Generate control settings for a chemical reactor

Abstract

Techniques are provided for autonomously controlling one or more chemical reactors using generative machine learning models. For example, one or more embodiments described herein may include a system that may include a memory that can store computer-executable components. The system may also include a processor operably coupled to the memory and that can execute the computer-executable components stored in the memory. The computer-executable components may include a model component that can build a generative machine learning model based on training data regarding past chemical reactor operations. The generative machine learning model can generate recommended chemical reactor control settings for experimental discoveries for polymers.

Description

Technical Field

[0001] The present invention relates to generating one or more control settings for one or more chemical reactors, and more particularly to using one or more generative machine learning models to generate one or more recommended chemical reactor control settings and / or autonomously control one or more chemical reactors. Background Art

[0002] The present invention relates to generating one or more control settings for one or more chemical reactors, and more particularly to using one or more generative machine learning models to generate one or more recommended chemical reactor control settings and / or autonomously control one or more chemical reactors. Summary of the Invention

[0003] The following presents a summary of the invention to provide a basic understanding of one or more embodiments of the present invention. The summary of the invention is not intended to identify key or important elements, or to delineate any scope of particular embodiments or any scope of the claims. Its sole purpose is to present concepts in a simplified form as a prelude to the more detailed description that is presented later. In one or more embodiments described herein, systems, computer-implemented methods, devices, and / or computer program products are described that can facilitate using one or more generative machine learning models to generate one or more recommended chemical reactor control settings.

[0004] According to an embodiment of the present invention, a system is provided. The system can include a memory that can store computer-executable components. The system can also include a processor operatively coupled to the memory and can execute the computer-executable components stored in the memory. The computer-executable components can include a model component that can build a generative machine learning model based on training data regarding past chemical reactor operations. The generative machine learning model can generate recommended chemical reactor control settings for experimental findings for polymers.

[0005] According to one embodiment, a computer-implemented method is provided. The computer-implemented method can include: generating, by a system operatively coupled to a processor, a generative machine learning model based on training data regarding past chemical reactor operations. The generative machine learning model can generate recommended chemical reactor control settings for experimental findings for polymers.

[0006] According to an embodiment of the present invention, a computer program product for controlling a chemical reactor is provided. The computer program product may include a computer-readable storage medium having program instructions embodied therewith. The program instructions may be executable by a processor to cause the processor to: generate a generative machine learning model by a system operably coupled to the processor based on training data regarding past chemical reactor operations. The generative machine learning model may generate recommended chemical reactor control settings for experimental discoveries of polymers. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 is a block diagram of an example system according to an embodiment of the present invention that may collect operation data regarding one or more past chemical reactor operations.

[0008] Figure 2 is a block diagram of an exemplary system according to an embodiment of the present invention that may construct one or more generative machine learning models to determine one or more recommended chemical reactor settings for experimental discoveries of one or more polymers.

[0009] Figure 3 is a diagram of an exemplary variational autoencoder model according to an embodiment of the present invention that may be generated by one or more systems to determine one or more recommended chemical reactor settings for experimental discoveries of one or more polymers.

[0010] Figure 4 is a diagram of an exemplary generative adversarial network model according to an embodiment of the present invention that may be generated by one or more systems to determine one or more recommended chemical reactor settings for experimental discoveries of one or more polymers.

[0011] Figure 5 is a block diagram of an example system according to an embodiment of the present invention that may operate one or more chemical reactors based on one or more recommended chemical reactor settings.

[0012] Figure 6 is a block diagram of an exemplary system according to an embodiment of the present invention that is capable of measuring and / or detecting one or more characteristics of one or more polymers synthesized by one or more chemical reactors as indicated by one or more recommended chemical reactor control settings generated by a generative machine learning model.

[0013] Figure 7 is a block diagram of an exemplary system according to an embodiment of the present invention that may update one or more training data sets based on one or more polymers synthesized by recommended chemical reactor control settings.

[0014] Figure 8is a block diagram of an exemplary system according to an embodiment of the present invention, which may use one or more variational autoencoders machine learning to facilitate the operation of one or more chemical reactors for experimental discovery of one or more polymers.

[0015] Figure 9 is a block diagram of an example system according to an embodiment of the present invention, which may use one or more generative adversarial network machine learning models to facilitate the operation of one or more chemical reactors for experimental discovery of one or more polymers.

[0016] Figure 10 is a flowchart of an exemplary method according to an embodiment of the present invention, which may use one or more generative machine learning models to facilitate the operation of one or more chemical reactors for experimental discovery of one or more polymers.

[0017] Figure 11 is a flowchart of an exemplary method according to an embodiment of the present invention, which may use one or more generative machine learning models to facilitate the operation of one or more chemical reactors for experimental discovery of one or more polymers.

[0018] Figure 12 depicts a cloud computing environment according to an embodiment of the present invention.

[0019] Figure 13 depicts an abstract model layer according to an embodiment of the present invention.

[0020] Figure 14 is a block diagram of an example operating environment in which one or more embodiments of the present invention described herein may be facilitated. Detailed Description

[0021] The following detailed description is merely illustrative and is not intended to limit the embodiments and / or the application or use of the embodiments. Further, there is no intention to be bound by any express or implied information presented in the foregoing background or summary sections or in the detailed description section.

[0022] One or more embodiments are now described with reference to the accompanying drawings, in which like reference numerals are used throughout to refer to like elements. In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a more thorough understanding of the embodiments. However, it is apparent that the embodiments may be practiced without these specific details in different instances.

[0023] For many life science applications, it is necessary to explore a particular class of polymeric materials in order to determine optimal structure-activity or system-activity relationships. Manual synthesis of such members can be laborious and / or may rely solely on the judgment of a list of human experiments. Conventional experimental techniques first predict the chemical structure of one or more polymers hypothesized to exhibit the desired characteristics, then derive a proposed synthesis scheme for generating the predicted chemical structure, and finally determine one or more reactor control settings to facilitate implementation of the proposed synthesis scheme.

[0024] Various embodiments of the present invention can relate to computer processing systems, computer-implemented methods, apparatuses, and / or computer program products that facilitate efficient, effective, and autonomous (e.g., without direct human guidance) control of one or more chemical reactors by using one or more generative machine learning models. The generative machine learning models can generate one or more recommended chemical reactor control settings to discover and / or synthesize one or more polymers based on past chemical reactor operations. The generative machine learning models can include, for example, variational autoencoder (“VAE”) models and / or generative adversarial network (“GAN”) models. Additionally, one or more embodiments can contemplate autonomously controlling one or more chemical reactors according to the recommended chemical reactor control settings.

