A method and system for automatically calculating ventilation time of dust explosion-proof electrical cabinet

Abstract

The present invention provides a method and system for automatically calculating the ventilation time of a dust explosion-proof electrical cabinet, and relates to the technical field of electrical cabinets. The method comprises the following steps: obtaining dust concentration data of the dust explosion-proof electrical cabinet, and analyzing the fluctuation characteristic parameters of the dust concentration by using the multi-fractal theory; constructing a ventilation capacity evaluation model of the dust explosion-proof electrical cabinet based on the fluctuation characteristic parameters of the dust concentration; determining the target ventilation standard of the dust explosion-proof electrical cabinet based on the use standard of the dust explosion-proof electrical cabinet; using the target ventilation standard as an input parameter, and calculating using the ventilation capacity evaluation model of the dust explosion-proof electrical cabinet to obtain the ventilation time required for the target ventilation standard. The present invention can arrange the maintenance and management plan of the dust explosion-proof electrical cabinet more reasonably by automatically calculating the ventilation time, prolonging the service life of the equipment, and reducing the maintenance cost.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical cabinets, and in particular to a method and system for automatically calculating ventilation time based on a dust explosion-proof electrical cabinet. Background Art

[0002] Dust explosion-proof electrical cabinets are special electrical equipment designed for industrial environments with combustible dust. They are widely used in chemical plants, flour mills, pharmaceutical plants, wood processing plants and other places. In the design and manufacturing process of this type of electrical cabinet, relevant safety standards are strictly followed to effectively prevent fire and explosion accidents caused by dust and ensure the safety of the working environment. In order to ensure the continuous safety of the internal environment of the electrical cabinet, it is usually equipped with an advanced ventilation system. This system regularly introduces clean air and exhausts dust-containing air, thereby effectively maintaining a low dust concentration environment inside the electrical cabinet. In addition, the ventilation system has been carefully designed to ensure its stable and efficient operation, and can work reliably for a long time in various harsh industrial environments, providing comprehensive safety protection for dust explosion-proof electrical cabinets.

[0003] Currently, ventilation systems in many industrial environments still operate with preset fixed ventilation schedules, which do not take into account actual changes in dust concentrations. When dust concentrations are below the hazardous threshold, fixed ventilation plans may lead to unnecessary energy consumption and increased operating costs. On the contrary, when the dust concentration in the environment is higher than the safety standard, this non-adaptive ventilation strategy may not provide sufficient ventilation, thereby increasing the risk of explosion or fire. This approach lacks flexibility and responsiveness and cannot effectively adapt to dynamic changes in the workplace.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of this, the present invention provides a method and system for automatically calculating the ventilation time of a dust explosion-proof electrical cabinet to solve the above-mentioned problems.

[0006] In order to solve the above problems, the specific technical solutions adopted by the present invention are as follows:

[0007] According to one aspect of the present invention, a method for automatically calculating the ventilation time of a dust explosion-proof electrical cabinet is provided. The method for automatically calculating the ventilation time of a dust explosion-proof electrical cabinet comprises the following steps:

[0008] S1. Obtain dust concentration data of dust explosion-proof electrical cabinets, and use multi-fractal theory to analyze the fluctuation characteristic parameters of dust concentration;

[0009] S2. Based on the fluctuation characteristic parameters of dust concentration, a model for evaluating the ventilation capacity of dust explosion-proof electrical cabinets is constructed;

[0010] S3. Based on the use standards of dust explosion-proof electrical cabinets, determine the target ventilation standards for dust explosion-proof electrical cabinets;

[0011] S4, taking the target ventilation standard as an input parameter, and using the dust explosion-proof electrical cabinet ventilation capacity evaluation model to calculate, to obtain the ventilation time required for the target ventilation standard;

[0012] Preferably, obtaining dust concentration data of a dust explosion-proof electrical cabinet and analyzing the fluctuation characteristic parameters of dust concentration using multifractal theory comprises the following steps:

[0013] S11, arranging the acquired dust concentration data in chronological order to obtain time series data of dust concentration;

[0014] S12. Based on the multifractal theory, multifractal analysis is performed on the time series data of dust concentration, and a multifractal spectrum is constructed;

[0015] S13. Calculate the multifractal characteristic parameters of the dust concentration time series according to the constructed multifractal spectrum, and identify the fluctuation characteristic parameters of the dust concentration.

[0016] Preferably, performing multifractal analysis on the time series data of dust concentration based on multifractal theory and constructing a multifractal spectrum comprises the following steps:

[0017] S121, preprocessing the time series data of dust concentration, including data denoising and data cleaning;

[0018] S122, binning the preprocessed time series data to obtain a number of boxes with equal intervals;

[0019] S123, respectively calculating the probability measure of dust concentration in each box and the generalized dimension of each box;

[0020] S124. Based on the calculated probability measure and generalized dimension, the multifractal theory is used to calculate the singularity index and construct the multifractal spectrum.

[0021] Preferably, calculating the multifractal characteristic parameters of the dust concentration time series according to the constructed multifractal spectrum and identifying the fluctuation characteristic parameters of the dust concentration comprises the following steps:

[0022] S131, based on the constructed multifractal spectrum, respectively obtaining the range of the fractal dimension and the singularity index with the largest occupied area;

[0023] S132, determining the span of the multifractal spectrum on the singularity index axis to obtain the width of the multifractal spectrum;

[0024] S133. Analyze the difference distribution of singularity index between adjacent sub-intervals in the multifractal spectrum, and identify the intensity and frequency characteristics of dust concentration fluctuations.

[0025] Preferably, the generalized dimension of each box is calculated as:

[0026] ;

[0027] D represents the generalized dimension of the box; s represents the scale factor; q Represents a random value; p i Indicates i The probability measure of the boxes; N Represents the total number of boxes.

