Fact-checked by Grok 2 weeks ago

Economic batch quantity

The Economic batch quantity (EBQ), also known as the economic production quantity (EPQ), is an model that determines the optimal production lot size to minimize the combined costs of production setups and holding in systems where items are produced at a finite rate rather than instantaneously replenished. Developed by E. W. Taft in 1918 as an extension of Ford W. Harris's 1913 (EOQ) model, the EBQ addresses scenarios in where levels build up gradually during the production run while demand continues, leading to a maximum that is lower than the full batch size. This model is fundamental in and , helping firms optimize to reduce waste and improve efficiency in industries such as , pharmaceuticals, and lines. The EBQ formula is derived by minimizing the total relevant cost function, which includes setup costs (fixed per batch) and holding costs (variable per unit over time), adjusted for the production rate. It is given by: EBQ = \sqrt{\frac{2DS}{H\left(1 - \frac{D}{P}\right)}} where D is the constant demand rate (e.g., units per year), S is the setup cost per production batch, H is the holding cost per unit per year, and P is the finite production rate (with P > D). The term \left(1 - \frac{D}{P}\right) reflects the net inventory accumulation rate during production, distinguishing EBQ from the EOQ formula \sqrt{\frac{2DS}{H}}, which assumes infinite production speed. Key assumptions include constant and known demand and production rates, no stockouts or backorders, negligible lead times for setups, and a constant holding cost independent of inventory location. In practice, the EBQ model provides a foundational tool for lot-sizing decisions, though real-world applications often require extensions to account for factors like imperfect production quality, machine breakdowns, deterioration, or multi-stage supply chains, as explored in numerous subsequent studies. These adaptations maintain the core principle of cost minimization while incorporating elements or constraints, enhancing its relevance in modern and just-in-time systems.

Overview

Definition and Purpose

The economic batch quantity (EBQ), also known as the (EPQ), refers to the optimal size of a batch that minimizes the total relevant costs associated with setup and holding in a manufacturing environment where the production rate is finite. This model determines the ideal number of units to produce in each run to balance inventory-related expenses without assuming instantaneous replenishment. The primary purpose of the EBQ is to achieve cost efficiency by trading off the disadvantages of frequent small batches, which incur high setup costs due to repeated machine changeovers and labor, against infrequent large batches, which lead to elevated holding costs from excess , risks, and tie-up. By identifying this equilibrium point, manufacturers can reduce overall operational expenses while meeting demand steadily, enhancing resource utilization in . Originating as an extension of early 20th-century inventory theory, the EBQ concept was first formalized in literature around the 1910s-1920s, paralleling the development of the (EOQ) model. Specifically, E. W. Taft introduced the foundational EBQ framework in 1918 while working as a , building on EOQ principles to address production scenarios. Unlike models assuming instant inventory arrival, the EBQ qualitatively accounts for the gradual accumulation of stock during the production phase, where inventory levels rise at the production rate minus the simultaneous rate until the batch is complete. This adjustment reflects real-world dynamics, such as assembly lines with constant output speeds.

Relation to Economic Order Quantity

The (EBQ) model shares significant similarities with the (EOQ) model, as both are deterministic inventory management frameworks aimed at minimizing total costs by determining optimal lot sizes under constant demand. They both incorporate core cost elements, including setup or ordering costs incurred per batch and holding costs associated with maintaining over time, thereby balancing trade-offs to achieve efficiency. Furthermore, the EOQ represents a special case of the EBQ when the production rate is infinite, effectively reverting to instantaneous replenishment without production buildup. Key differences arise in their treatment of replenishment processes: the EOQ assumes immediate and complete delivery of orders from external sources, focusing on purchasing decisions, whereas the EBQ models a finite production rate that leads to gradual inventory accumulation during the cycle. This adjustment in the EBQ accounts for the realities of in-house production, where items are produced incrementally rather than received all at once. Conceptually, the EBQ evolved as an extension of the EOQ to better suit internal production scenarios, with E.W. Taft introducing the model in 1918 to address gaps in F.W. Harris's 1913 EOQ formulation for make-to-stock environments. This adaptation filled a critical void by incorporating production dynamics into the original purchasing-oriented framework. In application, the EOQ is best suited for activities involving supplier orders, while the EBQ is employed for optimizing batch sizes in scheduling to align with manufacturing constraints.

