An ethanol production concentration online monitoring method, device and system

Abstract

The application relates to the technical field of ethanol production, and discloses an ethanol production concentration online monitoring method, device and system. The method collects historical data in an ethanol production process, and forms a feature data set after pretreatment. Based on the data set, an ethanol concentration prediction model is constructed, and a deep learning algorithm is used to predict a future concentration change trend. Production state data and environmental condition data are acquired in real time, input into the prediction model to obtain a predicted concentration value. The concentration value is detected in real time by combining sensors on an ethanol production line, the two are compared and analyzed, whether there is a deviation is judged by a preset concentration deviation threshold value, and a deviation point is recorded. According to the number of deviation points, the deviation value and a preset evaluation rule, the concentration control state is evaluated, an alarm mechanism is triggered if an abnormality is found, and evaluation results and alarm information are sent to relevant personnel in a timely manner. The application improves the intelligent level of concentration monitoring in the ethanol production process, and helps to find and prevent potential problems in advance.

Description

Technical Field

[0001] This invention relates to the field of ethanol production technology, specifically to a method, apparatus, and system for online monitoring of ethanol production concentration. Background Technology

[0002] In the ethanol production process, concentration monitoring and control are crucial, directly affecting product quality and production efficiency. Currently, the ethanol production industry widely uses various sensors and monitoring equipment to detect ethanol concentration in real time during production.

[0003] Currently, traditional ethanol concentration monitoring methods mainly rely on real-time concentration data fed back by sensors. While these methods can provide real-time concentration information during the production process, they often remain at the level of simple data collection and display, lacking in-depth data analysis and mining. Production personnel can only manually determine whether the concentration is within the normal range by observing real-time data. This method is not only inefficient but also highly susceptible to human factors and prone to misjudgment.

[0004] Most existing monitoring methods cannot automatically analyze historical and real-time data to predict future trends in ethanol concentration. This means that production personnel cannot anticipate potential concentration anomalies and therefore cannot take timely measures to adjust and optimize the production process. Consequently, production personnel often have to react passively after problems occur, rather than proactively preventing them from happening. Summary of the Invention

[0005] The purpose of this invention is to provide a method, apparatus, and system for online monitoring of ethanol production concentration, so as to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for online monitoring of ethanol production concentration, the method comprising:

[0007] S1: Collect historical concentration data, related production parameters, and environmental conditions during the ethanol production process; the concentration data includes ethanol concentration values ​​at different time points; the production parameters include raw material type, raw material ratio, reaction temperature, reaction pressure, catalyst type, and reaction time; the environmental conditions include the temperature, humidity, and air pressure of the production environment.

[0008] S2: Preprocess the data collected in S1, including data cleaning, data alignment and missing value handling, to form a complete feature dataset;

[0009] S3: Based on the feature dataset, construct an ethanol concentration prediction model; this model combines production parameters and environmental conditions, and uses machine learning or deep learning algorithms to predict the concentration change trend of ethanol in the future over a period of time during the ethanol production process.

[0010] S4: Real-time acquisition of production status data and environmental condition data during the current ethanol production process;

[0011] S5: Input the data obtained in S4 into the ethanol concentration prediction model and receive the predicted ethanol concentration value output by the model;

[0012] S6: Install an ethanol concentration sensor on the ethanol production line to detect the ethanol concentration in real time and obtain the actual ethanol concentration value output by the sensor; clean the raw detection data to remove outliers and noise interference;

[0013] S7: Plot the real-time ethanol concentration value obtained in S6 and the predicted ethanol concentration value output by the model in S5 as curves that change over time. Align the two curves with timestamps and compare them in the same coordinate system.

[0014] S8: Based on the preset concentration deviation threshold, determine whether there is a deviation exceeding the threshold at each point on the two curves; if there is a deviation exceeding the threshold, mark the point as a deviation point and record the deviation value and deviation time.

[0015] S9: Evaluate the concentration control status in the ethanol production process based on the number of deviation points, deviation values, and preset evaluation rules; if the evaluation results indicate that there is an abnormality in concentration control, trigger the alarm mechanism and send the evaluation results and alarm information to relevant personnel.

