A water-coal slurry production line operation safety supervision system

Abstract

The present invention relates to the technical field of safety supervision, and specifically to a water-coal slurry production line operation safety supervision system, comprising a data acquisition module, a data processing module and a safety supervision module; the data acquisition module is used to collect data from each link of the water-coal slurry production line; the data processing module is used to perform data processing on the collected data; the safety supervision module is used to perform safety supervision on the water-coal slurry production line according to the processed data; the present invention can timely discover potential safety hazards and reduce the occurrence of safety accidents by real-time monitoring of data from each link of the water-coal slurry production line, including raw materials, manufacturing and transportation stages; multi-scale spatiotemporal filtering and optical flow technology are used to eliminate noise and random fluctuations to ensure data accuracy and reliability; by monitoring the distribution and size of solid particles in the coal slurry, equipment wear can be predicted and slowed down, and the service life of the equipment can be extended, thereby reducing the cost of equipment maintenance and replacement.

Description

Technical Field

[0001] The present invention relates to the technical field of safety supervision, and in particular to a safety supervision system for operation of a water-coal slurry production line. Background Art

[0002] Coal-water slurry is a fluid fuel formed by mixing coal and water, which is widely used in the energy and industrial fields. It combines the advantages of coal and liquid fuel, and has the characteristics of efficient combustion, convenient transportation and environmental protection. However, in the actual operation of the coal-water slurry production line, there are still some technical difficulties:

[0003] 1. Solid particles in coal slurry will accelerate the wear of equipment, resulting in shortened equipment life and increased maintenance costs;

[0004] 2. The slurry is prone to precipitation and coagulation during transportation, resulting in pipeline blockage and affecting production continuity;

[0005] 3. Under high temperature and high pressure environment, coal slurry leakage or equipment failure may cause fire or explosion risks

[0006] In view of the above problems, the present invention proposes a water-coal slurry production line operation safety supervision system to improve production safety and efficiency. Summary of the invention

[0007] In view of the above-mentioned problems, the present invention is proposed.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: a water-coal slurry production line operation safety supervision system, comprising a data acquisition module, a data processing module and a safety supervision module;

[0009] The data acquisition module is used to collect data from each link of the coal water slurry production line;

[0010] The data processing module is used to process the collected data;

[0011] The safety supervision module is used to perform safety supervision on the water-coal slurry production line based on the processed data.

[0012] As a preferred solution of the water-coal slurry production line operation safety supervision system described in the present invention, the data processing module includes a data receiving unit, a data processing unit and a data sending unit. The data processing unit processes data in each link of the water-coal slurry, including data processing in the raw material link, data processing in the manufacturing stage and data processing in the transportation stage.

[0013] As a preferred solution of the water-coal slurry production line operation safety supervision system of the present invention, the data processing of the raw material link includes calculating the particle distribution of the raw material and calculating the size of the raw material, which is as follows:

[0014] Divide the collected water-coal slurry raw material data into two data subsets;

[0015] For the two data subsets X t1,1 and X t1,2 , calculate the standard particle size of the water-coal slurry raw material data of the two data subsets, then we have,

[0016]

[0017] Among them, x′ t1,i represents the standard size of raw material particles of the i-th data subset, X t1,i represents the i-th data subset, μ i represents the mean of the i-th data subset, σ i It represents the standard deviation of the i-th data subset, i represents the total number of data subsets divided by the collected raw material data, and the value satisfies the formula i≥2.

