Online monitoring method and system for reactor operating status based on neural network

Abstract

The present invention relates to the field of reactor status monitoring, and more specifically, to a method and system for online monitoring of reactor operating status based on a neural network. The method comprises: obtaining the multi-dimensional operating parameters and operating labels of the reactor at a target moment; calculating the volatility of any dimension at the target moment, and calculating the credibility of the operating parameters based on the volatility in each dimension at the target moment; calculating the degree of confusion between the operating parameters and operating labels in any dimension; calculating a random deactivation parameter based on the credibility and the degree of confusion in all dimensions; training a preset network based on the random deactivation parameter, inputting the real-time multi-dimensional operating parameters of the reactor into the trained preset network, outputting the reactor operating label, and completing status monitoring. The technical solution of the present invention can improve the accuracy of the reactor status monitoring results.

Description

Technical Field

[0001] The present invention relates to the field of reactor status monitoring, and more particularly to a method and system for online monitoring of reactor operating status based on a neural network. Background Art

[0002] Reactors are common and critical equipment in numerous industrial processes, widely used in fields such as chemical engineering, pharmaceuticals, and petroleum refining. The operating status of reactors directly impacts production efficiency, quality, and safety. Therefore, monitoring reactor status in real time to identify potential problems and provide early warnings has become a crucial task in modern industrial production.

[0003] Traditional reactor monitoring methods typically rely on physical sensors to collect parameters such as temperature, pressure, flow rate, and concentration within the reactor, and infer the reactor's operating status based on changes in these parameters. However, with the increasing number of variables in industrial processes, a single sensor is often unable to fully and accurately reflect the reactor's operating status. The dynamic processes within the reactor are often affected by a variety of factors, including fluctuations in raw material quality, changes in catalyst activity, and slight deviations in operating conditions. These factors are often coupled to each other, leading to complexity and uncertainty in sensor data. In addition, sensors in the reactor are limited by the installation environment or equipment accuracy, resulting in high data noise or missing data, resulting in inaccurate reactor status monitoring results. Summary of the Invention

[0004] In order to solve the problem of inaccurate reactor status monitoring results, the present invention proposes a method and system for online monitoring of reactor operating status based on neural network.

[0005] In a first aspect, the present invention discloses an online monitoring method for the operation status of a reactor based on a neural network, comprising: obtaining multi-dimensional working parameters and working labels of the reactor at a target moment, where the target moment is any sampling moment, and one multi-dimensional working parameter corresponds to one working label; constructing a window with the target moment as the center and a preset length as the window size, and for any dimension, taking the average difference between the working parameters at the target moment and the working parameters at the reference moment as the volatility of the target moment in any dimension, and the reference moment being the sampling moment other than the target moment in the window, and calculating the credibility of the working parameters according to the volatility of the target moment in each dimension; calculating the degree of confusion between the working parameters and the working labels of any dimension; calculating the product of the mean credibility of all sampling moments and the mean degree of confusion of all dimensions, and using the result of the product through negative correlation mapping as a random deactivation parameter; training a preset network according to the random deactivation parameter, inputting the real-time multi-dimensional working parameters of the reactor into the trained preset network, outputting the reactor working label, and completing status monitoring.

[0006] By analyzing the volatility of real-time sampling data, the complexity of the model can be dynamically adjusted to effectively avoid overfitting and underfitting problems, improve the prediction accuracy and robustness of the reactor in actual applications, and ensure that the model can provide stable monitoring results in a changing operating environment.

[0007] Preferably, the mean imputation method is used to fill in the missing working parameters, the Z-score method is used to identify and process the outliers in the working parameters, and the Kalman filter is used to reduce the noise in the working parameters.

[0008] Preferably, the credibility satisfies the relationship:

[0009] , Indicates target time The credibility of the working parameters, represents the mean volatility of all dimensions at the target moment, Indicates the total number of dimensions, Indicates target time In dimension volatility, Represents the exponential function.

[0010] Evaluating credibility based on fluctuations across multiple dimensions effectively avoids misjudgments due to abnormal fluctuations in a single dimension, thereby improving the overall accuracy of reactor status monitoring. This approach helps distinguish between noise and true anomalies, ensuring more accurate and reliable monitoring of the reactor's operating status.