[0016] Preferably, in step S2, the collected ethanol concentration data, production parameters, and environmental condition data are cleaned to remove duplicate data, erroneous data, and abnormal data; the erroneous data includes data errors caused by equipment failure, data transmission errors, or human error; the abnormal data includes extreme data that exceeds the preset range or does not conform to production patterns.

[0017] Preferably, in step S2, the data alignment is achieved by: performing time alignment on the cleaned data; and using interpolation or resampling techniques to align data collected at different frequencies.

[0018] Preferably, the ethanol concentration prediction model is trained using the Long Short-Term Memory (LSTM) network algorithm, and the steps include:

[0019] Step 1: Divide the S2 preprocessed feature dataset into training set, validation set and test set; the feature dataset includes time series ethanol concentration values, numerical representations of production parameters, and numerical values ​​of environmental conditions; perform one-hot encoding on the categorical variables in the production parameters;

[0020] Step 2: Construct a Long Short-Term Memory (LSTM) network model, including an input layer, an LSTM layer, a fully connected layer, and an output layer. The input layer receives preprocessed feature data. The LSTM layer consists of multiple LSTM units, each containing a forget gate, an input gate, and an output gate. These three gating mechanisms control the flow and retention of information. The fully connected layer maps the output of the LSTM layer to the prediction target. The output layer outputs the predicted ethanol concentration value.

[0021] Step 3: Train the LSTM model using the training set, minimizing the loss function through backpropagation and optimization algorithms; the loss function measures the difference between the model's predicted values ​​and the actual values; during training, monitor the model's performance using the validation set to prevent overfitting; use early stopping to terminate training, stopping when the loss on the validation set no longer decreases;

[0022] Step 4: Optimize the hyperparameters of the LSTM model using a grid search method, including the number of LSTM layers, the number of neurons in each layer, the learning rate, and the batch size;

[0023] Step 5: Evaluate the performance of the trained LSTM model on the test set and calculate the error index between the predicted and actual values;

[0024] Step 6: Deploy the trained LSTM model onto the ethanol production line.

[0025] Preferably, a two-layer LSTM design is used, with each layer containing 128 LSTM units; the first LSTM layer receives the output of the input layer, and the second LSTM layer receives the output of the first LSTM layer. A dropout layer is added between the two LSTM layers, with the dropout rate set to 0.2.

[0026] Preferably, in step 5, the mean squared error (MSE) is used as the evaluation index to calculate the average of the squared errors between the model's predicted values ​​and the actual values; the formula for calculating MSE is as follows:

[0027]

[0028] Where n is the number of samples in the test set, y i This is the actual ethanol concentration value of the i-th sample. It is the ethanol concentration value predicted by the model for the i-th sample;

[0029] The predictive performance of the LSTM model is evaluated based on the calculated MSE value; the smaller the MSE value, the more accurate the model's prediction and the smaller the deviation between the predicted value and the actual value.

[0030] Preferably, in step S8, the method for judging the ethanol concentration deviation is as follows:

[0031] Set a concentration deviation threshold: Based on the actual needs of the ethanol production process and historical data, set a reasonable concentration deviation threshold. This threshold is used to determine whether the difference between the predicted concentration value and the actual concentration value is acceptable.

[0032] Deviation calculation: For each time point, calculate the absolute deviation between the predicted concentration value and the actual concentration value; the calculation formula is: Deviation value = |Predicted concentration value - Actual concentration value|;

[0033] Deviation point determination: The calculated deviation value is compared with the concentration deviation threshold. If the deviation value is greater than or equal to the concentration deviation threshold, the point is marked as a deviation point, and the deviation value and deviation time are recorded.

[0034] Preferably, in step S9, the ethanol concentration assessment and alarm mechanism is designed as follows:

[0035] The number of deviations found within a certain period of time is counted, and the average or maximum deviation value of all deviations is calculated.

[0036] Based on the actual requirements of the ethanol production process, evaluation rules are set, including setting a condition that concentration control is considered abnormal when the number of deviation points exceeds a certain number or the average deviation value exceeds a certain threshold.

[0037] Based on the number and value of deviations, and the established evaluation rules, the concentration control status in the ethanol production process is determined. When the evaluation results indicate that there is an abnormality in concentration control, an alarm mechanism is triggered.

