Process Control Methods Research Articles

Microstructure control of ultra-high-strength AlZnMgCu alloys fabricated by wire arc directed energy deposition: the role of variable polarity electric pulse

ABSTRACT In the manufacturing of large-scale ultra-high strength AlZnMgCu alloy components, wire arc directed energy deposition can be an efficient and flexible candidate. However, the fabricated AlZnMgCu alloys are faced with problems like coarse microstructures and high sensitivity to defects. Although metallurgical methods like micro-alloying and ceramic particle addition have shown considerable effects in microstructural control, pure process control methods that don’t affect the composition still lack investigation. This work proposed an effective control method by simply adding electric pulses during manufacturing. Results show that the application of pulses significantly reduces pore defects. A 2 Hz pulse can reduce the porosity by 65.7% to 0.122%. Low-frequency pulses effectively promote grain refinements. At 2 Hz, the deposited metal exhibited a mix of short columnar and fine equiaxed grains with a near-random orientation. Applying electric pulses leads to at least a 4.8% increase in UTS and a 225.0% increase in elongation.

Control Method For Processes in a Horizontal Organization and its Relationship with Business Success Aligned with the Sustainable Development Goals (SDG)

Objective: This study aims to develop an appropriate control method for a horizontal organization that is managed by processes, based on the establishment of the functioning of this type of organizations from a theoretical conceptual point of view and in application of the mathematical method to find an appropriate equation. Methodology: In this research, the descriptive and analytical approach was used, both to understand the functioning of the processes of the horizontal organization and to infer the relationship between the fulfillment of the objectives of the different types of processes, assigning a specific weight to each one according to its relative impact on the mission and formulating the equations whose development converged in the proposed control method. Results: The results show that this method not only provides an effective quantitative tool for strategic decision making, but also faithfully reflects the collaborative and decentralized nature of horizontal organizations. The practical application of the equation will allow managers to prioritize the most critical processes and align actions with strategic objectives and mission. Conclusions: The development of the work confirmed the possibility of generating a control method for a horizontal organization based on the evaluation of its processes, thus becoming a decision-making tool that ensures organizational success, a necessary condition for having efficient business structures that support the growth of society aligned with the Sustainable Development Goals (SDG).

MONITORING THE SAUSAGE PRODUCT USING LANEY DEMERIT CHART BASED ANALYTICAL HIERARCHY PROCESS

Ready-to-eat sausage is a food product that has a limited shelf life. Therefore, regularly monitoring the quality of packaged ready-to-eat sausage products is important to ensure that the products meet the established quality standards. Twelve types of product defects need to be observed in the final checking process to meet the quality standards, namely Wrinkle, Dots, Leaking, Product Stain, Non-standard Form, Poor Print Quality, Vacuum Leaks, Weak Ties, Body Defects, Uneven Length, Broken Node, and Small Stain. This study aims to apply the Laney Demerit Control Chart (LDCC) and Analytical Hierarchy Process-Integrated Statistical Process Control (AHP-ISPC) methods to monitor the quality of packaged ready-to-eat sausage production at XYZ Inc. The data is from the quality testing of ready-to-eat sausage products taken from XYZ Inc. for six months from April 1, 2023, until September 30, 2023. The findings reveal that conventional control charts (u control chart, demerit control chart, and AHP-based demerit control chart) exhibited oversensitivity because it is attributed to the large number of samples produced by the company, prompting the need for a more balanced approach. Implementing the Laney u control chart, Laney demerit control chart, and the AHP-based Laney demerit control charts successfully achieved statistical control in phase I. In contrast, phase II still demonstrated challenges, particularly with the AHP-based Laney Demerit Control Chart detecting the highest number of out-of-control points. This suggests that phase II remains statistically out of control, necessitating further analysis or corrective measures to enhance process stability. Additionally, the process capability analysis indicated that the production process during the specified period lacked capability, as evidenced by a capability index value below one (0.883).

A likelihood-based monitoring method for social networks with auto-correlated labeled Poisson model

Social network monitoring aims to detect any significant change in the structure of communications from the normal condition. The normal condition can be a set of networks considered as a reference set. This set is represented in dynamic cases by a probability model. Statistical process control methods can be applied to signal changes in the reference set. These signals can be useful for decision-makers in various applications, from marketing analysis to criminal investigations. In most of the developed models, the networks are assumed independent over time. However, this assumption may be questioned in real-world applications. Accordingly, this article formulates the social network as an auto-correlated labeled Poisson model and monitors it using a control method based on likelihood statistics. A simulation study is performed to evaluate the performance of the proposed methods in terms of the average run length criterion. The obtained results revealed that the proposed methods can reliably detect significant changes.

