CN111680938B - Power flow type big data based rework and production monitoring method and system and readable medium - Google Patents

Power flow type big data based rework and production monitoring method and system and readable medium Download PDF

Info

Publication number
CN111680938B
CN111680938B CN202010811196.8A CN202010811196A CN111680938B CN 111680938 B CN111680938 B CN 111680938B CN 202010811196 A CN202010811196 A CN 202010811196A CN 111680938 B CN111680938 B CN 111680938B
Authority
CN
China
Prior art keywords
enterprise
time period
fitting
power consumption
value
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
Application number
CN202010811196.8A
Other languages
Chinese (zh)
Other versions
CN111680938A (en
Inventor
吴国诚
杜蜀薇
张宏达
郑斌
胡若云
沈百强
李熊
王正国
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.)
State Grid Zhejiang Electric Power Co Ltd
Marketing Service Center of State Grid Zhejiang Electric Power Co Ltd
Original Assignee
State Grid Zhejiang Electric Power Co Ltd
Marketing Service Center of State Grid Zhejiang Electric Power 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 State Grid Zhejiang Electric Power Co Ltd, Marketing Service Center of State Grid Zhejiang Electric Power Co Ltd filed Critical State Grid Zhejiang Electric Power Co Ltd
Priority to CN202010811196.8A priority Critical patent/CN111680938B/en
Publication of CN111680938A publication Critical patent/CN111680938A/en
Application granted granted Critical
Publication of CN111680938B publication Critical patent/CN111680938B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention aims to solve the problem that the existing compound work and compound work monitoring system cannot accurately monitor the compound work and compound work condition of an enterprise, provides a compound work and compound work monitoring method and system based on electric power streaming type big data, and improves the compound work and compound work monitoring accuracy. Generating a complex work and complex production monitoring map and generating a plurality of fitting time periods; acquiring historical electric quantity data and real-time electric quantity data; fitting and forming a time/power consumption relation function of the enterprise in each fitting time period according to historical power data of the fitting time period; calculating an estimation curve precision value of each time/power consumption relation function to determine a target estimation function; calculating the electric quantity consumption estimated value of the enterprise in the current time period according to the target estimation function; calculating the actual value of the electric quantity consumption of the enterprise in the current time period; according to the ratio of the actual value of the electric quantity consumption to the estimated value of the electric quantity consumption, zooming and filling a re-work and re-production profile of the enterprise; the technical scheme of the real-time monitoring system and the monitoring method can accurately monitor and reflect the repeated work and production conditions of repeated enterprises.

Description

Power flow type big data based rework and production monitoring method and system and readable medium
Technical Field
The invention belongs to the field of electric power big data processing, and particularly relates to a method and a system for monitoring rework and production recovery based on electric power streaming big data and a readable medium.
Background
Due to the influence of epidemic situations, an electric power department pushes electric power big data service, and by utilizing system mass data, according to data such as historical power consumption conditions and current day power consumption conditions of enterprises, enterprise reworking electric power indexes are obtained and displayed through a chart, the current enterprise reworking and reworking conditions are dynamically monitored and intuitively reflected, the difficult points of tedious step-by-step reporting, insufficient hands for epidemic situation prevention and control and the like are solved, and the government is assisted to make epidemic situation prevention and control and ordered reworking work; the ratio of the power consumption of the re-engineering enterprise to the current year is used as the basis of the re-engineering and re-production conditions, and the defects are that: 1. in the process of steady development of enterprises, the power consumption often changes, for example, the power consumption is gradually increased because the productivity is increased, and the power consumption is gradually reduced because the equipment is gradually replaced by energy-saving equipment, so that the ratio of the power consumption of a rework enterprise to the same period of the previous year is taken as the basis of the rework and rework situation of the current enterprise to reflect the rework and rework situation of the current enterprise, and the larger deviation from the actual rework and rework situation of the enterprise is often caused; 2. the enterprise rework electric power index is displayed in a chart form, and the position relationship of each enterprise and the rework and rework relationship gap of adjacent enterprises and the like are difficult to visually identify.
Disclosure of Invention
The invention aims to solve one of the problems in the prior art, and provides a method and a system for monitoring the rework and rework complex production based on power flow type big data, which improve the monitoring precision of the rework and rework complex production and more truly reflect the rework and rework situation of enterprises.
In order to achieve the object, in a first aspect of the present disclosure, a method for monitoring rework and production recovery based on power streaming big data includes:
generating a complex work and complex production monitoring map based on the geographical position information and the enterprise scale of each enterprise, wherein the complex work and complex production monitoring map comprises an enterprise outline map of each enterprise and a complex work and complex production outline map of each enterprise, and the initial position, the initial size and the initial shape of the complex work and complex production outline map are the same as those of the enterprise outline map;
generating a plurality of fitting time intervals based on a target non-epidemic year so that each working day of the target non-epidemic year is contained in at least two fitting time intervals, wherein the target non-epidemic year is the last year of the epidemic year;
acquiring historical electric quantity data and real-time electric quantity data of an enterprise;
based on the historical electric quantity data of the enterprise in each fitting time period, fitting to form a time/power consumption relation function of the enterprise in each fitting time period, wherein the number of samples used for forming each time/power consumption relation function in a fitting mode is the same;
calculating a daily power consumption estimation value of the enterprise in a verification period according to a time/power consumption relation function of the enterprise in each fitting period and a yearly growth coefficient of the enterprise, wherein the verification period is [ the 1 st working day of the last month, the Nth working day of the last month ], N is the total number of the working days of the last month, and the yearly growth coefficient is a preset value;
based on the daily power consumption estimated value of the enterprise in the verification period and the daily power consumption actual value of the enterprise in the verification period, calculating the estimated curve precision value of each time/power consumption relation function of the enterprise according to the following formula:
Figure 845150DEST_PATH_IMAGE001
，
wherein Z is an estimated curve precision value, j is a preset proportionality coefficient, and j is more than 0 and less than 1; si+1Actual daily power consumption value, S, for the i +1 th working day of the previous monthiActual daily electricity consumption value for the ith working day of the previous month, Gi+1Estimate of daily consumption for the i +1 th working day of the previous month, GiAn estimate of daily power consumption for the ith working day of the previous month;
selecting a time/power consumption relation function from a plurality of time/power consumption relation functions of an enterprise as a target estimation function of the enterprise by taking the minimum precision value of the estimation curve as a selection condition;
calculating the electric quantity consumption estimated value of the enterprise in the current time period according to the target estimation function of the enterprise;
calculating an actual value of the electricity consumption of the enterprise in the current time period based on the real-time electricity data of the enterprise;
and scaling and filling a rework and reproduction profile of the enterprise according to the ratio of the actual power consumption value of the enterprise in the current time period to the estimated power consumption value of the enterprise in the current time period.
Optionally, the annual growth factor of the enterprise is set as an average of annual power consumption growth rates of the enterprise over the years.
Alternatively to this, the first and second parts may,
Figure 214821DEST_PATH_IMAGE002
。
optionally, the generating a plurality of fitting periods based on the target non-epidemic year includes:
and generating a target non-epidemic year annual time period, a target non-epidemic year first quarter time period, a target non-epidemic year second quarter time period, a target non-epidemic year third quarter time period, a target non-epidemic year fourth quarter time period, a target non-epidemic year first half year time period and a target non-epidemic year second half year time period based on the target non-epidemic year.
Optionally, the generating a plurality of fitting periods based on the target non-epidemic year includes:
judging the industry of the enterprise;
according to the industry of the enterprise, selecting a fitting time period generation rule of the industry of the enterprise as a target rule from preset fitting time period generation rules of each industry;
and generating a plurality of fitting periods of the enterprise according to the target rule.
Optionally, the determining the industry of the enterprise includes:
acquiring an enterprise name;
according to the enterprise name, the latest enterprise introduction information of the enterprise is automatically retrieved and captured in the network;
according to the enterprise name, the latest product introduction information of the enterprise is automatically retrieved and captured in the network;
according to the enterprise name, automatically retrieving and capturing the latest business license information of the enterprise in the network;
inputting enterprise introduction information and product introduction information into a preset first neural network model to output three pre-judging industries, wherein input items of the first neural network model are the enterprise introduction information and the product introduction information, and output items of the neural network model are the three pre-judging industries;
and inputting the three pre-judging industry and business license information into a second neural network model to determine the industry of the enterprise, wherein the input items of the second neural network model are the three pre-judging industry and business license information, and the output items of the second neural network model are whether the three pre-judging industries are true or not.
Optionally, the current time period is [ T-24 hours, T ], where T is the current time.
In a second aspect of the present disclosure, a duplicate production and duplicate production monitoring system based on power streaming big data includes:
the map generation module is used for generating a complex work and complex production monitoring map based on the geographical position information of each enterprise, wherein the complex work and complex production monitoring map comprises an enterprise outline map of each enterprise and a complex work and complex production outline map of each enterprise, and the initial position, the initial size and the initial shape of the complex work and complex production outline map are the same as those of the enterprise outline map;
the fitting time interval generation module is used for generating a plurality of fitting time intervals based on a target non-epidemic year so that each working day of the target non-epidemic year is contained in at least two fitting time intervals, wherein the target non-epidemic year is the last year of the epidemic year;
the data acquisition module is used for acquiring historical electric quantity data and real-time electric quantity data of an enterprise;
the function fitting module is used for fitting and forming a time/power consumption relation function of the enterprise in each fitting time period based on the historical electric quantity data of the enterprise in each fitting time period, wherein the number of samples used for fitting and forming each time/power consumption relation function is the same;
a daily power consumption estimation value calculation module, configured to calculate a daily power consumption estimation value of an enterprise in a verification period according to a time/power consumption relation function of the enterprise in each fitting period and a yearly growth coefficient of the enterprise, where the verification period is [ last month, 1 st working day, last month, nth working day ], N is a total number of working days of the last month, and the yearly growth coefficient is a preset value;
the estimation curve precision value calculation module is used for calculating the estimation curve precision value of each time/power consumption relation function of the enterprise according to the following formula based on the daily power consumption estimated value of the enterprise in the verification period and the daily power consumption actual value of the enterprise in the verification period:
Figure 791295DEST_PATH_IMAGE003
，
wherein Z is an estimated curve precision value, j is a preset proportionality coefficient, and 1 & gtj & gt 0; si+1Actual daily power consumption value, S, for the i +1 th working day of the previous monthiActual daily electricity consumption value for the ith working day of the previous month, Gi+1Estimate of daily consumption for the i +1 th working day of the previous month, GiAn estimate of daily power consumption for the ith working day of the previous month;
the target estimation function selection module is used for selecting a time/power consumption relation function from a plurality of time/power consumption relation functions of an enterprise as a target estimation function of the enterprise by taking the minimum estimation curve precision value as a selection condition;
the electric quantity consumption estimation value calculation module is used for calculating the electric quantity consumption estimation value of the enterprise in the current time period according to the target estimation function of the enterprise;
the electric quantity consumption actual value calculating module is used for calculating the electric quantity consumption actual value of the enterprise in the current time period based on the real-time electric quantity data of the enterprise;
and the scaling control module is used for scaling and filling the rework and reproduction profile of the enterprise according to the ratio of the actual power consumption value of the enterprise in the current time period to the estimated power consumption value of the enterprise in the current time period.
In a third aspect of the disclosure, a computer program product comprising computer program code which, when executed by a computer, causes the computer to perform the method of any one of the first aspects of the disclosure.
A fourth aspect of the disclosure, a readable medium, comprising instructions which, when executed on a computer, cause the computer to perform the method of any of the first aspects of the disclosure.
The technical scheme of the present disclosure can be implemented to obtain the following beneficial technical effects: 1. the method disclosed by the invention can be used for calculating the electric quantity consumption estimated value of each enterprise in the current time period according to the historical electric quantity data of each enterprise, taking the electric quantity consumption estimated value of each enterprise in the current time period as a rework judgment basis, so that the rework and rework monitoring result is closer to the actual situation of the enterprise, the problem of the difference between the current year and the current power consumption in the previous year caused by various reasons such as enterprise development is solved, and the influence of the epidemic situation on the enterprises can be more accurately reflected by related data.
2. The method disclosed by the invention comprises the steps of fitting a plurality of time/power consumption relation functions according to historical electric quantity data of different fitting time periods, and selecting the time/power consumption relation function with the highest estimation precision in real time from the plurality of time/power consumption relation functions as an estimation function of an enterprise to ensure the estimation precision; the problem that enterprises of different types and different development speeds adopt the same estimation function to cause low precision is solved.
3. According to the method, through setting of the sample amount, the electric quantity time intervals of the historical electric power data in different fitting time periods are greatly different, and the power consumption characteristics of the fitting time periods can be better reflected by the function based on the historical electric power data fitting in different fitting time periods. If enterprises in obviously weak and busy seasons exist, the function fitted by the data in the fitting time period in the seasonal season can reflect the actual power utilization characteristics of the enterprises better.
4. The method disclosed by the invention displays the rework and reproduction information of the enterprise in a map form in the forms of the enterprise outline and the rework and reproduction outline, so that a user can intuitively observe the rework and reproduction condition of the enterprise according to the proportional relation between the rework and reproduction outline and the enterprise outline, and can intuitively observe the scale and the position relation of the enterprise according to the outline size and the position relation of the enterprise outline.
Drawings
Fig. 1 is a flowchart of a rework and production monitoring method based on power streaming big data in the embodiment of the present disclosure.
Fig. 2 is a flow chart of generating a plurality of fitting periods based on a target non-epidemic year in an embodiment of the disclosure.
Fig. 3 is a flowchart of determining an industry of an enterprise according to an embodiment of the disclosure.
Fig. 4 is a block diagram of a rework and production monitoring system based on power streaming big data in the embodiment of the present disclosure.
Detailed Description
To facilitate understanding of those skilled in the art, the present invention will be further described with reference to specific examples:
example 1:
as shown in fig. 1, the method for monitoring rework and production recovery based on power streaming big data includes:
step 101: and generating a re-work and re-work monitoring map based on the geographical position information and the enterprise scale of each enterprise, wherein the re-work and re-work monitoring map comprises an enterprise outline map of each enterprise and a re-work and re-work outline map of each enterprise, and the initial position, the initial size and the initial shape of the re-work and re-work outline map are the same as those of the enterprise.
In the step, the position and the size of an enterprise outline in the rework and reproduction monitoring map are determined according to the geographical position information and the enterprise scale of the enterprise, and the initial position, the initial size and the initial shape of the rework and reproduction outline are the same as those of the enterprise outline, so that the rework and reproduction outline can be conveniently zoomed in the subsequent steps; after the enterprise is zoomed, the reworking and reworking contour map of the enterprise is positioned in the enterprise contour map of the enterprise, and after the reworking and reworking contour map is zoomed and filled, a user can intuitively reach the approximate proportion of the reworking and reworking contour map of the enterprise in the enterprise contour map so as to determine the reworking and reworking condition of the enterprise; meanwhile, a reworking and reworking profile map of the whole map can be observed, and a region with good reworking and reworking conditions and a region with poor reworking and reworking conditions can be intuitively known; it can be known that the rework and reproduction monitoring map can be set into a format that can be zoomed as a whole; it can also be known that the enterprise contour map can be set into a three-dimensional contour map or a two-dimensional contour map according to the requirement, the design complexity of the three-dimensional contour map is higher, the design complexity of the two-dimensional contour map is lower, and when the enterprise contour map is the two-dimensional contour map, the enterprise contour maps on the upper and lower layers can be set to determine which enterprise contour map and the reworking and reproduction contour map thereof are displayed according to the selection of a user; meanwhile, it is also required to know that the enterprise profile map in the rework and reproduction monitoring map can be associated with information such as an enterprise name and the like, so that the information such as the enterprise name and the like can be displayed when the mouse is moved to the position of the enterprise profile map; and the reworking and reworking profile map in the reworking and reworking monitoring map can be associated with the actual power consumption value of the enterprise in the current time period, the estimated power consumption value of the enterprise in the current time period and the like, so that when the mouse is moved to the reworking and reworking profile map, the actual power consumption value of the enterprise in the current time period, the estimated power consumption value of the enterprise in the current time period and the like can be displayed.
Step 102: generating a plurality of fitting time periods based on the target non-epidemic year so that each working day of the target non-epidemic year is contained in at least two fitting time periods, wherein the target non-epidemic year is the last year of the epidemic year;
in the step, taking the epidemic situation happening in 2020 as an example, the target non-epidemic year is 2019; theoretically, the more the fitting time periods in the target non-epidemic situation year are, the higher the fitting time overlapping rate of the fitting time periods is, and the higher the monitoring accuracy of the reworking and production repeating of the method is; in the embodiment, the working day is used as a measurement standard, so that the relevant data can more accurately reflect the real situation of the enterprise.
Step 103: and acquiring historical electric quantity data and real-time electric quantity data of the enterprise.
Step 104: based on the historical electric quantity data of the enterprise in each fitting time period, fitting to form a time/power consumption relation function of the enterprise in each fitting time period, wherein the number of samples used for forming each time/power consumption relation function in the fitting mode is the same;
in the step, the X axis of the time/power consumption relation function is time, and the Y axis is power consumption; fitting a time/power consumption relation function to the historical electric quantity data of each fitting time period; the number of samples used for fitting and forming each time/power consumption relation function is the same; the samples are distributed evenly over time (or nearly so), taking 30 samples as an example, if the duration of the fitting period is 30 working days, one sample per working day, if the duration of the fitting period is 60 working days, one sample per two working days, if the duration of the fitting period is 90 working days, one sample per three working days. When the time/power consumption relation function is fitted according to the historical power data, an existing fitting method, such as a least square method, can be adopted.
Step 105: calculating a daily power consumption estimation value of the enterprise in a verification period according to a time/power consumption relation function of the enterprise in each fitting period and a yearly growth coefficient of the enterprise, wherein the verification period is [ the 1 st working day of the last month, the Nth working day of the last month ], N is the total number of the working days of the last month, and the yearly growth coefficient is a preset value;
in this step, the annual growth coefficient is determined and set according to the annual power consumption growth condition of the enterprise, and specifically, the annual growth coefficient may be an average value of annual power consumption growth rates of the enterprise in the annual. And multiplying the result calculated according to the time/power consumption relation function by the annual growth coefficient to calculate the daily power consumption estimated value in the enterprise verification period.
Step 106: based on the daily power consumption estimated value of the enterprise in the verification period and the daily power consumption actual value of the enterprise in the verification period, calculating the estimated curve precision value of each time/power consumption relation function of the enterprise according to the following formula:
Figure 779980DEST_PATH_IMAGE003
，
wherein Z is an estimated curve precision value, j is a preset proportionality coefficient, and j is more than 0 and less than 1; si+1Actual daily power consumption value, S, for the i +1 th working day of the previous monthiActual daily electricity consumption value for the ith working day of the previous month, Gi+1Estimate of daily consumption for the i +1 th working day of the previous month, GiThe estimated value of the daily power consumption of the ith working day of the previous month is N, and the N is the total number of the working days of the previous month;
in this step, Z is used to reflect the estimation accuracy when the time/power consumption relation function is used to estimate the power consumption value, and j may be set to 1-year growth coefficient/(year growth coefficient + 1); when the annual growth coefficient is the average value of the annual power consumption growth rate of the enterprise in the past year and j is set to be 1-annual growth coefficient/(annual growth coefficient +1), the estimated curve precision value can be adjusted according to the annual growth coefficient of the enterprise so as to ensure the accuracy of time/power consumption relation function selection; j may also be set to 0.5.
Step 107: and selecting a time/power consumption relation function from a plurality of time/power consumption relation functions of the enterprise as a target estimation function of the enterprise by taking the minimum estimation curve precision value as a selection condition.
Step 108: calculating the electric quantity consumption estimated value of the enterprise in the current time period according to the target estimation function of the enterprise;
in this step, it can be known that the current time period can be set as required, and the current time period can be [ T-24 hours, T ], where T is the current time; specifically, the estimated value of the power consumption in the current time period is calculated according to the target estimation function, the estimated values of the power consumption in the current time period per day may be calculated respectively, and the estimated values of the power consumption in the current time period may be calculated by summing the estimated values of the power consumption in the current time period per day.
Of course, if the current time period relates to non-whole days, such as the current time period is 12: 00-24: 00 of 7-month and 23-day and 24: 00-12 of 7-month and 24-day, the estimated value of the power consumption of 7-month and 23-day and the estimated value of the power consumption of 7-month and 24-day can be calculated according to the target estimation function; and multiplying the estimated electricity consumption value of day 23/7 by the first coefficient, and multiplying the estimated electricity consumption value of day 24/7 by the second coefficient to obtain the estimated electricity consumption value of the current time period. It should be noted that the sum of the first coefficient and the second coefficient is 1, the first coefficient and the second coefficient may both be set to 0.5, the first coefficient may also be set to 0.8, the second coefficient may also be set to 0.2, and the coefficients may also be determined according to the point-to-point of the business working time and the point-to-point involved in the current time period.
Step 109: calculating an actual value of the electricity consumption of the enterprise in the current time period based on the real-time electricity data of the enterprise;
in this step, it can be known that the actual value of the power consumption of the enterprise in the current period also needs historical power data of the enterprise, and the method for calculating the actual value of the power consumption in the current period is not described in detail in this application.
Step 110: and scaling and filling a rework and reproduction profile of the enterprise according to the ratio of the actual power consumption value of the enterprise in the current time period to the estimated power consumption value of the enterprise in the current time period.
In the step, scaling is carried out according to the ratio of the actual electric quantity consumption value of the enterprise in the current time period to the estimated electric quantity consumption value of the enterprise in the current time period and according to the initial size of the reworking and reworking profile of the enterprise as a basis; for example, when the ratio of the actual value of the power consumption in the current period to the estimated value of the power consumption of the enterprise in the current period is calculated for the first time to be 0.4, the size of the rework reproduction profile of the enterprise is scaled to be 0.4 times of the initial size, and when the ratio of the actual value of the power consumption in the current period to the estimated value of the power consumption of the enterprise in the current period is calculated for the second time to be 0.5 times of the initial size, the size of the rework reproduction profile of the enterprise is scaled to be 0.5 times of the initial size.
The method disclosed by the invention can be used for calculating the electric quantity consumption estimated value of each enterprise in the current time period according to the historical electric quantity data of each enterprise, taking the electric quantity consumption estimated value of each enterprise in the current time period as a rework judgment basis, so that the rework and rework monitoring result is closer to the actual situation of the enterprise, the problem of the difference between the current year and the current power consumption in the previous year caused by various reasons such as enterprise development is solved, and the influence of the epidemic situation on the enterprises can be more accurately reflected by related data.
The method disclosed by the invention comprises the steps of fitting a plurality of time/power consumption relation functions according to historical electric quantity data of different fitting time periods, and selecting the time/power consumption relation function with the highest estimation precision in real time from the plurality of time/power consumption relation functions as an estimation function of an enterprise to ensure the estimation precision; the problem that enterprises of different types and different development speeds adopt the same estimation function to cause low precision is solved.
According to the method, through setting of the sample amount, the electric quantity time intervals of the historical electric power data in different fitting time periods are greatly different, and the power consumption characteristics of the fitting time periods can be better reflected by the function based on the historical electric power data fitting in different fitting time periods. If enterprises in obviously weak and busy seasons exist, the function fitted by the data in the fitting time period in the seasonal season can reflect the actual power utilization characteristics of the enterprises better.
The method disclosed by the invention displays the rework and reproduction information of the enterprise in a map form in the forms of the enterprise outline and the rework and reproduction outline, so that a user can intuitively observe the rework and reproduction condition of the enterprise according to the proportional relation between the rework and reproduction outline and the enterprise outline, and can intuitively observe the scale and the position relation of the enterprise according to the outline size and the position relation of the enterprise outline.
As an alternative, generating a plurality of fitting periods based on the target non-epidemic years comprises: and generating a target non-epidemic year annual time period, a target non-epidemic year first quarter time period, a target non-epidemic year second quarter time period, a target non-epidemic year third quarter time period, a target non-epidemic year fourth quarter time period, a target non-epidemic year first half year time period and a target non-epidemic year second half year time period based on the target non-epidemic year.
It can be known that the more fitting time periods of the target non-epidemic year, the higher the monitoring accuracy of the method is; in the process of actually using the method, more fitting time periods can be automatically generated in a function mode in a plurality of fitting time periods, so that the monitoring accuracy of the method is higher.
As an alternative, as shown in fig. 2, a plurality of fitting periods are generated based on the target non-epidemic years, including:
step 201, judging the industry of an enterprise;
step 202, according to the industries of the enterprises, selecting the fitting time period generation rule of the industries of the enterprises from the preset fitting time period generation rules of each industry as a target rule;
step 203, generating a plurality of fitting time periods of the enterprise according to the target rule.
Here, set up different fitting periods to the trade characteristic of different enterprises, reject the not required fitting period, when can guaranteeing that the electric quantity consumption estimated value is accurate, reduce the calculated amount, for example: the strong season of the animal husbandry is the beginning of the year and the end of the year, and the weak season is the middle of the year, so that the time period of the beginning of the year and the end of the year of the animal husbandry can be used as a special fitting time period of the industry, and the time period of the middle of the year can be used as a special fitting time period of the industry. The off-season of the coke industry is 3-8 months, the off-season is 1-2 months, so that the 3-8 month period of the coke industry can be used as a special fitting period of the industry, and 1-2 months can be used as a special fitting period of the industry.
Further, as shown in fig. 3, determining the industry of the enterprise includes:
step 301, acquiring enterprise names;
step 302, automatically retrieving and capturing the latest enterprise introduction information of the enterprise in the network according to the name of the enterprise;
step 303, automatically retrieving and capturing latest product introduction information of the enterprise in the network according to the name of the enterprise;
step 304, automatically retrieving and capturing the latest business license information of the enterprise in the network according to the name of the enterprise;
305, inputting enterprise introduction information and product introduction information into a preset first neural network model to output three pre-judging industries, wherein input items of the first neural network model are the enterprise introduction information and the product introduction information, and output items of the neural network model are the three pre-judging industries;
and step 306, inputting the three pre-judging industry and business license information into a second neural network model to determine the industry where the enterprise is located, wherein the input items of the second neural network model are the three pre-judging industry and business license information, and the output items of the second neural network model are whether the three pre-judging industries are true or not.
The first neural network model and the second neural network model are set as required, and specifically, the first neural network model may be a convolutional neural network model, and the second neural network model may be a deep residual error network model.
The method automatically judges the industry of the enterprise based on the latest product introduction information, the latest enterprise introduction information and the latest enterprise operation range of the open network, improves the judgment accuracy of the industry of the enterprise, and reduces the workload of manual judgment. The method uses the first neural network model to prejudge the industry, and then uses the second neural network model to determine the industry, so that the training difficulty of the neural network model can be reduced.
Example 2:
as shown in fig. 4, a duplicate production and duplicate production monitoring system based on power streaming big data includes:
the map generation module 401 is configured to generate a rework and rework monitoring map based on the geographical location information of each enterprise, where the rework and rework monitoring map includes an enterprise profile of each enterprise and a rework and rework profile of each enterprise, and an initial position, an initial size, and an initial shape of the rework and rework profile are the same as those of the enterprise;
a fitting time interval generation module 402, configured to generate a plurality of fitting time intervals based on the target non-epidemic year, so that each working day of the target non-epidemic year is included in at least two fitting time intervals, where the target non-epidemic year is the last year of the epidemic year;
a data obtaining module 403, configured to obtain historical electricity quantity data and real-time electricity quantity data of an enterprise;
a function fitting module 404, configured to fit and form a time/power consumption relation function of the enterprise in each fitting time period based on historical electric quantity data of the enterprise in each fitting time period, where the number of samples used for forming each time/power consumption relation function in the fitting is the same;
a daily power consumption estimation value calculation module 405, configured to calculate a daily power consumption estimation value of the enterprise in a verification period according to a time/power consumption relation function of the enterprise in each fitting period and a yearly growth coefficient of the enterprise, where the verification period is [ last month, 1 st working day, last month, nth working day ], N is a total number of working days of the last month, and the yearly growth coefficient is a preset value;
an estimated curve precision value calculating module 406, configured to calculate an estimated curve precision value of each time/power consumption relation function of the enterprise according to the following formula based on the estimated value of the daily power consumption of the enterprise in the verification period and the actual value of the daily power consumption of the enterprise in the verification period:
Figure 859931DEST_PATH_IMAGE003
，
wherein Z is an estimated curve precision value, j is a preset proportionality coefficient, and 1 & gtj & gt 0; si+1Actual daily power consumption value, S, for the i +1 th working day of the previous monthiActual daily electricity consumption value for the ith working day of the previous month, Gi+1Estimate of daily consumption for the i +1 th working day of the previous month, GiAn estimate of daily power consumption for the ith working day of the previous month;
a target estimation function selection module 407, configured to select a time/power consumption relation function from a plurality of time/power consumption relation functions of an enterprise as a target estimation function of the enterprise, with a minimum estimation curve precision value as a selection condition;
the power consumption estimation value calculation module 408 is configured to calculate a power consumption estimation value of the enterprise in the current time period according to an objective estimation function of the enterprise;
the electric quantity consumption actual value calculating module 409 is used for calculating the electric quantity consumption actual value of the enterprise in the current time period based on the real-time electric quantity data of the enterprise;
and the scaling control module 410 is used for scaling and filling the rework and reproduction profile of the enterprise according to the ratio of the actual power consumption value of the enterprise in the current time period to the estimated power consumption value of the enterprise in the current time period.
The effects and principles in this embodiment can be referred to embodiment 1.
Example 3: a computer program product comprising computer program code which, when executed by a computer, causes the computer to perform the method of monitoring rework and rework complex production based on power streaming big data as in any of embodiment 1.
Example 4: a readable medium, comprising instructions, which when run on a computer, cause the computer to execute the method for monitoring rework and production based on power streaming big data as in any one of embodiment 1.
It should also be noted that 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. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The above description is only an embodiment of the present invention, but the technical features of the present invention are not limited thereto, and any changes or modifications within the technical field of the present invention by those skilled in the art are covered by the claims of the present invention.

Claims (4)

1. A re-work and re-production monitoring method based on power flow type big data is characterized by comprising the following steps:
generating a complex work and complex production monitoring map based on the geographical position information and the enterprise scale of each enterprise, wherein the complex work and complex production monitoring map comprises an enterprise outline map of each enterprise and a complex work and complex production outline map of each enterprise, and the initial position, the initial size and the initial shape of the complex work and complex production outline map are the same as those of the enterprise outline map; generate a plurality of fitting periods based on the target non-epidemic year so that each working day of the target non-epidemic year is contained in at least two of the fitting periods, wherein the target non-epidemic year is the last year of the epidemic year, and the fitting periods include: a target non-epidemic year annual time period, a target non-epidemic year first quarter time period, a target non-epidemic year second quarter time period, a target non-epidemic year third quarter time period, a target non-epidemic year fourth quarter time period, a target non-epidemic year first half year time period and a target non-epidemic year second half year time period; acquiring historical electric quantity data and real-time electric quantity data of an enterprise; based on the historical electric quantity data of the enterprise in each fitting time period, fitting to form a time/power consumption relation function of the enterprise in each fitting time period, wherein the number of samples used for forming each time/power consumption relation function in the fitting mode is the same, and the samples are distributed evenly according to time;
calculating a daily power consumption estimation value of the enterprise in a verification period according to a time/power consumption relation function of the enterprise in each fitting period and a yearly growth coefficient of the enterprise, wherein the verification period is [ the 1 st working day of the last month, the Nth working day of the last month ], N is the total number of the working days of the last month, and the yearly growth coefficient of the enterprise is set as an average value of yearly power consumption growth rates of the enterprise in the past year;
based on the daily power consumption estimated value of the enterprise in the verification period and the daily power consumption actual value of the enterprise in the verification period, calculating the estimated curve precision value of each time/power consumption relation function of the enterprise according to the following formula:
Figure 161489DEST_PATH_IMAGE001
，
wherein Z is an estimated curve precision value, j is a preset proportionality coefficient, j is more than 0 and less than 1,
Figure 619015DEST_PATH_IMAGE002
；Si+1actual daily power consumption value, S, for the i +1 th working day of the previous monthiActual daily electricity consumption value for the ith working day of the previous month, Gi+1Estimate of daily consumption for the i +1 th working day of the previous month, GiAn estimate of daily power consumption for the ith working day of the previous month;
selecting a time/power consumption relation function from a plurality of time/power consumption relation functions of an enterprise as a target estimation function of the enterprise by taking the minimum precision value of the estimation curve as a selection condition;
calculating the electric quantity consumption estimated value of the enterprise in the current time period according to the target estimation function of the enterprise;
calculating an actual value of the electricity consumption of the enterprise in the current time period based on the real-time electricity data of the enterprise;
scaling and filling a re-work and re-production contour map of the enterprise according to the ratio of the actual electric quantity consumption value of the enterprise in the current time period to the estimated electric quantity consumption value of the enterprise in the current time period;
generating a plurality of fitting periods based on the target non-epidemic years, including:
judging the industry of the enterprise;
according to the industry of the enterprise, selecting a fitting time period generation rule of the industry of the enterprise as a target rule from preset fitting time period generation rules of each industry;
generating a plurality of fitting time periods of the enterprise according to the target rule; the industry of the enterprise is judged, including:
acquiring an enterprise name;
according to the enterprise name, the latest enterprise introduction information of the enterprise is automatically retrieved and captured in the network;
according to the enterprise name, the latest product introduction information of the enterprise is automatically retrieved and captured in the network;
according to the enterprise name, automatically retrieving and capturing the latest business license information of the enterprise in the network;
inputting enterprise introduction information and product introduction information into a preset first neural network model to output three pre-judging industries, wherein input items of the first neural network model are the enterprise introduction information and the product introduction information, and output items of the first neural network model are the three pre-judging industries;
and inputting the three pre-judging industry and business license information into a second neural network model to determine the industry of the enterprise, wherein the input items of the second neural network model are the three pre-judging industry and business license information, and the output items of the second neural network model are whether the three pre-judging industries are true or not.
2. The method for monitoring rework and production based on power streaming big data as claimed in claim 1, wherein the current time period is [ T-24 hours, T ], where T is the current time.
3. A compound work and production monitoring system based on electric power streaming big data is characterized by comprising:
the map generation module is used for generating a complex work and complex production monitoring map based on the geographical position information of each enterprise, wherein the complex work and complex production monitoring map comprises an enterprise outline map of each enterprise and a complex work and complex production outline map of each enterprise, and the initial position, the initial size and the initial shape of the complex work and complex production outline map are the same as those of the enterprise outline map;
the fitting period generation module generates a plurality of fitting periods based on the target non-epidemic year so that each working day of the target non-epidemic year is contained in at least two of the fitting periods, wherein the target non-epidemic year is the last year of the epidemic year, and the fitting periods comprise: a target non-epidemic year annual time period, a target non-epidemic year first quarter time period, a target non-epidemic year second quarter time period, a target non-epidemic year third quarter time period, a target non-epidemic year fourth quarter time period, a target non-epidemic year first half year time period and a target non-epidemic year second half year time period;
the data acquisition module is used for acquiring historical electric quantity data and real-time electric quantity data of an enterprise;
the function fitting module is used for fitting and forming a time/power consumption relation function of the enterprise in each fitting time period based on the historical electric quantity data of the enterprise in each fitting time period, wherein the number of samples used for fitting and forming each time/power consumption relation function is the same, and the samples are evenly distributed according to time;
a daily power consumption estimation value calculation module, configured to calculate a daily power consumption estimation value of the enterprise in a verification period according to a time/power consumption relation function of the enterprise in each fitting period and a yearly growth coefficient of the enterprise, where the verification period is [ last month, 1 st working day, last month, nth working day ], N is a total number of working days of the last month,
setting the annual growth coefficient of the enterprise as the average value of annual power consumption growth rate of the enterprise in the past year;
the estimation curve precision value calculation module is used for calculating the estimation curve precision value of each time/power consumption relation function of the enterprise according to the following formula based on the daily power consumption estimated value of the enterprise in the verification period and the daily power consumption actual value of the enterprise in the verification period:
Figure 764213DEST_PATH_IMAGE001
，
wherein Z is an estimated curve precision value, j is a preset proportionality coefficient, 1 > j > 0,
Figure 914572DEST_PATH_IMAGE002
；Si+1actual daily power consumption value, S, for the i +1 th working day of the previous monthiActual daily electricity consumption value for the ith working day of the previous month, Gi+1Estimate of daily consumption for the i +1 th working day of the previous month, GiAn estimate of daily power consumption for the ith working day of the previous month;
the target estimation function selection module is used for selecting a time/power consumption relation function from a plurality of time/power consumption relation functions of an enterprise as a target estimation function of the enterprise by taking the minimum estimation curve precision value as a selection condition;
the electric quantity consumption estimation value calculation module is used for calculating the electric quantity consumption estimation value of the enterprise in the current time period according to the target estimation function of the enterprise;
the electric quantity consumption actual value calculating module is used for calculating the electric quantity consumption actual value of the enterprise in the current time period based on the real-time electric quantity data of the enterprise;
the scaling control module is used for scaling and filling the rework and reproduction profile of the enterprise according to the ratio of the actual electric quantity consumption value of the enterprise in the current time period to the estimated electric quantity consumption value of the enterprise in the current time period;
generating a plurality of fitting periods based on the target non-epidemic years, including:
judging the industry of the enterprise;
according to the industry of the enterprise, selecting a fitting time period generation rule of the industry of the enterprise as a target rule from preset fitting time period generation rules of each industry;
generating a plurality of fitting time periods of the enterprise according to the target rule;
the industry of the enterprise is judged, including:
acquiring an enterprise name;
according to the enterprise name, the latest enterprise introduction information of the enterprise is automatically retrieved and captured in the network;
according to the enterprise name, the latest product introduction information of the enterprise is automatically retrieved and captured in the network;
according to the enterprise name, automatically retrieving and capturing the latest business license information of the enterprise in the network;
inputting enterprise introduction information and product introduction information into a preset first neural network model to output three pre-judging industries, wherein input items of the first neural network model are the enterprise introduction information and the product introduction information, and output items of the first neural network model are the three pre-judging industries;
and inputting the three pre-judging industry and business license information into a second neural network model to determine the industry of the enterprise, wherein the input items of the second neural network model are the three pre-judging industry and business license information, and the output items of the second neural network model are whether the three pre-judging industries are true or not.
4. A readable medium comprising instructions which, when run on a computer, cause the computer to perform the method of claim 1 or 2.
CN202010811196.8A 2020-08-13 2020-08-13 Power flow type big data based rework and production monitoring method and system and readable medium Active CN111680938B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010811196.8A CN111680938B (en) 2020-08-13 2020-08-13 Power flow type big data based rework and production monitoring method and system and readable medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010811196.8A CN111680938B (en) 2020-08-13 2020-08-13 Power flow type big data based rework and production monitoring method and system and readable medium

Publications (2)

Publication Number Publication Date
CN111680938A CN111680938A (en) 2020-09-18
CN111680938B true CN111680938B (en) 2020-11-06

Family

ID=72438619

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010811196.8A Active CN111680938B (en) 2020-08-13 2020-08-13 Power flow type big data based rework and production monitoring method and system and readable medium

Country Status (1)

Country Link
CN (1) CN111680938B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112116396A (en) * 2020-09-25 2020-12-22 国网上海市电力公司 Power big data-based re-work and re-production monitoring method and system
CN112327775A (en) * 2020-11-10 2021-02-05 夏洋 Enterprise re-work and re-production degree monitoring system and method based on artificial intelligence
CN113935568A (en) * 2021-08-30 2022-01-14 国网江苏省电力有限公司物资分公司 Auxiliary decision-making method for making purchasing strategy in productivity recovery stage

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105260803B (en) * 2015-11-06 2019-04-19 国家电网公司 A kind of system power consumption prediction technique
CN107122864A (en) * 2017-04-28 2017-09-01 国网山东省电力公司泰安供电公司 Power consumer requirement analysis method and device
CN108959424B (en) * 2018-06-11 2021-08-20 长春电力设计有限公司 Operation method of urban electricity utilization map for monitoring load of power system
CN110084398A (en) * 2019-03-15 2019-08-02 国网上海市电力公司 A kind of Industrial Cycle self-adapting detecting method based on enterprise's electric power big data
CN110415140A (en) * 2019-07-31 2019-11-05 国网河南省电力公司经济技术研究院 A kind of annual power consumption prediction method based on industrial production person's producer price index

Also Published As

Publication number Publication date
CN111680938A (en) 2020-09-18

Similar Documents

Publication Publication Date Title
CN111680938B (en) Power flow type big data based rework and production monitoring method and system and readable medium
Hajdu et al. Sensitivity analysis in PERT networks: Does activity duration distribution matter?
CN107301570B (en) Traffic prediction method, abnormal traffic detection device and electronic equipment
CN107610021A (en) The comprehensive analysis method of environmental variance spatial and temporal distributions
CN106529704A (en) Monthly maximum power load forecasting method and apparatus
CN112734392B (en) BIM engineering project cost rapid calculation system and method
CN109886461A (en) A kind of Runoff Forecast method and device
CN110084439A (en) A kind of software cost measure and cloud system based on the estimation of NESMA function point
CN110991985A (en) Project progress data processing method
CN112288594A (en) Data quality transaction processing method and system based on real-time event triggering
CN117469603B (en) Multi-water-plant water supply system pressure optimal control method based on big data learning
Lebo et al. Contribution of river phosphate variations to apparent reactivity estimated from phosphate-salinity diagrams
CN109345021A (en) A method of using LSTM modeling and forecasting labour demand increment
CN112241512A (en) Method and system for improving audit precision
CN104809647A (en) Volatility index compiling method
Ansari et al. HistoRIA: A new tool for simulation input analysis
Henrich* et al. Reducing feedback requirements of workload control
CN110717244B (en) Data trust analysis computer simulation method based on average deviation algorithm
CN107862476A (en) A kind of metering table demand computational methods based on data analysis
Tokede et al. Perceptions of fuzzy set theory in construction risk analysis
Drobek et al. Parameter estimation and equation formulation in Business Dynamics
CN112381436B (en) Time-by-time electric load generation method and device, electronic equipment and storage medium
JP5600665B2 (en) Design man-hour estimation device and design man-hour estimation program
Jordan et al. Exploring meaningful visual effects and quantities of interest from dynamic models through dynamac
Lindsey et al. Fast, Accurate, Easy-Pick 3: Using monthly production ensembles for EUR estimation

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