[0018] As a preferred solution of the water-coal slurry production line operation safety supervision system of the present invention, the size of the raw material is calculated as follows:

[0019] The standard size of raw material particles in the data subset is used as the standard basis, and the raw material data in the data subset is compared with the standard size of raw material particles x′ t1,i Compare and count the comparison results. According to the number of statistics, and then according to the number of statistics and the total number of data subsets, calculate the particle distribution summary less than the standard size ratio, equal to the standard size ratio, and greater than the standard size ratio, then,

[0020]

[0021] Among them, N t1,i Represents the total number of data in the data subset, N(x t1,i >x′ t1,i ) indicates the amount of data larger than the standard size, N(x t1,i = x′ t1,i ) represents the amount of data equal to the standard size, N(x t1,i <x′ t1,i ) indicates the amount of data that is smaller than the standard size, P t1,i,＞ It indicates the proportion of data larger than the standard size in the divided data subset to the total data, P t1,i,＜ It indicates the proportion of data smaller than the standard size in the divided data subset to the total data, P t1,i,＝Indicates the proportion of data of standard size in the divided data subset to the total data;

[0022] Using two data subsets to verify each other, by comparing the differences between the distribution ratios of the data subsets, we can get:

[0023] ΔP t1,i,＞ =|P t1,1,＞ -P t1,2,＞ |,ΔP t1,i,＜ =|P t1,1,＜ -P t1,2,＜ |,ΔP t1,i,＝ =|P t1,1,＝ -P t1,2,＝ |

[0024] Where ΔP t1,i.j Represents the distribution ratio change rate of the data subset, which is used to verify the difference between the data. Then,

[0025] When the distribution ratio change rate of the data subset satisfies the formula ΔP t1,i,j →0, it means that the difference verification between the current data subsets is completed. Otherwise, the data subsets are re-divided by adjusting the data subset division rules until the formula is satisfied;

[0026] After the difference verification is completed, the standard size of the overall data is re-established, then,

[0027]

[0028] Among them, x′ t1,1 , x′ t1,2 Respectively represent the standard size of raw material particles in the two data subsets, x′ t1 Indicates the reformulated standard size of raw material particles, which is used for data analysis in subsequent analysis units.

[0029] As a preferred solution of the water-coal slurry production line operation safety supervision system of the present invention, the data processing of the manufacturing stage is specifically implemented as follows:

[0030] For the collected video data, the collected video data X t2 Divide the image into multiple frame images according to time intervals;

[0031] Then, multi-scale spatiotemporal filtering is used to perform multi-scale spatiotemporal filtering on the segmented video data to eliminate noise at different time and space scales. Then,

[0032]

[0033] Among them, X t2(x, y, t) represents the pixel value of the video after filtering, W(s, τ) represents the filtering weight at the sth spatial scale at the τth time scale, which is set by the implementer based on historical data, s represents the sequence number of the spatial scale, and τ represents the sequence number of the time scale;

[0034] Using optical flow technology to capture motion information in video images, we have:

[0035]

[0036] Ix+Iy+It=0

[0037]

[0038]

[0039] Among them, Ix, Iy, It represent the gradient of the image in the x, y and t directions respectively, and u s represents the component in the x direction of the video image at the sth spatial scale, v s represents the component in the y direction of the video image at the sth spatial scale, W s represents the filtering weight at the sth spatial scale, S represents the upper limit of the number of spatial scales, u represents the motion information in the x direction of the video image, and v represents the motion information in the y direction of the video image.

[0040] As a preferred solution of the water-coal slurry production line operation safety supervision system of the present invention, the data processing of the transportation stage is specifically implemented as follows:

[0041] For monitoring the coal water slurry status data X t3 , sorted by the collected time series, and used data cleaning to remove outliers to ensure the quality of the data, then,

[0042] Identification of outliers,

[0043] Among them, X t3,i Represents the i-th data in the water-coal slurry state data, including temperature data and pressure data, μ t3,i represents the mean value of the i-th data in the water-coal slurry state data, σ t3,i represents the standard deviation of the ith data in the water-coal slurry state data, Z i represents the calculation result of the i-th data in the water-coal slurry state data. If the calculation result satisfies the formula | Z i |≥3, indicating that the current data is an outlier;

[0044] After the outliers are removed, the moving average method is used to smooth the data to remove random fluctuations in the data, and then,

[0045]

[0046]

[0047] Among them, X′ t3 represents the coal-water slurry state data with outliers removed, n represents the moving average window size, t represents the time series, i represents the number of smoothing processes, N represents the total amount of coal-water slurry data, and x′ t3 It means that the data after moving average processing is sent to the safety supervision module for safety supervision of the water-coal slurry production line.

