Process Parameters For Production Research Articles

Ultra-early prediction of the process parameters of coal chemical production

Most accidents in a chemical process are caused by abnormal or deviations of the process parameters, and the existing research is focused on short-term prediction. When the early warning time is advanced, many false and missing alarms will occur in the system, which will cause certain problems for on-site personnel; how to ensure the accuracy of early warning as much as possible while the early warning time is a technical problem requiring an urgent solution. In the present work, a bidirectional long short-term memory network (BiLSTM) model was established according to the temporal variation characteristics of process parameters, and the Whale optimization algorithm (WOA) was used to optimize the model's hyperparameters automatically. The predicted value was further constructed as a Modified Inverted Normal Loss Function (MINLF), and the probability of abnormal fluctuations of process parameters was calculated using the residual time theory. Finally, the WOA-BiLSTM-MINLF process parameter prediction model with inherent risk and trend risk was established, and the fluctuation process of the process parameters was transformed into dynamic risk values. The results show that the prediction model alarms 16 min ahead of distributed control systems (DCS), which can reserve enough time for operators to take safety protection measures in advance and prevent accidents.

Characterization of Interfacial Corrosion Behavior of Hybrid Laminate EN AW-6082 ∪ CFRP.

The corrosion behavior of a hybrid laminate consisting of laser-structured aluminum EN AW-6082 ∪ carbon fiber-reinforced polymer was investigated. Specimens were corroded in aqueous NaCl electrolyte (0.1 mol/L) over a period of up to 31 days and characterized continuously by means of scanning electron and light microscopy, supplemented by energy dispersive X-ray spectroscopy. Comparative linear sweep voltammetry was employed on the first and seventh day of the corrosion experiment. The influence of different laser morphologies and production process parameters on corrosion behavior was compared. The corrosion reaction mainly arises from the aluminum component and shows distinct differences in long-term corrosion morphology between pure EN AW-6082 and the hybrid laminate. Compared to short-term investigations, a strong influence of galvanic corrosion on the interface is assumed. No distinct influences of different laser structuring and process parameters on the corrosion behavior were detected. Weight measurements suggest a continuous loss of mass attributed to the detachment of corrosion products.

Optimization of formulation and processing conditions for the production of functional noodles containing orange-fleshed sweet potatoes and biofortified beans.

The global demand for noodles continues to increase due to their convenience, wide appeal, and affordability. Instant noodles, in particular, are popular for their easy preparation. With annual consumption reaching 106 billion servings in 2019, there is a growing awareness of the importance of healthy food options. However, most noodle types currently available commercially are of low nutritional value. This study sought to develop a protocol for the production of functional noodles consisting of orange-fleshed sweet potatoes (OFSP) puree and biofortified bean powder (BBP). Response surface methodology (RSM) was used to optimize product formulation and processing parameters. Reduced quartic models were found to adequately represent the relationship between dependent variables (hardness, moisture, protein, dietary fiber, iron, and zinc content) and independent variables (dough thickness, drying temperature, and drying time). R 2 values were 0.86-0.99, with a nonsignificant lack-of-fit (p < .05). Using numerical optimization, the optimal protocol for the production of functional noodles was determined to include formulation consisting of wheat 73%, OFSP 21.5%, and BBP 5.5%; dough thickness of 2.0 mm; drying temperature and time of 80.0°C and 143.4 min, respectively. These conditions yielded noodles with 5.9% moisture, 11.0 N hardness, 34.5% protein, 11.9% dietary fiber, 86.9 ppm (parts per million) iron, and 50.53 ppm zinc, with a desirability value of 0.82. Experimental validation demonstrated no significant difference from predicted values. Sensory evaluation rated the noodles as acceptable to consumers, with an overall acceptability of 7.8 on a 9-point hedonic scale. These results show the potential of OFSP and BBP as ingredients for acceptable and nutrient-rich noodles.

