CN117314244A - Process flow data supervision system and method based on data analysis - Google Patents

Process flow data supervision system and method based on data analysis Download PDF

Info

Publication number
CN117314244A
CN117314244A CN202311285112.1A CN202311285112A CN117314244A CN 117314244 A CN117314244 A CN 117314244A CN 202311285112 A CN202311285112 A CN 202311285112A CN 117314244 A CN117314244 A CN 117314244A
Authority
CN
China
Prior art keywords
data
real
time
abnormal
similarity
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.)
Granted
Application number
CN202311285112.1A
Other languages
Chinese (zh)
Other versions
CN117314244B (en
Inventor
韩雷
冯迪
许江凯
孔晓峰
张朋伟
张广坡
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Cecep Shijiazhuang Environmental Protection Energy Co ltd
Original Assignee
Cecep Shijiazhuang Environmental Protection Energy Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Cecep Shijiazhuang Environmental Protection Energy Co ltd filed Critical Cecep Shijiazhuang Environmental Protection Energy Co ltd
Priority to CN202311285112.1A priority Critical patent/CN117314244B/en
Publication of CN117314244A publication Critical patent/CN117314244A/en
Application granted granted Critical
Publication of CN117314244B publication Critical patent/CN117314244B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0639Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395Quality analysis or management
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0633Workflow analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0639Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393Score-carding, benchmarking or key performance indicator [KPI] analysis

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Factory Administration (AREA)

Abstract

The invention discloses a process flow data supervision system and method based on data analysis, and belongs to the technical field of data supervision. The system of the invention comprises: the system comprises a data acquisition module, a data preprocessing module, a data classification module, an evaluation and adjustment module and a real-time monitoring module; the data acquisition module is used for acquiring historical data and real-time data and acquiring process parameters and product quality data; the data preprocessing module is used for preprocessing the acquired data; the data classification module is used for classifying the preprocessed historical data into normal data and abnormal data according to the time stamp of the maintenance record; the evaluation and adjustment module is used for evaluating the product quality of the normal data and the abnormal data and determining target data and adjustment data; the real-time monitoring module analyzes the real-time data and judges the approaching degree of the real-time data to the target data, the adjusting data and the abnormal data, so that the data monitoring is performed.

