Optical stability evaluation and prediction method based on improved LSTM model

Abstract

The invention relates to the technical field of optical microscope imaging, and discloses an optical stability evaluation and prediction method based on an improved LSTM model, and the method comprises the steps: obtaining the imaging data, environment sensor data and operation state data of a to-be-tested optical microscope, and carrying out the multi-source data fusion analysis through the improved LSTM model, and obtaining the optical stability of the to-be-tested optical microscope. And accurate evaluation of the imaging stability is realized. According to the method, the improved LSTM model is utilized to accurately identify the root cause of imaging instability, and the accuracy and reliability of an evaluation result are remarkably improved; a dynamic weight adjustment strategy and a real-time data processing technology are adopted, so that the model can quickly respond to environment change and equipment state fluctuation, efficient prediction of imaging stability is realized, and the problem of poor real-time performance of a traditional method is solved; and in combination with real-time evaluation and prediction results, an intelligent early warning function is also provided to help researchers to find and solve the problem of instability in the imaging process in advance, so that the imaging quality is effectively prevented from being reduced, and the experimental uncertainty is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of optical microscope imaging technology, and in particular to an optical stability evaluation and prediction method based on an improved LSTM model. BACKGROUND

[0002] In the scientific research application of optical microscopes, especially high-resolution electron microscopes, the imaging stability is directly related to the accuracy and reliability of the observation results. However, environmental factors (such as temperature, humidity, magnetic field changes), equipment vibration, and power fluctuations can all adversely affect the imaging stability, leading to a decline in image quality.

[0003] Traditional methods mainly rely on manual monitoring and post-adjustment to maintain imaging stability. Manual monitoring involves regular checks of environmental parameters (such as temperature, humidity) and equipment status by experimenters, while post-adjustment involves making corrections to microscope parameters or environmental conditions based on experience after image quality is found to have declined. However, these methods have significant drawbacks: first, they lack real-time performance and cannot achieve continuous monitoring, often only being discovered after problems occur; second, they have low accuracy and rely on subjective judgment, making it difficult to accurately identify the root cause of the problem; in addition, traditional methods lack predictive ability and cannot prevent imaging instability problems in advance, leading to increased experimental uncertainty. At the same time, manual monitoring and adjustment require a large amount of labor costs and have limited ability to respond and adapt in complex and changing environmental conditions, making it difficult to respond quickly and adapt. These limitations make traditional methods increasingly inadequate in high-precision scientific research applications, and there is an urgent need for more advanced automated solutions to improve imaging stability and experimental efficiency. SUMMARY

[0004] The present application provides an optical stability evaluation and prediction method based on an improved LSTM model to solve the defects of existing optical stability evaluation and prediction methods based on an improved LSTM model, such as poor real-time performance, low accuracy, and lack of preventive ability.

[0005] The present application provides an optical stability evaluation and prediction method based on an improved LSTM model, comprising:

[0006] Obtaining imaging data, environmental sensor data, and running state data of the optical microscope to be tested;

[0007] According to the imaging data, environmental sensor data, and running state data of the optical microscope to be tested, an optical microscope imaging stability evaluation model is used to obtain an imaging stability evaluation result of the optical microscope to be tested, wherein the optical microscope imaging stability evaluation model is an improved LSTM model.

[0008] The application provides an optical stability evaluation and prediction method based on an improved LSTM model, wherein the environmental sensor data comprises any one or any combination of the following: temperature, humidity, vibration, magnetic field and noise.

[0009] The application provides an optical stability evaluation and prediction method based on an improved LSTM model, wherein the running state data comprises light source current, vacuum value and liquid nitrogen content.

[0010] The application provides an optical stability evaluation and prediction method based on an improved LSTM model, wherein the imaging data, the environmental sensor data and the running state data of the to-be-tested optical microscope are used to obtain an imaging stability evaluation result of the to-be-tested optical microscope through an optical microscope imaging stability evaluation model, and the method comprises the following steps.

[0011] The environmental sensor data and the running state data are preprocessed, wherein the preprocessing comprises any one or any combination of the following: data cleaning, feature extraction and data normalization.