[0025] These computer processing systems, computer-implemented methods, devices, and / or computer program products employ hardware and / or software to solve problems that are inherently highly technical (e.g., experimental discovery of one or more polymers), not abstract, and not capable of being performed as a set of mental acts by a human. For example, an individual or multiple individuals cannot easily analyze large amounts of chemical reactor data with the efficiency of the various embodiments described herein. For example, one or more of the embodiments described herein can include one or more repeated training processes that can analyze numerous past operations of multiple chemical reactors to generate new chemical reactor control settings for the autonomous discovery of one or more polymers.

[0026] Figure 1 A system 100 is shown that can facilitate the autonomous discovery and / or synthesis of one or more polymeric materials based on one or more target polymer characteristics. Aspects of the systems (e.g., system 100, etc.), apparatuses, or processes in various embodiments of the present invention can constitute one or more machine-executable components embodied in one or more machines (e.g., embodied in one or more computer-readable media (or media) associated with one or more machines). Such components, when executed by a machine (e.g., a computer, a computing device, a virtual machine, etc.), can cause the machine to perform the described operations.

[0027] As Figure 1As shown, system 100 may include one or more servers 102, one or more networks 104, one or more input devices 106, and / or one or more chemical reactors 108. Server 102 may include a control component 110. The control component 110 may also include a communication component 112 and / or a data collection component 114. Similarly, server 102 may include at least one memory 116 or be otherwise associated therewith. Server 102 may also include a system bus 118 that may be coupled to different components such as, but not limited to, the control component 110 and / or associated components, the memory 116, and / or the processor 120. Although server 102 is shown in Figure 1 the figures, in other embodiments, multiple devices of different types may be associated with or include Figure 1 the features shown in Figure 1 the figures. Further, server 102 may communicate with one or more cloud computing environments.

[0028] Network 104 may include wired and wireless networks, including but not limited to cellular networks, wide area networks (WANs) (e.g., the Internet), or local area networks (LANs). For example, server 102 may communicate with input device 106 and / or chemical reactor 108 using almost any desired wired or wireless technology (and vice versa), the wired or wireless technologies including, for example but not limited to: cellular, WAN, Wi-Fi, Wi-Max, WLAN, Bluetooth technology, combinations thereof, etc. Further, although in the illustrated embodiment, control component 110 may be provided on server 102, it should be understood that the architecture of system 100 is not limited thereto. For example, control component 110 or one or more components of control component 110 may be located at another computing device such as another server device, a client device, etc.

[0029] The input device 106 may include one or more computerized devices, which may include but are not limited to: personal computers, desktop computers, laptop computers, cellular phones (e.g., smart phones), computerized tablet computers (e.g., including a processor), smart watches, keyboards, touchscreens, mice, combinations thereof, and / or the like. A user of the system 100 may utilize the input device 106 to input data into the system 100, thereby sharing the data (e.g., via a direct connection and / or via the network 104) with the server 102 and / or the chemical reactor 108. For example, the input device 106 may send data to the communication component 112 (e.g., via a direct connection and / or via the network 104). Additionally, the input device 106 may include one or more displays, which may present one or more outputs generated by the system 100 to the user. For example, these displays may include but are not limited to: cathode ray tube displays ("CRT"), light emitting diode displays ("LED"), electroluminescent displays ("ELD"), plasma display panels ("PDP"), liquid crystal displays ("LCD"), organic light emitting diode displays ("OLED"), combinations thereof, and / or the like.

[0030] The chemical reactor 108 may include one or more synthesis platforms such as flow reactors and / or batch reactors. For example, the chemical reactor 108 may facilitate chemical flow, where one or more chemical reactions may occur in a continuous flow stream of chemical reactants (e.g., using one or more pumps to push the chemical fluid through one or more tubes). In another example, the chemical reactor 108 may facilitate batch chemistry. Exemplary chemical reactors 108 may include but are not limited to: tubular reactors, fixed bed reactors, fluidized bed reactors, continuously stirred tank reactors, combinations thereof, etc.

[0031] The data collection component 114 can collect training data from the input device 106 and / or the chemical reactor 108 (e.g., via a direct electrical connection and / or the network 104). The training data can be about one or more previous operations of the chemical reactor 108. For example, the training data can include, but is not limited to, the following control settings implemented during one or more chemical reactions previously performed by the chemical reactor 108: chemical reactants, monomers, catalysts, cocatalysts, reactor parameter values, initiators, residence times, temperatures, flow rates, pressures, order of component addition / mixing, exposure to ultraviolet light and / or other radiation, combinations thereof, and the like. For example, the chemical reactor 108 can send one or more control settings to the data collection component 114 via the network 104 and / or the communication component 112. Additionally, a user of the system 100 can use the input device 106 to input control settings (e.g., regarding past operations of the chemical reactor 108) into the system 100 and / or send them to the data collection component 114 via the network 104 and / or the communication component 112.

[0032] The data collection component 114 can use the training data collected from the input device 106 and / or the chemical reactor 108 to generate and / or populate one or more training data sets 122. For example, the data collection component 114 can use the control settings of the chemical reactor 108 to generate and / or populate the training data set 122. As Figure 1 shown, the training data set 122 can be included within the memory 116. The training data set 122 can be included within one or more cloud computing environments.

[0033] Figure 2 A system 100 is shown that further includes a model component 202. The model component 202 can build one or more generative machine learning models based on the training data, where the models can generate one or more recommended chemical reactor 108 control settings. For example, the model component 202 can generate one or more VAE models and / or GAN models based on the training data.

[0034] The recommended control settings for the chemical reactor 108 can include one or more control settings for synthesizing one or more polymers by the chemical reactor 108. Additionally, the recommended control settings for the chemical reactor 108 can include one or more control settings and / or combinations of control settings that are not included in the training data. In other words, the recommended chemical reactor 108 control settings can include one or more control settings and / or combinations of control settings that have not been implemented on the chemical reactor 108 based on the knowledge of the system 100.

[0035] Figure 3Illustrates the VAE training process 300 that can be performed by the model component 202 when constructing one or more VAE models. As Figure 3 shown, the VAE model may include one or more encoders 302, a latent space 304, and / or a decoder 306. The encoder 302 may include one or more first neural networks that can encode training data included in the training dataset 122 into one or more latent variables included within the latent space 304. Further, the encoder 302 may normalize the latent variables. The latent space 304 may be stochastic, and / or the encoder 302 may encode to a Gaussian probability density. The decoder 306 may include one or more second neural networks that can decode the latent variables from the latent space 304 to output one or more vectors.

[0036] In addition, the model component 202 may utilize one or more loss functions to analyze the amount of information loss experienced by the training data as it goes through dimensions from small to large. The model component 202 may use a gradient descent algorithm to train the VAE model to optimize the loss function with respect to one or more parameters (e.g., weights, biases, and / or step sizes) of the encoder 302 and / or the decoder 306. During one or more VAE training processes 300, the model component 202 may repeatedly train the VAE model until the output vectors match the training data.

[0037] Figure 4 Illustrates the GAN training process 400 that can be performed by the model component 202 when constructing one or more GAN models. As Figure 4 shown, the GAN model may include one or more generator networks 402 and / or discriminator networks 404.

