CN113887380B - Intelligent sample preparation system for coal samples - Google Patents
Intelligent sample preparation system for coal samples Download PDFInfo
- Publication number
- CN113887380B CN113887380B CN202111145692.5A CN202111145692A CN113887380B CN 113887380 B CN113887380 B CN 113887380B CN 202111145692 A CN202111145692 A CN 202111145692A CN 113887380 B CN113887380 B CN 113887380B
- Authority
- CN
- China
- Prior art keywords
- data
- value
- temperature
- time
- past
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention relates to the technical field of intelligent sample preparation, in particular to an intelligent sample preparation system for a coal sample, which comprises a preparation and collection unit, a mutual matching unit, a cloud service unit, a preparation and branch management unit, a preparation and judgment unit, an adjusting unit and a sample display and extraction unit; the system set unit is used for collecting real-time sample preparation data, marking the real-time collected sample preparation data as real system information and transmitting the real system information to the mutual matching unit; according to the invention, the relevance calculation is carried out on the data acquired in real time and the analyzed influence numerical values, so that the numerical calculation and analysis are carried out on the manufacture of the related samples, the manufacture condition of the samples is known, the numerical value is checked again according to the manufacture condition required by the cloud service unit, the accuracy of data analysis is increased, and the manufacture efficiency of the samples is improved.
Description
Technical Field
The invention relates to the technical field of intelligent sample preparation, in particular to an intelligent sample preparation system for a coal sample.
Background
In order to determine certain characteristics of coal, a representative part of coal is collected according to regulations, and according to the data obtained by analyzing a coal sample, the type and the coal quality characteristics of the coal, the processing and utilization characteristics and the industrial utilization direction of the coal can be determined.
In the current sample preparation process, the sample preparation process is completed through machinery, the mechanical sample preparation is only set for executing one input, so that the sample preparation is carried out on coal, some accidents occurring in the sample preparation process cannot be coped with, and the failure rate of the mechanical sample preparation is increased.
Therefore, an intelligent sample preparation system for the coal samples is provided.
Disclosure of Invention
The invention aims to provide an intelligent sample preparation system for coal samples, which is characterized in that collected influences and recorded related images are identified and matched, so that corresponding data are extracted quickly, the data identification and extraction time is saved, the identification accuracy is improved, the association degree calculation is carried out according to the corresponding data, and different numerical values are subjected to influence analysis, so that whether the numerical values have influences or not is analyzed, the influence numerical values are determined, and the data inaccuracy in the data calculation process in the later period is avoided; the relevance degree is calculated through the data collected in real time and the analyzed influence numerical values, so that numerical calculation and analysis are carried out on the manufacturing of related samples, the manufacturing conditions of the samples are known, numerical value secondary accounting is carried out according to the required manufacturing conditions of the samples, the accuracy of data analysis is improved, and the manufacturing efficiency of the samples is improved.
The purpose of the invention can be realized by the following technical scheme: the intelligent sample preparation system for the coal samples comprises a preparation and collection unit, a mutual matching unit, a cloud service unit, a preparation and branch management unit, a decision making unit, an adjusting unit and a sample display and extraction unit;
the system set unit is used for collecting real-time sample preparation data, marking the real-time collected sample preparation data as real system information and transmitting the real system information to the mutual matching unit;
the cloud service unit stores forward information and shape information related to sample making recorded in the past, and the mutual matching unit acquires the forward information from the cloud service unit and performs mutual matching operation on the forward information and the mutual matching unit;
the system management unit is used for analyzing and managing the previous product data, previous sample data, previous time data, previous quality data, previous shape data, previous temperature data, previous humidity data, previous formation data and previous loss data together to obtain a damage average value, an average difference ratio, a temperature-time factor ui, an initial previous temperature value, a humidity-time factor vi, an initial previous humidity value, a safety degree value and a match array;
the formulating and judging unit carries out sample judging operation on the shape information, real shadow data, real temperature data, real humidity data, essential data, real time data, loss average value, mean difference ratio, temperature time factor ui, initial temperature value, humidity factor vi, initial humidity value, safety number value and shape matching number together, and transmits the obtained regulating signal and regulating value to the regulating unit and the sample display and extraction unit respectively;
the adjusting unit adjusts the value according to the received adjusting signal and the adjusting value, and the sample display and extraction unit is used for receiving and displaying the adjusting signal and the adjusting value.
Further, the specific operation process of the mutual matching operation is as follows:
selecting destination image data and real shadow data, and matching the destination image data with the real shadow data to obtain a matched signal and a matched error signal;
extracting a matching signal and a matching error signal, identifying the matching signal and the matching error signal, judging that the data acquired in real time is abnormal when the matching error signal is identified, generating a re-acquired signal, transmitting the re-acquired signal to an integration making unit, carrying out data acquisition by the integration making unit according to the re-acquired signal, judging that the data are matched when the matching signal is identified, extracting forward map data corresponding to real image data, and calibrating the corresponding forward map data into selected forward map data;
and extracting corresponding historical data, current time data, historical quality data, historical shape data, previous temperature data, previous humidity data, previous formation data and previous loss data according to the selected historical data.
Further, the specific operation process of the analysis management operation is as follows:
selecting a plurality of corresponding past sample data according to the past sample data, extracting corresponding past time data and past quality data according to the plurality of past sample data, respectively calibrating the past quality data of different time points of a manufactured sample, and performing difference calculation on the past quality data of two different time points so as to calculate a past quality difference value;
performing quality classification processing according to the previous quality difference value, the previous quality data and the current time data to obtain a loss average value and a mean-difference ratio;
selecting a plurality of corresponding previous temperature data according to the previous product data, extracting the time for making a sample from the previous product data according to the corresponding previous temperature data, calibrating the time point for starting making and the time point for finishing making respectively, calculating the difference between the time point for starting making and the time point for finishing making, calculating the temperature-time difference, selecting different previous temperature data and corresponding temperature-time difference values for variable analysis, and obtaining a forward temperature response signal, a reverse temperature response signal, an irrelevant temperature response signal, a temperature-time factor ui and an initial previous temperature value;
selecting a plurality of corresponding forward wetting data according to the forward wetting data, extracting the time for making a sample from the forward wetting data according to the forward wetting data, calibrating the time point for starting making and the time point for finishing making respectively, calculating the difference between the time point for starting making and the time point for finishing making, calculating the wet time difference, selecting different forward wetting data and corresponding wet time difference values for variable analysis, and obtaining a forward wet sound signal, a reverse wet sound signal, an irrelevant wet sound signal, a wet time factor vl and an initial forward wetting value;
and selecting the past shape data and the time data according to the past sample data, and carrying out shape time processing on the past shape data and the time data to obtain a shape matching array and a safety number value.