[0048] As a preferred solution of the water-coal slurry production line operation safety supervision system of the present invention, wherein: the safety supervision module performs safety analysis on the water-coal slurry production line based on data processing results, including comprehensive analysis and single data source analysis;

[0049] For the raw material data processing result x′ t1 , video data processing result x′ t2 And the water-coal slurry state data processing result x′ t3 , using data fusion technology, multi-source data are integrated to construct comprehensive safety status evaluation indicators for water-coal slurry, then,

[0050] X t =α1·x′ t1 +α2·x′ t2 +α3·x′ t3

[0051] Among them, X t represents the comprehensive safety status evaluation index of coal-water slurry after fusion, x′ t1 , x′ t2 , x′ t3 They respectively represent the raw material data processing results, video data processing results and water-coal slurry state data processing results, and α1, α2, and α3 represent weight coefficients.

[0052] As a preferred solution of the water-coal slurry production line operation safety supervision system of the present invention, the comprehensive analysis is specifically implemented as follows:

[0053] The historical data is used as the comparison implementation group of the data analysis model. The historical data is based on the weights set when constructing the comprehensive safety status evaluation index of water-coal slurry. The raw material data, image data and water-coal slurry status data when the safety failure occurs are combined and input into the data analysis model according to the set weights. At this time, the output result F of the model ismax (t), as the upper limit of safe operation of coal water slurry production line;

[0054] The integrated water-coal slurry comprehensive safety status evaluation index is used as the input of the data analysis model, and the safety analysis is performed based on the output results. Then,

[0055] F(t)=f(X t )

[0056] When the output result satisfies the formula F(t)<F max (t) indicates that the data under the current comprehensive safety status evaluation index of water-coal slurry can maintain the safe operation of the water-coal slurry production line;

[0057] When the output result satisfies the formula F(t)≥F max (t), it means that the data under the current comprehensive safety status assessment index of water-coal slurry cannot maintain the safe operation of the water-coal slurry production line. The analysis results will be sent to the safety supervision unit, and the water-coal slurry production line will be safely controlled by relevant staff.

[0058] Beneficial effects of the present invention: The present invention can timely discover potential safety hazards and reduce the occurrence of safety accidents by real-time monitoring of data from each link of the water-coal slurry production line, including the raw materials, manufacturing and transportation stages, thereby improving the safety of the production process; by adopting multi-scale spatiotemporal filtering and optical flow technology to eliminate noise and random fluctuations, the accuracy and reliability of the data are ensured, providing a solid foundation for subsequent safety analysis; by monitoring the distribution and size of solid particles in the coal slurry, equipment wear can be predicted and slowed down, and the service life of the equipment can be extended, thereby reducing the cost of equipment maintenance and replacement. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing 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. Among them:

[0060] Figure 1 The present invention is a schematic diagram of the overall composition structure of a water-coal slurry production line operation safety supervision system. DETAILED DESCRIPTION

[0061] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0062] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0063] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0064] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0065] Meanwhile, in the description of the present invention, it should be noted that the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0066] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0067] Example 1

[0068] Reference Figure 1 , which is the first embodiment of the present invention, provides a water-coal slurry production line operation safety supervision system, including the following steps: data acquisition module, data processing module, safety supervision module

[0069] Specifically, the data acquisition module is used to collect data from each link of the water-coal slurry production line; the data processing module is used to process the collected data; and the safety supervision module is used to perform safety supervision on the water-coal slurry production line based on the processed data.

