A method and an apparatus for generating a process documentation for a manufacturing process of a product

Abstract

It is provided a method for generating a process documentation. The method comprises obtaining one or more process control parameters with an initial target range, and one or more quality target parameters; and performing at least one iteration comprising the following actions: obtaining a process control parameter test set and a corresponding quality target parameter test set; classifying each parameter of the process control parameter test set as either influencing or not influencing each parameter of the quality target parameter test set; determining for each parameter of the process control parameter test set an updated target range; storing the updated target ranges of the process control parameters of the process control parameter test set and their classification. The method further comprises generating a process documentation comprising the stored updated target ranges and classifications for the process control parameters; and outputting the process documentation to a manufacturing system.

Description

[0001] A METHOD AND AN APPARATUS FOR GENERATING A PROCESS DOCUMENTATION FOR A MANUFACTURING PROCESS OF A PRODUCT

[0002] Field

[0003] The present disclosure relates to an apparatus, and a method. In particular, examples of the present disclosure relate an apparatus for generating a process documentation for a manufacturing process of a product and a method for generating a process documentation for a manufacturing process of a product.

[0004] Background

[0005] Efficient and reliable manufacturing processes are important in industries such as pharmaceuticals, where product quality, safety, and regulatory compliance are paramount. The development and optimization of manufacturing processes may require a thorough understanding of the relationships between process parameters and product attributes to ensure consistent outcomes and adherence to predefined standards. However, the complexity of modern manufacturing systems, combined with the need for data-driven approaches, may present challenges in identifying and managing critical process parameters that influence product quality. Further, it may be important to streamline process validation, facilitate regulatory compliance, and ensure adaptability to evolving industry requirements.

[0006] Summary

[0007] An example relates to a method for generating a process documentation for a manufacturing process of a product. The method comprises obtaining one or more process control parameters with an initial target range, and one or more quality target parameters. The method further comprises performing at least one iteration comprising the following actions: obtaining a process control parameter test set comprising at least one of the process control parameters and obtaining a corresponding quality target parameter test set comprising at least one of the quality target parameters; classifying each parameter of the process control parameter test set as either influencing or not influencing each parameter of the quality target parameter test set, based on an obtained experimental analysis data; determining for each parameter of the process control parameter test set being classified as influencing, an updated target range based on the obtained experimental analysis data; storing the updated target ranges of the process control parameters of the process control parameter test set and their classification with regards to the parameters of the quality target parameter test set. The method further comprises generating a process documentation comprising the stored updated target ranges and classifications for the process control parameters. The method further comprises outputting the process documentation to a manufacturing system.

[0008] An example relates to an apparatus for generating a process documentation for a manufacturing process of a product comprising interface circuitry, machine-readable instructions and processing circuitry to execute the machine-readable instructions to obtain one or more process control parameters with an initial target range, and one or more quality target parameters. The processing circuitry is further to execute the machine-readable instructions to perform at least one iteration comprising the following actions: obtain a process control parameter test set comprising at least one of the process control parameters and obtain a corresponding quality target parameter test set comprising at least one of the quality target parameters; classify each parameter of the process control parameter test set as either influencing or not influencing each parameter of the quality target parameter test set, based on an obtained experimental analysis data; determine for each parameter of the process control parameter test set being classified as influencing, an updated target range based on the obtained experimental analysis data; store the process documentation with the updated target ranges of the process control parameters of the process control parameter test set and their classification with regards to the parameters of the quality target parameter test set. The processing circuitry is further to execute the machine-readable instructions to generate a process documentation comprising the stored updated target ranges and classifications for the process control parameters. The processing circuitry is further to execute the machine- readable instructions to output the process documentation to a manufacturing system.

[0009] Brief description of the Figures

[0010] Some examples of apparatuses and / or methods will be described in the following by way of example only, and with reference to the accompanying figures, in which

[0011] Fig. 1 illustrates a flowchart of an example of a method for generating a process documentation for a manufacturing process of a product;

[0012] Fig. 2 illustrates a block diagram of an example of an apparatus or device for generating a process documentation for a manufacturing process of a product; and

[0013] Fig. 3 illustrates an example of a block chart of the herein disclosed technique.

[0014] Detailed Description Some examples are now described in more detail with reference to the enclosed figures. However, other possible examples are not limited to the features of these embodiments described in detail. Other examples may include modifications of the features as well as equivalents and alternatives to the features. Furthermore, the terminology used herein to describe certain examples should not be restrictive of further possible examples.

[0015] Throughout the description of the figures same or similar reference numerals refer to same or similar elements and / or features, which may be identical or implemented in a modified form while providing the same or a similar function. The thickness of lines, layers and / or areas in the figures may also be exaggerated for clarification.

[0016] When two elements A and B are combined using an “or”, this is to be understood as disclosing all possible combinations, i.e. only A, only B as well as A and B, unless expressly defined otherwise in the individual case. As an alternative wording for the same combinations, "at least one of A and B" or "A and / or B" may be used. This applies equivalently to combinations of more than two elements.

[0017] If a singular form, such as “a”, “an” and “the” is used and the use of only a single element is not defined as mandatory either explicitly or implicitly, further examples may also use several elements to implement the same function. If a function is described below as implemented using multiple elements, further examples may implement the same function using a single element or a single processing entity. It is further understood that the terms "include", "including", "comprise" and / or "comprising", when used, describe the presence of the specified features, integers, steps, operations, processes, elements, components and / or a group thereof, but do not exclude the presence or addition of one or more other features, integers, steps, operations, processes, elements, components and / or a group thereof.

[0018] Fig. 1 illustrates a flowchart of an example of a method 100 for generating a process documentation for a manufacturing process of a product. In some examples, the method 100 is, for instance, performed by an apparatus as described herein, such as apparatus 200 (see Fig. 2 below). For example, the process documentation is a formal record that includes process control parameters, their corresponding critical target ranges, and classifications, providing the necessary framework to ensure a consistent and compliant manufacturing process of a product. For example, the process documentation standardizes the manufacturing process of a product, and connects the optimized parameters to the manufacturing process. This enables their effective implementation and control and ensures it can be replicated reliably while maintaining quality and adhering to regulatory standards.

[0019] The method 100 comprises obtaining 110 one or more process control parameters with an initial target range, and one or more quality target parameters. For example, a process control parameter is a variable within the manufacturing process of a product that is monitored and / or controlled to influence the outcome of the manufacturing process. The target range for the process control parameter represents the specific values or acceptable bounds within which the parameter should be maintained during the manufacturing process to ensure the desired performance. The one or more process control parameters that are obtained before the beginning of the iteration may also be referred to as initial process control parameters or process control parameter candidates because these parameters are obtained for evaluation to determine whether their control is important for the manufacturing process or not. The initial target range refers to a preliminary bound for the process control parameter before further refinement through analysis and testing. For example, the one or more process control parameters may comprise physical variables such as temperature, pressure, and mixing speed and / or chemical variables such as pH, solvent composition, and concentration and / or biological variables such as cell density, nutrient levels, and growth rates and / or or operational variables such as flow rate, agitation time, and equipment rotation speed, depending on the manufacturing process.

[0020] For example, a quality target parameter is a measurable attribute of the final product and / or intermediate product, assessed during the manufacturing process, that reflects the product's performance. Each quality target parameter is associated with a predetermined quality target range (or a single predetermined quality target value) that should be met to ensure the manufactured product adheres to defined standards for quality, safety, and efficacy. A quality target parameter is considered to be met when its measured value falls within the predefined quality target range (or matches the predefined quality target value), confirming that the product satisfies its intended quality requirements. For example, the one or more quality target parameters serve as benchmarks for evaluating whether the manufacturing process produces a product that adheres to defined standards for quality, safety, and / or efficacy. For example, the one or more quality target parameters may comprise physical attributes such as particle size, tablet hardness, or viscosity and / or chemical attributes such as purity, potency, or pH stability and / or biological attributes such as protein activity, cell viability, or antigen binding capacity and / or and microbiological attributes such as sterility, microbial load, or endotoxin levels, and / or operational attributes such as process yield, production time, or resource efficiency, depending on the manufactured product's nature and application. In some examples, the one or more process control parameters with initial target ranges and / or the one or more quality target parameters with the predetermined target ranges are determined by an external entity. For example, the apparatus 200 (see Fig. 2) that is carrying out the method 100 obtains the one or more process control parameters with initial target ranges and / or the one or more quality target parameters with the predetermined target ranges are obtained via its interface circuitry 220 from the external entity. In some examples, the method 100 further comprises determining the one or more process control parameters with initial target ranges and / or the one or more quality target parameters with the predetermined target ranges (see more detailed description below).

[0021] In some examples, the one or more process control parameters are critical process parameters (CPPs), and the one or more quality target parameters are critical quality attributes (CQAs). CCPs and CQAs are established terms in pharmaceutical and biopharmaceutical manufacturing, as defined under regulatory frameworks such as “Q8(R2) Pharmaceutical Development” specification from the U.S. Food and Drug Administration, from November 2009 and Good Manufacturing Practices (GMP). These terms may be used in the development, characterization, and validation of pharmaceutical processes, where robust control of CCPs is necessary to ensure CQAs consistently meet predefined criteria.

[0022] In some example, the process documentation is for a pharmaceutical manufacturing process of a pharmaceutical product, the one or more process control parameters are parameters that are controllable during the pharmaceutical manufacturing process, and the one or more quality target parameters of the pharmaceutical product are parameters measured during and / or after the pharmaceutical manufacturing process to confirm the quality of the pharmaceutical product. For example, pharmaceutical manufacturing comprises different production types, such as the synthesis of small-molecule drugs, biologies such as vaccines and monoclonal antibodies, and sterile products like injectables. Biologies, unlike small molecules, are produced using living organisms and involve complex manufacturing processes, such as cell culture and purification, where even slight deviations in process control parameters like temperature, pH, or nutrient levels may significantly affect the quality and efficacy of the product. For example, in the production of a monoclonal antibody, parameters such as dissolved oxygen and cell density are critical for ensuring proper protein folding and biological activity. Similarly, in sterile manufacturing, stringent control over process control parameters like filtration pressure and environmental sterility is important to prevent contamination. For example, in pharmaceutical manufacturing, the process control parameters are important to maintain consistency across batches, ensuring that each product meets predefined quality attributes critical for patient safety and therapeutic efficacy. The quality target parameters, such as potency, purity, and sterility, are benchmarks for confirming the product complies with regulatory standards and may perform its intended therapeutic function. The need for strict parameter control and measurement is important in pharmaceuticals due to the high stakes involved, where deviations may lead to ineffective treatments, safety risks for patients, and regulatory non-compliance.

