Real-time image acquisition and processing system and method based on LabVIEW technology

Abstract

The invention discloses an image real-time acquisition and processing system and method based on a LabVI EW technology, particularly relates to the field of data processing, is used for solving the problem of closed-loop control between a LabVI EW platform and external image acquisition equipment, and is used for analyzing a parameter instruction sent by the LabVI EW and a parameter adjustment result returned by the image acquisition equipment through speed and consistency. And evaluating the closed-loop control stability and risk, calculating a closed-loop control stability coefficient by using a parameter adjustment response degree index and a consistency index, and finally determining a closed-loop control risk level. And identifying a risk mode by analyzing a closed-loop control stability coefficient and risk classification in combination with a time sequence and Kalman filtering. According to the method, multi-dimensional features are utilized to construct and evaluate the risk persistence and similarity, and the persistence risk is determined through clustering, so that the contingency of a single event can be eliminated, and the accurate evaluation of the closed-loop risk problem between the LabVI EW and the image acquisition equipment is ensured.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and more specifically, to a real-time image acquisition and processing system and method based on LabVIEW technology. Background Art

[0002] LabVIEW is a platform for image processing. It acquires real-time image data through image acquisition devices and processes, analyzes and displays them.

[0003] In order to better ensure the acquisition effect, the existing image acquisition devices have the ability to self-adjust parameters, and LabVIEW also has the function of controlling the image acquisition device, so there is a question of whether the image acquisition device follows its own self-adjustment control parameter settings or follows the control of LabVIEW. Collectively referred to as the "closed-loop control" problem. In this case, it is easy to cause the following problems: inconsistency in parameter adjustment, communication delays and conflicts, system performance degradation, and difficulty in debugging and maintenance. Closed-loop control problems may cause inconsistency in parameter adjustment, communication delays and conflicts, system performance degradation, and difficulty in debugging and maintenance, affecting the stability, accuracy and performance of the system. Therefore, it is necessary to identify and understand potential closed-loop control problems in a timely manner to ensure smooth collaboration between LabVIEW and image acquisition devices to achieve efficient operation of the system and optimize performance.

[0004] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a real-time image acquisition and processing system and method based on LabVIEW technology, which analyzes the parameter instructions sent by LabVIEW and the parameter adjustment results returned by the image acquisition device through speed and consistency, evaluates the stability and risk of the closed-loop control, and calculates the closed-loop control stability coefficient using the parameter adjustment response index and consistency index, and finally determines the closed-loop control risk level. By analyzing the closed-loop control stability coefficient and risk classification, combined with time series and Kalman filtering, risk patterns are identified. Using multi-dimensional feature construction, evaluating risk persistence and similarity, and determining persistent risks through clustering, it helps to eliminate the randomness of single events and ensure accurate evaluation of closed-loop risk issues between LabVIEW and image acquisition devices, so as to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: Step S1, connecting LabVIEW and an image acquisition device according to a communication protocol and a corresponding driver;

[0007] Step S2, analyzing the speed and consistency results between the parameter instructions sent by LabVIEW and the parameter adjustment results returned by the image acquisition device, clarifying the stability of the closed-loop control between LabVIEW and the image acquisition device, identifying potential hidden problems of the closed-loop control and classifying them;

[0008] In step S3, the closed-loop control stability and risk dynamic characteristics are evaluated through time series analysis and feature extraction, and cluster analysis is used to find out the persistent risks and determine the risk level of the closed-loop problems of LabVIEW and image acquisition equipment.

[0009] In a preferred embodiment, step S2 includes the following contents:

[0010] After LabVIEW and the image acquisition device are connected, the parameter adjustment response index and consistency index are calculated and analyzed based on the collected interaction data between LabVIEW and the image acquisition device.

[0011] In a preferred embodiment, the process of obtaining the parameter adjustment response index is as follows:

[0012] Step S2-1, setting the target value, which indicates the parameter that the image acquisition device is expected to adjust. After sending the instruction, the image acquisition device returns the actual parameter value to the LabVIEW platform, and this value is the actual value;

[0013] Step S2-2, calculating the difference between the target value and the actual value, the calculation formula is: e(t) = Setpoint-ProcessVariable;

[0014] Among them, Setpoint and ProcessVariable represent the target value and actual value respectively;

[0015] Step S2-3, calculate the controller output, the calculation formula is:

[0016]

[0017] in:

[0018] CS(t) represents the output of the controller;

[0019] e(t) represents the difference between the target value and the actual value;

[0020] Indicates the cumulative value of the difference between the target value and the actual value;

[0021] Indicates the rate of change of the difference between the target value and the actual value;

[0022] K p , Ki and K d Represent the coefficients of proportional, integral and differential parts respectively;

[0023] Step S2-4, obtaining the parameter adjustment response index, the calculation formula is:

[0024] in:

[0025] Rta represents the parameter adjustment response index;

[0026] T S and T F They are the timestamps of sending instructions and receiving results respectively;

[0027] CS(t) represents the output value of the controller at the current moment;

[0028] CS(t-Δt) represents the output value of the controller at the previous moment.

