A virtual instrument data acquisition and processing method and system

Abstract

The present invention discloses a virtual instrument data acquisition and processing method and system, which relates to the field of data acquisition and processing technology, and includes the following steps: obtaining industrial production management data and available resources for acquisition and processing that change on industrial production lines due to different virtual instrument data acquisition and processing frequencies; constructing an acquisition and processing resource constraint model based on the available resources for acquisition and processing in combination with preset resource constraints to obtain acquisition and processing resource coefficients; establishing an evaluation model based on a machine learning algorithm based on the acquisition and processing resource coefficients in combination with industrial production management data to generate production line acquisition and processing evaluation coefficients; drawing a two-dimensional curve graph of the production line acquisition and processing evaluation coefficient in combination with the data acquisition frequency, and calculating the curve smoothness, and determining the optimal acquisition and processing frequency according to the curve smoothness. The present invention reduces the problems caused by the high and low virtual instrument data acquisition and processing frequencies to industrial production by determining the optimal acquisition and processing frequency.

Description

Technical Field

[0001] The present invention relates to the technical field of data acquisition and processing, and more specifically, to a virtual instrument data acquisition and processing method and system. Background Art

[0002] A virtual instrument is a software-based instrument system that implements the functions of traditional hardware instruments through a combination of computer software and hardware interfaces. Virtual instruments usually use general-purpose computer hardware and programmable measuring devices to implement instrument functions through custom application software.

[0003] Deficiencies of existing technologies:

[0004] In industrial automation, the acquisition and processing frequency of virtual instruments directly affects the efficiency and quality of the production process; if the acquisition frequency of virtual instruments is not high enough, real-time data monitoring will be affected, making it difficult to detect abnormal conditions in the production process in a timely manner, which may lead to equipment failure or safety hazards; high-frequency data acquisition and processing requires more computing resources, which may cause system overload, increase CPU and memory consumption, and may affect the execution of other important tasks, reducing overall production efficiency. Therefore, the present invention analyzes and determines the optimal acquisition and processing frequency to reduce the problems caused by the high or low frequency of virtual instrument data acquisition and processing on industrial production.

[0005] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0006] In order to overcome the above defects of the prior art, an embodiment of the present invention provides a virtual instrument data acquisition and processing method and system, which solves the problems raised in the above background technology by determining the optimal data acquisition and processing frequency.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A virtual instrument data acquisition and processing method and system, comprising the following steps: obtaining industrial production management data and available resources for acquisition and processing that change on an industrial production line due to different virtual instrument data acquisition and processing frequencies; constructing an acquisition and processing resource constraint model based on the available resources for acquisition and processing in combination with preset resource constraints to obtain an acquisition and processing resource coefficient; establishing an evaluation model based on a machine learning algorithm based on the acquisition and processing resource coefficient in combination with the industrial production management data to generate a production line acquisition and processing evaluation coefficient; drawing a two-dimensional curve graph of the production line acquisition and processing evaluation coefficient in combination with the data acquisition frequency, calculating the curve smoothness, and determining the optimal acquisition and processing frequency based on the curve smoothness.

[0009] In a preferred embodiment, the industrial production management data includes a production line operation efficiency coefficient and a fault monitoring coefficient, and the collected available resource amount includes a maximum threshold value for collected processing resources.

[0010] In a preferred embodiment, the method for obtaining the production line operation efficiency coefficient is as follows: establish a production line operation efficiency influencing model; input the collection and processing frequency of the production line, the length of time for each collection and processing, the completion status of the collection task, and the work efficiency of the team as feature data into the model; and standardize and normalize the feature data; model the model based on the complex nonlinear relationship between multi-layer network learning in the neural network; and use the back propagation algorithm to train the model, adjust the learning rate and the number of neural network layers; input the collection and processing frequency and the standardized and normalized feature data into the trained model, and the output prediction result is the production line operation efficiency coefficient.