[0028] Preferably, based on the fluctuation characteristic parameters of dust concentration, constructing a dust explosion-proof electrical cabinet ventilation capacity evaluation model comprises the following steps:

[0029] S21. Based on the fluctuation characteristic parameters of dust concentration, the time series data of dust concentration is divided into fluctuations by a swing window algorithm to obtain fluctuation periods;

[0030] S22, clustering the fluctuation time periods that meet the similarity threshold in the dust concentration fluctuation characteristics to obtain a clustering result;

[0031] S23. Based on the clustering results and the fluctuation characteristic parameters of dust concentration, a dust explosion-proof electrical cabinet ventilation capacity evaluation model is constructed.

[0032] Preferably, based on the fluctuation characteristic parameters of dust concentration, the time series data of dust concentration is divided into fluctuations by a swing window algorithm to obtain the fluctuation period, which includes the following steps:

[0033] S211, based on the fluctuation characteristic parameters of dust concentration, initializing the parameters of the swing window algorithm, including the sliding window size and the fluctuation threshold;

[0034] S212, for each sliding window, determining dust concentration fluctuation characteristic parameters within the sliding window;

[0035] S213, judging whether the data in the sliding window constitutes fluctuation according to a preset fluctuation threshold, if the fluctuation characteristic parameter exceeds the fluctuation threshold, it indicates that there is fluctuation in the sliding window, and recording the starting point and the ending point of the fluctuation;

[0036] S214, traverse the entire time series data, and repeat steps S212-S213 to obtain the fluctuation period.

[0037] Preferably, clustering the fluctuation time periods that meet the similarity threshold in the dust concentration fluctuation characteristics to obtain the clustering results comprises the following steps:

[0038] S221. Constructing a characteristic vector for each fluctuation period based on the fluctuation characteristic parameters of dust concentration;

[0039] S222, calculating the dissimilarity between the characteristic vectors of any two fluctuation periods, and constructing a dissimilarity matrix;

[0040] S223. Based on the constructed dissimilarity matrix, a spectral clustering algorithm is used to perform cluster analysis on the fluctuation period to obtain a clustering result.

[0041] Preferably, based on the clustering results and the fluctuation characteristic parameters of the dust concentration, constructing a dust explosion-proof electrical cabinet ventilation capacity evaluation model comprises the following steps:

[0042] S231, integrating the clustering results and the fluctuation characteristic parameters of dust concentration to form an input data set;

[0043] S232, determining the evaluation index of the ventilation capacity of the dust explosion-proof electrical cabinet, and using it as the output target variable;

[0044] S233. Based on the linear regression method, the dust explosion-proof electrical cabinet ventilation capacity evaluation model is constructed and trained using the input data set and the output target variable;

[0045] S234. Collect a test data set, and verify the dust explosion-proof electrical cabinet ventilation capacity evaluation model, adjust the model parameters according to the verification results, and obtain an optimized dust explosion-proof electrical cabinet ventilation capacity evaluation model.

[0046] Preferably, taking the target ventilation standard as an input parameter and using the dust explosion-proof electrical cabinet ventilation capacity evaluation model to calculate, obtaining the ventilation time required for the target ventilation standard includes the following steps:

[0047] S41, inputting the target ventilation standard as an input parameter into a dust explosion-proof electrical cabinet ventilation capacity evaluation model;

[0048] S42, using a dust explosion-proof electrical cabinet ventilation capacity assessment model to calculate and obtain a predicted ventilation time based on a target ventilation standard;

[0049] S43, testing the predicted ventilation time. If the predicted ventilation time passes the test, it is output as the ventilation time required for the target ventilation standard. If it fails, the parameters of the dust explosion-proof electrical cabinet ventilation capacity evaluation model are adjusted, and the ventilation time is recalculated.

[0050] According to another aspect of the present invention, a ventilation time automatic calculation system based on a dust explosion-proof electrical cabinet is provided, and the ventilation time automatic calculation system based on a dust explosion-proof electrical cabinet comprises: a fluctuation characteristic analysis module, an evaluation model construction module, a ventilation standard determination module and a ventilation time calculation module, and the fluctuation characteristic analysis module, the evaluation model construction module, the ventilation standard determination module and the ventilation time calculation module are connected in sequence;

[0051] The fluctuation characteristic analysis module is used to obtain the dust concentration data of the dust explosion-proof electrical cabinet and analyze the fluctuation characteristic parameters of the dust concentration using the multi-fractal theory;

[0052] An evaluation model building module is used to build a dust explosion-proof electrical cabinet ventilation capacity evaluation model based on the fluctuation characteristic parameters of dust concentration;

[0053] A ventilation standard determination module is used to determine a target ventilation standard for a dust explosion-proof electrical cabinet based on the use standard of the dust explosion-proof electrical cabinet;

[0054] The ventilation time calculation module is used to take the target ventilation standard as an input parameter and use the dust explosion-proof electrical cabinet ventilation capacity evaluation model to calculate and obtain the ventilation time required for the target ventilation standard.

[0055] The beneficial effects of the present invention are:

[0056] 1. The present invention obtains dust concentration data of dust explosion-proof electrical cabinets and uses multiple fractal theory to analyze the fluctuation characteristic parameters of dust concentration, thereby more accurately capturing the dynamic changes of dust concentration, thereby improving the accuracy of ventilation time calculation. A dust explosion-proof electrical cabinet ventilation capacity evaluation model is constructed based on the fluctuation characteristic parameters of dust concentration, so that the model can more comprehensively consider the actual working environment and conditions of the dust explosion-proof electrical cabinet, thereby enhancing the applicability and generalization ability of the model. The dust explosion-proof electrical cabinet ventilation capacity evaluation model is used for calculation, thereby realizing automatic calculation of ventilation time, improving calculation efficiency, reducing manual intervention and errors, and automatically calculating ventilation time. The maintenance and management plan of the dust explosion-proof electrical cabinet can be more reasonably arranged, thereby extending the service life of the equipment and reducing maintenance costs.