[0023] For example, in the manufacturing of a monoclonal antibody therapy, which is a biologic pharmaceutical product, the manufacturing process involves cultivating mammalian cells in a bioreactor under tightly controlled conditions, followed by purification and formulation to achieve the desired therapeutic product. Biologies production requires precise management of the process control parameters to ensure consistent product quality and efficacy. For example, the process control parameters comprise temperature, pH, dissolved oxygen levels, and stirring speed, which are critical for maintaining cell viability, optimizing protein production, and preventing cellular stress. For example, the initial target ranges for these process control parameters might be 36.5°C to 37.5°C for temperature, 6.8 to 7.2 for pH, 40% to 60% saturation for dissolved oxygen, and 50 to 100 rpm for stirring speed. For example, the quality target parameters include protein purity, glycosylation profile, sterility, and endotoxin levels, with corresponding predetermined quality target ranges, such as a protein purity of greater than 98%, sterility requiring complete absence of microbial contamination, and endotoxin levels below 0.5 Ell / mL.

[0024] The method 100 comprises further performing 112 at least one iteration comprising a plurality of actions. In some examples, the iteration comprising the plurality of actions is repeated until one or more stopping criterions are satisfied. The at least one performed iteration of the method 100 comprises obtaining 114 a process control parameter test set. The process control parameter test set comprises at least one of the process control parameter candidates. For example, at the beginning of each iteration, a process control parameter test set is obtained. The obtained process control parameter test set may be a subset of all obtained process control parameters, for focused evaluation and testing during a current iteration. The process control parameter test set comprises at least one process control parameter and is intended to determine whether this process control parameter influences a specified quality target parameter and is therefore critical to the manufacturing process. The at least one performed iteration of the method 100 further comprises obtaining 114 a quality target parameter test set corresponding to the obtained process control parameter test. For example, a process control parameter test set and its corresponding quality target parameter test set are referred to a pair of a process control parameter test set and a corresponding quality target parameter test set. The quality target parameter test set comprises at least one of the quality target parameters. For example, at the beginning of each iteration, a quality target parameter test set is obtained. The obtained quality target parameter test set may be a subset of the quality target parameters for focused evaluation and testing during the current iteration. The quality target parameter test set comprises at least one quality target parameter and is intended to assess whether the process control parameters in the process control parameter test set influence the quality target parameters of the quality target parameter test set.

[0025] The process control parameters of the process control parameter test set are obtained for evaluation to determine their influence on the quality target parameters of the quality target parameter test set. The process control parameter test set comprises variables that are actively controlled during the manufacturing process, while the quality target parameter test set includes measurable attributes of the product that indicate whether it meets the required standards for quality, safety, and efficacy. For example, during each iteration, the process control parameters in the process control parameters test set are systematically evaluated to assess their impact on the quality target parameters as described below. For example, by obtaining different process control parameter test sets and corresponding quality target parameter test sets in different iterations, a systematic exploration of the relationships between the process control parameters and the quality target parameters is achieved. This iterative approach may allow for targeted evaluation of how variations in process control parameters influence specific quality target parameters, enabling the identification of critical process control parameters and the refinement of their target ranges to ensure consistent product quality, safety, and efficacy.

[0026] For example, one or more pairs of a process control parameter test set and a corresponding quality target parameter test set may be obtained and / or determined by an external entity. For example, the apparatus 200 (see Fig. 2) that is carrying out the method 100 obtains one or more pairs of a process control parameter test set and a corresponding quality target parameter test set via its interface circuitry 220 from an external entity. For example, one or more pairs a process control parameter test set and a corresponding quality target parameter test set may be included in a collection of paired test sets. For example, the method 100 comprises obtaining the collection of paired test sets. In some examples, the method 100 further comprises determining the collection of paired test sets (see detailed description below). The at least one performed iteration of the method 100 further comprises classifying 124 each parameter of the process control parameter test set as either influencing or not influencing each parameter of the quality target parameter test set, based on obtained experimental analysis data. For example, the obtained experimental analysis data refers to data derived from one or more performed experiments that evaluate the relationship between the parameters in the process control parameter test set and the parameters in the quality target parameter test set. In some examples, the obtained experimental analysis data comprises raw measured results from the one or more performed experiments and / or data analysis derived from the raw measured results of the one or more performed experiments. For example, the data analysis comprises target range data for determining updated target ranges for process control parameters. For example, the data analysis comprises statistical analysis derived from the raw measured results of the performed experiment.

[0027] For example, the statistical analysis indicates how variations in the process control parameter test set affect the quality target parameter test set by quantifying the relationships between the parameters. For example, the statistical analysis comprises statistical metrics such as correlation coefficients, regression outputs, p-values, analysis of variance results, and / or sensitivity indices, each of which provides insights into the strength, significance, and nature of the relationships between the process control parameters and the quality target parameters. These statistical metrics help identify whether changes in specific process control parameters are associated with measurable effects on quality target parameters, forming the basis for classification. In some examples, the obtained experimental analysis data is provided by an external source, such as an operator who performed the experiment manually and recorded the results. In other examples, the obtained experimental analysis data may be generated and transmitted by an external apparatus configured to conduct experiments or analyze experimental results, such as a bioreactor system that measures dissolved oxygen levels and their effect on cell viability or an analytical instrument like a chromatograph or spectrometer. In some examples, the apparatus performing the method (such as apparatus 200, see Fig. 2) processes the raw experimental results to determine the experimental analysis data.

[0028] The classifying 124 of each parameter of the process control parameter test set as either influencing or not influencing each parameter of the quality target parameter test set uses the obtained experimental analysis data as its input. For example, the classification determines whether each process control parameter in the obtained process control parameter test set influences each quality target parameter in the obtained quality target parameter test set based on the statistical analysis included in the obtained experimental analysis data. A process control parameter is considered influencing if changes in its value result in a measurable effect on a quality target parameter that exceeds a predetermined threshold. For example, classifying comprises applying predefined thresholds to the statistical metrics included in the obtained experimental analysis data. In some examples, a process control parameter in the obtained process control parameter test set is classified as influencing a parameter in the obtained quality target parameter test set if a statistical metric between the two parameters exceeds a predetermined threshold. In other words, the statistical metric is compared to a predefined value to assess whether it exceeds a predetermined threshold. If the threshold is exceeded, the process control parameter is classified as influencing the quality target parameter. If the threshold is not exceeded, the process control parameter is classified as not influencing the quality target parameter. By applying the threshold, the classification ensures that only process control parameters with a demonstrable and significant impact on the quality target parameters are identified as influencing, enabling targeted refinement and optimization of the manufacturing process.

[0029] In some examples, this influence may be direct, such as when a strong linear correlation exists between a process control parameter and a quality target parameter, where variations in the process control parameter proportionally affect the quality target parameter. For example, a high correlation coefficient exceeding a predefined threshold, such as 0.7, may indicate such direct influence. In other examples, the influence may be indirect, where the relationship between a process control parameter and a quality target parameter is mediated by other process control parameters or arises from complex interactions within the manufacturing process. For instance, sensitivity indices or regression models may reveal such indirect effects. In some examples, the influence may involve multivariate scenarios, where combinations of multiple process control parameters collectively impact one or more quality target parameters. Statistical methods such as analysis of variance or multivariate sensitivity analysis may be applied to quantify these collective influences and determine their significance. By systematically evaluating these relationships using various statistical metrics, the method enables a comprehensive understanding of both direct and indirect influences on quality target parameters.

[0030] For example, the influence may be a direct influence. For example, for direct influences, the classification relies on metrics such as correlation coefficients or regression outputs. For example, in the production of a monoclonal antibody, if a correlation coefficient between bioreactor temperature (process control parameter) and protein purity (quality target parameter) exceeds a threshold of 0.7, the temperature is classified as influencing the protein purity. Similarly, a significant regression coefficient indicating that increasing dissolved oxygen levels in the bioreactor improves protein yield may lead to the classification of dissolved oxygen as influencing protein yield. In another example, the influence is an indirect influence. In this case the relationship between a process control parameter and a quality target parameter is mediated by other process control parameters or involves complex interactions. For example, classification relies on statistical metrics such as sensitivity indices or interaction terms in regression models. For example, the effect of agitation speed (process control parameter) on protein aggregation (quality target parameter) may be mediated by its influence on dissolved oxygen levels. If a sensitivity index for agitation speed exceeds a threshold of 0.5, it may be classified as influencing protein aggregation indirectly. In another example, the influence may be multivariate scenario, where combinations of process control parameters collectively impact one or more quality target parameters. In this case, techniques like analysis of variance or multivariate regression are applied. For instance, in tablet manufacturing, the combined effects of granulation time, compression force, and drying temperature (process control parameters) on tablet dissolution rate (quality target parameter) may be evaluated using analysis of variance. If the F-statistic for the combined parameters exceeds the critical value, the parameters are collectively classified as influencing. For example, software tools like I DBS Polar, or I DBS Insight may be used to perform the statistical analysis based on the raw experimental results and / or the classification.

[0031] The at least one performed iteration of the method 100 further comprises determining 126 for each parameter of the process control parameter test set, which is classified as influencing, an updated target range based on the obtained experimental analysis data. In some examples, the updated target range for each parameter in the process control parameter test set is determined such that, within this updated target range, the corresponding quality target parameters are met. As described above, the obtained experimental analysis data comprises target range data for determining updated target ranges for the process control parameters classified as influencing. The target range data captures how specific variations in the process control parameters quantitatively affect the quality target parameters and serves as the foundation for defining the updated target ranges.