Further, the specific process of performing quality classification processing according to the previous quality difference value, the previous quality data and the current time data is as follows:
and performing difference calculation on the previous quality data at two different time points corresponding to the difference calculation, thereby calculating a quality time difference value, and bringing the quality time difference value and the previous quality difference value into a proportion calculation formula: calculating the speed loss value, summing the speed loss values corresponding to a plurality of previous sample data, and dividing the value obtained after summation by the number of the previous sample data to obtain a speed loss average value;
the method comprises the steps of summing a plurality of past quality difference values, dividing the numerical value obtained after summing calculation by the times of the plurality of past quality difference values to calculate a past quality average difference value, summing the past quality data corresponding to the plurality of past quality difference values, dividing the past quality data obtained after summing calculation by the number of the plurality of past quality data to calculate a past quality average value, carrying out proportion calculation on the past quality average value and the past quality average difference value, and calculating an average difference ratio.
Further, the specific process of performing variable analysis according to the selected different forward temperature data and the corresponding temperature difference value is as follows:
the previous temperature data is planned to be an X-axis numerical value and the temperature time difference value is planned to be a Y-axis numerical value, virtual plane rectangular coordinate system drawing is carried out, the value with the highest Y-axis numerical value is selected, the previous temperature data corresponding to the previous temperature data is marked to be an inefficient previous temperature value, the value with the lowest Y-axis numerical value is selected, and the previous temperature data corresponding to the previous temperature data is marked to be an efficient previous temperature value;
analyzing the temperature influence of the inefficient forward temperature value, the efficient forward temperature value and the virtual plane rectangular coordinate system, when the relation between the inefficient forward temperature value and the efficient forward temperature value in the virtual plane rectangular coordinate system is that the inefficient forward temperature value is in front of the efficient forward temperature value and the efficient forward temperature value is in back of the inefficient forward temperature value, judging that the manufacturing time is high along with the rise of the temperature, generating a forward temperature response signal, when the relation between the inefficient forward temperature value and the efficient forward temperature value in the virtual plane rectangular coordinate system is that the inefficient forward temperature value is in back of the inefficient forward temperature value and the efficient forward temperature value is in front of the efficient forward temperature value, judging that the manufacturing time is reduced along with the rise of the temperature, marking the forward temperature data and the temperature difference value as a reverse influence relation, generating a reverse temperature response signal, and when the numerical values of the inefficient forward temperature value and the efficient forward temperature value are the same, judging that the manufacturing time is kept unchanged along with the change of the temperature, and generating an irrelevant temperature response signal, respectively calibrating the forward temperature response signal, the reverse temperature response signal and the irrelevant temperature response signal into identification values 1,2 and 3;
according to different past temperature data and different temperature and time difference values, different past temperature data and different temperature and time difference values are brought into a calculation formula: the temperature-time difference value 1-the temperature-time difference value 2 is (previous temperature data 1-previous temperature data 2) × ui, wherein, the temperature-time difference value 1 and the temperature-time difference value 2 are respectively represented as two different previous temperature data, the temperature-time difference value 1 and the temperature-time difference value 2 are respectively represented as two different temperature-time difference values, and are corresponding to each other, ui is represented as an influence factor of the previous temperature data on the temperature-time difference value, namely, a temperature-time factor, and the previous temperature data when the temperature changes and the temperature-time difference value remains unchanged is selected and calibrated as an initial previous temperature value.
Further, the specific process of performing shape time processing on the past shape data and the past time data is as follows:
extracting corresponding shape data according to different time data, and extracting the shape data of a plurality of shape data at the same time point, thereby counting the occurrence times of various shapes, marking the shape with the most occurrence times as a matching shape, and sequentially marking the matching shapes of a plurality of different times as a shape array;
counting the occurrence times according to various shapes, comparing the shape corresponding to each past sample data with the matching shape of each past sample data, counting the times different from the matching shape, calibrating the times to be abnormal times, carrying out mean value calculation on the abnormal times of a plurality of past sample data, calculating an abnormal mean value, carrying out difference value calculation on the abnormal times and the abnormal mean value, and calculating a plurality of abnormal difference values;
sorting the plurality of abnormal difference values from large to small to obtain abnormal difference value sorting data, selecting the maximum value and the minimum value in the abnormal difference value sorting data, carrying out mean value calculation on the maximum value and the minimum value in the abnormal difference value sorting data to calculate an abnormal difference mean value, carrying out summation calculation on the abnormal difference mean value and the abnormal mean value, and calculating a safety number value.
Further, the specific operation process of the sample determination operation is as follows:
carrying out shape processing on real image data, real-time data, shape information, a safety order value and a matching shape group corresponding to the previous sample data to obtain an image identification value ra, wherein a is 7 and 8;
selecting the substantial data corresponding to the real-time before the sample is started to be manufactured, calculating the difference value of the substantial data and the first substantial data in the set time after the sample is started to be manufactured, calculating the difference value of the substantial data and the real-time data corresponding to the first substantial data, calculating the real-time difference value, and calculating the speed of the substantial difference value and the real-time difference value: calculating the real-time difference value and the real data to calculate the real-time difference value, and calculating the difference value of the real difference value and the average difference value to calculate the difference value;
the image identification value, the actual temperature data, the actual humidity data, the actual speed value, the speed loss mean value, the ratio difference value, the temperature-time factor ui, the initial forward temperature value, the humidity-time factor vl and the initial forward humidity value are substituted into a evaluation calculation formula to calculate a sample preparation evaluation score PIs divided into；
Setting a safety preset value of the sample preparation evaluation score, comparing the safety preset value with the sample preparation evaluation score, judging that a relevant value needs to be adjusted when the safety preset value of the sample preparation evaluation score is smaller than or equal to the sample preparation evaluation score, generating an adjusting signal, setting a qualification preset score of the sample preparation according to the adjusting signal, and bringing the qualification preset score into a calculation formula again, so that a real-time value is reversely deduced, a required standard value is calculated, a corresponding value is generated according to the change of the standard value, and the generated value is calibrated to be the adjusting value.