[0057] 2. The present invention can extract the multifractal characteristic parameters of the dust concentration time series in a refined manner through binning, calculation of probability measures and generalized dimensions, and construction of multifractal spectra. By identifying the fluctuation characteristic parameters of dust concentration, it is helpful to build a more accurate dust-proof explosion-proof electrical cabinet ventilation capacity assessment model, thereby improving the accuracy of ventilation time prediction. Accurate analysis of dust concentration fluctuation characteristics helps to formulate more effective ventilation strategies, improve workplace safety, and may improve efficiency by optimizing the ventilation process.

[0058] 3. The present invention divides the fluctuation of the time series data of dust concentration through the swing window algorithm, which can more accurately identify the fluctuation period of dust concentration, and provide a more accurate data basis for building the evaluation model. The time periods with similar fluctuation characteristics are clustered, which can enable the model to better learn and generalize the ventilation capacity under different fluctuation modes, thereby improving the applicability and robustness of the model. By integrating the clustering results and the fluctuation characteristic parameters of dust concentration as the input data set, and determining clear evaluation indicators as the target variables, the model construction process is made more systematic and orderly. By using the linear regression method to build and train the evaluation model, the mapping relationship between the input data set and the target variable can be established to achieve accurate prediction of the ventilation capacity of the dust-proof explosion-proof electrical cabinet. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0060] Figure 1 is a flow chart of a method for automatically calculating ventilation time based on a dust explosion-proof electrical cabinet according to an embodiment of the present invention;

[0061] Figure 2 The invention is a principle block diagram of a system for automatically calculating ventilation time based on a dust explosion-proof electrical cabinet according to an embodiment of the present invention.

[0062] In the figure:

[0063] 1. Fluctuation characteristic analysis module; 2. Evaluation model construction module; 3. Ventilation standard determination module; 4. Ventilation time calculation module. DETAILED DESCRIPTION

[0064] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0065] According to an embodiment of the present invention, a method and system for automatically calculating ventilation time based on a dust explosion-proof electrical cabinet are provided.

[0066] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a method for automatically calculating the ventilation time of a dust explosion-proof electrical cabinet is provided, and the method for automatically calculating the ventilation time of a dust explosion-proof electrical cabinet comprises the following steps:

[0067] S1. Obtain dust concentration data of dust explosion-proof electrical cabinets, and use multi-fractal theory to analyze the fluctuation characteristic parameters of dust concentration;

[0068] As a preferred implementation, obtaining dust concentration data of a dust explosion-proof electrical cabinet and analyzing the fluctuation characteristic parameters of dust concentration using multi-fractal theory include the following steps:

[0069] S11, arranging the acquired dust concentration data in chronological order to obtain time series data of dust concentration;

[0070] It should be noted that when collating the data, it is necessary to ensure that the timestamps of all dust concentration data points are synchronized, that is, they are all recorded based on the same time standard (such as UTC time). This helps to avoid errors caused by time deviation in subsequent analysis. Once the data is collated and the timestamps are synchronized, the data can be sorted in chronological order. After sorting and verification, the dust concentration data forms an ordered time series, which can be used for subsequent multifractal analysis and model building.

[0071] S12. Based on the multifractal theory, multifractal analysis is performed on the time series data of dust concentration, and a multifractal spectrum is constructed;

[0072] As a preferred implementation, performing multifractal analysis on the time series data of dust concentration based on multifractal theory and constructing a multifractal spectrum includes the following steps:

[0073] S121, preprocessing the time series data of dust concentration, including data denoising and data cleaning;

[0074] It should be noted that noise is a random or irregular change in data, which may be caused by measurement errors, environmental interference or other factors. The purpose of denoising is to reduce or eliminate the impact of noise on data analysis in order to more accurately reveal the inherent patterns and trends of the data. Common denoising methods include filtering, smoothing and fitting. For example, a moving average filter can be used to smooth time series data to reduce the impact of noise. Data cleaning refers to identifying and correcting errors, anomalies or inconsistencies in data. In the time series data of dust concentration, the situations that need to be cleaned include missing values, outliers or duplicate values. Missing values ​​can be filled by interpolation or estimation, outliers can be handled by detection and replacement or deletion, and duplicate values ​​can be resolved by deleting duplicates.

[0075] S122, binning the preprocessed time series data to obtain a number of boxes with equal intervals;

[0076] Specifically, binning the preprocessed time series data, that is, dividing the continuous dust concentration values ​​into several equal intervals, is an important step in multifractal analysis. The purpose of binning is to convert continuous data into discrete intervals to facilitate subsequent analysis, such as calculating the probability measure and generalized dimension of each box. The following are the binning steps:

[0077] First, determine the size or number of bins. The bin size should be small enough to capture local variations in the data, but not too small, otherwise there may be too few data points in the bin, affecting the statistical stability. The size of the bin is usually set based on the range of the data and the desired resolution.

[0078] Based on the determined bin size, a series of equally spaced bins are created within the range of the data. Each bin will cover a specific interval of the data.

[0079] Assign each dust concentration value in the time series data to the corresponding box. Specifically, if a dust concentration value falls within the interval of a box, then this value is considered to belong to this box.

[0080] S123, respectively calculating the probability measure of dust concentration in each box and the generalized dimension of each box;

[0081] It should be noted that for each box, all dust concentration data points contained in it are determined. All dust concentration data points in each box are summed to obtain the total data in the box. For each box, the sum of the data in it is divided by the total sum of the data in all boxes to obtain the probability measure of the box. The probability measure reflects the proportion of the data in the box in the overall data.