[0038] Preferably, an online monitoring system for ethanol production concentration includes:

[0039] The data acquisition module is used to execute step S1, collecting historical concentration data and related production parameters and environmental conditions during the ethanol production process. The concentration data includes ethanol concentration values ​​at different time points. The production parameters include raw material type, raw material ratio, reaction temperature, reaction pressure, catalyst type and reaction time. The environmental conditions include the temperature, humidity and air pressure of the production environment.

[0040] The data preprocessing module, connected to the data acquisition module, is used to execute step S2 to preprocess the data collected by the data acquisition module, including data cleaning, data alignment, and missing value handling, to form a complete feature dataset.

[0041] The model building module, connected to the data preprocessing module, is used to execute step S3. Based on the feature dataset, it builds an ethanol concentration prediction model. This model combines production parameters and environmental conditions and uses machine learning or deep learning algorithms to predict the concentration change trend of ethanol in the future over a period of time.

[0042] The real-time data acquisition module is used to execute step S4 to acquire real-time production status data and environmental condition data during the current ethanol production process.

[0043] The prediction module, connected to the model building module and the real-time data acquisition module, is used to execute step S5, inputting the data acquired by the real-time data acquisition module into the ethanol concentration prediction model and receiving the predicted ethanol concentration value output by the model.

[0044] The sensor module is installed on the ethanol production line to perform the first half of step S6, detect the ethanol concentration in real time, and obtain the actual ethanol concentration value output by the sensor.

[0045] The data cleaning module, connected to the sensor module, is used to perform the latter part of step S6, cleaning the raw detection data output by the sensor module to remove outliers and noise interference.

[0046] The comparison module, connected to the prediction module and the data cleaning module, is used to execute steps S7 and S8. It plots the real-time ethanol concentration value obtained by the data cleaning module and the predicted ethanol concentration value output by the prediction module as curves that change over time. It aligns the two curves with timestamps and compares them in the same coordinate system. Based on the preset concentration deviation threshold, it determines whether there is a deviation exceeding the threshold at each point on the two curves. If there is a deviation exceeding the threshold, the point is marked as a deviation point, and the deviation value and deviation time are recorded.

[0047] The assessment and alarm module, connected to the comparison module, is used to execute step S9. Based on the number of deviation points and deviation values ​​found by the comparison module and the preset assessment rules, it assesses the concentration control status in the ethanol production process. If the assessment results indicate that there is an abnormality in concentration control, the alarm mechanism is triggered, and the assessment results and alarm information are sent to relevant personnel.

[0048] Preferably, an online monitoring device for ethanol production concentration includes ethanol production equipment integrating the above-mentioned online monitoring system for ethanol production concentration.

[0049] Compared with the prior art, the beneficial effects of the present invention are:

[0050] This invention constructs an ethanol concentration prediction model using the Long Short-Term Memory (LSTM) algorithm. This model can intelligently predict the future trend of ethanol concentration changes over a period of time by combining production parameters and environmental conditions. This allows production personnel to be aware of potential concentration anomalies in advance, enabling them to take timely measures to adjust and optimize the production process, effectively preventing problems and improving production efficiency.

[0051] Enhancing the initiative and accuracy of concentration control: By comparing and analyzing the real-time detected ethanol concentration value with the predicted value, this invention can detect and mark deviation points in real time, record the deviation value and deviation time, which not only improves the accuracy of concentration control, but also enables production personnel to proactively respond to concentration changes and reduce product quality problems caused by concentration fluctuations.

[0052] Provides scientific assessment and decision support: Based on the number of deviation points, deviation values, and preset assessment rules, this invention can scientifically assess the concentration control status in the ethanol production process. Attached Figure Description

[0053] Figure 1 This is a flowchart illustrating the steps of an online monitoring method for ethanol production concentration according to the present invention.

[0054] Figure 2 The training flowchart for the ethanol concentration prediction model;

[0055] Figure 3 This is a schematic diagram of the design of an ethanol concentration deviation judgment, evaluation, and alarm mechanism. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] Please see Figure 1-3 This invention provides a method for online monitoring of ethanol production concentration, the method comprising:

[0058] S1: Collect historical concentration data, as well as relevant production parameters and environmental conditions, during the ethanol production process. Specifically, the concentration data includes ethanol concentration values ​​at different time points, the production parameters cover the type and proportion of raw materials, reaction temperature, reaction pressure, catalyst type, and reaction time, and the environmental conditions include the temperature, humidity, and air pressure of the production environment.