[0070] Further, the data acquisition module includes a data collection unit and a data sending unit. The data collection unit collects data from each link of the water-coal slurry production line by installing multiple sensors. The sensors are used to collect data from the water-coal slurry production line, including raw material stage sensors, manufacturing stage sensors, and transportation stage sensors. The raw material stage sensors are used to collect water-coal slurry raw material data X in the raw material production stage. t1 The collected water-coal slurry raw material data is divided into two data subsets for mutual verification in subsequent data processing. The manufacturing stage sensor is a camera sensor that collects video data of the water-coal slurry manufacturing site. t2 , including, the work monitoring video data of the staff and the smoke detection data of the manufacturing environment; the transportation stage sensor is used to collect the water-coal slurry loading data X t3 ; The data sending unit sends the data collected by the collection unit to the data processing module, providing a data basis for the data processing module.

[0071] Furthermore, the data processing module includes a data receiving unit, a data processing unit and a data sending unit. The data receiving unit is used to receive data sent by the data collection module. The data processing unit processes the data of each link of the water-coal slurry through the data received by the receiving unit. The data sending unit is used to send the processing results of the data processing unit to the safety supervision module for subsequent safety supervision of the water-coal slurry production line.

[0072] Specifically, the data processing unit processes the data of each link of the water-coal slurry, as follows:

[0073] When processing the data of the raw material link, the data processing of the raw material link is realized by calculating the particle distribution and size of the raw material, as follows:

[0074] For the two data subsets X t1,1 and X t1,2 , calculate the standard particle size of the water-coal slurry raw material data of the two data subsets, then we have,

[0075]

[0076] Among them, x′ t1,i represents the standard size of raw material particles of the i-th data subset, X t1,irepresents the i-th data subset, μ i represents the mean of the i-th data subset, σ i represents the standard deviation of the i-th data subset, i represents the total number of data subsets divided by the collected raw material data, and the value satisfies the formula i≥2. The implementation personnel shall determine the value according to actual needs. In this embodiment, the value is 2 for illustration;

[0077] After the calculation of the standard size of raw material particles in the two data subsets is completed, the particle distribution of the raw material is calculated using the calculated standard size of raw material particles, and then,

[0078] The standard size of raw material particles in the data subset is used as the standard basis, and the raw material data in the data subset is compared with the standard size of raw material particles x′ t1,i Compare and count the comparison results. According to the number of statistics, and then according to the number of statistics and the total number of data subsets, calculate the particle distribution summary less than the standard size ratio, equal to the standard size ratio, and greater than the standard size ratio, then,

[0079]

[0080] Among them, N t1,i Represents the total number of data in the data subset, N(x t1,i >x′ t1,i ) indicates the amount of data larger than the standard size, N(x t1,i = x′ t1,i ) represents the amount of data equal to the standard size, N(x t1,i <x′ t1,i ) indicates the amount of data that is smaller than the standard size, P t1,i,＞ It indicates the proportion of data larger than the standard size in the divided data subset to the total data, P t1,i,＜ It indicates the proportion of data smaller than the standard size in the divided data subset to the total data, P t1,i,＝ Indicates the proportion of data of standard size in the divided data subset to the total data;

[0081] Using two data subsets to verify each other, by comparing the differences between the distribution ratios of the data subsets, we can get:

[0082] ΔP t1,i,＞ =|P t1,1,＞ -P t1,2,＞ |,ΔP t1,i,＜ =|P t1,1,＜ -P t1,2,＜ |,ΔP t1,i,＝ =|P t1,1,＝ -P t1,2,＝ |

[0083] Where ΔPt1,i.j Represents the distribution ratio change rate of the data subset, which is used to verify the difference between the data. Then,

[0084] When the distribution ratio change rate of the data subset satisfies the formula ΔP t1,i,j →0, it means that the difference verification between the current data subsets is completed. Otherwise, the data subsets are re-divided by adjusting the data subset division rules until the formula is satisfied;

[0085] After the difference verification is completed, the standard size of the overall data is re-established, then,

[0086]

[0087] Among them, x′ t1,1 , x′ t1,2 Respectively represent the standard size of raw material particles in the two data subsets, x′ t1 Indicates the reformulated standard size of raw material particles, which is used for data analysis in subsequent analysis units.

