the fractional domain, which simplifies the algorithm. We carried out spectrum decomposition of the seismic signal, which showed that the instantaneous frequency slices obtained by the proposed algorithm are superior to the ones obtained by the traditional Gabor transform. The adaptive time frequency analysis is of great significance to seismic signal processing.

Switchable down-,up-and dual-chirped microwave waveform generation with improved time–bandwidth product based on polarization modulation and phase encoding

A switchable down-,up-and dual-chirped microwave waveform generation technique with improved time–bandwidth product(TBWP)is proposed and demonstrated based on a dual-polarization dual-parallel Mach–Zehnder modulator(DPDPMZM)cascaded with a polarization modulator(Pol M).By properly controlling the phase shifts of the radio frequency signals applied to the DP-DPMZM,switchable down-,up-and dual-chirped waveforms with simultaneous frequency and bandwidth doubling can be generated.To enlarge the TBWP further,splitting parabolic signal and phase-encoding splitting parabolic signal are used to drive the Pol M for the enhancement of bandwidth and time duration.Numerical results demonstrate the generation of down-,up-and dual-chirped microwave waveform with TBWP of 8,160 and 10240.The proposed method may find applications in future multifunction radar systems due to the high performance and flexibility.

Eco-Friendly Knit Garments Washing Implementation and Its Impact

Environment pollution is one of the major threats to today’s world and researchers say most of the pollution comes from the washing industry.So,the study aims to find out an alternative way to the existing chemical wash process of the washing industry to save the environment.To conduct this study,one knit washing factory has been selected that has eco-friendly wash facilities.The eco-friendly wash process samples have been developed and finally show the comparison in respect of time,per day production and test result to the conventional chemical wash processes along with the impact of production cost on the garment.For all eco-friendly process,it has been found that water consumptions are too less in comparison with conventional process potentials which is partially related to Sustainable Development Goals 13(Climate Action).This study might help to find out a new era of doing washed knitted product business without polluting the environment.

An inventory model under development cost-dependent imperfect production and reliability-dependent demand

This paper considers a model that deals with an imperfect production process where both perfect and imperfect quality items are produced.Here,demand depends on selling price and reliability of the product.Each manufacturing company expects to produce perfect quality items.But due to the long-run process,several kinds of problem such as labor,machinery,and technology arise.As a result,the manufacturing system becomes out-of-control state and consequently produces both perfect and imperfect quality items.Perfect items are ready to sell but imperfect items are reworked at a cost to become perfect.Reworking cost,reliability of the product and reliability parameter of the manufacturing system can be improved by introducing the development cost and also by improving the quality of the raw material of the production system.Under such circumstances,a profit function has been developed to find the optimum values of reliability parameter of the manufacturing system,reliability of the product and duration of production such that a manufacturer gets a maximum profit.Finally,the model has been illustrated with some numerical examples exploring the sensitivity analysis with respect to some parameters.

A review on casing while drilling technology for oil and gas production with well control model and economical analysis

The extraction of petroleum fluids from sub-surface accumulations mandates the drilling of a well into the formation containing the accumulation.The drilling techniques have evolved over time to overcome several challenges while some of the issues still prevail with the currently used drilling practices like loss circulation,large tripping time to change bottom hole assembly,stuck pipe problems and low well bore stability,to name a few.These decrease the drilling efficiency and increase the Non-Productive Time(NPT)of this highly capitalintensive industry encouraging the Petroleum Industry to look for new technology.Casing while Drilling(CwD)is a technique of drilling which has been proven to alleviate many of the problems faced while drilling.In this method,drilling and casing of a well bore is carried out simultaneously,which improves the drilling efficiency by reducing the NPT.It has proven to be beneficial in controlling loss circulation and improving wellbore stability by‘Plastering’effect,high quality cement job and increased rig floor safety.It uses smaller rig and less fuel thereby reducing carbon footprint in the environment.This paper studies comprehensive well control and casing string design consideration.Economics encourages its application that has been discussed in the paper.A case study on the application of CwD in Malay basin for top hole drilling is presented.Finally,the paper briefly outlines the technical challenges that need attention to get better results from CwD.

Therapeutic effect of acupuncture point injection with placental extract in knee osteoarthritis

OBJECTIVE： This study evaluated the effectiveness of acupuncture point injection （API） with placenta extract on pain reduction and joint function in patients with knee osteoarthritis （OA）. METHODS： Fifty-two patients with knee OA, with an average age of 64, and having a symptom duration of more than 3 months were studied in this report. Placental extract was injected weekly into acupuncture point ST35, BL23, BL24 and BL25 for 5 weeks; 8 mL of placental extract into ST35 on the affected side, and 1 mL of placental extract to BL23, BL24 and BL25 bilaterally. RESULTS： After a five-week treatment of API with placental extract, pain was substantially decreased in patients of all Kellgren-Lawrence （KL） grades. Improvement of knee joint swelling was also apparent Decrease of pain and joint swelling improved daily working productive time among patients of all KL grades. CONCLUSION： Study results imply that API with placental extract is a potentially useful therapy to control pain and maintain joint functions in knee OA patients.

China's textile and garment industry productivity 14 times the U.S.

Chinese Academy of Social Sciences released the "China Industry Competitiveness Report(2012) NO.2",Guo Chaoxian,deputy director of Industrial Organization Office of Academy of Social Sciences Institute of Industrial Economics,said that