System and method for dynamic correction enzyme selection and formulation for pulp and paper production

Abstract

The systems and methods disclosed herein provide automated real-time metering correction for industrial processes in which enzyme blends are applied to natural fibers used in pulp / paper production. An initial enzyme blend (e.g., enzyme and support formulation components, as relevant) and a corresponding dosage rate are selected for application based on expected fiber surface substrate characterization, expected fiber quality characterization, the physical conditions of the system being treated, and the corresponding characteristics of the initially selected enzyme blend components. After the initial enzyme blend is applied, online sensors provide real-time feedback data corresponding to the measured actual values ​​for fiber surface substrate characterization and fiber quality characterization. Based on the feedback data, alternative enzyme blends (enzyme and support formulation components) and their corresponding dosage rates are dynamically selected. The enzyme metering stage can be optimized substantially in real-time in response to changes in product and / or fiber source / blend and / or physical conditions.

Description

Technical Field

[0001] This invention generally relates to systems and methods for component characterization and feedback implementation in industrial processes.

[0002] More specifically, embodiments of the invention disclosed herein relate to systems and methods for optimizing enzyme selection and dosing in pulp and paper production, and for further proactive, real-time correction of enzyme dosing based on feedback from online sensors and data analysis. However, alternative embodiments of the systems and methods disclosed herein may be applied to other processes such as, for example, biomass production. Background Technology

[0003] Conventional papermaking methods typically include: forming an aqueous suspension of cellulose fibers, commonly referred to as pulp; adding various processing and paper-reinforcing materials, such as reinforcing, retention, drainage aids, and / or sizing materials, or other functional additives; sheeting and drying the fibers to form a desired cellulose web; and post-treating the web to impart various desired properties to the resulting paper, such as surface application of sizing materials, and the like. Various types of enzyme compositions with varying enzyme dosage ratios may be applied accordingly to treat the fibers to improve pulp properties (e.g., improve drainage of the fiber suspension pulp) and / or the properties of the finished sheet (e.g., strength, porosity, softness).

[0004] When pulp and paper producers purchase and / or produce fibers and conduct grading activities, the fiber properties are observed to vary for a variety of reasons, including but not limited to the species of tree used to produce the fiber, the blend of fibers used, whether the fiber is virgin or recycled, tree growth conditions, seasonality, pulping processes, pulp treatment, and the like. This introduces inherent variability into the process and can alter the type and amount of enzymes that should be metered into the system used to apply bleaching and / or fiber-modifying enzymes. Adding the wrong enzyme mixture or dosage can lead to unnecessary activity, wasted chemical expenditure, or overdevelopment of the fiber, further resulting in a loss of efficiency.

[0005] The goal is to generate and utilize a database of fiber surface characterization data, fiber quality analysis, system physical conditions (e.g., temperature, pH, flow rate, conductivity, ORP, biocide residues), and appropriate enzyme pumping equipment to ensure the metered addition of enzymes optimized for specific fibers / ingredients and systems.

[0006] Further aspiration would be if such optimized metering techniques could be applied to bleaching processes and / or paper machines to aid in the bleaching and / or physical properties of finished sheets (e.g., tensile strength, bursting strength, drainage, porosity, etc.).

[0007] Conventional systems and methods are known to achieve fiber surface characterization, fiber quality analysis, and manual and online sensors for physical conditions and enzyme formulations to improve stability and performance.

[0008] However, such conventional techniques are greatly limited because the technologies they utilize are often unreliable in practice and typically focus on a single part of enzyme selection and formulation methods rather than providing or otherwise enabling a more comprehensive framework. Summary of the Invention

[0009] Generally speaking, the systems and methods disclosed herein represent a technological advancement relative to the prior art, at least in that they can utilize databases of information to provide algorithms for product selection and application, which can be adjusted substantially in real time using measurements of fiber and physical conditions. Such algorithms can be dynamic in nature, based on observed correlations over time between various combinations of process inputs and fiber quality, product efficacy, and desired outcomes in the like.

[0010] The systems disclosed herein can preferably provide accessible visualizations, alerts, notifications, and the like via onboard user interfaces, mobile computing devices, web-based interfaces, etc., to complement any automation capabilities and actionable insights related to the relevant processes.