[0082] Generalized dimension is an important concept in multifractal analysis, which describes the complexity and irregularity of data at different scales. A detailed analysis is performed using the probability measure of each box at different scale factors. By selecting a series of scale factors and calculating the probability measure of each box at these scales, a formula can be used to estimate the generalized dimension. This dimension not only reveals the complexity and irregularity of data at different scales, but also captures different characteristics of data distribution by adjusting random values, such as capacity dimension, information dimension, and correlation dimension, thus providing a comprehensive perspective on the fractal properties of data.

[0083] As a preferred implementation, the calculation formula for the generalized dimension of each box is:

[0084] ;

[0085] D represents the generalized dimension of the box; s represents the scale factor; q Represents a random value; p i Indicates i The probability measure of the boxes; N Indicates the total number of boxes. Random value q is a parameter used to adjust the sensitivity of the generalized dimension to the distribution of the probability measure. q Different values ​​can be taken to analyze the fractal characteristics of data in different situations.

[0086] S124. Based on the calculated probability measure and generalized dimension, the multifractal theory is used to calculate the singularity index and construct the multifractal spectrum.

[0087] Specifically, based on the calculated probability measure and generalized dimension, the singularity index is calculated using multifractal theory, and the construction of the multifractal spectrum includes the following steps:

[0088] Calculate the singularity index, which is an important parameter in multifractal analysis. It describes the degree of singularity or irregularity of the data in different regions or boxes. The singularity index can be calculated by taking the derivative of the generalized dimension with respect to the random value;

[0089] Construct a multifractal spectrum that describes the relationship between the singularity index and the corresponding probability measure or number of data points.

[0090] The multifractal spectrum can be calculated by Legendre transformation, that is, f ( α )= qα - D This transformation converts the generalized dimension D and the singularity index α The shape and width of the multifractal spectrum can provide important information about the fractal structure and complexity of the data. For example, the width of the spectrum can indicate the diversity or irregularity of the data.

[0091] S13. Calculate the multifractal characteristic parameters of the dust concentration time series according to the constructed multifractal spectrum, and identify the fluctuation characteristic parameters of the dust concentration.

[0092] As a preferred embodiment, according to the constructed multifractal spectrum, calculating the multifractal characteristic parameters of the dust concentration time series and identifying the fluctuation characteristic parameters of the dust concentration include the following steps:

[0093] S131, based on the constructed multifractal spectrum, respectively obtaining the range of the fractal dimension and the singularity index with the largest occupied area;

[0094] Specifically, the multifractal spectrum describes the relationship between the singularity index and the corresponding probability measure. By observing the shape of the spectrum, the minimum and maximum values ​​can be determined, thereby obtaining the range of the fractal dimension. In the multifractal spectrum, the singularity index with the largest area represents the most important fractal feature in the data. This index has the largest probability measure and is therefore the most significant fractal feature in the data.

[0095] S132, determining the span of the multifractal spectrum on the singularity index axis to obtain the width of the multifractal spectrum;

[0096] It should be noted that the width of the multifractal spectrum refers to the difference between the maximum and minimum values ​​of the curve on the singularity index axis. The larger the width, the more diverse self-similarity the local area of ​​the data set exhibits, that is, the more complex the multifractal structure.

[0097] S133. Analyze the difference distribution of singularity index between adjacent sub-intervals in the multifractal spectrum, and identify the intensity and frequency characteristics of dust concentration fluctuations.

[0098] It should be noted that by analyzing the difference distribution of singularity index between adjacent subintervals in the multifractal spectrum, the intensity and frequency characteristics of dust concentration fluctuations can be identified. The multifractal spectrum describes the relationship between the singularity index and the probability measure, reflecting the degree of singularity of the data in different regions. By dividing the multifractal spectrum into several subintervals and calculating the difference in singularity index between adjacent subintervals, the changes in the fractal characteristics of the data in different regions can be analyzed. Larger differences in singularity index may indicate large fluctuations or mutations in dust concentration, while smaller differences may indicate that dust concentration is relatively stable. By analyzing the characteristics of these difference distributions, such as shape, peak value, width, and statistical characteristics such as asymmetry and skewness, a more comprehensive understanding of the fluctuation characteristics of dust concentration can be obtained. This approach helps to better understand and predict the changing behavior of dust concentration.

[0099] S2. Based on the fluctuation characteristic parameters of dust concentration, a model for evaluating the ventilation capacity of dust explosion-proof electrical cabinets is constructed;

[0100] As a preferred implementation, based on the fluctuation characteristic parameters of dust concentration, constructing a dust explosion-proof electrical cabinet ventilation capacity evaluation model includes the following steps:

[0101] S21. Based on the fluctuation characteristic parameters of dust concentration, the time series data of dust concentration is divided into fluctuations by a swing window algorithm to obtain fluctuation periods;

[0102] As a preferred implementation, based on the fluctuation characteristic parameters of dust concentration, the time series data of dust concentration is divided into fluctuations by a swing window algorithm to obtain the fluctuation period, which includes the following steps:

[0103] S211, based on the fluctuation characteristic parameters of dust concentration, initializing the parameters of the swing window algorithm, including the sliding window size and the fluctuation threshold;

[0104] It should be noted that the size of the sliding window should be reasonably set according to the characteristics of the dust concentration time series data and the analysis requirements. A larger window can capture fluctuation patterns over a longer time range, but may ignore rapid changes in the short term. A smaller window can more sensitively capture short-term fluctuations, but may not accurately reflect long-term trends. Therefore, when choosing the window size, it is necessary to comprehensively consider the fluctuation frequency of dust concentration, the purpose of analysis, and the limitations of computing resources.

[0105] The fluctuation threshold is used to determine whether the dust concentration data within the sliding window constitutes a significant fluctuation. The setting of the threshold should be based on the historical data of dust concentration or industry standards to ensure its rationality and effectiveness. A suitable threshold can be determined through statistical analysis (such as calculating standard deviation, percentile, etc.). The selection of the threshold should be able to accurately distinguish between normal fluctuations and abnormal fluctuations for subsequent analysis and processing.