Description

Process flow data supervision system and method based on data analysis
Technical Field
The invention relates to the technical field of data supervision, in particular to a process flow data supervision system and method based on data analysis.
Background
The concentrated solution to boiler pulping system is one of the key process flows of waste residue treatment links applied to the garbage incineration process, and the main purpose is to reduce the volume and weight of waste residues and facilitate the subsequent treatment and disposal by concentrating organic matters and moisture in the waste residues; key parameters of the system from the concentrated solution to the boiler pulping comprise the temperature, the pressure, the flow and the like of a slurry inlet and outlet; stability and accurate control of these parameters are critical to stable operation of the system and product quality; the existence of abnormal data may mean equipment failure, process abnormality or raw material change and other problems, which may cause production interruption, product quality degradation and even equipment damage; therefore, it is important to monitor the process flow of concentrate to the boiler pulping system.
Currently, there are methods for monitoring the process flow of concentrate to a boiler pulping system, but these methods have the following problems: the traditional supervision method is generally based on offline data analysis, and cannot provide real-time monitoring and response capability, so that measures cannot be taken in time to intervene and adjust when problems occur; the prior art is often limited to providing problem detection and warning functions, but the optimization adjustment schemes for the system are few, and targeted optimization suggestions cannot be provided through data analysis so as to improve the system efficiency and stability.
Disclosure of Invention
The invention aims to provide a process flow data supervision system and method based on data analysis, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme:
a technological process data supervision method based on data analysis comprises the following steps:
s100, collecting historical data, preprocessing the historical data, and classifying the preprocessed historical data into normal data and abnormal data through maintenance records of equipment; the preprocessing comprises data cleaning and standardization;
s200, obtaining a scoring threshold value interval Q according to a set product quality standard; evaluating the product quality of the normal data to obtain a scoring set A, and evaluating the product quality of the abnormal data to obtain a scoring set B;
s300, comparing the scores in the score set A with a score threshold interval Q, and selecting normal data belonging to the score threshold interval Q as target data; taking normal data which does not belong to the scoring threshold value interval Q as adjusting data, correspondingly adjusting, and associating the adjusting process with the corresponding adjusting data; correlating the maintenance process corresponding to the abnormal data in the grading set B with the abnormal data;
s400, acquiring real-time data, respectively calculating the similarity between the process parameters of the real-time data and the target data, the similarity between the process parameters of the real-time data and the abnormal data and the similarity between the process parameters of the real-time data and the abnormal data, selecting the final classification result with the maximum similarity, and correspondingly adjusting the final classification result according to the classification result.
Further, step S100 includes:
s101, collecting historical data, and preprocessing the historical data; the historical data comprises process parameters and product quality data; the process parameters refer to temperature, pressure and flow data in the pipeline in the process of the percolate treatment system and the boiler pulping system; the product quality data comprises data indexes of components, water content and suspended matter content of the product;
s102, dividing the preprocessed historical data into two types of normal data and abnormal data through a time stamp of a maintenance record; if the preprocessed historical data does not contain the time stamp of the maintenance record, marking the historical data as normal data; if the preprocessed historical data contains the time stamp of the maintenance record, the historical data is marked as abnormal data.
Because the existence of the maintenance record indicates that equipment faults or anomalies exist in the process flow from the concentrated solution to the boiler pulping system at the stage, the quality of pulping products can be influenced, and therefore, the historical data are divided into normal data and abnormal data through the timestamp of the maintenance record, the judgment of the subsequent real-time data is facilitated, corresponding processing is carried out in advance, and production interruption or quality problems are avoided.
Further, step S200 includes:
s201, obtaining a component index x, a water content index y and a suspended matter content index z according to a set product quality standard, and obtaining quality data of a qualified product to obtain the component index x 0 Index y of moisture content 0 And a suspended matter content index z 0 Calculating the scoring threshold interval Q of the product, and Q= [ S_min, S_max]Wherein S_min is the minimum value of the scoring threshold interval of the product, and S_max is the maximum value of the scoring threshold interval of the product;
component index x 0 The score maximum value calculation formula of (2) is:
max_scorce_x 0 =(max_x 0 -min_x)/(max_x-min_x)
min_scorce_x 0 =(min_x 0 -min_x)/(max_x-min_x)
index y of moisture content 0 And a suspended matter content index z 0 The maximum value and the minimum value of the scores are also calculated according to the formula, and the three scores are combined to obtain a total score, namely:
S_max=w 1 *max_scorce_x 0 +w 2 *max_scorce_y 0 +w 3 *max_scorce_z 0
S_min=w 1 *min_scorce_x 0 +w 2 *min_scorce_y 0 +w 3 *min_scorce_z 0
wherein max_x, max_y and max_z are the maximum values of the set ingredient index x, the water content index y and the suspended matter content index z, respectively, and min_x, min_y and min_z are the minimum values of the set ingredient index x, the water content index y and the suspended matter content index z, respectively; w (w) 1 、w 2 And w 3 Is the weight coefficient of each index, which is larger than 0 and w 1 +w 2 +w 3 =1;
S202, obtaining product quality data in normal data to obtain a component index x, a water content index y and a suspended matter content index z; according to the set product quality standard, calculating the score of each product, and calculating the scoring formula of the component index x as follows:
scorce_x=(x-min_x)/(max_x-min_x)
the scores of the water content index y and the suspended matter content index z are calculated according to the above formula, and then the three scores are combined to obtain a total score, namely:
Scorce=w 1 *scorce_x+w 2 *scorce_y+w 3 *scorce_z
through the calculation, a scoring set A of the product quality of the normal data is obtained;
s203, acquiring product quality data in the abnormal data, and evaluating the normal data in the step S202 to obtain a grading set B.
Further, step S300 includes:
s301, comparing scores in the score set A with a score threshold interval Q, selecting normal data with scores belonging to the threshold interval Q, correlating product quality data in the data with corresponding process parameters, marking the product quality data as target data, and calculating an average value of the process parameters of the target data;