Further, the specific processing of shape processing on the real image data, the real-time data, the shape information, the safety order value and the shape matching group corresponding to the previous sample data is specifically as follows:
selecting a corresponding shape matching array according to the time point corresponding to the real-time data, marking the shape of the shape matching array as shape matching data, selecting real image data corresponding to the same real-time data, matching the real image data with the shape image to obtain a corresponding shape image, selecting a corresponding shape name according to the shape image, matching the shape name with the shape matching data, judging that the results are consistent when the matching is successful, generating a same signal, judging that the results are inconsistent when the matching is successful, and generating a no signal;
extracting a non-signal, counting the times of non-signal occurrence, calibrating the times to be a non-time value, comparing the non-time value with a safety time value, judging that the abnormal times are more and generating an alarm signal when the non-time value is greater than or equal to the safety time value, and judging that the abnormal times are normal and generating a prompt signal when the non-time value is less than the safety time value;
extracting an alarm signal and a prompt signal, giving identification numbers to the alarm signal and the prompt signal, giving a numerical value 7 and a numerical value 8 to the alarm signal and the prompt signal respectively, calibrating an image identification value uniformly to the alarm signal and the prompt signal, marking the image identification value as ra, and marking a as 7 and 8.
Further, the evaluation calculation formula is specifically:
wherein, PIs divided intoExpressed as a sample preparation evaluation score, SW expressed as actual temperature data, CW expressed as an initial forward temperature value, ui expressed as a warm time factor, SS expressed as actual wet data, CS expressed as an initial forward wet value, vl expressed as a wet time factor, VS expressed as an actual speed value, VJ expressed as a loss rate mean value, e1 expressed as a weight coefficient of a difference value between the actual speed value and the loss rate mean value to the score, g expressed as an influence conversion adjustment factor of the sample preparation evaluation score, ZB expressed as a proportion difference value, e2 expressed as a weight coefficient of the proportion difference value, ra expressed as an image recognition value, and e3 expressed as a weight coefficient of the image recognition value.
The invention has the beneficial effects that:
(1) the collected influence and the recorded related image are identified and matched, so that corresponding data are extracted quickly, the data identification and extraction time is saved, the identification accuracy is improved, the association degree is calculated according to the corresponding data, different numerical values are subjected to influence analysis, whether the numerical values have influence or not is analyzed, the influence on the numerical values is determined, and the data inaccuracy in the data calculation process at the later stage is avoided;
(2) the relevance degree is calculated through the data collected in real time and the analyzed influence numerical values, so that numerical calculation and analysis are carried out on the manufacturing of related samples, the manufacturing conditions of the samples are known, numerical value secondary accounting is carried out according to the required manufacturing conditions of the samples, the accuracy of data analysis is improved, and the manufacturing efficiency of the samples is improved.
Drawings
The invention will be further described with reference to the accompanying drawings.
FIG. 1 is a system block diagram of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the invention relates to an intelligent sample preparation system for coal samples, which comprises a preparation and collection unit, a mutual matching unit, a cloud service unit, a preparation and branch management unit, a decision unit, an adjusting unit and a sample display and extraction unit;
the system collection unit is used for collecting real-time sample preparation data, marking the real-time collected sample preparation data as real system information, wherein the real system information comprises real shadow data, real temperature data, real humidity data, substantial data and real time data, the real shadow data refers to an image of a sample detected in real time, the real temperature data refers to the real-time temperature of the prepared sample, the real humidity data refers to the real-time humidity of the prepared sample, the substantial data refers to the real-time mass of the prepared sample, and the real time data refers to the real-time point of the prepared sample, and the real shadow data is transmitted to the mutual matching unit;
the cloud service unit stores past record sample making related past system information and shape information, the past system information comprises past product data, past sample data, time data, past quality data, past shape data, past graph data, past temperature data and past humidity data, the past product data refers to a sample type corresponding to the past record sample making, the past sample data refers to the past record made sample, the time data refers to a time point corresponding to the past record made sample, the past quality data refers to the mass size of the past record made sample, the past shape data refers to the shape of the past record made sample, the past graph data refers to an image of the record made sample, the past temperature data refers to the temperature size of the past record made sample, the past humidity data refers to the humidity size of the past record made sample, wherein the shape information comprises a shape image and a shape name, the shape image refers to the appearance of a figure or a video image, and the shape name refers to the name of the figure appearance, namely a square, a circle and the like;
mutual matching unit obtains toward article data, toward appearance data, data when going, toward matter data, toward shape data, toward picture data, toward temperature data and toward wet data from the cloud service unit to article data, toward appearance data, data when going, toward matter data, toward shape data, toward picture data, toward temperature data and toward wet data and reality shadow data carry out mutual matching operation, and mutual matching operation's specific operation process does:
selecting previous image data and real image data, matching the previous image data with the real image data, judging that the type of a sample image detected in real time is stored in the previous image data to generate a matching signal when the matching result of the previous image data and the real image data is consistent, and judging that the type of the sample image detected in real time is not stored in the previous image data to generate a matching error signal when the matching result of the previous image data and the real image data is inconsistent;
extracting a matching signal and a matching error signal, identifying the matching signal and the matching error signal, judging that the data acquired in real time is abnormal when the matching error signal is identified, generating a re-acquired signal, transmitting the re-acquired signal to an integration making unit, carrying out data acquisition by the integration making unit according to the re-acquired signal, judging that the data are matched when the matching signal is identified, extracting forward map data corresponding to real image data, and calibrating the corresponding forward map data into selected forward map data;
extracting corresponding previous product data, previous sample data, current time data, previous quality data, previous shape data, previous temperature data, previous wetness data, previous formation data and previous loss data according to the selected previous image data, and transmitting the previous product data, previous sample data, current time data, previous quality data, previous shape data, previous temperature data, previous wetness data, previous formation data and previous loss data which correspond to the previous image data and the real shadow data to the branch control unit;
the system divides the management unit to be used for to toward article data, toward appearance data, time data, toward quality data, toward shape data, toward temperature data, toward wet data, toward the data of becoming and the data of losing go together carries out analysis management operation, and analysis management operation's specific operation process is:
selecting a plurality of corresponding past sample data according to the past sample data, extracting corresponding past time data and past quality data according to the plurality of past sample data, respectively calibrating the past quality data of different time points of a manufactured sample, and performing difference calculation on the past quality data of two different time points so as to calculate a past quality difference value;
and performing difference calculation on the previous quality data at two different time points corresponding to the difference calculation, thereby calculating a quality time difference value, and bringing the quality time difference value and the previous quality difference value into a proportion calculation formula: calculating the speed loss value, summing the speed loss values corresponding to a plurality of previous sample data, and dividing the value obtained after summation by the number of the previous sample data to obtain a speed loss average value;
summing the plurality of past quality difference values, dividing the value obtained after the summation by the times of the plurality of past quality difference values to obtain a past quality average difference value, summing the past quality data corresponding to the plurality of past quality difference values, dividing the past quality data obtained after the summation by the number of the plurality of past quality data to obtain a past quality average value, performing proportion calculation on the past quality average value and the past quality average difference value, and calculating an average difference ratio;
selecting a plurality of corresponding previous temperature data according to the previous product data, extracting the time for making a sample from the previous product data according to the corresponding previous temperature data, calibrating the time point for starting making and the time point for finishing making respectively, calculating the difference between the time point for starting making and the time point for finishing making, calculating the temperature-time difference, and selecting different previous temperature data and corresponding temperature-time difference values for variable analysis, specifically:
the previous temperature data is planned to be an X-axis numerical value and the temperature time difference value is planned to be a Y-axis numerical value, virtual plane rectangular coordinate system drawing is carried out, the value with the highest Y-axis numerical value is selected, the previous temperature data corresponding to the previous temperature data is marked to be an inefficient previous temperature value, the value with the lowest Y-axis numerical value is selected, and the previous temperature data corresponding to the previous temperature data is marked to be an efficient previous temperature value;
analyzing the temperature influence of the inefficient forward temperature value, the efficient forward temperature value and the virtual plane rectangular coordinate system, when the relation between the inefficient forward temperature value and the efficient forward temperature value in the virtual plane rectangular coordinate system is that the inefficient forward temperature value is in front of the efficient forward temperature value and the efficient forward temperature value is in back of the inefficient forward temperature value, judging that the manufacturing time is high along with the rise of the temperature, generating a forward temperature response signal, when the relation between the inefficient forward temperature value and the efficient forward temperature value in the virtual plane rectangular coordinate system is that the inefficient forward temperature value is in back of the inefficient forward temperature value and the efficient forward temperature value is in front of the efficient forward temperature value, judging that the manufacturing time is reduced along with the rise of the temperature, marking the forward temperature data and the temperature difference value as a reverse influence relation, generating a reverse temperature response signal, and when the numerical values of the inefficient forward temperature value and the efficient forward temperature value are the same, judging that the manufacturing time is kept unchanged along with the change of the temperature, and generating an irrelevant temperature response signal, respectively calibrating the forward temperature response signal, the reverse temperature response signal and the irrelevant temperature response signal into identification values 1,2 and 3;
according to different past temperature data and different temperature and time difference values, different past temperature data and different temperature and time difference values are brought into a calculation formula: the temperature-time difference value 1-the temperature-time difference value 2 is (previous temperature data 1-previous temperature data 2) × ui, wherein, the temperature-time difference value 1 and the temperature-time difference value 2 are respectively represented as two different previous temperature data, the temperature-time difference value 1 and the temperature-time difference value 2 are respectively represented as two different temperature-time difference values, ui is represented as an influence factor of the previous temperature data on the temperature-time difference value, namely a temperature-time factor, i is 1,2,3, and ui respectively corresponds to three situations of a forward temperature response signal, a reverse temperature response signal and an irrelevant temperature response signal, when i is 1, u1 is a forward value, when i is 2, u2 is a negative value, when i is 3, u3 is zero, the previous temperature data when the temperature difference value is changed and the temperature-time difference value is kept unchanged are selected and are calibrated as an initial previous temperature value;
selecting a plurality of corresponding forward wetting data according to the forward wetting data, extracting the time for making a sample of the forward wetting data according to the forward wetting data, calibrating the time point for starting making and the time point for finishing making respectively, calculating the difference value between the time point for starting making and the time point for finishing making, calculating the wet time difference value, selecting different forward wetting data and corresponding wet time difference values for variable analysis, and specifically:
the forward wetting data is planned to be an X-axis numerical value and the wet time difference value is planned to be a Y-axis numerical value, virtual plane rectangular coordinate system drawing is carried out, the value with the highest Y-axis numerical value is selected, the forward wetting data corresponding to the forward wetting data is marked to be an inefficient forward wetting value, the value with the lowest Y-axis numerical value is selected, and the forward wetting data corresponding to the forward wetting data is marked to be an efficient forward wetting value;
analyzing the temperature influence of the inefficient forward wetting value, the efficient forward wetting value and the virtual plane rectangular coordinate system, when the relation between the inefficient forward wetting value and the efficient forward wetting value in the virtual plane rectangular coordinate system is that the inefficient forward wetting value is in front of the inefficient forward wetting value and the efficient forward wetting value is in back of the efficient forward wetting value, judging that the manufacturing time is high along with the rise of the humidity, generating a forward wet sound signal, when the relation between the inefficient forward wetting value and the efficient forward wetting value in the virtual plane rectangular coordinate system is that the inefficient forward wetting value is in back of the inefficient forward wetting value and the efficient forward wetting value is in front of the efficient forward wetting value, judging that the manufacturing time is reduced along with the rise of the humidity, marking the forward wetting data and the wet time difference value as a reverse influence relation, generating a reverse wet sound signal, and when the numerical values of the inefficient forward wetting value and the efficient forward wetting value are the same, judging that the manufacturing time is kept unchanged along with the change of the humidity, and generating an irrelevant wet sound signal, respectively calibrating the forward wet sound signal, the reverse wet sound signal and the irrelevant wet sound signal into identification values 1,2 and 3;