Enhancing Manufacturing Quality Through Statistical Process Control

In the manufacturing industry, statistical process control, often known as SPC, is a strong instrument that can improve both the quality of the product and the efficiency of the process. It comprises the utilization of statistical approaches for the purpose of monitoring and controlling a process in order to guarantee that it functions effectively and generates products that are of a consistently high grade. The statistical process control (SPC) method enables producers to identify variances, trends, and irregularities that may have an impact on product quality. This is accomplished by collecting and analyzing data from the production process. It is possible for manufacturers to discover and rectify problems in real time with the assistance of statistical process control (SPC), which is accomplished through the utilization of control charts, process capability analysis, and other statistical approaches. This results in decreased waste, greater productivity, and increased customer satisfaction. This article examines the fundamentals of statistical process control (SPC), as well as its application in manufacturing environments and the advantages it offers in terms of improving both product quality and process performance.

Reduction of Pediatric Gastrostomy Tube Healthcare Utilization and Socioeconomic Disparities: Longitudinal Benefits of Quality Improvement

BackgroundDisparities in emergency department (ED) utilization after gastrostomy (G-) tube placement were previously demonstrated at our children’s hospital. We aimed to reduce postoperative G-tube dislodgements and ED visits with a particular focus on socially vulnerable children. MethodsOur improvement team implemented a G-tube care bundle (6/2018-9/2019) targeting caregiver preparedness and standardizing care in the pre-, intra-, and post-operative periods. Patients who had G tubes placed between 1/2011-8/2022 were categorized to either pre- or post-intervention groups. Primary outcomes were tracked prospectively. National area deprivation index (ADI) was assigned retrospectively and employed to evaluate social risk. Univariate comparisons were made between pre- and post-intervention groups, and between High ADI (≥80) and Low ADI (<80) subgroups in both pre- and post- intervention periods. We used statistical process control methods to further analyze change over time. Results396 children were included (188 pre-intervention, 208 post-intervention). The post-intervention cohort demonstrated a lower rate of outpatient dislodgement at 90 days following G-tube placement (21.3% vs 10.1%, p=0.002) and fewer G-tube-related ED visits per G-tube placed within one year of placement (mean 0.8 visits vs 0.6 visits, p=0.012). Pre-intervention, children from high ADI neighborhoods had significantly greater healthcare utilization compared to those from lower ADI neighborhoods. Post-intervention, previously statistically significant disparities were no longer present. Outpatient G-tube dislodgements within 90 days were particularly mitigated. ConclusionsA longstanding quality improvement initiative has led to sustained reductions in overall G-tube-related health care utilization. Care standardization and improvement may mitigate outcome disparities related to socioeconomic advantage. Type of studyRetrospective Comparative Study and Prospective Quality Improvement Level of EvidenceLevel III

Analisis Pengendalian Kualitas Menggunakan Statistical Process Control untuk Mengurangi Produk Cacat pada Mebel UD Sadewo Jagat di Ngawi

UD Sadewo Jagat is a company engaged in furniture production, this company provides sales of finished, semi-finished products and maintenance for various types of teak wood furniture. Finished products include tables, chairs, shelves and various other types of displays. However, in this study, we only analyzed defective products for wooden box table products because the production process of wooden box table products because the production process of wooden box tables experienced problems, namely the number of defects exceending 5% of the company’s standard provisions. The aim of this research is to analyze product quality control techniques using the Statistical Process Control method in reducing defective products, and to find out what factors cause defects in products produced by UD Sadewo Jagat. This research uses the Statistical Process Control (SPC) method, which is one of the analytical methods used to analyze the causes of defects that occur, both in terms of product quality and in terms of the quality of the production process. Quality control analysis is carried out using. The results of the check sheet analysis show an average of 9,6% product defects per month. From the results of the Pareto diagram, it can be seen that the highest level of defects is crack defects, with a total of 80 units or 44,94% of total product defects in 2023. Meanwhile, the results of the control chart that has been made can be seen that quality control is uncontrolled and not according to standards. From the results of the fishbone diagram, it is concluced that the factors causing product defects are human factors, materials, environment, and methods.