s302, acquiring normal data with scores not belonging to a threshold value interval Q, correlating product quality data in the data with corresponding process parameters, and marking the product quality data as adjustment data; correspondingly adjusting the process parameters of the adjustment data until the process parameters are equal to the average value of the process parameters of the target data, and associating the adjustment process with the corresponding adjustment data;
s303, acquiring abnormal data in the grading set B, and associating technological parameters of the abnormal data in the grading set B with corresponding maintenance processes.
Through the step S200 and the step S300, a scoring threshold interval is obtained according to a set product quality standard, and product quality scores of normal data and abnormal data are calculated respectively to obtain a scoring set; dividing normal data into target data and adjusting data through a grading threshold interval, wherein the target data represents that the set grading threshold interval is met, the technological parameters corresponding to the target data are met, the adjusting data represents that the set grading threshold interval is not met, the technological process corresponding to the adjusting data is not subjected to equipment failure, and the technological parameters need to be adjusted; and the technological parameters of the abnormal data are associated with the corresponding maintenance process, so that the abnormal condition can be found out quickly, and control measures can be taken timely, thereby improving the stability and efficiency of the production process.
Further, step S400 includes:
s401, acquiring real-time data, and respectively calculating the similarity between the process parameters of the real-time data and target data, adjusting data and abnormal data in a selected period, wherein the calculation formula is as follows:
S=∑(d i -d′ j ) 2 (i=1,...,n;j=1,...,m)
wherein d is i Representing the process parameters of the ith real-time data, and i is a positive integer from 1 to n, d' j Representing the j-th process parameter of the selected target data, or the j-th process parameter of the regulated data, or the j-th process parameter of the abnormal data, and j is a positive integer from 1 to m; the similarity of the temperature, pressure and flow data in the pipeline in the process of the process parameters is required to be calculated separately, and then the average value of the similarity of the temperature, the pressure and the flow data is taken as a final similarity result, namely, the calculation process of the similarity of the process parameters of the real-time data and the target data in the selected period is as follows: respectively calculating the similarity of temperature, pressure and flow data in the pipeline in the two technological processes, and then taking the average value of the temperature, the pressure and the flow data; the similarity of the real-time data and the process parameters of the adjusting data and the abnormal data in the selected period is calculated according to the process;
s402, comparing the process parameters of the real-time data with the similarity of the target data, the adjustment data and the abnormal data in the selected period;
if the similarity between the real-time data and the target data in the selected period is the maximum, marking the real-time target data, and continuing to monitor the data;
if the similarity between the real-time data and the adjusting data in the selected period is the largest, marking the real-time adjusting data, correlating the real-time adjusting data with the adjusting data in the historical data, finding out a corresponding adjusting process for adjusting, if the corresponding adjusting process does not exist, feeding back the adjusting process to an operator, and recording that the adjusting process of the operator is correlated with the real-time adjusting data;
if the similarity between the real-time data and the abnormal data in the selected period is the largest, the real-time abnormal data is marked, the real-time abnormal data is associated with the abnormal data in the historical data, the corresponding maintenance process is matched and output to an operator, if the corresponding maintenance process does not exist, the real-time abnormal data is fed back to the operator, and the maintenance process of the operator is recorded to be associated with the real-time abnormal data.
A process flow data supervisory system based on data analysis, the system comprising: the system comprises a data acquisition module, a data preprocessing module, a data classification module, an evaluation and adjustment module and a real-time monitoring module;
the data acquisition module is used for acquiring historical data and real-time data and acquiring process parameters and product quality data; the data preprocessing module is used for preprocessing the acquired data; the data classification module is used for classifying the preprocessed historical data into normal data and abnormal data according to the time stamp of the maintenance record;
the evaluation and adjustment module is used for evaluating the product quality of the normal data and the abnormal data, dividing the normal data into target data and adjustment data according to a threshold interval obtained by a set product quality standard, correspondingly adjusting the process parameters of the adjustment data until the average value of the process parameters of the target data is met, and associating the adjustment process with the corresponding adjustment data; associating the maintenance process corresponding to the abnormal data with the abnormal data;
the real-time monitoring module analyzes the real-time data, calculates the similarity between the real-time data and the target data, the similarity between the real-time data and the abnormal data, and determines a final classification result according to the similarity, so that corresponding adjustment is performed.
Further, the data acquisition module comprises a historical data acquisition unit and a real-time data acquisition unit; the historical data acquisition unit acquires process parameters and product quality data from the historical record; the real-time data acquisition unit acquires real-time data and acquires process parameters and product quality data in real time;
the data preprocessing module comprises a data cleaning unit and a data standardization unit; the data cleaning unit is used for cleaning data and removing abnormal values and noise; the data normalization unit performs normalization processing on the acquired data;
the data classification module comprises a normal data unit and an abnormal data unit; the normal data unit judges according to the existence of the maintenance record, and divides the historical data without the maintenance record into normal data; the exception data unit is used to receive historical data of the presence service record.
Further, the evaluation and adjustment module comprises a product quality evaluation unit, a target data screening unit, a regulation data screening unit and a correlation unit;
the product quality evaluation unit is used for calculating product quality evaluation scores of normal data and abnormal data in the historical data to obtain a scoring set A and a scoring set B;
the target data screening unit compares the threshold interval Q obtained according to the set product quality standard with scores in the score set A, and marks normal data with the score value belonging to the threshold interval Q as target data;
the adjusting data screening unit compares the threshold value interval Q obtained according to the set product quality standard with the scores in the score set A, and marks the normal data with the score value not belonging to the threshold value interval Q as adjusting data;
the association unit is used for correspondingly adjusting the process parameters of the adjustment data until the average value of the process parameters of the target data is met, and associating the adjustment process with the corresponding adjustment data; and associating the maintenance process corresponding to the abnormal data with the abnormal data.