[0038] The generator network 402 may upsample one or more noise vectors to generate new data, such as new control settings. The discriminator network 404 may receive the new data generated by the generator network 402 and the training data from the training dataset 122 as inputs. Further, the discriminator network 404 may receive the inputs without knowing the input source. Thus, the discriminator network 404 may analyze the inputs without prior knowledge of whether the subject input is new data or training data. Further, the discriminator network 404 may analyze the inputs to determine whether the input is new data generated by the generator network 402 (e.g., new chemical reactor 108 control settings) or training data from the training dataset 122 (e.g., past control settings implemented by one or more chemical reactors 108). For example, the discriminator network 404 may be a binomial classifier.

[0039] The GAN training process 400 may include an iterative exchange between a generator network 402 and a discriminator network 404. With each exchange, the generator network 402 may generate new data, and the discriminator network 404 may attempt to discern whether the new data was generated by the generator network 402 or sampled from the training data set 122. Further, the generator network 402 and / or the discriminator network 404 may learn from previous exchanges to further enhance and / or refine their respective functions (e.g., enhance the ability of the generator network 402 to generate new data that is reasonably considered training data, and / or enhance the ability of the discriminator network 404 to discriminate between new data and training data). When the discriminator network 404 is unable to distinguish between the new data generated by the generator network 402 and the training data, the generator network 402 may achieve a state of training.

[0040] The model component 202 may generate a generative machine learning model (e.g., a VAE model and / or a GAN model), train a generative machine learning model (e.g., via one or more VAE training processes 300 and / or GAN training processes 400), and / or generate one or more recommended chemical reactor 108 settings from the trained generative machine learning model. For example, one or more trained VAE models may sample and / or decode one or more latent variables from the latent space 304 to generate recommended chemical reactor 108 control settings. In another example, one or more trained GAN models may generate one or more recommended chemical reactor 108 control settings from one or more trained generator networks 402.

[0041] Figure 5 System 100 is shown, which further includes a reactor control component 502. The reactor control component 502 may operate the chemical reactor 108 according to the recommended chemical reactor 108 control settings generated by the model component 202. Although Figure 5 The reactor control component 502 included within the server 102 is depicted, but the architecture of system 100 is not limited thereto. For example, the reactor control component 502 may be included within the chemical reactor 108, the input device 106, and / or a cloud computing environment (e.g., accessible via the network 104).

[0042] The reactor control component 502 can set and / or change one or more control settings of the chemical reactor 108 based on the recommended chemical reactor 108 control settings. Additionally, the reactor control component 502 can start, abort, resume, and / or stop the operation of the chemical reactor 108. In the case where the system 100 includes multiple chemical reactors 108, the reactor control component 502 can further determine which chemical reactor 108 to implement the recommended chemical reactor 108 control settings based on one or more reactor characteristics of the chemical reactor 108. Exemplary reactor characteristics can include, but are not limited to: the operating state of the chemical reactor 108, compounds readily accessible to the chemical reactor 108 (e.g., reagents, catalysts, and / or initiators), the type of chemical reactor 108 included within the system 100, one or more user preferences (e.g., input into the system 100 via the input device 106), combinations thereof, and the like.

[0043] The reactor control component 502 can autonomously implement the recommended chemical reactor 108 control settings. Accordingly, the production time for discovering and / or synthesizing one or more polymers can be reduced and / or minimized by the autonomous nature of the system 100.

[0044] Figure 6 Shown is a system 100 that further includes one or more measurement components 602 and / or verification components 604. The measurement component 602 can measure and / or detect one or more characteristics of the polymers synthesized by the chemical reactor 108.

[0045] For example, the chemical reactor 108 can include one or more measurement components 602, which can measure and / or detect one or more characteristics of the polymer materials produced by the chemical reactor 108 operating according to the recommended chemical reactor 108 control settings (e.g., via the reactor control component 502). Each chemical reactor 108 can include one or more measurement components 602. Exemplary characteristics that can be measured and / or detected by the measurement component 602 can include, but are not limited to: the molecular weight, chemical properties, chemical activity, molecular weight, PDI, ultraviolet-visible spectrum, retention time, temperature, combinations thereof, and the like. Exemplary sensors that can be included within and / or controlled by the measurement component 602 can include, but are not limited to: timers, thermometers, calorimeters, spectroscopic devices, devices for mechanical testing, biochemical assays, combinations thereof, and the like.

[0046] A user of system 100 may define one or more target polymer properties via input device 106 and / or network 104. Additionally, the target polymer properties may define one or more properties that a user desires the synthesized polymer to exhibit. The target polymer properties may define a range of values for one or more parameters related to the physical and / or chemical properties of the synthesized polymer.

[0047] Verification component 604 may analyze one or more properties measured and / or detected by measurement component 602 to determine whether the synthesized polymer material exhibits the target polymer properties. Additionally, verification component 604 may share with one or more users of system 100 recommended chemical reactor 108 control settings, properties obtained from measurement component 602, and / or determinations generated by verification component 604 via input device 106 and / or network 104.

[0048] Figure 7 System 100 is shown to further include one or more update components 702. Update component 702 may further populate and / or update the training data included within training data set 122 based on the recommended chemical reactor 108 control settings and / or determinations made by verification component 604. For example, update component 702 may update training data set 122 with the recommended chemical reactor 108 control settings based on polymers synthesized with the recommended chemical reactor 108 control settings that exhibit the target polymer properties (e.g., as measured by measurement component 602 and / or determined by verification component 604).

[0049] Thus, as chemical reactor 108 synthesizes more and more polymers (e.g., according to the recommended chemical reactor 108 control settings), more and more training data may be made available to model component 202. System 100 may autonomously: grow the amount of training data included within training data set 122, increase the accuracy of the recommended chemical reactor 108 control settings, and / or operate chemical reactor 108 to synthesize new polymers.

[0050] Figure 8 An operational procedure 800 that may be performed by system 100 is shown. For example, operational procedure 800 may include using one or more trained VAE machine learning models to facilitate autonomous control of one or more chemical reactors 108. The trained VAE models depicted in Figure 3 may be trained using the training data included within training data set 122 (e.g., as depicted in Figure 8 via one or more VAE training processes 300.

[0051] As in Figure 8As shown, the model component 202 may sample and / or decode one or more latent variables included within the latent space 304 of the trained VAE model to generate one or more recommended chemical reactor 108 control settings. Additionally, the reactor control component 502 may operate the chemical reactor 108 in accordance with the recommended chemical reactor 108 control settings (e.g., as described herein). Further, one or more measurement components 602 (e.g., included within the chemical reactor 108) may measure and / or detect one or more properties of one or more polymers synthesized by the chemical reactor 108 operated in accordance with the chemical reactor 108 control settings. For example, the measurement component 602 may measure and / or detect the synthesized polymer with respect to one or more parameters of physical activity, chemical activity, and / or chemical reactor 108 operation. Moreover, the verification component 604 may share the measured and / or detected polymer properties and / or associated recommended chemical reactor 108 control settings with one or more users of the system 100 via an input device.

