Digital twin-based chemical experiment monitoring and optimization method and apparatus

Abstract

Provided are a digital twin-based chemical experiment monitoring and optimization method and apparatus. The method comprises: partitioning a laboratory into a plurality of operational unit areas, and creating a corresponding management shell for each operational unit area for experiment control and data acquisition; converting a current experiment process into an experiment task and an experiment operation, and mapping collected data to a corresponding experiment object; creating and training a prediction model, and inputting into the prediction model the data mapped to the experiment object, so as to monitor a current experiment state; and optimizing the current experiment process according to a result of the current experiment process and the data mapped to the experiment object. A closed-loop from data acquisition to experiment monitoring and optimization is established for laboratories so as to implement data acquisition, prediction, monitoring, index analysis, experiment optimization and simulation display for experiment processes.

Description

A chemical experiment monitoring optimization method and device based on digital twin Technical Field

[0001] The present invention relates to the field of digital twin technology, and in particular to a chemical experiment monitoring optimization method, device, electronic device and computer-readable medium based on digital twin. Background Art

[0002] Chemical experiments are primarily used to assist in chemical teaching or research, typically requiring operators to perform experiments according to the experimental process, record experimental data, and analyze the experimental data. Clearly, this traditional approach is overly reliant on manual labor. Furthermore, due to the wide variety of laboratory chemical reactions and the unique operational procedures for each reaction, it is difficult to predict and monitor the experimental process. Furthermore, optimizing the experimental process requires continuous and repeated experimentation, resulting in significant losses in both manpower and financial resources. Technical issues

[0003] The present invention aims to solve the technical problem in the prior art that chemical experiments cannot be effectively monitored, analyzed and predicted, resulting in huge loss of manpower and financial resources. Technical Solutions

[0004] In order to solve the above technical problems, the first aspect of the present invention proposes a chemical experiment monitoring optimization method based on digital twins, which includes:

[0005] Divide the laboratory into multiple operating unit areas, and create a corresponding management shell for each operating unit area to perform experimental control and data collection;

[0006] Convert the current experimental process into experimental tasks and experimental operations, and map the collected data to corresponding experimental objects; the experimental objects include experimental tasks and / or experimental operations;

[0007] Creating and training a prediction model, and inputting data mapped to the experimental object into the prediction model to monitor the status of the current experiment;

[0008] Optimize the current experimental process based on the results of the current experimental process and the data mapped to the experimental object.

[0009] According to a preferred embodiment of the present invention, mapping the collected data to the corresponding experimental objects includes:

[0010] Create a mapping relationship between each instrument and experimental object in the operation unit area;

[0011] The data collected from each operation unit area is mapped to the corresponding experimental object according to the mapping relationship.

[0012] According to a preferred embodiment of the present invention, the experimental object is an experimental task, and the experimental task includes a reaction, and the data mapped to the experimental object is a reaction formula, then a first model is created and trained, and the reaction formula is input into the first model to predict and monitor the feasible probability of the current reaction;

[0013] The experimental object is an experimental operation, and the data mapped to the experimental object is a time series of experimental operation parameters, then a second model is created and trained, and the time series of experimental operation parameters is input into the second model to predict and monitor the probability of anomalies occurring in the current experimental task;

[0014] The experimental object is an experimental operation, and the data mapped to the experimental object does not include a time series of experimental operation parameters; the execution result of the current experimental task is predicted by the distribution of the historical execution results of the experimental operation.

[0015] According to a preferred embodiment of the present invention, optimizing the current experimental process according to the results of the current experimental process and the data mapped to the experimental object includes:

[0016] Determine the results of the current experimental process and the parameters mapped to the experimental operation, adjust the experimental process and / or experimental operation parameters according to the preset reaction parameters and process optimization algorithm, and obtain the adjusted experimental process execution results;

[0017] Alternatively, the results of the current experimental process and the data mapped to the experimental operation are determined, and the experimental operation is adjusted according to the analysis results of the current experimental process results and the experimental operation data.

[0018] According to a preferred embodiment of the present invention, adjusting the experimental operation according to the analysis results of the current experimental process results and experimental operation data includes:

[0019] Analyze the causal relationship between the current experimental process results and the data mapped to the experimental operation, and make the first adjustment to the experimental operation;

[0020] And / or, compare multiple execution results of the same experimental operation in multiple experimental processes, and perform a second adjustment on the experimental operation according to the execution results.

[0021] According to a preferred embodiment of the present invention, the method further comprises:

[0022] After performing the first adjustment and the second adjustment on the experimental operation, the experimental operation before the adjustment and the experimental operation after the adjustment are respectively executed multiple times, and the execution data are analyzed to verify the adjustment efficiency.

[0023] According to a preferred embodiment of the present invention, the method further comprises:

[0024] Analyze the business indicators of the current experimental process in real time based on the data mapped to the experimental object; the business indicators include: at least one of: experimental efficiency, manual load, and automation rate.

[0025] According to a preferred embodiment of the present invention, the method further comprises:

[0026] Collect the time distribution of the same type of experimental tasks during execution;

[0027] The execution time of the current experimental process is predicted based on the time consumption distribution.

[0028] According to a preferred embodiment of the present invention, the method further comprises:

[0029] The monitoring results of the current experimental process, the business indicators of the current experimental process, and the execution time of the current experimental process are sent to the user.

[0030] According to a preferred embodiment of the present invention, the method further comprises:

[0031] Simulate and demonstrate the execution effects before and after the experimental process is optimized;

[0032] Receive the experimental support conditions input by the user, and search for target experimental processes that match the experimental support conditions based on the business indicators and execution time of each experimental process;

[0033] The experimental expansion conditions input by the user are received, and the experimental support conditions matching the experimental expansion conditions are searched according to the business indicators of each experimental process.