Model Foundations

Key Variables

The (EBQ) model, also known as the (EPQ) model, depends on a set of core input parameters that capture the dynamics of demand, , and associated costs. These variables provide the foundational data for analyzing inventory buildup during finite runs, distinguishing the EBQ from instantaneous replenishment models like the (EOQ). Annual demand, denoted as D, quantifies the total units of the product required over a planning horizon, typically one year, and serves as the primary driver of inventory requirements. It is measured in units per year and assumes a constant, known value based on historical sales or forecasts. Setup cost, commonly symbolized as S or K, represents the fixed expenses incurred for each production batch initiation, including machine preparation, tooling changes, and labor mobilization. This cost is expressed in monetary units (e.g., dollars) per batch and remains independent of batch size. Holding cost, denoted H or h, is the per-unit of storing over time, typically on an annual basis, and includes components such as warehousing, , tied up, and potential or spoilage. It is measured in monetary units per unit per year and often calculated as a of the item's value. Production , represented as P or p, specifies the finite speed at which units are manufactured during an active production period, expressed in units per unit time (e.g., units per day or per year). This parameter accounts for the gradual accumulation in settings and is assumed to exceed the demand to prevent shortages. Demand rate, symbolized as d, indicates the continuous consumption rate of the product, often computed as D divided by the relevant time period (e.g., daily or hourly demand), and is measured in units per unit time. It reflects the steady outflow of inventory between production runs. Notation for these variables may vary across sources—such as \lambda for demand rate or \mu for production rate in some formulations—but the underlying concepts remain consistent in standard EBQ analyses.

Assumptions and Limitations

The Economic Batch Quantity (EBQ), also known as the (EPQ) model, relies on several foundational assumptions to derive its optimal production lot size. These include a constant and known demand rate that remains deterministic over an infinite planning horizon, ensuring steady depletion of without fluctuations. The production rate is assumed to be constant and finite, exceeding the demand rate to allow for gradual buildup during production runs. Holding costs and setup costs per batch are treated as constant and known, independent of batch size or time variations. Additionally, the model assumes instantaneous setup times with no lead times, no shortages or backorders permitted, and a focus on a single product without interactions from multiple items. Perfect quality output is presupposed, with no defects or rework required during production. These assumptions simplify the mathematical formulation but impose significant limitations on the model's real-world applicability. The EBQ model ignores variability in or production rates, such as seasonal fluctuations or breakdowns, which can lead to overstocking or stockouts if not addressed. It also neglects capacity constraints on production facilities and assumes static costs that do not account for inflation, quantity discounts, or changing economic conditions. Furthermore, the prohibition on shortages and the emphasis on make the model incompatible with just-in-time () systems, where minimal and frequent small lots are prioritized to reduce . When these assumptions are violated—such as through variable —optimal batch sizes become suboptimal, increasing total costs and necessitating model extensions like EPQ variants. Historically, the EBQ model evolved from the (EOQ) framework introduced by Ford W. Harris in 1913, with the EPQ developed by E. W. Taft in 1918 to accommodate finite production rates under idealized conditions of perfect information and operations. Early formulations from the assumed flawless manufacturing environments without quality issues or disruptions. Post-1950s research, amid the rise of and , critiqued these perfect-condition premises, highlighting deviations like imperfect production and variable costs that render basic EBQ unreliable in dynamic settings. For instance, studies from the emphasized that such assumptions are rarely met in practice, prompting integrations with quality costs and reliability factors.

