Intelligent equipment fault management system and method

Abstract

The invention discloses an intelligent equipment fault management system and method, relates to the technical field of fault diagnosis, and solves the technical problems that in fault management, it is difficult to screen out equipment which may have faults and positions and manage the equipment in advance, and it is neglected that fault probabilities of multiple excessive work equipment are superposed. The method comprises the following steps: acquiring similar equipment of current intelligent equipment, extracting fault information of the similar equipment, preprocessing the fault information to obtain a standard fault probability of each fault type, and calculating working time and the standard fault probability to obtain a fault factor of each fault type of the current intelligent equipment; judging based on the fault factor, sending a management instruction, and pre-managing the intelligent equipment based on the management instruction; according to the invention, intelligent monitoring and early warning of equipment faults can be realized, the downtime of the equipment is reduced, and the maintenance cost is reduced.

Description

Technical Field

[0001] The present invention belongs to the field of equipment fault management, relates to fault diagnosis technology, and specifically is an intelligent equipment fault management system and method. Background Art

[0002] With the rapid development of Internet of Things technology, smart devices are increasingly being used in various fields. From smart homes and industrial automation to healthcare and smart cities, smart devices have become an important part of modern life and production. These devices are usually highly intelligent and automated, and can complete complex tasks autonomously, but they also face a higher risk of failure. Traditional fault management is usually handled after the fact, that is, repairs are performed only after the failure occurs, which lacks foresight and initiative.

[0003] At present, the fault management systems of most intelligent devices find it difficult to screen out the devices and locations that may fail and manage them in advance, and it is difficult to intervene and manage the equipment before failure through prediction and prevention, which increases the losses caused by equipment failure. At the same time, the fault management systems of most intelligent devices ignore the fact that the devices that work overtime multiple times will have a superposition of failure probabilities, which leads to inaccurate analysis of the probability of failure, increases the system's misjudgment rate and troubleshooting costs.

[0004] Therefore, the present invention discloses a smart device fault management system and method for solving the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an intelligent device fault management system and method, which are used to solve the technical problems that it is difficult to screen out the equipment and locations that may fail and manage them in advance during fault management, and ignore the superposition of failure probabilities of equipment that has worked overtime for multiple times. The present invention obtains similar devices to the current intelligent device, extracts fault information of similar devices, pre-processes the fault information to obtain the standard fault probability of each fault type, calculates the working time and the standard fault probability to obtain the fault factor of each fault type of the current intelligent device; makes judgments based on the fault factors to issue management instructions, and pre-manages the intelligent device based on the management instructions to solve the above problems.

[0006] To achieve the above object, the first aspect of the present invention provides an intelligent device fault management system, comprising: an intelligent analysis module, and a data collection module, a fault management module and a database connected thereto;

[0007] The data collection module is used to obtain the working time and basic information of the smart device; wherein the working time includes the start time and the stop time; the basic information includes the characteristic values ​​of the working voltage, the working current and the working temperature;

[0008] The intelligent analysis module is used to obtain similar devices based on basic information, extract fault information of similar devices, pre-process the fault information to obtain standard fault probabilities of various fault types, and calculate the working time and standard fault probability to obtain the fault factors of various fault types of the current intelligent device; wherein the fault information includes the fault type and preliminary fault probability;

[0009] The fault management module is used to extract fault factors, make judgments based on the fault factors and issue management instructions, and pre-manage the smart devices based on the management instructions.

[0010] Preferably, the obtaining of the working time and basic information of the smart device includes:

[0011] The start time and stop time of each operation of the smart device are obtained through a time calculator; the voltage during each operation is obtained through a voltage detection sensor, and the voltage is marked as the working voltage; the current during each operation is obtained through a current detection sensor, and the current is marked as the working current; the temperature during each operation is obtained through a temperature sensor, and the voltage is marked as the working temperature; the characteristic values ​​of the working voltage, working current and working temperature of the smart device are obtained each time it works.