[0032] In some examples, for each parameter of the process control parameter test set that is classified as influencing, the updated target range is already included in the target range data of the obtained experimental analysis data. In such cases, determining the updated target ranges comprises reading out the updated target ranges directly from the target range data. In this case the target range data in the obtained experimental analysis data comprise the predetermined quality target ranges, ensuring that the quality target parameters are met within the updated target ranges of the process control parameters. In some examples, the target range data of the obtained experimental analysis data comprises functional relationships between the values of one or more process control parameters and the corresponding one or more quality target parameters, such as a discrete or continuous mathematical mapping. This functional relationship represents how variations in the values of the process control parameters influence the quality target parameters. For example, determining the updated target range for each parameter in the process control parameter test set comprises evaluating these functional relationship to identify the specific values or subranges of the process control parameter within which the corresponding quality target range is met. For example, the updated target range is refined by analyzing the functional relationship to determine the boundaries where the quality target parameter consistently falls within its predefined acceptable range.

[0033] There may be different methods applied to determine these functional relationships. For example, statistical methods such as regression analysis, correlation analysis, analysis of variance, sensitivity analysis, and / or p-value analysis are applied to quantify these relationships. Regression analysis may identify functional trends, such as linear or quadratic relationships, while correlation analysis measures the strength and direction of these effects. Analysis of variance evaluates variability across parameter levels to determine optimal ranges, and sensitivity analysis quantifies the relative importance of individual process control parameters on quality target parameters. P-value analysis ensures that the observed effects are statistically significant, reinforcing the reliability of the target range data. Another method for quantify the relationships between process control parameters and quality target parameters are machine learning models, such as neural networks. These may be good at uncovering complex, non-linear relationships and subtle interactions within large datasets and can identify patterns and dependencies that are not easily detected using traditional methods. Another method for quantify the relationships between process control parameters and quality target parameters are principal component analysis which can reduce the dimensionality of the data by identifying the most critical factors influencing quality target parameters, simplifying the analysis while retaining essential information. In some examples, cluster analysis is used which groups similar combinations of process control parameter values and their associated quality outcomes to reveal optimal operating conditions. In some examples, simulation models, such as computational fluid dynamics may be used to provide insights into physical interactions that impact quality target parameters. For example, software tools like ID Business Solutions (IDBS) Polar, or IDBS Insight may be used to determine the target range data of the experimental analysis data and / or the functional relationships.

[0034] The at least one performed iteration of the method 100 further comprises storing 128 the updated target ranges of the process control parameters of the process control parameter test set and their classification with regards to the parameters of the quality target parameter test set. That is, for each process control parameter, the storage comprise information on which quality target parameters it is classified as influencing or not influencing, as well as the specific quality target parameters used as the basis for adapting its target range. In some examples, the stored data includes all evaluated parameters, even those classified as not influencing, to provide a comprehensive record of the analysis.

[0035] In some examples, the method 100 further comprises storing additional data corresponding to the parameter and classifying and updating process. For example, the additional data comprises the initial target ranges for each parameter and data describing the methods and statistical analyses used to refine the updated ranges. In some examples, the additional data further comprises experimental raw data and / or the obtained experimental analysis data are stored alongside the updated target ranges and classifications. This enables full lifecycle traceability of the process control parameters and quality target parameters by ensuring that all data related to their refinement, classification, and application is comprehensively stored and accessible. For instance, the data is stored in a storage circuitry 240 of the apparatus 200 which is carrying out the method 100.

[0036] As described above, in some examples, the iteration comprising the plurality of actions of as described above, is repeated until one or more stopping criterions are met. In some examples, the method 100 comprises determining 130 whether a stopping criterion is satisfied, and if the stopping criterion is not satisfied, performing at least one additional iteration of the actions. For example, the determining whether a stopping criterion is satisfied is performed after the storing 128 of the updated target ranges. For example, the stopping criterion is satisfied when all pairings of process control parameter test sets and corresponding quality target parameter test sets from the collection of paired test sets are processed. For example, if the stopping criterion is not satisfied the iteration starts again with obtaining 114 a process control parameter test set comprising at least one of the process control parameters and obtaining a corresponding quality target parameter test set comprising at least one of the quality target parameters. For example, each iteration comprises a different pair of a process control parameter test set and a corresponding quality target parameter test set. For example, this approach allows the method 100 to evaluate how variations in different process control parameters impact specific quality target parameters, ensuring comprehensive coverage of all relevant combinations. For example, if the pairings are determined randomly, a probabilistic method may be used to select a new pair from the pool of all available process control parameters and quality target parameters for each iteration. For example, if the pairings are obtained from a predetermined collection of test sets, the method may systematically select a next pairing in the predetermined collection of test sets to ensure that all pairings are evaluated without duplication. By using a different pair in each iteration, the method minimizes redundancy and ensures that each step contributes unique insights into the relationship between the process control parameters and quality target parameters. For example, this systematic evaluation enables the identification of critical parameters and their target ranges, ultimately refining the manufacturing process and improving quality outcomes.

[0037] The method 100 further comprises 132 generating the process documentation for the manufacturing process of the product comprising the stored updated target ranges and classifications for the process control parameters. As described above the process documentation is a formal record that includes and structures the stored updated target ranges and classifications for the process control parameters. In some examples, only the process control parameters with the updated target range that are classified as influencing at least one of the quality target parameters are included into the process documentation. In some examples, the process documentation further comprises the additional data corresponding to the parameter and classifying and updating process. This ensures that the process documentation not only provides the final parameters required for manufacturing but also delivers full traceability and contextual information about how these parameters were derived.

[0038] The method 100 further comprises 134 outputting the process documentation to a manufacturing system. For example, the manufacturing system is a computer-based system to manage, control, monitor and / or or analyze the manufacturing process of the product. For example, it components such as a manufacturing execution and control systems for real-time monitoring and control of the production processes and / or a process information management systems (PIMS) for collecting, storing, and analyzing data during the manufacturing process. For example, the manufacturing execution and control system may directly implement the updated target ranges from the process documentation by adjusting equipment settings such as temperature, pressure, or stirring speed. The PIMS, on the other hand, may analyze real-time and historical data to verify compliance with the process documentation and provide feedback for process optimization. For example, the manufacturing system communicates with hardware components, such as sensors, controllers, and manufacturing equipment, to implement process adjustments and continuously monitor operational conditions. For example, sensors may provide real-time feedback on parameters like temperature or pH, allowing the manufacturing system to ensure these values remain within the updated target ranges specified in the process documentation. This integration ensures that the process documentation is not only a static record but an active tool guiding and optimizing the manufacturing process in real time. For example, the generated process documentation is output via an interface circuitry 220 of the apparatus 200 (see Fig. 2) which is carrying out the method 100.

[0039] The above-described technique provides a systematic and data-driven lifecycle management of process control parameters, enabling continuous improvement of the manufacturing process. By iteratively classifying, refining, and storing process control parameters, it integrates these actions into an improved framework that ties parameter refinement to its application in manufacturing. This technique may enhance process reliability, align process control parameters with quality target parameters, and support the identification and optimization of critical parameters. Further, by generating a process documentation with updated target ranges and classifications and outputting it to the manufacturing system, the technique establishes a connection between parameter refinement and the manufacturing process of the product. This may enable the manufacturing system to actively monitor, adjust, and control process control parameters during production, ensuring that corresponding quality target parameters are consistently met. The result is reduced variability, improved product consistency, and optimized resource utilization, leading to enhanced manufacturing system performance and adherence to predefined quality standards. By refining target ranges and ensuring their consistent application throughout the manufacturing process, the technique improves operational precision, eliminates inefficiencies associated with fragmented or manual processes, and drives consistent quality outcomes. As a result, the manufacturing process benefits from enhanced efficiency, adaptability, and robustness, ensuring optimized performance and regulatory compliance.

[0040] Further, the above-described technique allows for monitoring and adjustments based on the process documentation which enables proactive control, ensuring that critical quality target parameters are consistently achieved. This integrated approach supports regulatory compliance, improves system reliability, and ensures high-quality product outcomes, making the manufacturing process robust, efficient, and adaptable to evolving challenges.

[0041] Manufacturing System For example, the process documentation may be stored in a digital format, such as a database entry, structured XML, XLSX, or JSON files, or as a textual report for regulatory submissions. In some examples, the process documentation is organized in a relational database to allow efficient querying and cross-referencing of parameters, classifications, and their corresponding quality target parameters. This formalized process documentation ensures that the updated process control parameters are accessible, standardized, and readily available for use in the implementation and execution of the manufacturing process of the product. Furthermore, the process documentation supports validation processes, regulatory compliance verification, and continuous improvement initiatives by providing comprehensive traceability and contextual information about the parameters and their refinement. In some examples, the process documentation is formatted in a data format compatible with the manufacturing system. For example, this facilitates seamless integration, automated data exchange, and implementation of process control parameters. This compatibility ensures that the updated target ranges and classifications for process control parameters can be directly imported into the manufacturing system, minimizing manual input errors and streamlining the execution of the manufacturing process. Additionally, such formatting supports efficient monitoring, control, and validation of the process parameters within the manufacturing environment, enabling compliance with regulatory standards and operational efficiency.

[0042] In some examples, the method 100 further comprises applying 136 the updated target ranges to adjust the process control parameters during the manufacturing process of the product. For example, the adjusting of the process control parameters is performed in real-time. This ensured that the process control parameters remain within the updated target ranges such that the corresponding quality target parameters are consistently met. The iterative refinement of process control parameters and their application in the manufacturing process ensures that process control parameters are maintained within the optimal bounds necessary to achieve the corresponding quality target parameters. The real-time adjustment of process control parameters leverages data-driven insights from the process documentation, integrating the refinement process into active manufacturing operations. This enables precise control over manufacturing conditions, reduces manual intervention, and ensures consistent product quality, minimizing variability, and improving overall manufacturing system performance.