[0029] In a preferred embodiment, the process of obtaining the degree of data consistency is as follows:

[0030] Step S2-21, the parameter instruction sent by LabVIEW and the parameter adjustment result returned by the image acquisition device are represented as two time series data, respectively recorded as X(t) and Y(t), where t represents time;

[0031] Step S2-22, calculate the covariance matrix between X(t) and Y(t), taking into account the dynamic and nonlinear characteristics of time series data:

[0032] Among them, μ X and μ Y They represent the means of X(t) and Y(t), respectively, and T represents the length of the time series;

[0033] Step S2-23, based on the complexity measurement method of information theory, the complexity of the dynamic change characteristics of X(t) and Y(t) is calculated:

[0034]

[0035] Among them, σ X (t) and σ Y (t) represents the standard deviation of X(t) and Y(t), respectively;

[0036] Step S2-24, using the Pearson correlation coefficient analysis method to calculate the correlation ρ between X(t) and Y(t);

[0037] Step S2-25, combining the results of correlation analysis, covariance analysis and complexity analysis, obtains the consistency index, which is calculated as follows:

[0038] Among them, Con is the consistency index, ρ is the correlation coefficient, Cov(X(t), Y(t)) is the covariance, and C(X(t)) and C(X(t)) are the complexity measures of the data.

[0039] In a preferred embodiment, the parameter adjustment response degree index and the consistency index are dimensionlessly converted and normalized to obtain a closed-loop control stability coefficient, and the closed-loop control stability coefficient is compared with the first stability threshold and the second stability threshold, respectively; if the closed-loop control stability coefficient is less than the first stability threshold, a high-risk signal is generated; if the first stability threshold is less than or equal to the closed-loop control stability coefficient and less than the second stability threshold, a medium-risk signal is generated; if the closed-loop control stability coefficient is greater than or equal to the second stability threshold, a low-risk signal is generated.

[0040] In a preferred embodiment, step S3 includes the following contents:

[0041] Step S3-1, collecting all closed-loop control stability coefficients and corresponding risk classification results, and normalizing each closed-loop control stability coefficient;

[0042] Step S3-2, performing time series analysis on the risk classification results of all time periods, converting the risk classification labels in each time period into numerical representations to form a time series;

[0043] Using sliding window technology, the Kalman filter algorithm is used to calculate the frequency and duration of each risk classification in different time windows;

[0044] Step S3-3, using the time series analysis method, converting the risk classification results into a high-dimensional time series matrix;

[0045] Use phase space reconstruction to deeply mine the time series matrix and extract its temporal dynamic features;

[0046] Based on the extracted temporal dynamic features, a multidimensional time series feature space is constructed, and the weighted sum of the distances between various features is used as the distance metric to measure the similarity and persistence of risk classifications in different time periods;

[0047] Using the K cluster analysis method, the temporal dynamic characteristics are clustered and classified, and the risk accumulation index of each cluster is calculated;

[0048] Step S3-4, statistics and analysis are performed on the risk accumulation index obtained for each cluster to find the cluster with the highest risk accumulation index, that is, the candidate set of persistent risks.

[0049] In a preferred embodiment, step S3-5 extracts a candidate set of persistent risks, averages the values ​​corresponding to the risk classifications, rounds off the values ​​to one decimal place, converts the rounded values ​​into risk classification labels, and determines the risk level of the closed-loop problem between LabVIEW and the image acquisition device based on the risk classification labels.

[0050] The real-time image acquisition and processing system based on LabVIEW technology includes a connection module, a closed-loop stabilization module, a risk measurement module, and a pair analysis module;

[0051] The connection module configures and establishes the communication connection between LabVIEW and the image acquisition device according to the communication protocol and the corresponding driver;

[0052] The closed-loop stability module analyzes the speed and consistency between the parameter instructions sent by LabVIEW and the parameter adjustment results returned by the image acquisition device, clarifies the stability of the closed-loop control between LabVIEW and the image acquisition device, and sends the processing results to the risk measurement module;

[0053] The risk measurement module identifies and classifies potential hidden problems in closed-loop control, and sends the classification results to the pair analysis module;

[0054] The pair analysis module evaluates the closed-loop control stability and risk dynamic characteristics through time series analysis and feature extraction, and uses cluster analysis to identify persistent risks and determine the risk level of closed-loop problems in LabVIEW and image acquisition equipment.

[0055] The technical effects and advantages of the real-time image acquisition and processing system and method based on LabVIEW technology of the present invention are as follows:

[0056] 1. The present invention evaluates the stability and risk of closed-loop control by performing speed and consistency analysis on the parameter instructions sent by LabVIEW and the parameter adjustment results returned by the image acquisition device, and calculates the closed-loop control stability coefficient by using the parameter adjustment response degree index and consistency index combined with dimensionless processing. Finally, the closed-loop control risk level between LabVIEW and the image acquisition device is determined according to the size of the stability coefficient.