[0034] To solve the above technical problems, the second aspect of the present invention provides a chemical experiment monitoring and optimization device based on digital twins, the device comprising:

[0035] The acquisition module is used to divide the laboratory into multiple operation unit areas and create a corresponding management shell for each operation unit area to perform experimental control and data acquisition;

[0036] A mapping module is used to convert the current experimental process into experimental tasks and experimental operations, and map the collected data to corresponding experimental objects; the experimental objects include experimental tasks and / or experimental operations;

[0037] A monitoring module is used to create and train a prediction model, input data mapped to the experimental object into the prediction model to monitor the status of the current experiment;

[0038] The optimization module is used to optimize the current experimental process based on the results of the current experimental process and the data mapped to the experimental object.

[0039] In order to solve the above technical problems, the third aspect of the present invention provides an electronic device, including:

[0040] processor; and

[0041] A memory storing computer executable instructions, which, when executed, cause the processor to perform the above method.

[0042] In order to solve the above technical problems, the fourth aspect of the present invention proposes a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, the above method is implemented. Beneficial effects

[0043] The present invention realizes automated data collection by dividing the laboratory into multiple operation unit areas and creating a corresponding management shell for each operation unit area to perform experimental control and data collection. By converting the current experimental process into experimental tasks and experimental operations, and mapping the collected data to the corresponding experimental objects; completing the docking of experimental data with specific experimental objects, and realizing business layer modeling. By creating and training a prediction model, the data mapped to the experimental object is input into the prediction model to monitor the status of the current experiment; finally, the current experimental process is optimized according to the results of the current experimental process and the data mapped to the experimental object. Finally, a closed loop from data collection to experimental monitoring optimization is established in the laboratory. Compared with the existing technology, the present invention has at least the following beneficial effects:

[0044] 1. Create a corresponding management shell in each operation unit area to perform experimental control and data collection, realizing automated data collection;

[0045] 2. By creating and training a predictive model, the physical simulation modeling process of the chemical reaction can be bypassed to predict and monitor the results and process of the experiment.

[0046] 3. There is no need to conduct repeated experiments for optimization. The current experimental process can be automatically optimized based on the results of the current experimental process and the data mapped to the experimental object, effectively saving manpower and financial resources.

[0047] 4. Ability to analyze laboratory indicators based on data mapped to experimental objects to obtain information such as laboratory execution efficiency, experimental time, reaction success rate, etc., to provide support for subsequent experiments.

[0048] 5. Based on the data and prediction models mapped to the experimental objects, it can provide experimental monitoring results, experimental business indicators, and experimental execution time for decision-making reference.

[0049] 6. Ability to simulate experiments based on experimental monitoring results, experimental business indicators, and experimental execution time, and estimate the support and expansion conditions required for the experiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to make the technical problems solved by the present invention, the technical means adopted, and the technical effects achieved more clearly, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it should be noted that the drawings described below are only drawings of exemplary embodiments of the present invention. Those skilled in the art can derive drawings of other embodiments based on these drawings without inventive effort.

[0051] FIG1 is a schematic diagram of a process of a chemical experiment monitoring optimization method based on digital twins of the present invention;

[0052] FIG2 is a schematic diagram of the implementation framework of chemical experiment monitoring optimization based on digital twins of the present invention;

[0053] FIG3 is a schematic diagram of the structural framework of a chemical experiment monitoring and optimization device based on digital twins of the present invention;

[0054] FIG4 is a structural block diagram of an exemplary embodiment of an electronic device according to the present invention;

[0055] FIG. 5 is a schematic diagram of an embodiment of a computer-readable medium according to the present invention. Best Mode for Carrying Out the Invention

[0056] The exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. Although each exemplary embodiment can be implemented in a variety of specific ways, it should not be understood that the present invention is limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided to make the content of the present invention more complete and to more fully convey the inventive concept to those skilled in the art.

[0057] Under the premise of being consistent with the technical concept of the present invention, the structure, performance, effect or other characteristics described in a specific embodiment may be combined with one or more other embodiments in any appropriate manner.

[0058] In the introduction of specific embodiments, the detailed description of the structure, performance, effect or other features is intended to enable those skilled in the art to fully understand the embodiments. However, this does not preclude those skilled in the art from implementing the present invention with a technical solution that does not include the aforementioned structure, performance, effect or other features under specific circumstances.

[0059] The flowcharts in the accompanying drawings are merely illustrative of the process flow and do not necessarily include all of the content, operations, and steps in the flowcharts, nor do they necessarily imply that all of the steps in the flowcharts must be executed in the order shown. For example, some of the steps in the flowcharts may be separated, some may be combined or partially combined, and so on. The execution order shown in the flowcharts may be changed according to actual circumstances without departing from the spirit of the present invention.

[0060] The block diagrams in the accompanying drawings generally represent functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0061] The same reference numerals in the accompanying drawings represent the same or similar elements, components or parts, and thus repeated descriptions of the same or similar elements, components or parts may be omitted below. It should also be understood that although the first, second, third and other numbered adjectives may be used herein to describe various devices, elements, components or parts, these devices, elements, components or parts should not be limited by these adjectives. In other words, these adjectives are only used to distinguish one from another. For example, the first device may also be called the second device, but this does not deviate from the essential technical solution of the present invention. In addition, the terms "and / or" and "and / or" refer to all combinations including any one or more of the listed items.