[0043] In some examples, the method 100 further comprises monitoring 136 the process control parameters. If deviations from the updated target ranges specified in the process documentation are detected, the method 100 further comprises adjusting 136 the process control parameters such that the corresponding quality target parameters are met. This monitoring and adjustment of process control parameters ensures continuous alignment with the updated target ranges specified in the process documentation. By detecting deviations from these ranges and triggering adjustments as necessary, the method integrates active feedback control into the manufacturing process. This ensures that process control parameters are dynamically maintained within optimal bounds, directly supporting the consistent achievement of the corresponding quality target parameters. The combination of monitoring and automated adjustment reduces variability, enhances system reliability, and minimizes manual intervention, contributing to a robust and efficient manufacturing process that consistently meets predefined quality standards.

[0044] In some examples, the compliance of the process control parameters with the updated target ranges specified in the process documentation is validated using sensor data collected during the manufacturing process. For example, the sensor data provides real-time, accurate measurements of critical process variables, ensuring that deviations or inconsistencies are immediately identified. By validating compliance through objective and continuous data collection, this enhances the reliability of the manufacturing process and ensures adherence to predefined quality standards. By using sensors to provide precise, continuous measurements, the method 100 ensures that deviations are promptly detected and addressed, reducing the risk of variability and quality defects. This real-time validation strengthens process control, enhances system automation, and ensures the consistent achievement of corresponding quality target parameters, thereby improving product reliability, operational efficiency, and regulatory compliance.

[0045] Initial Target Ranges, Test Sets and Stopping Criterion

[0046] As described above, in some examples, the method 100 further comprises obtaining and / or determining the one or more process control parameters with initial target ranges and / or the one or more quality target parameters with the predetermined target ranges. For example, the apparatus 200 (see Fig. 2) that is carrying out the method 100 obtains the one or more process control parameters with initial target ranges and / or the one or more quality target parameters with the predetermined target ranges via its interface circuitry 220 from the external entity.

[0047] For example, the one or more process control parameters with initial target ranges and / or the one or more quality target parameters with the predetermined target ranges are determined based on regulatory requirements. The regulatory requirements may be based on industry guidelines, scientific literature, contract manufacturing organizations and / or research institutions, which have experience with similar products or processes. For instance, such requirements may be outlined in the “Q8(R2) Pharmaceutical Development” specification from the U.S. Food and Drug Administration issued in November 2009 or in Good Manufacturing Practices (GMP). For example, the regulatory requirements define critical attributes and acceptable ranges for specific types of pharmaceutical products and manufacturing processes.

[0048] In some examples, the obtained process control parameters with initial target ranges and the quality target parameters with predetermined target ranges are determined based on historical data from one or more similar manufactured products or manufacturing processes. For example, a product is considered similar if it shares critical attributes with the current product, such as comparable active pharmaceutical ingredients or excipients, similar physical forms (e.g., tablet, injectable, or biologic), analogous therapeutic functions, or overlapping critical quality attributes, such as purity exceeding a certain percentage, bioavailability within a defined range, or stability over a specified shelf life. For example, a manufacturing process is considered similar if it involves the same or comparable production techniques (e.g., fermentation, lyophilization, or tableting), equipment (e.g., bioreactors, tablet presses, or dryers), and operational conditions (e.g., temperature ranges, pH levels, or mixing speeds). Similarity may also depend on the production scale (e.g., pilot-scale versus commercialscale) and adherence to regulatory guidelines or industry standards applicable to the current process. For example, the historical data refers to documented information generated from previous manufacturing processes or products, including process documentation, batch records, and quality reports. This data provides insights into process control parameters with initial target ranges and / or quality target parameters with predetermined target ranges that have been previously defined, tested, and / or validated. The historical data may include information compiled from multiple products and manufacturing processes, even those with varying degrees of similarity to the current product or process. For example, the historical data from monoclonal antibody therapies with slightly different glycosylation profiles but similar bioreactor conditions can be analyzed together to identify trends and refine initial target ranges for process control parameters, such as temperature or dissolved oxygen levels. The historical data may also encompass variability in process control parameters, root cause analyses, or deviations encountered and resolved, contributing to a deeper understanding of quality target parameters critical to ensuring product quality. Statistical analysis, aggregation, and normalization of historical data may be performed to ensure consistency and relevance when deriving initial target ranges for process control parameters and predetermined quality target ranges for the current manufacturing process.

[0049] In some example, the one or more process control parameters with initial target ranges and quality target parameters with predetermined target ranges may be obtained by an input from a person, such as a skilled professionals, for example a process engineer, quality assurance specialist, or scientist with domain expertise. For example, these person may draw upon his knowledge of the product's requirements and manufacturing context to propose one or more process control parameters with initial target ranges and quality target parameters with predetermined target ranges for evaluation.

[0050] As described above, in some examples, the method 100 comprises obtaining and / or determining the one or more pairs of a process control parameter test set and a corresponding quality target parameter test set. In some examples, the one or more pairs of a process control parameter test set and a corresponding quality target parameter test are determined by an external entity. For example, the apparatus 200 (see Fig. 2) that is carrying out the method 100 obtains the one or more pairs of a process control parameter test set and a corresponding quality target parameter test via its interface circuitry 220 from the external entity.

[0051] In some examples, the process control parameter test set and the quality target parameter test set are obtained from a predetermined collection of paired test sets. For example, the predetermined collection of paired test sets may refer to a structured framework that organizes the pairings of process control parameter test sets and quality target parameter test sets to be used in the iterative process. In some examples, the predetermined collection of paired test sets is an ordered list that specifies the sequence in which the pairings are to be processed. In some examples, the predetermined collection of paired test sets is a database that allows querying and flexible access to the pairings. The predetermined collection of paired test sets ensures that the iterative process is guided by a clearly defined scope, covering all relevant relationships between process control parameters and quality target parameters. By obtaining test sets from this collection, the method ensures consistency, traceability, and efficiency in evaluating the relationships and refining the parameters.

[0052] In some examples, the predetermined collection of paired test sets is determined based on regulatory requirements. The regulatory requirements may mandate the evaluation of specific parameters and their interactions to ensure compliance and product quality. For instance, such requirements may be outlined in the “Q8(R2) Pharmaceutical Development” specification from the U.S. Food and Drug Administration issued in November 2009 or in Good Manufacturing Practices (GMP).

[0053] In some examples, the predetermined collection of paired test sets may be based on historical data from one or more similar manufactured products and / or manufacturing processes. Similarity of manufactured products and / or manufacturing processes may be defined as described above. For instance, data from previous manufacturing cycles may provide insights into critical parameter pairings that have influenced quality outcomes, allowing the list to focus on the most relevant combinations.

[0054] In some examples, the one or more pairs of a process control parameter test set and a corresponding quality target parameter test and / or the collection of paired test sets list is determined and obtained by an input from a person, such as a skilled professionals, for example a process engineer, quality assurance specialist, or scientist with domain expertise. For example, these person may draw upon his knowledge of the product's requirements and manufacturing context to propose the one or more pairs of a process control parameter test set and a corresponding quality target parameter test and / or the collection of paired test sets list for evaluation.

[0055] In some examples, the process control parameter test set and the corresponding quality target parameter test set are randomly determined. For example, the random determination may involve a probabilistic approach to selecting pairings from all available process control parameters and quality target parameters, ensuring a diverse and unbiased exploration of parameter relationships. For example, this approach help uncover unexpected influences or interactions between process control parameters and quality target parameters that might otherwise be overlooked in a predefined framework. For example, in this case, the iterative process may stop after a predetermined number of iterations, providing a structured endpoint for the random exploration.

[0056] Coming back to the stopping criterion for the iteration of actions. In some examples, the method 100 comprises determining 130 whether a stopping criterion is satisfied, and if the stopping criterion is not satisfied, performing at least one additional iteration of the actions. For example, this determining whether a stopping criterion is satisfied is performed after the storing 128 of the updated target ranges. In some examples, the stopping criterion is satisfied when each process control parameter is classified as either influencing or not influencing each quality target parameter. This stopping criterion marks the conclusion of the iterative classification process by ensuring that the relationship between every process control parameter and every quality target parameter has been evaluated and fully classified. Once all classifications are complete, the stopping criterion is fulfilled, signaling that the iterative process has addressed all relevant relationships between the parameters. This ensures that the subsequent stages of the method, such as updating target ranges and generating process documentation, are based on a comprehensive understanding of how process control parameters influence quality target parameters.

[0057] In some examples, the stopping criterion is satisfied when each process control parameter is classified as either influencing or not influencing each quality target parameter, and for each influencing process control parameter, a corresponding target range that meets the quality target parameter is defined. This criterion ensures that the iterative process concludes only after all relationships between the process control parameters and quality target parameters have been fully evaluated and classified, and when the updated target ranges for the influencing process control parameters are refined to meet the corresponding quality target parameters. The classification step identifies which process control parameters have a measurable effect on the quality target parameters, and the target range determination step updates the acceptable bounds within which these parameters operate to consistently meet quality standards. By combining these two conditions, this stopping criterion ensures that the iterative process is both thorough and actionable, providing a complete and optimized set of classifications and updated target ranges before proceeding to subsequent steps, such as generating process documentation or implementing the parameters in manufacturing.

[0058] In some examples, the stopping criterion is satisfied when all pairings of process control parameter test sets and corresponding quality target parameter test sets from the predetermined collection of paired test sets are processed. For example, this means that each pairing in the predetermined collection is used once in the iterative process, ensuring that the method systematically evaluates all relevant combinations of parameters. The processing of the pairings may follow an ordered sequence defined within the predetermined collection, or it may involve another systematic approach to ensure all pairings are covered without duplication. By completing the processing of all pairings, the method ensures comprehensive refinement and classification of process control parameters and their relationships with quality target parameters, providing a thorough basis for optimizing the manufacturing process. In some examples, the stopping criterion is satisfied when a predetermined number of iterations has been completed. This provides a structured and predictable endpoint for the iterative process, ensuring that the refinement of process control parameters and quality target parameters is carried out within a defined scope. For example, the process control parameter test sets and quality target parameter test sets evaluated in each iteration may be determined randomly or according to specific selection criteria as described above. The predetermined number of iterations ensures that even when the sets are selected randomly, the iterative process still encompasses a sufficient number of evaluations to optimize the parameters comprehensively.