[0012] Preferably, the step of obtaining characteristic values ​​of the operating voltage, operating current and operating temperature of the smart device each time it operates includes:

[0013] Extract the working voltage, working current and working temperature of each operation of the smart device in sequence, divide the working voltage into Aj group, divide the working current into Bj group, and divide the working temperature into Cj group; wherein j is the number of each operation;

[0014] Extract the maximum value Dij, minimum value Xij and mode Zij of the data in group Aj, group Bj and group Cj in turn;

[0015] When i is 1 or 2, the characteristic value TZij of group Aj or group Bj is obtained based on the formula TZij=(BTi1×Dij+BTi2×Xij+Zij) / 2; wherein BTi1 and BTi2 are both proportional adjustment coefficients greater than 0, and BTi1+BTi2=1, BTi1>BTi2;

[0016] When the value of i is 3, the characteristic value TZij of each group corresponding to the working temperature is obtained based on the formula TZij=α×exp((BCW-CW) / BCW)×(BTi1×Dij+BTi2×Xij+Zij) / 2; where α is the amplitude adjustment coefficient, and the value range of α is (0,2]; CW is the initial temperature of each operation of the smart device, and BCW is the standard initial temperature set manually.

[0017] It is worth noting that in the present invention, exp((BCW-CW) / BCW) is transformed by the exp(-(CW-BCW) / BCW) function, and the function curve trend of the exp(-(CW-BCW) / BCW) function is: the calculated value gradually decreases as the initial temperature CW increases. When obtaining the characteristic value of the operating temperature, the present invention uses the exp((BCW-CW) / BCW) function for proportional adjustment to obtain the calculated value. This is because the initial temperature of the smart device can roughly indicate the ambient temperature of the environment in which it is located. During the operation of the smart device, the ambient temperature will have a fluctuating effect on the heat generation of the smart device, resulting in the calculated result being not the heat generation caused by the current operation of the smart device; for example: when the power of the smart devices is the same, the heat generation of the smart device in a low ambient temperature is lower than that in a high ambient temperature, so the obtained heat temperature will be lower, which will lead to inaccurate calculation results. The present invention uses the exp((BCW-CW) / BCW) function to adjust the heating temperature of smart devices in different ambient temperatures. When the ambient temperature is low, the temperature ratio of the calculation result is increased, and when the ambient temperature is high, the temperature ratio of the calculation result is reduced, so that the final temperature obtained is the heating temperature of the current smart device in a normal environment, so that the analysis of each device is in the same temperature range, which increases the accuracy of the analysis.

[0018] Preferably, the acquiring of similar devices based on basic information includes:

[0019] Sequentially extract the characteristic value TZ1j of the working voltage, the characteristic value TZ2j of the working current, and the characteristic value TZ3j of the working temperature of the current smart device each time it works;

[0020] The number of each work is used as the horizontal coordinate and each eigenvalue is used as the vertical coordinate. The two-dimensional curve Qi of each eigenvalue is constructed by interpolation method. n numbers are extracted at fixed intervals, and the extracted numbers are used as target numbers. The vertical coordinate value corresponding to the target number is marked as the target vertical value MZn; wherein the fixed interval is obtained based on experience;

[0021] Extract the target vertical value MZn in the two-dimensional curve Qi of the current smart device, and extract the target vertical values ​​QMZn in the two-dimensional curves Qi of other smart devices in the database in turn; obtain the deviation rate CLni of each target vertical value between the current smart device and the compared smart device based on the formula CLni=|MZn-QMZn| / MZn; obtain the number GSi of values ​​of the deviation rate CLni that are less than the deviation threshold, obtain the discrimination probability PLni based on the formula PLni=GSi / n, and mark the smart device whose discrimination probability PLni is greater than the discrimination threshold as a candidate device for the current smart device; wherein the deviation threshold and the discrimination threshold are both obtained through experience;

[0022] The smart devices marked as the to-be-selected devices in the determination of the two-dimensional curve Q1, the two-dimensional curve Q2 and the two-dimensional curve Q3 are marked as the same type of the current smart device.

[0023] It is worth noting that the present invention obtains similar devices of the current smart device by analyzing and judging all smart devices based on the two-dimensional curve Q1, the two-dimensional curve Q2 and the two-dimensional curve Q3. After three screenings, devices with different external factors such as usage scenarios or usage environments can be effectively removed, which removes interference factors for subsequent analysis of failure rates based on similar devices and improves the accuracy of data analysis.