[0011] Exemplary techniques for developing predictive models may include supervised and unsupervised learning, hard and soft clustering, classification, forecasting, and the like.

[0012] One objective of this disclosure is to provide a database of several key fiber, enzyme, and system data points to determine the optimal enzyme blends and dosages for specific applications. In short, the systems and methods can correlate fiber surface substrate characterization, fiber quality analysis data (including elements such as fiber length, fiber width, fibrillation, kinking, crimp, etc.), enzyme activity fingerprints, physical measurements from the process (pH, temperature, and flow rate / retention time), and product efficacy data to provide initial product blends and dosing rates. The system can be implemented for a single aspect of the entire process or as part of a pumping skid that blends multiple raw materials together to obtain optimal blends and dosing rates. For example, the skid can be integrated with online sensors for flow rate, temperature, chemical residues, and pH, as well as system data related to the strength, degrees of freedom, and quality of the finished sheet, to determine whether optimal dosing has been achieved. Furthermore, as data related to fiber quality and substrate prevalence are collected and uploaded to the system, the balance of the present enzyme raw materials can be adjusted over time.

[0013] The system output can, for example, be fed into a metering skid that blends the enzyme raw materials for direct delivery to pulp or paper applications, and can be particularly advantageous in at least pulp bleaching and tissue / packaging / paper applications.

[0014] The systems and methods disclosed herein can further utilize a front-end data acquisition application that feeds information into the entire database, wherein such information can be further transmitted wirelessly or via integrated signals to the blending and metering add-on skid. Various sensors, controllers, online devices, and other intermediate components can be compatible with the Internet of Things (IoT) or otherwise form an interconnected network, where relevant outputs can be uploaded to a cloud-based server in real time.

[0015] In view of some or all of the above-mentioned problems and objectives, a first exemplary embodiment of the method disclosed herein automatically provides real-time metering correction in an industrial process in which one or more enzymes (and supporting formulation components) are applied to natural fibers used to produce pulp or paper products. Such natural fibers may, of course, include wood fibers, but may also potentially include other cellulosic fibers and non-traditional paper ingredients, including bamboo, grass (e.g., bagasse), etc. The first step includes, at least in part, selecting an initial enzyme blend to be applied, and a corresponding dosage rate for one or more of its components, based on input data including a characterization of the expected fiber surface substrate for the pulp or paper product, a characterization of the expected fiber quality for the pulp or paper product, and one or more corresponding properties of the one or more enzyme blend components. After the initial enzyme blend and the corresponding dosage rate for one or more of its components are applied, real-time feedback data corresponding to the measured actual values ​​of the fiber surface substrate characterization and fiber quality characterization are provided. Another step includes, at least in part, dynamically selecting an alternative enzyme blend to be applied, and a corresponding dosage rate for one or more of its components, based on the feedback data.

[0016] In a second embodiment, an exemplary aspect of the first embodiment described above may include further selecting the initial enzyme blend to be applied and the corresponding dosage rate based on expected values ​​for one or more industrial process characteristics, and real-time feedback data further including measurements of the one or more industrial process characteristics.

[0017] In a third embodiment, an exemplary aspect of either the first or second embodiment described above may further include that the real-time feedback data further includes measurements of industrial process characteristics, including one or more of temperature, system flow rate, pH value, conductivity value, ORP value, biocide residue value, and residence time. Further examples of the characteristics considered may include pulp furnishing and pulping methods.

[0018] In a fourth embodiment, an exemplary aspect of any of the first to third embodiments described above may include using a predetermined model associated with pulp or paper product to select an initial enzyme blend and a corresponding dosage rate to produce results from an industrial process, and the method further includes selectively altering the predetermined model based at least in part on provided real-time feedback data.

[0019] In a fifth embodiment, an exemplary aspect of any of the first to fourth embodiments described above may include blending one or more components of an initial enzyme blend according to a first total dose rate, and applying the blended initial enzyme blend to one or more components during an industrial process. This exemplary aspect may be provided via a metering control stage (e.g., embodied by or otherwise included by a metering controller), which may be further configured, for example, to blend one or more components of a selected alternative enzyme blend according to a total dose rate, and to apply the blended selected alternative enzyme blend to replace one or more components of the initial enzyme blend.