[0059] Experimental Analysis Data

[0060] As described above, the obtained experimental analysis data refers to data derived from one or more performed experiments that evaluate the relationship between the parameters in the process control parameter test set and the parameters in the quality target parameter test set. In some examples, the experimental analysis is obtained by the apparatus 200 (see Fig. 2) that carries out the method 100 via the interface circuitry 220 from an external entity. For example, input by a person that performed the one or more experiments or from an external apparatus that processed the raw experimental results. In some examples, the method 100 comprises performing and / or controlling one or more actions of determining the experimental analysis data, as described below. In some examples, only one or some or all of the following actions may be performed by the method 100.

[0061] In some examples, the at least one performed iteration of the method 100 further comprises designing 116 an experimental setup for one or more experiments to test the influence of the process control parameters of the process control parameter test set on the corresponding quality target parameters of the quality target parameter test set. For example, the design of the experimental setup may comprise using input data such as the process control parameter test set, the corresponding quality target parameter test set, initial target ranges for the process control parameters, and predefined experimental constraints, such as available equipment, environmental conditions, or regulatory requirements. Based on this input, the experimental setup is generated to define the specific conditions under which the experiments will be conducted to evaluate the relationships between the parameters in the process control parameter test set and the parameters in the quality target parameter test set according to the current iteration. This includes determining the specific values or ranges of the process control parameters to be tested, selecting the methods and equipment for measuring the quality target parameters, and defining the criteria for assessing whether the quality target parameters are met under varying conditions. The output of this design process is a detailed experimental setup, which specifies the parameter values to be applied in each experiment, the required equipment settings (e.g., bioreactor temperature, pH, and agitation speed), the procedural steps to be followed during the experiments, and the expected format for recording and analyzing results. For example, the method 100 comprises obtaining the procedural steps required to conduct the experiments. In some examples, a software tool, such as I DBS Polar, designs the procedural steps to be followed during the experiments, and the method 100 obtains these procedural steps from the software tool. In other examples, the procedural steps are obtained by the apparatus 200, which carries out the method 100, from an external apparatus. For instance, the procedural steps, obtained from a software tool such as I DBS Polar, serve as a foundation for the designed experimental setup. For example, the additional elements of the experimental setup, such as determining the specific values or ranges of the process control parameters to be tested, selecting the methods and equipment for measuring the quality target parameters, and defining the criteria for assessing whether the quality target parameters are met under varying conditions, are then applied to these obtained procedural steps to complete the overall setup for the experiment. The experimental setup ensures that the experiments systematically generate measurable data to analyze how variations in the process control parameters influence the quality target parameters, providing the basis for refining target ranges and classifications. For example, the designing of the experimental setup may be performed by a software such as I DBS Polar and / or I DBS Polar Insight.

[0062] For example, the experimental setup involves testing the effect of temperature (process control parameter) on protein purity (quality target parameter) in a bioreactor. The design may specify testing at temperature levels of 34°C, 36°C, and 38°C while keeping other parameters constant, such as pH at 7.0 and agitation speed at 50 rpm. The setup would also include instructions for using specific sensors to measure protein purity at each temperature level. This ensures the experiments are conducted systematically, generating data that can be analyzed to refine target ranges and improve process control. The design process may be automated using software tools such as I DBS Polar Insight, which facilitate the creation of precise and efficient experimental setups.

[0063] In some examples, the at least one performed iteration of the method 100 further comprises transmitting 118 the designed experimental setup to an external apparatus configured to perform the one or more experiments according to the designed experimental setup. For example, the external apparatus 250 may be connected to the apparatus 200 carrying out the method 100 via the interface circuitry 220 (see Fig. 2 below). For example, the external apparatus is a bioreactor, chromatography system, or spectrometer, or the like. For example, the designed experimental setup includes specific instructions and conditions necessary to evaluate the relationships between the parameters in the process control parameter test set and the parameters in the quality target parameter test set. For example, the experimental setup specifies the process control parameter values or ranges to be tested, the equipment settings, and the procedures to measure the quality target parameters under those conditions. The transmission of the experimental setup ensures that the external apparatus is configured to execute the experiments accurately and according to the defined parameters. The transmission may include data packets containing the experimental setup in a digital format compatible with the external apparatus, such as structured files in XML or JSON, or direct integration with the apparatus’s control system. This ensures that the external apparatus operates within the specified conditions, generating data required for further analysis and refinement of the process control parameters and quality target parameters. For example, a bioreactor may receive the setup instructions to test temperature ranges from 34°C to 38°C while maintaining constant pH and stirring speed, enabling precise evaluation of how these conditions influence protein purity.

[0064] In some examples, the at least one performed iteration of the method 100 further comprises obtaining 120 an experimental result of the one or more experiments performed according to the designed experimental setup. In some examples, the experimental result is obtained by an input of a person that performed the one or more experiments. For example, the person may manually input measured values or observations recorded during the experiment into a system or device configured to process the data. In some examples, the experimental result is obtained by an external apparatus that processed the output of the one or more experiments. For example, an analytical device such as a spectrometer or chromatography system may process raw experimental outputs, such as spectral data or chromatograms, into a structured format that includes the required experimental results.

[0065] In some examples, the at least one performed iteration of the method 100 further comprises obtaining 120 an experimental result from an external apparatus that performed the designed experimental setup. For instance, a bioreactor may directly perform the experiment under the conditions specified in the designed experimental setup, measure parameters such as temperature, pH, and dissolved oxygen, and transmit the processed experimental result to the apparatus 200 performing the method 100. This ensures that the experimental result reflects the relationship between the process control parameters and the quality target parameters under the specified experimental conditions. The obtained experimental result serves as a critical input for subsequent steps, such as classifying the process control parameters and refining their target ranges.

[0066] For example, the obtained experimental result comprises the raw measured results, obtained by an external apparatus that performed the one or more experiments, or by a person that performed the one or more experiments, or by an external apparatus that processed the output of the one or more experiments.

[0067] In some examples, the at least one performed iteration of the method 100 further comprises analyzing 122 the experimental result to determine the experimental analysis data. As described above, the determined experimental analysis data may comprise the raw measured results from the one or more performed experiments and / or data analysis derived from the raw measured results of the one or more performed experiments. For example, the data analysis comprises target range data for determining updated target ranges for process control parameters and statistical analysis derived from the raw measured results of the performed experiment.

[0068] For example, analyzing 122 the experimental result may comprise performing statistical analysis to determine statistical metrics to the experimental results. For example, the statistical analysis and statistical metrics as described may be performed and determined, such as correlation coefficients, regression outputs, p-values, analysis of variance results, and / or sensitivity indices, each of which provides insights into the strength, significance, and nature of the relationships between the process control parameters and the quality target parameters. In some examples, analyzing 122 the experimental result may comprise determining the target range data. For example, this comprises determining the functional relationships between the values of one or more process control parameters and the corresponding one or more quality target parameters as described above.

[0069] Further details and aspects are mentioned in connection with the examples described above or below. The example shown in Fig. 1 may include one or more optional additional features corresponding to one or more aspects mentioned in connection with the proposed concept or one or more examples described below (e.g., Figs. 2 - 3).

[0070] Fig. 2 illustrates a block diagram of an example of an apparatus 200 or device 200 for generating a process documentation for a manufacturing process of a product. The apparatus 200 comprises circuitry that is configured to provide the functionality of the apparatus 200. For example, the apparatus 200 of Fig. 2 comprises interface circuitry 220, processing circuitry 230 and (optional) storage circuitry 240. For example, the processing circuitry 230 may be coupled with the interface circuitry 220 and optionally with the storage circuitry 240.

[0071] For example, the processing circuitry 230 may be configured to provide the functionality of the apparatus 200, in conjunction with the interface circuitry 220. For example, the interface circuitry 220 is configured to exchange information, e.g., with other components inside or outside the apparatus 200 and the storage circuitry 240. Likewise, the device 200 may comprise means that is / are configured to provide the functionality of the device 200.

[0072] The components of the device 200 are defined as component means, which may correspond to, or implemented by, the respective structural components of the apparatus 200. For example, the device 200 of Fig. 2 comprises means for processing 230, which may correspond to or be implemented by the processing circuitry 230, means for communicating 220, which may correspond to or be implemented by the interface circuitry 220, and (optional) means for storing information 240, which may correspond to or be implemented by the storage circuitry 240. In the following, the functionality of the device 200 is illustrated with respect to the apparatus 200. Features described in connection with the apparatus 200 may thus likewise be applied to the corresponding device 200.

[0073] In general, the functionality of the processing circuitry 230 or means for processing 230 may be implemented by the processing circuitry 230 or means for processing 230 executing machine-readable instructions. Accordingly, any feature ascribed to the processing circuitry 230 or means for processing 230 may be defined by one or more instructions of a plurality of machine-readable instructions. The apparatus 200 or device 200 may comprise the machine- readable instructions, e.g., within the storage circuitry 240 or means for storing information 240.

[0074] The interface circuitry 220 or means for communicating 220 may correspond to one or more inputs and / or outputs for receiving and / or transmitting information, which may be in digital (bit) values according to a specified code, within a module, between modules or between modules of different entities. For example, the interface circuitry 220 or means for communicating 220 may comprise circuitry configured to receive and / or transmit information.

[0075] For example, the processing circuitry 230 or means for processing 230may be implemented using one or more processing units, one or more processing devices, any means for processing, such as a processor, a computer or a programmable hardware component being operable with accordingly adapted software. In other words, the described function of the processing circuitry 230 or means for processing 230 may as well be implemented in software, which is then executed on one or more programmable hardware components. Such hardware components may comprise a general-purpose processor, a Digital Signal Processor (DSP), a micro-controller, etc.

[0076] For example, the storage circuitry 240 or means for storing information 240 may comprise at least one element of the group of a computer readable storage medium, such as a magnetic or optical storage medium, e.g., a hard disk drive, a flash memory, Floppy-Disk, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read Only Memory (PROM), Erasable Programmable Read Only Memory (EPROM), an Electronically Erasable Programmable Read Only Memory (EEPROM), or a network storage.