[0106] For example, suppose there is continuous dust concentration monitoring data with a sampling interval of 1 minute in mg / m³. It is observed that the data shows periodic fluctuations, with an average period of about 30 minutes.

[0107] Sliding window size: You can choose 15 minutes (i.e. 15 data points) as the sliding window size to capture half-cycle fluctuations.

[0108] Fluctuation threshold: If data analysis shows that the standard deviation of dust concentration is about 10 mg / m³, the fluctuation threshold may be set to 20 mg / m³ (i.e., 2 times the standard deviation) to filter out small fluctuations and noise.

[0109] S212, for each sliding window, determining dust concentration fluctuation characteristic parameters within the sliding window;

[0110] It should be noted that for each sliding window, the complexity and irregularity of the dust concentration time series are quantified by calculating the fractal dimension, and the singularity index and its distribution are determined to describe the fluctuation characteristics of dust concentration in different regions or states. Furthermore, the width of the multi-fractal spectrum is calculated to reflect the richness of the dust concentration fluctuation characteristics. In addition, the difference in the singularity index of adjacent sub-intervals is analyzed to capture the local variation characteristics of dust concentration fluctuations. Combining these calculation and analysis results, a set of dust concentration fluctuation characteristic parameters can be determined for each sliding window.

[0111] S213, judging whether the data in the sliding window constitutes fluctuation according to a preset fluctuation threshold, if the fluctuation characteristic parameter exceeds the fluctuation threshold, it indicates that there is fluctuation in the sliding window, and recording the starting point and the ending point of the fluctuation;

[0112] It should be noted that, according to the preset fluctuation threshold, the dust concentration fluctuation characteristic parameters in each sliding window can be judged to determine whether the data in the window constitutes fluctuation. Specifically, if the calculated fluctuation characteristic parameters (such as fractal dimension, maximum value of singularity index, width of multifractal spectrum, etc.) exceed the preset fluctuation threshold, then it is considered that there is significant fluctuation in the sliding window.

[0113] Once it is determined that there is a fluctuation in a sliding window, the starting point and the ending point of the fluctuation are recorded. The starting point corresponds to the start time of the sliding window, and the ending point corresponds to the end time of the sliding window. In this way, the specific time period in the dust concentration time series where there is a fluctuation can be accurately identified.

[0114] S214, traverse the entire time series data, and repeat steps S212-S213 to obtain the fluctuation period.

[0115] S22, clustering the fluctuation time periods that meet the similarity threshold in the dust concentration fluctuation characteristics to obtain a clustering result;

[0116] As a preferred implementation, clustering the fluctuation periods that meet the similarity threshold in the dust concentration fluctuation characteristics to obtain the clustering results includes the following steps:

[0117] S221. Constructing a characteristic vector for each fluctuation period based on the fluctuation characteristic parameters of dust concentration;

[0118] Specifically, based on the fluctuation characteristic parameters of dust concentration, constructing the characteristic vector of each fluctuation period includes the following steps:

[0119] Process the dust concentration data in each fluctuation period, including denoising, smoothing, normalization and other operations to ensure the accuracy and comparability of the data;

[0120] According to the determined characteristic parameters, the corresponding characteristic values ​​are extracted from the preprocessed data. For example, the maximum value of the fractal dimension and singularity index of the fluctuation period is calculated;

[0121] The extracted eigenvalues ​​are combined into a eigenvector in a certain order. Each dimension of the eigenvector corresponds to a eigenparameter.

[0122] S222, calculating the dissimilarity between the characteristic vectors of any two fluctuation periods, and constructing a dissimilarity matrix;

[0123] Specifically, for any two feature vectors of fluctuation periods, the distance between them is calculated by the Euclidean distance method. The smaller the distance, the more similar the two feature vectors are; the larger the distance, the less similar the two feature vectors are.

[0124] Among them, constructing the dissimilarity matrix includes the following steps:

[0125] Create a matrix of size M×M, where M is the number of fluctuation periods. This matrix will be used to store the dissimilarity between the feature vectors of any two fluctuation periods.

[0126] For each element (x, y) in the matrix, fill in the position with the dissimilarity (i.e., distance) between the eigenvector of the xth fluctuation period and the eigenvector of the yth fluctuation period.

[0127] For the diagonal elements of the matrix (x, y), they represent the difference between the fluctuation period and itself. Usually, these elements are set to 0, because the difference between anything and itself should be minimal.

[0128] S223. Based on the constructed dissimilarity matrix, a spectral clustering algorithm is used to perform cluster analysis on the fluctuation period to obtain a clustering result.

[0129] Specifically, according to the constructed dissimilarity matrix, the spectral clustering algorithm is used to perform cluster analysis on the fluctuation period, and the clustering results are obtained by the following steps:

[0130] Convert the dissimilarity matrix to a similarity matrix. Usually, the similarity matrix can be obtained by some transformation of the dissimilarity matrix, such as using a Gaussian kernel function to convert distance to similarity;

[0131] Calculate the Laplacian matrix of the similarity matrix. The Laplacian matrix is ​​a key concept in spectral clustering, which reflects the connection relationship between data points;

[0132] Perform eigendecomposition on the Laplace matrix to obtain its eigenvalues ​​and corresponding eigenvectors. Eigendecomposition is the core step in spectral clustering, which reveals the intrinsic structure of the data;

[0133] According to the size of the eigenvalue, select the eigenvectors corresponding to the first k largest eigenvalues. These eigenvectors will be used in the subsequent clustering process;

[0134] The selected feature vector is used as a new feature space, and the data is clustered using a traditional clustering algorithm (such as K-means) in this space; based on the output of the clustering algorithm, the clustering results of the fluctuation period are obtained. Each cluster contains a group of similar fluctuation periods.