[0062] In the embodiments of the present invention, digital twins leverage data from physical models, sensor updates, and operational history to integrate multidisciplinary, multi-physics, multi-scale, and multi-probability simulation processes, mapping them in virtual space to reflect the full lifecycle of the corresponding physical equipment. Based on modeling tools, they construct precise physical object models in digital space, then utilize real-time IoT data to drive model operation. This integration of data and models builds comprehensive decision-making capabilities, driving closed-loop optimization of the entire industrial business process.

[0063] Currently, digital twin technology cannot be applied in chemical laboratories for the following reasons:

[0064] In existing chemical laboratory scenarios, most operations rely on manual labor, and some equipment (such as rotary evaporators) do not have data collection functions and cannot provide the data required for modeling.

[0065] Laboratory chemical reactions are highly diverse, and the operating procedures of each reaction are different, making it difficult to model and predict the experimental process.

[0066] The conditions that determine the success of an experiment or a specific experimental task in a chemical laboratory are not determined by the physical equipment and its operation. For example, the success of a chemical reaction is mainly determined by the reaction mechanism, the choice of reaction conditions, the raw materials, the operating steps (such as the process and order of feeding), and the specific operational decisions (whether there are any misoperations). In a reactor, information such as the reaction duration and temperature can be read from the instrument, but other information is difficult to simulate through physical simulation. Therefore, the process of chemical reactions is difficult to predict through physical models. Chemical reaction simulation software such as COMSOL also simulates large-scale, mature reactions and lacks solutions for new chemical reactions.

[0067] Based on this, the present invention provides a chemical experiment monitoring and optimization method based on digital twins to realize data collection of chemical experiments, prediction, monitoring and optimization of experimental processes.

[0068] FIG1 is a flow chart of a chemical experiment monitoring optimization method based on digital twins provided by the present invention; as shown in FIG1 , the method includes:

[0069] S1. Divide the laboratory into multiple operation unit areas and create a corresponding management shell for each operation unit area to perform experimental control and data collection;

[0070] The management shell is a digital model "shell" that adds a physical device to the physical device. Multiple devices in the management shell receive cloud commands through some connection method (including but not limited to websocket persistent connection and MQTT), and report the actual execution results, thereby realizing data exchange.

[0071] For example, a laboratory can be divided into automated operation areas, manual operation areas, and mixed operation areas based on the operating entities. The automated operation area includes instruments that can automatically perform experimental operations, such as automated reactors, automatic weighing equipment, and liquid chromatography-mass spectrometers (LC-MS), as shown in Figure 2. Data generated by instruments in the automated operation area can be collected via protocols such as RS485, Modbus, and OPC-UA, and reported to the cloud via MQTT.

[0072] The manual operation area contains some instruments that require manual experimental operation, such as ordinary fume hoods. In this embodiment, an interactive terminal (such as a pad) can be installed in the manual operation area. The operator works according to the instructions of the terminal and enters the process and results of the instrument execution into the terminal, as shown in Figure 2, and reports to the cloud through the https interface.

[0073] The mixed operation area includes some instruments that can perform automatic experimental operations but require manual assistance, such as semi-automatic column machines. The data generated by the instruments can be collected through protocols such as RS485, Modbus, and OPC-UA, and reported to the cloud through MQTT; data manually entered into the terminal can be reported to the cloud through the https interface.

[0074] To facilitate subsequent data processing, the collected data can be further processed. As shown in Figure 2, in the data layer, the raw data layer stores data reported by instruments and interactive terminals. Data reported by instruments can include instrument parameters and logs, while data from interactive terminals can include operator interaction and input. The data detail layer (DWD) cleanses the raw data in the raw data layer, for example, by deleting or filling in missing data. For example, a reactor may have a log at a certain point in time. Normally, a log should include a timestamp and content. However, if the log only contains a timestamp and the content is missing, this data is useless and should be deleted. The common data model layer (CDM) defines the data model based on the relationships between business entities. Data in the data detail layer is normalized through ETL and stored in the common model layer. For example, the log formats returned by different reactor models may vary, requiring conversion to a unified data content before storage. The data service layer (DWS) distributes the cleansed data from the data detail layer and performs light aggregation by topic through ETL, forming a "large wide table" with different topics for query and use by downstream services.

[0075] S2. Convert the current experimental process into experimental tasks and experimental operations, and map the collected data to corresponding experimental objects; the experimental objects include experimental tasks and / or experimental operations;

[0076] In this embodiment, the experimental process includes all the processes for completing the experiment, which can be composed of multiple experimental tasks, and each experimental task can be completed by multiple experimental operations. Optionally, the experimental process can be represented by a directed graph constructed by experimental tasks and the order of experimental tasks, in which each node represents an experimental task, and each experimental task has corresponding multiple experimental operations to complete. A simple arrow means that the previous task is done first, and the next task is executed after the previous task is completed. The parallel tasks controlled by the parallel task switch indicate that the processes between the start of the parallel task and the end of the parallel task are carried out simultaneously.

[0077] An experimental task refers to completing a task with a chemical purpose, such as collecting materials, returning materials, weighing, adding materials, reacting, quenching, recrystallizing, column chromatography, extraction, filtration, separation, crystallization, column chromatography, solvent extraction, dehydration with desiccant, and pH adjustment. An experimental operation refers to the series of operations required to complete an experimental task. For example, dehydration with desiccant includes four experimental operations: 1. Add desiccant until no more lumps form; 2. Allow to stand; 3. Filter; and 4. Wash.