Decreasing Invasive Urinary Tract Infection Screening in a Pediatric Emergency Department to Improve Quality of Care.

Obtaining urine samples in younger children undergoing urinary tract infection (UTI) screening can be challenging in busy emergency departments (EDs), and sterile techniques, like catheterization, are invasive, traumatizing, and time consuming to complete. Noninvasive techniques have been shown to reduce catheterization rates but are variably implemented. Our aim was to implement a standardized urine bag UTI screening approach in febrile children aged 6 to 24 months to decrease the number of unnecessary catheterizations by 50% without impacting ED length of stay (LOS) or return visits (RVs). After forming an interprofessional study team and engaging key stakeholders, a multipronged intervention strategy was developed using the Model for Improvement. A urine bag screening pathway was created and implemented using Plan, Do, Study Act (PDSA) cycles for children aged 6 to 24 months being evaluated for UTIs. A urine bag sample with point-of-care (POC) urinalysis (UA) was integrated as a screening approach. The outcome measure was the rate of ED urine catheterizations, and balancing measures included ED LOS and RVs. Statistical process control methods were used for analysis. During the 3-year study period from January 2019 to June 2022, the ED catheterization rate successfully decreased from a baseline of 73.3% to 37.7% and was sustained for approximately 2 years. Unnecessary urine cultures requiring microbiology processing decreased from 79.8% to 40.7%. The ED LOS initially decreased; however, it increased by 17 minutes during the last 8 months of the study. There was no change in RVs. A urine bag screening pathway was successfully implemented to decrease unnecessary, invasive catheterizations for UTI screening in children with only a slight increase in ED LOS. In addition to the urine bag pathway, an ED nursing champion, strategic alignment, and broad provider engagement were all instrumental in the initiative's success.

A novel RUL prediction method for rolling bearings based on dynamic control chart and adaptive incremental filtering

Abstract Degradation of rolling bearings typically consists of two stages: a stable stage (Stage I) characterized by stable fluctuations in the health indicator (HI), and a degradation stage (Stage II) where early damage leads to HI degradation, eventually reaching the failure threshold. Therefore, to achieve online RUL prediction for bearings, three aspects should be studied: 1) Degradation modeling; 2) Inter stage change point identification; 3) Online degradation state updating. Firstly, a two-stage degradation model is constructed by simultaneously considering inherent randomness, individual differences, and measurement errors. Then, a dynamic statistical process control (SPC) method is proposed to identify the change point from Stage I to Stage II. The SPC is designed to dynamically control limits based on the bearing's condition monitoring (CM) data to prevent false alarms. An adaptive incremental filtering (AIF) is proposed to update the degradation states by simultaneously considering the state increment and the dynamics of the system noise and measurement noise. The effectiveness of the proposed method is validated on 16004 bearing test data and XJTU-SY bearing data. Results show that the proposed method can accuracy identify the change point and improve the accuracy of the prediction result during stage II.&amp;#xD;

Analytical study on improving the efficiency and environmental friendliness of solid organic fuels

The purpose of this study was to analyse methods of increasing the efficiency and environmental friendliness of the use of solid organic fuels (SOF) in electricity generation. This study employed a comprehensive approach to the analysis and optimisation of technological processes, operational systems, and environmental aspects of the use of SOF. The study found that the use of modern technologies, such as gasification and pyrolysis, considerably increases the efficiency of converting SOF into electricity. Optimisation of boiler and turbine designs and automation of fuel supply systems helps to reduce energy losses and improve overall system efficiency. It was found that the use of new materials for boilers increases their resistance to corrosion and erosion, which extends the service life of the equipment. The study also showed that the introduction of gas cleaning and secondary combustion systems significantly reduces emissions of harmful substances, which improves environmental performance. An analysis of ash utilisation opportunities showed that its use as a fertiliser or construction material is a promising area. The study proved that an integrated approach to the use of SOF can substantially increase their efficiency and environmental friendliness. The findings of the study suggest that the use of innovative methods of combustion process control allows achieving more stable and efficient power generation. It was proved that the introduction of automated monitoring and control systems reduces operating costs and increases the reliability of equipment. The study also found that the use of advanced analytical tools to predict equipment wear and tear allows for prompt preventive maintenance, which further increases the efficiency and duration of uninterrupted operation of energy systems