according to the different forward wetting data and the different wet time difference values, the different forward wetting data and the different wet time difference values are brought into a calculation formula: the wet time difference value 1-the wet time difference value 2 ═ is (forward wet data 1-forward wet data 2) × vi, wherein, the wet time difference value 1 and the wet time difference value 2 are respectively represented as two different forward wet data, the wet time difference value 1 and the wet time difference value 2 are respectively represented as two different wet time difference values, and two pairs of values correspond to each other, vl is represented as an influence factor of the forward wet data on the wet time difference value, namely a wet time factor, and l is 4,5,6, and vl respectively corresponds to three cases of a positive wet sound signal, a reverse wet sound signal and an irrelevant wet sound signal, when l is 4, v4 is a positive value, when l is 5, v5 is a negative value, when l is 6, v6 is zero, the forward wet data when the wet time difference value is changed and the wet time difference value is kept unchanged are selected and are calibrated as an initial forward wet value;
selecting the past shape data and the past time data according to the past shape data, extracting corresponding past shape data according to different past time data, and extracting the past shape data of a plurality of the past shape data at the same time point, thereby counting the occurrence times of various shapes, marking the shape with the most occurrence times as a matching shape, and sequentially marking the matching shapes of a plurality of different times as a matching shape array; extracting various shapes to perform occurrence frequency statistics, comparing the shape corresponding to each past sample data with the matching shape of each past sample data, counting the times different from the matching shape, calibrating the times as abnormal times, performing mean value calculation on the abnormal times of a plurality of past sample data, calculating an abnormal mean value, performing difference value calculation on the abnormal times and the abnormal mean value, calculating a plurality of abnormal difference values, sequencing the abnormal difference values from large to small to obtain abnormal difference value sequencing data, selecting the maximum value and the minimum value in the abnormal difference value sequencing data, performing mean value calculation on the maximum value and the minimum value in the abnormal difference value sequencing data, calculating an abnormal difference mean value, summing the abnormal difference mean value and the abnormal mean value, and calculating a safety number value;
transmitting the damage average value, the mean difference ratio, the temperature-time factor ui, the initial temperature-going value, the wet-time factor vi, the initial humidity-going value, the safety number value and the shape-matching number to a formulation and judgment unit;
the formulation and judgment unit performs sample judgment operation on the shape information, real shadow data, real temperature data, real humidity data, essential data, real time data, loss rate average value, mean difference ratio, temperature and time factor ui, initial temperature value, humidity factor vi, initial humidity value, safety number value and shape matching number together, and the specific operation process of the sample judgment operation is as follows:
the method comprises the following steps of carrying out shape processing on real image data, real-time data, shape information, a safety number value and a shape matching number group corresponding to previous sample data, and specifically comprises the following steps:
selecting a corresponding shape matching array according to the time point corresponding to the real-time data, marking the shape of the shape matching array as shape matching data, selecting real image data corresponding to the same real-time data, matching the real image data with the shape image to obtain a corresponding shape image, selecting a corresponding shape name according to the shape image, matching the shape name with the shape matching data, judging that the results are consistent when the matching is successful, generating a same signal, judging that the results are inconsistent when the matching is successful, and generating a no signal;
extracting a non-signal, counting the times of non-signal occurrence, calibrating the times to be a non-time value, comparing the non-time value with a safety time value, judging that the abnormal times are more and generating an alarm signal when the non-time value is greater than or equal to the safety time value, and judging that the abnormal times are normal and generating a prompt signal when the non-time value is less than the safety time value;
extracting an alarm signal and a prompt signal, giving identification numbers to the alarm signal and the prompt signal, giving a numerical value 7 and a numerical value 8 to the alarm signal and the prompt signal respectively, calibrating an image identification value uniformly to the alarm signal and the prompt signal, marking the image identification value as ra, and marking a as 7 and 8;
selecting the substantial data corresponding to the real-time before the sample is started to be manufactured, calculating the difference value of the substantial data and the first substantial data in the set time after the sample is started to be manufactured, calculating the difference value of the substantial data and the real-time data corresponding to the first substantial data, calculating the real-time difference value, and calculating the speed of the substantial difference value and the real-time difference value: calculating the real-time difference value and the real data to calculate the real-time difference value, and calculating the difference value of the real difference value and the average difference value to calculate the difference value;
and substituting the image identification value, the actual temperature data, the actual humidity data, the actual speed value, the speed loss mean value, the ratio difference value, the temperature-time factor ui, the initial forward temperature value, the humidity-time factor vl and the initial forward humidity value into an evaluation calculation formula:
wherein, PIs divided intoExpressing the evaluation value of the sample preparation, expressing SW as real temperature data, CW as an initial forward temperature value, ui as a warm-time factor, SS as real wet data, CS as an initial forward wet value, vl as a wet-time factor, VS as an actual speed value, VJ as a damage mean value, e1 as a weight coefficient of the difference value between the actual speed value and the damage mean value to the score, g as an influence transformation adjustment factor of the evaluation value of the sample preparation, ZB as a proportion difference value, e2 as a weight coefficient of the proportion difference value, ra as an image identification value, and e3 as a weight coefficient of the image identification value, wherein the numerical values in all the calculation formulas are calculated by quantization processing and only the numerical values are selected for calculation, and the numerical values in the evaluation calculation formulas except the evaluation value of the sample preparation are known numerical values or preset values;
setting a safety preset value of the sample preparation evaluation score, comparing the safety preset value with the sample preparation evaluation score, judging that a relevant value needs to be adjusted when the safety preset value of the sample preparation evaluation score is smaller than or equal to the sample preparation evaluation score, generating an adjusting signal, setting a qualified preset score of a prepared sample according to the adjusting signal, and bringing the qualified preset score into a calculation formula again, so that a real-time value is reversely deduced, a required standard value is calculated, a corresponding value is generated according to the change of the standard value, and the generated value is calibrated to be the adjusting value;
respectively transmitting the adjusting signal and the adjusting value to an adjusting unit and a sample display and extraction unit;
the adjusting unit adjusts the numerical value according to the received adjusting signal and the adjusting numerical value, the sample display and extraction unit is used for receiving and displaying the adjusting signal and the adjusting numerical value, reminding technicians to supervise adjustment of the adjusting unit and correct data adjustment in time, and the sample display and extraction unit is specifically a tablet computer.