[0077] The processing circuitry 230 is configured to obtain one or more process control parameters with an initial target range, and one or more quality target parameters. The processing circuitry 230 is further configured to perform at least one iteration comprising the following: The processing circuitry 230 that is configured to perform the at least one iteration is configured to obtaining a process control parameter test set. The processing circuitry 230 that is configured to perform the at least one iteration is configured to obtain a process control parameter test set comprising at least one of the process control parameters and to obtain a corresponding quality target parameter test set comprising at least one of the quality target parameters. The processing circuitry 230 that is configured to perform the at least one iteration is configured to classify each parameter of the process control parameter test set as either influencing or not influencing each parameter of the quality target parameter test set, based on an obtained experimental analysis data. The processing circuitry 230 that is configured to perform the at least one iteration is configured to determine for each parameter of the process control parameter test set being classified as influencing, an updated target range based on the obtained experimental analysis data. The processing circuitry 230 that is configured to perform the at least one iteration is configured to store the process documentation with the updated target ranges of the process control parameters of the process control parameter test set and their classification with regards to the parameters of the quality target parameter test set.

[0078] The processing circuitry 230 is further configured to generate a process documentation comprising the stored updated target ranges and classifications for the process control parameters. The processing circuitry 230 is further configured to output the process documentation to a manufacturing system. In some examples, the apparatus 200 may be connected an external apparatus 250. For example, the external apparatus 205 is configured to perform the one or more experiments according to the designed experimental setup according to an experimental setup. For example, the external apparatus 250 is a bioreactor, chromatography system, or spectrometer, or the like. The external apparatus may be connected to the apparatus 200 via the interface circuitry 220. For example, as described above with regards to the method 100, the external apparatus may receive the designed experimental setup from the apparatus 200 via the interface 220 and perform the one or more experiments according to the designed experimental setup. The external apparatus 205 may be further configured to transmit processes or raw experimental results and / or experimental analysis data to the apparatus 200.

[0079] The apparatus 200, for example, the processing circuitry 230, is configured to carry out the method 100 as described with regards to Fig. 1. Further details and aspects are mentioned in connection with the examples described above or below. The example shown in Fig. 2 may include one or more optional additional features corresponding to one or more aspects mentioned in connection with the proposed concept or one or more examples described above (e.g., Fig. 1) or below (e.g., Fig. 3).

[0080] Further Examples

[0081] Fig. 3 illustrates an example of a block chart 300 of the herein disclosed technique. For example, the block chart comprises multiple blocks representing functional steps of the method 100. For example, one or more blocks may correspond to one or more steps described in the method 100. For example, one or more blocks may be implemented by the apparatus 200 and its components.

[0082] In block 310, a process of obtaining one or more initial process control parameters with initial target ranges and one or more quality target parameters is performed (see, for example, step 110 as described with regards to Figs. 1 and 2). For example, the process control parameter candidates, such as pH, temperature, dissolved oxygen (DO), and partial pressure of CO2 (PCO2), and quality target parameters, such as aggregation and purity, may be determined based on historical data, regulatory requirements, or expert input. This process is also referred to as risk assessment. Block 310 outputs the obtained process control parameter candidates and quality target parameters to block 320. This block may be implemented by the software tool Polar Control by IDBS. In block 320, unit operations involved in the manufacturing process are determined (see, for example, step 120 as described with regards to Figs. 1 and 2). For example, these unit operations may involve using a bioreactor or harvest processes, alongside associated process control parameters like pH, temperature, DO, and PCO2. This ensures that unit operations are well-structured and standardized for integration into subsequent experimental setups. Block 320 outputs the documented unit operations to block 330. This block may be implemented by the software tool Polar Control by I DBS.

[0083] In block 330, the iteration starts. In each iteration, the process control parameters and the quality target parameters are documented. For example, a process control parameter test set and a corresponding quality target parameter test set are obtained (see step 114 as described with regards to Figs. 1 and 2). For example, the process control parameter test set comprises pH, temperature, DO, and PCO2, while the corresponding quality target parameter test set comprises purity. In each iteration, block 330 outputs the documented parameters to block 340 and block 350. This block 330 may be implemented by the software tool Polar Control by IDBS.

[0084] In block 340, an experimental setup is designed to test the influence of the process control parameter test set on the quality target parameter test set (see, for example, step 116 as described with regards to Figs. 1 and 2). For example, the design process may use inputs such as process control parameter test sets with initial target ranges (e.g., pH = 6.8-7.2, temperature = 36-40°C, DO = 70-90%) and predefined experimental constraints, such as available equipment or regulatory requirements. The quality target parameter test set comprises purity. The output is a detailed experimental plan specifying test conditions, measurement methods, and evaluation criteria. Block 340 outputs the designed experimental setup to block 350 for performing the one or more experiments. As described above, some parts of the experimental setup may be obtained by the block 340. For example, the design of the procedural steps to be followed during the experiments may be designed by a software tool such as IDBS Polar and then obtained by the block 340. Some or all parts of the block 340 may be implemented by the software tool Polar Insight or Polar by IDBS.

[0085] In block 350, the experimental setup according to the experimental design is executed to test the relationships between the process control parameter test set and the quality target parameter test set. For example, the experiments may involve running 12 iterations at specified setpoints (e.g., pH = 6.9, temperature = 37°C) to gather data on parameter interactions. Block 350 outputs the experimental results to block 360 for analysis. Further, block 350 receives the parameter test sets and initial target ranges for further analysis or forwards them for further analysis from block 330. This block may be implemented by the software tool Polar Core by I DBS.

[0086] In block 360, the experimental results are analyzed to determine relationships between the process control parameters and quality target parameters (see, for example, step 122 as described with regards to Figs. 1 and 2). For example, statistical metrics like correlation coefficients, regression outputs, and sensitivity indices are calculated to assess the impact of specific process control parameters on quality target parameters. The analysis results are transmitted to block 370 for parameter updates. This block may be implemented by the software tool Polar Insight by I DBS.

[0087] In block 370, the process control parameters are classified, and the target ranges are updated based on the analyzed experimental results (see, for example, steps 124 and 126 as described with regards to Figs. 1 and 2). For example, the process control parameters of the process control parameter test set from block 330 are classified as follows: pH and DO are influencing the quality target parameter purity, while temperature and PCO2 are not influencing the quality target parameter purity. Further, the initial target range of pH from 6.8 to 7.2 is updated to 6.9. The updated and classified information is transmitted to block 330, where it is stored and documented. This block may be implemented by the software tool Polar Control by I DBS.

[0088] Then, in block 330, it is determined if the stopping criterion is satisfied. If the stopping criterion is not satisfied, the iteration continues. If it is satisfied, then in block 330, the process documentation is generated and output to the manufacturing system in block 380.

[0089] In block 380, the manufacturing system is implemented. For example, block 380 is implemented by a process information management system (PIMS) (see, for example, step 136 as described with regards to Figs. 1 and 2). For example, the process documentation is formatted to integrate seamlessly with the PIMS. The manufacturing system uses this documentation to monitor, adjust, and validate the manufacturing process, ensuring compliance with quality standards.

[0090] Further details and aspects are mentioned in connection with the examples described above. The example shown in Fig. 3 may include one or more optional additional features corresponding to one or more aspects mentioned in connection with the proposed concept or one or more examples described above (e.g., Figs. 1 - 2). In the following, some examples of the proposed concept are presented:

[0091] An example (e.g., example 1) relates to a method (100) (100) for generating a process documentation for a manufacturing process of a product comprising obtaining (110) one or more process control parameters with an initial target range, and one or more quality target parameters, performing (112) at least one iteration comprising the following actions obtaining (114 a process control parameter test set comprising at least one of the process control parameters and obtaining a corresponding quality target parameter test set comprising at least one of the quality target parameters, classifying (124) each parameter of the process control parameter test set as either influencing or not influencing each parameter of the quality target parameter test set, based on an obtained experimental analysis data, determining (126) for each parameter of the process control parameter test set being classified as influencing, an updated target range based on the obtained experimental analysis data, storing (128) the updated target ranges of the process control parameters of the process control parameter test set and their classification with regards to the parameters of the quality target parameter test set, generating (132) a process documentation comprising the stored updated target ranges and classifications for the process control parameters, and outputting (134) the process documentation to a manufacturing system.

[0092] Another example (e.g., example 2) relates to a previous example (e.g., example 1) or to any other example, further comprising that the method (100) further comprises applying (136) the updated target ranges to adjust the process control parameters during the manufacturing process.

[0093] Another example (e.g., example 3) relates to a previous example (e.g., one of the examples 1 to 2) or to any other example, further comprising that the method (100) further comprises monitoring (136) the process control parameters, and if deviations from the updated target ranges specified in the process documentation are detected, adjusting the process control parameters such that the corresponding quality target parameters are met.

[0094] Another example (e.g., example 4) relates to a previous example (e.g., one of the examples 1 to 3) or to any other example, further comprising that the at least one iteration further comprises designing (116) an experimental setup for one or more experiments to test the influence of the process control parameters of the process control parameter test set on the corresponding quality target parameters of the quality target parameter test set. Another example (e.g., example 5) relates to a previous example (e.g., example 4) or to any other example, further comprising that the at least one iteration further comprises transmitting (118) the designed experimental setup to an external apparatus configured to perform the one or more experiments according to the designed experimental setup.

[0095] Another example (e.g., example 6) relates to a previous example (e.g., one of the examples 4 to 5) or to any other example, further comprising that the at least one iteration further comprises obtaining (120) an experimental result of the one or more experiments performed according to the designed experimental setup.

[0096] Another example (e.g., example 7) relates to a previous example (e.g., one of the examples 4 to 6) or to any other example, further comprising that the at least one iteration further comprises obtaining (120) an experimental result from an external apparatus that performed the designed experimental setup.

[0097] Another example (e.g., example 8) relates to a previous example (e.g., one of the examples 6 to 7) or to any other example, further comprising that the at least one iteration further comprises analyzing (122) the experimental result by performing statistical analysis to determine the experimental analysis data.