[0057] 2. The present invention quantifies the closed-loop control stability coefficients and risk classification results, uses time series analysis and Kalman filter algorithms to identify the pattern and persistence of risks, and more accurately assesses the severity of risks. Then, phase space reconstruction and multi-dimensional time series feature space construction are used to extract temporal dynamic features, and the similarity and persistence of risk classifications in different time periods are evaluated by distance metrics. With the help of the K clustering analysis method, the risk accumulation indicators are clustered to determine the candidate set of persistent risks. Such a processing process helps to eliminate the contingency of single events. Through multiple analyses and comprehensive evaluations, the closed-loop risk problem between LabVIEW and the image acquisition device can be judged more accurately, ensuring that the evaluation results are more stable and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a flowchart of the real-time image acquisition and processing method based on LabVIEW technology of the present invention;

[0059] Figure 2 It is a structural schematic diagram of the real-time image acquisition and processing system based on LabVIEW technology of the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] Example 1

[0062] Figure 1 The present invention provides a real-time image acquisition and processing method based on LabVIEW technology, comprising:

[0063] Step S1, connecting LabVIEW and an image acquisition device according to a communication protocol and a corresponding driver;

[0064] Step S2, analyzing the speed and consistency results between the parameter instructions sent by LabVIEW and the parameter adjustment results returned by the image acquisition device, clarifying the stability of the closed-loop control between LabVIEW and the image acquisition device, identifying potential hidden problems of the closed-loop control and classifying them;

[0065] Step S3, through time series analysis and feature extraction, evaluate the closed-loop control stability and risk dynamic characteristics, combine with cluster analysis to find out the persistent risks, and determine the risk level of the closed-loop problems of LabVIEW and image acquisition equipment.

[0066] Step S1 includes the following contents:

[0067] Step S1-1, LabVIEW can connect to the image acquisition device through various communication protocols (such as USB, Ethernet, RS-232, etc.). This involves using the adapter or communication module provided by LabVIEW to establish a communication connection and ensure that LabVIEW can exchange data with the image acquisition device;

[0068] Step S1-2, for image acquisition devices of different models and brands, realize connection and communication with LabVIEW according to corresponding drivers or interfaces. These drivers are provided by device manufacturers, or there are third-party drivers available in the LabVIEW community;

[0069] Step S1-3, using the control and analysis modules of LabVIEW to collect the interaction data between LabVIEW and the image acquisition device.

[0070] This includes using the graphical programming tools provided by LabVIEW to design the data acquisition process, data processing logic, and control strategy. By calling related functions and modules, users can control and monitor image acquisition devices, collect real-time data, and analyze them. Optimizing the performance of these algorithms and modules can improve the efficiency and accuracy of data interaction between LabVIEW and image acquisition devices, thereby achieving efficient management and optimization of image acquisition devices.

[0071] Step S2 includes the following contents:

[0072] After LabVIEW and the image acquisition device are combined, the parameter adjustment response index and consistency index are calculated and analyzed based on the collected interaction data between LabVIEW and the image acquisition device.

[0073] When analyzing the closed-loop problem of parameter adjustment between LabVIEW and image acquisition devices, it is necessary to analyze the speed at which LabVIEW sends parameter adjustment instructions to the image acquisition device and receives the parameter adjustment results returned by the device, as well as the data consistency between the parameter instructions sent by LabVIEW and the parameter adjustment results returned by the image acquisition device. This is because they provide important information about the stability of the closed-loop control. First, analyzing the speed at which LabVIEW sends parameter adjustment instructions to the image acquisition device and receives the parameter adjustment results returned by the device can help evaluate the response speed of the closed-loop system. If the response speed of parameter adjustment is fast, it means that the system can achieve real-time parameter adjustment and feedback, which helps to improve the stability and performance of the system. Second, analyzing the data consistency between the parameter instructions sent by LabVIEW and the parameter adjustment results returned by the image acquisition device can help evaluate the accuracy and stability of the closed-loop control. If the data consistency between the two is high, it means that the change trend and correlation between the parameter instructions and the adjustment results are good, and the system can stably achieve the expected parameter adjustment. Comprehensive analysis of these two data can help identify and understand the parameter control stability problems existing in closed-loop control, and provide an important basis for problem diagnosis and performance optimization.

[0074] The parameter adjustment response index is of great significance for identifying and understanding potential closed-loop control problems. By analyzing the speed of sending instructions and receiving results when LabVIEW sends parameter adjustment instructions to the image acquisition device and receives the parameter adjustment results returned by the device, the real-time performance and responsiveness of the system can be evaluated. If the parameter adjustment response index is small, it means that the speed of sending instructions and receiving results is slow, and there may be communication delays or untimely responses. This may imply that the collaboration between LabVIEW and the image acquisition device is not smooth, the system's ability to adapt to changes in the external environment is poor, and there are closed-loop control problems. Therefore, by monitoring and analyzing the parameter adjustment response index, potential closed-loop control problems can be discovered in a timely manner, and corresponding measures can be taken to optimize and improve them, thereby improving the stability and performance of the system.

[0075] The process of obtaining the parameter adjustment response index is as follows:

[0076] Step S2-1, setting the target value, which indicates the parameter that the image acquisition device is expected to adjust. After sending the instruction, the image acquisition device returns the actual parameter value to the LabVIEW platform, and this value is the actual value;

[0077] In a PID control system, the set target value (Setpoint) is used to indicate the desired state or value that the system is expected to achieve. Specifically, the target value indicates the ideal value that the control system expects the system output to achieve during the control process. In the context of parameter adjustment, the target value usually indicates the parameter value that the system is expected to adjust to, such as temperature, speed, position, etc.