[0011] In a preferred embodiment, the specific method for obtaining the fault monitoring coefficient is as follows: obtaining the acquisition and processing frequency of the industrial production line; collecting the operation signal data of the equipment, preprocessing the collected signal, using a filter to remove high-frequency and low-frequency noise, and obtaining a processed time domain signal; using the Fourier transform spectrum analysis method to convert the time domain signal into a frequency domain signal, plotting the frequency and amplitude into a spectrum diagram to display the frequency components of the signal; finding significant peaks in the spectrum diagram, which correspond to characteristic frequencies; measuring signal power and noise power, bringing the signal power and noise power into the signal-to-noise ratio calculation formula to obtain the signal-to-noise ratio, and calculating the inverse of the signal-to-noise ratio to obtain noise interference data;

[0012] The number of correctly detected faults and the number of actual existing faults are obtained, and the ratio of the number of correctly detected faults to the number of actual existing faults is used as the sensitivity of the fault detection algorithm; the data acquisition frequency, the characteristic frequency of the fault signal, the noise interference data and the sensitivity are comprehensively considered, and the fault detection coefficient is obtained according to the preset fault detection coefficient calculation formula.

[0013] In a preferred embodiment, the steps of acquiring the acquisition processing resource coefficient are as follows:

[0014] Define the various resources involved in the collection and processing process, including human resources, material resources, and financial resources;

[0015] Obtain the total number of collection and processing production lines, and combine human resources, material resources, and financial resources to obtain the collection and processing resource coefficient in the evaluation production process; construct a collection and processing resource constraint model based on the available collection resources and constraint conditions, and obtain the collection and processing resource coefficient after constraints based on the collection and processing resource constraint model.

[0016] In a preferred embodiment, the specific process of determining the optimal acquisition and processing frequency based on the smoothness of the curve is as follows: establish a coordinate system with the acquisition and processing frequency as the X-axis and the acquisition and processing evaluation coefficient as the Y-axis; and draw a two-dimensional curve graph according to the acquisition and processing evaluation coefficients corresponding to different acquisition and processing frequencies; find the peak in the curve graph, and calculate the smoothness of the curve by quadratic derivation; determine that the acquisition and processing frequency corresponding to the peak of the smoothest curve is the optimal acquisition and processing frequency.

[0017] A virtual instrument data acquisition and processing system comprises an acquisition module, a constraint module, an evaluation module and a determination module, wherein the modules are connected: the acquisition module is used to acquire industrial production management data and available resources for acquisition and processing that change on an industrial production line due to different virtual instrument data acquisition and processing frequencies; the constraint module is used to construct an acquisition and processing resource constraint model based on the available resources for acquisition and processing in combination with preset resource constraint conditions to obtain an acquisition and processing resource coefficient; the evaluation module is used to establish an evaluation model based on a machine learning algorithm based on the acquisition and processing resource coefficient in combination with industrial production management data to generate an acquisition and processing evaluation coefficient for a production line; the determination module is used to draw a two-dimensional curve graph combining the acquisition and processing evaluation coefficient for the production line with the data acquisition frequency, calculate the curve smoothness, and determine the optimal acquisition and processing frequency based on the curve smoothness. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The present invention is a schematic diagram of the structure of a virtual instrument data acquisition and processing method.

[0019] Figure 2 The present invention is a schematic diagram of the system structure of a virtual instrument data acquisition and processing method. DETAILED DESCRIPTION

[0020] 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.

[0021] Embodiment 1, Figure 1 The present invention provides a virtual instrument data acquisition and processing method and system.

[0022] S10, obtaining industrial production management data that changes due to different frequencies of virtual instrument data collection and processing on the industrial production line and the amount of available resources for collection and processing;

[0023] The industrial production management data includes a production line operation efficiency coefficient and a fault monitoring coefficient, and the amount of resources used for collection includes a maximum threshold value of collection and processing resources;

[0024] The method for obtaining the production line operation efficiency coefficient is as follows:

[0025] First, a model is established to predict the relationship between the frequency of data collection and processing and the operating efficiency of the production line. The frequency of data collection and processing, the length of time for each data collection and processing, the completion of tasks (such as the difference between the planned time and the actual time), and the work efficiency of the team (such as the amount of work completed per hour) are input into the model as feature data. The feature data is standardized and normalized to ensure that the scale of each feature is consistent.