[0088] When processing data in the manufacturing stage, video processing technology is used to process the collected video data to improve the clarity of the data in order to improve the accuracy of subsequent data analysis, as follows:

[0089] For the collected video data, the collected video data X t2 Divide the image into multiple frame images according to time intervals;

[0090] Then, multi-scale spatiotemporal filtering is used to perform multi-scale spatiotemporal filtering on the segmented video data to eliminate noise at different time and space scales. Then,

[0091]

[0092] Among them, X t2 (x, y, t) represents the pixel value of the video after filtering, W(s, τ) represents the filtering weight at the sth spatial scale at the τth time scale, which is set by the implementer based on historical data, s represents the sequence number of the spatial scale, and τ represents the sequence number of the time scale;

[0093] Using optical flow technology to capture motion information in video images, we have:

[0094]

[0095] Ix+Iy+It=0

[0096]

[0097]

[0098] Among them, Ix, Iy, It represent the gradient of the image in the x, y and t directions respectively, and u s represents the component in the x direction of the video image at the sth spatial scale, v s represents the component in the y direction of the video image at the sth spatial scale, W s represents the filtering weight at the sth spatial scale, S represents the upper limit of the number of spatial scales, u represents the motion information in the x direction of the video image, and v represents the motion information in the y direction of the video image.

[0099] When processing data in the transportation stage, the water-coal slurry status data during transportation is monitored in real time, as follows:

[0100] For monitoring the coal water slurry status data X t3 , sorted by the collected time series, and used data cleaning to remove outliers to ensure the quality of the data, then,

[0101] Identification of outliers,

[0102] Among them, X t3,i Represents the i-th data in the water-coal slurry state data, including temperature data and pressure data, μ t3,i represents the mean value of the i-th data in the water-coal slurry state data, σ t3,i represents the standard deviation of the ith data in the water-coal slurry state data, Z i represents the calculation result of the i-th data in the water-coal slurry state data. If the calculation result satisfies the formula | Z i |≥3, indicating that the current data is an outlier;

[0103] After the outliers are removed, the moving average method is used to smooth the data to remove random fluctuations in the data, and then,

[0104]

[0105]

[0106] Among them, X′ t3 represents the coal-water slurry state data with outliers removed, n represents the moving average window size, t represents the time series, i represents the number of smoothing processes, N represents the total amount of coal-water slurry data, and x′ t3 It represents the data after moving average processing, which is the processing result of the data processing module and is sent to the safety supervision module for safety supervision of the water-coal slurry production line.

[0107] Furthermore, the safety supervision module receives the data processing results of the data processing module, and based on the data processing results, performs a safety analysis on the water-coal slurry production line, thereby realizing safety supervision of the water-coal slurry production line. The safety supervision module includes a data receiving unit, a data analysis unit, and a safety supervision unit. The data receiving unit is used to receive the data results sent by the data processing module, the data analysis unit performs a safety analysis on the water-coal slurry production line based on the data processing results, and the safety supervision unit realizes safety supervision of the water-coal slurry production line according to the safety analysis results.

[0108] Specifically, the data analysis unit performs safety analysis on the data of each environment of the water-coal slurry by constructing a data analysis model. The data analysis model is a mathematical model for water-coal slurry safety analysis. The raw material data processing results, video data processing results and water-coal slurry state data processing results are used as the input of the model, and the corresponding analysis results are output. The output analysis results serve as the basis for the safety supervision of the water-coal slurry production line operation. The specific implementation is as follows:

[0109] For the raw material data processing result x′ t1 , video data processing result x′ t2 And the water-coal slurry state data processing result x′ t3 , using data fusion technology, multi-source data are integrated to construct comprehensive safety status evaluation indicators for water-coal slurry, then,

[0110] X t =α1·x′ t1 +α2·x′ t2 +α3·x′ t3

[0111] Among them, X t represents the comprehensive safety status evaluation index of coal-water slurry after fusion, x′ t1 , x′ t2 , x′ t3 They represent the processing results of raw material data, video data and water-coal slurry state data respectively. α1, α2 and α3 represent weight coefficients, which are set by the implementers according to the proportion of historical data that affects the safe operation of the water-coal slurry production line.