[0078] The purpose of setting the target value is to guide the behavior of the control system and adjust it in the expected direction so that the system output is as close to or as close to the set target value as possible. The control system will continuously compare with the target value and adjust the controller output according to the error to achieve regulation and control of the system.

[0079] In PID control, the controller will continuously adjust the system output to make the system output as close to the target value as possible, so as to achieve precise control of the system. Setting the target value is a crucial step in the PID control system, which directly affects the control effect and performance of the system.

[0080] Step S2-2, the error represents the difference between the target value and the actual value, and is calculated as follows: e(t) = Setpoint - ProcessVariable;

[0081] Among them, Setpoint and ProcessVariable represent the target value and actual value respectively;

[0082] Step S1-3, calculate the controller output, the calculation formula is:

[0083]

[0084] in:

[0085] CS(t) represents the output of the controller;

[0086] e(t) represents the difference between the target value and the actual value;

[0087] Indicates the cumulative value of the difference between the target value and the actual value;

[0088] Indicates the rate of change of the difference between the target value and the actual value;

[0089] K p , K i and K d Represent the coefficients of the proportional, integral, and differential parts respectively.

[0090] The proportional coefficient controls the influence of the proportional part, indicating the reaction speed of the controller to the current error, that is, the linear relationship between the controller output and the error;

[0091] The integral coefficient controls the influence of the integral part, indicating the degree of reaction of the controller to the accumulated value of the error, and is used to eliminate the static error of the system;

[0092] The differential coefficient controls the influence of the differential part, indicating the degree of response of the controller to the error change rate, and is used to suppress system oscillation and stabilize system response.

[0093] According to the output of the controller, the parameters of the image acquisition device are adjusted, including sending corresponding instructions or signals to the image acquisition device.

[0094] Step S2-3, obtaining the parameter adjustment response index, the calculation formula is:

[0095] in:

[0096] Rta represents the parameter adjustment response index;

[0097] T S and T F They are the timestamps of sending instructions and receiving results respectively;

[0098] CS(t) represents the output value of the controller at the current moment;

[0099] CS(t-Δt) represents the output value of the controller at the previous moment.

[0100] The parameter adjustment responsiveness index is used to evaluate the speed of sending and receiving parameters when LabVIEW sends parameter adjustment commands to the image acquisition device and receives the parameter adjustment results returned by the device.

[0101] Specifically, the faster the parameter adjustment response index is, the faster the system can complete the parameter adjustment in a shorter time and feedback the results in a timely manner, thereby achieving real-time parameter adjustment and feedback. Conversely, the slower the parameter adjustment response index is, the longer it takes for the system to complete the parameter adjustment and feedback the results.

[0102] The parameter adjustment response index is closely related to the smoothness of the collaboration between LabVIEW and the image acquisition device. Specifically, the larger the parameter adjustment response index, the faster LabVIEW sends parameter adjustment instructions to the image acquisition device and receives the parameter adjustment results returned by the device, that is, the better the collaboration smoothness.

[0103] Good collaboration smoothness means that LabVIEW can send parameter adjustment instructions in a timely manner, and the image acquisition device can respond quickly and return the parameter adjustment results. This efficient collaboration can achieve real-time parameter adjustment and feedback, thereby improving the stability and performance of the system. On the contrary, if the parameter adjustment response index is small, it means that the collaboration smoothness between LabVIEW and the image acquisition device is poor, which may cause delays in sending instructions or receiving results, reducing the response speed and stability of the system.

[0104] Therefore, the size of the parameter adjustment response index directly reflects the smoothness of the collaboration between LabVIEW and the image acquisition device, and is one of the important indicators for evaluating system performance and stability.

[0105] The process of obtaining data consistency is as follows:

[0106] Step S2-11, the parameter instruction sent by LabVIEW and the parameter adjustment result returned by the image acquisition device are represented as two time series data, respectively recorded as X(t) and Y(t), where t represents time;

[0107] Step S2-22, calculate the covariance matrix between X(t) and Y(t), taking into account the dynamic and nonlinear characteristics of time series data:

[0108] Among them, μ X and μ Y They represent the means of X(t) and Y(t) respectively, and T represents the length of the time series.

[0109] The covariance matrix is ​​used to measure whether the trends of two variables are similar, that is, whether they change in a similar way. A larger covariance means that the trends of the two variables are similar, otherwise they are not similar.

[0110] Step S2-23, based on the complexity measurement method of information theory, the complexity of the dynamic change characteristics of X(t) and Y(t) is calculated:

[0111]

[0112] Among them, σ X (t) and σ Y (t) represents the standard deviation of X(t) and Y(t), respectively;

[0113] Complexity analysis is used to evaluate the dynamic change characteristics of data and describe its dynamics by measuring the complexity of the data.

[0114] Step S2-24, using the Pearson correlation coefficient analysis method to calculate the correlation ρ between X(t) and Y(t);

[0115] Correlation analysis is used to measure the degree of linear relationship between two variables and evaluate their correlation by calculating the correlation coefficient. The correlation coefficient reflects whether the changing trends of the two variables are consistent. A value close to 1 indicates a positive correlation, a value close to -1 indicates a negative correlation, and a value close to 0 indicates no correlation.

[0116] Step S2-25, combining the results of correlation analysis, covariance analysis and complexity analysis, obtains the consistency index, which is calculated as follows:

[0117] Among them, Con is the consistency index, ρ is the correlation coefficient, Cov(X(t), Y(t)) is the covariance, and C(X(t)) and C(X(t)) are the complexity measures of the data.

[0118] The consistency index is used to indicate the data consistency between the parameter instructions sent by LabVIEW and the parameter adjustment results returned by the image acquisition device. This index reflects the data change trend and correlation between the two, that is, whether they change in the same direction and the degree of change. If the consistency index is large, it means that the data consistency between the two is high, that is, the change trend between the parameter instructions and the adjustment results is highly consistent, and the amplitude of the change is relatively consistent. This means that the parameter adjustment of the system is accurate and stable, and can ensure high performance and reliability of the system. On the contrary, if the consistency index is small, it means that the data consistency between the two is low, that is, the change trend between the parameter instructions and the adjustment results is not consistent enough, or there is a large difference in the amplitude of the change. This may lead to inaccuracy and instability of the system parameter adjustment, which in turn affects the performance and reliability of the system. Therefore, the size of the consistency index can reflect the accuracy and stability level of the system parameter adjustment, which is of great significance to the performance and reliability of the system.

[0119] The parameter adjustment response index and consistency index are dimensionless and normalized to obtain the closed-loop control stability coefficient. For example, it can be calculated by the following calculation formula:

[0120]

[0121] Wherein, S represents the closed-loop control stability index, Rta′ represents the normalized parameter adjustment response index, Con′ represents the normalized consistency index, and w1 and w2 are the preset proportional coefficients of the normalized parameter adjustment response index and the normalized consistency index, respectively.

[0122] The larger the closed-loop control stability coefficient, the more stable the closed-loop control effect between LabVIEW and the image acquisition device, the higher the accuracy and stability of parameter adjustment, and the better the system performance and reliability. This means that the system can achieve the desired parameter adjustment more accurately and remain stable in a dynamic environment. On the contrary, the smaller the closed-loop control stability coefficient, the potential closed-loop control problem may cause inaccurate or unstable parameter adjustment, which in turn affects the performance and reliability of the system. For the parameter condition problem of LabVIEW and the image acquisition device, when the closed-loop control stability coefficient is large, it may indicate that the parameter conditions are relatively good and the system can stably achieve the expected parameter adjustment; when the closed-loop control stability coefficient is small, it may indicate that there is a problem of poor parameter conditions, which requires further investigation and optimization.

[0123] Compare the closed-loop control stability coefficient with the first stability threshold and the second stability threshold respectively;

[0124] If the closed-loop control stability coefficient is less than the first stability threshold, it means that the stability of the closed-loop control system is poor, there is a greater risk, there are serious problems of inaccurate parameter adjustment or closed-loop control failure, and timely adjustment and optimization are required, indicating that there is a serious risk in image acquisition, and a high-risk signal is generated;

[0125] If the first stability threshold is less than or equal to the closed-loop control stability coefficient and less than the second stability threshold, it means that the stability of the closed-loop control system is average, there is a certain risk, some parameters are not adjusted accurately or the closed-loop control effect is not ideal, further monitoring and improvement are needed, and a medium-risk signal is generated;

[0126] The closed-loop control stability coefficient is greater than or equal to the second stability threshold, indicating that the closed-loop control system has good stability, low risk, high parameter adjustment accuracy and stability, good closed-loop control effect, guaranteed system performance and reliability, and generates a low-risk signal.

[0127] The invention evaluates the stability and risk of closed-loop control by performing speed and consistency analysis on parameter instructions sent by LabVIEW and parameter adjustment results returned by image acquisition devices, calculates the closed-loop control stability coefficient by using parameter adjustment response degree index and consistency index combined with dimensionless processing, and finally determines the closed-loop control risk level between LabVIEW and image acquisition devices according to the size of the stability coefficient.

[0128] Step S3 includes the following contents:

[0129] Step S3-1, collecting all closed-loop control stability coefficients and corresponding risk classification results, and normalizing each closed-loop control stability coefficient to ensure that data of different magnitudes can be compared;

[0130] Step S3-2, performing time series analysis on the risk classification results of all time periods, converting the risk classification labels in each time period into numerical representations to form a time series;

[0131] This can be achieved by mapping risk classification labels to numeric codes, for example, high risk is coded as 3, medium risk is coded as 2, and low risk is coded as 1.

[0132] Using sliding window technology, the Kalman filter algorithm is used to calculate the frequency and duration of each risk classification in different time windows;

[0133] The sliding window technique combined with the Kalman filter algorithm can be used to calculate the frequency and duration of each risk classification in different time windows. The following are the specific steps and examples:

[0134] First, determine the size and step size of the sliding window. The window size indicates the length of the time period considered during each sliding process, while the step size indicates the interval between each movement of the sliding window.

[0135] Obtain timestamps and corresponding risk classification label data from previous risk classification results;

[0136] Apply sliding window technology to risk classification data to divide time series data into multiple windows, each containing continuous time period data;

[0137] The risk classification data in each window is processed using the Kalman filter algorithm. In this process, the Kalman filter is used to smooth the risk classification label data to reduce the impact of noise and extract the frequency and duration information of the risk classification;

[0138] Count the frequency of each risk classification in each window, that is, the number of times the risk classification appears in the time period;

[0139] For each risk category that appears in a window, calculate its duration, that is, the length of time that the risk category exists continuously in the window;

[0140] The calculated frequency and duration data are statistically analyzed to assess the occurrence pattern and persistence of risk categories.

[0141] Example:

[0142] Assume that there is a set of historical risk classification data as follows (assuming that each time point represents a window):

[0143] Time window 1: [A,A,B,A,C]

[0144] Time window 2: [A,B,B,C,C]

[0145] Time window 3: [B,B,B,C,C]

[0146] Time window 4: [A,A,B,B,C]

[0147] Now we perform sliding window processing with a window size of 5 and a step size of 1. For each window, we apply the Kalman filter algorithm to process the risk classification data and calculate the frequency and duration of each risk classification within the window.

[0148] For example, in the first window, the frequency of occurrence of risk category A is 3 / 5=0.6, and the duration is 2 time points; the frequency of occurrence of risk category B is 2 / 5=0.4, and the duration is 1 time point; the frequency of occurrence of risk category C is 1 / 5=0.2, and the duration is 1 time point.

[0149] Step S3-3, using the time series analysis method, converting the risk classification results into a high-dimensional time series matrix;

[0150] Divide time into different windows, each of which represents the risk classification results within a period of time. The selection of this time window can be determined according to actual conditions, for example, every day, every week or every month as a time window.

[0151] For each risk classification result in each time window, it is necessary to encode it and convert it into a vector or matrix. The dimension of this vector or matrix depends on the number of all possible risk classification categories. For example, if there are 3 risk classification categories (A, B, C), a vector of length 3 can be used to represent the number of occurrences or probabilities of each risk in each time window.

[0152] After encoding the risk classification results in each time window, they are combined into a time series matrix. In this matrix, each row represents a time window, each column represents a risk classification category, and the elements in the matrix represent the number of occurrences or probabilities of each type of risk in the corresponding time window.

[0153] This time series matrix is ​​a high-dimensional data structure, where the number of dimensions depends on the number of risk classification categories and the number of time windows. This high-dimensional representation can help better understand the evolution and trend of risk classification results and provide a basis for subsequent analysis.

[0154] Use phase space reconstruction to deeply mine the time series matrix and extract its temporal dynamic features;

[0155] Treat each row in the time series matrix (representing a time window) as a data point and construct these data points into a phase space;

[0156] In phase space reconstruction, it is necessary to select a suitable delay embedding parameter to construct the phase space. The delay embedding parameter is usually determined by the characteristics of the time series and the specific application scenario. Common selection methods include the autocorrelation function method, the mutual information method, etc.

[0157] According to the selected delay embedding parameters, a delay embedding matrix is ​​constructed from the time series matrix. Each row of the delay embedding matrix represents a delay embedding vector, which contains the information of the current time point and several time points before it;

[0158] Each row in the delay embedding matrix is ​​taken as a data point to construct the phase space. Each data point in the phase space corresponds to a delay embedding vector, which reflects the dynamic characteristics of the time series data;

[0159] Use dimensionality reduction methods (such as principal component analysis, manifold learning, etc.) to reduce the dimensionality of the phase space and project it into a low-dimensional space;

[0160] In the low-dimensional space after dimensionality reduction, various feature extraction methods (such as eigenvalue analysis, frequency domain analysis, nonlinear dynamic feature extraction, etc.) are used to extract the dynamic features of time series data. These features can reflect the dynamic characteristics of time series data such as periodicity, trend, and period multiples.

[0161] Based on the extracted temporal dynamic features, a multidimensional time series feature space is constructed, and the weighted sum of the distances between various features is used as the distance metric to measure the similarity and persistence of risk classifications in different time periods;

[0162] Select appropriate time dynamic features as the dimensions for constructing a multi-dimensional time series feature space. These features can include dynamic features such as periodicity, trend, and volatility;

[0163] The temporal dynamic features extracted in each time period are combined into a feature vector;

[0164] The feature vector of each time period is taken as a data point to construct a multi-dimensional time series feature space. Then each time period corresponds to a data point in the feature space;

[0165] In the feature space, a complex distance metric is defined to measure the similarity and persistence of risk classifications in different time periods. This distance metric can take into account the correlation between features of different dimensions and comprehensively consider the importance and weight of each feature.

[0166] Assume that there are two feature vectors X and Y, which represent the risk classification features in two different time periods. Define a complex distance metric D(X,Y) to measure the similarity between X and Y. This distance metric can include distance calculations and weighted summations between various features to comprehensively consider the contribution and importance of each feature.

[0167] According to the defined distance metric, the corresponding distance is calculated for each pair of feature vectors of time periods. These distance values ​​reflect the similarity and continuity of risk classifications in different time periods. Smaller distance values ​​indicate that risk classifications are more similar, while larger distance values ​​indicate that risk classifications are more different.

[0168] Using the K cluster analysis method, the temporal dynamic characteristics are clustered and classified, and the risk accumulation index of each cluster is calculated;

[0169] 1. Determine the K value, that is, the number of clusters. Determine the appropriate number of clusters by manual selection or using some heuristic methods (such as the elbow rule);

[0170] 2. Randomly select K data points as the initial cluster centers;

[0171] 3. For each data point, calculate its distance from each cluster center and assign it to the category corresponding to the cluster center closest to it;

[0172] 4. For each cluster, calculate the average value of all its data points and update the cluster center to the point corresponding to these average values;

[0173] 5. Repeat steps 3 and 4 until the cluster center no longer changes or the predetermined number of iterations is reached;

[0174] 6. Based on the clustering results, the sum of the distances of the data points within the cluster is statistically calculated as a risk accumulation indicator to assess the risk level of the cluster.

[0175] Step S3-4, statistics and analysis are performed on the risk accumulation index obtained for each cluster to find the cluster with the highest risk accumulation index, that is, the candidate set of persistent risks.

[0176] Step S3-5, extract the candidate set of persistent risks, average the values ​​corresponding to the risk classification, round off the values ​​to one decimal place of the average value, convert the rounded values ​​into risk classification labels, and determine the risk level of the closed-loop problem between LabVIEW and the image acquisition device based on the risk classification labels.

[0177] The present invention quantifies the closed-loop control stability coefficients and risk classification results, uses time series analysis and Kalman filter algorithm to identify the pattern and persistence of risks, and more accurately assesses the severity of risks. Then, phase space reconstruction and multi-dimensional time series feature space construction are used to extract time dynamic features, and the similarity and persistence of risk classification in different time periods are evaluated by distance measurement. With the help of K clustering analysis method, the risk accumulation index is clustered to determine the candidate set of persistent risks. Such a processing process helps to eliminate the contingency of single events. Through multiple analyses and comprehensive evaluations, the closed-loop risk problem between LabVIEW and image acquisition equipment can be judged more accurately, ensuring that the evaluation results are more stable and reliable.

[0178] Example 2

[0179] Figure 2 The present invention provides a real-time image acquisition and processing system based on LabVIEW technology, including a connection module, a closed-loop stabilization module, a risk measurement module, and a pair analysis module;

[0180] The connection module configures and establishes the communication connection between LabVIEW and the image acquisition device according to the communication protocol and the corresponding driver;

[0181] The closed-loop stability module analyzes the speed and consistency between the parameter instructions sent by LabVIEW and the parameter adjustment results returned by the image acquisition device, clarifies the stability of the closed-loop control between LabVIEW and the image acquisition device, and sends the processing results to the risk measurement module;

[0182] The risk measurement module identifies and classifies potential hidden problems in closed-loop control, and sends the classification results to the pair analysis module;

[0183] The pair analysis module evaluates the closed-loop control stability and risk dynamic characteristics through time series analysis and feature extraction, and uses cluster analysis to identify persistent risks and determine the risk level of closed-loop problems in LabVIEW and image acquisition equipment.

[0184] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0185] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0186] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0187] In the several embodiments provided in the present application, it should be understood that the disclosed systems and devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0188] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0189] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0190] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0191] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0192] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A real-time image acquisition and processing method based on LabVIEW technology, characterized in that: Step S1, connecting LabVIEW and an image acquisition device according to a communication protocol and a corresponding driver; Step S2, analyzing the speed and consistency results between the parameter instructions sent by LabVIEW and the parameter adjustment results returned by the image acquisition device, clarifying the stability of the closed-loop control between LabVIEW and the image acquisition device, identifying potential hidden problems of the closed-loop control and classifying them; In step S3, the closed-loop control stability and risk dynamic characteristics are evaluated through time series analysis and feature extraction, and cluster analysis is used to find out the persistent risks and determine the risk level of the closed-loop problems of LabVIEW and image acquisition equipment.

2. The method for real-time image acquisition and processing based on LabVIEW technology according to claim 1, characterized in that: Step S2 includes the following contents: After LabVIEW and the image acquisition device are connected, the parameter adjustment response index and consistency index are calculated and analyzed based on the collected interaction data between LabVIEW and the image acquisition device.

3. The method for real-time image acquisition and processing based on LabVIEW technology according to claim 2, characterized in that: The process of obtaining the parameter adjustment response index is as follows: Step S2-1, setting the target value, which indicates the parameter that the image acquisition device is expected to adjust. After sending the instruction, the image acquisition device returns the actual parameter value to the LabVIEW platform, and this value is the actual value; Step S2-2, calculating the difference between the target value and the actual value, the calculation formula is: e(t) = Setpoint-ProcessVariable; Among them, Setpoint and ProcessVariable represent the target value and actual value respectively; Step S2-3, calculate the controller output, the calculation formula is: in: CS(t) represents the output of the controller; e(t) represents the difference between the target value and the actual value; Indicates the cumulative value of the difference between the target value and the actual value; Indicates the rate of change of the difference between the target value and the actual value; K p , K i and K d Represent the coefficients of proportional, integral and differential parts respectively; Step S2-4, obtaining the parameter adjustment response index, the calculation formula is: in: Rta represents the parameter adjustment response index; T S and T F They are the timestamps of sending instructions and receiving results respectively; CS(t) represents the output value of the controller at the current moment; CS(t-Δt) represents the output value of the controller at the previous moment.

4. The method for real-time image acquisition and processing based on LabVIEW technology according to claim 3 is characterized in that: The process of obtaining data consistency is as follows: Step S2-21, the parameter instruction sent by LabVIEW and the parameter adjustment result returned by the image acquisition device are represented as two time series data, respectively recorded as X(t) and Y(t), where t represents time; Step S2-22, calculate the covariance matrix between X(t) and Y(t), taking into account the dynamic and nonlinear characteristics of time series data: Among them, μ X and μ Y They represent the means of X(t) and Y(t), respectively, and T represents the length of the time series; Step S2-23, based on the complexity measurement method of information theory, the complexity of the dynamic change characteristics of X(t) and Y(t) is calculated: Among them, σ X (t) and σ Y (t) represents the standard deviation of X(t) and Y(t), respectively; Step S2-24, using the Pearson correlation coefficient analysis method to calculate the correlation ρ between X(t) and Y(t); Step S2-25, combining the results of correlation analysis, covariance analysis and complexity analysis, obtains the consistency index, which is calculated as follows: Among them, Con is the consistency index, ρ is the correlation coefficient, Cov(X(t), Y(t)) is the covariance, and C(X(t)) and C(X(t)) are the complexity measures of the data.

5. The real-time image acquisition and processing method based on LabVIEW technology according to claim 4 is characterized in that: The parameter adjustment response index and consistency index are dimensionlessly converted and normalized to obtain the closed-loop control stability coefficient, and the closed-loop control stability coefficient is compared with the first stability threshold and the second stability threshold respectively; if the closed-loop control stability coefficient is less than the first stability threshold, a high-risk signal is generated; if the first stability threshold is less than or equal to the closed-loop control stability coefficient and less than the second stability threshold, a medium-risk signal is generated; if the closed-loop control stability coefficient is greater than or equal to the second stability threshold, a low-risk signal is generated.

6. The real-time image acquisition and processing method based on LabVIEW technology according to claim 5 is characterized in that: Step S3 includes the following contents: Step S3-1, collecting all closed-loop control stability coefficients and corresponding risk classification results, and normalizing each closed-loop control stability coefficient; Step S3-2, performing time series analysis on the risk classification results of all time periods, converting the risk classification labels in each time period into numerical representations to form a time series; Using sliding window technology, the Kalman filter algorithm is used to calculate the frequency and duration of each risk classification in different time windows; Step S3-3, using the time series analysis method, converting the risk classification results into a high-dimensional time series matrix; Use phase space reconstruction to deeply mine the time series matrix and extract its temporal dynamic features; Based on the extracted temporal dynamic features, a multidimensional time series feature space is constructed, and the weighted sum of the distances between various features is used as the distance metric to measure the similarity and persistence of risk classifications in different time periods; Using the K cluster analysis method, the temporal dynamic characteristics are clustered and classified, and the risk accumulation index of each cluster is calculated; Step S3-4, statistics and analysis are performed on the risk accumulation index obtained for each cluster to find the cluster with the highest risk accumulation index, that is, the candidate set of persistent risks.

7. The real-time image acquisition and processing method based on LabVIEW technology according to claim 6 is characterized in that: Step S3-5, extract the candidate set of persistent risks, average the values ​​corresponding to the risk classification, round off the values ​​to one decimal place of the average value, convert the rounded values ​​into risk classification labels, and determine the risk level of the closed-loop problem between LabVIEW and the image acquisition device based on the risk classification labels.

8. A real-time image acquisition and processing system based on LabVIEW technology, used to implement the real-time image acquisition and processing method based on LabVIEW technology according to any one of claims 1 to 7, comprising: Connection module, closed-loop stability module, risk measurement module, pair analysis module; The connection module configures and establishes the communication connection between LabVIEW and the image acquisition device according to the communication protocol and the corresponding driver; The closed-loop stability module analyzes the speed and consistency between the parameter instructions sent by LabVIEW and the parameter adjustment results returned by the image acquisition device, clarifies the stability of the closed-loop control between LabVIEW and the image acquisition device, and sends the processing results to the risk measurement module; The risk measurement module identifies and classifies potential hidden problems in closed-loop control, and sends the classification results to the pair analysis module; The pair analysis module evaluates the closed-loop control stability and risk dynamic characteristics through time series analysis and feature extraction, and uses cluster analysis to identify persistent risks and determine the risk level of closed-loop problems in LabVIEW and image acquisition equipment.

Images