[0026] The specific process of the normalization process is as follows:

[0027] Arrange the characteristic data in ascending order according to the time field, calculate the mean and standard deviation of each characteristic data, combine the preset standardization calculation formula, and use the sliding window stacking tomography method to make all characteristic data have the same scale and variation range;

[0028] The sliding window stacking chromatography method is specifically:

[0029] Select a window function JH with a fixed length L, divide the procurement time series data set with a fixed step length l, and obtain data segments of fixed length. The specific calculation formula of the window function is:

[0030] ;

[0031] Among them, JH is the total set of sliced ​​time series data sets, is a dataset of time series fragments, is the first data in the data set. For each sample, the signal difference is the jth time series segment after slicing, N is the total amount of data in the data set, is the signal smoothing value of each sample;

[0032] Based on the complex nonlinear relationship between multi-layer network learning in the neural network, the model is modeled and trained using the back propagation algorithm to adjust the learning rate and the number of neural network layers. Based on the trained model, given the acquisition processing frequency and feature data, the impact of acquisition processing on production efficiency is predicted, and the output prediction result is the production line operation efficiency coefficient K.

[0033] By constructing the production line operation efficiency coefficient, it can help industrial production managers quantify the impact of the frequency of collection and processing on progress and efficiency; use appropriate features and models to handle complex nonlinear relationships, thereby optimizing the collection and processing strategy, improving the overall progress and efficiency of production, and clarifying the specific impact of the frequency of collection and processing on production progress and efficiency; reduce unnecessary collection and processing processes, and ensure that the frequency of collection and processing can both guarantee production quality and not delay production progress; by understanding the resources (time, personnel, etc.) required for each collection and processing, more reasonable resource allocation can be achieved to avoid excessive time and manpower consumption in collection and processing;

[0034] The specific method for obtaining the fault monitoring coefficient is as follows:

[0035] First, obtain the collection and processing frequency of the production line;

[0036] The characteristic frequency of the fault signal is obtained through spectrum analysis. The specific process is as follows:

[0037] First, collect the equipment's operating signal data. These signals can be vibration signals, sound signals, current signals, etc., depending on the equipment to be monitored and the type of fault;

[0038] Preprocess the collected signal and use filters to remove high-frequency and low-frequency noise to obtain a processed time domain signal;

[0039] Use Fourier transform spectrum analysis method to convert time domain signal into frequency domain signal, plot frequency and amplitude into spectrum diagram to show the frequency components of the signal;

[0040] Find significant peaks in the spectrogram that correspond to characteristic frequencies;

[0041] The noise interference data is obtained by quantifying the signal-to-noise ratio. The noise interference data is inversely proportional to the signal-to-noise ratio. The specific acquisition process is as follows:

[0042] Measure the signal power and noise power, substitute the signal power and noise power into the signal-to-noise ratio calculation formula to obtain the signal-to-noise ratio, and calculate the inverse of the signal-to-noise ratio to obtain the noise interference data. The calculation formula for the signal-to-noise ratio is as follows: ; Where E is the noise interference data, is the signal power, is the noise power;

[0043] The number of correctly detected faults and the number of actually existing faults are obtained, and the ratio of the number of correctly detected faults to the number of actually existing faults is used as the sensitivity of the fault detection algorithm;

[0044] The fault detection coefficient is obtained according to the preset fault detection coefficient calculation formula by comprehensively considering the data acquisition frequency, the characteristic frequency of the fault signal, the noise interference data and the sensitivity; the specific calculation formula of the fault detection coefficient is as follows: ; In the formula, M is the fault monitoring coefficient, S is the sensitivity of the fault detection algorithm, fs is the data acquisition frequency, f is the characteristic frequency of the fault signal, and E is the noise interference data;

[0045] From the above, it can be seen that the higher the data acquisition frequency, the closer the acquisition frequency is to the characteristic frequency, the higher the sensitivity of the fault detection algorithm, the smaller the noise interference data, the higher the fault monitoring coefficient value, and the stronger the effectiveness of fault monitoring.