[0020] In the sixth embodiment, an exemplary aspect of any of the first to fifth embodiments described above may include determining fiber quality characterization relative to one or more of fiber length, width, fibrillation, cell wall thickness, fineness density / distribution, fiber kinking, and fiber crimp.

[0021] In the seventh embodiment, an exemplary aspect of any of the first to sixth embodiments described above may include real-time feedback data that further includes system performance data regarding one or more of the following: fiber strength, porosity, caliper, softness, crepe count, degrees of freedom, and drainage of the pulp or paper product.

[0022] In the eighth embodiment, an exemplary aspect of any of the first to seventh embodiments described above may include providing the selected initial enzyme blend and the dynamically selected alternative enzyme blend to be applied, along with their respective dosage rates, to the pulp bleaching process controller.

[0023] In the ninth embodiment, an exemplary aspect of any of the first to seventh embodiments described above may include providing the selected initial enzyme blend and the dynamically selected alternative enzyme blend to be applied, along with their respective dosage rates, to the papermaking controller.

[0024] In a tenth exemplary embodiment, the system as disclosed herein automatically provides real-time metering correction in an industrial process in which one or more components of an enzyme blend are applied to natural fibers used to produce pulp or paper products. The data storage unit includes models relating one or more pulps or paper products to corresponding expected fiber surface substrate characterization and expected fiber quality characterization, and further includes data corresponding to enzyme properties. One or more online sensors are configured to generate output signals representing measured actual values ​​for the fiber surface substrate characterization and fiber quality characterization. The production stage may include multiple containers, each configured to store and selectively deliver corresponding raw materials corresponding to selected enzyme blend components. The metering control stage may include one or more computing devices functionally linked to the data storage unit and the one or more online sensors, and configured to guide the implementation of steps in a method corresponding to any of the first to ninth embodiments.

[0025] The one or more computing devices may include, for example, a metering addition controller according to the fifth exemplary embodiment described above.

[0026] In a further optional aspect, the production stage according to the tenth exemplary embodiment may include a pulp bleaching process controller configured to receive and apply an initial set of selected one or more enzymes and a dynamically selected alternative set of one or more enzymes, and their corresponding dosage rates.

[0027] In a further optional aspect, the production stage according to the tenth exemplary embodiment may include a papermaking controller configured to receive and apply an initial set of selected one or more enzymes and a dynamically selected alternative set of one or more enzymes, and their corresponding dosage rates.

[0028] The computing device, metering add-in controller, pulp bleaching process controller, and / or papermaking controller described in any of the first to tenth exemplary embodiments may be integrated in the same device within the scope of this disclosure, or some or all of them may be provided as discrete components.

[0029] Many of the objects, features and advantages of the embodiments set forth herein will readily become apparent to those skilled in the art upon reading the following disclosure in conjunction with the accompanying drawings. Attached Figure Description

[0030] Figure 1 This is a block diagram representing an exemplary implementation of the system disclosed herein.

[0031] Figure 2These are figures and simplified flowcharts representing exemplary embodiments of the methods disclosed herein for initial product and dosage selection, as well as subsequent adjustments based on fiber and system parameters. Detailed Implementation

[0032] In short, the systems and methods disclosed herein enable the correlation of ingredients, systems, and enzyme properties to provide customized or otherwise optimized metering for enzyme blends as needed, maintaining desirable properties of the finished pulp or paper product. While the following description of embodiments of the systems and methods disclosed herein may focus on the selection and formulation of one or more enzymes for illustrative purposes, those skilled in the art will understand the relevance of such methods to the corresponding selection and / or formulation of supporting components (e.g., nonionic surfactants, polymers, etc.) used in enzyme technology, which potentially contributes to system optimization regarding enzyme activity. Enzymes and corresponding auxiliaries, such as polymeric surfactants used in the systems and methods disclosed herein, may be supplied individually or collectively as enzyme blends, and their selection, formulation, and dynamic adaptation can be enhanced through various embodiments of this disclosure.

[0033] Original Reference Figure 1 As disclosed herein, system 100 may include multiple metering control stages 106a, 106b, ... 106x, as shown in coordination with a production stage 110 (e.g., a pulp or paper production stage), wherein each metering control stage is provided for a corresponding enzyme to be applied to the prepared composition. Alternatively, the selection and metering operation may be performed within the scope of this disclosure with respect to multiple enzymes mixed together to form an enzyme product via a single metering control stage.

[0034] An array of sensors 102, including, for example, online sensors 102, is linked to a metering addition control stage 106 and a data storage 104, including, for example, one or more databases 104, having models, algorithms, and data for implementing the methods and operations disclosed herein. Output from the metering addition control stage may include metering addition information 108 provided to the pulp or paper production stage 110, which further provides feedback information 112 to the metering addition control stage. The feedback information 112 from the production stage 110 is shown independently of the array of sensors 102, but it will be understood that feedback 112 may include signals from the array of sensors. The metering addition control stage 106 may further provide feedback information 114 to the data storage 104, for example, in cases where the model is improved through observation and machine learning.

[0035] The term "sensor" may include, but is not limited to, physical level sensors, relays, and equivalent monitoring devices, which may be provided to directly measure the value or variable of a relevant process component or element, or to measure or calculate an appropriate derivative value of a process component or element. As used herein, the term "online" generally refers to the use of equipment, sensors, or corresponding elements located in proximity to a container, machine, or relevant process element, and generating an output signal corresponding to the desired process element substantially in real time, as opposed to "offline" analysis involving manual or automated sample collection and in a laboratory setting or by visual observation by one or more operators.

[0036] The online sensor 102 is well known in the art for the purpose of sensing or calculating properties such as temperature, flow rate, ORP, conductivity, biocide residues, pH, and the like, and exemplary such sensors are considered to be fully compatible with the scope of the systems and methods disclosed herein. A single sensor may be installed and configured individually, or system 100 may be provided with a modular housing that includes, for example, multiple sensors or sensing elements. Sensors or sensing elements may be permanently or portablely mounted at a specific location associated with production phase 110, or may be dynamically adjustable in location to collect data from multiple locations during operation.

[0037] The online sensor 102 disclosed herein provides substantially continuous and substantially real-time measurements of various process components and elements. As used herein, the terms "continuous" and "real-time," at least with respect to the disclosed sensor output, do not require an explicit degree of continuity, but rather generally describe a series of measurements corresponding to the physical and technical capabilities of the sensor, the physical and technical capabilities of the transmission medium, any intervening local controller, communication equipment, and / or interfaces configured to receive the sensor output signal, etc. For example, measurements may be performed and provided periodically and at a rate slower than the maximum possible rate based on the relevant hardware components or based on the communication network configuration that smooths out input values ​​over time, and are still considered "continuous."

[0038] The user interface (not shown) may further enable users (e.g., operators, administrators, and the like) to provide periodic input regarding the conditions or states of additional components related to models, algorithms, or the like, as further discussed herein. The user interface may functionally communicate with metering-added control phase 106, a distributed control system (not shown) associated with the industrial facility, and / or a remote hosting server (not shown) to receive and display process-related information or provide other forms of feedback regarding control processes, such as those further discussed herein. Unless otherwise stated, the term "user interface" as used herein may include any input-output modules relating to the controller and / or the hosting data server, including but not limited to: stationary operator panels, touchscreens, buttons, dials, or the like with keyed data input; portals, such as single web pages or those collectively defining the hosting website; mobile device applications; and the like.

[0039] The term "communication network" as used herein, relating to data communication between two or more system components or otherwise between communication network interfaces associated with two or more system components, may refer to any one or any combination of two or more of the following: telecommunications networks (whether wired, wireless, cellular, or the like), global networks such as the Internet, local networks, network links, Internet Service Providers (ISPs), and intermediate communication interfaces. Any one or more conventionally recognized interface standards may be used for implementation therein, including but not limited to Bluetooth, RF, Ethernet, and the like.

[0040] The implementation scheme of method 200 is now available for reference. Figure 2 The steps described herein are exemplary only and are not intended to explicitly limit the scope of this disclosure unless otherwise stated.

[0041] Various inputs 211-215 are provided for initial product selection 220, which may refer to selecting each enzyme to be applied, one of a variety of enzymes to be applied, or an enzyme blend further incorporating one or more adjuvants (e.g., nonionic surfactants or the like).

[0042] Fiber surface substrate characterization data 211 can be selectively extracted from a database linked to a metering adder controller in various embodiments. Many conventional techniques are known to characterize fiber surface substrates in a manner that facilitates enzyme selection and formulation, and such techniques are considered to be within the scope of this disclosure and can be combined with one or more other inputs as further described herein. Many techniques are conventionally known for fiber surface characterization, including, for example, X-ray photoelectron spectroscopy (XPS), scanning electron microscopy (SEM), time-of-flight secondary ion mass spectrometry (ToF-SIMS), Fourier transform infrared (FTIR), etc. However, in the context of this disclosure, techniques for the rapid characterization of fiber surface polymers are preferred, as these techniques will better enable the prediction of the effects of various treatments on pulp or paper. Exemplary sensors (detection probes) and methods of using them, as disclosed in U.S. Patent No. 10,788,477, are incorporated herein by reference and can be implemented accordingly within the scope of this disclosure for such characterization, or data obtained therefrom may be selectively accessible in databases for various enzyme selection and formulation steps or operations based on other inputs as described below.

[0043] Fiber quality data 212 can be collected and transmitted or uploaded to the metering add controller from one or more sensors known in the art, substantially in real time, and involves, for example, conventional fiber quality variables such as fiber length, fiber width, fiber roughness, fiber kink angle, fraction quantity / density, fiber crimp, external fibrillation, cell wall thickness, and the like. Such sensors may be, within the scope of this disclosure, online measuring devices and / or automated or manually operable offline fiber image analyzers, and the like. Related outputs of the metering add control phase may further include the raw sensed signal, its converted and / or derivative values, machine learning classification of the sensed signal, and the like.

[0044] Enzyme function characterization data 213 may, for example, involve activity profiles or fingerprints associated with a given enzyme, measured from a data storage facility or otherwise retrieved.

[0045] Application results data 214 may typically involve observed results from system performance feedback, such as in the context of machine learning, with the aim of optimizing future product blends and relative dosages, but may also encompass user input from the user interface to, for example, further define, confirm, or otherwise reverse findings generated by the system.

[0046] Physical condition data 215 can be collected and transmitted or uploaded substantially in real time from one or more sensors known in the art to the metering adder controller, relating to, for example, common variables such as temperature, pH, flow rate, residence time, and the like. Such sensors providing physical condition data can be online sensors and / or manual sensors within the scope of this disclosure.

[0047] The product identification and initial dose rate setting phase 230 can typically be configured to use the aforementioned inputs, such as relevant fiber, enzyme, and system data points, to identify the optimal enzyme blend and initial dose rate for the selected product application.

[0048] The next stage 240 and related sub-steps collectively refer to the application of the selected enzyme to the process, with a newly specified dosage rate 250 and a product blend 260. Feedback from measured physical conditions of the process, such as measured retention time or system flow rate 251, measured pH 252, measured temperature 253, or the like. Additional data affecting the product blend may further include new fiber surface substrate characterization data 261, new fiber quality analysis data 262, and enzyme characterization data 263.

[0049] The newly specified product and associated continuous dose rate 270, along with any other information that can be determined as relevant by the metering add controller, can be provided to the onsite blending and pumping controller and associated equipment 280. In embodiments as previously noted herein, metering add control stage 106 (or corresponding metering add control stages 106a, 106b for different enzymes) can be integrated with production stage 110, for example, in the case of a metering add skid with appropriate enzyme pumping equipment. In other embodiments, metering add control stage 106 (or corresponding metering add control stages 106a, 106b for different enzymes) can be a discrete product or component of the entire system and is configured to transmit relevant information for downstream implementation (i.e., enzyme formulation and pumping) via a communication network (e.g., wirelessly or via integrated signals).

[0050] Feedback data including system performance data 290 may relate to the bleaching and / or physical quality of the finished product (e.g., sheet material), including, for example, strength data, porosity, caliper readings, wrinkle count, softness, degrees of freedom, drainage, and the like, preferably obtained in real time or a reasonable approximation thereof. Such feedback can be provided to the metering controller to determine whether optimal metering has been achieved, and subsequently, steps 240 to 280 can be repeated as needed to dynamically adjust the selection and / or balance of enzyme raw materials present over time. System performance data may be obtained by offline or online methods and may be directly accessible from existing process data repositories (e.g., distributed control systems (DCS)).