[0024] Preferably, the extracting fault information of similar equipment includes:

[0025] Fault types in smart devices marked as similar devices and the fault probabilities of each fault type occurring in similar devices are extracted, and the fault probabilities are marked as preliminary fault probabilities.

[0026] Preferably, the preprocessing of the fault information to obtain the standard fault probability of each fault type includes:

[0027] Divide the extracted preliminary fault probability into several probability groups according to the fault type, extract the probability groups in sequence, obtain the variance of the probability groups, and judge whether the variance is less than the corresponding variance threshold; if yes, retain the data of the probability group; if no, remove the data in the data group that differs the most from the mode of the data group, and re-judge the variance until the variance of the data group is less than the corresponding variance threshold, and retain the remaining data of the data group; wherein the variance threshold is obtained through experience;

[0028] The target mean is obtained by calculating the average value of the data retained in each probability group, and the target mean corresponding to each fault type is marked as the standard fault probability of each fault type.

[0029] It is worth noting that the present invention pre-processes the fault information through variance judgment to obtain the standard fault probability of each fault type, which can remove the interference data with relatively large fluctuations in each fault type and provide data support for the subsequent calculation of the fault factor of each fault type.

[0030] Preferably, the calculation of the working time and the standard failure probability to obtain the failure factor of each failure type of the current smart device includes:

[0031] Based on the working time, the working time of each of the h complete works closest to the current time of the current smart device is obtained, the average value PJ of the working time is obtained, and the target time MC of the current smart device is obtained based on the formula MC=β×PJ; wherein β is a proportional adjustment coefficient greater than 0, and h is obtained by manual setting;

[0032] Sequentially obtain the target duration MC of the smart device corresponding to the data retained in the step of obtaining the target mean value for each fault type, and average several of the target durations MC to obtain a control target duration DMC;

[0033] Extract the target duration MC of the current smart device, and extract the control target duration DMC and standard failure probability BZL of each fault type in turn; obtain the fault factor ZY corresponding to the current smart device in the current fault type based on the formula ZY=δ×(exp(MC / DMC)-1)×BZL; where δ is the amplitude adjustment coefficient, and the value range of δ is (0,1].

[0034] It is worth noting that a single overtime operation has a certain impact on the failure rate of the intelligent device. When the working time of a single operation exceeds the specified value, the probability of failure of the current device will increase. If this working condition is maintained for a long time, there will be a superimposed influence between the increase in the probability of failure caused by the working time of multiple operations exceeding the specified value, which will cause the growth of the probability of failure to be a nonlinear state. Therefore, the present invention analyzes the working time of the previous h operations of the current intelligent device to obtain the target time. This target time can indirectly reflect the working condition of the intelligent device within a certain time range, and then compares the target time with the control target time. The comparison result is used to adjust the standard failure probability, which can effectively reflect the superimposed influence between the increase in the probability of failure caused by the working time of multiple operations exceeding the specified value.

[0035] Preferably, the issuing of management instructions based on the fault factor includes:

[0036] R1: Extract the fault factor ZY corresponding to each fault type of the current smart device in turn, and determine whether the value of the fault factor ZY is greater than the factor threshold 1 set for the corresponding fault type; if yes, issue the fault type and management instruction 1; if no, jump to R2; wherein the factor threshold 1 and the factor threshold 2 are both obtained through experience, and the factor threshold 1 is greater than the factor threshold 2; the management instruction includes management instruction 1, management instruction 2, and management instruction 3;

[0037] R2: Determine whether the value of the fault factor ZY is less than the factor threshold 2 established for the corresponding fault type; if yes, issue fault type and management instruction 3; if no, issue fault type and management instruction 2.

[0038] Preferably, the pre-managing of the smart device based on the management instruction includes:

[0039] Receive management instructions. When receiving management instruction 1, mark the corresponding fault type as a high-probability fault and arrange personnel to conduct an immediate investigation;

[0040] When management instruction 2 is received, the corresponding fault type is marked as a medium-probability fault, and the fault type is marked, and personnel are arranged to conduct a unified investigation;

[0041] When management instruction three is received, the corresponding fault type is marked as a low-probability fault and monitoring continues.