[0135] S23. Based on the clustering results and the fluctuation characteristic parameters of dust concentration, a dust explosion-proof electrical cabinet ventilation capacity evaluation model is constructed.

[0136] As a preferred implementation, based on the clustering results and the fluctuation characteristic parameters of dust concentration, constructing a dust explosion-proof electrical cabinet ventilation capacity evaluation model includes the following steps:

[0137] S231, integrating the clustering results and the fluctuation characteristic parameters of dust concentration to form an input data set;

[0138] It should be noted that the clustering results are aligned with the fluctuation characteristic parameter data. For each fluctuation period, a data record is created, which contains the clustering label and all related fluctuation characteristic parameter values ​​of the period. These data records will constitute the input data set, where each row represents a fluctuation period and each column represents a feature (including clustering label and fluctuation characteristic parameter).

[0139] S232, determining the evaluation index of the ventilation capacity of the dust explosion-proof electrical cabinet, and using it as the output target variable;

[0140] It should be noted that the selection of evaluation indicators should be based on the safe operation requirements of the electrical cabinet and the dust explosion-proof standards. The evaluation indicators of the ventilation capacity of the dust explosion-proof electrical cabinet include: ventilation efficiency, ventilation time, dust residue, pressure stability, etc. Ventilation efficiency refers to the replacement rate of air inside the electrical cabinet, usually measured in the number of ventilation times per hour. Ventilation time refers to the time required for the electrical cabinet to reach a safe dust concentration level from the initial state; dust residue refers to the amount of dust remaining inside the electrical cabinet after ventilation, usually expressed as dust mass per unit volume (mg / m³); pressure stability refers to the stability of the internal pressure of the electrical cabinet during the ventilation process, to avoid dust re-suspension or damage to electrical equipment due to pressure fluctuations.

[0141] When building a model, you can determine which indicators are used as the main output target variables based on the specific situation. For example, if the focus is on rapid response, then ventilation time and ventilation efficiency may be the main targets; if you focus on long-term operating costs and equipment maintenance, dust residue and pressure stability may be more important.

[0142] S233. Based on the linear regression method, the dust explosion-proof electrical cabinet ventilation capacity evaluation model is constructed and trained using the input data set and the output target variable;

[0143] It should be noted that the linear regression algorithm is used as the basis of the model. According to the number of features of the input data set and the number of target variables, the input layer and output layer of the model are determined, and the weight and bias parameters of the model are initialized.

[0144] The model is trained by collecting training set data. The weights and bias parameters of the model are then adjusted through iterative optimization algorithms (such as gradient descent) to minimize the difference between the predicted value and the actual value. The loss function value is monitored during the training process to ensure that the performance of the model on the training set is gradually improving.

[0145] S234. Collect a test data set, and verify the dust explosion-proof electrical cabinet ventilation capacity evaluation model, adjust the model parameters according to the verification results, and obtain an optimized dust explosion-proof electrical cabinet ventilation capacity evaluation model.

[0146] It should be noted that the trained model is used to predict the test data set to obtain the evaluation results of ventilation capacity. The performance of the model is evaluated by comparing the model prediction results with the actual observation values ​​and calculating the evaluation indicators (such as accuracy, mean square error, etc.). Then, visualization tools such as charts are used to compare and analyze the prediction results and actual values ​​to understand the performance of the model more intuitively.

[0147] Analyze the impact of model parameters on performance based on the validation results. Adjust model parameters such as learning rate, number of iterations, etc. based on the analysis results to improve the model's predictive ability. Retrain the model with the adjusted parameters and validate again to confirm the performance improvement.

[0148] S3. Based on the use standards of dust explosion-proof electrical cabinets, determine the target ventilation standards for dust explosion-proof electrical cabinets;

[0149] Specifically, based on the use standards of dust explosion-proof electrical cabinets, determining the target ventilation standard for dust explosion-proof electrical cabinets requires comprehensive consideration of multiple factors, including dust characteristics, environmental conditions, equipment requirements, and safety regulations. Based on the above sound velocity, the target ventilation standard for dust explosion-proof electrical cabinets can be determined, including but not limited to the following aspects:

[0150] Air exchange rate: Specifies the air exchange rate that should be achieved inside the electrical cabinet to ensure that the dust concentration is controlled within a safe range.

[0151] Ventilation time: clearly define the time required from the start of ventilation in the electrical cabinet to achieve the predetermined ventilation effect.

[0152] Air pressure and flow: Specifies the air pressure range and flow requirements that the ventilation system should maintain to ensure stable and reliable ventilation effects.

[0153] S4, taking the target ventilation standard as an input parameter, and using the dust explosion-proof electrical cabinet ventilation capacity evaluation model to calculate, to obtain the ventilation time required for the target ventilation standard;

[0154] As a preferred implementation, the target ventilation standard is used as an input parameter, and the dust explosion-proof electrical cabinet ventilation capacity evaluation model is used to calculate the ventilation time required for the target ventilation standard, which includes the following steps:

[0155] S41, inputting the target ventilation standard as an input parameter into a dust explosion-proof electrical cabinet ventilation capacity evaluation model;

[0156] S42, using a dust explosion-proof electrical cabinet ventilation capacity assessment model to calculate and obtain a predicted ventilation time based on a target ventilation standard;

[0157] Specifically, the calculation using the dust explosion-proof electrical cabinet ventilation capacity evaluation model to obtain the predicted ventilation time based on the target ventilation standard includes the following steps:

[0158] Quantify the target ventilation standards (such as ventilation rate, air pressure range, flow requirements, etc.) into specific values ​​or ranges;

[0159] The model will calculate based on the input target ventilation standard and its internal training algorithm. During the calculation process, the model will consider factors such as the characteristics of the electrical cabinet, environmental conditions, and the performance of the ventilation system;

[0160] After the model calculation is completed, the predicted ventilation time based on the target ventilation standard will be output. This predicted ventilation time indicates the time required to reach the target ventilation standard.