Further, the real-time monitoring module comprises a similarity calculation unit, a classification result determination unit and a feedback unit;
the similarity calculation unit is used for calculating the similarity between the real-time data and the target data, the adjustment data and the abnormal data;
the classification result determining unit is used for classifying according to the calculation result of the similarity calculating unit, and marking the real-time target data if the similarity between the real-time data and the target data is highest; if the similarity between the real-time data and the adjustment data is the highest, marking the real-time data as the real-time adjustment data; if the similarity between the real-time data and the abnormal data is the highest, marking the real-time abnormal data as the real-time abnormal data;
the feedback unit is used for associating the real-time adjustment data with the adjustment data in the historical data according to the classification result of the classification result determining unit, finding out a corresponding adjustment process for adjustment, feeding back to an operator if the corresponding adjustment process does not exist, and recording that the adjustment process of the operator is associated with the real-time adjustment data; and (3) correlating the real-time abnormal data with the abnormal data in the historical data, finding out a corresponding maintenance process, outputting the corresponding maintenance process to an operator, feeding back the corresponding maintenance process to the operator, and recording that the maintenance process of the operator is correlated with the real-time abnormal data.
Compared with the prior art, the invention has the following beneficial effects: by combining the historical data and the equipment maintenance records, the abnormal data can be identified more accurately, so that potential equipment faults or abnormal conditions can be found in time, corresponding processing can be performed in advance, and production interruption or quality problems can be avoided; by evaluating the normal data as the target data and adjusting, the process parameters can be optimized to reach the expected average value, which is helpful for improving the product quality, the production efficiency and the stability; the abnormal data are associated with the maintenance records, so that the connection between equipment faults and the abnormal data can be established, the maintenance history of the equipment can be tracked, and more information is provided for fault diagnosis, maintenance planning and maintenance process improvement; the real-time data is compared with the normal data, the target data and the abnormal data in similarity, so that the process flow can be monitored in real time, and corresponding adjustment is carried out according to the classification result, thereby being beneficial to quickly finding out abnormal conditions and timely taking control measures, and further improving the stability and efficiency of the production process.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow diagram of a process flow data supervision method based on data analysis according to the present invention;
fig. 2 is a schematic diagram of a real-time monitoring flow of a process flow data supervision method based on data analysis according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, the present invention provides the following technical solutions:
a technological process data supervision method based on data analysis comprises the following steps:
s100, collecting historical data, preprocessing the historical data, and classifying the preprocessed historical data into normal data and abnormal data through maintenance records of equipment; the preprocessing comprises data cleaning and standardization;
s101, collecting historical data, and preprocessing the historical data; the historical data comprises process parameters and product quality data; the process parameters refer to temperature, pressure and flow data in the pipeline in the process of the percolate treatment system and the boiler pulping system; the product quality data comprises data indexes of components, water content and suspended matter content of the product;
s102, dividing the preprocessed historical data into two types of normal data and abnormal data through a time stamp of a maintenance record; if the preprocessed historical data does not contain the time stamp of the maintenance record, marking the historical data as normal data; if the preprocessed historical data contains the time stamp of the maintenance record, the historical data is marked as abnormal data.
S200, obtaining a scoring threshold value interval Q according to a set product quality standard; evaluating the product quality of the normal data to obtain a scoring set A, and evaluating the product quality of the abnormal data to obtain a scoring set B;
s201, obtaining a component index x, a water content index y and a suspended matter content index z according to a set product quality standard, and obtaining quality data of a qualified product to obtain the component index x 0 Index y of moisture content 0 And a suspended matter content index z 0 Calculating the scoring threshold interval Q of the product, and Q= [ S_min, S_max]Wherein S_min is the minimum value of the scoring threshold interval of the product, and S_max is the maximum value of the scoring threshold interval of the product;
component index x 0 The score maximum value calculation formula of (2) is:
max_scorce_x 0 =(max_x 0 -min_x)/(max_x-min_x)
min_scorce_x 0 =(min_x 0 -min_x)/(max_x-min_x)
index y of moisture content 0 And a suspended matter content index z 0 The maximum value and the minimum value of the scores are also calculated according to the formula, and the three scores are combined to obtain a total score, namely:
S_max=w 1 *max_scorce_x 0 +w 2 *max_scorce_y 0 +w 3 *max_scorce_z 0
S_min=w 1 *min_scorce_x 0 +w 2 *min_scorce_y 0 +w 3 *min_scorce_z 0
wherein max_x, max_y and max_z are the maximum values of the set ingredient index x, the water content index y and the suspended matter content index z, respectively, and min_x, min_y and min_z are the minimum values of the set ingredient index x, the water content index y and the suspended matter content index z, respectively; w (w) 1 、w 2 And w 3 Is the weight coefficient of each index, which is larger than 0 and w 1 +w 2 +w 3 =1;
S202, obtaining product quality data in normal data to obtain a component index x, a water content index y and a suspended matter content index z; according to the set product quality standard, calculating the score of each product, and calculating the scoring formula of the component index x as follows:
scorce_x=(x-min_x)/(max_x-min_x)
the scores of the water content index y and the suspended matter content index z are calculated according to the above formula, and then the three scores are combined to obtain a total score, namely:
Scorce=w 1 *scorce_x+w 2 *scorce_y+w 3 *scorce_z
through the calculation, a scoring set A of the product quality of the normal data is obtained;
s203, acquiring product quality data in the abnormal data, and evaluating the normal data in the step S202 to obtain a grading set B.
Assuming quality assessment of the product from the concentrate to the boiler pulping system, the set product quality criteria are as follows:
component index x: it is required to be between 10% and 20%, i.e., min_x=10%, max_x=20%;
the water content index y: between 5% and 15% is required, i.e. min_y=5%, max_y=15%;
suspension content index z: it is required to be between 0.5% and 1%, i.e. min_z=0.5%, max_z=1%;
according to the set product quality standard, a comprehensive scoring threshold value interval Q of the component index x, the water content index y and the suspended matter content index z can be obtained, wherein Q= [ S_min, S_max ] = [0.4,0.6];
assume that there is a set of normal data and a set of abnormal data, respectively as follows:
normal data:
product 1: x=12%, y=8%, z=0.5%;
product 2: x=15%, y=10%, z=0.8%;
product 3: x=18%, y=12%, z=0.9%;
abnormal data:
product 4: x=8%, y=16%, z=0.7%;
product 5: x=20%, y=6%, z=1.2%;
calculating the score of each product according to the set product quality standard, and assuming that the weight coefficient is w 1 =0.4,w 2 =0.3,w 3 =0.3:
Product 1:
scorce_x=(x-min_x)/(max_x-min_x)=0.2,
scorce_y=(y-min_y)/(max_y-min_y)=0.3,
scorce_z=(z-min_z)/(max_z-min_z)=0;
Scorce=w 1 *scorce_x+w 2 *scorce_y+w 3 *scorce_z=0.17;
product 2:
scorce_x=(x-min_x)/(max_x-min_x)=0.5,
scorce_y=(y-min_y)/(max_y-min_y)=0.5,
scorce_z=(z-min_z)/(max_z-min_z)=0.6;
Scorce=w 1 *scorce_x+w 2 *scorce_y+w 3 *scorce_z=0.53;
product 3:
scorce_x=(x-min_x)/(max_x-min_x)=0.8,
scorce_y=(y-min_y)/(max_y-min_y)=0.7,
scorce_z=(z-min_z)/(max_z-min_z)=0.8;
Scorce=w 1 *scorce_x+w 2 *scorce_y+w 3 *scorce_z=0.77;
product 4:
scorce_x=(x-min_x)/(max_x-min_x)=-0.2,
scorce_y=(y-min_y)/(max_y-min_y)=1.1,
scorce_z=(z-min_z)/(max_z-min_z)=0.4;
Scorce=w 1 *scorce_x+w 2 *scorce_y+w 3 *scorce_z=0.37;
product 5:
scorce_x=(x-min_x)/(max_x-min_x)=1,
scorce_y=(y-min_y)/(max_y-min_y)=0.1,
scorce_z=(z-min_z)/(max_z-min_z)=1.2;
Scorce=w 1 *scorce_x+w 2 *scorce_y+w 3 *scorce_z=0.79;
through the calculation, a product quality score set A, A= {0.17,0.53,0.77} of normal data and a product quality score set B, B= {0.37,0.79} of abnormal data are obtained.
S300, comparing the scores in the score set A with a score threshold interval Q, and selecting normal data belonging to the score threshold interval Q as target data; taking normal data which does not belong to the scoring threshold value interval Q as adjusting data, correspondingly adjusting, and associating the adjusting process with the corresponding adjusting data; correlating the maintenance process corresponding to the abnormal data in the grading set B with the abnormal data;
s301, comparing scores in the score set A with a score threshold interval Q, selecting normal data with scores belonging to the threshold interval Q, correlating product quality data in the data with corresponding process parameters, marking the product quality data as target data, and calculating an average value of the process parameters of the target data;
s302, acquiring normal data with scores not belonging to a threshold value interval Q, correlating product quality data in the data with corresponding process parameters, and marking the product quality data as adjustment data; correspondingly adjusting the process parameters of the adjustment data until the process parameters are equal to the average value of the process parameters of the target data, and associating the adjustment process with the corresponding adjustment data;
s303, acquiring abnormal data in the grading set B, and associating technological parameters of the abnormal data in the grading set B with corresponding maintenance processes.
Obtaining a product quality score set A, A= {0.17,0.53,0.77} of normal data and a product quality score set B, B= {0.37,0.79} of abnormal data through the quality evaluation calculation; and because the comprehensive scoring threshold value interval Q of the component index x, the water content index y and the suspended matter content index z can be obtained according to the set product quality standard, and Q= [ S_min, S_max ] = [0.4,0.6];
in the quality score set A, the quality score of the product 2 can be obtained to belong to a score threshold value interval Q, so that the process parameters of the product 2 and the quality data of the product 2 are associated, marked as target data, and the average value of the process parameters of the target data is calculated; the quality scores of the products 1 and 3 do not belong to the score threshold value interval Q, so that the process parameters of the products 1 and 3 are associated with the corresponding quality data and marked as adjustment data, the process parameters of the adjustment data are adjusted according to the average value of the process parameters of the target data, and the adjustment process is associated with the corresponding adjustment data;
in the quality score set B, it can be seen that there is no significant difference from the final score of the conditioning data in score set a, but there is a difference in calculating the individual scores of the ingredient index x, the moisture content index y, and the suspended matter content index z, and the score set of anomaly data is calculated not to directly distinguish the anomaly data of the real-time data from the final score, but to correlate the process parameters of the anomaly data with the corresponding repair process.
S400, acquiring real-time data, respectively calculating the similarity between the process parameters of the real-time data and the target data, the similarity between the process parameters of the real-time data and the abnormal data and the similarity between the process parameters of the real-time data and the abnormal data, selecting the final classification result with the maximum similarity, and correspondingly adjusting the final classification result according to the classification result.
S401, acquiring real-time data, and respectively calculating the similarity between the process parameters of the real-time data and target data, adjusting data and abnormal data in a selected period, wherein the calculation formula is as follows:
S=∑(d i -d′ j ) 2 (i=1,...,n;j=1,...,m)
wherein d is i Representing the process parameters of the ith real-time data, and i is a positive integer from 1 to n, d' j Representing selected representation of target data within a selected periodj process parameters, or the j process parameters of the regulating data, or the j process parameters of the abnormal data, and j is a positive integer from 1 to m; the similarity of the temperature, pressure and flow data in the pipeline in the process of the process parameters is required to be calculated separately, and then the average value of the similarity of the temperature, the pressure and the flow data is taken as a final similarity result, namely, the calculation process of the similarity of the process parameters of the real-time data and the target data in the selected period is as follows: respectively calculating the similarity of temperature, pressure and flow data in the pipeline in the two technological processes, and then taking the average value of the temperature, the pressure and the flow data; the similarity of the real-time data and the process parameters of the adjusting data and the abnormal data in the selected period is calculated according to the process;
s402, comparing the process parameters of the real-time data with the similarity of the target data, the adjustment data and the abnormal data in the selected period;
if the similarity between the real-time data and the target data in the selected period is the maximum, marking the real-time target data, and continuing to monitor the data;
if the similarity between the real-time data and the adjusting data in the selected period is the largest, marking the real-time adjusting data, correlating the real-time adjusting data with the adjusting data in the historical data, finding out a corresponding adjusting process for adjusting, if the corresponding adjusting process does not exist, feeding back the adjusting process to an operator, and recording that the adjusting process of the operator is correlated with the real-time adjusting data;
if the similarity between the real-time data and the abnormal data in the selected period is the largest, the real-time abnormal data is marked, the real-time abnormal data is associated with the abnormal data in the historical data, the corresponding maintenance process is matched and output to an operator, if the corresponding maintenance process does not exist, the real-time abnormal data is fed back to the operator, and the maintenance process of the operator is recorded to be associated with the real-time abnormal data.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (9)