[0112] According to the data processing results, the data analysis model is used to analyze the safe operation of the water-coal slurry production line.

[0113] When conducting a comprehensive analysis, the integrated water-coal slurry comprehensive safety status assessment index is used as the input of the data analysis model for analysis. Then,

[0114] The historical data is used as the comparison implementation group of the data analysis model. The historical data is based on the weights set when constructing the comprehensive safety status evaluation index of water-coal slurry. The raw material data, image data and water-coal slurry status data when the safety failure occurs are combined and input into the data analysis model according to the set weights. At this time, the output result F of the model is max (t), as the upper limit of safe operation of coal water slurry production line;

[0115] The integrated water-coal slurry comprehensive safety status evaluation index is used as the input of the data analysis model, and the safety analysis is performed based on the output results. Then,

[0116] F(t)=f(X t )

[0117] When the output result satisfies the formula F(t)<F max (t) indicates that the data under the current comprehensive safety status evaluation index of water-coal slurry can maintain the safe operation of the water-coal slurry production line;

[0118] When the output result satisfies the formula F(t)≥F max (t), it means that the data under the current comprehensive safety status assessment index of water-coal slurry cannot maintain the safe operation of the water-coal slurry production line. The analysis results will be sent to the safety supervision unit, and the water-coal slurry production line will be safely controlled by relevant staff.

[0119] When a single data source is analyzed, the data processing results are analyzed independently using a data analysis model and the corresponding analysis results are output.

[0120] When the raw data processing result x′ t1 When used as the input of the data analysis model, the linear regression analysis algorithm is used to analyze the safe operation of the water-coal slurry production line, then,

[0121] By constructing a linear regression equation and transforming the raw material data processing result x′ t1 As the input of the linear regression equation, we have f(x) = a·x′ t1 +b

[0122] At the same time, the raw material data x″ when the safety failure of the water-coal slurry production line occurred in the historical data t1 As a comparison group, we have f′(x)=a·x″ t1 +b

[0123] Among them, a represents the slope of the linear equation, and b represents the intercept of the linear equation, which are set by the implementer according to the actual application scenario;

[0124] Compare the output results of the data analysis model under the raw material data processing results with the data results of the comparison group, then we have:

[0125] If the comparison result satisfies the formula f(x)≥f′(x), it means that the raw material data at this time does not meet the water-coal slurry manufacturing specifications. The raw material data at this time is used as the construction amount of the comprehensive safety status evaluation index of water-coal slurry, and the comprehensive safety status evaluation index of water-coal slurry is reconstructed. A secondary analysis is performed based on the reconstructed comprehensive safety status evaluation index of water-coal slurry. If the secondary analysis result satisfies F(t)<F max (t), it means that the current raw material data does not meet the manufacturing specifications, but does not cause safety operation failure of the water-coal slurry production line; if the secondary analysis result satisfies F(t)≥F max (t), it means that the current raw material data does not meet the manufacturing specifications and causes safety operation failure of the water-coal slurry production line;

[0126] When the multiple comparison results satisfy the formula f(x)<f′(x), it means that the current raw material data meets the manufacturing specifications, and no secondary analysis is performed to maintain the safe operation of the current water-coal slurry production line;

[0127] When the video data processing result x′ t2 When used as the input of the data analysis model, the behavior recognition algorithm is used to analyze the safe operation of the water-coal slurry production line, then,

[0128] For the motion information in the video data processing results, the target detection algorithm is used to identify the moving objects in the video, and the object tracking method is used to track the movement trajectory of the object and predict the movement trajectory at the next time node;

[0129] Use historical data as a training set for the data analysis model to improve its accuracy through training. Use the final test results as the limit value of the running trajectory to limit the prediction of the object's running trajectory.