[0059] S2: Preprocess the data collected in S1. The preprocessing process includes removing duplicate data, erroneous data, and abnormal data; erroneous data includes data errors caused by equipment failure, data transmission errors, or human error; abnormal data includes extreme data that exceeds the preset range or does not conform to production patterns; data alignment to ensure the consistency of data from different sources over time; and missing value handling, which involves reasonably filling in or interpolating missing data to form a complete feature dataset.

[0060] The data alignment is achieved by aligning the cleaned data by time. For data collected at different frequencies, interpolation methods or resampling techniques are used for alignment.

[0061] S3: Based on the preprocessed feature dataset, an ethanol concentration prediction model is constructed. This model combines production parameters and environmental conditions, utilizing deep learning algorithms (such as Long Short-Term Memory networks) to predict the concentration change trend of ethanol over a future period during the production process. The model construction process includes steps such as data partitioning, feature selection, model training, and parameter optimization to ensure the accuracy and stability of the model.

[0062] S4: Real-time acquisition of production status and environmental condition data during the current ethanol production process. This data is also collected in real time through sensors and monitoring equipment and input into the ethanol concentration prediction model.

[0063] S5: Input the real-time acquired data into the ethanol concentration prediction model and receive the predicted ethanol concentration value output by the model. This predicted value represents the model's prediction of the ethanol concentration over a future period.

[0064] S6: Install an ethanol concentration sensor on the ethanol production line to detect the ethanol concentration in real time and obtain the actual ethanol concentration value output by the sensor. Clean the raw detection data to remove outliers and noise interference to ensure data accuracy.

[0065] S7: Plot the real-time ethanol concentration value and the model-predicted ethanol concentration value as curves over time, and align the timestamps. Compare the two curves in the same coordinate system to visually observe the difference between the actual and predicted concentrations.

[0066] S8: Based on the preset concentration deviation threshold, determine whether there is a deviation exceeding the threshold at each point on the two curves. If a deviation exceeding the threshold exists, mark the point as a deviation point and record the deviation value and deviation time. This helps to promptly detect abnormalities in concentration control.

[0067] S9: Based on the number of detected deviations, their values, and the preset evaluation rules, assess the concentration control status during ethanol production. If the assessment results indicate an anomaly in concentration control, an alarm mechanism is triggered, sending the assessment results and alarm information to relevant personnel. These personnel can then take timely measures to adjust and optimize the process, thereby ensuring the stability of the ethanol production process and product quality.

[0068] The present invention will be further described below with reference to Examples 1 to 3:

[0069] Example 1:

[0070] See appendix Figure 2 This embodiment describes a specific implementation of training an ethanol concentration prediction model using the Long Short-Term Memory (LSTM) network algorithm. The detailed steps are as follows:

[0071] Step 1: Divide the S2 preprocessed feature dataset into a training set (70%), a validation set (15%), and a test set (15%) according to the time series. The feature dataset contains time series ethanol concentration values, numerical representations of production parameters (such as temperature, pressure, etc.), and numerical values ​​of environmental conditions (such as humidity, temperature, etc.).

[0072] For categorical variables in production parameters (such as raw material type, catalyst type, etc.), one-hot encoding is used to process them and convert them into numerical representations.

[0073] Step 2: Construct a two-layer LSTM network model. The model includes an input layer, two LSTM layers, a fully connected layer, and an output layer.

[0074] The input layer receives preprocessed feature data, with the data dimensions being (time step, number of features).

[0075] The first LSTM layer contains 128 LSTM units, receiving the output from the input layer. The internal structure of each LSTM unit includes a forget gate, an input gate, and an output gate. These three gating mechanisms control the flow and retention of information. The forget gate determines the degree to which old information is retained, the input gate determines the degree to which new information is added, and the output gate determines the output information based on the current cell state. The LSTM unit is computed as follows:

[0076] Forgotten Gate: f t =σ(W f ·[h t-1 ,x t ]+b f );

[0077] Input gate: i t =σ(W i ·[h t-1 ,x t ]+b i );

[0078] Output gate: o t =σ(W o ·[h t-1 ,x t ]+b o );

[0079] Where W and b represent the weight matrix and bias term, respectively, and σ represents the sigmoid activation function.