1. The technological process data supervision method based on data analysis is characterized by comprising the following steps of: the method comprises the following steps:
s100, collecting historical data, preprocessing the historical data, and classifying the preprocessed historical data into normal data and abnormal data through maintenance records of equipment; the preprocessing comprises data cleaning and standardization;
s200, obtaining a scoring threshold value interval Q according to a set product quality standard; evaluating the product quality of the normal data to obtain a scoring set A, and evaluating the product quality of the abnormal data to obtain a scoring set B;
s300, comparing the scores in the score set A with a score threshold interval Q, and selecting normal data belonging to the score threshold interval Q as target data; taking normal data which does not belong to the scoring threshold value interval Q as adjusting data, correspondingly adjusting, and associating the adjusting process with the corresponding adjusting data; correlating the maintenance process corresponding to the abnormal data in the grading set B with the abnormal data;
s400, acquiring real-time data, respectively calculating the similarity between the process parameters of the real-time data and the target data, the similarity between the process parameters of the real-time data and the abnormal data and the similarity between the process parameters of the real-time data and the abnormal data, selecting the final classification result with the maximum similarity, and correspondingly adjusting the final classification result according to the classification result.
2. The process flow data supervision method based on data analysis according to claim 1, wherein: the step S100 includes:
s101, collecting historical data, and preprocessing the historical data; the historical data comprises process parameters and product quality data; the process parameters refer to temperature, pressure and flow data in the pipeline in the process of the percolate treatment system and the boiler pulping system; the product quality data comprises data indexes of components, water content and suspended matter content of the product;
s102, dividing the preprocessed historical data into two types of normal data and abnormal data through a time stamp of a maintenance record; if the preprocessed historical data does not contain the time stamp of the maintenance record, marking the historical data as normal data; if the preprocessed historical data contains the time stamp of the maintenance record, the historical data is marked as abnormal data.
3. The process flow data supervision method based on data analysis according to claim 2, wherein: the step S200 includes:
s201, obtaining a component index x, a water content index y and a suspended matter content index z according to a set product quality standard, and obtaining quality data of a qualified product to obtain the component index x 0 Index y of moisture content 0 And a suspended matter content index z 0 Calculating the scoring threshold interval Q of the product, and Q= [ S_min, S_max]Wherein S_min is the minimum value of the scoring threshold interval of the product, and S_max is the maximum value of the scoring threshold interval of the product;
component index x 0 The score maximum value calculation formula of (2) is:
max_scorce_x 0 =(max_x 0 -min_x)/(max_x-min_x)
min_scorce_x 0 =(min_x 0 -min_x)/(max_x-min_x)
index y of moisture content 0 And a suspended matter content index z 0 The maximum value and the minimum value of the scores are also calculated according to the formula, and the three scores are combined to obtain a total score, namely:
S_max=w 1 *max_scorce_x 0 +w 2 *max_scorce_y 0 +w 3 *max_scorce_z 0
S_min=w 1 *min_scorce_x 0 +w 2 *min_scorce_y 0 +w 3 *min_scorce_z 0
wherein max_x, max_y and max_z are the maximum values of the set ingredient index x, the water content index y and the suspended matter content index z, respectively, and min_x, min_y and min_z are the minimum values of the set ingredient index x, the water content index y and the suspended matter content index z, respectively; w (w) 1 、w 2 And w 3 Is the weight coefficient of each index, which is larger than 0 and w 1 +w 2 +w 3 =1;
S202, obtaining product quality data in normal data to obtain a component index x, a water content index y and a suspended matter content index z; according to the set product quality standard, calculating the score of each product, and calculating the scoring formula of the component index x as follows:
scorce_x=(x-min_x)/(max_x-min_x)
the scores of the water content index y and the suspended matter content index z are calculated according to the above formula, and then the three scores are combined to obtain a total score, namely:
Scorce=w 1 *scorce_x+w 2 *scorce_y+w 3 *scorce_z
through the calculation, a scoring set A of the product quality of the normal data is obtained;
s203, acquiring product quality data in the abnormal data, and evaluating the normal data in the step S202 to obtain a grading set B.
4. A process flow data supervision method based on data analysis according to claim 3, wherein: the step S300 includes:
s301, comparing scores in the score set A with a score threshold interval Q, selecting normal data with scores belonging to the threshold interval Q, correlating product quality data in the data with corresponding process parameters, marking the product quality data as target data, and calculating an average value of the process parameters of the target data;
s302, acquiring normal data with scores not belonging to a threshold value interval Q, correlating product quality data in the data with corresponding process parameters, and marking the product quality data as adjustment data; correspondingly adjusting the process parameters of the adjustment data until the process parameters are equal to the average value of the process parameters of the target data, and associating the adjustment process with the corresponding adjustment data;
s303, acquiring abnormal data in the grading set B, and associating technological parameters of the abnormal data in the grading set B with corresponding maintenance processes.
5. The method for monitoring and controlling process flow data based on data analysis according to claim 4, wherein: the step S400 includes:
s401, acquiring real-time data, and respectively calculating the similarity between the process parameters of the real-time data and target data, adjusting data and abnormal data in a selected period, wherein the calculation formula is as follows:
S=∑(d i -d′ j ) 2 (i=1,...,n;j=1,...,m)
wherein d is i Representing the process parameters of the ith real-time data, and i is a positive integer from 1 to n, d' j A j-th process parameter of the target data in the selected period, or a j-th process parameter of the regulating data, or a j-th process parameter of the abnormal data, and j is a positive integer from 1 to m; the similarity of the temperature, pressure and flow data in the pipeline in the process of the process parameters is required to be calculated separately, and then the average value of the similarity of the temperature, the pressure and the flow data is taken as a final similarity result, namely, the calculation process of the similarity of the process parameters of the real-time data and the target data in the selected period is as follows: respectively calculating the similarity of the temperature, the pressure and the flow data in the pipeline in the two technological processes, and then taking three partsAverage value of the above; the similarity of the real-time data and the process parameters of the adjusting data and the abnormal data in the selected period is calculated according to the process;