LIQUID NEURAL NETWORKS: PRINCIPLE OF WORK AND AREAS OF APPLICATION

The article deals with the architecture of liquid neural networks (LNN) and their potential in modern technologies. Thanks to the constant development of algorithms and hardware, neural networks are becoming more and more powerful and efficient, which opens up new opportunities for their application. The authors describe the principle of operation of liquid neural networks, which includes the process of learning and inference, which allows effective use of the natural dynamics of the system to solve various tasks, including classification, prediction, and control. We note that the concept of LNNs arose as an attempt to overcome some of the limitations and problems faced by traditional neural networks. The study considers the basic concepts and principles of LNNs and their application potential in various fields, from robotics to medicine and industry. The study also determines the main advantages and disadvantages of LNNs compared to traditional models. It is possible to use them to process a large stream of data, such as video, audio, or sensory data from various sensor types, allowing robots to receive information about their environment and make decisions based on that data. In medical diagnostics and image processing, liquid neural networks can significantly contribute to the quality and efficiency of diagnostic procedures. LNNs can enable the implementation of automatic control systems that monitor and regulate parameters of production processes or adapt to changes in the environment and optimise parameters to achieve maximum productivity and product quality. The field of LNN lacks standards and is limited to using performance metrics. Establishing standards and objective metrics will allow researchers and engineers to understand and compare different LNN implementations. Although LNNs are relatively efficient in terms of power consumption, their implementation at the hardware level may require new technologies and architectures to optimise performance. As a result, the study outlines the prospects for the further development of this technology. Keywords: liquid neural networks, artificial intelligence, adaptive control, learning efficiency, application potential.

Legume Fortified Instant Noodles: Optimization of Product Formulation and Processing Parameters using Response Surface Methodology

Cereal-pulses-based fortification has been attempted to improve the protein and dietary fibre content of instant noodles without altering the overall acceptability. Response surface methodology (RSM) was employed to optimize the process parameters and level of ingredients for manufacturing instant noodles. The effect of maize flour and split yellow pea flour fortification (6-18% each), the addition of vital wheat gluten (0.4-2.0%), and steaming time (1.5-7.5 min) on cooking loss, water uptake, volume expansion, cooking time, overall acceptability, L*, a* and b* values were investigated using the central composite rotatable design (CCRD). Results showed that maize flour and split yellow pea flour significantly (p≤0.05) affected cooking loss, water uptake, volume expansion, cooking time, overall acceptability, L*, a*, and b* values at linear levels. Vital wheat gluten had a significant effect on cooking loss, overall acceptability, L*, and a* value. Steaming time had a significant interactive effect with split yellow pea flour and vital wheat gluten on the responses. Incorporation of 18.0% maize flour, 11.25% split yellow pea flour, and 0.4% vital wheat gluten in formulation with 5.87 minutes of steaming time resulted in optimum quality instant noodles. A 20% increase in protein and a 50% increase in fiber content was observed in optimized instant noodles.

Process Investigation on Robust Electrospinning of Non-Aligned and Aligned Polyvinylidene Fluoride Nanofiber Mats for Flexible Piezoelectric Sensors.

Polyvinylidene fluoride (PVDF) nanofiber mats have played a significant role in wearable electronic devices that have been in great demand in recent decades. Although manifold PVDFbased freely stacked or well-aligned nanofiber mats created via the electrospinning process have been demonstrated to achieve multisensory capabilities with high sensitivity and long detection range, rarely have any of them proved their ability with a stable process and accurate processing parameters. In this work, we successfully developed freely stacked and well-aligned PVDF nanofiber mats with diameters ranging from micrometers to nanometers, providing stable performance for wearable electronic devices. Through in-depth investigations into material preparation, electrospinning, and fiber collection processes, we revealed the relationship between the nanofiber morphology, β-phase fraction, and piezoelectric output with various process parameters. Characterized by analytical methods, we have established a mature, reliable nanofiber mat fabrication system capable of mass-producing PVDF nanofibers with the required diameter and consistent properties. At 18 kV voltage and 60% RH humidity, the uniformity of the fiber diameter and β-phase content was maintained in a favorable range. When the drum speed increased to 2000 r/s, the fiber orientation and β-phase content increased. We assembled aligned PVDF nanofiber mats with conductive fabric in a flexible piezoelectric sensor that successfully monitored different body movements and produced an output voltage of 0.1 V. This study provides the necessary process parameters for the large-scale production of high-quality PVDF nanofiber mats and provides clear guidance for beginners in the field of nanofiber mat manufacturing.

APPLICATION OF PREDICTIVE CONTROL TO IMPROVE THE QUALITY OF MANUFACTURING PROCESSES

A progressive method of condition -based maintenance of production processes is considered. It is shown that an effective means for its implementation is the use of predictive control. Proposals have been formulated for the use of a reliability-cost criterion that characterizes the effectiveness of maintenance with predictive performance, quantitative relationships have been derived that make it possible to evaluate the reduction in the number of gradual failures when using maintenance with predictive control, as well as establishing the relationship between the effectiveness of maintenance and the reliability of forecasting. Using the concept of unused resource, the minimum reliability of predictive control is determined. Relationships have been obtained and practical recommendations have been formulated related to the selection of production process parameters for forecasting, which are based on the principle of their comparison based on the steepness of change over the observation interval, the root-mean-square error of prediction and the cost of costs for measures to monitor and prevent failures.

Developing a data-driven operational guide for the texturized yarn production process: data mining and intelligence approach

PurposeThe textile industry holds immense significance in the economy of any nation, particularly in the production of synthetic yarn and fabrics. Consequently, the pursuit of acquiring high-quality products at a reduced cost has become a significant concern for countries. The primary objective of this research is to leverage data mining and data intelligence techniques to enhance and refine the production process of texturized yarn by developing an intelligent operating guide that enables the adjustment of production process parameters in the texturized yarn manufacturing process, based on the specifications of raw materials.Design/methodology/approachThis research undertook a systematic literature review to explore the various factors that influence yarn quality. Data mining techniques, including deep learning, K-nearest neighbor (KNN), decision tree, Naïve Bayes, support vector machine and VOTE, were employed to identify the most crucial factors. Subsequently, an executive and dynamic guide was developed utilizing data intelligence tools such as Power BI (Business Intelligence). The proposed model was then applied to the production process of a textile company in Iran 2020 to 2021.FindingsThe results of this research highlight that the production process parameters exert a more significant influence on texturized yarn quality than the characteristics of raw materials. The executive production guide was designed by selecting the optimal combination of production process parameters, namely draw ratio, D/Y and primary temperature, with the incorporation of limiting indexes derived from the raw material characteristics to predict tenacity and elongation.Originality/valueThis paper contributes by introducing a novel method for creating a dynamic guide. An intelligent and dynamic guide for tenacity and elongation in texturized yarn production was proposed, boasting an approximate accuracy rate of 80%. This developed guide is dynamic and seamlessly integrated with the production database. It undergoes regular updates every three months, incorporating the selected features of the process and raw materials, their respective thresholds, and the predicted levels of elongation and tenacity.

Analysis of the Uniformity of Mechanical Properties along the Length of Wire Rod Designed for Further Cold Plastic Working Processes for Selected Parameters of Thermoplastic Processing.

This study presents the results of research, the aim of which was to analyze the uniformity of the distribution of selected mechanical properties along the length of a 5.5 mm diameter wire rod of 20MnB4 steel for specific thermoplastic processing parameters. The scope of the study included, inter alia, metallographic analyses, microhardness tests, thermovision investigations, and tests of the wire rod mechanical properties (yield strength, ultimate tensile strength, elongation, relative reduction in area at fracture), along with their statistical analysis, for three technological variants of the rolling process differing by rolling temperature in the final stage of the rolling process (Reducing Sizing Mill rolling block [RSM]) and by cooling rate using STELMOR® cooling process. The obtained results led to the conclusion that the analyzed rolling process is characterized by a certain disparity of the analyzed mechanical properties along the length of the wire rod, which, however, retains a certain stability. This disparateness is caused by a number of factors. One of them, which ultimately determines the properties of the finished wire rod, is the process of controlled cooling in the STELMOR® line. Despite technological advances concerning technical solutions (among them, increasing the roller track speed in particular sections), it is currently not possible to completely eliminate the temperature difference along the length of the wire rod caused by the contact of individual coils with each other. From this point of view, for the analyzed thermoplastic processing parameters, there is no significant impact by the production process parameters on the quality of the finished steel product. Whereas, while comparing the mechanical properties and microstructure of the wire rod produced in the different technological combinations, it was found that the wire rod rolled in an RSM block at 850 °C and cooled after the rolling process on a roller conveyor at 10 °C/s had the best set of mechanical properties and the smallest microstructure variations. The wire rod produced in this way had the required level of plasticity reserve, which enables further deformation of the given type of steel in compression tests with a relative plastic strain of 75%. The uniformity of mechanical properties along the length of wire rods designed for further cold plastic working processes is an important problem. This is an important issue, given that wire rods made from 20MnB4 steel are an input material for further cold plastic working processes, e.g., for the drawing processes or the production of nails.