Mathematical Derivation

Cost Components

The Economic Batch Quantity (EBQ) model, also known as the (EPQ) model, identifies and balances two primary variable costs associated with production batching: setup costs and holding costs. Setup costs represent the fixed expenses incurred each time a production run is initiated, such as machine preparation, labor reconfiguration, or . These costs are independent of the batch size but occur more frequently as batch sizes decrease. The total annual setup cost is given by \frac{D}{Q} \cdot S, where D is the annual demand rate, Q is the batch quantity, and S is the setup cost per batch. Holding costs encompass the expenses of maintaining over time, including , , , and opportunity costs of tied up in stock. In the EBQ model, builds up gradually during at a finite rate, rather than instantly as in the (EOQ) model, leading to a modified average level. The average is \frac{Q}{2} \left(1 - \frac{D}{P}\right), where D is the annual demand rate and P is the annual production rate (with P > D). Consequently, the total annual holding cost is \frac{Q}{2} \left(1 - \frac{D}{P}\right) \cdot H, where H is the holding cost per unit per year. This adjustment accounts for the net accumulation rate of during the phase. The total relevant cost (TRC) in the EBQ model is the sum of the annual setup and holding costs: TRC(Q) = \frac{D}{Q} \cdot S + \frac{Q}{2} \left(1 - \frac{D}{P}\right) \cdot H. Production costs, which are typically linear with the total output volume, are excluded from this optimization because they remain constant regardless of batch size and do not influence the choice of Q. Graphically, the TRC curve as a function of Q exhibits a convex, U-shaped profile, with setup costs decreasing hyperbolically as Q increases and holding costs rising linearly. The minimum point on this curve occurs at the optimal batch quantity, where the marginal increase in holding costs equals the marginal decrease in setup costs.

Formula and Optimization

The economic batch quantity (EBQ), also known as the (EPQ), is determined by minimizing the total relevant cost (TRC) function, which balances setup and holding costs under finite production rates. The optimal batch size Q^* is given by Q^* = \sqrt{ \frac{2DS}{H \left(1 - \frac{D}{P}\right)} }, where D is the annual demand rate, S is the setup cost per batch, H is the holding cost per unit per year, and P is the annual production rate (P > D). To derive this formula, the TRC per year is expressed as the sum of average setup cost \frac{D}{Q} S and average holding cost \frac{Q}{2} \left(1 - \frac{D}{P}\right) H, reflecting the maximum inventory level adjusted for the net accumulation rate during production. Setting the first derivative of TRC with respect to Q to zero yields \frac{d(\text{TRC})}{dQ} = -\frac{DS}{Q^2} + \frac{1}{2} \left(1 - \frac{D}{P}\right) H = 0, which solves to the EBQ formula above. The second derivative \frac{d^2(\text{TRC})}{dQ^2} = \frac{2DS}{Q^3} > 0 for Q > 0 confirms that this critical point is a minimum. This optimization equates the marginal holding cost per additional unit in the batch to the marginal reduction in setup costs from larger batches, ensuring cost efficiency in scheduling. Sensitivity analysis shows that Q^* decreases as the production rate P increases, since higher P increases the \left(1 - \frac{D}{P}\right) factor, enlarging the denominator and leading to lower average inventory and thus smaller optimal batches; as P approaches infinity, the EBQ converges to the economic order quantity (EOQ) formula \sqrt{\frac{2DS}{H}}. The formula maintains units consistency, as the expression under the square root has dimensions of (cost × quantity) / cost per unit = quantity², yielding Q^* in units of quantity.

Practical Applications

Calculation Procedure

To apply the Economic Batch Quantity (EBQ) model in practice, practitioners follow a structured procedure that begins with data collection and culminates in validation and scheduling adjustments. This process ensures the optimal production batch size minimizes total relevant costs while aligning with operational constraints. The EBQ formula, as derived in the mathematical section, is Q = \sqrt{\frac{2DS}{H\left(1 - \frac{D}{P}\right)}}, where D is annual demand (units/year), S is setup cost per batch (/batch), H is holding cost per unit per year (/unit/year), and P is annual production rate (units/year, with P > D). The calculation proceeds in the following steps:
  1. Gather the key inputs: Determine annual demand D (units/year), setup cost S (/batch), holding cost \( H \) (/unit/year), and production rate P (units/year, where P > D). These values are typically sourced from historical sales data, accounting records, and production capacity analyses.
  2. Calculate the adjustment factor \left(1 - \frac{D}{P}\right): This finite production rate correction reflects the buildup of inventory during production, preventing overestimation of holding costs compared to instantaneous replenishment models. Both D and P must use consistent time units (e.g., annual) to ensure the ratio is dimensionless.
  3. Plug the values into the EBQ formula to obtain the optimal batch size Q. Use consistent units to avoid scaling errors.
  4. Verify the result using total relevant cost (TRC): Compute setup costs \left(\frac{D}{Q} \times S\right) and average holding costs \left[\frac{Q}{2} \times \left(1 - \frac{D}{P}\right) \times H\right], sum them, and confirm the minimum by testing nearby values if needed.
  5. Adjust for integer batches: If Q is non-integer, round to the nearest whole number and re-evaluate TRC for floor and ceiling values, selecting the one with lower cost; practical constraints like minimum run sizes may further refine this.
For computation, spreadsheets like Microsoft Excel are widely used, with formulas such as =SQRT(2DS/(H*(1-(D/P)))) for Q, enabling sensitivity analysis by varying inputs (e.g., via data tables for changes in S or H). Advanced software integrates these calculations for scenario testing. Once Q is determined, cycle time implications guide scheduling: The production run time is Q/P (duration of active manufacturing), while the time between runs is Q/D (full inventory cycle from replenishment to depletion). These metrics help forecast resource needs and avoid stockouts. In enterprise systems, EBQ informs production scheduling within Material Requirements Planning (MRP) or Enterprise Resource Planning (ERP) modules by setting lot sizes in the master production schedule, triggering automated releases for setups and ensuring material availability aligns with calculated cycles. A common error is omitting the \left(1 - \frac{D}{P}\right) adjustment factor, which approximates EBQ with the (EOQ) model and overstates optimal batch sizes when production rates are finite, leading to excess holding costs.

Example Computation

Consider a hypothetical scenario where the annual demand D is 10,000 units, the setup cost per batch S is $100, the annual holding cost per unit H is $5, and the production rate P is 2,000 units per month, or 24,000 units per year. To compute the optimal economic batch quantity Q^*, first determine the utilization ratio \rho = D / P = 10,000 / 24,000 \approx 0.4167, so $1 - \rho \approx 0.5833. The formula for Q^*, derived from balancing setup and holding costs adjusted for finite production rate, is Q^* = \sqrt{\frac{2 D S}{H (1 - \rho)}} Substituting the values yields Q^* = \sqrt{\frac{2 \times 10,000 \times 100}{5 \times 0.5833}} = \sqrt{\frac{2,000,000}{2.9165}} \approx \sqrt{685,714} \approx 828 units per batch. The maximum inventory level occurs at the end of the production phase and is given by I_{\max} = Q^* (1 - \rho) \approx 828 \times 0.5833 \approx 483 units, reflecting the net buildup rate during production. The number of production cycles per year is D / Q^* \approx 10,000 / 828 \approx 12. The total annual cost at Q^* is approximately $2,415, calculated as setup costs of (D / Q^*) S \approx 1,208 plus holding costs of H \times (I_{\max} / 2) \approx 1,208. Compared to an arbitrary batch size of 600 units, the total cost rises to about $2,542 (setup $1,667 + holding $875), yielding annual savings of roughly $127; for 1,000 units, the cost is $2,458 (setup $1,000 + holding $1,458), saving about $43 annually. In , if the production rate P approaches (\rho \to 0), then $1 - \rho \to 1 and Q^* approaches the \sqrt{2 D S / H} = \sqrt{2,000,000 / 5} = \sqrt{400,000} \approx 632 units, with total cost increasing to about $3,162 and highlighting the savings potential from the production-rate adjustment. The profile over one depicts a sawtooth pattern: starts at zero, builds linearly at the net rate P - D = 14,000 units per year during the production time Q^* / P \approx 0.0345 years (reaching 483 units), then depletes linearly at rate D = 10,000 units per year over the remaining time of approximately 0.0655 years back to zero. This visualization highlights how the finite production rate limits average exposure compared to instantaneous replenishment models.

Extensions and Criticisms

Advanced Variations

One significant extension of the basic economic batch quantity (EBQ) model addresses demand variability by incorporating or probabilistic ordering policies, such as (s, S) thresholds where inventory is replenished when stock falls below a s, up to level S. This approach mitigates stockouts and overstocking in uncertain environments, often modeled through Markov decision processes or approximation techniques for computational efficiency. In multi-product settings, the EBQ model is adapted to schedule multiple items on shared production resources, accounting for setup times and sequence-dependent costs via dynamic programming algorithms like the Wagner-Whitin procedure, which optimizes lot sizes over a finite horizon by solving a shortest-path problem on a network graph. This method ensures feasibility while minimizing total holding and setup costs across items. Capacity constraints in EBQ models arise from limited machine availability, prompting adjustments that integrate backorder allowances to balance production runs against finite time horizons, often formulated as the economic lot scheduling problem (ELSP) where cycle times are synchronized to avoid overlaps. Seminal dynamic programming solutions provide near-optimal schedules by bounding the search space with relaxation techniques. For scenarios involving quantity on setups or materials, the EBQ model employs marginal to evaluate breakpoints where the function shifts due to tiered , comparing the basic EBQ against discounted lot sizes to select the minimum-cost option across discount intervals. This all-units discount structure is solved iteratively, ensuring the optimal batch size respects incentives. Post-2000 developments in EBQ models have increasingly integrated principles by emphasizing just-in-time batching to reduce waste, alongside AI-driven optimizations in Industry 4.0 contexts, such as algorithms for and adaptive lot sizing under constraints. These advancements, often incorporating or sustainable factors like carbon emissions, enhance model robustness in dynamic supply chains. Ongoing research as of 2025 continues to explore extensions in and sustainable production environments.