[0052] The verification component 604 may further analyze the properties measured and / or detected by the measurement component 602 to determine whether the properties are target polymer properties. For example, the target polymer properties may be set by a user of the system 100 via the input device 106 and / or may define one or more desired properties (e.g., with respect to the chemical and / or physical activity of the synthesized polymer). The verification component 604 may also update the training data set 122 with the recommended chemical reactor 108 control settings in response to determining that the synthesized polymer exhibits one or more target polymer properties. Thus, the recommended chemical reactor 108 control settings found to achieve polymers with target properties may be used to further train a generative machine learning model (e.g., a VAE model) for generating subsequent recommended chemical reactor 108 control settings.

[0053] Figure 9 An operational procedure 900 that may be performed by the system 100 is shown. For example, the operational procedure 900 may include using one or more trained GAN machine learning models to facilitate autonomous control of one or more chemical reactors 108. The trained GAN models may be trained using training data included within the training data set 122 (e.g., as depicted Figure 4 as) via one or more GAN training processes 400 Figure 9 as depicted.

[0054] As Figure 9As shown, the model component 202 can generate one or more recommended chemical reactor 108 control settings via one or more trained generator networks 402. Additionally, the reactor control component 502 can operate the chemical reactor 108 according to the recommended chemical reactor 108 control settings (e.g., as described herein). Further, one or more measurement components 602 (e.g., included within the chemical reactor 108) can measure and / or detect one or more properties of one or more polymers synthesized by the chemical reactor 108 operating according to the chemical reactor 108 control settings. For example, the measurement component 602 can measure and / or detect the synthesized polymers with respect to one or more parameters of physical activity, chemical activity, and / or chemical reactor 108 operation. Moreover, the verification component 604 can share the measured and / or detected polymer properties and / or associated recommended chemical reactor 108 control settings with a user of the system 100 via an input device.

[0055] The verification component 604 can further analyze the properties measured and / or detected by the measurement component 602 to determine whether the properties are target polymer properties. For example, the target polymer properties can be set by a user of the system 100 via the input device 106 and / or can define one or more desired properties (e.g., with respect to the chemical and / or physical activity of the synthesized polymer). The verification component 604 can also update the training data set 122 with the recommended chemical reactor 108 control settings in response to determining that the synthesized polymer exhibits one or more target polymer properties. Thus, the recommended chemical reactor 108 control settings found to achieve polymers with target properties can be used to further train a generative machine learning model (e.g., a GAN model) for generating subsequent recommended chemical reactor 108 control settings. For example, the updated training data (e.g., containing the recommended chemical reactor 108 control settings) can be analyzed by the discriminator network 404 to further train the discriminator network 404 and, thereby, train the generator network 402.

[0056] Figure 10 A method 1000 is shown that can use one or more generative machine learning models to facilitate controlling one or more chemical reactors 108.

[0057] At 1002, method 1000 may include collecting, by system 100 (e.g., via data collection component 114), training data regarding the operation of one or more past chemical reactors 108 operatively coupled to processor 120. For example, the training data may include, but is not limited to, the following control settings implemented during one or more chemical reactions previously performed by chemical reactor 108: chemical reactants, monomers, catalysts, cocatalysts, reactor parameter values, initiators, residence times, temperatures, flow rates, pressures, order of component addition / mixing, exposure to ultraviolet light and / or other radiation, combinations thereof, and / or the like. The collection at 1002 may include generating and / or populating one or more training data sets 122 using the training data (e.g., as described herein).

[0058] At 1004, method 1000 may include training, by system 100 (e.g., via model component 202), one or more VAE machine models based on the training data using one or more gradient descent algorithms, where the one or more gradient descent algorithms may optimize a loss function with respect to one or more parameters of one or more encoders 302 and / or decoders 306. For example, the training at 1004 may be performed according to different features described herein regarding the VAE training process 300.

[0059] At 1006, method 1000 may include generating, by system 100 (e.g., via model component 202), one or more recommended chemical reactor 108 control settings for experimental discovery of one or more polymers. For example, the recommended chemical reactor 108 control settings may be generated by sampling and / or decoding one or more latent variables from the latent space 304 included within the VAE machine learning model (e.g., as described herein). Further, the generation at 1006 may be facilitated by one or more VAE machine learning models that have achieved a trained state through the training at 1004.

[0060] At 1008, method 1000 may include operating, by system 100 (e.g., via reactor control component 502), one or more chemical reactors 108 according to the recommended chemical reactor 108 control settings. Exemplary chemical reactors 108 that may be operated according to the recommended chemical reactor 108 control settings may include, but are not limited to: tubular reactors, fixed bed reactors, fluidized bed reactors, continuously stirred tank reactors, combinations thereof, and / or the like. Operating chemical reactor 108 at 1008 may be performed autonomously by system 100.

[0061] At 1010, method 1000 may include the system 100 determining (e.g., via measurement component 602) one or more characteristics of the polymer produced by chemical reactor 108. For example, chemical reactor 108 may include one or more sensors to measure and / or detect one or more physical and / or chemical characteristics of the synthesized polymer. Example sensors may include, but are not limited to: timers, thermometers, calorimeters, spectroscopic devices, devices for mechanical testing, biochemical assays, combinations thereof, and / or the like.

[0062] At 1012, method 1000 may include the system 100 determining (e.g., via verification component 604) whether the characteristics are within an allowable range defined by target polymer characteristics. For example, the determination at 1012 may include analyzing the measurements and / or detections generated at 1010 to determine whether the characteristics of the synthesized polymer are consistent with the target polymer characteristics.

[0063] At 1014, method 1000 may include the system 100 updating (e.g., via update component 702) training data based on recommended chemical reactor 108 control settings. Further, the update at 1014 may include updating one or more training data sets 122 based on the measurements and / or detections generated at 1010. The update at 1014 may facilitate one or more iterations of the training conducted at 1004.

[0064] Figure 11 A flowchart of an example non - limiting method 1100 is shown that may use one or more generative machine - learning models to facilitate controlling one or more chemical reactors 108.

[0065] At 1102, method 1100 may include the system 100 collecting (e.g., via data collection component 114) training data regarding one or more past chemical reactor 108 operations. For example, the training data may include, but is not limited to, the following control settings implemented during one or more chemical reactions previously performed by chemical reactor 108: reactants, monomers, catalysts, cocatalysts, reactor parameter values, initiators, residence times, temperatures, flow rates, pressures, order of component addition / mixing, exposure to ultraviolet light and / or other radiation, combinations thereof, and / or the like. The collection at 1002 may include generating and / or populating one or more training data sets 122 with the training data (e.g., as described herein).