[0080] A dropout layer is added after the first LSTM layer, with a dropout rate set to 0.2 to prevent overfitting.

[0081] The second LSTM layer also contains 128 LSTM units, receiving the output of the first LSTM layer.

[0082] The fully connected layer is used to map the output of the second LSTM layer onto the prediction target, namely the ethanol concentration value.

[0083] The output layer outputs the predicted ethanol concentration value using a linear activation function.

[0084] Step 3: Train the LSTM model using the training set, minimizing the loss function through backpropagation and optimization algorithms (such as the Adam optimizer). The loss function uses mean squared error (MSE) to measure the difference between the model's predictions and the actual values. The formula for calculating MSE is as follows:

[0085]

[0086] Where n is the number of samples in the test set, y i This is the actual ethanol concentration value of the i-th sample. It is the ethanol concentration value predicted by the model for the i-th sample.

[0087] The predictive performance of the LSTM model is evaluated based on the calculated MSE value; the smaller the MSE value, the more accurate the model's prediction and the smaller the deviation between the predicted value and the actual value.

[0088] During training, the model's performance is monitored using a validation set to prevent overfitting. Early stopping is employed to terminate training when the loss on the validation set no longer decreases.

[0089] Step 4: Optimize the hyperparameters of the LSTM model using a grid search method, including the number of LSTM layers (fixed to 2 layers), the number of neurons per layer (fixed to 128), the learning rate (e.g., 0.001, 0.0001, etc.), and the batch size (e.g., 32, 64, etc.).

[0090] During the grid search process, each hyperparameter combination is trained and its performance is evaluated on the validation set. The hyperparameter combination with the best performance is then selected.

[0091] Step 5: Evaluate the performance of the trained LSTM model on the test set and calculate error metrics between the predicted and actual values, such as accuracy and F1 score.

[0092] Error metrics are used to evaluate the model's predictive accuracy and generalization ability.

[0093] Step 6: Deploy the trained LSTM model to the ethanol production line, receive production data in real time, and output the predicted ethanol concentration value.

[0094] Based on the predicted ethanol concentration, production parameters are adjusted to optimize the ethanol production process.

[0095] Example 2:

[0096] See appendix Figure 3 In the specific implementation of the online monitoring method for ethanol production concentration, this embodiment is used to describe in detail the implementation method of the deviation judgment and evaluation mechanism:

[0097] ① The implementation methods of the deviation judgment mechanism include:

[0098] Set a concentration deviation threshold: Based on historical data and ethanol production requirements, set a concentration deviation threshold of 5% (that is, a difference of more than 5% between the predicted concentration value and the actual concentration value is considered a deviation).

[0099] Deviation calculation: For each time point, the system calculates the absolute deviation between the predicted concentration value and the actual concentration value. For example, at a certain time point, if the predicted concentration is 70% and the actual concentration is 65%, then the deviation value is |70% - 65%| = 5%.

[0100] Deviation point judgment: The system compares the calculated deviation value with the concentration deviation threshold. If the deviation value is greater than or equal to 5%, the system marks the point as a deviation point and records the specific deviation value and deviation time.

[0101] ②The assessment and alarm mechanism can be implemented in the following ways:

[0102] Deviation statistics: The system counts the number of deviations found within a production cycle (e.g., 24 hours). For example, the system found a total of 8 deviations within a certain production cycle.

[0103] Deviation analysis: The system calculates the average deviation value of all deviation points. For example, if the deviation values ​​of 8 deviation points are 5%, 6%, 7%, 5.5%, 4.8%, 5.2%, 6.1%, and 5.9%, then the average deviation value is (5+6+...+5.9) / 8 = 5.6875%.

[0104] Evaluation rule setting: Based on production requirements, the evaluation rule is set as follows: when the number of deviation points exceeds 5 or the average deviation value exceeds 5%, the concentration control is considered abnormal.

[0105] Evaluation Result Judgment: The system determines the concentration control status based on the number of deviation points, the average deviation value, and the set evaluation rules. In this example, since the number of deviation points is 8 (greater than 5) and the average deviation value is 5.6875% (greater than 5%), the system determines that the concentration control is abnormal.