[0098] Another example (e.g., example 9) relates to a previous example (e.g., one of the examples 1 to 8) or to any other example, further comprising that the process documentation is formatted in a data format compatible with the manufacturing system.

[0099] Another example (e.g., example 10) relates to a previous example (e.g., one of the examples 1 to 9) or to any other example, further comprising that a process control parameter in the obtained process control parameter test set is classified as influencing a parameter in the obtained quality target parameter test set if a statistical metric between the two parameters exceeds a predetermined threshold.

[0100] Another example (e.g., example 11) relates to a previous example (e.g., one of the examples 1 to 10) or to any other example, further comprising that the method (100) comprises determining (130) whether a stopping criterion is satisfied, and if the stopping criterion is not satisfied, performing at least one additional iteration of the actions.

[0101] Another example (e.g., example 12) relates to a previous example (e.g., example 11) or to any other example, further comprising that the stopping criterion is satisfied when each process control parameter is classified as either influencing or not influencing each quality target parameter.

[0102] Another example (e.g., example 13) relates to a previous example (e.g., one of the examples 11 to 12) or to any other example, further comprising that the stopping criterion is satisfied when each process control parameter is classified as either influencing or not influencing each quality target parameter, and for each influencing process control parameter, a corresponding target range that meets the quality target parameter is defined.

[0103] Another example (e.g., example 14) relates to a previous example (e.g., one of the examples 11 to 13) or to any other example, further comprising that the stopping criterion is satisfied when a predetermined number of iterations has been completed.

[0104] Another example (e.g., example 15) relates to a previous example (e.g., one of the examples 1 to 14) or to any other example, further comprising that the stopping criterion is satisfied when all pairings of process control parameter test sets and corresponding quality target parameter test sets from a predetermined collection of paired test sets are processed.

[0105] Another example (e.g., example 16) relates to a previous example (e.g., one of the examples 1 to 15) or to any other example, further comprising that the process control parameter test set and the quality target parameter test set are obtained from a predetermined collection of paired test sets

[0106] Another example (e.g., example 17) relates to a previous example (e.g., one of the examples 1 to 16) or to any other example, further comprising that the predetermined collection of paired test sets is determined based on regulatory requirements.

[0107] Another example (e.g., example 18) relates to a previous example (e.g., example 17) or to any other example, further comprising that the predetermined collection of paired test sets is determined based on historical data from one or more similar manufactured products and / or manufacturing processes.

[0108] Another example (e.g., example 19) relates to a previous example (e.g., one of the examples 1 to 18) or to any other example, further comprising that process control parameter test set and the corresponding quality target parameter test set are randomly determined. Another example (e.g., example 20) relates to a previous example (e.g., one of the examples 1 to 19) or to any other example, further comprising that each iteration comprises a different pair of a process control parameter test set and a corresponding quality target parameter test set.

[0109] Another example (e.g., example 21) relates to a previous example (e.g., one of the examples 1 to 20) or to any other example, further comprising that the process documentation for is for a pharmaceutical manufacturing process of a pharmaceutical product, the one or more process control parameters are parameters that are controllable during the pharmaceutical manufacturing process, and the one or more quality target parameters of the pharmaceutical product are parameters measured during and / or after the pharmaceutical manufacturing process to confirm the quality of the pharmaceutical product.

[0110] Another example (e.g., example 22) relates to a previous example (e.g., one of the examples 1 to 21) or to any other example, further comprising that the one or more process control parameters are critical process parameters, and the one or more quality target parameters are critical quality attributes.

[0111] Another example (e.g., example 23) relates to a previous example (e.g., one of the examples 1 to 22) or to any other example, further comprising that the obtained process control parameters with the initial target ranges and / or quality target parameters are determined based on historical data from one or more similar manufactured products and / or manufacturing processes.

[0112] An example (e.g., example 24) relates to an apparatus (200) for generating a process documentation for a manufacturing process of a product comprising interface circuitry (220), machine-readable instructions and processing circuitry (230) to execute the machine- readable instructions to obtain one or more process control parameters with an initial target range, and one or more quality target parameters, perform at least one iteration comprising the following actions obtain a process control parameter test set comprising at least one of the process control parameters and obtain a corresponding quality target parameter test set comprising at least one of the quality target parameters, classify each parameter of the process control parameter test set as either influencing or not influencing each parameter of the quality target parameter test set, based on an obtained experimental analysis data, determine for each parameter of the process control parameter test set being classified as influencing, an updated target range based on the obtained experimental analysis data, store the process documentation with the updated target ranges of the process control parameters of the process control parameter test set and their classification with regards to the parameters of the quality target parameter test set, generate a process documentation comprising the stored updated target ranges and classifications for the process control parameters, and output the process documentation to a manufacturing system.

[0113] Another example (e.g., example 25) relates to a previous example (e.g., example 25) or to any other example, further comprising that the processing circuitry (230) is further to execute the machine-readable instructions to apply the updated target ranges to adjust the process control parameters during the manufacturing process.

[0114] Another example (e.g., example 26) relates to a previous example (e.g., one of the examples 24 or 25) or to any other example, further comprising that the processing circuitry (230) is further to execute the machine-readable instructions to monitor the process control parameters and, if deviations from the updated target ranges specified in the process documentation are detected, adjust the process control parameters such that the corresponding quality target parameters are met.

[0115] Another example (e.g., example 27) relates to a previous example (e.g., one of the examples 24 to 26) or to any other example, further comprising that the processing circuitry (230) is further to execute the machine-readable instructions to design an experimental setup for one or more experiments to test the influence of the process control parameters of the process control parameter test set on the corresponding quality target parameters of the quality target parameter test set.

[0116] Another example (e.g., example 28) relates to a previous example (e.g., example 27) or to any other example, further comprising that the processing circuitry (230) is further to execute the machine-readable instructions to transmit the designed experimental setup to an external apparatus configured to perform the one or more experiments according to the designed experimental setup.

[0117] Another example (e.g., example 29) relates to a previous example (e.g., one of the examples 27 to 28) or to any other example, further comprising that the processing circuitry (230) is further to execute the machine-readable instructions to obtain an experimental result of the one or more experiments performed according to the designed experimental setup.

[0118] Another example (e.g., example 30) relates to a previous example (e.g., one of the examples 27 to 29) or to any other example, further comprising that the processing circuitry (230) is further to execute the machine-readable instructions to obtain an experimental result from an external apparatus that performed the designed experimental setup.

[0119] Another example (e.g., example 31) relates to a previous example (e.g., one of the examples 29 to 30) or to any other example, further comprising that the processing circuitry (230) is further to execute the machine-readable instructions to analyze the experimental result by performing statistical analysis to determine the experimental analysis data.

[0120] Another example (e.g., example 32) relates to a previous example (e.g., one of the examples 24 to 31) or to any other example, further comprising that the process documentation is formatted in a data format compatible with the manufacturing system.

[0121] Another example (e.g., example 33) relates to a previous example (e.g., one of the examples 24 to 32) or to any other example, further comprising that the processing circuitry (230) is further to execute the machine-readable instructions to classify a process control parameter in the obtained process control parameter test set as influencing a parameter in the obtained quality target parameter test set if a statistical metric between the two parameters exceeds a predetermined threshold.

[0122] Another example (e.g., example 34) relates to a previous example (e.g., one of the examples 24 to 33) or to any other example, further comprising that the processing circuitry (230) is further to execute the machine-readable instructions to determine whether a stopping criterion is satisfied and, if the stopping criterion is not satisfied, perform at least one additional iteration of the actions.

[0123] Another example (e.g., example 35) relates to a previous example (e.g., example 34) or to any other example, further comprising that the stopping criterion is satisfied when each process control parameter is classified as either influencing or not influencing each quality target parameter.

[0124] Another example (e.g., example 36) relates to a previous example (e.g., one of the examples 34 to 35) or to any other example, further comprising that the stopping criterion is satisfied when each process control parameter is classified as either influencing or not influencing each quality target parameter, and for each influencing process control parameter, a corresponding target range that meets the quality target parameter is defined. Another example (e.g., example 37) relates to a previous example (e.g., one of the examples 34 to 36) or to any other example, further comprising that the stopping criterion is satisfied when a predetermined number of iterations has been completed.

[0125] Another example (e.g., example 38) relates to a previous example (e.g., one of the examples 24 to 37) or to any other example, further comprising that the stopping criterion is satisfied when all pairings of process control parameter test sets and corresponding quality target parameter test sets from a predetermined collection of paired test sets are processed.

[0126] Another example (e.g., example 39) relates to a previous example (e.g., one of the examples 24 to 38) or to any other example, further comprising that the process control parameter test set and the quality target parameter test set are obtained from a predetermined collection of paired test sets.

[0127] Another example (e.g., example 40) relates to a previous example (e.g., one of the examples 24 to 39) or to any other example, further comprising that the predetermined collection of paired test sets is determined based on regulatory requirements.

[0128] Another example (e.g., example 41) relates to a previous example (e.g., example 39) or to any other example, further comprising that the predetermined collection of paired test sets is determined based on historical data from one or more similar manufactured products and / or manufacturing processes.

[0129] Another example (e.g., example 42) relates to a previous example (e.g., one of the examples 24 to 41) or to any other example, further comprising that the process control parameter test set and the corresponding quality target parameter test set are randomly determined.

[0130] Another example (e.g., example 43) relates to a previous example (e.g., one of the examples 45 to 42) or to any other example, further comprising that each iteration comprises a different pair of a process control parameter test set and a corresponding quality target parameter test set.

[0131] Another example (e.g., example 44) relates to a previous example (e.g., one of the examples 24 to 43) or to any other example, further comprising that the process documentation is for a pharmaceutical manufacturing process of a pharmaceutical product, the one or more process control parameters are parameters that are controllable during the pharmaceutical manufacturing process, and the one or more quality target parameters of the pharmaceutical product are parameters measured during and / or after the pharmaceutical manufacturing process to confirm the quality of the pharmaceutical product.