[0042] A second aspect of the present invention provides a method for managing intelligent device faults, comprising the following steps:

[0043] S1: Obtain the working time and basic information of smart devices;

[0044] S2: Based on the basic information, similar devices are obtained, the fault information of similar devices is extracted, the fault information is preprocessed to obtain the standard fault probability of each fault type, and the working time and the standard fault probability are calculated to obtain the fault factor of each fault type of the current smart device;

[0045] S3: issuing management instructions based on the fault factors, and pre-managing the smart devices based on the management instructions.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] 1. The present invention obtains similar devices of the current smart device, extracts fault information of similar devices, pre-processes the fault information to obtain standard fault probabilities of various fault types, calculates the working time and the standard fault probability to obtain fault factors of various fault types of the current smart device; makes judgments based on the fault factors and issues management instructions, and pre-manages the smart devices based on the management instructions, thereby solving the technical problems of difficulty in screening out and managing devices and locations that may fail in advance, and ignoring the superposition of fault probabilities of devices that have worked overtime for multiple times in fault management; the present invention can achieve effective monitoring and early warning of equipment failures, reduce equipment downtime, and reduce maintenance costs.

[0048] 2. When obtaining the characteristic value of the working temperature, the present invention uses the exp((BCW-CW) / BCW) function to proportionally adjust the calculated value. This is because the initial temperature of the smart device can roughly indicate the ambient temperature of the environment in which it is located. During the operation of the smart device, the ambient temperature will have a fluctuating effect on the heating of the smart device, resulting in the obtained calculation result not being the heating condition caused by the current operation of the smart device; such as: when the power of the smart device is the same, the heating condition of the smart device in a low ambient temperature is lower than that in a high ambient temperature, so the heating temperature obtained will be lower, which will lead to inaccurate calculation results. The present invention uses the exp((BCW-CW) / BCW) function to adjust the heating temperature of smart devices in different ambient temperatures, increases the temperature ratio of the calculation result when the ambient temperature is low, and reduces the temperature ratio of the calculation result when the ambient temperature is high, so that the final temperature obtained is the heating temperature of the current smart device in a normal environment, so that the analysis of each device is in the same temperature range, which increases the accuracy of the analysis.

[0049] 3. Because a single overtime operation has a certain influence on the failure rate of the intelligent device, when the working time of a single operation exceeds the specified value, the probability of failure of the current device will increase. If this working condition is maintained for a long time, there will be a superimposed influence between the increase in the probability of failure caused by the working time of multiple operations exceeding the specified value, which will cause the growth of the probability of failure to be a nonlinear state; therefore, the present invention analyzes the working time of the previous h operations of the current intelligent device to obtain the target time, and this target time can indirectly reflect the working condition of the intelligent device within a certain time range, and then compares the target time with the control target time, and uses the comparison result to adjust the standard failure probability, which can effectively reflect the superimposed influence between the increase in the probability of failure caused by the working time of multiple operations exceeding the specified value. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 It is a schematic diagram of the operation steps of the present invention;

[0052] Figure 2 It is a schematic diagram of the system module of the present invention;

[0053] Figure 3 A schematic diagram of the operation steps of similar equipment is obtained for the present invention;

[0054] Figure 4 The figure is a schematic diagram of the operation steps for obtaining the fault factor of the present invention. DETAILED DESCRIPTION

[0055] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0056] See also Figure 1-Figure 2 , the first aspect of the present invention provides an intelligent device fault management system, including: an intelligent analysis module, and a data collection module, a fault management module and a database connected thereto;

[0057] Data collection module: used to obtain the working time and basic information of smart devices; the working time includes the start time and stop time of working; the basic information includes the characteristic values ​​of working voltage, working current and working temperature;

[0058] Intelligent analysis module: used to obtain similar devices based on basic information, extract fault information of similar devices, pre-process the fault information to obtain the standard fault probability of each fault type, calculate the working time and the standard fault probability to obtain the fault factor of each fault type of the current intelligent device; wherein the fault information includes the fault type and the preliminary fault probability;

[0059] Fault management module: used to extract fault factors, make judgments based on the fault factors and issue management instructions, and pre-manage smart devices based on the management instructions.