[0051] Throughout the specification and claims, the following terms take on the meaning explicitly associated herein, unless the context otherwise requires. The meanings defined below are not necessarily limiting of the terms, but merely illustrative examples. The meanings of “a,” “an,” and “the” can include plural references, and the meaning of “in” can include both “in” and “on”. The phrase “in one embodiment” as used herein does not necessarily refer to the same embodiment, although it may. As used herein, the phrase “one or more” when used with a list of items means that different combinations of one or more items may be used, and that only one of each item in the list may be required. For example, “one or more” in items A, B, and C can include, for example, but not limited to, item A, or items A and B. This example may also include items A, B, and C, or items B and C.

[0052] The various illustrative logic blocks, modules, and algorithmic steps described in conjunction with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, various illustrative components, blocks, modules, and steps have been described above in general terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and design constraints imposed on the entire system. The described functionality can be implemented in different ways for each specific application, but such implementation decisions should not be construed as causing a departure from the scope of the disclosure.

[0053] The various illustrative logic blocks and modules associated with the embodiments disclosed herein may be implemented or executed by a machine designed to perform the functions described herein, such as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. The general-purpose processor may be a microprocessor, but alternatively, it may be a controller, a microcontroller, or a state machine, a combination thereof, or the like. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, a combination of one or more microprocessors and a DSP core, or any other such configuration.

[0054] The steps of the methods, processes, or algorithms related to the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or a combination of both. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable medium known in the art. An exemplary computer-readable medium may be coupled to a processor, enabling the processor to read information from and write information to the memory / storage medium. Alternatively, the medium may be integrated into the processor. The processor and medium may reside in an ASIC. The ASIC may reside in a user terminal. Alternatively, the processor and medium may reside as discrete components in the user terminal.

[0055] The conditional language used herein, particularly words such as “can,” “might,” “may,” “e.g.,” and the like, unless otherwise specifically stated or otherwise understood in the context in which they are used, is generally intended to convey that certain embodiments include certain features, elements, and / or states that are not included in other embodiments. Therefore, such conditional language is not generally intended to imply that one or more embodiments require features, elements, and / or states in any way, or that one or more embodiments must include logic for determining (with or without author input or prompting) whether such features, elements, and / or states are included or to be performed in any particular embodiment.

[0056] The foregoing detailed description has been provided for purposes of illustration and description. Therefore, although specific embodiments of the new and useful invention have been described, such designations are not intended to be construed as limiting the scope of the invention, except as set forth in the following claims.

Claims

1. A method for automatically providing real-time metering correction for an industrial process, wherein one or more enzyme compositions are applied to natural fibers used in the production of pulp or paper products, the method comprising: For each of a plurality of pulps or paper products, a predictive machine learning model is developed by observing the correlation over time between various combinations of results and process inputs, the results being correlated with fiber surface substrate characterization and fiber quality characterization for the respective pulp or paper product, the various combinations of process inputs including the characteristics of the respective enzyme blends; For a specific pulp or paper product to be produced, an associated model is used to select the initial enzyme blend to be applied, and the corresponding dosage rate for one or more of its components, based at least in part on input data, which includes the expected fiber surface substrate characterization and the expected fiber quality characterization for the pulp or paper product. After applying the initial enzyme blend and the corresponding dosage rate for one or more of its components, real-time feedback data is provided, including measurements corresponding to the characterization of the actual fiber surface substrate and the actual fiber quality. Based at least in part on feedback data, the alternative enzyme blends are dynamically selected, along with the corresponding dose rates for one or more of their components; and During the industrial process, a selected alternative enzyme blend is applied in place of at least a portion of the initial enzyme blend.

2. The method of claim 1, wherein the initial enzyme blend to be applied and the corresponding dosage rate are further selected based on expected values ​​for one or more industrial process characteristics, and the real-time feedback data further includes measurements of the one or more industrial process characteristics.

3. The method of claim 2, wherein the real-time feedback data further includes measurements of industrial process characteristics, said industrial process characteristics including one or more of temperature, system flow rate, pH value, conductivity value, ORP value, biocide residue value, and residence time.

4. The method of claim 1, wherein the method further comprises selectively altering a predetermined model based at least in part on provided real-time feedback data.

5. The method of claim 1, further comprising: One or more components of the initial enzyme blend are blended according to a first total dose rate, and One or more components of the initial enzyme blend are applied during the industrial process.