The invention is operated, the real-time sample preparation data is collected through the collection unit, the real-time collected sample preparation data is marked as real preparation information, the real preparation information comprises real shadow data, real temperature data, real humidity data, substantial data and real time data, the real shadow data is transmitted to the mutual matching unit, the cloud service unit stores past preparation information and shape information related to the sample preparation recorded in the past, the past preparation information comprises past sample data, time data, past quality data, past shape data, past graph data, past temperature data and past humidity data, the mutual matching unit obtains the past sample data, the time data, the past shape data, the past graph data, the past temperature data and the past humidity data from the cloud service unit, and the past sample data, the time data, the past quality data, the past shape data, the past graph data, the past temperature data and the past humidity data are mutually matched with the real shadow data, obtaining previous product data, previous sample data, previous time data, previous quality data, previous shape data, previous temperature data, previous humidity data, previous formation data and previous loss data which correspond to previous image data, transmitting the previous formation data and the previous loss data to a manufacturing and distributing unit together, carrying out analysis management operation on related data obtained by mutual matching operation by the manufacturing and distributing unit to obtain a speed loss mean value, an average difference ratio, a temperature time factor ui, an initial previous temperature value, a humidity time factor vi, an initial previous humidity value, a safety number value and a shape matching number group, transmitting the related data to a formulated judging unit, carrying out sample judging operation on the related data processed by the manufacturing and distributing unit by the formulated judging unit to obtain an adjusting signal and an adjusting number value, and transmitting the adjusting signal and the adjusting number value to an adjusting unit and a sample display and extraction unit respectively; the adjusting unit adjusts the value according to the received adjusting signal and the adjusting value, the sample display and extraction unit receives and displays the adjusting signal and the adjusting value, and reminds technicians to supervise adjustment of the adjusting unit and correct data adjustment in time.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (9)
1. The intelligent sample preparation system for the coal sample is characterized by comprising a preparation and collection unit, a mutual matching unit, a cloud service unit, a preparation and branch management unit, a preparation and judgment unit, an adjusting unit and a sample display and extraction unit;
the system set unit is used for collecting real-time sample preparation data, marking the real-time collected sample preparation data as real system information and transmitting the real system information to the mutual matching unit;
the cloud service unit is internally stored with past system information and shape information related to past recorded sample manufacturing, and the mutual matching unit acquires past product data, past sample data, time data, past quality data, past shape data, past image data, past temperature data and past humidity data from the cloud service unit and mutually matches the past product data, the past sample data, the time data, the past quality data, the past shape data, the past image data, the past temperature data, the past humidity data and the real image data;
the system management unit is used for analyzing and managing the previous product data, previous sample data, previous time data, previous quality data, previous shape data, previous temperature data, previous humidity data, previous formation data and previous loss data together to obtain a damage average value, an average difference ratio, a temperature-time factor ui, an initial previous temperature value, a humidity-time factor vi, an initial previous humidity value, a safety degree value and a match array;
the formulating and judging unit performs sample judging operation on the shape information, real shadow data, real temperature data, real humidity data, substantial data, real-time data, loss rate average value, mean difference ratio, temperature-time factor ui, initial temperature-going value, humidity-time factor vi, initial humidity-going value, safety number value and shape matching number together, and transmits the obtained regulating signal and regulating value to the regulating unit and the sample display and extraction unit respectively;
the adjusting unit adjusts the value according to the received adjusting signal and the adjusting value, and the sample display and extraction unit is used for receiving and displaying the adjusting signal and the adjusting value.
2. The intelligent coal sample preparation system according to claim 1, wherein the specific operation process of the mutual matching operation is as follows:
selecting destination image data and real shadow data, and matching the destination image data with the real shadow data to obtain a matched signal and a matched error signal;
extracting a matching signal and a matching error signal, identifying the matching signal and the matching error signal, judging that the data acquired in real time is abnormal when the matching error signal is identified, generating a re-acquired signal, transmitting the re-acquired signal to an integration making unit, carrying out data acquisition by the integration making unit according to the re-acquired signal, judging that the data are matched when the matching signal is identified, extracting forward map data corresponding to real image data, and calibrating the corresponding forward map data into selected forward map data;
and extracting corresponding historical data, current time data, historical quality data, historical shape data, previous temperature data, previous humidity data, previous formation data and previous loss data according to the selected historical data.
3. The intelligent coal sample preparation system according to claim 2, wherein the specific operation process of the analysis management operation is as follows:
selecting a plurality of corresponding past sample data according to the past sample data, extracting corresponding past time data and past quality data according to the plurality of past sample data, respectively calibrating the past quality data of different time points of a manufactured sample, and performing difference calculation on the past quality data of two different time points so as to calculate a past quality difference value;
performing quality classification processing according to the previous quality difference value, the previous quality data and the current time data to obtain a loss average value and a mean-difference ratio;
selecting a plurality of corresponding previous temperature data according to the previous product data, extracting the time for making a sample from the previous product data according to the corresponding previous temperature data, calibrating the time point for starting making and the time point for finishing making respectively, calculating the difference between the time point for starting making and the time point for finishing making, calculating the temperature-time difference, selecting different previous temperature data and corresponding temperature-time difference values for variable analysis, and obtaining a forward temperature response signal, a reverse temperature response signal, an irrelevant temperature response signal, a temperature-time factor ui and an initial previous temperature value;
selecting a plurality of corresponding forward wetting data according to the forward wetting data, extracting the time for making a sample from the forward wetting data according to the forward wetting data, calibrating the time point for starting making and the time point for finishing making respectively, calculating the difference between the time point for starting making and the time point for finishing making, calculating the wet time difference, selecting different forward wetting data and corresponding wet time difference values for variable analysis, and obtaining a forward wet sound signal, a reverse wet sound signal, an irrelevant wet sound signal, a wet time factor vl and an initial forward wetting value;
and selecting the past shape data and the time data according to the past sample data, and carrying out shape time processing on the past shape data and the time data to obtain a shape matching array and a safety number value.
4. The intelligent coal sample preparation system according to claim 3, wherein the specific process of quality classification processing according to the forward quality difference value, the forward quality data and the forward time data comprises:
and performing difference calculation on the previous quality data at two different time points corresponding to the difference calculation, thereby calculating a quality time difference value, and bringing the quality time difference value and the previous quality difference value into a proportion calculation formula: the speed loss value = a previous quality difference value/a previous quality time difference value, the speed loss value is calculated, the speed loss values corresponding to a plurality of previous sample data are summed, and the summed value is divided by the number of the plurality of previous sample data, so that a speed loss average value is obtained;
the method comprises the steps of summing a plurality of past quality difference values, dividing the numerical value obtained after summing calculation by the times of the plurality of past quality difference values to calculate a past quality average difference value, summing the past quality data corresponding to the plurality of past quality difference values, dividing the past quality data obtained after summing calculation by the number of the plurality of past quality data to calculate a past quality average value, carrying out proportion calculation on the past quality average value and the past quality average difference value, and calculating an average difference ratio.