[0012] The application provides an optical stability evaluation and prediction method based on an improved LSTM model, wherein when the preprocessing is feature extraction, the imaging data, the environmental sensor data and the running state data of the to-be-tested optical microscope are used to obtain an imaging stability evaluation result of the to-be-tested optical microscope through an optical microscope imaging stability evaluation model, and the method comprises the following steps.

[0013] The imaging data, the environmental sensor data and the running state data of the to-be-tested optical microscope are used to obtain feature data that has an influence on imaging stability, wherein the feature data that has an influence on imaging stability comprises any one or any combination of the following: temperature fluctuation range, temperature change trend, humidity fluctuation range, humidity change trend, vibration acceleration peak value, vibration frequency, light source current stability and image definition score.

[0014] The application provides an optical stability evaluation and prediction method based on an improved LSTM model, wherein the imaging data, the environmental sensor data and the running state data of the to-be-tested optical microscope are used to obtain feature data that has an influence on imaging stability, and the method comprises the following steps.

[0015] The environmental sensor data of the to-be-tested optical microscope is used to calculate a difference between a maximum value and a minimum value of temperature in the past n time steps, so as to obtain a temperature fluctuation range of the to-be-tested optical microscope in the past n time steps.

[0016] The environmental sensor data of the to-be-tested optical microscope is used to calculate a temperature difference value of adjacent time steps, so as to obtain a temperature change trend.

[0017] According to the optical stability evaluation and prediction method based on the improved LSTM model provided by the application, the imaging data, the environmental sensor data and the running state data of the to-be-tested optical microscope are used to obtain feature data that has an influence on imaging stability, and the feature data includes:

[0018] According to the environmental sensor data of the to-be-tested optical microscope, the difference between the maximum value and the minimum value of the humidity in the past n time steps is calculated to obtain the humidity fluctuation range of the to-be-tested optical microscope in the past n time steps.

[0019] According to the environmental sensor data of the to-be-tested optical microscope, the humidity difference value of adjacent time steps is calculated to obtain the humidity change trend.

[0020] According to the optical stability evaluation and prediction method based on the improved LSTM model provided by the application, the imaging data, the environmental sensor data and the running state data of the to-be-tested optical microscope are used to obtain feature data that has an influence on imaging stability, and the feature data includes:

[0021] According to the environmental sensor data of the to-be-tested optical microscope, the maximum value of the vibration acceleration of the to-be-tested optical microscope in n time steps is obtained as the vibration acceleration peak value of the to-be-tested optical microscope in n time steps.

[0022] According to the optical stability evaluation and prediction method based on the improved LSTM model provided by the application, the imaging data, the environmental sensor data and the running state data of the to-be-tested optical microscope are used to obtain feature data that has an influence on imaging stability, and the feature data includes:

[0023] According to the imaging data, the environmental sensor data and the running state data of the to-be-tested optical microscope, the time-domain vibration signal is converted into a frequency-domain signal by fast Fourier transform to obtain a main vibration frequency component as a vibration frequency characteristic.

[0024] According to the optical stability evaluation and prediction method based on the improved LSTM model provided by the application, the imaging data, the environmental sensor data and the running state data of the to-be-tested optical microscope are used to obtain feature data that has an influence on imaging stability, and the feature data includes:

[0025] According to the imaging data of the to-be-tested optical microscope, the Laplacian operator is used to perform edge detection on the imaging data to obtain the image edge intensity sum of the to-be-tested optical microscope as an image sharpness score.

[0026] The application provides an optical stability evaluation and prediction method based on an improved LSTM model.

[0027] The application provides an optical stability evaluation and prediction method based on an improved LSTM model.

[0028] The application provides an optical stability evaluation and prediction method based on an improved LSTM model.

[0029] The application provides an optical stability evaluation and prediction method based on an improved LSTM model.

[0030] The application provides an optical stability evaluation and prediction method based on an improved LSTM model.

[0031]

[0032] The application provides an optical stability evaluation and prediction method based on an improved LSTM model. N The application provides an optical stability evaluation and prediction method based on an improved LSTM model.

[0033] The application provides an optical stability evaluation and prediction method based on an improved LSTM model.