Evaluation of Coal Supplied to Soma Thermal Power Plant (Türkiye) with Statistical Process Control Techniques

Statistical Process Control (SPC) is a method developed to ensure that production activities are carried out inaccordance with predetermined quality specifications and to minimize the production of defective products/goods bylargely preventing non-standard production. Various scientific methods are used when the calorific values of coal fed tothermal power plants are examined in terms of quality. In this study, the calorific values and other specifications of thecoal fed to the Soma Thermal Power Plant (Manisa/Türkiye) and whether the process is under control or not are examinedby considering the two-year data for tracking and monitoring the process with the Statistical Process Control (SPC)method, taking into account both the design conditions of the power plant and the production parameters. The adequacyof the processes for which stability analysis was performed was evaluated in the next stage. When the two-year controlcharts (

Effects of soldering temperature and preheating temperature on the properties of Sn–Zn solder alloys using wave soldering

Purpose This study aims to address the problem of low-temperature wave soldering in industry production with Sn-9Zn-2.5 Bi-1.5In alloys and develop qualified process parameters. Sn–Zn eutectic alloys are lead-free solders applied in consumer electronics due to their low melting point, high strength, and low cost. In the electronic assembly industry, Sn–Zn eutectic alloys have great potential for use. Design/methodology/approach This paper explored developing and implementing process parameters for low-temperature wave soldering of Sn–Zn alloys (SN-9ZN-2.5BI-1.5 In). A two-factor, three-level design of the experiments experiment was designed to simulate various conditions parameters encountered in Sn–Zn soldering, developed the nitrogen protection device of waving soldering and proposed the optimal process parameters to realize mass production of low-temperature wave soldering on Sn–Zn alloys. Findings The Sn-9Zn-2.5 Bi-1.5In alloy can overcome the Zn oxidation problem, achieve low-temperature wave soldering and meet IPC standards, but requires the development of nitrogen protection devices and the optimization of a series of process parameters. The design experiment reveals that preheating temperature, soldering temperature and flux affect failure phenomena. Finally, combined with the process test results, an effective method to support mass production. Research limitations/implications In term of overcome Zn’s oxidation characteristics, anti-oxidation wave welding device needs to be studied. Various process parameters need to be developed to achieve a welding process with lower temperature than that of lead solder(Sn–Pb) and lead-free SAC(Sn-0.3Ag-0.7Cu). The process window of Sn–Zn series alloy (Sn-9Zn-2.5 Bi-1.5In alloy) is narrow. A more stringent quality control chart is required to make mass production. Practical implications In this research, the soldering temperature of Sn-9Zn-2.5 Bi-1.5In is 5 °C and 25 °C lower than Sn–Pb and Sn-0.3Ag-0.7Cu(SAC0307). To the best of the authors’ knowledge, this work was the first time to apply Sn–Zn solder alloy under actual production conditions on wave soldering, which was of great significance for the study of wave soldering of the same kind of solder alloy. Social implications Low-temperature wave soldering can supported green manufacturing widely, offering a new path to achieve carbon emissions for many factories and also combat to international climate change. Originality/value There are many research papers on Sn–Zn alloys, but methods of achieving low-temperature wave soldering to meet IPC standards are infrequent. Especially the process control method that can be mass-produced is more challenging. In addition, the metal storage is very high and the cost is relatively low, which is of great help to provide enterprise competitiveness and can also support the development of green manufacturing, which has a good role in promoting the broader development of the Sn–Zn series.

Pointwise profile monitoring considering covariates based on Gaussian process

In the intelligent manufacturing process, sensors are increasingly becoming an important means of measurement and data acquisition. Profile data from sensors are generally huge, irregular, and correlated. Meanwhile, profiles are usually affected by many external factors, which are referred to as covariates in this paper. Existing statistical process control methods are mainly based on statistical models, which have many limitations in dealing with such complex profile data. Motivated by the real life problem of industrial busbar temperature monitoring, this paper proposes a nonparametric pointwise profile monitoring scheme for unbalanced data considering time varying covariates. The developed Gaussian process-based model provides flexibility for predicting autocorrelated profiles. To incorporate time varying covariates, the Gaussian process model kernel is modified by an automatic relevance determination structure. The control chart is then constructed based on the difference between the observed and predicted profiles. Instantaneous anomalies within a profile can be detected by pointwise monitoring without waiting for the entire profile data collection. The effectiveness and applicability of the proposed monitoring scheme are validated by both simulations and a real case of busbar temperature monitoring in the workshop of an automotive manufacturer.