5. The intelligent coal sample preparation system according to claim 4, wherein the specific process of performing variable analysis according to the selected different forward temperature data and the corresponding temperature difference value comprises:
the previous temperature data is planned to be an X-axis numerical value and the temperature time difference value is planned to be a Y-axis numerical value, virtual plane rectangular coordinate system drawing is carried out, the value with the highest Y-axis numerical value is selected, the previous temperature data corresponding to the previous temperature data is marked to be an inefficient previous temperature value, the value with the lowest Y-axis numerical value is selected, and the previous temperature data corresponding to the previous temperature data is marked to be an efficient previous temperature value;
analyzing the temperature influence of the inefficient forward temperature value, the efficient forward temperature value and the virtual plane rectangular coordinate system, when the relation between the inefficient forward temperature value and the efficient forward temperature value in the virtual plane rectangular coordinate system is that the inefficient forward temperature value is in front of the efficient forward temperature value and the efficient forward temperature value is in back of the inefficient forward temperature value, judging that the manufacturing time is increased along with the increase of the temperature, generating a forward temperature response signal, when the relation between the inefficient forward temperature value and the efficient forward temperature value in the virtual plane rectangular coordinate system is that the inefficient forward temperature value is in back of the inefficient forward temperature value and the efficient forward temperature value is in front of the efficient forward temperature value, judging that the manufacturing time is reduced along with the increase of the temperature, marking the forward temperature data and the temperature difference value as a reverse influence relation, generating a reverse temperature response signal, and when the numerical values of the inefficient forward temperature value and the efficient forward temperature value are the same, judging that the manufacturing time is kept unchanged along with the change of the temperature, and generating an irrelevant temperature response signal, respectively calibrating the forward temperature response signal, the reverse temperature response signal and the irrelevant temperature response signal into identification values 1,2 and 3;
according to different past temperature data and different temperature and time difference values, different past temperature data and different temperature and time difference values are brought into a calculation formula: the temperature time difference value 1-the temperature time difference value 2= (past temperature data 1-past temperature data 2) × ui, wherein, the temperature time difference value 1 and the temperature time difference value 2 are respectively represented as two different past temperature data, the temperature time difference value 1 and the temperature time difference value 2 are respectively represented as two different temperature time difference values, and are corresponding to each other, ui is represented as an influence factor of the past temperature data on the temperature time difference value, namely, the temperature time factor, and the past temperature data when the temperature changes and the temperature time difference value is kept unchanged are selected and calibrated as the initial past temperature value.
6. The intelligent coal sample preparation system according to claim 5, wherein the specific process of shape time processing of the past shape data and the past time data is as follows:
extracting corresponding shape data according to different time data, and extracting the shape data of a plurality of shape data at the same time point, thereby counting the occurrence times of various shapes, marking the shape with the most occurrence times as a matching shape, and sequentially marking the matching shapes of a plurality of different times as a shape array;
counting the occurrence times according to various shapes, comparing the shape corresponding to each past sample data with the matching shape of each past sample data, counting the times different from the matching shape, calibrating the times to be abnormal times, carrying out mean value calculation on the abnormal times of a plurality of past sample data, calculating an abnormal mean value, carrying out difference value calculation on the abnormal times and the abnormal mean value, and calculating a plurality of abnormal difference values;
sorting the plurality of abnormal difference values from large to small to obtain abnormal difference value sorting data, selecting the maximum value and the minimum value in the abnormal difference value sorting data, carrying out mean value calculation on the maximum value and the minimum value in the abnormal difference value sorting data to calculate an abnormal difference mean value, carrying out summation calculation on the abnormal difference mean value and the abnormal mean value, and calculating a safety number value.
7. The intelligent coal sample preparation system according to claim 6, wherein the concrete operation process of the sample judgment operation is as follows:
carrying out shape processing on real image data, real-time data, shape information, a safety order value and a shape matching number group corresponding to the previous sample data to obtain an image identification value ra, wherein a =7, 8;
selecting the substantial data corresponding to the real-time before the sample is started to be manufactured, calculating the difference value of the substantial data and the first substantial data in the set time after the sample is started to be manufactured, calculating the difference value of the substantial data and the real-time data corresponding to the first substantial data, calculating the real-time difference value, and calculating the speed of the substantial difference value and the real-time difference value: the real speed value = real difference value/real-time difference value, the real difference value and the real data are subjected to ratio calculation, a real-difference ratio value is calculated, the real-difference ratio value and an average-difference ratio value are subjected to difference calculation, and a ratio difference value is calculated;
substituting the image identification value, the actual temperature data, the actual humidity data, the actual speed value, the speed loss mean value, the ratio difference value, the temperature-time factor ui, the initial forward temperature value, the humidity-time factor vl and the initial forward humidity value into a evaluation calculation formula to calculate a sample preparation evaluation score;
setting a safety preset value of the sample preparation evaluation score, comparing the safety preset value with the sample preparation evaluation score, judging that a relevant value needs to be adjusted when the safety preset value of the sample preparation evaluation score is smaller than or equal to the sample preparation evaluation score, generating an adjusting signal, setting a qualification preset score of the sample preparation according to the adjusting signal, and bringing the qualification preset score into a calculation formula again, so that a real-time value is reversely deduced, a required standard value is calculated, a corresponding value is generated according to the change of the standard value, and the generated value is calibrated to be the adjusting value.
8. The intelligent coal sample preparation system according to claim 7, wherein the shape processing of the real image data, the real-time data, the shape information, the safety order value and the shape matching group corresponding to the previous sample data is specifically performed by:
selecting a corresponding shape matching array according to the time point corresponding to the real-time data, marking the shape of the shape matching array as shape matching data, selecting real image data corresponding to the same real-time data, matching the real image data with the shape image to obtain a corresponding shape image, selecting a corresponding shape name according to the shape image, matching the shape name with the shape matching data, judging that the results are consistent when the matching is successful, generating a same signal, judging that the results are inconsistent when the matching is failed, and generating a no signal;
extracting a non-signal, counting the times of non-signal occurrence, calibrating the times to be a non-time value, comparing the non-time value with a safety time value, judging that the abnormal times are more and generating an alarm signal when the non-time value is greater than or equal to the safety time value, and judging that the abnormal times are normal and generating a prompt signal when the non-time value is less than the safety time value;
extracting an alarm signal and a prompt signal, giving identification numbers to the alarm signal and the prompt signal, giving a numerical value 7 and a numerical value 8 to the alarm signal and the prompt signal respectively, calibrating an image identification value uniformly to the alarm signal and the prompt signal, marking the image identification value as ra, and marking a =7 and 8.