[0034] When the imaging stability evaluation score of the optical microscope to be measured is outside the preset range and less than the minimum value in the preset range, it is determined that the imaging stability evaluation result of the optical microscope to be measured is that the imaging stability decreases, and the influencing factors affecting the imaging stability are obtained according to the environmental sensor data and the running state data of the optical microscope to be measured, a warning signal and the influencing factors affecting the imaging stability are issued;

[0035] When the imaging stability evaluation score of the optical microscope to be measured is within the preset range, it is determined that the imaging stability evaluation result of the optical microscope to be measured is that the imaging stability is qualified.

[0036] When the imaging stability evaluation score of the optical microscope to be measured is outside the preset range and higher than the maximum value in the preset range, it is determined that the imaging stability evaluation result of the optical microscope to be measured is that the imaging stability increases.

[0037] The application also provides an optical stability evaluation and prediction system based on an improved LSTM model, comprising:

[0038] A data acquisition module is configured to acquire imaging data, environmental sensor data and running state data of an optical microscope to be measured.

[0039] An optical microscope imaging stability evaluation module is configured to obtain an imaging stability evaluation result of the optical microscope to be measured by an optical microscope imaging stability evaluation model according to the imaging data, the environmental sensor data and the running state data of the optical microscope to be measured, wherein the optical microscope imaging stability evaluation model is an improved LSTM model.

[0040] The application also provides an electronic device comprising a processor and a memory storing a computer program, wherein the processor implements the optical stability evaluation and prediction method based on the improved LSTM model when executing the computer program.

[0041] The application also provides a non-transitory computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the optical stability evaluation and prediction method based on the improved LSTM model.

[0042] The application also provides a computer program product comprising a computer program, wherein the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor to implement the optical stability evaluation and prediction method based on the improved LSTM model.

[0043] The application provides an optical stability evaluation and prediction method based on an improved LSTM model. The imaging data, environmental sensor data and running state data of the optical microscope to be measured are obtained, and the improved LSTM model is used for multi-source data fusion analysis to realize accurate evaluation of the imaging stability. Compared with traditional manual monitoring and post-adjustment, the application has the following advantages: first, the improved LSTM model can accurately identify the root cause of imaging instability, significantly improving the accuracy and reliability of the evaluation results; second, the dynamic weight adjustment strategy and real-time data processing technology are used to enable the model to quickly respond to environmental changes and equipment state fluctuations, realize efficient prediction of the imaging stability, and solve the problem of poor real-time performance of traditional methods; in addition, the application also provides an intelligent warning function based on the real-time evaluation and prediction results, which helps researchers to find and solve unstable problems in the imaging process in advance, thereby effectively preventing the decline of imaging quality and reducing experimental uncertainty. At the same time, the application greatly reduces the need for manual monitoring and adjustment through automation technology, reduces labor costs, and has stronger adaptability in complex and variable environmental conditions. These advantages enable the application to significantly improve the imaging stability and experimental efficiency in high-precision scientific research applications, and overcome the limitations of traditional methods. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0045] Figure 1 The flowchart of the optical stability evaluation and prediction method based on the improved LSTM model provided by the application.

[0046] Figure 2 The architecture diagram of the optical microscope imaging stability evaluation model.

[0047] Figure 3 The structure diagram of the optical stability evaluation and prediction system based on the improved LSTM model provided by the application.

[0048] Figure 4 The structure diagram of the electronic device provided by the application. DETAILED DESCRIPTION

[0049] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, and should not be understood as limiting the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application. In the description of the present application, it should be understood that the terms used are only for the purpose of description and should not be understood as indicating or implying relative importance.

[0050] Figure 1 A flowchart of an optical stability evaluation and prediction method based on an improved LSTM model is provided. The execution subject of the optical stability evaluation and prediction method based on the improved LSTM model provided by the present application can be any applicable terminal-side device or network-side device, such as an optical microscope imaging stability evaluation device.

[0051] Referring to Figure 1 The optical stability evaluation and prediction method based on the improved LSTM model provided by the present application can include the following steps.

[0052] S110, obtaining imaging data, environmental sensor data and running state data of the optical microscope to be tested, wherein the imaging data is an image obtained after imaging using the optical microscope to be tested; in the embodiment, the environmental sensor data includes temperature, humidity and vibration, and the running state data includes light source current.