Optimization of Pyrolysis Process Parameters for Fuel Oil Production from the Thermal Recycling of Waste Polypropylene Grocery Bags Using the Box–Behnken Design

The impact of dumping plastic waste is realized in different ecosystems of the planet. Several methods have been adopted to dispose of these wastes for energy recovery. This study, for the first time, proposed the Box–Behnken design technique to optimize the pyrolysis process parameters for fuel oil production from waste polypropylene (PP) grocery bags using a semibatch-type pyrolytic reactor. The semibatch-type pyrolytic reactor was developed and employed to produce fuel oil from waste PP grocery bags. The effect of different process parameters on fuel oil production was comprehensively analyzed using the response surface methodology (RSM) with the conjunction of the Box–Behnken design (BBD). The BBD facilitates the prediction of the response variables with respect to changes in the input variables by developing a response model. The BBD was used to optimize the process parameters, such as the reaction temperature (400–550 °C), nitrogen flow rate (5–20 mL min−1), and substrate feed rate (0.25–1.5 kg h−1), and their effect on the responses were observed. The optimum response yields of the fuel oil (89.34 %), solid residue (2.74%), and gas yield (7.92%) were obtained with an optimized temperature (481 °C), a nitrogen flow rate (13 mL min−1), and a feed rate (0.61 kg h−1). The quadratic model obtained for the fuel oil response denotes the greater R2 value (0.99). The specific gravity and calorific value of the fuel oil were found to be 0.787 and 45.42 MJ kg−1, respectively. The fuel oil had higher research octane number (RON) (100.0 min) and motor octane number (MON) (85.1 min) values. These characteristics of the fuel oil were matched with conventional petroleum fuels. Further, Fourier transform infrared spectroscopy (FT-IR) and gas chromatography–mass spectroscopy (GC-MS) were used to analyze the fuel oil, and the results revealed that the fuel oil was enriched with different hydrocarbons, namely, alkane (paraffins) and alkene (olefins), in the carbon range of C4–C20. These results, and also the fractional distillation of the fuel oil, show the presence of petroleum-range hydrocarbons in the waste PP fuel oil.

Nutrient Properties of Fresh and Composted Cotton Gin Byproducts and Cattle Manure for Soil Amendment

Highlights N and P concentrations in composted vs. fresh Cotton Gin Byproducts (CGB) were at least 55% (dry basis) higher. P concentrations in composted vs. raw Beef Manure (BM) were approximately 25% higher. Characterization informs product formulations and process parameters for co-pelleting CGB with BM. Accurate formulation would enhance the potential for sustainable utilization of both byproducts. Abstract. Applications of fresh and composted Cotton Gin Byproducts (CGB) and cattle manure as soil amendments are very common practices in the industry. However, composting and direct application of the materials are often limited by factors such as bulkiness, varying nutrient composition and application rates, and handling/transportation costs. This study was conducted to characterize fresh and composted CGB and beef manure (BM) for subsequent co-pelletization and utilization as soil amendments, and to investigate the effects of composting on the nutrient composition and agronomic values. Raw and composted samples of CGB and BM at different storage periods and composting ages were sourced from two commercial gins and a beef farm. Nutrient content, acidity, and compost maturity indices such as carbon/nitrogen (C/N) and ammonium/nitrate (NH4-N/NO3-N) ratios were determined and compared. All samples were obtained at four sampling points on the respective storage or composting piles. The results showed that composted CGB generally contained at least 55% more total-N and phosphorus oxide (P2O5), but approximately 35% less potassium oxide (K2O) than fresh CGB. Composted BM had approximately 3% less total-N, but at least 25% more P2O5 than raw BM. The nutrient compositions affirm the potential for co-pelletizing both forms of CGB and BM to improve the agronomic values and enhance the utilization as soil amendments. In addition, establishing the various properties of CGB and BM is crucial for determining product formulations and selecting process parameters for co-pelletization. Keywords: Beef manure, Composting, Cotton ginning, Nutrient composition, Soil fertility.

OPTIMIZATION OF PROCESS PARAMETER OF BIODIESEL DERIVED FROM A HYBRID BLEND OF KARANJA AND CHLORELLA VULGARIS OIL

In this study, the response surface approach was employed to predict and optimize the biodiesel yield. Blend of Karanja and Chlorella vulgaris oil was used in a volumetric ratio of 75:25 to lower the free fatty acid content. The biodiesel production process parameters from this hybrid oil were optimized through a single-step transesterification process. The optimized conditions resulted in a maximum biodiesel yield of 97.55&amp;#37; . These conditions included a catalyst amount of 1.09&amp;#37; (w/w), a reaction time of 91.47 minutes, a reaction temperature of 56.86&amp;deg;C, and a methanol-to-oil molar ratio of 8.46:1. The experimental biodiesel yield was compared with the predicted response obtained from the response surface methodology (RSM). The comparison demonstrated good agreement between the experimental and predicted values.