[0130] According to the predicted results of the operation trajectory, the safe operation analysis of the water-coal slurry production line is carried out. When the predicted operation trajectory exceeds the set operation trajectory limit value, the personnel operation in the water-coal slurry production line manufacturing stage is not standardized. The analysis results are sent to the safety supervision unit, and the relevant staff are notified to conduct safety management and control of the operators at this time;

[0131] When the water-coal slurry state data processing result x′ t3 When used as the input of the data analysis model, the isolation forest algorithm is used to analyze the safe operation of the water-coal slurry production line, then,

[0132] For the processed water-coal slurry state data, the isolation forest algorithm is used to identify abnormal data in the water-coal slurry state data, as follows:

[0133] Calculate the average path length in the composition data of the water-coal slurry state data, then we have,

[0134]

[0135] Where n represents the total number of composition data in the water-coal slurry state data, h(x) represents the average path length of different composition data, and h i (x′ t3 ) represents the path length of different composition data in the ith tree, and the different composition data of the water-coal slurry state data include temperature and pressure;

[0136] Calculate the abnormal fraction of water-coal slurry state data, then we have,

[0137]

[0138]

[0139] Where n represents the total number of component data in the water-coal slurry state data, h(x) represents the average path length of different component data, H(n-1) represents the n-1th harmonic number, and c(n) represents the average path length of the binary tree;

[0140] According to the calculated scores, we can identify abnormal data, then we have,

[0141] If the calculated anomaly score satisfies the formula s(x′ t3 ,n)>s max (x″ t3 ,n), indicating that the current water-coal slurry state data is abnormal, the analysis results are sent to the safety supervision unit, and the relevant staff are notified to conduct safety control of water-coal slurry data;

[0142] If the calculated anomaly score satisfies the formula s(x′ t3 ,n)≤s max (x″ t3 ,n), indicating that the current water-coal slurry status data is normal, maintaining the safe operation of the current water-coal slurry production line;

[0143] It should be noted that s max (x″ t3 ,n) represents the anomaly score calculated in the encouragement forest of the historical state data of the water-coal slurry when a safety failure occurs. According to the calculated anomaly score, the abnormal data in the processed water-coal slurry state data is identified.

[0144] Furthermore, if the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0145] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0146] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0147] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0148] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0149] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A water-coal slurry production line operation safety supervision system, characterized by: Including data acquisition module, data processing module and safety supervision module; The data acquisition module is used to collect data from each link of the coal water slurry production line; The data processing module is used to process the collected data; The data processing module includes a data receiving unit, a data processing unit and a data sending unit. The data processing unit processes the data of each link of the water-coal slurry, including the data processing of the raw material link, the data processing of the manufacturing stage and the data processing of the transportation stage. The data processing of the raw material link includes calculating the particle distribution of the raw material and calculating the size of the raw material, as follows: Divide the collected water-coal slurry raw material data into two data subsets; For the two data subsets as well as , calculate the standard particle size of the water-coal slurry raw material data of the two data subsets, then we have, in, Indicates The standard size of raw material particles for each data set, Indicates A subset of data, Indicates The mean of a subset of data, Indicates The standard deviation of a subset of data; The size of the raw materials is calculated as follows: The standard size of raw material particles in the data subset is used as the standard basis, and the raw material data in the data subset is compared with the standard size of raw material particles. Compare and count the comparison results, then calculate the particle distribution summary less than the standard size ratio, equal to the standard size ratio and greater than the standard size ratio based on the number of statistics and the total number of data subsets, then, , , in, The total number of data representing the data subset, Indicates an amount of data larger than the standard size, Indicates an amount of data equal to the standard size, Indicates an amount of data that is smaller than the standard size. Indicates the proportion of data larger than the standard size in the divided data subset to the total data. It indicates the proportion of data smaller than the standard size in the divided data subset to the total data. Indicates the proportion of data of standard size in the divided data subset to the total data; Using two data subsets to verify each other, by comparing the differences between the distribution ratios of the data subsets, we can get: , , in, represents the rate of change of the distribution ratio of the data subset, In express , or , used to verify the difference between data, then we have, When the distribution ratio change rate of the data subset satisfies the formula When , it indicates that the difference verification between the current data subsets is completed. Otherwise, the data subsets are re-divided by adjusting the data subset division rules until the formula is satisfied. After the difference verification is completed, the standard size of the overall data is re-established, then, in, , Respectively represent the standard size of raw material particles in the two data subsets, Indicates the reformulated standard size of raw material particles, which is used for data analysis of subsequent analysis units; The specific implementation of data processing in the manufacturing stage is as follows: For the collected video data, the collected video data Divide the image into multiple frame images according to time intervals; Then, multi-scale spatiotemporal filtering is used to perform multi-scale spatiotemporal filtering on the segmented video data to eliminate noise at different time and space scales. Then, in, Represents the video pixel value after filtering, Indicates Time scale The filter weights at each spatial scale are set by the implementer based on historical data. A sequence number indicating the spatial scale, A sequence number representing the time scale; Using optical flow technology to capture motion information in video images, we have: in, , , The images are respectively , as well as The gradient in direction, Indicates In video images at different spatial scales The weight in direction, Indicates In video images at different spatial scales The weight in direction, Indicates The filter weights at each spatial scale are represents the upper limit of the number of spatial scales, Indicates the video image Movement information in direction, Indicates the video image Movement information in direction; The data processing in the transportation phase is specifically implemented as follows: For monitoring coal water slurry status data , sorted by the collected time series, and used data cleaning to remove outliers to ensure the quality of the data, then, Identification of outliers, in, Indicates the first data, including temperature data and pressure data, Indicates the first The mean of the data, Indicates the first The standard deviation of the data, Indicates the first The calculation result of the data, if the calculation result satisfies the formula , indicating that the current data is an outlier; After the outliers are removed, the moving average method is used to smooth the data to remove random fluctuations in the data, and then, in, It represents the coal-water slurry state data with outliers removed. represents the moving average window size, represents a time series, Indicates the number of smoothing processes, Indicates the total amount of water-coal slurry data, Represents data after moving average processing; The safety supervision module is used to perform safety supervision on the water-coal slurry production line based on the processed data.

2. A coal water slurry production line operation safety supervision system as claimed in claim 1, characterized in that: The safety supervision module conducts safety analysis on the water-coal slurry production line based on data processing results. Including, comprehensive analysis and single data source analysis; For raw material data processing results , Video data processing results And the results of water-coal slurry state data processing , using data fusion technology, multi-source data are integrated to construct comprehensive safety status evaluation indicators for water-coal slurry, then, in, It represents the comprehensive safety status evaluation index of coal-water slurry after fusion. , , They represent the raw material data processing results, video data processing results and water-coal slurry state data processing results respectively. , , Represents the weight coefficient.

3. A water-coal slurry production line operation safety supervision system as claimed in claim 2, characterized in that: The comprehensive analysis is specifically implemented as follows: The historical data is used as a comparison implementation group of the data analysis model. The historical data is based on the weights set when constructing the comprehensive safety status evaluation index of water-coal slurry. The raw material data, image data and water-coal slurry status data when the safety failure occurs are combined and input into the data analysis model according to the set weights. At this time, the output result of the model is , as the upper limit of safe operation of coal water slurry production line; The integrated water-coal slurry comprehensive safety status evaluation index is used as the input of the data analysis model, and the safety analysis is performed based on the output results. Then, When the output satisfies the formula When , it means that the data under the current comprehensive safety status evaluation index of water-coal slurry can maintain the safe operation of the water-coal slurry production line; When the output satisfies the formula It means that the data under the current comprehensive safety status assessment index of water-coal slurry cannot maintain the safe operation of the water-coal slurry production line. The analysis results will be sent to the safety supervision unit, and the water-coal slurry production line will be safely controlled by relevant staff.

Images