[0046] S20, constructing an acquisition and processing resource constraint model according to the available acquisition and processing resources combined with preset resource constraint conditions to obtain an acquisition and processing resource coefficient;

[0047] The constraints include minimizing the amount of resource waste and ensuring that the acquisition and processing resource coefficient does not exceed a threshold.

[0048] Define the various resources involved in the collection and processing process, including human resources, material resources, and financial resources;

[0049] The total number of acquisition and processing production lines is obtained, and the acquisition and processing resource coefficient in the production process is obtained by combining human resources, material resources, and financial resources. According to the available acquisition resources combined with the minimum resource waste, the acquisition and processing resource coefficient does not exceed the threshold constraint condition, and the acquisition and processing resource constraint model is constructed. The specific construction of the acquisition and processing resource constraint model is as follows:

[0050] ;

[0051] In the formula, W is the amount of resource waste, H is human resources, B is material resources, F is financial resources, z is the efficiency coefficient of human resources, d is the efficiency coefficient of material resources, v is the efficiency coefficient of financial resources, R is the collection and processing resource coefficient in the collection and processing process, c represents the influence factor of human resources in the collection and processing, a represents the influence factor of material resources in the collection and processing, and b represents the influence factor of financial resources in the collection and processing. is the maximum threshold of the acquisition and processing resource coefficient, C is the total amount of available resources, and Q is the total number of acquisition and processing production lines.

[0052] S30, establishing an evaluation model based on a machine learning algorithm according to the acquisition and processing resource coefficient combined with industrial production management data to generate a production line acquisition and processing evaluation coefficient;

[0053] The specific calculation formula of the production line acquisition and processing evaluation coefficient is as follows:

[0054] ;

[0055] Where PG is the production line acquisition and processing evaluation coefficient, R is the production line acquisition and processing evaluation coefficient, M is the fault monitoring coefficient, and K is the production line operation efficiency coefficient;

[0056] The production line collection and processing evaluation coefficient plays many roles in determining the optimal collection and processing frequency, as follows:

[0057] Optimize data collection frequency: The evaluation coefficient can help enterprises identify the best frequency for data collection. By analyzing data quality, system load, and production efficiency at different frequencies, enterprises can find a balance to ensure that sufficient information is obtained while avoiding the waste of resources caused by excessive collection.

[0058] Improve production efficiency: By properly setting the collection frequency, the evaluation coefficient can help the production line reduce downtime and resource waste while ensuring product quality, which means higher production efficiency and faster response time, thereby improving overall production capacity;

[0059] Reduce costs: Optimized acquisition and processing frequency can reduce unnecessary data acquisition and storage, reduce the cost of data processing and analysis, and at the same time, the appropriate frequency can reduce the energy consumption and maintenance costs of equipment and improve economic benefits;

[0060] Enhance data quality: The evaluation coefficient can help determine which data collection frequency can improve data accuracy and reliability in a specific situation. With the appropriate collection frequency, enterprises can reduce data redundancy and noise, thereby improving data quality;

[0061] Real-time monitoring and early warning: Appropriate data collection frequency can ensure real-time monitoring of the status of the production line, timely detection of potential problems, and taking corresponding measures for early warning. For example, during the data collection process, by analyzing the evaluation coefficient, it is possible to determine in real time whether the equipment is operating normally and adjust the operating parameters in a timely manner;

[0062] Support decision-making: The collection and processing evaluation coefficients provide important data support for management, which helps to make scientific decisions. Through data analysis, management can understand the operation status of the production line, bottleneck problems and their solutions, thereby optimizing the production process;

[0063] Flexible response to changes: Production environment and market demand often change. The evaluation coefficient can help enterprises flexibly adjust the collection frequency to adapt to new production conditions, technological updates or changes in market demand. This flexibility enables enterprises to maintain their advantages in competition;

[0064] S40, the production line collection and processing evaluation coefficient is combined with the data collection frequency to draw a two-dimensional curve graph, and the curve smoothness is calculated, and the optimal collection and processing frequency is determined according to the curve smoothness.

[0065] A coordinate system is established with the acquisition and processing frequency as the X-axis and the acquisition and processing evaluation coefficient as the Y-axis, and a two-dimensional curve graph is drawn according to the acquisition and processing evaluation coefficients corresponding to different acquisition and processing frequencies, the peak value in the curve graph is found, and the smoothness of the curve is calculated by quadratic derivation, and the acquisition and processing frequency corresponding to the peak value of the smoothest curve is determined to be the optimal acquisition and processing frequency;

[0066] The acquisition and processing evaluation coefficients obtained from the evaluation model are plotted into a curve graph and the curve smoothness is calculated to determine the optimal acquisition and processing frequency, which has the following benefits:

[0067] Visually display data: The curve chart can intuitively display the changing trend of the collection and processing evaluation coefficient, which is convenient for managers to quickly understand the relationship and fluctuation of the data; through visualization, managers can easily identify the periodic changes, trends and abnormal values ​​in the data, providing a basis for decision-making;

[0068] Quantitative analysis and comparison: By calculating the smoothness of the curve, the stability and consistency of the data can be quantified, so as to judge the rationality of the frequency of collection and processing. This quantitative analysis is helpful for comparison between different projects or stages. A curve with high smoothness indicates that the data changes less, which helps to determine the appropriateness of the frequency of collection and processing, reduce the frequency of collection and processing, and thus save resources;

[0069] Optimize the frequency of acquisition and processing: By analyzing the smoothness of the curve, the optimal frequency of acquisition and processing can be identified to ensure that acquisition and processing are carried out when necessary, and to reduce acquisition and processing in the stable stage to improve the efficiency of acquisition and processing. A reasonable frequency of acquisition and processing can reduce the cost of acquisition and processing, improve the efficiency of human resources, and make the acquisition and processing work more targeted;

[0070] Risk control and early warning: Abnormal fluctuations that may appear in the curve chart can serve as risk warnings, helping managers to adjust the collection and processing frequency in a timely manner, conduct targeted analysis and intervention, and better predict and control the financial and schedule risks of the project through changes in smoothness.

[0071] Embodiment 2, Figure 2 The present invention is a schematic diagram of the system structure of a virtual instrument data acquisition and processing method.

[0072] The virtual instrument data acquisition and processing system includes an acquisition module, a constraint module, an evaluation module, and a determination module, and there are connections between the modules:

[0073] An acquisition module is used to acquire industrial production management data that changes due to different frequencies of virtual instrument data acquisition and processing on industrial production lines, as well as the amount of available resources for acquisition and processing;

[0074] A constraint module is used to construct a collection and processing resource constraint model according to the available resources for collection and processing combined with preset resource constraint conditions to obtain a collection and processing resource coefficient;

[0075] An evaluation module is used to establish an evaluation model based on a machine learning algorithm according to the acquisition and processing resource coefficient combined with industrial production management data to generate a production line acquisition and processing evaluation coefficient;

[0076] The determination module is used to draw a two-dimensional curve graph by combining the production line collection and processing evaluation coefficient with the data collection frequency, and calculate the curve smoothness, and determine the optimal collection and processing frequency according to the curve smoothness.

[0077] 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 in the formula are set by technicians in this field according to actual conditions.

[0078] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0079] Those of ordinary skill in the art will appreciate that the modules 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.

[0080] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0081] 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.

[0082] 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 virtual instrument data acquisition and processing method, characterized in that: The following steps are involved: Obtain industrial production management data and available resources for acquisition and processing that change due to different frequencies of virtual instrument data acquisition and processing on industrial production lines; According to the available resources for collection and processing and the preset resource constraint conditions, a collection and processing resource constraint model is constructed to obtain a collection and processing resource coefficient; the constraint conditions include minimizing the amount of resource waste and the collection and processing resource coefficient not exceeding a threshold value; Define the various resources involved in the collection and processing process, including human resources, material resources, and financial resources; The total number of acquisition and processing production lines is obtained, and the acquisition and processing resource coefficients in the production process are obtained by combining human resources, material resources, and financial resources. According to the available acquisition resources and constraint conditions, an acquisition and processing resource constraint model is constructed. The specific construction of the acquisition and processing resource constraint model is as follows: ; In the formula, W is the amount of resource waste, H is human resources, B is material resources, F is financial resources, z is the efficiency coefficient of human resources, d is the efficiency coefficient of material resources, v is the efficiency coefficient of financial resources, R is the collection and processing resource coefficient in the collection and processing process, c represents the influence factor of human resources in the collection and processing, a represents the influence factor of material resources in the collection and processing, b represents the influence factor of financial resources in the collection and processing, is the maximum threshold of the acquisition and processing resource coefficient, C is the total amount of available resources, and Q is the total number of acquisition and processing production lines; Obtaining a constrained acquisition and processing resource coefficient according to an acquisition and processing resource constraint model; According to the acquisition and processing resource coefficient combined with industrial production management data, an evaluation model is established based on a machine learning algorithm to generate a production line acquisition and processing evaluation coefficient; the specific calculation formula of the production line acquisition and processing evaluation coefficient is as follows: ; In the formula, PG is the production line acquisition and processing evaluation coefficient, R is the acquisition and processing resource coefficient, M is the fault monitoring coefficient, and K is the production line operation efficiency coefficient; The production line collection and processing evaluation coefficient is combined with the data collection frequency to draw a two-dimensional curve graph, and the curve smoothness is calculated. The optimal collection and processing frequency is determined according to the curve smoothness. The specific process of determining the optimal collection and processing frequency is as follows: A coordinate system is established with the acquisition and processing frequency as the X-axis and the acquisition and processing evaluation coefficient as the Y-axis; And draw a two-dimensional curve graph according to the acquisition and processing evaluation coefficients corresponding to different acquisition and processing frequencies; find the peak value in the curve graph, and calculate the smoothness of the curve through quadratic derivation; The acquisition processing frequency corresponding to the peak of the smoothest curve is determined as the optimal acquisition processing frequency.

2. The virtual instrument data acquisition and processing method according to claim 1, characterized in that: The industrial production management data includes a production line operation efficiency coefficient and a fault monitoring coefficient, and the available acquisition and processing resources include a maximum threshold value of the acquisition and processing resources.

3. The virtual instrument data acquisition and processing method according to claim 2 is characterized in that: The method for obtaining the production line operation efficiency coefficient is as follows: Establish a model that affects production line operation efficiency; The collection and processing frequency of the production line, the length of time for each collection and processing, the completion of the collection task, and the work efficiency of the team are input into the model as feature data; And standardize and normalize the feature data; The model is modeled based on the complex nonlinear relationship between multi-layer network learning in the neural network; the model is trained using the back-propagation algorithm to adjust the learning rate and the number of neural network layers; The collected processing frequency and the standardized and normalized feature data are input into the trained model, and the output prediction result is the production line operation efficiency coefficient.

4. The virtual instrument data acquisition and processing method according to claim 3 is characterized in that: The specific method for obtaining the fault monitoring coefficient is as follows: Obtain the frequency of data collection and processing for industrial production lines; Collect the operation signal data of the equipment, pre-process the collected signals, use filters to remove high-frequency and low-frequency noise, and obtain the processed time domain signals; Use Fourier transform spectrum analysis method to convert time domain signal into frequency domain signal, plot frequency and amplitude into spectrum diagram to show the frequency components of the signal; Find the significant peaks in the spectrum graph, which correspond to the characteristic frequencies; Measure the signal power and noise power, substitute the signal power and noise power into the signal-to-noise ratio calculation formula to obtain the signal-to-noise ratio, and calculate the inverse of the signal-to-noise ratio to obtain the noise interference data; The number of correctly detected faults and the number of actually existing faults are obtained, and the ratio of the number of correctly detected faults to the number of actually existing faults is used as the sensitivity of the fault detection algorithm; The fault detection coefficient is obtained according to a preset fault detection coefficient calculation formula by comprehensively considering the data acquisition frequency, the characteristic frequency of the fault signal, the noise interference data and the sensitivity.

5. The virtual instrument data acquisition and processing method according to claim 4 is characterized in that: The specific calculation formula of the fault detection coefficient is as follows: ; In the formula, M is the fault monitoring coefficient, S is the sensitivity of the fault detection algorithm, fs is the data acquisition frequency, f is the characteristic frequency of the fault signal, and E is the noise interference data.

6. A virtual instrument data acquisition and processing system, characterized in that: It includes acquisition module, constraint module, evaluation module and determination module. There are connections between modules: An acquisition module is used to acquire industrial production management data that changes due to different frequencies of virtual instrument data acquisition and processing on industrial production lines, as well as the amount of available resources for acquisition and processing; A constraint module, used to construct a collection and processing resource constraint model according to the available resources for collection and processing combined with preset resource constraint conditions, and obtain a collection and processing resource coefficient; the constraint conditions include minimizing the amount of resource waste and the collection and processing resource coefficient not exceeding a threshold; Define the various resources involved in the collection and processing process, including human resources, material resources, and financial resources; The total number of acquisition and processing production lines is obtained, and the acquisition and processing resource coefficients in the production process are obtained by combining human resources, material resources, and financial resources. According to the available acquisition resources and constraint conditions, an acquisition and processing resource constraint model is constructed. The specific construction of the acquisition and processing resource constraint model is as follows: ; In the formula, W is the amount of resource waste, H is human resources, B is material resources, F is financial resources, z is the efficiency coefficient of human resources, d is the efficiency coefficient of material resources, v is the efficiency coefficient of financial resources, R is the collection and processing resource coefficient in the collection and processing process, c represents the influence factor of human resources in the collection and processing, a represents the influence factor of material resources in the collection and processing, b represents the influence factor of financial resources in the collection and processing, is the maximum threshold of the acquisition and processing resource coefficient, C is the total amount of available resources, and Q is the total number of acquisition and processing production lines; Obtaining a constrained acquisition and processing resource coefficient according to an acquisition and processing resource constraint model; The evaluation module is used to establish an evaluation model based on the machine learning algorithm according to the acquisition and processing resource coefficient combined with the industrial production management data to generate the production line acquisition and processing evaluation coefficient; the specific calculation formula of the production line acquisition and processing evaluation coefficient is as follows: ; In the formula, PG is the production line acquisition and processing evaluation coefficient, R is the acquisition and processing resource coefficient, M is the fault monitoring coefficient, and K is the production line operation efficiency coefficient; The determination module is used to draw a two-dimensional curve graph by combining the production line acquisition and processing evaluation coefficient with the data acquisition frequency, and calculate the curve smoothness, and determine the optimal acquisition and processing frequency according to the curve smoothness. The specific process of determining the optimal acquisition and processing frequency is as follows: A coordinate system is established with the acquisition and processing frequency as the X-axis and the acquisition and processing evaluation coefficient as the Y-axis; And draw a two-dimensional curve graph according to the acquisition and processing evaluation coefficients corresponding to different acquisition and processing frequencies; find the peak value in the curve graph, and calculate the smoothness of the curve through quadratic derivation; The acquisition processing frequency corresponding to the peak of the smoothest curve is determined as the optimal acquisition processing frequency.

Images