[0011] Preferably, calculating the degree of disorder includes calculating a normal disorder degree of any dimension when the working tag is in normal working order, and the normal disorder degree satisfies the relationship:

[0012] , Indicates that when the work label is normal operation, the dimension Normal level of disorder, Representation Dimension The working parameter value is The probability of Represents a logarithmic function; the abnormal disorder degree of any dimension when the work label is abnormal work is obtained in the same way as the calculation method of the normal disorder degree; the mean of the normal disorder degree and the abnormal disorder degree is used as the disorder degree between the work parameter and the work label of any dimension.

[0013] It can effectively distinguish between normal fluctuations and abnormal changes, and in practical applications, it helps to accurately monitor the operating status of the reactor or system, identify potential faults or anomalies in advance, and thus improve the safety and reliability of the system.

[0014] Preferably, the calculation of the degree of disorder also satisfies the relationship:

[0015] , Indicates the degree of confusion, represents the variance of all working parameters in any dimension, It represents the variance of all working parameters in any dimension when the working label is normal operation. It represents the variance of all working parameters of any dimension when the working label is abnormal working.

[0016] This calculation method can effectively reflect the relationship between working parameters and working tags, and optimize the monitoring and abnormal warning effects of the operating status of reactors or equipment.

[0017] Preferably, the preset network is a BP neural network, which includes an input layer, a hidden layer and an output layer; the input layer is used to receive input of multi-dimensional working parameters, and the hidden layer extracts features from the input information and inputs the extracted features into the output layer to output the reactor working label.

[0018] Preferably, the training process of the preset network includes: taking the multi-dimensional working parameters of the reactor in history as input information, and taking the true value of the reactor's working label as a label to obtain a set of training data; calculating the loss value of the preset network through the reactor's working label and the label, setting the random inactivation parameters of the neurons in the preset network, and using the cross-entropy loss function as the loss function; iteratively updating the network parameters of the preset network, and when the preset network reaches the set maximum number of training times or the network loss value is less than the set loss value, stopping the update to obtain a trained preset network.

[0019] In a second aspect, the present invention discloses an online monitoring system for the operation status of a reactor based on a neural network, comprising: a processor; and a memory, wherein the memory stores computer instructions. When the computer instructions are executed by the processor, the system executes the above-mentioned online monitoring method for the operation status of a reactor based on a neural network.

[0020] Beneficial effects of the present invention:

[0021] The present invention dynamically evaluates the working status of the reactor through the volatility of multi-dimensional working parameters, credibility assessment, and calculation of the degree of chaos, and then outputs real-time working labels by training a neural network. Specifically, through windowed data sampling, missing value filling, outlier processing, and noise filtering, high-quality data input is ensured; and through the calculation of the degree of chaos and credibility, not only can the system performance under different working conditions be accurately reflected, but a neural network with strong predictive capabilities can also be trained based on historical data, thereby improving the accuracy of the reactor's operating status monitoring results. This method can promptly identify abnormal conditions in the reactor, prevent equipment failures, and improve the safety and operating efficiency of the reactor. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an illustrative and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0023] Figure 1 This is a flow chart of a method for online monitoring of reactor operating status based on a neural network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0025] It should be understood that when the terms "first," "second," and the like are used in the claims, description, and drawings of the present invention, they are merely used to distinguish between different objects, rather than to describe a specific order. The terms "comprise" and "comprising" used in the description and claims of the present invention indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or combinations thereof.

[0026] The present invention provides a method for online monitoring of reactor operating status based on neural network. Figure 1 As shown, the online monitoring method for reactor operation status based on neural network includes steps S1 to S5, which are described in detail below.

[0027] S1, obtain the multi-dimensional working parameters and working labels of the reactor at the target time.

[0028] In one embodiment, sensors are used to collect the operating parameters of the reactor. For example, by installing a voltage sensor, the DC and AC voltages of the reactor can be monitored. A current sensor is used to collect changes in DC and AC currents. A temperature sensor records temperature changes inside and outside the reactor in real time. These sensor data can provide basic information for determining the operating status of the reactor. Based on actual operating conditions and equipment operating specifications, technicians in this field can analyze the collected operating parameters to evaluate the operating status of the reactor and assign an operating label to each collected operating parameter based on set standards and thresholds. The operating label may include normal operation or abnormal operation.

[0029] The target time is any sampling time. The working parameters are multi-dimensional, and a multi-dimensional working parameter corresponds to a working label.

[0030] The mean imputation method is used to fill in missing working parameters, the Z-score method is used to identify and process outliers in working parameters, and the Kalman filter is used to reduce noise in working parameters. This completes the preprocessing of multi-dimensional working parameters.

[0031] S2, builds a window with the target moment as the center and the preset length as the window size. For any dimension, the average difference between the working parameters at the target moment and the working parameters at the reference moment is used as the volatility of the target moment in any dimension. The credibility of the working parameters is calculated based on the volatility of the target moment in each dimension.

[0032] It should be noted that the credibility of the collected working parameters has a crucial impact on the performance of the preset network, because low-credibility working parameters may introduce noise, which in turn affects the learning effect and prediction accuracy of the preset network. Therefore, it is necessary to conduct a credibility assessment on each working parameter and process it according to the assessment results. When the credibility of a certain working parameter is low, the probability of neuron inactivation in the neural network can be increased during the training process, so that the preset network can maintain strong robustness when facing these noisy training data. In this way, even if there is a certain amount of noise or outliers in the training data, the preset network can still avoid overfitting and maintain good generalization performance, ensuring that it still has stable performance under incomplete or inaccurate data.

[0033] In one embodiment, for any dimension, the average difference between the operating parameters at the target moment and the operating parameters at the reference moment is used as the volatility of the target moment in any dimension. The volatility is expressed using the relationship:

[0034] , Indicates target time In dimension volatility, Indicates target time In dimension The working parameter values, Indicates the reference time In dimension The working parameter values, Indicates the window size.

[0035] Credibility satisfies the relationship:

[0036] , Indicates target time The credibility of the working parameters, represents the mean volatility of all dimensions at the target moment, Indicates the total number of dimensions, Indicates target time In dimension volatility, Represents the exponential function.

[0037] When the operating parameters of multiple dimensions at a certain sampling moment fluctuate synchronously, that is, when the volatility of each dimension is close to the mean volatility of all dimensions at that sampling moment, then the credibility is high. This is because if the volatility of multiple dimensions is close to the mean, it means that these fluctuations are more likely to be part of normal fluctuations rather than external noise or occasional interference, further indicating that the fluctuations at that moment may reflect the real change in the state of the reactor system, or even be a sign of an abnormality. On the contrary, if the difference between the volatility of each dimension and the volatility mean is large, it indicates that the fluctuations of each dimension do not show synchronization, and this volatility deviates far from the mean, and the credibility is low. This situation usually means that the fluctuations in some dimensions may be caused by noise or other irrelevant factors, and thus cannot accurately reflect the true state of the reactor system.

[0038] Evaluating credibility based on fluctuations across multiple dimensions effectively avoids misjudgments due to abnormal fluctuations in a single dimension, thereby improving the overall accuracy of reactor status monitoring. This approach helps distinguish between noise and true anomalies, ensuring more accurate and reliable monitoring of the reactor's operating status.

[0039] It's important to note that the reliability of a given sampling moment depends not only on the fluctuation amplitude of a single dimension at that moment but also on the synchronization of fluctuations across multiple dimensions. If multiple reactor parameters (such as voltage, current, and temperature) exhibit similar and significant fluctuations at the same sampling moment, this synchronization typically indicates a common problem within the reactor system, rather than simply random noise.

[0040] S3, calculates the degree of confusion between the work parameters and work labels in any dimension.

[0041] In one embodiment, calculating the degree of disorder includes calculating the normal disorder degree of any dimension when the working label is normal working, and the normal disorder degree satisfies the relationship:

[0042] , Indicates that when the work label is normal operation, the dimension Normal level of disorder, Representation Dimension The working parameter value is The probability of Represents the logarithmic function.

[0043] The abnormal disorder degree of any dimension is obtained in the same way as the calculation method of the normal disorder degree when the work label is abnormal work; the average of the normal disorder degree and the abnormal disorder degree is used as the disorder degree between the work parameter and the work label of any dimension.

[0044] By introducing a method for calculating the degree of chaos, we can quantify the degree of match between work labels and the working parameters of each dimension from a probabilistic perspective. Under normal operating conditions, the normal degree of chaos for a dimension reflects the distribution uncertainty of the working parameter values. This is achieved by calculating the probability distribution of each possible working parameter value for that dimension under normal operating conditions and measuring its information entropy. Similarly, under abnormal operating conditions, the abnormal degree of chaos measures the uncertainty of the parameter distribution under abnormal operating conditions. Taking the mean of these two degrees of chaos as the dimension's degree of chaos helps accurately identify changes in working conditions by comparing the fluctuation characteristics under normal and abnormal conditions.

[0045] During normal operation, the distribution of parameter values should be relatively stable, with low levels of chaos. However, during abnormal operation, the parameter distribution often deviates from the normal state, resulting in a high degree of chaos. Therefore, this chaos-based comparison can effectively distinguish between normal fluctuations and abnormal changes. In practical applications, it helps accurately monitor the operating status of reactors or systems, identify potential failures or anomalies in advance, and thus improve system safety and reliability.

[0046] In another embodiment, the degree of disorder further satisfies the relationship:

[0047] , Indicates the degree of confusion, represents the variance of all working parameters in any dimension, It represents the variance of all working parameters in any dimension when the working label is normal operation. It represents the variance of all working parameters of any dimension when the working label is abnormal working.

[0048] When the intra-class variance (i.e., the variance of parameters under each work label) is small, while the inter-class variance (i.e., the difference in variance under different work labels) is large, it indicates that the distribution of parameters differs significantly between normal and abnormal operating states, and the system is able to distinguish between normal and abnormal operation. In this case, the degree of confusion is low, indicating a high degree of match between parameters and labels, reflecting the accuracy of identifying the system state.

[0049] This calculation method can effectively reflect the relationship between working parameters and working tags, and optimize the monitoring and abnormal warning effects of the operating status of reactors or equipment.

[0050] S4, calculate the product of the mean credibility of all sampling moments and the mean chaos degree of all dimensions, and use the result of the product through negative correlation mapping as the random inactivation parameter.

[0051] It's important to note that dropout in neural networks is primarily used to prevent overfitting and improve generalization. When the confidence level of the operating parameters is high, meaning there's less noise in them, the network can better learn the true patterns of the data. In this case, adding dropout is less necessary because the network already fits the training data well and isn't prone to overfitting.

[0052] When the degree of confusion between the working parameters and the labels is large, it indicates that there is a strong nonlinear relationship between the labels and the working parameters. The preset network requires more complexity to capture these relationships. Therefore, there is no need to introduce too much random inactivation, because increasing inactivation may limit the expressive power of the model, making it difficult to fully capture the complex patterns of the data.

[0053] In general, random dropout is used to avoid overfitting of the model and classifying some incorrect samples as correct samples. The preset network works well on the test set, but the effect decreases in actual use.

[0054] S5, train the preset network according to the random deactivation parameters, input the real-time multi-dimensional working parameters of the reactor into the trained preset network, output the reactor working label, and complete the status monitoring.

[0055] In one embodiment, the network is assumed to be a BP neural network, which includes an input layer, a hidden layer, and an output layer; the input layer is used to receive input of multi-dimensional working parameters, and the hidden layer extracts features from the input information and inputs the extracted features into the output layer to output the reactor working label.

[0056] The training process of the preset network includes: taking the multi-dimensional working parameters of the reactor in history as input information, and taking the true value of the reactor's working label as the label to obtain a set of training data; calculating the loss value of the preset network through the reactor's working label and the label, setting the random inactivation parameters of the neurons in the preset network, and using the cross-entropy loss function as the loss function; iteratively updating the network parameters of the preset network, and stopping the update when the preset network reaches the set maximum number of training times or the network loss value is less than the set loss value to obtain a trained preset network.