[0078] In one example, the experimental process can be described by text, and a conversion model that can convert the experimental process text into an experimental flowchart can be pre-trained. Through the conversion model, the experimental flowchart is obtained, and the experimental tasks and experimental operations can be directly extracted from the experimental flowchart nodes. Wherein: the conversion model may include: a classification module for performing text classification at the sentence level to determine the task type of the node; an extraction module for extracting experimental substances and parameters in the experimental task from the sentence; a construction module connected to the classification module for extracting keywords representing the sequence of experimental tasks from the sentence (such as: before, after, at the same time, etc.), and constructing the sequence between tasks based on the keywords; a generation module connected to the classification module, the extraction module and the construction module for generating a flowchart based on the sequence between the nodes, experimental substances and parameters. Optionally, the above-mentioned classification module, extraction module and construction module can realize their functions by training corresponding models. For example, the classification module can first annotate the text representing the experimental tasks in the existing experimental process text (for example, if a text describes how to add materials, the text can be annotated as adding materials), and then a large amount of annotated experimental process text is input as a training set into the classification model for supervised training, so that the trained classification model can identify the experimental tasks (i.e., the task type of the node) based on the input text. The extraction module can first annotate the text representing the experimental substances and parameters in the existing experimental process text, and then a large amount of annotated experimental process text is input as a training set into the extraction model for supervised training, so that the trained extraction model can extract the experimental substances and parameters from the text. The construction module can first annotate the text representing the sequence of experimental tasks in the existing experimental process text, and then a large amount of annotated experimental process text and the experimental tasks in the text are input as a training set into the construction model for supervised training, so that the trained extraction model can extract keywords with a sequence from the text and construct the sequence between experimental tasks based on the keywords. The generation module can be combined with a process editor, and professional scientists can use the process editor to adjust the sequence of nodes, experimental materials, parameters, and tasks of a single specific chemical experiment to generate a flow chart of the single specific chemical experiment.

[0079] An experimental object refers to the mapping of an experimental entity in reality on a data model. An experimental object has a unique identifier id to track it, so that even if its status and data change, it is considered to be the same object. For example: laboratory employees have their work numbers as unique id identifiers, and their age, length of service, rank, etc. are employee data that may change, but their work numbers remain unchanged. An experiment has a fixed experimental number that tracks the status of the experiment, such as never started, in progress, and successful, as well as the data of the experiment. This makes it easy to track the data and status of an experimental object throughout its life cycle. In this embodiment, the experimental object can be just an experimental task, an experimental operation, or both an experimental task and an experimental operation. Optionally, before performing data mapping, a mapping relationship between each instrument and the experimental object in the operation unit area can be created; that is, different instruments will correspond to different experimental tasks and experimental operations. For example, in one mapping relationship, reactor data in the data service layer is mapped to corresponding experimental tasks and stirring operations, where the experimental tasks are determined by central control signals. For example, when the central control issues an instruction for experimental task A to the reactor, it records a timestamp t1, and when experimental task A is completed, it records a timestamp t2. The reactor's log data between t1 and t2 is mapped to experimental task A. This step maps the data collected in each operating unit area to the corresponding experimental object based on the mapping relationship.

[0080] Optionally, the present invention can also pre-configure the annotation data of each experimental object, and this step can also judge the execution status of the experimental object by comparing the data mapped to each experimental object with the annotation data of each experimental object. For example: in a reaction task, the expected reaction time is 3 hours, but the data mapped to the experimental task reflects that the reaction stopped at 10 minutes, then the execution status of the reaction task is failure. Furthermore, the cause of the failure of the experimental task can be diagnosed based on the subsequent mapping data of the experimental task. For example: if the subsequent mapping data of the experimental task reflects the cancellation status of the experiment (the subsequent experimental data is empty), it can be judged that an abnormal event has occurred in the reaction. Further checking the log of the reactor can determine the cause of the abnormal termination, such as the occurrence of liquid spraying.

[0081] This step maps the collected data to the data object, completing the establishment of the business model in Figure 2.

[0082] S3. Create and train a prediction model, input the data mapped to the experimental object into the prediction model to monitor the status of the current experiment;

[0083] To address the problem that chemical experiments cannot be simulated and predicted through physical models, the present invention adopts artificial intelligence technology to create and train a prediction model, input the data mapped to the experimental object into the prediction model to monitor the status of the current experiment.

[0084] In one example, when the experimental object is an experimental task that includes a reaction, and the data mapped to the experimental object is a reaction formula, a first model is created and trained. The reaction formula is input into the first model to predict and monitor the feasibility probability of the current reaction. Considering that the reaction is the most critical part of an experimental task, the first model can be pre-trained using a large amount of reaction text to determine the feasibility probability of the reaction. After training, a test set is created, which contains feasible reactions (reported in the literature) and infeasible reactions (reactions that failed in actual experiments and were judged infeasible by human experts). The performance of the first model is tested on the test set.

[0085] On the basis of the feasibility of the reaction, this step can also predict the execution status of the experimental task. When the experimental object is an experimental operation, and the data mapped to the experimental object is a time series of experimental operation parameters, a second model is created and trained, and the time series of experimental operation parameters is input into the second model to predict and monitor the probability of abnormality of the current experimental task. Among them: the experimental operation parameters can be: duration, temperature, pressure, etc., and the changes in the reaction parameters are trained through the time of the parameters. The second model can be trained in advance based on the time series of historical experimental operation parameters and the results of the experimental task, so that the second model can predict the probability of abnormality of the experimental task based on the time series of experimental operation parameters. For example: when the reading of the thermocouple rises sharply, the experimental task will often have an abnormal phenomenon of overheating.