[0066] At 1104, method 1100 may include training (e.g., via model component 202) one or more GAN machine models based on training data by the system 100 by upsampling a noise vector to generate new data and / or analyzing the training data and the new data to discern a classification difference between the training data and the new data. For example, the training at 1104 may be performed according to different features described herein regarding the GAN training process 400.

[0067] At 1106, method 1000 may include generating (e.g., via model component 202) by the system 100 one or more recommended chemical reactor 108 control settings for experimental discovery of one or more polymers by the GAN machine learning model. For example, the recommended chemical reactor 108 control settings may be generated by one or more trained generator networks 402 included within the GAN machine learning model. Further, the generation at 1106 may be facilitated by one or more GAN machine learning models that have achieved a trained state, where the generator network 402 may generate new data that cannot be easily discerned by the discriminator network 404 from the training data.

[0068] At 1108, method 1100 may include operating (e.g., via reactor control component 502) one or more chemical reactors 108 by the system 100 according to the recommended chemical reactor 108 control settings. Exemplary chemical reactors 108 that may be operated according to the recommended chemical reactor 108 control settings may include, but are not limited to: tubular reactors, fixed bed reactors, fluidized bed reactors, continuous stirred tank reactors, combinations thereof, and / or the like. Operating the chemical reactor 108 at 1108 may be performed autonomously by the system 100.

[0069] At 1110, method 1100 may include determining (e.g., via measurement component 602) by the system 100 one or more properties of the polymer produced by the chemical reactor 108. For example, the chemical reactor 108 may include one or more sensors to measure and / or detect one or more physical and / or chemical properties of the synthesized polymer. Example sensors may include, but are not limited to: timers, thermometers, calorimeters, spectroscopic devices, devices for mechanical testing, biochemical assays, combinations thereof, and / or the like.

[0070] At 1112, method 1100 may include determining (e.g., via verification component 604) by the system 100 whether the property is within an allowable range defined by the target polymer property. For example, the determination at 1112 may include analyzing the measurements and / or detections made at 1110 to determine whether the properties of the synthesized polymer are consistent with the target polymer properties.

[0071] In 1114, method 1100 may include updating (e.g., via update component 702) training data by system 100 based on the recommended chemical reactor 108 control settings. Further, the update at 1114 may include updating one or more training data sets 122 based on the measurements and / or detections generated at 1110. The update at 1114 may facilitate one or more iterations of the training conducted at 1104.

[0072] It should be understood that although this disclosure includes a detailed description of cloud computing, the implementation of the teachings recited herein is not limited to a cloud computing environment. Instead, embodiments of the invention are capable of being implemented in conjunction with any other type of computing environment now known or later developed.

[0073] Cloud computing is a service delivery model for enabling convenient, on-demand network access to a shared pool of configurable computing resources such as networks, network bandwidth, servers, processing, memory, storage, applications, virtual machines, and services that can be rapidly provisioned and released with minimal management effort or service provider interaction. This cloud model may include at least five characteristics, at least three service models, and at least four deployment models.

[0074] The characteristics are as follows:

[0075] On-demand self-service: Cloud consumers can unilaterally and automatically provision computing capabilities such as server time and network storage as needed, without human interaction with the service provider.

[0076] Broad network access: The capabilities are available over a network and accessed through standard mechanisms that facilitate use by heterogeneous thin or thick client platforms (e.g., mobile phones, laptop computers, and PDAs).

[0077] Resource pooling: The provider's computing resources are pooled and served to multiple consumers via a multi-tenant model, where different physical and virtual resources are dynamically allocated and reallocated as needed. In general, consumers do not control or even know the exact location of the provided resources, but can specify the location at a higher level of abstraction (e.g., country, state, or data center), thus having location independence.

[0078] Rapid elasticity: Capable of rapidly and elastically (sometimes automatically) deploying computing capabilities to enable rapid scaling and rapidly releasing to scale down quickly. To the consumer, the available computing capabilities for deployment often appear to be infinite and any amount of computing capabilities can be obtained at any time.

[0079] Measurable Services: The cloud system automatically controls and optimizes resource utilization by leveraging metering capabilities at a certain level of abstraction suitable for service types such as storage, processing, bandwidth, and active user accounts. Resource usage can be monitored, controlled, and reported, providing transparency to both service providers and consumers.

[0080] The service models are as follows:

[0081] Software as a Service (SaaS): The ability provided to consumers is to use applications that the provider runs on the cloud infrastructure. The applications can be accessed from various client devices through a thin client interface such as a web browser (e.g., web-based email). Except for limited user-specific application configuration settings, consumers neither manage nor control the underlying cloud infrastructure, including the network, servers, operating systems, storage, and even individual application capabilities.

[0082] Platform as a Service (PaaS): The ability provided to consumers is to deploy applications created or acquired by the consumers on the cloud infrastructure, where these applications are created using programming languages and tools supported by the provider. Consumers neither manage nor control the underlying cloud infrastructure, including the network, servers, operating systems, or storage, but have control over the deployed applications and possibly over the application hosting environment configuration.

[0083] Infrastructure as a Service (IaaS): The ability provided to consumers is that they can deploy and run any software, including operating systems and applications, on processing, storage, networking, and other basic computing resources. Consumers neither manage nor control the underlying cloud infrastructure, but have control over the operating systems, storage, and the deployed applications, and may have limited control over selected network components (e.g., host firewalls).

[0084] The deployment models are as follows:

[0085] Private Cloud: The cloud infrastructure runs solely for a particular organization. The cloud infrastructure can be managed by the organization or a third party and can exist either inside or outside the organization.

[0086] Community Cloud: The cloud infrastructure is shared by several organizations and supports a specific community with common interests (e.g., mission, security requirements, policies, and compliance considerations). The community cloud can be managed by multiple organizations within the community or a third party and can exist either inside or outside the community.

[0087] Public Cloud: The cloud infrastructure is provided to the public or a large industrial group and is owned by the organization selling the cloud services.

[0088] Hybrid Cloud: The cloud infrastructure consists of two or more clouds (private cloud, community cloud, or public cloud) of deployment models, which remain distinct entities but are bound together by standardized or proprietary technologies that enable data and application portability (such as cloud bursting traffic sharing technology for load balancing between clouds).

[0089] The cloud computing environment is service-oriented, with characteristics focused on statelessness, low coupling, modularity, and semantic interoperability. The core of cloud computing is the infrastructure that includes a network of interconnected nodes.