[0132] Another example (e.g., example 45) relates to a previous example (e.g., one of the examples 24 to 44) or to any other example, further comprising that the one or more process control parameters are critical process parameters, and the one or more quality target parameters are critical quality attributes.

[0133] Another example (e.g., example 46) relates to a previous example (e.g., one of the examples 24 to 45) or to any other example, further comprising that the obtained process control parameters with the initial target ranges and / or quality target parameters are determined based on historical data from one or more similar manufactured products and / or manufacturing processes.

[0134] Another example (e.g., example 47) relates to a non-transitory computer-readable medium storing instructions that, when executed by one or more processing circuitries, causing the one or more processing circuitries to perform the method (100) of any one of examples 1 to 23.

[0135] An example (e.g., example 48) relates to an apparatus comprising a processor circuitry configured to obtain one or more process control parameters with an initial target range, and one or more quality target parameters, perform at least one iteration comprising the following actions obtain a process control parameter test set comprising at least one of the process control parameters and obtain a corresponding quality target parameter test set comprising at least one of the quality target parameters, classify each parameter of the process control parameter test set as either influencing or not influencing each parameter of the quality target parameter test set, based on an obtained experimental analysis data, determine for each parameter of the process control parameter test set being classified as influencing, an updated target range based on the obtained experimental analysis data, store the process documentation with the updated target ranges of the process control parameters of the process control parameter test set and their classification with regards to the parameters of the quality target parameter test set, generate a process documentation comprising the stored updated target ranges and classifications for the process control parameters, and output the process documentation to a manufacturing system.

[0136] An example (e.g., example 49) relates to a device comprising means for processing for obtaining (110) one or more process control parameters with an initial target range, and one or more quality target parameters, performing (112) at least one iteration comprising the following actions obtaining (114 a process control parameter test set comprising at least one of the process control parameters and obtaining a corresponding quality target parameter test set comprising at least one of the quality target parameters, classifying (124) each parameter of the process control parameter test set as either influencing or not influencing each parameter of the quality target parameter test set, based on an obtained experimental analysis data, determining (126) for each parameter of the process control parameter test set being classified as influencing, an updated target range based on the obtained experimental analysis data, storing (128) the updated target ranges of the process control parameters of the process control parameter test set and their classification with regards to the parameters of the quality target parameter test set, generating (132) a process documentation comprising the stored updated target ranges and classifications for the process control parameters, and outputting (134) the process documentation to a manufacturing system.

[0137] Another example (e.g., example 50) relates to a computer program having a program code for performing the method of any one of examples 1 to 23 when the computer program is executed on a computer, a processor, or a programmable hardware component.

[0138] Another example (e.g., example 51) relates to a machine-readable storage including machine readable instructions, when executed, to implement a method or realize an apparatus as claimed in any pending claim.

[0139] The aspects and features described in relation to a particular one of the previous examples may also be combined with one or more of the further examples to replace an identical or similar feature of that further example or to additionally introduce the features into the further example.

[0140] Examples may further be or relate to a (computer) program including a program code to execute one or more of the above methods when the program is executed on a computer, processor or other programmable hardware component. Thus, steps, operations or processes of different ones of the methods described above may also be executed by programmed computers, processors or other programmable hardware components. Examples may also cover program storage devices, such as digital data storage media, which are machine-, processor- or computer-readable and encode and / or contain machineexecutable, processor-executable or computer-executable programs and instructions. Program storage devices may include or be digital storage devices, magnetic storage media such as magnetic disks and magnetic tapes, hard disk drives, or optically readable digital data storage media, for example. Other examples may also include computers, processors, control units, (field) programmable logic arrays ((F)PLAs), (field) programmable gate arrays ((F)PGAs), graphics processor units (GPU), application-specific integrated circuits (ASICs), integrated circuits (ICs) or system-on-a-chip (SoCs) systems programmed to execute the steps of the methods described above.

[0141] It is further understood that the disclosure of several steps, processes, operations or functions disclosed in the description or claims shall not be construed to imply that these operations are necessarily dependent on the order described, unless explicitly stated in the individual case or necessary for technical reasons. Therefore, the previous description does not limit the execution of several steps or functions to a certain order. Furthermore, in further examples, a single step, function, process or operation may include and / or be broken up into several sub-steps, -functions, -processes or -operations.

[0142] If some aspects have been described in relation to a device or system, these aspects should also be understood as a description of the corresponding method. For example, a block, device or functional aspect of the device or system may correspond to a feature, such as a method step, of the corresponding method. Accordingly, aspects described in relation to a method shall also be understood as a description of a corresponding block, a corresponding element, a property or a functional feature of a corresponding device or a corresponding system.

[0143] The following claims are hereby incorporated in the detailed description, wherein each claim may stand on its own as a separate example. It should also be noted that although in the claims a dependent claim refers to a particular combination with one or more other claims, other examples may also include a combination of the dependent claim with the subject matter of any other dependent or independent claim. Such combinations are hereby explicitly proposed, unless it is stated in the individual case that a particular combination is not intended. Furthermore, features of a claim should also be included for any other independent claim, even if that claim is not directly defined as dependent on that other independent claim.

Claims

1. ClaimsWhat is claimed is:

1. A method (100) (100) for generating a process documentation for a manufacturing process of a product comprising: obtaining (110) one or more process control parameters with an initial target range, and one or more quality target parameters; performing (112) at least one iteration comprising the following actions: obtaining (114 a process control parameter test set comprising at least one of the process control parameters and obtaining a corresponding quality target parameter test set comprising at least one of the quality target parameters; classifying (124) each parameter of the process control parameter test set as either influencing or not influencing each parameter of the quality target parameter test set, based on an obtained experimental analysis data; determining (126) for each parameter of the process control parameter test set being classified as influencing, an updated target range based on the obtained experimental analysis data; storing (128) the updated target ranges of the process control parameters of the process control parameter test set and their classification with regards to the parameters of the quality target parameter test set; generating (132) a process documentation comprising the stored updated target ranges and classifications for the process control parameters; and outputting (134) the process documentation to a manufacturing system.

2. The method (100) of claim 1 , wherein the method (100) further comprises applying (136) the updated target ranges to adjust the process control parameters during the manufacturing process.

3. The method (100) of any one of claims 1 to 2, wherein the method (100) further comprises monitoring (136) the process control parameters; and if deviations from the updated target ranges specified in the process documentation are detected, adjusting the process control parameters such that the corresponding quality target parameters are met.

4. The method (100) of any one of claims 1 to 3, wherein the at least one iteration further comprises designing (116) an experimental setup for one or more experiments to test the influence of the process control parameters of the process control parameter test set on the corresponding quality target parameters of the quality target parameter test set.

5. The method (100) of claim 4, wherein the at least one iteration further comprises transmitting (118) the designed experimental setup to an external apparatus configured to perform the one or more experiments according to the designed experimental setup.

6. The method (100) of any one of claims 4 to 5, wherein the at least one iteration further comprises obtaining (120) an experimental result of the one or more experiments performed according to the designed experimental setup.

7. The method (100) of any one of claims 4 to 6, wherein the at least one iteration further comprises obtaining (120) an experimental result from an external apparatus that performed the designed experimental setup.

8. The method (100) of any one of claims 6 to 7, wherein the at least one iteration further comprises analyzing (122) the experimental result by performing statistical analysis to determine the experimental analysis data.

9. The method (100) of any one of claims 1 to 8, wherein the process documentation is formatted in a data format compatible with the manufacturing system.

10. The method (100) of any one of claims 1 to 9, wherein a process control parameter in the obtained process control parameter test set is classified as influencing a parameter in the obtained quality target parameter test set if a statistical metric between the two parameters exceeds a predetermined threshold.

11. The method (100) of any one of claims 1 to 10, wherein the method (100) comprises determining (130) whether a stopping criterion is satisfied, and if the stopping criterion is not satisfied, performing at least one additional iteration of the actions.

12. The method (100) of claim 11 , wherein the stopping criterion is satisfied when each process control parameter is classified as either influencing or not influencing each quality target parameter.

13. The method (100) of any one of claims 11 to 12, wherein the stopping criterion is satisfied when each process control parameter is classified as either influencing or not influencing each quality target parameter, and for each influencing process control parameter, a corresponding target range that meets the quality target parameter is defined.

14. The method (100) of any one of claims 11 to 13, wherein the stopping criterion is satisfied when a predetermined number of iterations has been completed.

15. The method (100) of any one of claims 1 to 14, wherein the stopping criterion is satisfied when all pairings of process control parameter test sets and corresponding quality target parameter test sets from a predetermined collection of paired test sets are processed.

16. The method (100) of any one of claims 1 to 15, wherein the process control parameter test set and the quality target parameter test set are obtained from a predetermined collection of paired test sets17. The method (100) of any one of claims 1 to 16, wherein the predetermined collection of paired test sets is determined based on regulatory requirements.

18. The method (100) of claim 17, wherein the predetermined collection of paired test sets is determined based on historical data from one or more similar manufactured products and / or manufacturing processes.

19. The method (100) of any one of claims 1 to 18, wherein the obtained process control parameters with the initial target ranges and / or quality target parameters are determined based on historical data from one or more similar manufactured products and / or manufacturing processes.

20. An apparatus (200) for generating a process documentation for a manufacturing process of a product comprising interface circuitry (220), machine-readable instructions and processing circuitry (230) to execute the machine-readable instructions to: obtain one or more process control parameters with an initial target range, and one or more quality target parameters; perform at least one iteration comprising the following actions: obtain a process control parameter test set comprising at least one of the process control parameters and obtain a corresponding quality target parameter test set comprising at least one of the quality target parameters; classify each parameter of the process control parameter test set as either influencing or not influencing each parameter of the quality target parameter test set, based on an obtained experimental analysis data; determine for each parameter of the process control parameter test set being classified as influencing, an updated target range based on the obtained experimental analysis data;store the process documentation with the updated target ranges of the process control parameters of the process control parameter test set and their classification with regards to the parameters of the quality target parameter test set; generate a process documentation comprising the stored updated target ranges and classifications for the process control parameters; and output the process documentation to a manufacturing system.

Images