[0086] When the experimental object is an experimental operation, and the data mapped to the experimental object does not include the time series of the experimental operation parameters, or in cases where it is impossible to determine whether the experimental task has an anomaly based on the operation parameters (such as manually executed tasks), the execution result of the current experimental task can be predicted based on the distribution of the historical execution results of the experimental operation. For example, the execution results of the same experimental task can be collected in advance, and the distribution of the execution results can be analyzed through big data to predict the execution result of the current experimental task based on this distribution.

[0087] As a preferred method, after the first model and the second model are trained, they can also be verified to ensure the accuracy of the model output. Specifically, the results output by the first model / second model are compared with the actual experimental execution results, and the model is run in shadow mode: that is, the model is run while the experiment is being carried out, but the model output is not perceived by the experimenter, in order to evaluate whether the model's prediction is close to reality. After verification, it was found that: although there is a large variance in the prediction of a single or a few experiments (the model predicts a high probability of success, but actually fails), in a large number of experiments, the success rate of the model prediction and the occurrence of various anomalies are very consistent with the actual execution results.

[0088] Through this step, the first model and the second model are established to predict and monitor the experimental status, completing the creation of the AI ​​model in Figure 2.

[0089] Corresponding to Figure 2, this step of monitoring the current experimental status may include: while the experiment is in progress, using the data mapped to the experimental object by the acquisition layer, data layer and business model to monitor the status of each experimental task in real time, and using the AI ​​model in the model layer to predict the feasibility of the ongoing experimental task and the probability of various anomalies.

[0090] S4. Optimize the current experimental process based on the results of the current experimental process and the data mapped to the experimental object.

[0091] In this embodiment, the reaction process and reaction conditions in the experimental process can be optimized, which can be applied to the process optimization scenario. As shown in Figure 2, the results of the current experimental process and the parameters mapped to the experimental operation are determined by the data acquisition layer, and the parameters of the experimental process and / or experimental operation are adjusted according to the preset reaction parameters and process optimization algorithm, and the adjusted experimental process execution results are obtained, thereby achieving the purpose of optimizing the reaction process and reaction conditions. Exemplarily, the preset reaction parameters and process optimization algorithm first train a surrogate model of a class of reactions based on the training data according to the predetermined optimization target (such as yield). And repeat the following operations: 1. Set the acquisition function, and select a series of parameter points by maximizing the acquisition function.

[0092] 2. Conduct experiments based on the parameter points, and update the surrogate posterior model as a new surrogate model based on the experimental results.

[0093] Until the predetermined optimization target (such as yield) no longer improves or the resources are exhausted, the parameter point obtained is the "optimal parameter" after optimization.

[0094] In addition, the experimental process of the present invention can also be parameterized, and then the parameterized experimental process can be optimized and adjusted using the above-mentioned preset reaction parameters and process optimization algorithm.

[0095] This embodiment can also optimize a single experimental operation. The results of the current experimental process and the data mapped to the experimental operation can be determined, and the experimental operation can be adjusted based on the analysis of the current experimental process results and experimental operation data. The experimental operation can also be parameterized, and then the parameterized experimental operation can be optimized and adjusted using the preset reaction parameters and process optimization algorithm.

[0096] In one example, the causal relationship between the current experimental process results and the data mapped to the experimental operation can be analyzed to make a first adjustment to the experimental operation; it can be applied to the optimization of the experimental operation. For example: in the experimental operation data, it is found that in the recrystallization operation, some operators like to put the solution directly into the ice bath after heating and dissolving, which produces the abnormal phenomenon of crystal explosion. Then, the experimental operation can be optimized and changed to cooling at room temperature and then putting it into the ice bath to slowly cool down. Preferably, the correspondence between the above-mentioned causal relationship and the optimized experimental operation can be stored in advance, and then after analyzing the causal relationship, the optimized experimental operation can be directly obtained.

[0097] In another example, the results of multiple executions of the same experimental operation across multiple experimental flows can be compared, and adjustments to the experimental operation can be made based on the results. This can be applied to diagnose bottlenecks in experimental operations. For example, in a data analysis of 56 experimental operations, it was found that weighing operations accounted for 7% of all human operation tasks, a relatively large proportion. Developing automated weighing methods to replace manual weighing can improve efficiency.

[0098] Furthermore, after optimizing a single experimental operation using the two aforementioned methods, the adjustment efficiencies can be compared, and the experimental operation with the highest adjustment efficiency can be selected as the final optimized experimental operation. This step can also involve performing the first and second adjustments on the experimental operation, executing the experimental operation before and after the adjustments multiple times, and analyzing the execution data to verify the adjustment efficiency. For example, after optimizing an experimental operation using the first and second adjustment methods, executing the experimental operation before and after the optimization multiple times, and verifying the improved efficiency through execution data analysis.

[0099] At this point, the optimization of the application layer in FIG2 is completed through step S4.

[0100] Furthermore, the present invention can also automatically analyze the laboratory's business indicators to provide support for operational decisions, and the method further includes:

[0101] S5. Analyze the business indicators of the current experimental process in real time based on the data mapped to the experimental object;

[0102] The business indicators may include at least one of experimental efficiency, manual load, and automation rate.

[0103] Experimental efficiency refers to the number of experiments completed per person per day, which can be calculated by the number of experiments completed within a predetermined time period / day.

[0104] The labor load can be calculated by the operating time / attendance time of the person.

[0105] The automation rate can be calculated by dividing the time it takes for an experiment to be automatically performed by a machine by the time it takes for all experiments to be performed.

[0106] At this point, the indicators of the application layer in FIG2 are completed through step S5.