s402, comparing the process parameters of the real-time data with the similarity of the target data, the adjustment data and the abnormal data in the selected period;
if the similarity between the real-time data and the target data in the selected period is the maximum, marking the real-time target data, and continuing to monitor the data;
if the similarity between the real-time data and the adjusting data in the selected period is the largest, marking the real-time adjusting data, correlating the real-time adjusting data with the adjusting data in the historical data, finding out a corresponding adjusting process for adjusting, if the corresponding adjusting process does not exist, feeding back the adjusting process to an operator, and recording that the adjusting process of the operator is correlated with the real-time adjusting data;
if the similarity between the real-time data and the abnormal data in the selected period is the largest, the real-time abnormal data is marked, the real-time abnormal data is associated with the abnormal data in the historical data, the corresponding maintenance process is matched and output to an operator, if the corresponding maintenance process does not exist, the real-time abnormal data is fed back to the operator, and the maintenance process of the operator is recorded to be associated with the real-time abnormal data.
6. The utility model provides a technological process data supervisory systems based on data analysis which characterized in that: the system comprises: the system comprises a data acquisition module, a data preprocessing module, a data classification module, an evaluation and adjustment module and a real-time monitoring module;
the data acquisition module is used for acquiring historical data and real-time data and acquiring process parameters and product quality data; the data preprocessing module is used for preprocessing the acquired data; the data classification module is used for classifying the preprocessed historical data into normal data and abnormal data according to the time stamp of the maintenance record;
the evaluation and adjustment module is used for evaluating the product quality of the normal data and the abnormal data, dividing the normal data into target data and adjustment data according to a threshold interval obtained by a set product quality standard, correspondingly adjusting the process parameters of the adjustment data until the average value of the process parameters of the target data is met, and associating the adjustment process with the corresponding adjustment data; associating the maintenance process corresponding to the abnormal data with the abnormal data;
the real-time monitoring module analyzes the real-time data, calculates the similarity between the real-time data and the target data, the similarity between the real-time data and the abnormal data, and determines a final classification result according to the similarity, so that corresponding adjustment is performed.
7. The data analysis-based process flow data monitoring system of claim 6, wherein: the data acquisition module comprises a historical data acquisition unit and a real-time data acquisition unit; the historical data acquisition unit acquires process parameters and product quality data from a historical record; the real-time data acquisition unit acquires real-time data and acquires process parameters and product quality data in real time;
the data preprocessing module comprises a data cleaning unit and a data standardization unit; the data cleaning unit is used for cleaning data and removing abnormal values and noise; the data normalization unit performs normalization processing on the acquired data;
the data classification module comprises a normal data unit and an abnormal data unit; the normal data unit judges according to the existence of the maintenance record and divides the historical data without the maintenance record into normal data; the exception data unit is configured to receive historical data of the presence service record.
8. The data analysis-based process flow data monitoring system of claim 6, wherein: the evaluation and adjustment module comprises a product quality evaluation unit, a target data screening unit, an adjustment data screening unit and an association unit;
the product quality evaluation unit is used for calculating product quality evaluation scores of normal data and abnormal data in the historical data to obtain a scoring set A and a scoring set B;
the target data screening unit compares the threshold interval Q obtained according to the set product quality standard with scores in the score set A, and marks normal data with score values belonging to the threshold interval Q as target data;
the adjusting data screening unit compares the threshold interval Q obtained according to the set product quality standard with scores in the score set A, and marks normal data with the score value not belonging to the threshold interval Q as adjusting data;
the association unit is used for correspondingly adjusting the process parameters of the adjustment data until the average value of the process parameters of the target data is met, and associating the adjustment process with the corresponding adjustment data; and associating the maintenance process corresponding to the abnormal data with the abnormal data.
9. The data analysis-based process flow data monitoring system of claim 6, wherein: the real-time monitoring module comprises a similarity calculation unit, a classification result determination unit and a feedback unit;
the similarity calculation unit is used for calculating the similarity between the real-time data and the target data, the similarity between the real-time data and the abnormal data and the similarity between the real-time data and the abnormal data are calculated;
the classification result determining unit is used for classifying according to the calculation result of the similarity calculating unit, and if the similarity between the real-time data and the target data is highest, the real-time data is marked as the real-time target data; if the similarity between the real-time data and the adjustment data is the highest, marking the real-time data as the real-time adjustment data; if the similarity between the real-time data and the abnormal data is the highest, marking the real-time abnormal data as the real-time abnormal data;
the feedback unit is used for associating the real-time adjustment data with the adjustment data in the historical data according to the classification result of the classification result determining unit, finding out a corresponding adjustment process for adjustment, feeding back to an operator if the corresponding adjustment process does not exist, and recording that the adjustment process of the operator is associated with the real-time adjustment data; and (3) correlating the real-time abnormal data with the abnormal data in the historical data, finding out a corresponding maintenance process, outputting the corresponding maintenance process to an operator, feeding back the corresponding maintenance process to the operator, and recording that the maintenance process of the operator is correlated with the real-time abnormal data.
CN202311285112.1A 2023-10-07 2023-10-07 Process flow data supervision system and method based on data analysis Active CN117314244B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311285112.1A CN117314244B (en) 2023-10-07 2023-10-07 Process flow data supervision system and method based on data analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311285112.1A CN117314244B (en) 2023-10-07 2023-10-07 Process flow data supervision system and method based on data analysis