[0057] By inputting the real-time multi-dimensional working parameters of the reactor into the preset network, the reactor working label can be obtained, thereby obtaining the reactor status result and completing the status monitoring.

[0058] An embodiment of the present invention also discloses an online monitoring system for the operation status of a reactor based on a neural network, comprising a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, an online monitoring method for the operation status of a reactor based on a neural network according to the present invention is implemented.

[0059] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0060] In the present invention, the aforementioned memory may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium may be part of, accessible to, or connectable to a device.

[0061] While this specification has shown and described several embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

[0062] The above are all preferred embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for online monitoring of reactor operating status based on neural network, characterized in that: include: Obtaining the multi-dimensional operating parameters and operating tags of the reactor at a target time, where the target time is any sampling time, and one multi-dimensional operating parameter corresponds to one operating tag; A window is constructed with the target time as the center and a preset length as the window size. For any dimension, the average difference between the operating parameters at the target time and the operating parameters at the reference time is used as the volatility of the target time in any dimension. The reference time is the sampling time in the window except the target time. The credibility of the operating parameters is calculated based on the volatility of the target time in each dimension. Calculate the degree of confusion between the work parameters and work labels in any dimension; Calculate the product of the mean credibility of all sampling moments and the mean chaos degree of all dimensions, and use the result of negative correlation mapping as the random inactivation parameter; The preset network is trained based on random deactivation parameters, and the real-time multi-dimensional working parameters of the reactor are input into the trained preset network. The reactor working label is output to complete the state monitoring. The credibility satisfies the relationship: , Indicates target time The credibility of the working parameters, represents the mean volatility of all dimensions at the target moment, Indicates the total number of dimensions, Indicates target time In dimension volatility, represents the exponential function; Calculating the disorder level includes: When the work label is calculated as normal operation, the normal disorder degree of any dimension satisfies the relationship: , Indicates that when the work label is normal operation, the dimension The normal level of disorder, Representation Dimension The working parameter value is The probability of represents the logarithmic function; The abnormal disorder degree of any dimension is obtained in the same way as the calculation method of normal disorder degree when the work label is abnormal work; The mean of normal disorder level and abnormal disorder level is taken as the disorder level between the work parameter and the work label of any dimension; Calculating the disorder level also includes: , Indicates the degree of confusion, represents the variance of all working parameters in any dimension, It represents the variance of all working parameters in any dimension when the working label is normal operation. It represents the variance of all working parameters of any dimension when the working label is abnormal working.

2. The method for online monitoring of reactor operating status based on neural network according to claim 1, characterized in that: The mean imputation method is used to fill in the missing working parameters, the Z-score method is used to identify and process the outliers in the working parameters, and the Kalman filter is used to reduce the noise in the working parameters.

3. The method for online monitoring of reactor operating status based on neural network according to claim 1, characterized in that: The preset network is a BP neural network, which includes an input layer, a hidden layer and an output layer; the input layer is used to receive input of multi-dimensional working parameters, and the hidden layer extracts features from the input information and inputs the extracted features into the output layer to output the reactor working label.

4. The method for online monitoring of reactor operating status based on neural network according to claim 1, characterized in that: The training process of the preset network includes: The multi-dimensional working parameters of the reactor in history are used as input information, and the actual value of the reactor's working label is used as the label to obtain a set of training data; Calculate the loss value of the preset network through the reactor work label and label, set the random inactivation parameters of the neurons in the preset network, and use the cross entropy loss function as the loss function; Iteratively update the network parameters of the preset network. When the preset network reaches the set maximum number of training times or the network loss value is less than the set loss value, stop updating and obtain the trained preset network.

5. The online monitoring system of reactor operation status based on neural network is characterized by: include: processor; and A memory storing computer instructions, wherein when the computer instructions are executed by the processor, the system executes the online monitoring method for the reactor operating status based on a neural network according to any one of claims 1 to 4.

Images