[0107] Furthermore, the present invention can also predict the execution time required for a new experimental process based on the data mapped to the experimental object to provide support for the experiment. The method further includes:

[0108] S6. Collect the time consumption distribution of the same type of experimental tasks during execution; and predict the execution time of the current experimental process based on the time consumption distribution.

[0109] Specifically, the current experimental process can be converted into multiple target experimental tasks, the time distribution of each target experimental task can be queried, and the execution time of each target experimental task can be determined. The execution time of the current experimental process is the sum of the execution time of all target experimental tasks.

[0110] Furthermore, the present invention also supports interaction with the user, and the method further includes:

[0111] S7. Send the monitoring results of the current experimental process, the business indicators of the current experimental process, and the execution time of the current experimental process to the user.

[0112] The monitoring results may include: prediction results of reaction feasibility, prediction results of abnormal probability of experimental tasks, and monitoring results of data mapped to experimental objects.

[0113] Optionally, the monitoring results, business indicators, and execution time of the experimental process can be provided to users in the form of reports to support decision-making.

[0114] At this point, the report of the decision-making layer in FIG2 is completed through step S7.

[0115] Furthermore, the present invention also supports a virtual laboratory cockpit function to simulate the progress of the experimental process, and the method further includes:

[0116] S8. Simulate and demonstrate the execution effect before and after the experimental process optimization;

[0117] This step can show decision makers the effects of optimizing the reaction and operation processes: for example, how much the efficiency can be improved by changing the recrystallization operation; how much the efficiency can be improved by introducing automatic weighing equipment during weighing.

[0118] Specifically, the optimization indicator input by the user is received. The optimization indicator may include: the optimization object and the optimization method. For example, if the optimization object is a weighing operation and the optimization method is to introduce an automatic weighing device, the execution effect before and after the optimization is determined based on the manual weighing data and the automatic weighing data.

[0119] S9. Receive the experimental support conditions input by the user, and search for a target experimental process that matches the experimental support conditions based on the business indicators and execution time of each experimental process;

[0120] Among them: experimental support conditions may include: manpower required for the experiment, equipment conditions, time required for the experiment, etc.

[0121] S10: receiving the experiment expansion conditions input by the user, and searching for the experiment support conditions matching the experiment expansion conditions according to the business indicators of each experiment process.

[0122] Among them: the experimental expansion conditions may include: the expansion capacity of the experimental instruments.

[0123] At this point, the virtual laboratory cockpit of the decision-making layer in Figure 2 is completed through steps S8 to S10.

[0124] In summary, the present invention realizes automated data collection by dividing the laboratory into multiple operation unit areas and creating a corresponding management shell for each operation unit area to perform experimental control and data collection. By converting the current experimental process into experimental tasks and experimental operations, and mapping the collected data to the corresponding experimental objects; completing the docking of experimental data with specific experimental objects, and realizing business layer modeling. By creating and training a prediction model, the data mapped to the experimental object is input into the prediction model to monitor the status of the current experiment; finally, the current experimental process is optimized according to the results of the current experimental process and the data mapped to the experimental object. Finally, a closed loop from data collection to experimental monitoring optimization is established in the laboratory. Compared with the prior art, the present invention has at least the following beneficial effects:

[0125] 1. Create a corresponding management shell in each operation unit area to perform experimental control and data collection, realizing automated data collection;

[0126] 2. By creating and training a predictive model, the physical simulation modeling process of the chemical reaction can be bypassed to predict and monitor the results and process of the experiment.

[0127] 3. There is no need to conduct repeated experiments for optimization. The current experimental process can be automatically optimized based on the results of the current experimental process and the data mapped to the experimental object, effectively saving manpower and financial resources.

[0128] 4. Ability to analyze laboratory indicators based on data mapped to experimental objects to obtain information such as laboratory execution efficiency, experimental time, reaction success rate, etc., to provide support for subsequent experiments.

[0129] 5. Based on the data and prediction models mapped to the experimental objects, it can provide experimental monitoring results, experimental business indicators, and experimental execution time for decision-making reference.

[0130] 6. Ability to simulate experiments based on experimental monitoring results, experimental business indicators, and experimental execution time, and estimate the support and expansion conditions required for the experiment.

[0131] FIG3 is a schematic diagram of the structural framework of a chemical experiment monitoring and optimization device based on digital twins of the present invention. As shown in FIG3 , the device includes:

[0132] The acquisition module 31 is used to divide the laboratory into multiple operation unit areas and create a corresponding management shell for each operation unit area to perform experimental control and data acquisition;

[0133] A mapping module 32 is used to convert the current experimental process into experimental tasks and experimental operations, and map the collected data to corresponding experimental objects; the experimental objects include experimental tasks and / or experimental operations;

[0134] A monitoring module 33 is used to create and train a prediction model, input data mapped to the experimental object into the prediction model to monitor the status of the current experiment;

[0135] The optimization module 34 is used to optimize the current experimental process according to the results of the current experimental process and the data mapped to the experimental object.

[0136] In a specific embodiment, the mapping module 32 includes:

[0137] A creation module is used to create a mapping relationship between each instrument and experimental object in the operation unit area;

[0138] The sub-mapping module is used to map the data collected by each operation unit area to the corresponding experimental object according to the mapping relationship.