[0106] Alarm mechanism triggering: When the system detects an anomaly in concentration control, the alarm mechanism is triggered. The alarm mechanism includes: sending an alarm SMS to the production supervisor, notifying the technical department via email, and displaying a red alarm indicator on the monitoring interface.

[0107] Assessment Report Generation: The system automatically generates an assessment report, which includes assessment results, alarm information, specific concentration data, and deviation information (including deviation time and deviation value). The assessment report is saved in PDF format and can be downloaded or printed through the system interface.

[0108] Example 3:

[0109] This embodiment describes an online monitoring system for ethanol production concentration and its implementation apparatus. The system includes the following main modules:

[0110] Data Acquisition Module: This module is responsible for collecting historical concentration data, as well as relevant production parameters and environmental conditions, during the ethanol production process. Concentration data includes ethanol concentration values ​​at different time points. Production parameters cover raw material type, raw material ratio, reaction temperature, reaction pressure, catalyst type, and reaction time. Environmental conditions include the temperature, humidity, and air pressure of the production environment. This data provides the foundation for subsequent data analysis and model building.

[0111] Data preprocessing module: Connected to the data acquisition module, this module preprocesses the collected data, including data cleaning (removing erroneous and invalid data), data alignment (ensuring consistency of timestamps for each data point), and missing value handling (filling in or estimating missing data), ultimately forming a complete feature dataset to provide high-quality data input for subsequent model building.

[0112] Model Building Module: Based on the preprocessed feature dataset, this module uses machine learning or deep learning algorithms to build an ethanol concentration prediction model. This model, combining production parameters and environmental conditions, can predict the concentration trend of ethanol over a future period, providing a scientific basis for production decisions.

[0113] Real-time data acquisition module: This module acquires real-time production status data and environmental condition data during the current ethanol production process, including but not limited to real-time parameters such as raw material flow rate, reaction temperature, and pressure, as well as information such as ambient temperature and humidity, to provide data support for real-time prediction.

[0114] Prediction Module: This module inputs data acquired by the real-time data acquisition module into the ethanol concentration prediction model, which then outputs predicted ethanol concentration values. These predictions reflect the expected changes in ethanol concentration over a future period under current production conditions.

[0115] Sensor module: Installed on the ethanol production line, it monitors ethanol concentration in real time and outputs the actual ethanol concentration value. This data is crucial for verifying the accuracy of the predictive model and monitoring production status.

[0116] Data cleaning module: Cleans the raw detection data output by the sensor module, removing outliers and noise interference to ensure the accuracy and reliability of the data.

[0117] Comparison Module: This module plots the real-time ethanol concentration value obtained by the data cleaning module and the predicted ethanol concentration value output by the prediction module as curves over time, and aligns them with timestamps. The two curves are compared in the same coordinate system, and based on a preset concentration deviation threshold, it determines whether each point has a deviation exceeding the threshold. If a deviation exceeding the threshold exists, it is marked as a deviation point, and the deviation value and deviation time are recorded.

[0118] Assessment and Alarm Module: Based on the number and value of deviations detected by the comparison module and the preset assessment rules, the module assesses the concentration control status during ethanol production. If the assessment results indicate an abnormality in concentration control, an alarm mechanism is triggered, sending the assessment results and alarm information to relevant personnel so that timely measures can be taken to adjust production conditions or troubleshoot the problem.

[0119] Regarding the implementation device, this embodiment provides an online monitoring device for ethanol production concentration. This device integrates the aforementioned online monitoring system for ethanol production concentration and is applied to ethanol production equipment. Through this device, real-time monitoring and prediction of ethanol production concentration can be achieved, improving the controllability and stability of the production process, thereby enhancing production efficiency and product quality.

[0120] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0121] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for online monitoring of ethanol production concentration, characterized in that, The method includes: S1: Collect historical concentration data, related production parameters, and environmental conditions during the ethanol production process; the concentration data includes ethanol concentration values ​​at different time points; the production parameters include raw material type, raw material ratio, reaction temperature, reaction pressure, catalyst type, and reaction time; the environmental conditions include the temperature, humidity, and air pressure of the production environment. S2: Preprocess the data collected in S1, including data cleaning, data alignment and missing value handling, to form a complete feature dataset; S3: Based on the feature dataset, construct an ethanol concentration prediction model; this model combines production parameters and environmental conditions, and uses machine learning or deep learning algorithms to predict the concentration change trend of ethanol in the future over a period of time during the ethanol production process. S4: Real-time acquisition of production status data and environmental condition data during the current ethanol production process; S5: Input the data obtained in S4 into the ethanol concentration prediction model and receive the predicted ethanol concentration value output by the model; S6: Install an ethanol concentration sensor on the ethanol production line to detect the ethanol concentration in real time and obtain the actual ethanol concentration value output by the sensor; clean the raw detection data to remove outliers and noise interference; S7: Plot the real-time ethanol concentration value obtained in S6 and the predicted ethanol concentration value output by the model in S5 as curves that change over time. Align the two curves with timestamps and compare them in the same coordinate system. S8: Based on the preset concentration deviation threshold, determine whether there is a deviation exceeding the threshold at each point on the two curves; if there is a deviation exceeding the threshold, mark the point as a deviation point and record the deviation value and deviation time. S9: Evaluate the concentration control status in the ethanol production process based on the number of deviation points, deviation values, and preset evaluation rules; if the evaluation results indicate that there is an abnormality in concentration control, trigger the alarm mechanism and send the evaluation results and alarm information to relevant personnel.

2. The method for online monitoring of ethanol production concentration according to claim 1, characterized in that: In step S2, the collected ethanol concentration data, production parameters, and environmental condition data are cleaned to remove duplicate data, erroneous data, and abnormal data. Erroneous data includes data errors caused by equipment failure, data transmission errors, or human error. Abnormal data includes extreme data that exceeds the preset range or does not conform to production patterns.

3. The method for online monitoring of ethanol production concentration according to claim 2, characterized in that, In step S2, the data alignment is achieved by aligning the cleaned data by time. For data collected at different frequencies, interpolation or resampling techniques are used for alignment.

4. The method for online monitoring of ethanol production concentration according to claim 1, characterized in that, The steps for training an ethanol concentration prediction model using the Long Short-Term Memory (LSTM) network algorithm include: Step 1: Divide the S2 preprocessed feature dataset into training set, validation set and test set; the feature dataset includes time series ethanol concentration values, numerical representations of production parameters, and numerical values ​​of environmental conditions; perform one-hot encoding on the categorical variables in the production parameters; Step 2: Construct a Long Short-Term Memory (LSTM) network model, including an input layer, an LSTM layer, a fully connected layer, and an output layer. The input layer receives preprocessed feature data. The LSTM layer consists of multiple LSTM units, each containing a forget gate, an input gate, and an output gate. These three gating mechanisms control the flow and retention of information. The fully connected layer maps the output of the LSTM layer to the prediction target. The output layer outputs the predicted ethanol concentration value. Step 3: Train the LSTM model using the training set, minimizing the loss function through backpropagation and optimization algorithms; the loss function measures the difference between the model's predicted values ​​and the actual values; during training, monitor the model's performance using the validation set to prevent overfitting; use early stopping to terminate training, stopping when the loss on the validation set no longer decreases; Step 4: Optimize the hyperparameters of the LSTM model using a grid search method, including the number of LSTM layers, the number of neurons in each layer, the learning rate, and the batch size; Step 5: Evaluate the performance of the trained LSTM model on the test set and calculate the error index between the predicted and actual values; Step 6: Deploy the trained LSTM model onto the ethanol production line.

5. The method for online monitoring of ethanol production concentration according to claim 4, characterized in that: The design incorporates two LSTM layers, each containing 128 LSTM units. The first LSTM layer receives the output from the input layer, and the second LSTM layer receives the output from the first LSTM layer. A dropout layer is added between the two LSTM layers, with a dropout rate of 0.

2.

6. The method for online monitoring of ethanol production concentration according to claim 4, characterized in that: In step 5, the mean squared error (MSE) is used as an evaluation index to calculate the average of the squared errors between the model's predicted values ​​and the actual values; the formula for calculating MSE is as follows: Where n is the number of samples in the test set, y i This is the actual ethanol concentration value of the i-th sample. It is the ethanol concentration value predicted by the model for the i-th sample; The predictive performance of the LSTM model is evaluated based on the calculated MSE value; the smaller the MSE value, the more accurate the model's prediction and the smaller the deviation between the predicted value and the actual value.