[0090] Now refer to Figure 12 , which depicts an illustrative cloud computing environment 1200. As shown, the cloud computing environment 1200 includes one or more cloud computing nodes 1202, and local computing devices used by cloud consumers (such as personal digital assistants (PDAs) or cellular phones 1204, desktop computers 1206, laptop computers 1208, and / or in-vehicle computer systems 1210) can communicate with the cloud computing nodes 1202. The nodes 1202 can communicate with each other. They can be physically or virtually grouped (not shown) in one or more networks (such as the private cloud, community cloud, public cloud, or hybrid cloud or a combination thereof described above). This allows the cloud computing environment 1200 to provide infrastructure, platform, and / or software as services such that cloud consumers do not need to maintain resources on local computing devices. It should be understood that Figure 12 the types of computing devices 1204 - 1210 shown in

[0091] Now refer to Figure 13 , which shows a set of functional abstraction layers provided by the cloud computing environment 1200 ( Figure 12 ). It should be understood in advance that Figure 13 the components, layers, and functions shown in

[0092] are only illustrative, and embodiments of the present invention are not limited thereto. As depicted, the following layers and corresponding functions are provided.

[0093] The hardware and software layer 1302 includes hardware and software components. Examples of hardware components include: hosts 1304; servers 1306 based on RISC (Reduced Instruction Set Computer) architecture; servers 1308; blade servers 1310; storage devices 1312; and network and networking components 1314. In some embodiments, the software components include network application server software 1316 and database software 1318.

[0093] The virtualization layer 1320 provides an abstraction layer from which the following examples of virtual entities can be provided: virtual servers 1322; virtual storage 1324; virtual networks 1326, including virtual private networks; virtual applications and operating systems 1328; and virtual clients 1330.

[0094] In one example, the management layer 1332 can provide the functions described below. Resource provisioning 1334 provides the dynamic acquisition of computing resources and other resources used to perform tasks within the cloud computing environment. Metering and pricing 1336 provides cost tracking when resources are utilized within the cloud computing environment and provides accounting or invoicing for the consumption of these resources. In one example, these resources can include application software licenses. Security provides authentication for cloud consumers and tasks, as well as protection for data and other resources. The user portal 1338 provides access to the cloud computing environment for consumers and system administrators. Service level management 1340 provides cloud computing resource allocation and management such that the required service levels are met. Service level agreement (SLA) planning and fulfillment 1342 provides the pre-arrangement and procurement of cloud computing resources in accordance with future requirements of the cloud computing resources as expected by the SLA.

[0095] The workload layer 1344 provides examples of functions that can utilize the capabilities of the cloud computing environment. Examples of workloads and functions that can be provided from this layer include: mapping and navigation 1346; software development and lifecycle management 1348; virtual classroom education delivery 1350; data analysis processing 1352; transaction processing 1354; and deep learning discovery of chemical reactor 108 control settings 1356. Various embodiments of the present invention can utilize the cloud computing environment described with reference to Figure 12 and 13 to generate one or more recommended chemical reactor 108 control settings and / or autonomously operate one or more chemical reactors to facilitate the experimental discovery of polymers.

[0096] The present invention can be a system, method, and / or computer program product at any possible level of integrated technical detail. The computer program product may include a computer-readable storage medium (or media) having computer-readable program instructions thereon for causing a processor to perform aspects of the present invention. A computer-readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium may be, for example but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage medium includes the following: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device such as a punched card or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing: A computer-readable storage medium as used herein should not be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0097] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a corresponding computing / processing device or downloaded to an external computer or external storage device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network). The network may include copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium within the corresponding computing / processing device.

[0098] The computer-readable program instructions for carrying out operations of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state-setting data, configuration data for integrated circuits, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and procedural programming languages such as the "C" programming language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the latter case, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, an electronic circuit, including, for example, a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA), may execute the computer-readable program instructions by utilizing state information of the computer-readable program instructions to personalize the electronic circuit for performing aspects of the present invention.

[0099] Aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0100] These computer-readable program instructions may be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing apparatus to produce a machine, which, when executed by the processor of the computer or other programmable data processing apparatus, creates a means for implementing the functions / acts specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, a programmable data processing device, and / or other devices to function in a particular manner, such that the computer-readable storage medium having instructions stored therein comprises an article of manufacture, the article of manufacture including: instructions for implementing aspects of the functions / acts specified in one or more blocks of the flowchart and / or block diagram.

[0101] The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices that cause a series of operational steps to be performed on the computer, other programmable apparatus, or other devices to produce a computer-implemented process such that the instructions executed on the computer, other programmable apparatus, or other devices implement the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0102] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Accordingly, each box in the flowchart or block diagram may represent a module, segment, or portion of instructions, which includes one or more executable instructions for implementing the specified logical function. In some alternative embodiments, the functions noted in the boxes may occur out of the order noted in the figures. For example, two boxes shown in succession may, in fact, be executed substantially concurrently, or the boxes may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by special-purpose hardware-based systems that perform the specified functions or actions or carry out combinations of special-purpose hardware and computer instructions.

[0103] To provide context for the various aspects of the disclosed subject matter, Figure 14 and the following discussion is intended to provide a general description of the suitable environment in which the various aspects of the disclosed subject matter may be implemented. Referring Figure 14, A suitable operating environment 1400 for implementing various aspects of the present invention may include a computer 1412. The computer 1412 may also include a processing unit 1414, a system memory 1416, and a system bus 1418. The system bus 1418 may operably couple system components including, but not limited to, the system memory 1416 to the processing unit 1414. The processing unit 1414 may be any of a variety of available processors. Dual microprocessors and other multi-processor architectures may also be used as the processing unit 1414. The system bus 1418 may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus or external bus, and / or a local bus using various available bus architectures, various available bus architectures including, but not limited to, Industry Standard Architecture (ISA), Micro Channel Architecture (MSA), Extended ISA (EISA), Intelligent Drive Electronics (IDE), VESA Local Bus (VLB), Peripheral Component Interconnect (PCI), Card Bus, Universal Serial Bus (USB), Advanced Graphics Port (AGP), FireWire, and Small Computer System Interface (SCSI). The system memory 1416 may also include volatile memory 1420 and non-volatile memory 1422. A basic input / output system (BIOS) containing basic routines that transfer information between elements within the computer 1412 during startup may be stored in the non-volatile memory 1422. By way of illustration and not limitation, the non-volatile memory 1422 may contain read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or non-volatile random access memory (RAM) (e.g., ferroelectric RAM (FeRAM)). The volatile memory 1420 may also include random access memory (RAM) that acts as an external cache. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), direct Rambus RAM (DRRAM), direct Rambus dynamic RAM (DRDRAM), and Rambus dynamic RAM.