P‐260: Late‐News Poster: Doping Ratio Control of Organic Composite Layer in OELDs by Spectroscopic Ellipsometry

The OLEDs industry needs a reliable nondestructive process control method for measuring the correct thickness of layers and estimation of doping or mixing ratio. Using spectroscopic ellipsometry, we applied for thickness and doping ratio monitoring for emission layer (EML) and mixed electron transport layer (mETL) grown on glass by evaporator. Optical properties of EML host and dopant, mETL host and mixing material have been investigated. We present the effect of doping on optical constants dispersions of EML and mETL layers in the photon energy range 1.2 to 5.0 eV. We adopted the Effective Medium Theory (EMT) to monitoring mixing ratio and dispersion equation to monitoring doping ratio. In result developed monitoring tool can measure imperceptible difference doping ratio.

Quality 4.0: Learning quality control, the evolution of SQC/SPC

This article marks a significant advancement in the field of quality management, specifically focusing on the evolution from traditional Statistical Quality Control (SQC) and Statistical Process Control (SPC) methods to a more advanced Learning Quality Control (LQC) approach. The research introduces Quality 4.0 (Q4.0) as a novel paradigm that fuses the technologies of the fourth industrial revolution, Manufacturing Big Data (MBD), Industrial Internet of Things (IIoT), Cloud Storage and Computing (CSC) and Artificial Intelligence (AI), with traditional quality management practices. The central theme of this study is exploring the limitations inherent in conventional quality control methods when faced with the complexities of modern manufacturing environments. The authors propose LQC systems as a solution, employing binary classification algorithms to predict and detect defects in manufacturing processes. This represents a shift from reactive to proactive quality measures enabled by AI’s real-time data processing capabilities. The document delves into the evolution of manufacturing data across industrial revolutions, highlighting the exponential growth of unstructured data and its challenges. Through case studies, the authors illustrate the practical applications of LQC systems, demonstrating their ability to learn complex patterns in hyperdimensional spaces and automate tasks traditionally performed visually.

Online nonparametric process monitoring for IoT systems using edge computing

Facilitated by modern sensing and integrated circuit technology, Internet of Things (IoT) systems now have the ability to intelligently and automatically collect data, perform computational tasks on an edge, and efficiently make decisions locally or remotely. However, existing multivariate statistical process control methods commonly assume that sensors directly transmit the raw measurements to the central server, and thus the edge computing capability of IoT systems is not effectively harnessed. To fill this literature gap, we propose a monitoring scheme tailored for IoT systems by leveraging their edge computational power. In particular, inspired by the inherent hierarchical structure of the IoT system, we construct the monitoring statistics hierarchically. At each edge device, we first construct a nonparametric stream-level statistic for each data stream and aggregate them to derive the device-level statistics. To eliminate the inconsistency in device-level statistics across different edge devices, the device-level statistics are transformed into time-related statistics, which are then sent to the central server. At the central server, a system-level monitoring statistic is constructed, and the most informative edge devices that should transmit statistics are intelligently determined. Theoretical analyses are carried out to justify the effectiveness of the data transmission strategy. Both simulations and a case study, which is based on an IoT system we built, are conducted to evaluate the performance and validate the superiority of the proposed monitoring scheme.

Development of an indirect measurement method for the Contact Tube to Workpiece Distance (CTDW) in the Direct Energy Deposition – Arc (DED-ARC) process for different arc types

During the layer-by-layer build-up in the Direct Energy Deposition (DED) - Arc additive manufacturing (AM) process, the distance between the contact tube and the workpiece, effectively the welded layer, changes. Since the weld paths are predefined by the path planning software, a constant Contact Tube to Workpiece Distance (CTWD) and weld bead height is assumed. However, even small changes in geometry, such as crossovers of weld paths, result in higher weld beads than assumed. Similarly, an incorrectly assumed bead height as input to the path planning will result in a change in the CTWD. The sum of the deviations of the real weld geometries from the assumed ones in the path planning can greatly influence the CTWD. This implies that the dimensional accuracy may be significantly compromised. This research presents an approach for a general indirect measurement method using the welding current to obtain the CTWD during the actual welding process. A real-time process control method is implemented and validated using the mechanically controlled short arc and the pulsed arc process. Varying process parameters are used to validate the general applicability for a specific material. For the mechanically controlled short arc process, the model underestimates the measured CTWD by a mean error of 3.4 mm. The pulse process is overestimated by a mean error of 2.2 mm. The standard deviation for the pulse process with 1.3 mm is slightly smaller than for the short arc process with 1.7 mm.