Real-World Considerations

In practice, the economic batch quantity (EBQ) model finds application across various industries to optimize production runs and minimize waste. The primary benefits of EBQ include substantial savings through optimized levels. By balancing setup and holding costs, firms can achieve reductions in total inventory expenses, with applications reporting up to 17% lower costs in sectors like . Additionally, it improves by minimizing and freeing capital tied in excess stock, enabling better financial flexibility for reinvestment. Despite these advantages, EBQ faces criticisms for its overemphasis on cost minimization at the expense of and production flexibility. The model often overlooks imperfect item and variable production rates, potentially leading to suboptimal outcomes in quality-sensitive environments. It performs poorly in volatile markets where assumptions of constant demand fail. Furthermore, its computational demands increase in dynamic settings, as estimating parameters like holding costs requires extensive , limiting applicability. Effective implementation of EBQ involves pilot testing within (ERP) systems to validate parameters before full rollout, as demonstrated in automotive supply chains. Hybrid approaches combining EBQ with (JIT) principles are recommended for small-batch , enhancing responsiveness while retaining cost efficiencies. A notable case is Toyota's , where integrating EOQ-like batch optimization with JIT via the reduced setup times and inventory disruptions, improving turnover by 12% in select facilities. As of 2025, trends in manufacturing emphasize and for dynamic optimization amid sustainability imperatives, including to reduce by 10-25% through efficient scheduling and minimization in production processes.

