[go: up one dir, main page]

CN112070264B - Big data-based equipment predictive maintenance method - Google Patents

Big data-based equipment predictive maintenance method Download PDF

Info

Publication number
CN112070264B
CN112070264B CN202010719765.6A CN202010719765A CN112070264B CN 112070264 B CN112070264 B CN 112070264B CN 202010719765 A CN202010719765 A CN 202010719765A CN 112070264 B CN112070264 B CN 112070264B
Authority
CN
China
Prior art keywords
equipment
day
working state
historical
subsequent
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
CN202010719765.6A
Other languages
Chinese (zh)
Other versions
CN112070264A (en
Inventor
李源林
蒋明川
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.)
Huasong Technology Group Co.,Ltd.
Original Assignee
Shanghai Hoosun Intelligent Technology 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 Shanghai Hoosun Intelligent Technology Co ltd filed Critical Shanghai Hoosun Intelligent Technology Co ltd
Priority to CN202010719765.6A priority Critical patent/CN112070264B/en
Publication of CN112070264A publication Critical patent/CN112070264A/en
Application granted granted Critical
Publication of CN112070264B publication Critical patent/CN112070264B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • 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
    • G06Q10/20Administration of product repair or maintenance

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Theoretical Computer Science (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The invention discloses a big data-based equipment predictive maintenance method, which comprises the following steps: acquiring historical working state information corresponding to equipment to be maintained in historical duration; according to the obtained historical working state information, big data analysis is carried out, and a daily fault loss value corresponding to the equipment is obtained through calculation; predicting the subsequent working state of the equipment according to the daily fault loss value obtained by calculation; the purpose of performing predictive maintenance on the equipment is achieved by analyzing the big data related to the equipment, and the intelligence of equipment maintenance is improved; further, the service life of the equipment and the operation efficiency of the equipment are improved to a certain extent.

Description

Big data-based equipment predictive maintenance method
Technical Field
The invention relates to the technical field of data processing, in particular to a big data-based equipment predictive maintenance method.
Background
With the continuous development and improvement of big data processing technology and the analysis of big data, more objective and comprehensive reference basis can be provided for people more and more, therefore, a good idea is provided for the predictive maintenance of equipment based on big data.
In the prior art, when equipment is maintained, maintenance operations such as daily monitoring, maintenance and calibration of the equipment according to a certain period are usually performed, and subsequent working conditions and operating states of the equipment cannot be objectively predicted according to the current working conditions and specific operating states of the equipment, and the equipment can be monitored to have failed usually when the equipment runs under overload for a certain time and fails. Therefore, how to perform predictive maintenance on equipment by using big data is one of the problems to be solved urgently at present.
Disclosure of Invention
The invention provides a device predictive maintenance method based on big data, aiming at objectively and intelligently performing predictive maintenance on a device by analyzing the big data related to the device.
The invention provides a big data-based equipment predictive maintenance method, which comprises the following steps:
acquiring historical working state information corresponding to equipment to be maintained in historical duration; wherein the historical operating state information includes: the total historical running time of the equipment running in the historical time length and the task completion quantity of the equipment on the historical day corresponding to each day in the historical time length respectively;
according to the obtained historical working state information, big data analysis is carried out, and a daily fault loss value corresponding to the equipment is obtained through calculation;
predicting the subsequent working state of the equipment according to the daily fault loss value obtained by calculation; wherein the subsequent operating state of the device comprises: and when the current time is up, the current running total time of the equipment and the current task completion amount of the equipment each day are obtained.
Further, the predicting the subsequent working state of the equipment according to the daily fault loss value obtained by calculation further comprises the following steps:
and judging whether the subsequent working state of the equipment exceeds the self load of the equipment or not according to the prediction result, and maintaining the equipment according to the judgment result.
Further, the obtaining of the historical operating state information corresponding to the device to be maintained within the historical duration includes:
and acquiring historical working state information which is recorded by the equipment and/or monitored by the system and contains the running time of the equipment every day and the task completion amount of the equipment every day and corresponds to each day according to the equipment ID of the equipment to be maintained.
Further, the analyzing big data according to the acquired historical working state information, and calculating to obtain a daily fault loss value corresponding to the device includes:
according to the acquired historical working state information, analyzing the historical working state information corresponding to the equipment by using big data through a mathematical expression (1), and calculating to obtain a daily fault loss value X corresponding to the equipment, wherein the daily fault loss value X comprises the following steps:
Figure GDA0003124610590000021
in the mathematical expression (1), X represents a daily fault loss value corresponding to the equipment, and tiRepresenting the total operation time corresponding to the ith day in the historical working state information corresponding to the equipment; giRepresenting the task amount finished on the ith day in the historical working state information corresponding to the equipment; n represents the total days contained in the historical duration in the historical working state information corresponding to the equipment.
Further, the predicting the subsequent operating state of the device according to the calculated daily fault loss value includes:
acquiring the current-day operation working state corresponding to the equipment and containing the current-day operation total time and the current-day task completion amount;
and calculating the total time length of the next day of operation and the task amount of the next day of completion corresponding to the subsequent working state of the equipment according to the daily fault loss value obtained by calculation and by combining the obtained current day of operation working state.
Further, the calculating, according to the daily fault loss value obtained by calculation and in combination with the acquired current-day operating state, a total operable time on the second day and a task amount that can be completed on the second day corresponding to the subsequent operating state of the device includes:
according to the daily fault loss value X calculated by using the mathematical expression (1), and in combination with the operation state on the same day, calculating the total operable time length on the next day corresponding to the subsequent operation state of the equipment by using the mathematical expression (2), then:
Figure GDA0003124610590000031
in the mathematical expression (2), t represents the total operable time of the equipment on the next day corresponding to the prediction of the equipment; t is ttRepresenting the total operation time of the current day in the operation working state of the current day corresponding to the equipment on the prediction current day; x represents the daily fault loss corresponding to the equipmentA consumption value;
meanwhile, calculating the task amount which can be completed in the next day corresponding to the subsequent working state of the equipment by using a mathematical expression (3), and then:
Figure GDA0003124610590000041
in the mathematical expression (3), g represents the task amount which can be completed by the equipment on the next day when the equipment is predicted; gtIndicating the task completion amount of the current day in the current day running working state corresponding to the equipment on the current day; x represents the daily fault loss value corresponding to the equipment.
Further, the determining, according to the prediction result, whether the subsequent operating state of the device will exceed the load of the device itself includes:
calculating an overload early warning value P corresponding to the subsequent working state of the equipment by using a mathematical expression (4) according to the total operable time of the equipment on the second day and the task amount which can be completed on the second day and is obtained by using the mathematical expression (2) and the mathematical expression (3), wherein the following steps are as follows:
Figure GDA0003124610590000042
in the mathematical expression (4), P represents an overload early warning value corresponding to the equipment; t is t0Representing the total length of time that a completely new device, identical to the device, may operate on the day for which the device is predicted; g0Representing the task amount which can be completed by the brand-new equipment on the same day; u 2]Denotes a step function, i.e., when the value in the parentheses is greater than or equal to 0, u [ 2 ]]The function value is 1, and when the value in the parentheses is less than 0, u [ 2 ]]The function value is 0; x represents the daily fault loss value corresponding to the equipment;
and judging whether the subsequent working state of the equipment exceeds the self load of the equipment or not according to the value of the overload early warning value P.
Further, the determining whether the subsequent working state of the device will exceed the self-load of the device according to the value of the overload warning value P includes:
if the overload early warning value P is less than or equal to 0, judging that the subsequent working state of the equipment does not exceed the self load of the equipment;
and if the overload early warning value P is larger than 0, judging that the subsequent working state of the equipment exceeds the self load of the equipment.
Further, the maintaining the device according to the judgment result includes:
if the judgment result is that: if the subsequent working state of the equipment exceeds the self load of the equipment, calculating the reduction amount corresponding to the subsequent working state of the equipment according to the overload early warning value P, the total time length of the next day of operation corresponding to the subsequent working state of the equipment and the task amount which can be completed on the second day;
and according to the calculated reduction amount, reducing the corresponding workload of the equipment so that the equipment can execute corresponding work based on the task after the reduction amount.
Further, the calculating a reduction amount corresponding to the subsequent working state of the device according to the overload warning value P, the total time length of the next day of operation corresponding to the subsequent working state of the device, and the task amount completed on the next day includes:
calculating the time length reduction amount delta t of the total time length which can be operated on the second day corresponding to the subsequent working state of the equipment by using a mathematical expression (5) according to the overload early warning value P and the total time length which can be operated on the second day corresponding to the subsequent working state of the equipment, and then:
Figure GDA0003124610590000051
in the mathematical expression (5), Δ t represents a time length reduction amount of the next day operational time length corresponding to the subsequent working state of the equipment; δ () represents a unit impact function, that is, when the value in parentheses is 0, the δ () function value is 1, and when the value in parentheses is not 0, the δ () function value is 0; t represents the next day operable time length corresponding to the subsequent working state of the equipment; p represents an overload early warning value corresponding to the equipment; u () represents a step function, that is, when a value in parentheses is greater than or equal to 0, the value of the u () function is 1, and when the value in parentheses is less than 0, the value of the u () function is 0;
meanwhile, by using a mathematical expression (6), calculating and obtaining a task reduction amount Δ g of the task amount which can be completed in the next day corresponding to the subsequent working state of the equipment, then:
Figure GDA0003124610590000061
in the mathematical expression (6), Δ g represents a task reduction amount of the task amount that can be completed on the next day corresponding to the subsequent working state of the equipment; u () represents a step function, that is, when a value in parentheses is greater than or equal to 0, the value of the u () function is 1, and when the value in parentheses is less than 0, the value of the u () function is 0; p represents an overload early warning value corresponding to the equipment; δ () represents a unit impact function, that is, when the value in parentheses is 0, the δ () function value is 1, and when the value in parentheses is not 0, the δ () function value is 0; g represents the task amount which can be completed on the next day corresponding to the subsequent working state of the equipment.
The invention relates to a big data-based equipment predictive maintenance method, which comprises the steps of obtaining historical working state information corresponding to equipment to be maintained in historical duration; according to the obtained historical working state information, big data analysis is carried out, and a daily fault loss value corresponding to the equipment is obtained through calculation; predicting the subsequent working state of the equipment according to the daily fault loss value obtained by calculation; the purpose of performing predictive maintenance on the equipment is achieved by analyzing the big data related to the equipment, and the intelligence of equipment maintenance is improved; further, the service life of the equipment and the operation efficiency of the equipment are improved to a certain extent.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described below by means of the accompanying drawings and examples.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart diagram of an embodiment of the big data-based equipment predictive maintenance method of the present invention.
Fig. 2 is a schematic flow chart of an implementation manner of step S30 in the embodiment of fig. 1 in the method for predictive maintenance of big data-based devices according to the present invention.
FIG. 3 is a flow chart of another embodiment of the predictive maintenance method for big data based devices according to the present invention.
Fig. 4 is a schematic flow chart of an implementation manner of maintaining the device according to the overload determination result in step S40 in the embodiment of fig. 3 in the big data based device predictive maintenance method of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The invention provides a big data-based equipment predictive maintenance method, which objectively and intelligently predicts the subsequent working state of equipment by analyzing the big data related to the equipment and performs predictive maintenance on the equipment based on prediction information.
FIG. 1 is a flow chart of an embodiment of the predictive maintenance method for big data based device according to the present invention; a big data-based device predictive maintenance method of the present invention may be implemented as steps S10-S30 as described below.
And step S10, acquiring historical working state information corresponding to the equipment to be maintained in historical duration.
In the embodiment of the invention, aiming at equipment to be maintained, a system acquires historical working state information corresponding to the equipment in historical duration; the historical working state information can be recorded by the equipment according to the running state of the equipment; or the system can record and store the operation state of the equipment according to the monitoring of the operation state of the equipment.
The system obtains the historical operating state information corresponding to the device in the historical duration, including but not limited to: the total historical running time of the equipment running in the historical time length and the task completion quantity of the equipment on the historical day corresponding to each day in the historical time length respectively. Aiming at the historical current task completion quantity, because different types of equipment have different work tasks to be executed by the equipment, the task completion quantity of the equipment also corresponds to different calculation and acquisition modes; in the embodiment of the present invention, the system may calculate and obtain the task completion amount of the device on the corresponding day in one day according to different types of devices, different tasks that need to be executed by the same type of devices, and other specific application scenarios.
Further, in an embodiment, when obtaining the historical operating state information corresponding to the device to be maintained within the historical duration, the following technical means may also be implemented:
and acquiring the equipment ID of the equipment to be maintained, and acquiring historical working state information which is recorded by the equipment and/or is recorded by a system monitor and contains the running time of the equipment every day and the task completion amount of the equipment on the same day and corresponds to each day respectively according to the equipment ID of the equipment to be maintained.
And step S20, according to the acquired historical working state information, performing big data analysis, and calculating to obtain a daily fault loss value corresponding to the equipment.
And calculating the daily fault loss value corresponding to the equipment by utilizing a big data analysis mode according to the acquired historical working state information of the equipment.
In the embodiment of the invention, the daily fault loss value corresponding to the equipment can be calculated according to the total historical operating time in the historical operating state information of the equipment and the task completion amount of the equipment on the historical day corresponding to each day in the historical time. For example, regarding the device, the historical total operating time and the historical current task completion amount corresponding to the device are used as calculation parameters, and for the calculation parameters, the loss weights corresponding to the calculation parameters are respectively set, so that the daily fault loss value of the device is calculated according to the calculation parameters and the loss weights corresponding to the calculation parameters.
And step S30, predicting the subsequent working state of the equipment according to the daily fault loss value obtained by calculation.
And predicting possible working state information of the equipment in the subsequent working according to the daily fault loss value obtained by calculation. For example, in one embodiment, the second day corresponding to the current day of the prediction by the device is predicted, the possible working time of the device on the second day and the possible task amount completed on the second day are predicted, and whether the normal load of the device is exceeded or not is comprehensively determined according to the possible working time of the device on the second day and the possible task amount completed on the second day.
In the embodiment of the present invention, the subsequent operating state of the device includes, but is not limited to: and when the current time is up, the current running total time of the equipment and the current task completion amount of the equipment each day are obtained.
The invention relates to a big data-based equipment predictive maintenance method, which comprises the steps of obtaining historical working state information corresponding to equipment to be maintained in historical duration; according to the obtained historical working state information, big data analysis is carried out, and a daily fault loss value corresponding to the equipment is obtained through calculation; predicting the subsequent working state of the equipment according to the daily fault loss value obtained by calculation; the purpose of performing predictive maintenance on the equipment is achieved by analyzing the big data related to the equipment, and the intelligence of equipment maintenance is improved; further, the service life of the equipment and the operation efficiency of the equipment are improved to a certain extent.
Further, in an embodiment, regarding "step S20, performing big data analysis according to the obtained historical operating state information, and calculating a daily fault loss value corresponding to the device" in the embodiment of fig. 1, the method may also be implemented according to the following technical means:
according to the acquired historical working state information, analyzing the historical working state information corresponding to the equipment by using big data through a mathematical expression (1), and calculating to obtain a daily fault loss value X corresponding to the equipment, wherein the daily fault loss value X comprises the following steps:
Figure GDA0003124610590000091
in the mathematical expression (1), X represents a daily fault loss value corresponding to the equipment, and tiRepresenting the total operation time corresponding to the ith day in the historical working state information corresponding to the equipment; giRepresenting the task amount finished on the ith day in the historical working state information corresponding to the equipment; n represents the total days contained in the historical duration in the historical working state information corresponding to the equipment.
And the daily fault loss value corresponding to the equipment is calculated by using a mathematical model, so that the evaluation accuracy of the daily fault loss of the equipment is improved.
Further, in an embodiment, as shown in fig. 2, fig. 2 is a flowchart illustrating an implementation manner of step S30 in the embodiment of fig. 1 in the big data based device predictive maintenance method of the present invention. In the embodiment of fig. 2, "step S30, predicting the subsequent operating state of the equipment according to the calculated daily fault loss value" in the embodiment of fig. 1 may be implemented as steps S31-S32 described below.
And step S31, obtaining the current-day operation working state corresponding to the equipment and containing the current-day operation total time and the current-day task completion amount.
In the embodiment of the present invention, when performing predictive maintenance on the device, it is necessary to simultaneously refer to the corresponding operating state information of the device in the last operating process, for example, the system refers to the current operating state information of the device corresponding to the current day of prediction. In one embodiment, the system obtains the current-day operation working state corresponding to the device and including the current-day operation total time and the current-day task completion amount.
And step S32, calculating the total operable time length on the next day and the task amount which can be completed on the next day corresponding to the subsequent working state of the equipment according to the daily fault loss value obtained by calculation and by combining the obtained operating state on the same day.
According to the calculation method in the embodiment, the system calculates the daily fault loss value of the equipment, meanwhile, the obtained current day running working state corresponding to the equipment and including the current day running total time and the current day task completion amount is referred to, the subsequent working state of the equipment corresponding to the next day adjacent to the current day is calculated, and the subsequent working state is used as a prediction basis and a reference for predicting the equipment. Wherein the subsequent working state corresponding to the second day includes but is not limited to: and in the next day adjacent to the current day, the equipment can run for the total time length on the corresponding second day and can complete the task amount on the second day.
Further, in an embodiment, in "step S32 in the embodiment of fig. 2, according to the calculated daily fault loss value, and in combination with the obtained operating state of the current day, calculating a total time length of the next day that the device may operate and a task amount that the next day may complete corresponding to the subsequent operating state" may be implemented according to the following technical means:
according to the daily fault loss value X calculated by using the mathematical expression (1), in combination with the current-day operation working state, such as the current-day operation total time and the current-day task completion amount, calculating the next-day operation total time corresponding to the subsequent working state of the equipment by using the mathematical expression (2), then:
Figure GDA0003124610590000111
in the mathematical expression (2), t represents the total operable time of the equipment on the next day corresponding to the prediction of the equipment; t is ttRepresenting the total operation time of the current day in the operation working state of the current day corresponding to the equipment on the prediction current day; x represents the daily fault loss value corresponding to the equipment;
meanwhile, calculating the task amount which can be completed in the next day corresponding to the subsequent working state of the equipment by using a mathematical expression (3), and then:
Figure GDA0003124610590000112
in the mathematical expression (3), g represents the task amount which can be completed by the equipment on the next day when the equipment is predicted; gtIndicating the task completion amount of the current day in the current day running working state corresponding to the equipment on the current day; x represents the daily fault loss value corresponding to the equipment.
In the embodiment of the invention, according to the daily fault loss value obtained by calculation and in combination with the acquired operation working state on the same day, the total operation time length on the next day and the task amount which can be completed on the next day corresponding to the subsequent working state of the equipment are calculated, so that the accuracy of predicting the subsequent working state of the equipment is improved; further, an important basis is provided for maintaining the equipment.
Further, in an embodiment, as shown in fig. 3, fig. 3 is a schematic flow chart of another implementation of the big data based device predictive maintenance method of the present invention. In the embodiment of fig. 3, after "step S30 of the embodiment of fig. 1, predicting the subsequent operating state of the equipment according to the calculated daily fault loss value", the method further includes step S40.
And step S40, judging whether the subsequent working state of the equipment exceeds the self load of the equipment according to the prediction result, and maintaining the equipment according to the judgment result.
In the embodiment of the present invention, after predicting the subsequent operating state of the device, according to the prediction result, for example, in the above embodiment, the total time length of the next day of operation and the task amount of the next day of operation, which are obtained by calculation and correspond to the subsequent operating state of the device, are calculated, and based on the quantized prediction result obtained by calculation, according to the subsequent operating state of the device, it can be determined whether the load of the device in the subsequent operating state exceeds the load of the device itself. If the load exceeds the self load, the working time and/or the task completion amount of the equipment need to be properly reduced so as to prevent the equipment from being excessively worn due to overload work and further possibly causing damage to the equipment.
Further, in an embodiment, in the step S40, determining whether the subsequent operating state of the device will exceed the self-load of the device according to the prediction result, may be implemented according to the following technical means:
calculating an overload early warning value P corresponding to the subsequent working state of the equipment by using a mathematical expression (4) according to the total operable time of the equipment on the second day and the task amount which can be completed on the second day and is obtained by using the mathematical expression (2) and the mathematical expression (3), wherein the following steps are as follows:
Figure GDA0003124610590000121
in the mathematical expression (4), P represents an overload early warning value corresponding to the equipment; t is t0Representing the total length of time that a completely new device, identical to the device, may operate on the day for which the device is predicted; g0Representing the task amount which can be completed by the brand-new equipment on the same day; u 2]Denotes a step function, i.e., when the value in the parentheses is greater than or equal to 0, u [ 2 ]]Function value of 1, when in parenthesesWhen the value of (d) is less than 0, u [, ]]The function value is 0; x represents the daily fault loss value corresponding to the equipment;
and judging whether the subsequent working state of the equipment exceeds the self load of the equipment or not according to the value of the overload early warning value P.
Further, in an embodiment, the determining, according to the value of the overload warning value P, whether the subsequent working state of the device will exceed the load of the device itself may be implemented as:
if the overload early warning value P is less than or equal to 0, judging that the subsequent working state of the equipment does not exceed the self load of the equipment; and if the overload early warning value P is larger than 0, judging that the subsequent working state of the equipment exceeds the self load of the equipment.
In the embodiment of the present invention, for a specific application scenario, when the overload early warning value P is greater than 0, specifically, when the overload early warning value P is 1, it is determined that only one parameter of the total time length of the next-day operable operation and the task amount of the next-day operable operation, which corresponds to the device, exceeds the load of the device; and when the value of the overload early warning value P is 2, judging that the two parameters of the total operable time of the next day and the task amount which can be completed on the next day corresponding to the equipment exceed the load of the equipment.
Further, based on the description of the above embodiments, in an embodiment, as shown in fig. 4, fig. 4 is a flowchart illustrating an implementation manner of maintaining the device according to the overload determination result in step S40 in the embodiment of fig. 3 in the big data based device predictive maintenance method of the present invention, fig. 4 is a flowchart illustrating a big data based device predictive maintenance method of the present invention. As shown in FIG. 4, the system performs maintenance on the device according to the overload determination result, which may be implemented as steps S41-S42 described below.
And step S41, calculating the reduction amount corresponding to the subsequent working state of the equipment according to the overload early warning value P, the total time length of the next day of operation corresponding to the subsequent working state of the equipment and the task amount completed on the next day.
And step S42, according to the calculated reduction amount, reducing the corresponding workload of the equipment so that the equipment can execute corresponding work based on the task after the reduction amount.
In the embodiment of the present invention, if the system determines that the device is a device: and if the subsequent working state of the equipment exceeds the self load of the equipment, the system calculates the specific reduction amount corresponding to the subsequent working state of the equipment, and performs task arrangement on the equipment according to the calculated reduction amount, so that the maintenance of the equipment is realized, and the equipment executes corresponding work based on the reduced task. The reduction amount in the embodiment of the present invention may determine, according to a specific value of the overload warning value P, the total time length that the device can be operated on the second day and the task amount that the device can complete on the second day, which is specific to which parameter is overloaded, and further reduce, according to a determination result, the total time length that the device can be operated on the second day and/or the task amount that the device can complete on the second day by using the reduction amount, so as to achieve the purpose of maintaining the device.
Further, in an embodiment, in "step S41, calculating a reduction amount corresponding to the subsequent operating state of the device according to the overload warning value P, the total time length of the next day of operation corresponding to the subsequent operating state of the device, and the task amount that can be completed on the second day" in the embodiment shown in fig. 4 may be implemented according to the following technical means:
calculating the time length reduction amount delta t of the total time length which can be operated on the second day corresponding to the subsequent working state of the equipment by using a mathematical expression (5) according to the overload early warning value P and the total time length which can be operated on the second day corresponding to the subsequent working state of the equipment, and then:
Figure GDA0003124610590000141
in the mathematical expression (5), Δ t represents a time length reduction amount of the next day operational time length corresponding to the subsequent working state of the equipment; δ () represents a unit impact function, that is, when the value in parentheses is 0, the δ () function value is 1, and when the value in parentheses is not 0, the δ () function value is 0; t represents the next day operable time length corresponding to the subsequent working state of the equipment; p represents an overload early warning value corresponding to the equipment; u () represents a step function, that is, when a value in parentheses is greater than or equal to 0, the value of the u () function is 1, and when the value in parentheses is less than 0, the value of the u () function is 0;
meanwhile, by using a mathematical expression (6), calculating and obtaining a task reduction amount Δ g of the task amount which can be completed in the next day corresponding to the subsequent working state of the equipment, then:
Figure GDA0003124610590000142
in the mathematical expression (6), Δ g represents a task reduction amount of the task amount that can be completed on the next day corresponding to the subsequent working state of the equipment; u () represents a step function, that is, when a value in parentheses is greater than or equal to 0, the value of the u () function is 1, and when the value in parentheses is less than 0, the value of the u () function is 0; p represents an overload early warning value corresponding to the equipment; δ () represents a unit impact function, that is, when the value in parentheses is 0, the δ () function value is 1, and when the value in parentheses is not 0, the δ () function value is 0; g represents the task amount which can be completed on the next day corresponding to the subsequent working state of the equipment.
According to the reduction calculated by the embodiment, the system performs predictive maintenance on the equipment, so that the accuracy and intelligence of equipment maintenance are improved, the flexibility of equipment maintenance is also improved, and the service life of the equipment is also prolonged to a certain extent.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (6)