From laboratory to industrial use: Understanding process variation during enzymatic protein hydrolysis with dry film fourier-transform infrared spectroscopy

Industries are continuously looking for dedicated sensor solutions for evaluating the chemical composition of products that can provide valuable insights into process control, process optimization, and product quality. A rapid and robust analytical method, Fourier-Transform Infrared (FTIR) spectroscopy, holds significant potential in this regard as it provides detailed compositional values of food nutrients. The main aim of the present study was to use dry film FTIR spectroscopy as an analytical tool to characterize products from an industrial enzymatic protein hydrolysis process and link this to understand industrial process variations. For this purpose, 463 protein hydrolysate samples were obtained from an industrial enzymatic protein hydrolysis plant. In the same period, systematic variations in process parameters such as raw material composition, enzyme type, and water addition, were performed. All samples were analyzed using dry film FTIR spectroscopy. Two subsets containing 200 and 68 hydrolysate samples were chosen for measuring average molecular weight (AMW) and collagen content respectively, providing reference data for constructing calibration models based on partial least squares regression (PLSR). The percentage of low molecular weight constituents was derived from the molecular weight distribution of size exclusion chromatograms of protein hydrolysates and also used in the modeling. Calibration models for the prediction of AMW, low molecular weight constituents, and collagen content were obtained with a good fit and lower estimation errors. Principal component analysis (PCA) of protein hydrolysates' FTIR spectra effectively differentiated process variations (enzyme types and raw materials) without extensive reference analysis. One-factor analysis of variance (ANOVA) tests was used to observe the impact of process variation on product quality. FTIR proved to be a sensitive method for liquid protein analysis and process control with a significant potential in process optimization approaches. To the authors’ knowledge, this is the first time dry film FTIR spectroscopy has been used to evaluate an industrial bioprocess with designed process variations.

A variable sampling interval EWMA control chart for urinary tract infections data

Control chart is an important method in Statistical Process Control, which is used to study how a process changes over time. The exponential distribution is one of the commonly used models for fitting data, especially in areas such as component life, aviation accidents, or health-care processes. In order to further improve the sensitivity of the control chart, we propose an exponentially weighted moving average control chart with a variable sampling interval scheme, denoted as VSIEWMA-T control chart, for monitoring exponentially distributed quality characteristics (e.g. Urinary Tract Infections data). In this paper, the average time to signal property of the proposed control chart is investigated using the Markov chain method. In addition, parameter optimization algorithms for known or unknown shift levels are provided. Subsequently, numerical analysis shows that the proposed control chart outperforms other competitive control charts. Finally, an example of urinary tract infections data is provided for illustration.

Optimal operation of reverse osmosis desalination process with deep reinforcement learning methods

The reverse osmosis (RO) process is a well-established desalination technology, wherein energy-efficient techniques and advanced process control methods significantly reduce production costs. This study proposes an optimal real-time management method to minimize the total daily operation cost of an RO desalination plant, integrating a storage tank system to meet varying daily freshwater demand. Utilizing the dynamic model of the RO process, a cascade structure with two reinforcement learning (RL) agents, namely the deep deterministic policy gradient (DDPG) and deep Q-Network (DQN), is developed to optimize the operation of the RO plant. The DDPG agent, manipulating the high-pressure pump, controls the permeate flow rate to track a reference setpoint value. Simultaneously, the DQN agent selects the optimal setpoint value and communicates it to the DDPG controller to minimize the plant’s operation cost. Monitoring storage tanks, permeate flow rates, and water demand enables the DQN agent to determine the required amount of permeate water, optimizing water quality and energy consumption. Additionally, the DQN agent monitors the storage tank’s water level to prevent overflow or underflow of permeate water. Simulation results demonstrate the effectiveness and practicality of the designed RL agents.