6. The method of claim 5, further comprising: The selected alternative enzyme blend is blended with one or more components according to the total dose rate, and One or more components of the selected alternative enzyme blend are applied to replace one or more components of the initial enzyme blend.

7. The method of claim 1, wherein fiber quality characterization is determined relative to one or more of fiber length, width, fibrillation, cell wall thickness, fineness density / distribution, fiber kinking, and fiber crimp.

8. The method of claim 1, wherein the real-time feedback data further comprises system performance data regarding one or more of the following: fiber strength, porosity, calipers, softness, wrinkle count, degrees of freedom, and drainage of the pulp or paper product.

9. The method of claim 1, wherein the selected initial enzyme blend and the dynamically selected alternative enzyme blend to be applied, along with their respective dosage rates, are provided to the pulp bleaching process controller.

10. The method of claim 1, wherein the selected initial enzyme blend and the dynamically selected alternative enzyme blend to be applied, along with their respective dosage rates, are provided to the papermaking controller.

11. A system for automatically providing real-time metering correction in an industrial process, wherein one or more components of an enzyme blend are applied to natural fibers used in the production of pulp or paper products, the system comprising: One or more online sensors are configured to generate output signals representing measured actual values ​​for fiber surface substrate characterization and fiber quality characterization; Multiple containers, each configured to store and selectively deliver the corresponding raw material corresponding to the selected enzyme blend component; and One or more computing devices, functionally linked to the one or more online sensors and multiple containers, and configured to: For each of a plurality of pulps or paper products, a predictive machine learning model is developed by observing the correlation over time between various combinations of results and process inputs, the results being correlated with fiber surface substrate characterization and fiber quality characterization for the respective pulp or paper product, the various combinations of process inputs including the characteristics of the respective enzyme blends; For a specific pulp or paper product to be produced, an associated model is used to select the initial enzyme blend to be applied, and the corresponding dosage rate for one or more of its components, based at least in part on input data, which includes the expected fiber surface substrate characterization for the pulp or paper product being produced and the expected fiber quality characterization for the pulp or paper product. After applying the initial enzyme blend and the corresponding dose rate for one or more of its components, real-time feedback data is provided, including measurements corresponding to the characterization of the actual fiber surface substrate and the characterization of the actual fiber quality. Based at least in part on feedback data, the alternative enzyme blends are dynamically selected, along with the corresponding dose rates for one or more of their components; and During the industrial process, a selected alternative enzyme blend is applied in place of at least a portion of the initial enzyme blend.

12. The system of claim 11, wherein the initial enzyme blend and the corresponding dosage rate for one or more of its components are further selected based on expected values ​​for one or more industrial process characteristics, and the real-time feedback data further includes measurements of the one or more industrial process characteristics.

13. The system of claim 12, wherein the real-time feedback data further comprises measurements by one or more online sensors corresponding to industrial process characteristics, said industrial process characteristics including one or more of temperature, system flow rate, conductivity, ORP, biocide residue, pH, and residence time.

14. The system of claim 13, wherein the residual value of the biocide is a free halogen value.

15. The system of claim 11, wherein the computing device is further configured to selectively change the model based at least in part on the provided real-time feedback data.

16. The system of claim 11, wherein one or more computing devices are configured to: One or more components of the initial enzyme blend are blended according to a first total dose rate, and The initial enzyme blend is applied during the industrial process.

17. The system of claim 16, wherein one or more computing devices are further configured to: The selected alternative enzyme blend is blended with one or more components according to the total dose rate, and The original enzyme blend is replaced with a blend of alternative enzymes.

18. The system of claim 11, wherein fiber quality characterization is determined relative to one or more of fiber length, width, fibrillation, cell wall thickness, fineness density / distribution, fiber kinking, and fiber crimp.

19. The system of claim 11, wherein the real-time feedback data further comprises system performance data regarding one or more of the following: fiber strength, porosity, calipers, softness, wrinkle count, degrees of freedom, and drainage of the pulp or paper product.

20. The system of claim 11, comprising a pulp bleaching process controller configured to receive and apply an initial set of selected one or more enzymes and a dynamically selected alternative set of one or more enzymes, and their respective dosage rates.

21. The system of claim 11, comprising a papermaking controller configured to receive and apply an initial set of selected one or more enzymes and a dynamically selected alternative set of one or more enzymes, and their respective dose rates.

Images