[0060] It should be noted that the smart devices used for analysis in the present invention are all smart devices of the same type and model.

[0061] It should be noted that the fault types include abnormal voltage, abnormal current, abnormal operating temperature, etc.

[0062] This application obtains the working hours and basic information of smart devices, including:

[0063] The start working time and stop working time of each operation of the smart device are obtained through the time calculator; the voltage during each operation is obtained through the voltage detection sensor, and the voltage is marked as the working voltage; the current during each operation is obtained through the current detection sensor, and the current is marked as the working current; the temperature during each operation is obtained through the temperature sensor, and the voltage is marked as the working temperature; the characteristic values ​​of the working voltage, working current and working temperature of the smart device are obtained each time it works.

[0064] In this application, the characteristic values ​​of the operating voltage, operating current and operating temperature of the smart device are obtained each time it works, including:

[0065] The working voltage, working current and working temperature of each operation of the smart device are extracted in sequence, and the working voltage is divided into the Aj group, the working current is divided into the Bj group, and the working temperature is divided into the Cj group; wherein j is the number of each operation;

[0066] Extract the maximum value Dij, minimum value Xij and mode Zij of the data in group Aj, group Bj and group Cj in turn;

[0067] When i is 1 or 2, the characteristic value TZij of group Aj or group Bj is obtained based on the formula TZij=(BTi1×Dij+BTi2×Xij+Zij) / 2; wherein BTi1 and BTi2 are both proportional adjustment coefficients greater than 0, and BTi1+BTi2=1, BTi1>BTi2;

[0068] When the value of i is 3, the characteristic value TZij of each group corresponding to the working temperature is obtained based on the formula TZij=α×exp((BCW-CW) / BCW)×(BTi1×Dij+BTi2×Xij+Zij) / 2; where α is the amplitude adjustment coefficient, and the value range of α is (0,2]; CW is the initial temperature of each operation of the smart device, and BCW is the standard initial temperature set manually.

[0069] It should be noted that when i is 1, it represents the data of the Aj group, when i is 2, it represents the data of the Bj group, and when i is 3, it represents the data of the Cj group.

[0070] It should be noted that when obtaining the modes of the Aj group, the Bj group, and the Cj group, if the mode of a certain group is not unique, the average value of the mode of this group is calculated, and the result is used as the mode of this group.

[0071] For example, the mode of group C6 is 56°C and 57°C; the result of calculating the average value of the mode of group C6 is 56.5°C, and 56.5°C is taken as the mode of this group.

[0072] It should be noted that in the proportional adjustment coefficients BTi1 and BTi2, when the value of i is different, the values ​​of BTi1 and BTi2 are also different. For example, Aj group: BT11 = 0.6, BT12 = 0.4; Bj group: BT21 = 0.8, BT22 = 0.2; Cj group: BT31 = 0.59, BT32 = 0.41.

[0073] See also Figure 3 , in this application, similar devices are obtained based on basic information, including:

[0074] Sequentially extract the characteristic value TZ1j of the working voltage, the characteristic value TZ2j of the working current, and the characteristic value TZ3j of the working temperature of the current smart device each time it works;

[0075] The number of each work is used as the horizontal coordinate and each eigenvalue is used as the vertical coordinate. The two-dimensional curve Qi of each eigenvalue is constructed by interpolation method. n numbers are extracted at fixed intervals, and the extracted numbers are used as target numbers. The vertical coordinate value corresponding to the target number is marked as the target vertical value MZn; wherein the fixed interval is obtained based on experience;

[0076] Extract the target vertical value MZn in the two-dimensional curve Qi of the current smart device, and extract the target vertical values ​​QMZn in the two-dimensional curves Qi of other smart devices in the database in turn; obtain the deviation rate CLni of each target vertical value between the current smart device and the compared smart device based on the formula CLni=|MZn-QMZn| / MZn; obtain the number of values ​​of the deviation rate CLni that are less than the deviation threshold GSi, obtain the discrimination probability PLni based on the formula PLni=GSi / n, and mark the smart device whose discrimination probability PLni is greater than the discrimination threshold as the candidate device for the current smart device; wherein the deviation threshold and the discrimination threshold are both obtained through experience;

[0077] The smart devices marked as the to-be-selected devices in the determination of the two-dimensional curve Q1, the two-dimensional curve Q2 and the two-dimensional curve Q3 are marked as the same type of the current smart device.

[0078] It should be noted that when marking the candidate device of the current smart device, the two-dimensional curve Q1, the two-dimensional curve Q2 and the two-dimensional curve Q3 are analyzed and judged, and the analysis steps may be:

[0079] 1. Filter all smart devices through the two-dimensional curve Q1 to obtain the devices to be selected by the two-dimensional curve Q1; filter all smart devices through the two-dimensional curve Q2 to obtain the devices to be selected by the two-dimensional curve Q2; filter all smart devices through the two-dimensional curve Q3 to obtain the devices to be selected by the two-dimensional curve Q3; then mark the smart devices marked as the devices to be selected three times as the same type of the current smart device.

[0080] 2. Filter all smart devices through the two-dimensional curve Q1 to obtain the candidate device one filtered by the two-dimensional curve Q1; filter all the candidate devices one through the two-dimensional curve Q2 to obtain the candidate device two filtered by the two-dimensional curve Q2; filter all the candidate devices two through the two-dimensional curve Q3 to obtain the candidate device three filtered by the two-dimensional curve Q3; mark the smart device marked as the candidate device three as the same device as the current smart device.

[0081] This application extracts fault information of similar devices, including:

[0082] Fault types in smart devices marked as similar devices and the fault probability of each fault type occurring in similar devices are extracted, and the fault probability is marked as preliminary fault probability.

[0083] In this application, the fault information is preprocessed to obtain the standard fault probability of each fault type, including:

[0084] Divide the extracted preliminary fault probability into several probability groups according to the fault type, extract the probability groups in sequence, obtain the variance of the probability groups, and judge whether the variance is less than the corresponding variance threshold; if yes, retain the data of the probability group; if no, remove the data in the data group that differs the most from the mode of the data group, and re-judge the variance until the variance of the data group is less than the corresponding variance threshold, and retain the remaining data of the data group; wherein the variance threshold is obtained through experience;

[0085] The target mean is obtained by calculating the average value of the data retained in each probability group, and the target mean corresponding to each fault type is marked as the standard fault probability of each fault type.

[0086] See also Figure 4 In this application, the working time and standard failure probability are calculated to obtain the failure factors of each failure type of the current smart device, including:

[0087] Based on the working time, the working time of each work of the current smart device in the nearest h complete works to the current time is obtained, and the average working time PJ is obtained. Based on the formula MC=β×PJ, the target working time MC of the current smart device is obtained; wherein β is a proportional adjustment coefficient greater than 0, and h is obtained by manual setting;

[0088] The target duration MC of the smart device corresponding to the data retained in the step of obtaining the target mean value for each fault type is obtained in sequence, and the average of several target durations MC is calculated to obtain the control target duration DMC;

[0089] Extract the target duration MC of the current smart device, and extract the control target duration DMC and standard failure probability BZL of each fault type in turn; obtain the fault factor ZY corresponding to the current smart device in the current fault type based on the formula ZY=δ×(exp(MC / DMC)-1)×BZL; where δ is the amplitude adjustment coefficient, and the value range of δ is (0,1].

[0090] It should be noted that the specific explanation of extracting each fault type in turn and retaining the data corresponding to the smart device in the step of obtaining the target mean value is as follows:

[0091] The retained data is in the probability group judgment: when the variance is less than the corresponding variance threshold, the retained data; or when the variance is not less than the corresponding variance threshold, the data in the data group that is most different from the mode of the data group is removed, and the variance judgment is performed again until the variance of the data group is less than the corresponding variance threshold, the retained data; then the target duration MC of the smart device corresponding to the retained data is obtained.

[0092] It should be noted that the h complete jobs extracted from the data of the h complete jobs closest to the current time of the current smart device are the h complete jobs before the current time and closest to the current time; wherein, a complete job is a complete job from the start of the work to the stop of the work.