[0161] S43, testing the predicted ventilation time. If the predicted ventilation time passes the test, it is output as the ventilation time required for the target ventilation standard. If it fails, the parameters of the dust explosion-proof electrical cabinet ventilation capacity evaluation model are adjusted, and the ventilation time is recalculated.

[0162] like Figure 2 As shown, according to another embodiment of the present invention, a ventilation time automatic calculation system based on a dust explosion-proof electrical cabinet is provided, and the ventilation time automatic calculation system based on a dust explosion-proof electrical cabinet comprises: a fluctuation characteristic analysis module 1, an evaluation model construction module 2, a ventilation standard determination module 3 and a ventilation time calculation module 4, and the fluctuation characteristic analysis module 1, the evaluation model construction module 2, the ventilation standard determination module 3 and the ventilation time calculation module 4 are connected in sequence;

[0163] The fluctuation characteristic analysis module 1 is used to obtain the dust concentration data of the dust explosion-proof electrical cabinet and analyze the fluctuation characteristic parameters of the dust concentration by using the multi-fractal theory;

[0164] Evaluation model building module 2 is used to build a dust explosion-proof electrical cabinet ventilation capacity evaluation model based on the fluctuation characteristic parameters of dust concentration;

[0165] A ventilation standard determination module 3 is used to determine a target ventilation standard for the dust explosion-proof electrical cabinet based on the use standard of the dust explosion-proof electrical cabinet;

[0166] The ventilation time calculation module 4 is used to take the target ventilation standard as an input parameter and use the dust explosion-proof electrical cabinet ventilation capacity evaluation model to calculate and obtain the ventilation time required for the target ventilation standard.

[0167] To sum up, with the help of the above-mentioned technical scheme of the present invention, the present invention obtains the dust concentration data of the dust explosion-proof electrical cabinet and uses the multi-fractal theory to analyze the fluctuation characteristic parameters of the dust concentration, so as to more accurately capture the dynamic changes of the dust concentration, thereby improving the accuracy of the ventilation time calculation, and constructing a dust explosion-proof electrical cabinet ventilation capacity evaluation model based on the fluctuation characteristic parameters of the dust concentration, so that the model can more comprehensively consider the actual working environment and conditions of the dust explosion-proof electrical cabinet, enhance the applicability and generalization ability of the model, and use the dust explosion-proof electrical cabinet ventilation capacity evaluation model for calculation, realize the automatic calculation of the ventilation time, improve the calculation efficiency, reduce manual intervention and errors, and through the automatic calculation of the ventilation time, the maintenance and management plan of the dust explosion-proof electrical cabinet can be more reasonably arranged, the service life of the equipment can be extended, and the maintenance cost can be reduced. The present invention can extract the multifractal characteristic parameters of the dust concentration time series in a refined manner through binning processing, calculation of probability measure and generalized dimension, and construction of multifractal spectrum. By identifying the fluctuation characteristic parameters of dust concentration, it is helpful to build a more accurate dust explosion-proof electrical cabinet ventilation capacity evaluation model, thereby improving the accuracy of ventilation time prediction. Accurate dust concentration fluctuation characteristic analysis is helpful to formulate more effective ventilation strategies, improve workplace safety, and may improve efficiency by optimizing the ventilation process. The present invention divides the fluctuation of time series data of dust concentration through the swing window algorithm, which can more accurately identify the fluctuation period of dust concentration, and provide a more accurate data basis for building an evaluation model. Clustering the time periods with similar fluctuation characteristics can enable the model to better learn and generalize the ventilation capacity under different fluctuation modes, thereby improving the applicability and robustness of the model. By integrating the clustering results and the fluctuation characteristic parameters of dust concentration as the input data set, and determining clear evaluation indicators as the target variables, the model construction process is made more systematic and orderly. The evaluation model is constructed and trained using the linear regression method, and a mapping relationship between the input data set and the target variable can be established to achieve accurate prediction of the ventilation capacity of dust-proof explosion-proof electrical cabinets.

[0168] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program code.