7. The method for online monitoring of ethanol production concentration according to claim 1, characterized in that, In step S8, the method for judging the ethanol concentration deviation is as follows: Set a concentration deviation threshold: Based on the actual needs of the ethanol production process and historical data, set a reasonable concentration deviation threshold. This threshold is used to determine whether the difference between the predicted concentration value and the actual concentration value is acceptable. Deviation calculation: For each time point, calculate the absolute deviation between the predicted concentration value and the actual concentration value; the calculation formula is: Deviation value = |Predicted concentration value - Actual concentration value|; Deviation point judgment: Compare the calculated deviation value with the concentration deviation threshold. If the deviation value is greater than or equal to the concentration deviation threshold, mark the point as a deviation point and record the deviation value and deviation time.

8. The method for online monitoring of ethanol production concentration according to claim 1, characterized in that: In S9, the ethanol concentration assessment and alarm mechanism is designed as follows: Count the number of deviations found within a certain period of time, and calculate the average or maximum deviation value of all deviations. Based on the actual requirements of the ethanol production process, evaluation rules are set, including setting a condition that concentration control is considered abnormal when the number of deviation points exceeds a certain number or the average deviation value exceeds a certain threshold. Based on the number and value of deviations, and the established evaluation rules, the concentration control status in the ethanol production process is determined. When the evaluation results indicate that there is an abnormality in concentration control, an alarm mechanism is triggered.

9. An online monitoring system for ethanol production concentration, characterized in that, The system includes: The data acquisition module is used to execute step S1, collecting historical concentration data and related production parameters and environmental conditions during the ethanol production process. The concentration data includes ethanol concentration values ​​at different time points. The production parameters include raw material type, raw material ratio, reaction temperature, reaction pressure, catalyst type and reaction time. The environmental conditions include the temperature, humidity and air pressure of the production environment. The data preprocessing module, connected to the data acquisition module, is used to execute step S2 to preprocess the data collected by the data acquisition module, including data cleaning, data alignment, and missing value handling, to form a complete feature dataset. The model building module, connected to the data preprocessing module, is used to execute step S3. Based on the feature dataset, it builds an ethanol concentration prediction model. This model combines production parameters and environmental conditions and uses machine learning or deep learning algorithms to predict the concentration change trend of ethanol in the future over a period of time. The real-time data acquisition module is used to execute step S4 to acquire real-time production status data and environmental condition data during the current ethanol production process. The prediction module, connected to the model building module and the real-time data acquisition module, is used to execute step S5, inputting the data acquired by the real-time data acquisition module into the ethanol concentration prediction model and receiving the predicted ethanol concentration value output by the model. The sensor module is installed on the ethanol production line to perform the first half of step S6, detect the ethanol concentration in real time, and obtain the actual ethanol concentration value output by the sensor. The data cleaning module, connected to the sensor module, is used to perform the latter part of step S6, cleaning the raw detection data output by the sensor module to remove outliers and noise interference. The comparison module, connected to the prediction module and the data cleaning module, is used to execute steps S7 and S8. It plots the real-time ethanol concentration value obtained by the data cleaning module and the predicted ethanol concentration value output by the prediction module as curves that change over time. It aligns the two curves with timestamps and compares them in the same coordinate system. Based on the preset concentration deviation threshold, it determines whether there is a deviation exceeding the threshold at each point on the two curves. If there is a deviation exceeding the threshold, the point is marked as a deviation point, and the deviation value and deviation time are recorded. The assessment and alarm module, connected to the comparison module, is used to execute step S9. Based on the number of deviation points and deviation values ​​found by the comparison module and the preset assessment rules, it assesses the concentration control status in the ethanol production process. If the assessment results indicate that there is an abnormality in concentration control, the alarm mechanism is triggered, and the assessment results and alarm information are sent to relevant personnel.

10. An online monitoring device for ethanol production concentration, characterized in that: Ethanol production equipment that integrates the online monitoring system for ethanol production concentration as described in claim 9.

Images