[0093] In this application, the management instructions are issued based on the fault factors, including:

[0094] R1: Extract the fault factor ZY corresponding to each fault type of the current smart device in turn, and determine whether the value of the fault factor ZY is greater than the factor threshold 1 set for the corresponding fault type; if yes, issue the fault type and management instruction 1; if no, jump to R2; wherein, the factor threshold 1 and the factor threshold 2 are both obtained through experience, and the factor threshold 1 is greater than the factor threshold 2; the management instructions include management instruction 1, management instruction 2, and management instruction 3;

[0095] R2: Determine whether the value of the fault factor ZY is less than the factor threshold 2 set for the corresponding fault type; if yes, issue fault type and management instruction 3; if no, issue fault type and management instruction 2.

[0096] In this application, smart devices are pre-managed based on management instructions, including:

[0097] Receive management instructions. When receiving management instruction 1, mark the corresponding fault type as a high-probability fault and arrange personnel to conduct an immediate investigation;

[0098] When management instruction 2 is received, the corresponding fault type is marked as a medium-probability fault, and the fault type is marked, and personnel are arranged to conduct a unified investigation;

[0099] When management instruction three is received, the corresponding fault type is marked as a low-probability fault and monitoring continues.

[0100] It should be noted that the specific explanation of arranging personnel to conduct unified inspection upon receiving the second management instruction is: arranging personnel to check the marked faults at a fixed time.

[0101] A second aspect of the present invention provides a method for managing faults of an intelligent device, comprising the following steps:

[0102] S1: Obtain the working time and basic information of smart devices;

[0103] S2: Based on the basic information, similar devices are obtained, the fault information of similar devices is extracted, the fault information is preprocessed to obtain the standard fault probability of each fault type, and the working time and the standard fault probability are calculated to obtain the fault factor of each fault type of the current smart device;

[0104] S3: issuing management instructions based on the fault factors, and pre-managing the smart devices based on the management instructions.

[0105] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0106] Working principle of the present invention:

[0107] The present invention first obtains the working time and basic information of the intelligent device; then obtains similar devices based on the basic information. This step makes the comparison devices used for analyzing the present intelligent device within the same standard, thereby increasing the accuracy of the analysis; extracts the fault information of the similar devices, and pre-processes the fault information to obtain the standard fault probability of each fault type. This step can remove the interference data with relatively large fluctuations in each fault type, thereby providing data support for the subsequent calculation of the fault factor of each fault type; calculates the working time and the standard fault probability to obtain the fault factor of each fault type of the current intelligent device. This step takes into account the mutual superposition of the effects of the increase in the fault probability caused by the working time of multiple operations exceeding the prescribed value, thereby increasing the accuracy of the system analysis; finally, makes a judgment based on the fault factor to issue a management instruction, and pre-manages the intelligent device based on the management instruction.

[0108] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A smart device fault management system, characterized in that: include: Intelligent analysis module, and the data collection module, fault management module and database connected thereto; The data collection module is used to obtain the working time and basic information of the smart device; wherein the working time includes the start time and the stop time; the basic information includes the characteristic values ​​of the working voltage, the working current and the working temperature; The intelligent analysis module is used to obtain similar devices based on basic information, extract fault information of similar devices, pre-process the fault information to obtain standard fault probabilities of various fault types, and calculate the working time and standard fault probability to obtain the fault factors of various fault types of the current intelligent device; wherein the fault information includes the fault type and preliminary fault probability; The fault management module is used to extract fault factors, make judgments based on the fault factors and issue management instructions, and pre-manage the smart devices based on the management instructions.

2. The intelligent device fault management system according to claim 1, characterized in that: The obtaining of working hours and basic information of smart devices includes: The start time and stop time of each operation of the smart device are obtained through a time calculator; the voltage during each operation is obtained through a voltage detection sensor, and the voltage is marked as the working voltage; the current during each operation is obtained through a current detection sensor, and the current is marked as the working current; the temperature during each operation is obtained through a temperature sensor, and the voltage is marked as the working temperature; the characteristic values ​​of the working voltage, working current and working temperature of the smart device are obtained each time it works.