Взгляд на функционирование проектной организации через призму теории СМО

In the context of the ongoing digitalization of the Russian economy as a whole and the construction industry in particular, solutions aimed at increasing the efficiency of construction organizations that carry out their functions at various stages of the construction project lifecycle remain in demand. Recognizing that the primary task of any organizations or enterprise in the construction industry, including project organizations, is the efficient using of all types of resources, the set objective can be achieved by reducing the organization’s overheads while at the same time increasing the efficiency of decisions aimed at managing core production processes. It is important to view the entire production process as a unified system with the ability to evaluate its performance indicators and forecast changes in these indicators when production process parameters will be changed.One potential modeling approach for the development of design and estimate documentation processes may involve conceiving it as a queuing system. From the authors’ perspective, in terms of queuing theory the activities of a project team under the guidance of the Chief project engineer (CPE) can be represented as a multi-phase open queuing network. The article provides computation formulas for the determining several key performances indicators of queuing system operation, which can be used to evaluate the performances of both individual performers of parts of the design and estimate documentation as well as the entire project team. Furthermore, this approach offers the possibility of calculating the effectiveness of changing these indicators with minimal expenses for the organization.

High-purity corundum grinding balls, obtained by quasi-isostatic pressing

The influence of the composition of press powders based on alumina CT 3000 LS SG, quasi-isostatic pressing and firing parameters on the structural and mechanical characteristics of grinding balls with a diameter of 40 mm is shown. Process parameters of production of high-density corundum balls are optimized on the basis of revealed regularities. The results of complex studies of physical and mechanical properties of ceramic articles are given. The determining effect of the particle size of raw material component on the hardness, density and operational characteristics of the grinding bodies was revealed.

An Expert System Based on Data Mining for a Trend Diagnosis of Process Parameters

In order to diagnose abnormal trends in the process parameters of industrial production, the Expert System based on rolling data Kernel Principal Component Analysis (ES-KPCA) and Support Vector Data Description (ES-SVDD) are proposed in this paper. The expert system is capable of identifying large-scale trend changes and abnormal fluctuations in process parameters using data mining techniques, subsequently triggering timely alarms. The system consists of a rule-based assessment of process parameter stability to evaluate whether the process parameters are stable. Also, when the parameters are unstable, the rolling data-based KPCA and SVDD methods are used to diagnose abnormal trends. ES-KPCA and ES-SVDD methods require adjusting seven threshold parameters during the offline parameter adjustment phase. The system obtains the adjusted parameters and performs a real-time diagnosis of process parameters based on the set diagnosis interval during the online diagnosis phase. The ES-KPCA and ES-SVDD methods emphasize the real-time alarms and the first alarm of process parameter abnormal trends, respectively. Finally, the system validates the experimental data from UniSim simulation and a chemical plant. The results show that the expert system has an outstanding diagnostic performance for abnormal trends in process parameters.

Influence of Process Parameters in Material Extrusion on Product Properties Using the Example of the Electrical Resistivity of Conductive Polymer Composites.

Additive manufacturing of components using the material extrusion (MEX) of thermoplastics enables the integration of multiple materials into a single part. This can include functional structures, such as electrically conductive ones. The resulting functional structure properties depend on the process parameters along the entire manufacturing chain. The aim of this investigation is to determine the influence of process parameters in filament production and additive manufacturing on resistivity. Filament is produced from a commercially available composite of polylactide (PLA) with carbon nanotubes (CNT) and carbon black (CB), while the temperature profile and screw speed were varied. MEX specimens were produced using a full-factorial variation in extrusion temperature, layer height and deposition speed from the most and least conductive in-house-produced filament and the commercially available filament from the same composite. The results show that the temperature profile during filament production influences the resistivity. The commercially available filament has a lower conductivity than the in-house-produced filament, even though the starting feedstock is the same. The process parameters during filament production are the main factors influencing the resistivity of an additively manufactured structure. The MEX process parameters have a minimal influence on the resistivity of the used PLA/CNT/CB composite.