[0104] The computer 1412 may also include removable / non-removable, volatile / non-volatile computer storage media. Figure 14Shows, for example, a disk storage 1424. The disk storage 1424 may also include, but is not limited to, devices such as disk drives, floppy disk drives, tape drives, Jaz drives, Zip drives, LS-100 drives, flash cards, or memory sticks. The disk storage 1424 may also include storage media, separately or in combination with other storage media, including but not limited to optical disk drives such as compact disk ROM devices (CD-ROM), CD recordable drives (CD-R drives), CD rewritable drives (CD-RW drives), or digital versatile disk ROM drives (DVD-ROM). To facilitate the connection of the disk storage 1424 to the system bus 1418, a removable or non-removable interface, such as interface 1426, may be used. Figure 14 Also depicted is software that can act as a mediator between a user and the basic computer resources described in a suitable operating environment 1400. Such software may also include, for example, an operating system 1428. The operating system 1428, which may be stored on the disk storage 1424, is used to control and allocate the resources of the computer 1412. System applications 1430 may utilize the operating system 1428's management of resources through, for example, program modules 1432 and program data 1434 stored in the system memory 1416 or on the disk storage 1424. It should be understood that the present disclosure may be implemented with different operating systems or combinations of operating systems. A user inputs commands or information into the computer 1412 through one or more input devices 1436. The input devices 1436 may include, but are not limited to, pointing devices such as mice, trackballs, styli, touchpads, keyboards, microphones, joysticks, gamepads, satellite dishes, scanners, TV tuner cards, digital cameras, digital video cameras, webcams, etc. These and other input devices may be connected to the processing unit 1414 via the system bus 1418 through one or more interface ports 1438. The interface ports 1438 may include, for example, serial ports, parallel ports, game ports, and universal serial bus (USB). One or more output devices 1440 may use some of the same types of ports as the input devices 1436. Thus, for example, a USB port may be used to provide input to the computer 1412 and output information from the computer 1412 to the output device 1440. An output adapter 1442 may be provided to account for some output devices 1440 that require special adapters, such as monitors, speakers, and printers, as well as other output devices 1440. By way of illustration and not limitation, the output adapter 1442 may include video and sound cards that provide a means of connection between the output device 1440 and the system bus 1418. It should be noted that other devices and / or device systems provide both input and output capabilities, such as one or more remote computers 1444.

[0105] Computer 1412 may operate in a networked environment using a logical connection to one or more remote computers, such as remote computer 1444. Remote computer 1444 can be a computer, server, router, network PC, workstation, microprocessor-based appliance, peer device, or other common network node, etc., and generally can also include many or all of the elements described relative to computer 1412. For simplicity, only memory storage device 1446 is illustrated for remote computer 1444. Remote computer 1444 can be logically connected to computer 1412 via network interface 1448 and then physically connected via communication connection 1450. Further, operations can be distributed across multiple (local and remote) systems. Network interface 1448 can include wired and / or wireless communication networks, such as local area networks (LANs), wide area networks (WANs), cellular networks, etc. LAN technologies include Fiber Distributed Data Interface (FDDI), Copper Distributed Data Interface (CDDI), Ethernet, Token Ring, etc. WAN technologies include, but are not limited to, point-to-point links, circuit-switched networks (such as Integrated Services Digital Network (ISDN)) and its variants, packet-switched networks, and Digital Subscriber Line (DSL). One or more communication connections 1450 refer to the hardware / software for connecting network interface 1448 to system bus 1418. Although communication connection 1450 is shown inside computer 1412 for clarity of illustration, it can also be outside computer 1412. The hardware / software for connecting to network interface 1448 can also (for illustrative purposes only) include internal and external technologies, such as modems including conventional telephone-grade modems, cable modems, and DSL modems, ISDN adapters, and Ethernet cards.

[0106] Embodiments of the present invention can be systems, methods, devices, and / or computer program products at any possible level of integration of technical details. A computer program product can include a computer-readable storage medium (or media) having computer-readable program instructions thereon for causing a processor to execute aspects of the present invention. A computer-readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer-readable storage medium can further include the following: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanical encoding device (such as a punched card or raised structures in grooves having instructions recorded thereon), and any suitable combination of the foregoing. As used herein, a computer-readable storage medium should not be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0107] The computer-readable program instructions described herein can be downloaded to a corresponding computing / processing device from a computer-readable storage medium or downloaded to an external computer or an external storage device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network). The network may include copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium within the corresponding computing / processing device. The computer-readable program instructions for performing the operations of the various aspects of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state-setting data, configuration data for integrated circuits, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and procedural programming languages such as the "C" programming language or similar programming languages. These computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network (including a local area network (LAN) or a wide area network (WAN)), or may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, an electronic circuit (including, for example, a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA)) can execute the computer-readable program instructions by utilizing the state information of the computer-readable program instructions to customize the electronic circuit to perform the various aspects of the present invention.

[0108] Aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer-readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the functions / acts specified in one or more blocks of the flowchart and / or block diagram. The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other device to produce a computer-implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions / acts specified in one or more blocks of the flowchart and / or block diagram.

[0109] The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to different embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

[0110] Although the subject matter has been described above in the general context of computer-executable instructions of a computer program product running on one computer and / or multiple computers, those skilled in the art will recognize that the invention may also be implemented in or in conjunction with other program modules. Generally, program modules include routines, programs, components, data structures, etc. that perform specific tasks and / or implement specific abstract data types. Additionally, those skilled in the art will recognize that the computer-implemented methods of the present invention may be practiced with other computer system configurations, including single-processor or multi-processor computer systems, small computing devices, mainframe computers, and computers, handheld computing devices (e.g., PDAs, telephones), microprocessor-based or programmable consumer or industrial electronic products, etc. The aspects shown may also be practiced in a distributed computing environment where tasks are performed by remote processing devices linked through a communication network. However, some (if not all) aspects of the present disclosure may be practiced on a stand-alone computer. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0111] As used in this application, the terms "component", "system", "platform", "interface", etc. may refer to and / or may include a computer-related entity or an entity related to an operating machine having one or more specific functions. The entities disclosed herein may be hardware, a combination of hardware and software, software, or software in execution. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an executing thread, a program, and / or a computer. By way of illustration, both an application running on a server and the server may be components. One or more components may reside within a process and / or an executing thread, and a component may be located on one computer and / or distributed between two or more computers. In another example, corresponding components may execute from different computer-readable media having different data structures stored thereon. Components may communicate via local and / or remote procedure calls, such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with a local system, another component in a distributed system, and / or interacting across a network, such as the Internet, with other systems via a signal). As another example, a component may be a device having a specific function provided by a mechanical component operated by an electrical or electronic circuit, where the electrical or electronic circuit is operated by a software or firmware application executed by a processor. In such a case, the processor may be internal or external to the device and may execute at least a portion of the software or firmware application. As yet another example, a component may be a device that provides a specific function through an electronic component without a mechanical component, where the electronic component may include a processor or other means for executing software or firmware that at least partially imparts the function of the electronic component. In one aspect, a component may emulate an electronic component via, for example, a virtual machine within a cloud computing system.

[0112] In addition, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless otherwise specified or clear from the context, "X employs A or B" is intended to mean any natural inclusive arrangement. That is, if X employs A; X employs B; or X employs both A and B, then "X employs A or B" is satisfied in any of the foregoing instances. Further, the articles "a" and "an" as used in this specification and the drawings are generally to be construed to mean "one or more" unless otherwise specified or clear from the context to be directed to the singular form. As used herein, the terms "example" and / or "exemplary" are used to mean serving as an example, instance, or illustration. To avoid doubt, the subject matter disclosed herein is not limited by such examples. Further, any aspect or design described herein as "example" and / or "exemplary" is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it intended to exclude equivalent exemplary structures and techniques known to those of ordinary skill in the art.

[0113] As used in this specification, the term "processor" can refer to substantially any computing processing unit or device, including but not limited to a single-core processor; a single processor with software multithreaded execution capabilities; a multi-core processor; a multi-core processor with software multithreaded execution capabilities; a multi-core processor with hardware multithreaded technology; a parallel platform; and a parallel platform with distributed shared memory. Additionally, a processor can refer to an integrated circuit, an application specific integrated circuit (ASIC), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic controller (PLC), a complex programmable logic device (CPLD), discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. Further, a processor can utilize nanoscale architectures such as, but not limited to, molecule and quantum dot-based transistors, switches, and gates in order to optimize space usage or enhance the performance of a user device. A processor can also be implemented as a combination of computing processing units. In the present disclosure, terms such as "storage", "memory", "data storage", "data memory", "database", and substantially any other information storage component related to the operation and functionality of a component are used to refer to "memory components", entities embodied in a "memory", or components that include a memory. It should be understood that the memory and / or memory components described herein can be volatile memory or non-volatile memory, or can include both volatile memory and non-volatile memory. By way of illustration and not limitation, non-volatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM), flash memory, or non-volatile random access memory (RAM) (e.g., ferroelectric RAM (FeRAM)). Volatile memory can include RAM, which can, for example, act as an external cache memory. By way of illustration and not limitation, RAM is available in many forms such as synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), direct Rambus RAM (DRRAM), direct Rambus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM). Additionally, the memory components of the systems or computer-implemented methods disclosed herein are intended to include, but not be limited to, including these and any other suitable types of memory.

[0114] The foregoing merely includes examples of systems, computer program products, and computer-implemented methods. Of course, for purposes of describing the present disclosure, it is not possible to describe every conceivable combination of components, products, and / or computer-implemented methods, but those of ordinary skill in the art will recognize that many further combinations and permutations of the present disclosure are possible. Additionally, insofar as the terms “including,” “having,” “owning,” etc. are used in the detailed description, claims, appendices, and drawings, such terms are intended to be inclusive in a manner similar to the term “comprising” as interpreted when used as a transitional word in claims. The description of the different embodiments has been presented for purposes of illustration, but the description is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope of the described embodiments. The terms used herein were chosen to best explain the principles of the embodiments, the practical application, or a technical improvement found in the marketplace, or to enable those of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A system, comprising: a memory; a processor operatively coupled to the memory, wherein the processor: constructs a generative machine learning model based on training data regarding past chemical reactor operations, wherein the generative machine learning model generates recommended chemical reactor control settings for experimental discoveries of a polymer having target properties; measures properties of the polymer synthesized by the chemical reactor; determines whether the properties are within a defined range of the target properties; and updates the training data with the recommended chemical reactor control settings based on the determination that the properties are within the defined range.

2. The system according to claim 1, wherein The generative machine learning model is a variational autoencoder model trained via a gradient descent algorithm that optimizes a loss function with respect to parameters of an encoder and a decoder.

3. The system according to claim 2, wherein, The generative machine learning model generates the recommended chemical reactor control settings by sampling latent variables from a latent space and decoding the latent variables via the decoder.

4. The system according to claim 1, wherein The generative machine learning model is via a generative adversarial network model that includes a generator network and a discriminator network.

5. The system according to claim 4, wherein, The generator network upsamples a noise vector to generate new data, and wherein the discriminator network is a binomial classifier that analyzes the training data and the new data.

6. The system according to claim 5, wherein, The generator network achieves a training state based on the discriminator network's inability to discriminate between the training data and the new data, and wherein when the generator network is in the training state, the recommended chemical reactor control settings are included within the new data generated by the generator network.

7. The system according to claim 1, wherein, The training data includes control settings implemented by the chemical reactor during past chemical reactor operations.

8. The system of claim 1, wherein the processor: operates the chemical reactor according to the recommended chemical reactor control settings to synthesize the polymer.

9. The system of claim 8, wherein the target properties include molecular weight.

10. The system of claim 9, wherein the target properties include retention time.

11. A computer-implemented method, comprising: generating, by a system operatively coupled to a processor, a generative machine learning model based on training data regarding past chemical reactor operations, wherein the generative machine learning model generates recommended chemical reactor control settings for experimental discoveries of a polymer having target properties; measuring, by the system, properties of the polymer synthesized by the chemical reactor; determining, by the system, whether the properties are within a defined range of the target properties; and updating, by the system, the training data with the recommended chemical reactor control settings based on the determination that the properties are within the defined range.

12. The computer-implemented method according to claim 11, wherein, The generative machine learning model is a variational autoencoder, and wherein the computer-implemented method further comprises: The system uses a gradient descent algorithm to train the generative machine learning model, and the gradient descent algorithm optimizes a loss function with respect to the parameters of the encoder and the decoder.

13. The computer-implemented method according to claim 12, wherein, The generative machine learning model generates the recommended chemical reactor control settings by sampling latent variables from a latent space and decoding the latent variables via the decoder.

14. The computer-implemented method according to claim 11, wherein, The generative machine learning model is via a generative adversarial network, which includes a generator network and a discriminator network.

15. The computer-implemented method according to claim 14, further comprising: The system trains the generative adversarial network by upsampling a noise vector to generate new data and analyzing the training data together with the new data to discern a classification difference between the training data and the new data.

16. A computer program product for controlling a chemical reactor, the computer program product comprising a computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to: A system operatively coupled to the processor generates a generative machine learning model based on training data regarding past chemical reactor operations, where The generative machine learning model generates recommended chemical reactor control settings for experimental findings of a polymer having target properties; The system measures the properties of the polymer synthesized by the chemical reactor; The system determines whether the properties are within a defined range of the target properties; and The system updates the training data with the recommended chemical reactor control settings based on the determination that the properties are within the defined range.

17. The computer program product according to claim 16, wherein, The program instructions cause the processor to generate the generative machine learning model in a cloud computing environment.

18. The computer program product according to claim 16, wherein The training data includes control settings achieved by the chemical reactor during past chemical reactor operations.

19. The computer program product according to claim 16, wherein, The generative machine learning model is a variational autoencoder, and wherein the program instructions further cause the processor to: The system uses a gradient descent algorithm to train the generative machine learning model, and the gradient descent algorithm optimizes a loss function with respect to the parameters of the encoder and the decoder.

20. The computer program product according to claim 16, wherein, The generative machine learning model is via a generative adversarial network, which includes a generator network and a discriminator network.

Images