[0139] Optionally, the experimental object is an experimental task, and the experimental task includes a reaction, and the data mapped to the experimental object is a reaction formula, then the monitoring module 33 is used to create and train a first model, input the reaction formula into the first model to predict and monitor the feasible probability of the current reaction;

[0140] Optionally, the experimental object is an experimental operation, and the data mapped to the experimental object is a time series of experimental operation parameters, then the monitoring module 33 is used to create and train a second model, input the time series of experimental operation parameters into the second model to predict and monitor the probability of anomalies in the current experimental task;

[0141] Optionally, the experimental object is an experimental operation, and the data mapped to the experimental object does not include a time series of experimental operation parameters; the monitoring module 33 is used to predict the execution result of the current experimental task based on the distribution of the historical execution results of the experimental operation.

[0142] In one example, the optimization module 34 includes:

[0143] The first optimization module is used to determine the results of the current experimental process and the parameters mapped to the experimental operation, adjust the parameters of the experimental process and / or the experimental operation according to the preset reaction parameters and the process optimization algorithm, and obtain the adjusted experimental process execution results;

[0144] Alternatively, the second optimization module is used to determine the result of the current experimental process and the data mapped to the experimental operation, and adjust the experimental operation according to the analysis result of the current experimental process result and the experimental operation data.

[0145] Furthermore, the second optimization module includes:

[0146] An analysis and adjustment module is used to analyze the causal relationship between the current experimental process results and the data mapped to the experimental operation, and make a first adjustment to the experimental operation;

[0147] And / or, a comparison and adjustment module is used to compare multiple execution results of the same experimental operation in multiple experimental processes, and perform a second adjustment on the experimental operation according to the execution results.

[0148] Furthermore, the device further comprises:

[0149] The analysis and verification module is used to perform the first adjustment and the second adjustment on the experimental operation, execute the experimental operation before the adjustment and the experimental operation after the adjustment for multiple times, and analyze the execution data to verify the adjustment efficiency.

[0150] The indicator analysis module is used to analyze the business indicators of the current experimental process in real time based on the data mapped to the experimental object; the business indicators include: at least one of: experimental efficiency, manual load, and automation rate.

[0151] The first collection module is used to collect the time distribution of the same type of experimental tasks during execution;

[0152] The first prediction module is used to predict the execution time of the current experimental process according to the time consumption distribution.

[0153] The sending module is used to send the monitoring results of the current experimental process, the business indicators of the current experimental process, and the execution time of the current experimental process to the user.

[0154] The display module is used to simulate and display the execution effects before and after the optimization of the experimental process;

[0155] The first matching module is used to receive the experimental support conditions input by the user and search for a target experimental process that matches the experimental support conditions based on the business indicators and execution time of each experimental process;

[0156] The second matching module is configured to receive the experimental expansion conditions input by the user and search for experimental support conditions that match the experimental expansion conditions according to the business indicators of each experimental process.

[0157] Those skilled in the art will appreciate that the modules in the above device embodiments may be distributed in the device as described, or may be modified accordingly and distributed in one or more devices different from the above embodiments. The modules in the above embodiments may be combined into one module or further split into multiple submodules.

[0158] The following describes an electronic device embodiment of the present invention. This electronic device can be considered a physical implementation of the method and apparatus embodiments of the present invention described above. Details described in the electronic device embodiment of the present invention should be considered supplementary to the above-described method or apparatus embodiments; details not disclosed in the electronic device embodiment of the present invention can be implemented with reference to the above-described method or apparatus embodiments.

[0159] Figure 4 is a block diagram of an exemplary embodiment of an electronic device according to the present invention. The electronic device shown in Figure 4 is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0160] As shown in FIG4 , the electronic device 400 of this exemplary embodiment is implemented as a general-purpose data processing device. Components of the electronic device 400 may include, but are not limited to, at least one processing unit 410, at least one storage unit 420, a bus 430 connecting various electronic device components (including the storage unit 420 and the processing unit 410), a display unit 440, and the like.

[0161] The storage unit 420 stores a computer-readable program, which may be a source program or a read-only program. The program may be executed by the processing unit 410, causing the processing unit 410 to perform the steps of various embodiments of the present invention. For example, the processing unit 410 may perform the steps shown in FIG1 .

[0162] The storage unit 420 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 4201 and / or a cache memory unit 4202, and may further include a read-only memory unit (ROM) 4203. The storage unit 420 may also include a program / utility 4204 having a set (at least one) of program modules 4205. Such program modules 4205 include, but are not limited to, operating the electronic device, one or more application programs, other program modules, and program data. Each of these examples or some combination thereof may include the implementation of a network environment.

[0163] Bus 430 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0164] The electronic device 400 can also communicate with one or more external devices 300 (e.g., a keyboard, display, network device, Bluetooth device, etc.), allowing a user to interact with the electronic device 400 via these external devices 400 and / or enabling the electronic device 400 to communicate with one or more other data processing devices (e.g., a router, modem, etc.). This communication can occur via an input / output (I / O) interface 450, or via a network adapter 460 with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet). The network adapter 460 can communicate with other modules of the electronic device 400 via the bus 430. It should be understood that, although not shown in FIG. 4 , other hardware and / or software modules may be used in the electronic device 400, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID electronics, tape drives, and data backup storage electronics.

[0165] FIG5 is a schematic diagram of an embodiment of a computer-readable medium of the present invention. As shown in FIG5 , the computer program can be stored on one or more computer-readable media. The computer-readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electronic device, device, or component that is electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. When the computer program is executed by one or more data processing devices, the computer-readable medium is enabled to implement the above-mentioned method of the present invention, namely: dividing the laboratory into multiple operation unit areas, and creating a corresponding management shell for each operation unit area to perform experimental control and data collection; converting the current experimental process into experimental tasks and experimental operations, and mapping the collected data to the corresponding experimental objects; the experimental objects include experimental tasks and / or experimental operations; creating and training a prediction model, and inputting the data mapped to the experimental objects into the prediction model to monitor the status of the current experiment; optimizing the current experimental process according to the results of the current experimental process and the data mapped to the experimental objects.