9. The intelligent coal sample preparation system according to claim 8, wherein the evaluation calculation formula is specifically:
wherein, the evaluation score is expressed as a sample preparation evaluation score, SW is expressed as actual temperature data, CW is expressed as an initial forward temperature value, ui is expressed as a temperature time factor, SS is expressed as actual humidity data, CS is expressed as an initial forward humidity value, vl is expressed as a humidity time factor, VS is expressed as an actual speed value, VJ is expressed as a damage speed mean value, e1 is expressed as a weight coefficient of a difference value between the actual speed value and the damage speed mean value to the score, g is expressed as an influence conversion adjustment factor of the sample preparation evaluation score, ZB is expressed as a proportion difference value, e2 is expressed as a weight coefficient of the proportion difference value, ra is expressed as an image recognition value, and e3 is expressed as a weight coefficient of the image recognition value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111145692.5A CN113887380B (en) | 2021-09-28 | 2021-09-28 | Intelligent sample preparation system for coal samples |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111145692.5A CN113887380B (en) | 2021-09-28 | 2021-09-28 | Intelligent sample preparation system for coal samples |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113887380A CN113887380A (en) | 2022-01-04 |
| CN113887380B true CN113887380B (en) | 2022-04-26 |
Family
ID=79007517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111145692.5A Active CN113887380B (en) | 2021-09-28 | 2021-09-28 | Intelligent sample preparation system for coal samples |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113887380B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115857441B (en) * | 2022-11-16 | 2023-07-21 | 淮北矿业股份有限公司煤炭运销分公司 | Coal type control information transmission system in coking coal washing and selecting process |
| CN116448174B (en) * | 2023-04-11 | 2023-10-31 | 深圳市森辉智能自控技术有限公司 | Online monitoring system for environment of clean production workshop |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105987834A (en) * | 2015-02-06 | 2016-10-05 | 湖南三德科技股份有限公司 | Integrated sampling method used for coal sample detection and integrated sampling system |
| WO2017148094A1 (en) * | 2016-02-29 | 2017-09-08 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for reconstructing ect image |
| CN109299507A (en) * | 2018-08-20 | 2019-02-01 | 浙江大学 | A kind of different degrees of Analysis on Fault Diagnosis method under the coal pulverizer multi-state based on dynamic modeling |
| CN111337447A (en) * | 2020-03-20 | 2020-06-26 | 中国矿业大学 | Coal and gangue bionic identification system and method |
| CN111745685A (en) * | 2019-03-29 | 2020-10-09 | 湖南三德科技股份有限公司 | Sample preparation robot collision detection method and system and sample preparation system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7293000B2 (en) * | 2002-02-22 | 2007-11-06 | Lee Shih-Jong J | Information integration method for decision regulation in hierarchic decision systems |
| US7981517B2 (en) * | 2007-08-28 | 2011-07-19 | Dow Global Technologies Inc. | Bituminous compositions and methods of making and using same |
| CN109685066B (en) * | 2018-12-24 | 2021-03-09 | 中国矿业大学(北京) | Mine target detection and identification method based on deep convolutional neural network |
| CN110082170A (en) * | 2019-04-09 | 2019-08-02 | 湖南三德科技股份有限公司 | A kind of band weighs and the automatic sample-making system of data analysis function |
-
2021
- 2021-09-28 CN CN202111145692.5A patent/CN113887380B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105987834A (en) * | 2015-02-06 | 2016-10-05 | 湖南三德科技股份有限公司 | Integrated sampling method used for coal sample detection and integrated sampling system |
| WO2017148094A1 (en) * | 2016-02-29 | 2017-09-08 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for reconstructing ect image |
| CN109299507A (en) * | 2018-08-20 | 2019-02-01 | 浙江大学 | A kind of different degrees of Analysis on Fault Diagnosis method under the coal pulverizer multi-state based on dynamic modeling |
| CN111745685A (en) * | 2019-03-29 | 2020-10-09 | 湖南三德科技股份有限公司 | Sample preparation robot collision detection method and system and sample preparation system |
| CN111337447A (en) * | 2020-03-20 | 2020-06-26 | 中国矿业大学 | Coal and gangue bionic identification system and method |
Non-Patent Citations (2)
| Title |
|---|
| Coal mine wastes recycling for coal recovery and eco-friendly bricks production;Yassine et al.;《Minerals Engineering》;20160907;全文 * |
| 基于机器视觉的选煤流程闸板群开度及控制***研究;姜瑾;《中国优秀硕士学位论文全文数据库(工程科技Ⅰ辑)》;20210115;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113887380A (en) | 2022-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113887380B (en) | Intelligent sample preparation system for coal samples | |
| EP3547057A1 (en) | Abnormality detection system, support device, and abnormality detection method | |
| CN113407651B (en) | Progress information feedback and deviation real-time display method | |
| CN110782324B (en) | Electronic commerce commodity information management method and system based on cloud platform | |
| CN113344745A (en) | Engineering project intelligent construction site data acquisition and analysis integrated cloud platform based on remote video monitoring and cloud computing | |
| CN111652167A (en) | Intelligent evaluation method and system for chromosome karyotype image | |
| CN117394337A (en) | Power grid load early warning method and system thereof | |
| CN115269958A (en) | Internet reliability data information acquisition and analysis system | |
| CN113535050B (en) | Multi-interface display method, system and equipment based on interface linkage | |
| CN114322796A (en) | System and method for intelligently detecting coating film thickness uniformity of optical coating machine | |
| CN116522096B (en) | Three-dimensional digital twin content intelligent manufacturing method based on motion capture | |
| CN117592656A (en) | Carbon footprint monitoring method and system based on carbon data accounting | |
| CN112241512A (en) | Method and system for improving audit precision | |
| CN114691661B (en) | Assimilation-based cloud air guide and temperature and humidity profile pretreatment analysis method and system | |
| CN116342177A (en) | BIM-based whole-process cost consultation service management system | |
| CN115713720A (en) | Intelligent analysis method based on video image | |
| CN115063207A (en) | Building material purchasing intelligent price comparison analysis and processing system based on cloud computing | |
| CN113986911B (en) | Information acquisition method and system for monitoring racing field operation | |
| CN110599622A (en) | Parameter characterization method applied to airplane flight state | |
| CN116958053B (en) | Yolov 4-tiny-based bamboo stick counting method | |
| CN115409944B (en) | Three-dimensional scene rendering and data correction system based on low-code digital twin | |
| CN116880365B (en) | Method, system and readable storage medium for monitoring equipment production process | |
| Duan et al. | Selection of dimensionless methods in the back-to-back brand valuation | |
| CN116448174B (en) | Online monitoring system for environment of clean production workshop | |
| CN118112595A (en) | Laser radar data processing algorithm and monitoring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |