A data analysis cloud platform for Internet devices

Abstract

The present invention relates to the field of data analysis technology, and specifically discloses a data analysis cloud platform for Internet devices, including: an acquisition module: dividing a monitoring cycle into n fault cycles of the same length, counting the number of equipment failures in each fault cycle, and determining the time interval between each fault occurrence and the adjacent last maintenance, and determining the maintenance time of each fault; an analysis module: calculating a correction value for the number of faults; calculating a time ratio, and obtaining the maximum value thereof, obtaining a curve of the maximum value changing with time, and obtaining a determination ratio; a correction module: calculating a maintenance cycle correction coefficient, and determining the time of the next maintenance according to the maintenance cycle correction coefficient and the initially set maintenance cycle. The present invention can dynamically adjust the length of the maintenance cycle, improve the reliability of equipment operation, and reduce downtime caused by failures.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a data analysis cloud platform for Internet devices. Background Art

[0002] The Internet, also known as the international network, refers to a huge network of networks connected in series. These networks are connected by a set of common protocols to form a logically single huge international network. Usually, the Internet refers to the Internet in general, while the Internet specifically refers to the Internet. This method of connecting computer networks to each other can be called "network interconnection". On this basis, a global Internet network covering the whole world is called the Internet, that is, a network structure connected to each other.

[0003] In the prior art, in order to ensure the normal use of equipment, real-time monitoring of certain parameters of the equipment is usually adopted, and maintenance is carried out when an abnormality occurs. However, at this time, the equipment has already become abnormal, and there is a certain lag in repairing it. Usually, a method of repairing the equipment at a fixed period can solve this problem. However, in this case, the number of devices that need to be repaired will be relatively large, requiring a large amount of manpower and material resources, and taking a long time, and the efficiency of the maintenance is low. Summary of the invention

[0004] The purpose of the present invention is to provide a data analysis cloud platform for Internet devices to solve the above technical problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A data analysis cloud platform for Internet devices, comprising:

[0007] Acquisition module: set a monitoring cycle T, divide the monitoring cycle into n fault cycles t of the same length, where n is a preset value, count the number of equipment failures in each fault cycle, and determine the time interval Δt between each fault occurrence and the adjacent last maintenance, and determine the maintenance time of each fault, where the maintenance time is the length of time the equipment cannot be used due to the fault;

[0008] Analysis module: Calculate the fault number correction value through the formula, the formula is: Wherein αi represents the preset number correction coefficient, Gi represents the number of equipment failures in the i-th failure cycle, and α1<α2<…<αi<…<αn;

[0009] Calculate the time ratio Bij=Tij / t, where Tij represents the repair time of the jth fault of the equipment within the i-th fault cycle, and generate a ratio set SETi=(Bi1, Bi2, Bi2, ...), and obtain the maximum value Bi'=max(SETi), generate corresponding data points in the coordinate system, and fit them. The fitting formula is f(t), and a curve of the maximum value changing with time is obtained, and the current time is substituted into the curve of the maximum value changing with time to obtain the judgment ratio Bcur';

[0010] Correction module: calculates the maintenance cycle correction coefficient K, and determines the time of the next maintenance according to the maintenance cycle correction coefficient and the initially set maintenance cycle Tini.

[0011] As a further solution of the present invention: in the acquisition module, when a device has been in use for a time period less than a preset usage time threshold, subsequent steps will not be performed on the device, and the device will be inspected when the time interval from the last inspection is Tini.

[0012] As a further solution of the present invention: in the analysis module, another calculation method of the determination ratio specifically includes:

[0013] Calculate the ratio of the maintenance time to the fault cycle as the pending ratio, Ci represents the pending ratio corresponding to the i-th fault cycle, and generate a pending set CJH = (C1, C2, C3, ...);

[0014] Calculate the mean value C' of the pending proportions, set a value range of [C'-ΔC, C'+ΔC], where ΔC represents a preset mean correction value, and determine a ratio E of the pending proportions within the value range to all the pending proportions;

[0015] When the ratio E is less than or equal to the preset ratio threshold E', let ΔC = ΔC + ΔC', where ΔC' represents the preset mean correction constant, and repeat the above steps until the ratio E>E', and calculate the mean of the undetermined ratio within the value range at this time as the determination ratio.

[0016] As a further solution of the present invention: in the correction module, the process of determining the time of the next maintenance specifically includes:

[0017] Calculate the maintenance cycle correction factor K, the calculation formula is:

[0018]

[0019] Wherein, Cfre represents the number of times the time interval Δt is less than or equal to the preset time interval threshold, and μ represents a preset correction constant;

[0020] Calculate the maintenance interval Tint = K*Tini, and perform maintenance on the equipment when the time interval from the last maintenance is Tint.

[0021] As a further solution of the present invention: setting a maintenance interval range [Tmin, Tmax], when the maintenance interval Tint ≤ Tmin, sending an early warning message to remind the staff;

[0022] When the maintenance interval Tint≥Tmax, let the maintenance interval Tint=Tmax.

[0023] As a further solution of the present invention: the total number of equipment failures within the monitoring period is obtained, and when it is greater than a preset number threshold, the minimum value of the maintenance interval is obtained as the maintenance interval corresponding to the equipment.

[0024] As a further solution of the present invention: Another method for determining the maintenance interval specifically includes:

[0025] The time interval between two adjacent faults is obtained, the scale parameter λ and shape parameter β of the Weibull distribution are determined by the maximum likelihood estimation (MLE), the confidence level P is set, and the maintenance interval is determined based on the cumulative distribution function.

[0026] As a further solution of the present invention: the cumulative distribution function is:

[0027]

[0028] Beneficial effects of the present invention: In the present invention, firstly, a monitoring cycle is set, and a fault cycle is determined according to the monitoring cycle, and relevant data such as the number of faults in the fault cycle are collected. It can be understood that the time point at which the monitoring cycle ends is the time point of the last maintenance adjacent to the current time, and the collected data is the basis for subsequent analysis and processing; then the fault number correction value is determined, and it is worth noting that the reason why the correction coefficient is larger as it is closer to the current time is to ensure that the proportion of the fault cycle close to the current time in the final correction value of the number of faults is larger, which helps to more accurately reflect the state of the current equipment, thereby formulating a more reasonable maintenance plan; then, according to the maximum value in the time ratio, fitting is performed to obtain a curve of the maximum value changing with time, and the current time is substituted into the curve to obtain the determination ratio; it is worth noting that the time ratio is used to quantitatively measure the severity of the equipment failure. The more serious the failure, the more time should be spent on maintenance, and vice versa, the lighter the failure, the shorter the time spent on maintenance; it should be noted that one maximum value corresponds to one fault cycle; finally, the maintenance cycle correction coefficient is calculated, and the maintenance cycle initially set is corrected. The present invention can dynamically adjust the length of the maintenance cycle, improve the reliability of equipment operation and reduce the downtime caused by failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The present invention will be further described below in conjunction with the accompanying drawings.

[0030] Figure 1 It is a flow chart of a data analysis cloud platform for Internet devices according to the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] See also Figure 1 As shown, the present invention is a data analysis cloud platform for Internet devices, comprising:

[0033] Acquisition module: set a monitoring cycle T, divide the monitoring cycle into n fault cycles t of the same length, where n is a preset value, count the number of equipment failures in each fault cycle, and determine the time interval Δt between each fault occurrence and the adjacent last maintenance, and determine the maintenance time of each fault, where the maintenance time is the length of time the equipment cannot be used due to the fault;

[0034] Analysis module: Calculate the fault number correction value through the formula, the formula is: Wherein αi represents the preset number correction coefficient, Gi represents the number of equipment failures in the i-th failure cycle, and α1<α2<…<αi<…<αn;

[0035] Calculate the time ratio Bij=Tij / t, where Tij represents the repair time of the jth fault of the equipment within the i-th fault cycle, and generate a ratio set SETi=(Bi1, Bi2, Bi2, ...), and obtain the maximum value Bi'=max(SETi), generate corresponding data points in the coordinate system, and fit them. The fitting formula is f(t), and a curve of the maximum value changing with time is obtained, and the current time is substituted into the curve of the maximum value changing with time to obtain the judgment ratio Bcur';

[0036] Correction module: calculates the maintenance cycle correction coefficient K, and determines the time of the next maintenance according to the maintenance cycle correction coefficient and the initially set maintenance cycle Tini.

[0037] It should be noted that, first, the monitoring cycle is set, and the fault cycle is determined according to the monitoring cycle, and relevant data such as the number of faults in the fault cycle are collected. It can be understood that the time point at which the monitoring cycle ends is the time point of the last maintenance adjacent to the current time, and the collected data is the basis for subsequent analysis and processing; then the correction value of the number of faults is determined. It is worth noting that the reason why the correction coefficient is larger as it is closer to the current time is to ensure that the proportion of the fault cycle close to the current time in the final correction value of the number of faults is larger, which helps to more accurately reflect the current status of the equipment and thus formulate a more reasonable maintenance plan; then, the maximum value in the time ratio is determined and fitted to obtain a curve of the maximum value changing with time, and the current time is substituted into the curve to obtain the judgment ratio; it is worth noting that the time ratio is used to quantitatively measure the severity of the equipment failure. The more serious the failure, the more time should be spent on maintenance, and vice versa. The lighter the failure, the shorter the time spent on maintenance; it should be noted that one maximum value corresponds to one fault cycle; finally, the maintenance cycle correction coefficient is calculated, and the initially set maintenance cycle is corrected.

[0038] In another preferred implementation of the present invention, in the acquisition module, when a device has been in use for a time period less than a preset usage time threshold, subsequent steps are not performed on the device, and the device is inspected when the time interval from the last inspection is Tini.

[0039] It is worth noting that when the equipment has been in use for a short time, the collected fault data may not be sufficient to reflect the actual operating status of the equipment. Fault data in a short period of time may be accidental and uncertain, avoiding the unreliability of subsequent analysis results due to insufficient or inaccurate data. By ignoring data with insufficient use time, it can ensure that the data based on the analysis is more representative and accurate. At the same time, for newly put into use and short-term running equipment, immediately carrying out subsequent steps (such as detailed fault analysis and frequent maintenance) may lead to a waste of resources.

[0040] In another preferred implementation of the present invention, in the analysis module, another calculation method of the determination ratio specifically includes:

[0041] Calculate the ratio of the maintenance time to the fault cycle as the pending ratio, Ci represents the pending ratio corresponding to the i-th fault cycle, and generate a pending set CJH = (C1, C2, C3, ...);

[0042] Calculate the mean value C' of the pending proportions, set a value range of [C'-ΔC, C'+ΔC], where ΔC represents a preset mean correction value, and determine a ratio E of the pending proportions within the value range to all the pending proportions;

[0043] When the ratio E is less than or equal to the preset ratio threshold E', let ΔC = ΔC + ΔC', where ΔC' represents the preset mean correction constant, and repeat the above steps until the ratio E>E', and calculate the mean of the undetermined ratio within the value range at this time as the determination ratio.

[0044] It can be understood that determining the proportion of maintenance time in the overall time in each fault cycle provides basic data for subsequent analysis. By calculating the mean, a central value that can represent all pending proportions is obtained, which is used to set the value range and dynamically adjust the value range to ensure that the final judgment ratio can accurately reflect the reasonable proportion of maintenance time in the fault cycle, thereby improving the representativeness of the data and the reliability of the judgment ratio.

[0045] In another preferred implementation of the present invention, in the correction module, the process of determining the time of the next maintenance specifically includes:

[0046] Calculate the maintenance cycle correction factor K, the calculation formula is:

[0047]

[0048] Wherein, Cfre represents the number of times the time interval Δt is less than or equal to the preset time interval threshold, and μ represents a preset correction constant;

[0049] Calculate the maintenance interval Tint = K*Tini, and perform maintenance on the equipment when the time interval from the last maintenance is Tint.

[0050] In another preferred implementation of the present invention, a maintenance interval range [Tmin, Tmax] is set, and when the maintenance interval Tint≤Tmin, an early warning message is sent to remind the staff;

[0051] When the maintenance interval Tint≥Tmax, let the maintenance interval Tint=Tmax.

[0052] It should be noted that when Tint≤Tmin, it indicates that the equipment may not be suitable for continued use, so the staff is reminded; when the maintenance interval Tint≥Tmax, it means that the time for the next maintenance of the equipment is too long, and the equipment may be abnormal due to the long period of no maintenance.

[0053] In another preferred implementation of the present invention, the total number of equipment failures within the monitoring period is obtained, and when it is greater than a preset number threshold, the minimum value of the maintenance interval is obtained as the maintenance interval corresponding to the equipment.

[0054] It is understandable that when the failure frequency of equipment increases significantly, it means that its operating status may have deteriorated and more frequent maintenance is required to ensure safety. By shortening the maintenance cycle, potential problems can be discovered and resolved in a timely manner to prevent equipment failures from further deteriorating.

[0055] In another preferred implementation of the present invention, another method for determining the maintenance interval specifically includes:

[0056] The time interval between two adjacent faults is obtained, the scale parameter λ and shape parameter β of the Weibull distribution are determined by the maximum likelihood estimation (MLE), the confidence level P is set, and the maintenance interval is determined based on the cumulative distribution function.

[0057] In another preferred implementation of the present invention, the cumulative distribution function is:

[0058]

[0059] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A data analysis cloud platform for Internet devices, characterized in that: include: Acquisition module: set monitoring cycle T, divide the monitoring cycle into n fault cycles of equal length, n is a preset value, count the number of equipment failures in each fault cycle, and determine the time interval Δt between each fault occurrence and the adjacent last maintenance, and determine the maintenance time of each fault, the maintenance time is the length of time the equipment cannot be used due to the fault; Analysis module: Calculate the fault number correction value through the formula, the formula is: Wherein αi represents the preset number correction coefficient, Gi represents the number of equipment failures in the i-th failure cycle, and α1<α2<…<αi<…<αn; Calculate the ratio of the maintenance time to the fault cycle as the pending ratio, Ci represents the pending ratio corresponding to the i-th fault cycle, and generate a pending set CJH = (C1, C2, C3, ...); Calculate the mean value C' of the pending proportions, set a value range of [C'-ΔC, C'+ΔC], where ΔC represents a preset mean correction value, and determine a ratio E of the pending proportions within the value range to all the pending proportions; When the ratio E is less than or equal to the preset ratio threshold E', let ΔC = ΔC + ΔC', where ΔC' represents the preset mean correction constant, and repeat the above steps until the ratio E>E', and calculate the mean of the undetermined ratio within the value range at this time as the determination ratio Bcur; Correction module: calculates the maintenance cycle correction coefficient K, and determines the time of the next maintenance according to the maintenance cycle correction coefficient and the initially set maintenance cycle Tini; The process of determining the next maintenance time includes: Calculate the maintenance cycle correction factor K, the calculation formula is: Wherein, Cfre represents the number of times the time interval Δt is less than or equal to the preset time interval threshold, and μ represents a preset correction constant; Calculate the maintenance interval Tint = K*Tini, and perform maintenance on the equipment when the time interval from the last maintenance is Tint.

2. A data analysis cloud platform for Internet devices according to claim 1, characterized in that: In the acquisition module, when a device has been in use for less than a preset usage time threshold, no subsequent steps are performed on the device, and the device is repaired when the time interval from the last maintenance is Tini.

3. A data analysis cloud platform for Internet devices according to claim 1, characterized in that: Set the maintenance interval range [Tmin, Tmax], and when the maintenance interval Tint≤Tmin, send an early warning message to remind the staff; When the maintenance interval Tint≥Tmax, let the maintenance interval Tint=Tmax.

4. A data analysis cloud platform for Internet devices according to claim 1, characterized in that: The total number of equipment failures within the monitoring period is obtained, and when it is greater than a preset number threshold, the minimum value of the maintenance interval is obtained as the maintenance interval corresponding to the equipment.

Images