[0166] From the above description of the embodiments, those skilled in the art will readily appreciate that the exemplary embodiments described herein can be implemented via software or via a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored on a computer-readable storage medium (such as a CD-ROM, USB flash drive, or portable hard drive) or on a network and includes instructions for causing a data processing device (such as a personal computer, server, or network device) to execute the above-described methods according to the present invention.

[0167] The computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction-executing electronic device, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0168] Program code for performing the operations of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0169] In summary, the present invention can be implemented by a method, apparatus, electronic device, or computer-readable medium that executes a computer program. In practice, a general-purpose data processing device such as a microprocessor or digital signal processor (DSP) can be used to implement some or all of the functions of the present invention.

[0170] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the present invention is not inherently related to any specific computer, virtual device, or electronic device, and various general-purpose devices can also implement the present invention. The above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. A chemical experiment monitoring optimization method based on digital twin, characterized in that: The method comprises: Divide the laboratory into multiple operation unit areas, and create a corresponding management shell for each operation unit area to perform experimental control and data collection; Convert the current experimental process into experimental tasks and experimental operations, and map the collected data to corresponding experimental objects; the experimental objects include experimental tasks and / or experimental operations; Creating and training a prediction model, and inputting data mapped to the experimental object into the prediction model to monitor the status of the current experiment; Optimize the current experimental process based on the results of the current experimental process and the data mapped to the experimental object.

2. The method according to claim 1, characterized in that Mapping the collected data to the corresponding experimental object includes: Create a mapping relationship between each instrument and experimental object in the operation unit area; The data collected from each operation unit area is mapped to the corresponding experimental object according to the mapping relationship.

3. The method according to claim 1, characterized in that The experimental object is an experimental task, and the experimental task includes a reaction, and the data mapped to the experimental object is a reaction formula, then a first model is created and trained, and the reaction formula is input into the first model to predict and monitor the feasible probability of the current reaction; The experimental object is an experimental operation, and the data mapped to the experimental object is a time series of experimental operation parameters, then a second model is created and trained, and the time series of experimental operation parameters is input into the second model to predict and monitor the probability of abnormality of the current experimental task; The experimental object is an experimental operation, and the data mapped to the experimental object does not include the time series of the experimental operation parameters; the execution result of the current experimental task is predicted by the distribution of the historical execution results of the experimental operation.

4. The method according to claim 1, characterized in that: Optimizing the current experimental process according to the results of the current experimental process and the data mapped to the experimental object includes: Determine the results of the current experimental process and the parameters mapped to the experimental operation, adjust the parameters of the experimental process and / or experimental operation according to the preset reaction parameters and process optimization algorithm, and obtain the adjusted experimental process execution results; Alternatively, the result of the current experimental process and the data mapped to the experimental operation are determined, and the experimental operation is adjusted according to the analysis result of the current experimental process result and the experimental operation data.

5. The method according to claim 4, characterized in that The adjusting of the experimental operation according to the analysis result of the current experimental process result and the experimental operation data includes: Analyze the causal relationship between the current experimental process results and the data mapped to the experimental operation, and make the first adjustment to the experimental operation; And / or, compare multiple execution results of the same experimental operation in multiple experimental processes, and perform a second adjustment on the experimental operation according to the execution results.

6. The method according to claim 5, characterized in that The method further comprises: After the first adjustment and the second adjustment are made to the experimental operation, the experimental operation before the adjustment and the experimental operation after the adjustment are respectively executed multiple times, and the execution data are analyzed to verify the adjustment efficiency.

7. The method according to claim 1, characterized in that The method further comprises: The business indicators of the current experimental process are analyzed in real time according to the data mapped to the experimental object; the business indicators include: at least one of the experimental efficiency, manual load, and automation rate.

8. The method according to claim 7, characterized in that The method further comprises: Collect the time distribution of the same type of experimental tasks during execution; The execution time of the current experimental process is predicted according to the time consumption distribution.

9. The method according to claim 8, characterized in that The method further comprises: The monitoring results of the current experimental process, the business indicators of the current experimental process, and the execution time of the current experimental process are sent to the user.

10. The method according to claim 8, characterized in that The method further comprises: Simulate and demonstrate the execution effect before and after the experimental process is optimized; Receive the experimental support conditions input by the user, and search for a target experimental process that matches the experimental support conditions according to the business indicators and execution time of each experimental process; The experimental expansion conditions input by the user are received, and the experimental support conditions matching the experimental expansion conditions are searched according to the business indicators of each experimental process.

11. A chemical experiment monitoring and optimization device based on digital twin, characterized in that: The device comprises: The acquisition module is used to divide the laboratory into multiple operation unit areas and create a corresponding management shell for each operation unit area to perform experimental control and data acquisition; A mapping module, used to convert the current experimental process into experimental tasks and experimental operations, and map the collected data to corresponding experimental objects; the experimental objects include experimental tasks and / or experimental operations; A monitoring module, used to create and train a prediction model, input data mapped to the experimental object into the prediction model to monitor the status of the current experiment; The optimization module is used to optimize the current experimental process according to the results of the current experimental process and the data mapped to the experimental object.

12. An electronic device comprising: processor; as well as A memory storing computer executable instructions which, when executed, cause the processor to perform a method according to any one of claims 1-10.

13. A computer-readable storage medium, wherein: The computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images