[0169] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for automatically calculating the ventilation time of a dust explosion-proof electrical cabinet, characterized in that: The automatic calculation method of ventilation time based on dust explosion-proof electrical cabinet comprises the following steps: S1. Obtain dust concentration data of dust explosion-proof electrical cabinets, and use multi-fractal theory to analyze the fluctuation characteristic parameters of dust concentration; S2. Based on the fluctuation characteristic parameters of dust concentration, a model for evaluating the ventilation capacity of dust explosion-proof electrical cabinets is constructed; S3. Based on the use standards of dust explosion-proof electrical cabinets, determine the target ventilation standards for dust explosion-proof electrical cabinets; S4, taking the target ventilation standard as an input parameter, and using the dust explosion-proof electrical cabinet ventilation capacity evaluation model to calculate, to obtain the ventilation time required for the target ventilation standard; The method of obtaining dust concentration data of a dust explosion-proof electrical cabinet and analyzing the fluctuation characteristic parameters of dust concentration using multi-fractal theory includes the following steps: S11, arranging the acquired dust concentration data in chronological order to obtain time series data of dust concentration; S12. Based on the multifractal theory, multifractal analysis is performed on the time series data of dust concentration, and a multifractal spectrum is constructed; S13. Calculate the multifractal characteristic parameters of the dust concentration time series according to the constructed multifractal spectrum, and identify the fluctuation characteristic parameters of the dust concentration; The method of performing multifractal analysis on the time series data of dust concentration based on multifractal theory and constructing a multifractal spectrum includes the following steps: S121, preprocessing the time series data of dust concentration, wherein the preprocessing includes data denoising and data cleaning; S122, binning the preprocessed time series data to obtain a number of boxes with equal intervals; S123, respectively calculating the probability measure of dust concentration in each box and the generalized dimension of each box; S124. Based on the calculated probability measure and generalized dimension, the singularity index is calculated using multifractal theory to construct a multifractal spectrum; The method of calculating the multifractal characteristic parameters of the dust concentration time series according to the constructed multifractal spectrum and identifying the fluctuation characteristic parameters of the dust concentration includes the following steps: S131, based on the constructed multifractal spectrum, respectively obtaining the range of the fractal dimension and the singularity index with the largest occupied area; S132, determining the span of the multifractal spectrum on the singularity index axis to obtain the width of the multifractal spectrum; S133, analyzing the difference distribution of singularity index between adjacent sub-intervals in the multifractal spectrum, and identifying the intensity and frequency characteristics of dust concentration fluctuations; The calculation formula for the generalized dimension of each box is: ； D represents the generalized dimension of the box; s represents the scale factor; q Represents a random value; p i Indicates i The probability measure of the boxes; N Indicates the total number of boxes; The construction of the dust explosion-proof electrical cabinet ventilation capacity evaluation model based on the dust concentration fluctuation characteristic parameter comprises the following steps: S21. Based on the fluctuation characteristic parameters of dust concentration, the time series data of dust concentration is divided into fluctuations by a swing window algorithm to obtain fluctuation periods; S22, clustering the fluctuation time periods that meet the similarity threshold in the dust concentration fluctuation characteristics to obtain a clustering result; S23. Based on the clustering results and the fluctuation characteristic parameters of dust concentration, a dust explosion-proof electrical cabinet ventilation capacity evaluation model is constructed; The method of dividing the time series data of dust concentration into fluctuations based on the fluctuation characteristic parameters of dust concentration by a swing window algorithm to obtain the fluctuation period includes the following steps: S211, based on the fluctuation characteristic parameters of dust concentration, initializing the parameters of the swing window algorithm, including the sliding window size and the fluctuation threshold; S212, for each sliding window, determining dust concentration fluctuation characteristic parameters within the sliding window; S213, judging whether the data in the sliding window constitutes fluctuation according to a preset fluctuation threshold, if the fluctuation characteristic parameter exceeds the fluctuation threshold, it indicates that there is fluctuation in the sliding window, and recording the starting point and the ending point of the fluctuation; S214, traverse the entire time series data, and repeat steps S212-S213 to obtain the fluctuation period; The step of clustering the fluctuation time periods in the dust concentration fluctuation characteristics that meet the similarity threshold to obtain the clustering results includes the following steps: S221. Constructing a characteristic vector for each fluctuation period based on the fluctuation characteristic parameters of dust concentration; S222, calculating the dissimilarity between the characteristic vectors of any two fluctuation periods, and constructing a dissimilarity matrix; S223, performing cluster analysis on the fluctuation period using a spectral clustering algorithm according to the constructed dissimilarity matrix to obtain a clustering result; The construction of a dust explosion-proof electrical cabinet ventilation capacity evaluation model based on the clustering results and the fluctuation characteristic parameters of the dust concentration includes the following steps: S231, integrating the clustering results and the fluctuation characteristic parameters of dust concentration to form an input data set; S232, determining the evaluation index of the ventilation capacity of the dust explosion-proof electrical cabinet, and using it as the output target variable; S233. Based on the linear regression method, the dust explosion-proof electrical cabinet ventilation capacity evaluation model is constructed and trained using the input data set and the output target variable; S234. Collect a test data set, and verify the dust explosion-proof electrical cabinet ventilation capacity evaluation model, adjust the model parameters according to the verification results, and obtain an optimized dust explosion-proof electrical cabinet ventilation capacity evaluation model.

2. The method for automatically calculating the ventilation time of a dust explosion-proof electrical cabinet according to claim 1, characterized in that: The target ventilation standard is used as an input parameter, and the dust explosion-proof electrical cabinet ventilation capacity evaluation model is used to calculate and obtain the ventilation time required for the target ventilation standard, which includes the following steps: S41, inputting the target ventilation standard as an input parameter into a dust explosion-proof electrical cabinet ventilation capacity evaluation model; S42, using a dust explosion-proof electrical cabinet ventilation capacity assessment model to calculate and obtain a predicted ventilation time based on a target ventilation standard; S43, testing the predicted ventilation time. If the predicted ventilation time passes the test, it is output as the ventilation time required for the target ventilation standard. If it fails, the parameters of the dust explosion-proof electrical cabinet ventilation capacity evaluation model are adjusted, and the ventilation time is recalculated.

3. A system for automatically calculating ventilation time of a dust explosion-proof electrical cabinet, used to implement the method for automatically calculating ventilation time of a dust explosion-proof electrical cabinet according to any one of claims 1 to 2, characterized in that: The automatic calculation system for ventilation time based on dust explosion-proof electrical cabinets comprises: a fluctuation characteristic analysis module, an evaluation model construction module, a ventilation standard determination module and a ventilation time calculation module, and the fluctuation characteristic analysis module, the evaluation model construction module, the ventilation standard determination module and the ventilation time calculation module are connected in sequence; The fluctuation characteristic analysis module is used to obtain dust concentration data of the dust explosion-proof electrical cabinet and analyze the fluctuation characteristic parameters of the dust concentration using multi-fractal theory; The evaluation model building module is used to build a dust explosion-proof electrical cabinet ventilation capacity evaluation model based on the fluctuation characteristic parameters of dust concentration; The ventilation standard determination module is used to determine the target ventilation standard of the dust explosion-proof electrical cabinet based on the use standard of the dust explosion-proof electrical cabinet; The ventilation time calculation module is used to take the target ventilation standard as an input parameter and use the dust explosion-proof electrical cabinet ventilation capacity evaluation model to calculate and obtain the ventilation time required for the target ventilation standard.

Images