1. A big-data-based predictive maintenance method for a device, the method comprising:
acquiring historical working state information corresponding to equipment to be maintained in historical duration; wherein the historical operating state information includes: the total historical running time of the equipment running in the historical time length and the task completion quantity of the equipment on the historical day corresponding to each day in the historical time length respectively;
according to the obtained historical working state information, big data analysis is carried out, and a daily fault loss value corresponding to the equipment is obtained through calculation;
predicting the subsequent working state of the equipment according to the daily fault loss value obtained by calculation; wherein the subsequent operating state of the device comprises: the current running total time of the equipment and the current task completion amount of the equipment each day corresponding to the current time are obtained;
the analyzing big data according to the acquired historical working state information, and calculating to obtain the daily fault loss value corresponding to the equipment comprises the following steps:
according to the acquired historical working state information, analyzing the historical working state information corresponding to the equipment by using big data through a mathematical expression (1), and calculating to obtain a daily fault loss value X corresponding to the equipment, wherein the daily fault loss value X comprises the following steps:
Figure FDA0003124610580000011
in the mathematical expression (1), X represents a daily fault loss value corresponding to the equipment, and tiRepresenting the total operation time corresponding to the ith day in the historical working state information corresponding to the equipment; giRepresenting the task amount finished on the ith day in the historical working state information corresponding to the equipment; n represents the total days contained in the historical duration in the historical working state information corresponding to the equipment;
predicting the subsequent working state of the equipment according to the daily fault loss value obtained by calculation, wherein the predicting comprises the following steps:
acquiring the current-day operation working state corresponding to the equipment and containing the current-day operation total time and the current-day task completion amount;
according to the daily fault loss value obtained through calculation, the total time length of the next day of operation and the task amount of the next day of completion corresponding to the subsequent working state of the equipment are calculated by combining the obtained current day of operation working state;
the calculating, according to the daily fault loss value obtained by calculation and in combination with the obtained current-day operating state, a total next-day operable time and a next-day task-completed amount corresponding to the subsequent operating state of the device includes:
according to the daily fault loss value X calculated by using the mathematical expression (1), and in combination with the operation state on the same day, calculating the total operable time length on the next day corresponding to the subsequent operation state of the equipment by using the mathematical expression (2), then:
Figure FDA0003124610580000021
in the mathematical expression (2), t represents the total operable time of the equipment on the next day corresponding to the prediction of the equipment; t is ttRepresenting the total operation time of the current day in the operation working state of the current day corresponding to the equipment on the prediction current day; x represents the daily fault loss value corresponding to the equipment;
meanwhile, calculating the task amount which can be completed in the next day corresponding to the subsequent working state of the equipment by using a mathematical expression (3), and then:
Figure FDA0003124610580000022
in the mathematical expression (3), g represents the task amount which can be completed by the equipment on the next day when the equipment is predicted; gtIndicating the task completion amount of the current day in the current day running working state corresponding to the equipment on the current day; x represents the daily fault loss value corresponding to the equipment.
2. The method for predictive maintenance of big data based equipment according to claim 1, wherein said predicting a subsequent operating state of said equipment based on said calculated daily fault loss value further comprises the steps of:
and judging whether the subsequent working state of the equipment exceeds the self load of the equipment or not according to the prediction result, and maintaining the equipment according to the judgment result.
3. The big data-based equipment predictive maintenance method according to claim 1 or 2, wherein the obtaining of the historical operating state information corresponding to the equipment to be maintained in the historical time period comprises:
and acquiring historical working state information which is recorded by the equipment and/or monitored by the system and contains the running time of the equipment every day and the task completion amount of the equipment every day and corresponds to each day according to the equipment ID of the equipment to be maintained.
4. The big-data-based predictive maintenance method for equipment according to claim 2, wherein said determining whether the subsequent operating status of the equipment will exceed the self-load of the equipment according to the prediction result comprises:
calculating an overload early warning value P corresponding to the subsequent working state of the equipment by using a mathematical expression (4) according to the total operable time of the equipment on the second day and the task amount which can be completed on the second day and is obtained by using the mathematical expression (2) and the mathematical expression (3), wherein the following steps are as follows:
Figure FDA0003124610580000031
in the mathematical expression (4), P represents an overload early warning value corresponding to the equipment; t is t0Representing the total length of time that a completely new device, identical to the device, may operate on the day for which the device is predicted; g0To representThe task amount that the brand-new device can complete on the same day; u 2]Denotes a step function, i.e., when the value in the parentheses is greater than or equal to 0, u [ 2 ]]The function value is 1, and when the value in the parentheses is less than 0, u [ 2 ]]The function value is 0; x represents the daily fault loss value corresponding to the equipment; t is tiRepresenting the total operation time corresponding to the ith day in the historical working state information corresponding to the equipment; giRepresenting the task amount finished on the ith day in the historical working state information corresponding to the equipment; n represents the total days contained in the historical duration in the historical working state information corresponding to the equipment;
and judging whether the subsequent working state of the equipment exceeds the self load of the equipment or not according to the value of the overload early warning value P.
5. The big-data-based predictive maintenance method for equipment according to claim 4, wherein the determining whether the subsequent operating state of the equipment will exceed the self-load of the equipment according to the value of the overload warning value P comprises:
if the overload early warning value P is less than or equal to 0, judging that the subsequent working state of the equipment does not exceed the self load of the equipment;
and if the overload early warning value P is larger than 0, judging that the subsequent working state of the equipment exceeds the self load of the equipment.
6. The predictive maintenance method for big data based device according to claim 5, wherein said maintaining said device according to the determination result comprises:
if the judgment result is that: if the subsequent working state of the equipment exceeds the self load of the equipment, calculating the reduction amount corresponding to the subsequent working state of the equipment according to the overload early warning value P, the total time length of the next day of operation corresponding to the subsequent working state of the equipment and the task amount which can be completed on the second day;
and according to the calculated reduction amount, reducing the corresponding workload of the equipment so that the equipment can execute corresponding work based on the task after the reduction amount.
CN202010719765.6A 2020-07-23 2020-07-23 Big data-based equipment predictive maintenance method Active CN112070264B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010719765.6A CN112070264B (en) 2020-07-23 2020-07-23 Big data-based equipment predictive maintenance method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010719765.6A CN112070264B (en) 2020-07-23 2020-07-23 Big data-based equipment predictive maintenance method

Publications (2)

Publication Number Publication Date
CN112070264A CN112070264A (en) 2020-12-11
CN112070264B true CN112070264B (en) 2021-08-17

Family

ID=73656660

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010719765.6A Active CN112070264B (en) 2020-07-23 2020-07-23 Big data-based equipment predictive maintenance method

Country Status (1)

Country Link
CN (1) CN112070264B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116681426B (en) * 2023-08-03 2023-10-27 山东港口科技集团烟台有限公司 Industrial Internet equipment predictive maintenance system and method

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109034413A (en) * 2018-07-11 2018-12-18 广东人励智能工程有限公司 Intelligence manufacture equipment fault prediction technique and system based on neural network model
CN109120451A (en) * 2018-08-31 2019-01-01 深圳市麦斯杰网络有限公司 Equipment evaluation method, equipment and computer readable storage medium based on Internet of Things

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB201621631D0 (en) * 2016-12-19 2017-02-01 Palantir Technologies Inc Predictive modelling

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109034413A (en) * 2018-07-11 2018-12-18 广东人励智能工程有限公司 Intelligence manufacture equipment fault prediction technique and system based on neural network model
CN109120451A (en) * 2018-08-31 2019-01-01 深圳市麦斯杰网络有限公司 Equipment evaluation method, equipment and computer readable storage medium based on Internet of Things

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
dafa童话的店.设备损耗的计算方法.《https://wenku.baidu.com/view/f73dbb8f68eae009581b6bd97f1922791688beab.html》.2020, *
设备损耗的计算方法;dafa童话的店;《https://wenku.baidu.com/view/f73dbb8f68eae009581b6bd97f1922791688beab.html》;20200412;全文 *

Also Published As

Publication number Publication date
CN112070264A (en) 2020-12-11

Similar Documents

Publication Publication Date Title
US9618993B2 (en) System and method for power management of mobile devices
US7107187B1 (en) Method for modeling system performance
CN113077172A (en) Equipment state trend analysis and fault diagnosis method
US20200225118A1 (en) Failure detection device for detecting an issue with a part of a machine
CN110119339A (en) Appraisal procedure, system, equipment and the storage medium of the health status of industrial equipment
JP6629815B2 (en) Life estimation device and machine learning device
US20230131828A1 (en) Predictive maintenance system and method for intelligent manufacturing equipment
CN111157245B (en) Supervision method and system for rail transit running gear bearing
CN113495547A (en) Real-time safe unmanned fault diagnosis and protection method and system
CN112181629A (en) Security inspection centralized image judging system and automatic working mode switching control method thereof
CN112070264B (en) Big data-based equipment predictive maintenance method
JP2009086896A (en) Failure prediction system and failure prediction method for computer
CN119444177A (en) A risk management system for equipment based on model predictive control
CN116579133A (en) Industrial robot life prediction system based on digital twin and operation and maintenance method thereof
CN119248527A (en) Information management system and method based on cloud computing and big data
CN113348473B (en) Management artificial intelligence module installation foundation
CN109740191B (en) Method, device and equipment for predicting residual service life of wind sensor
CN115701890A (en) Method for adjusting alarm rule and related equipment
CN119721380A (en) A fault analysis and prediction method and system for intelligent manufacturing equipment
CN117405968B (en) Equipment energy consumption detection method and system based on big data
US20030056156A1 (en) Method and apparatus for monitoring the activity of a system
CN113032239A (en) Risk prompting method and device, electronic equipment and storage medium
CN117852806A (en) MES energy efficiency optimization method and system based on nonlinear wear model
CN110956308A (en) Chemical equipment health state prediction method based on time sequence
CN113808727A (en) Equipment monitoring method and device, computer equipment and readable storage medium

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
CP01 Change in the name or title of a patent holder

Address after: Room b703-b706, 7th floor, building 1, 2816 Yixian Road, Baoshan District, Shanghai, 200940

Patentee after: Huasong Technology Group Co.,Ltd.

Address before: Room b703-b706, 7th floor, building 1, 2816 Yixian Road, Baoshan District, Shanghai, 200940

Patentee before: SHANGHAI HOOSUN INTELLIGENT TECHNOLOGY Co.,Ltd.

CP01 Change in the name or title of a patent holder