OPTIMIZATION OF BIOETHANOL PRODUCTION FROM GAMBA GRASS (Andropogon gayanus) AND LOVE GRASS (Eragrostis tremula) USING ACID HYDROLYSIS

Bioethanol is a widely utilized liquid biofuel and demand for it has been increasing, there is a need to enhance production of it from more affordable and environmentally friendly raw materials. In this study Gamba grass and Love grass both were used as resources for the production of bioethanol using dilute acid hydrolysis. Reducing sugar was determined after hydrolysis with UV spectrophotometer at 540 nm with pH values of 4.0, 4.5, and 5.0 of samples and the results were compared. Optimization of process parameters for comparative production of bioethanol from Gamba grass and Love grass using Saccharomyces cerevisiae were carried out using Response surface based on Box-Beinkhen design. The optimum yield of bioethanol from sample A was 69.0% and sample B was 67.0% at the temperature, pH and reaction time of 32.5°C, 5.0, 120 hours respectively. This research shows that Gamba grass has the highest yield of bioethanol when compared with Love grass. The studies revealed suitability of both Gamba and Love grass as potential sources of good quality bioethanol.

Dynamic recrystallization behavior and microstructure evolution of high-Mn austenitic steel for application in a liquefied natural gas carrier

The hot-working behavior of high-Mn austenitic steel for liquefied natural gas carriers at the deformation temperature in the range of 1073–1273 K and the strain rate in the range of 0.01–10 s−1 was studied on a Gleeble-3800 thermomechanical simulator using a compression test. Electron backscatter diffraction was used to study the microstructure after deformation. Under each deformation condition, a peak stress appears in the stress-strain curve, which conforms to traditional dynamic recrystallization hot-working flow stress curves. A hyperbolic sine-law-type constitutive equation was established to predict the peak stress. The thermal deformation activation energy was 414.19 kJ/mol, and the stress index n was 4.94. The texture of the deformed grains consisted of strong <110> and weak <100> fibers along the compression direction. The main recrystallization mechanism was discontinuous dynamic recrystallization. The grain size of the discontinuous dynamic recrystallization grains tended to increase with increasing deformation temperature or decreasing strain rate. Processing maps were drawn based on the dynamic material model. At high deformation temperatures, the power consumption factor of dynamic recovery was greater than that of dynamic recrystallization, whereas at low deformation temperatures, the power consumption factor of discontinuous dynamic recrystallization was greater than that of dynamic recovery. There are two flow instability regions in the processing maps, 1243–1273 K/1-10 s−1 and 1073–1203 K/0.05–10 s−1. The formation of a ‘necklace microstructure’ was the main cause of deformation instability. The optimized process parameters for industrial production were 1243–1273 K/1-10 s−1.

Sponge-like wet electrospun polycaprolactone fibres

Polycaprolactone biocompatible and biodegradable fibrous materials with hierarchically-structured fibres provide appropriate materials for medical applications. Wet electrospinning is used to produce structured fibrous materials with specific properties. Via the careful choice of the polymer, solvent system and collector liquid, it is possible to produce unusual fibre shapes and structures. In general, wet electrospinning produces bulky structures. Moreover, by using a combination of a liquid collector containing a mixture of a non-solvent and a partial solvent, it is possible to obtain large internal porosity sponge-like fibres and tubular hollow fibres with porous walls. This article presents optimized material parameters and the respective electrospinning production process parameters for this production approach, as well as an analysis of the material via scanning electron microscopy and differential scanning calorimetry.

Optimal points of operational parameters of sulphuric acid, phosphic acid, and ammonia production process

PT Petrokimia Gresik is the most complete fertilizer producer in Indonesia and produces various types of fertilizers. NPK is a fertilizer that contains nitrogen (N) to make plants greener, phosphorus (P) to stimulate root growth, and potassium (K) to make plants more upright and sturdy. This study aims to determine the optimum value of using sulfuric acid, phosphoric acid, and ammonia so as to obtain the best value in producing NPK fertilizer. This research method uses quantitative descriptive research methods by collecting secondary data, namely the use of sulfuric acid, phosphoric acid, and ammonia for a period of 1 year. Researchers use multiple regression analysis to determine whether or not there is an influence between the three variables to be studied, then the data is processed and analyzed to determine whether the regression model used is feasible to use before finally calculating the optimal point of NPK fertilizer production. The stages of data optimization in this study are the data collection stage, the data processing stage (descriptive data, parameter estimation, regression model), the data analysis and interpretation stage (F test, t test, IIDN assumption test for determining the optimum point), and the conclusion and suggestion stage. This study concluded that obtaining the optimum point for the amount of NPK fertilizer production can be done by regulating the use of phosphoric acid at 211.91 tons, Sulphuric acid at 844,099 tons, and ammonia at 308,055 tons. Total fertilizer production achieved with the use of optimum parameters amounted to 2085.38 tons.