Publications (2)

Publication Number Publication Date
CN117314244A true CN117314244A (en) 2023-12-29
CN117314244B CN117314244B (en) 2024-03-19

Family

ID=89249568

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311285112.1A Active CN117314244B (en) 2023-10-07 2023-10-07 Process flow data supervision system and method based on data analysis

Country Status (1)

Country Link
CN (1) CN117314244B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117520999A (en) * 2024-01-08 2024-02-06 浙江德塔森特数据技术有限公司 Intelligent operation and maintenance method and system for edge data center equipment
CN117933822A (en) * 2024-01-31 2024-04-26 珠海爱浦京软件股份有限公司 Internet of things data management system and method based on edge calculation

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105096053A (en) * 2015-08-14 2015-11-25 哈尔滨工业大学 Health management decision-making method suitable for complex process system
CN108873830A (en) * 2018-05-31 2018-11-23 华中科技大学 A kind of production scene online data collection analysis and failure prediction system
KR101936283B1 (en) * 2017-12-28 2019-01-08 주식회사 한국가스기술공사 Diagnostic and prognostics method for machine fault
CN113361939A (en) * 2021-06-15 2021-09-07 红云红河烟草(集团)有限责任公司 Dynamic association method and system for quality and equipment management of wrapping machine type
CN114638476A (en) * 2022-02-18 2022-06-17 国电南京自动化股份有限公司 Water conservancy integrated operation and maintenance management method and system
CN115131946A (en) * 2022-06-27 2022-09-30 南京凯奥思数据技术有限公司 Adaptive equipment alarm method and system considering working condition fluctuation
CN116522156A (en) * 2023-03-22 2023-08-01 壹品慧数字科技(上海)有限公司 Equipment state data analysis system and method based on energy management platform
CN116823227A (en) * 2023-07-07 2023-09-29 淮安瀚唐信息技术有限公司 Intelligent equipment management system and method based on Internet of things

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105096053A (en) * 2015-08-14 2015-11-25 哈尔滨工业大学 Health management decision-making method suitable for complex process system
KR101936283B1 (en) * 2017-12-28 2019-01-08 주식회사 한국가스기술공사 Diagnostic and prognostics method for machine fault
CN108873830A (en) * 2018-05-31 2018-11-23 华中科技大学 A kind of production scene online data collection analysis and failure prediction system
CN113361939A (en) * 2021-06-15 2021-09-07 红云红河烟草(集团)有限责任公司 Dynamic association method and system for quality and equipment management of wrapping machine type
CN114638476A (en) * 2022-02-18 2022-06-17 国电南京自动化股份有限公司 Water conservancy integrated operation and maintenance management method and system
CN115131946A (en) * 2022-06-27 2022-09-30 南京凯奥思数据技术有限公司 Adaptive equipment alarm method and system considering working condition fluctuation
CN116522156A (en) * 2023-03-22 2023-08-01 壹品慧数字科技(上海)有限公司 Equipment state data analysis system and method based on energy management platform
CN116823227A (en) * 2023-07-07 2023-09-29 淮安瀚唐信息技术有限公司 Intelligent equipment management system and method based on Internet of things

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
贺宗江;: "工业大数据技术在石化设备预警预测中的研究与实践", 当代石油石化, no. 06, 20 June 2020 (2020-06-20) *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117520999A (en) * 2024-01-08 2024-02-06 浙江德塔森特数据技术有限公司 Intelligent operation and maintenance method and system for edge data center equipment
CN117520999B (en) * 2024-01-08 2024-04-05 浙江德塔森特数据技术有限公司 Intelligent operation and maintenance method and system for edge data center equipment
CN117933822A (en) * 2024-01-31 2024-04-26 珠海爱浦京软件股份有限公司 Internet of things data management system and method based on edge calculation

Also Published As

Publication number Publication date
CN117314244B (en) 2024-03-19

Similar Documents

Publication Publication Date Title
CN117314244B (en) Process flow data supervision system and method based on data analysis
CN113255795B (en) Equipment state monitoring method based on multi-index cluster analysis
CN104573850A (en) Method for evaluating state of thermal power plant equipment
CN112173636B (en) Method for detecting faults of belt conveyor carrier roller by inspection robot
CN117032415B (en) Equipment data supervision system and method based on temperature change
CN111353236B (en) Health state evaluation system of petrochemical normal-pressure oil storage tank based on multiple factors
CN109141625B (en) Online state monitoring method for ball screw pair
CN117391427A (en) Medical instrument production intelligent supervision system based on artificial intelligence
CN116028887B (en) Analysis method of continuous industrial production data
CN112700351A (en) Data processing method and system for intelligent water management platform
CN116244765A (en) Equipment maintenance management method based on industrial Internet
CN116522156A (en) Equipment state data analysis system and method based on energy management platform
CN116177146A (en) Conveying belt detection system and method based on AI and laser monitoring technology
CN117234164A (en) Intelligent factory control system for comprehensive digital production management
CN117032102A (en) Equipment fault prediction method and system based on big data
CN117113104A (en) Intelligent management system and method applying data analysis technology
CN116610915A (en) Pneumatic ash conveying abnormal state diagnosis and fault early warning method
CN108759479A (en) Sintering machine based on the unilateral detection method of blind source separating leaks out on-line fault diagnosis method
CN116243675A (en) Method for monitoring production abnormality of cleaning liquid of coagulometer
CN115356970A (en) Dynamic loop monitoring system and method based on real-time data and operation and maintenance data
CN115487589A (en) Automatic filtration control management system for water plant filter tank
CN114781671A (en) Intelligent monitoring system and monitoring test method for electric oil
CN112734251A (en) Visual neural network monitoring system for intelligent water management platform
CN108627242A (en) Ring cold machine air leak rate of air curtain detection method based on the unilateral detection method of blind source separating
CN117870034B (en) Control method, device and system for environmental parameters of clean room

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