[0053] In an embodiment, after obtaining the imaging data, the environmental sensor data and the running state data of the optical microscope to be tested, the data can be preprocessed, and the preprocessing includes any one or any combination of the following: data cleaning, feature extraction, data normalization.

[0054] In an embodiment, the data cleaning may, for example, be removing noise data, outliers and repeated records in the imaging data, the environmental sensor data and the running state data of the optical microscope to be tested, to ensure the accuracy and consistency of the data.

[0055] In an embodiment, the feature extraction can be, for example, according to the imaging data, the environmental sensor data and the running state data of the optical microscope to be tested, to obtain feature data that has an impact on the imaging stability (e.g. directly or indirectly causes image quality fluctuations (such as resolution degradation, signal-to-noise ratio reduction or drift) in the imaging process of the optical microscope) to provide important basis for model prediction. In this embodiment, the feature data that has an impact on the imaging stability includes: temperature fluctuation range, temperature change trend, humidity fluctuation range, humidity change trend, vibration acceleration peak value, vibration frequency, image sharpness score.

[0056] In this embodiment, according to the environmental sensor data of the optical microscope to be tested, the difference between the maximum and minimum values of the temperature in the past n time steps is calculated to obtain the temperature fluctuation range of the optical microscope to be tested in the past n time steps. The expression can be: T_range = max(T_1, T_2, …, T_n) - min(T_1, T_2, …, T_n), where T_i is the temperature value of the i-th time step; according to the environmental sensor data of the optical microscope to be tested, the temperature difference value of adjacent time steps is calculated to obtain the temperature change trend. The expression can be: T_rate = T_i - T_{i-1}.

[0057] In this embodiment, similarly, according to the environmental sensor data of the optical microscope to be tested, the difference between the maximum and minimum values of the humidity in the past n time steps is calculated to obtain the humidity fluctuation range of the optical microscope to be tested in the past n time steps; according to the environmental sensor data of the optical microscope to be tested, the humidity difference value of adjacent time steps is calculated to obtain the humidity change trend.

[0058] In this embodiment, according to the environmental sensor data of the optical microscope to be tested, the maximum vibration acceleration value of the optical microscope to be tested in n time steps is obtained as the vibration acceleration peak value of the optical microscope to be tested in n time steps. The expression can be: A_peak = max(A_1, A_2, …, A_n), where A_i is the vibration acceleration value of the i-th time step.

[0059] In this embodiment, according to the imaging data, the environmental sensor data and the running state data of the optical microscope to be tested, the time-domain vibration signal is converted into a frequency-domain signal by fast Fourier transform (FFT) to obtain the main vibration frequency component as the vibration frequency characteristic.

[0060] In this embodiment, according to the imaging data of the optical microscope to be tested, the Laplacian operator is used to perform edge detection on the imaging data to obtain the image edge intensity sum of the optical microscope to be tested as the image sharpness score. The expression can be: wherein is the gradient value of the image at pixel point (x, y). The greater the edge strength and, the more clear the image is, and vice versa. By extracting the image definition feature, the imaging quality can be quantitatively evaluated.

[0061] In an embodiment, data normalization may, for example, be converting feature values of different dimensions and ranges to a unified scale for model processing. This embodiment adopts a min-max normalization method to normalize feature data, converting feature values of different dimensions and ranges to the interval [0, 1], with the formula x' = (x-x_min) / (x_max-x_min), where x is the original feature value, x_min and x_max are the minimum and maximum values of the feature data respectively, and x' is the normalized feature value.

[0062] S120, according to the imaging data, the environmental sensor data and the running state data of the optical microscope to be tested, the imaging stability evaluation result of the optical microscope to be tested is obtained by the optical microscope imaging stability evaluation model, wherein the optical microscope imaging stability evaluation model is an improved LSTM model.

[0063] In an embodiment, the optical microscope imaging stability evaluation model includes l-layer stacked LSTM layers, a feature splicing module, and a fully connected layer including a Dropout mechanism, wherein an attention mechanism layer is arranged between adjacent LSTM layers in the l-layer stacked LSTM layers, the fully connected layer includes two hidden layers and an output layer, and the Dropout mechanism acts on the two hidden layers, wherein the first LSTM layer in the l-layer stacked LSTM layers is arranged to receive the environmental sensor data and the running state data of the optical microscope to be tested, the output of the l-th LSTM layer in the l-layer stacked LSTM layers is taken as the input of the feature splicing module, the output of the feature splicing module is taken as the input of the hidden layer of the fully connected layer, the output of the hidden layer in the fully connected layer is taken as the input of the output layer thereof, and the output layer of the fully connected layer is arranged to output the imaging stability evaluation result of the optical microscope to be tested.

[0064] This embodiment adopts stacked LSTM (Stacked LSTM) to construct a deeper network structure for the optical microscope imaging stability evaluation model, improves the learning ability and nonlinear expression ability of the model, introduces an attention mechanism (Attention Mechanism) to enhance the model's ability to capture key information, and uses Dropout and other technologies to prevent overfitting and improve the generalization ability of the model.

[0065] In this embodiment, the application adopts a stacked LSTM layer, specifically a three-layer LSTM structure. The first layer LSTM contains 50 neurons for preliminary extraction of short-term features in the time series data; the second layer LSTM contains 30 neurons for further mining of medium-term features in the data; and the third layer LSTM contains 20 neurons for focusing on extracting long-term features. Through this hierarchical feature extraction method, the time series information in the input data (imaging data, environmental sensor data and running state data of the optical microscope to be tested) can be more comprehensively captured. When constructing the stacked LSTM layer, a layer-by-layer training method is adopted. First, the first layer LSTM is trained to learn the basic pattern of the data, and then the output of the first layer LSTM is taken as the input of the second layer LSTM for training. In this way, the third layer LSTM is finally fine-tuned together to improve the overall performance of the model.

[0066] In the optical microscope imaging stability evaluation model, the input is a time series X composed of tx multi-dimensional vectors x, where tx is the input time step, denoted as:

[0067] X = (x1, x2, x3, …, x tx )

[0068] The output is a time series prediction result composed of ty numbers from 0 to 1 ty is the output time step, denoted as:

[0069]

[0070] In one embodiment, considering that the influence degree of various factors on imaging stability may change in different time periods, this embodiment proposes a dynamic weight adjustment strategy. According to the change trend of historical data and the current environmental state, the weights of various input features are dynamically adjusted. For example, when the real-time monitored temperature value deviates from its normal change trend and causes the imaging quality to decrease, the weight of the temperature feature is increased, so that the model is more adapted to the actual situation and the prediction accuracy is improved.

[0071] In one embodiment, S120 can include:

[0072] According to the imaging data, environmental sensor data and running state data of the optical microscope to be tested, the imaging stability evaluation score of the optical microscope to be tested is obtained by using the optical microscope imaging stability evaluation model and the imaging stability evaluation expression, wherein the imaging stability evaluation expression is:

[0073]

[0074] In the imaging stability evaluation expression, A1, B2, …, Z Nindicate the feature data in the imaging data, environmental sensor data and running state data of the optical microscope to be tested that have an impact on imaging stability, and a, b, …, z indicate the dynamic weights of the corresponding feature data, and S indicates the imaging stability evaluation score of the optical microscope to be tested;

[0075] The imaging stability evaluation score of the optical microscope to be tested is compared with a preset range (for example ), and the imaging stability evaluation result of the optical microscope to be tested is obtained. In this embodiment, when the imaging stability evaluation score of the optical microscope to be tested is outside the preset range and less than the minimum value within the preset range, it is determined that the imaging stability evaluation result of the optical microscope to be tested is that the imaging stability is decreased, and the influencing factors affecting the imaging stability are obtained according to the environmental sensor data and the running state data of the optical microscope to be tested, a pre-warning signal and the influencing factors affecting the imaging stability are issued; when the imaging stability evaluation score of the optical microscope to be tested is within the preset range, it is determined that the imaging stability evaluation result of the optical microscope to be tested is that the imaging stability is qualified; and when the imaging stability evaluation score of the optical microscope to be tested is outside the preset range and higher than the maximum value within the preset range, it is determined that the imaging stability evaluation result of the optical microscope to be tested is that the imaging stability is increased. This embodiment can also predict future scores according to past n time steps of real-time scores based on real-time scores obtained by real-time evaluation.

[0076] The application provides an optical stability evaluation and prediction method based on an improved LSTM model, which realizes accurate evaluation of imaging stability by obtaining imaging data, environmental sensor data and running state data of an optical microscope to be tested, and performing multi-source data fusion analysis by using an improved LSTM model. Compared with traditional manual monitoring and post-adjustment, the application has the following advantages: first, by applying the improved LSTM model, the root cause of imaging instability can be accurately identified, significantly improving the accuracy and reliability of the evaluation result; second, by using a dynamic weight adjustment strategy and real-time data processing technology, the model can quickly respond to environmental changes and equipment state fluctuations, realize efficient prediction of imaging stability, and solve the problem of poor real-time performance of traditional methods; in addition, combined with real-time evaluation and prediction results, the application also provides an intelligent warning function to help researchers discover and solve unstable problems in the imaging process in advance, thereby effectively preventing imaging quality decline and reducing experimental uncertainty. At the same time, the application greatly reduces the need for manual monitoring and adjustment through automation technology, reduces labor costs, and performs better in complex and variable environmental conditions. These advantages enable the application to significantly improve imaging stability and experimental efficiency in high-precision scientific research applications, overcoming the limitations of traditional methods.

[0077] The improved LSTM model-based optical stability evaluation and prediction system provided by the present application is described below, and the improved LSTM model-based optical stability evaluation and prediction system described below can be referred to in correspondence with the improved LSTM model-based optical stability evaluation and prediction method described above.

[0078] Referring to Figure 3 The improved LSTM model-based optical stability evaluation and prediction system provided by the present application can include:

[0079] The data acquisition module is configured to acquire imaging data, environmental sensor data, and running state data of the optical microscope to be tested.

[0080] The optical microscope imaging stability evaluation module is configured to obtain an imaging stability evaluation result of the optical microscope to be tested by using an optical microscope imaging stability evaluation model according to the imaging data, the environmental sensor data, and the running state data of the optical microscope to be tested, wherein the optical microscope imaging stability evaluation model is an improved LSTM model.

[0081] The optical microscope imaging stability evaluation model is deployed into the system to form the improved LSTM model-based optical stability evaluation and prediction system, which can receive the imaging data, the environmental sensor data, and the running state data of the optical microscope to be tested in real time, and perform online evaluation and prediction. When the imaging stability is predicted to decrease, the system immediately issues a warning signal and gives specific influencing factor prompts (such as the current environmental noise being too high), thereby helping researchers to take timely measures to ensure stable and reliable imaging quality.

[0082] Figure 4 An example of an entity structure diagram of an electronic device is shown in Figure 4 The electronic device can include a processor 810, a communications interface 820, a memory 830, and a communications bus 840, wherein the processor 810, the communications interface 820, and the memory 830 can communicate with each other through the communications bus 840. The processor 810 can invoke a logical instruction in the memory 830 to perform the following steps:

[0083] The imaging data, the environmental sensor data, and the running state data of the optical microscope to be tested are acquired.

[0084] The imaging stability evaluation result of the optical microscope to be tested is obtained by using an optical microscope imaging stability evaluation model according to the imaging data, the environmental sensor data, and the running state data of the optical microscope to be tested, wherein the optical microscope imaging stability evaluation model is an improved LSTM model.

[0085] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0086] In another aspect, the present invention further provides a computer program product, comprising a computer program, which may be stored on a non-transitory computer-readable storage medium, and wherein when the computer program is executed by a processor, the computer is capable of performing the following steps:

[0087] Acquire imaging data, environmental sensor data, and operating status data of the optical microscope to be tested;

[0088] According to the imaging data, environmental sensor data and operating status data of the optical microscope to be tested, the imaging stability evaluation result of the optical microscope to be tested is obtained through the optical microscope imaging stability evaluation model, wherein the optical microscope imaging stability evaluation model is an improved LSTM model.

[0089] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is configured to execute the following steps when executed by a processor:

[0090] Acquire imaging data, environmental sensor data, and operating status data of the optical microscope to be tested;

[0091] According to the imaging data, environmental sensor data and operating status data of the optical microscope to be tested, the imaging stability evaluation result of the optical microscope to be tested is obtained through the optical microscope imaging stability evaluation model, wherein the optical microscope imaging stability evaluation model is an improved LSTM model.

[0092] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0093] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0094] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An optical stability evaluation and prediction method based on an improved LSTM model, characterized in that: include: Acquire imaging data, environmental sensor data, and operating status data of the optical microscope to be tested; According to the imaging data, environmental sensor data and operating status data of the optical microscope to be tested, the imaging stability evaluation result of the optical microscope to be tested is obtained through the optical microscope imaging stability evaluation model, wherein the optical microscope imaging stability evaluation model is an improved LSTM model.

2. The optical stability evaluation and prediction method based on the improved LSTM model according to claim 1, characterized in that: Environmental sensor data includes any one of the following or any combination thereof: temperature, humidity, vibration, magnetic field, and noise; operating status data includes light source current, vacuum value, and liquid nitrogen content.

3. The optical stability evaluation and prediction method based on the improved LSTM model according to claim 2, characterized in that: The imaging stability evaluation result of the optical microscope to be tested is obtained by using an optical microscope imaging stability evaluation model based on the imaging data, environmental sensor data, and operating status data of the optical microscope to be tested, including: Preprocessing the environmental sensor data and the operating status data, wherein the preprocessing includes any one of the following or any combination thereof: data cleaning, feature extraction, and data normalization.

4. The optical stability evaluation and prediction method based on the improved LSTM model according to claim 3 is characterized in that: When the preprocessing is feature extraction, the imaging stability evaluation result of the optical microscope to be tested is obtained by using an optical microscope imaging stability evaluation model based on the imaging data, environmental sensor data, and operating status data of the optical microscope to be tested, including: Based on the imaging data, environmental sensor data and operating status data of the optical microscope to be tested, characteristic data affecting the imaging stability are obtained, wherein the characteristic data affecting the imaging stability include any one of the following items or any combination thereof: temperature fluctuation range, temperature change trend, humidity fluctuation range, humidity change trend, vibration acceleration peak, vibration frequency, light source current stability, and image clarity score.

5. The optical stability evaluation and prediction method based on the improved LSTM model according to claim 4 is characterized in that: The method of obtaining characteristic data affecting imaging stability based on imaging data, environmental sensor data, and operating status data of the optical microscope to be tested includes: According to the environmental sensor data of the optical microscope to be tested, the difference between the maximum and minimum temperature in the past n time steps is calculated to obtain the temperature fluctuation range of the optical microscope to be tested in the past n time steps; According to the environmental sensor data of the optical microscope to be tested, the temperature difference between adjacent time steps is calculated to obtain the temperature change trend.

6. The optical stability evaluation and prediction method based on the improved LSTM model according to claim 4, characterized in that: The method of obtaining characteristic data affecting imaging stability based on imaging data, environmental sensor data, and operating status data of the optical microscope to be tested includes: According to the environmental sensor data of the optical microscope to be tested, the difference between the maximum and minimum humidity values ​​in the past n time steps is calculated to obtain the humidity fluctuation range of the optical microscope to be tested in the past n time steps; According to the environmental sensor data of the optical microscope to be tested, the humidity difference between adjacent time steps is calculated to obtain the humidity change trend.

7. The optical stability evaluation and prediction method based on the improved LSTM model according to claim 4, characterized in that: The method of obtaining characteristic data affecting imaging stability based on imaging data, environmental sensor data, and operating status data of the optical microscope to be tested includes: According to the environmental sensor data of the optical microscope to be tested, the maximum value of the vibration acceleration of the optical microscope to be tested in n time steps is obtained as the peak value of the vibration acceleration of the optical microscope to be tested in n time steps.

8. The optical stability evaluation and prediction method based on the improved LSTM model according to claim 4, characterized in that: The method of obtaining characteristic data affecting imaging stability based on imaging data, environmental sensor data, and operating status data of the optical microscope to be tested includes: According to the imaging data, environmental sensor data and operating status data of the optical microscope to be tested, the time domain vibration signal is converted into a frequency domain signal through fast Fourier transform, and the main vibration frequency component is obtained as the vibration frequency characteristic.

9. The optical stability evaluation and prediction method based on the improved LSTM model according to claim 4, characterized in that: The method of obtaining characteristic data affecting imaging stability based on imaging data, environmental sensor data, and operating status data of the optical microscope to be tested includes: According to the imaging data of the optical microscope to be tested, the Laplace operator is used to perform edge detection on the imaging data to obtain the image edge intensity sum of the optical microscope to be tested as the image clarity score.

10. The optical stability evaluation and prediction method based on the improved LSTM model according to any one of claims 1 to 9, characterized in that: The optical microscope imaging stability evaluation model includes l stacked LSTM layers, a feature splicing module and a fully connected layer including a Dropout mechanism, wherein an attention mechanism layer is arranged between adjacent LSTM layers in the l stacked LSTM layers, the fully connected layer includes two hidden layers and an output layer, and the Dropout mechanism acts on the two hidden layers, wherein the first LSTM layer in the l stacked LSTM layers is arranged to receive environmental sensor data and operating status data of the optical microscope to be tested, the output of the lth LSTM layer in the l stacked LSTM layers is used as the input of the feature splicing module, the output of the feature splicing module is used as the input of the hidden layer of the fully connected layer, the output of the hidden layer in the fully connected layer is used as the input of its output layer, and the output layer of the fully connected layer is arranged to output the imaging stability evaluation result of the optical microscope to be tested.

11. The optical stability evaluation and prediction method based on the improved LSTM model according to any one of claims 1 to 9, characterized in that: The imaging stability evaluation result of the optical microscope to be tested is obtained by using an optical microscope imaging stability evaluation model based on the imaging data, environmental sensor data, and operating status data of the optical microscope to be tested, including: According to the imaging data, environmental sensor data and operating status data of the optical microscope to be tested, the imaging stability evaluation model of the optical microscope is used to obtain the imaging stability evaluation score of the optical microscope to be tested by using the imaging stability evaluation expression; The imaging stability evaluation score of the optical microscope to be tested is compared with a preset range to obtain an imaging stability evaluation result of the optical microscope to be tested.

12. The optical stability evaluation and prediction method based on the improved LSTM model according to claim 11, characterized in that: The imaging stability evaluation expression is: In the imaging stability evaluation expression, A1, B2,…, Z N represents the feature data that affects the imaging stability in the imaging data, environmental sensor data, and operating status data of the optical microscope to be tested. α, β, …, ζ represent the dynamic weights of the corresponding feature data. S represents the imaging stability evaluation score of the optical microscope to be tested.

13. The optical stability evaluation and prediction method based on the improved LSTM model according to claim 11, characterized in that: The step of comparing the imaging stability evaluation score of the optical microscope to be tested with a preset range to obtain an imaging stability evaluation result of the optical microscope to be tested includes: When the imaging stability evaluation score of the optical microscope to be tested is outside a preset range and is less than a minimum value within the preset range, determining that the imaging stability evaluation result of the optical microscope to be tested is that the imaging stability has decreased, and obtaining influencing factors affecting the imaging stability based on the environmental sensor data and the operating status data of the optical microscope to be tested, and issuing a warning signal and the influencing factors affecting the imaging stability; When the imaging stability evaluation score of the optical microscope to be tested is within a preset range, the imaging stability evaluation result of the optical microscope to be tested is determined to be passing; When the imaging stability evaluation score of the optical microscope to be tested is outside the preset range and higher than the maximum value within the preset range, it is determined that the imaging stability evaluation result of the optical microscope to be tested is that the imaging stability has increased.

14. An optical stability evaluation and prediction system based on an improved LSTM model, characterized in that: include: A data acquisition module is used to obtain imaging data, environmental sensor data and operating status data of the optical microscope to be tested; The optical microscope imaging stability evaluation module is used to obtain the imaging stability evaluation result of the optical microscope to be tested based on the imaging data, environmental sensor data and operating status data of the optical microscope to be tested through the optical microscope imaging stability evaluation model, wherein the optical microscope imaging stability evaluation model is an improved LSTM model.

15. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the optical stability evaluation and prediction method based on the improved LSTM model as described in any one of claims 1 to 13 is implemented.

16. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the optical stability evaluation and prediction method based on the improved LSTM model as described in any one of claims 1 to 13.

Images