References

  1. [1]
    [PDF] Chapter 5. Inventory Systems - Logistics Systems Design
    The optimal batch size can then also be called the “Economic Production. Quantity” or EPQ for a finite production rate. The optimal total cost is then given by:.
  2. [2]
    Net Present Value Analysis of the Economic Production Quantity
    Aug 6, 2025 · Using Laplace transforms we extend the Economic Production Quantity (EPQ) model by analysing cash flows from a Net Present Value (NPV) viewpoint ...
  3. [3]
    Economic Production Quantity Model (EPQ) - EOQ
    The EPQ model uses the same assumptions as the simple or basic EOQ model, except that it use a finite replenishment rate.
  4. [4]
    Economic production quantity models for an imperfect ...
    An early extension of Harris (1913) [12] work on the Economic Order Quantity (EOQ) model was Taft's (1918) economic production quantity (EPQ) inventory model.
  5. [5]
    (PDF) Economic production quantity model for defective items under ...
    Aug 9, 2025 · Traditional economic production quantity (EPQ) model assumes that the production products are perfect. However, this assumption does not hold ...
  6. [6]
    [PDF] Economic Production Quantity Model with Scrapped Items and ...
    In manufacturing companies, when items are internally produced instead of being obtained from an outside supplier, the Economic Production Quantity. (EPQ) model ...
  7. [7]
    The Optimal Inventory Policy of Production Management
    Aug 6, 2025 · The traditional Economic Production Quantity (EPQ) assumes that the replenishments are instantaneous and the relevant cost only consists of ...<|control11|><|separator|>
  8. [8]
    [PDF] An easy method to derive EOQ and EPQ inventory models with ...
    The economic production quantity (EPQ) model was presented by Taft [2]. ... Taft, The most economical production lot, The Iron Age 101 (May 30) (1918) 1410–1412.
  9. [9]
    EOQ and EPQ Production-Inventory Models with Variable Holding ...
    Oct 20, 2018 · Abstract. In production-inventory control, economic order quantity (EOQ) and economic production quantity (EPQ) models are used to determine ...
  10. [10]
    A century of evolution from Harris׳s basic lot size model
    As reported by Best (1930) an EOQ formula was used at Eli Lilly and Company from 1917 onwards. The EPQ/EOQ inventory control models are still widely accepted by ...
  11. [11]
    [PDF] Week 5 Lesson 3: Economic Order Quantity (EOQ) Extensions - edX
    One can think of the EPQ equations as generalized forms where the EOQ is a special case where. P=infinity. As the production rate decreases, the optimal ...
  12. [12]
    A note on cost comparisons method for the EOQ and EPQ problems
    Aug 23, 2021 · Inventory · Economic order quantity (EOQ) · Economic production quantity (EPQ) · Algebraic methods · Cost comparisons · Derivative-free methods.
  13. [13]
    8.6 Inventory Models for Certain Demand: Economic Production ...
    The Economic Production Quantity (EPQ) model is applicable when an organization has its own internal production capabilities rather than ordering from an ...Missing: origin | Show results with:origin
  14. [14]
    [PDF] 1 The EOQ and Extensions
    Sep 9, 2004 · The infinite production rate case is also known as the Economic Order Quantity (EOQ) model. This optimal order interval for this model is given ...
  15. [15]
    None
    ### Summary of EPQ Calculation from https://www.iise.org/uploadedfiles/Webcasts/Determining%20Economic%20Production%20Quantities%207-14-09.pdf
  16. [16]
    Economic Order Quantity & Economic Order Quantity Formula
    Economic order quantity is the optimal amount of product to order without your holding costs going up. Learn more about EOQ and how to use it in this post.
  17. [17]
    What is MRP Material Requirements Planning? - Epicor
    Apr 13, 2023 · By tracking exact materials requirements, you can identify Economic Order Quantities, or the specific volume and frequency of product orders.
  18. [18]
    None
    ### Summary of Economic Production Quantity (EPQ) Example from Exercise 4
  19. [19]
    An Economic production quantity model with stochastic demand in ...
    Aug 6, 2025 · The paper deals with an economic production quantity (EPQ) model for both continuous and discrete random demand of merchandise.Missing: seminal | Show results with:seminal
  20. [20]
    Dynamic Version of the Economic Lot Size Model - PubsOnLine
    A multi-machine multi-product EPQ problem for an imperfect manufacturing ... The reverse Wagner/Whitin model with variable manufacturing and remanufacturing cost.
  21. [21]
    An EOQ model with quantity discounts for both purchasing price and ...
    Abstract. This paper deals with an EOQ model in which both the unit purchasing price and the freight cost depend on the quantity of the lot size.
  22. [22]
    Recent trends of economic production quantity models (2000-2022)
    Aug 9, 2025 · Recent trends of economic production quantity models (2000-2022) - a literature review · January 2024 · International Journal of Mathematics in ...
  23. [23]
    (PDF) ECONOMIC ORDER QUANTITY MODEL : A REVIEW
    Jan 16, 2015 · Economic Order Quantity (EOQ) models have been effectively employed in marketing, automotive, pharmaceutical, and retail sectors of the economy ...
  24. [24]
    [PDF] Toyota's Application of JIT vs. EOQ Models - ijrpr
    This research investigates inventory management optimization through a comparative analysis of Just-in-Time (JIT) and Economic Order Quantity (EOQ).
  25. [25]
    Calculating the Economic Batch Quantity (EBQ) - Agriculture Institute
    Feb 16, 2024 · The Economic Batch Quantity formula mathematically balances these competing costs to find the optimal batch size. The standard EBQ formula is:.What is Economic Batch... · Understanding the cost... · The EBQ formula explained
  26. [26]
    Economic production quantity model for items with continuous ...
    The economic production quantity (EPQ) model is a well-known and commonly used inventory control technique. However, the model is built on an unrealistic ...
  27. [27]
    Economic Order Quantity: A State-of-the-Art in the Era of Uncertain ...
    Jul 12, 2024 · Economic order quantity (EOQ) is the optimal number of items a company should buy to meet customer demand while keeping costs low.
  28. [28]
    Toyota Information System & Toyota ERP Case Study - IvyPanda
    May 24, 2024 · The key research objective is to determine how an organization can use Enterprise Resource Planning, as an information system in order to enhance productivity.
  29. [29]
    Artificial Intelligence and Machine Learning for Sustainable ...
    This comprehensive review analyzes the transformative impact of AI technologies on sustainable manufacturing, focusing on critical applications.