3. The intelligent device fault management system according to claim 2, characterized in that: The step of obtaining characteristic values ​​of the operating voltage, operating current and operating temperature of the smart device each time the smart device operates includes: Extract the working voltage, working current and working temperature of each operation of the smart device in sequence, divide the working voltage into Aj group, divide the working current into Bj group, and divide the working temperature into Cj group; wherein j is the number of each operation; Extract the maximum value Dij, minimum value Xij and mode Zij of the data in group Aj, group Bj and group Cj in turn; When i is 1 or 2, the characteristic value TZij of group Aj or group Bj is obtained based on the formula TZij=(BTi1×Dij+BTi2×Xij+Zij) / 2; wherein BTi1 and BTi2 are both proportional adjustment coefficients greater than 0, and BTi1+BTi2=1, BTi1>BTi2; When the value of i is 3, the characteristic value TZij of each group corresponding to the working temperature is obtained based on the formula TZij=α×exp((BCW-CW) / BCW)×(BTi1×Dij+BTi2×Xij+Zij) / 2; where α is the amplitude adjustment coefficient, and the value range of α is (0,2]; CW is the initial temperature of each operation of the smart device, and BCW is the standard initial temperature.

4. The intelligent device fault management system according to claim 3, characterized in that: The obtaining of similar devices based on basic information includes: Sequentially extract the characteristic value TZ1j of the working voltage, the characteristic value TZ2j of the working current, and the characteristic value TZ3j of the working temperature of the current smart device each time it works; The number of each job is used as the horizontal coordinate and each eigenvalue is used as the vertical coordinate. The two-dimensional curve Qi of each eigenvalue is constructed by interpolation method. n numbers are extracted at fixed intervals. The extracted numbers are used as target numbers, and the vertical coordinate value corresponding to the target number is marked as the target vertical value MZn. Extract the target vertical value MZn in the two-dimensional curve Qi of the current smart device, and extract the target vertical values ​​QMZn in the two-dimensional curves Qi of other smart devices in the database in turn; obtain the deviation rate CLni of each target vertical value between the current smart device and the compared smart device based on the formula CLni=|MZn-QMZn| / MZn; obtain the number GSi of values ​​of the deviation rate CLni that are less than the deviation threshold, obtain the discrimination probability PLni based on the formula PLni=GSi / n, and mark the smart device whose discrimination probability PLni is greater than the discrimination threshold as the candidate device for the current smart device; The smart devices marked as the to-be-selected devices in the determination of the two-dimensional curve Q1, the two-dimensional curve Q2 and the two-dimensional curve Q3 are marked as the same type of the current smart device.

5. The intelligent device fault management system according to claim 1, characterized in that: The extracting fault information of the same type of equipment includes: Fault types in smart devices marked as similar devices and the fault probabilities of each fault type occurring in similar devices are extracted, and the fault probabilities are marked as preliminary fault probabilities.

6. The intelligent device fault management system according to claim 1, characterized in that: The preprocessing of the fault information to obtain the standard fault probability of each fault type includes: Divide the extracted preliminary fault probability into several probability groups according to the fault type, extract the probability groups in sequence, obtain the variance of the probability groups, and judge whether the variance is less than the corresponding variance threshold; if yes, retain the data of the probability group; if no, remove the data in the data group that differs the most from the mode of the data group, and re-judge the variance until the variance of the data group is less than the corresponding variance threshold, and retain the remaining data of the data group; The target mean is obtained by calculating the average value of the data retained in each probability group, and the target mean corresponding to each fault type is marked as the standard fault probability of each fault type.

7. The intelligent device fault management system according to claim 6, characterized in that: The calculation of the working time and the standard failure probability to obtain the failure factors of each failure type of the current smart device includes: Based on the working time, the working time of each of the h complete works closest to the current time of the current smart device is obtained, the average value PJ of the working time is obtained, and the target time MC of the current smart device is obtained based on the formula MC=β×PJ; wherein β is a proportional adjustment coefficient greater than 0; Sequentially obtain the target duration MC of the smart device corresponding to the data retained in the step of obtaining the target mean value for each fault type, and average several of the target durations MC to obtain a control target duration DMC; Extract the target duration MC of the current smart device, and extract the control target duration DMC and standard failure probability BZL of each fault type in turn; obtain the fault factor ZY corresponding to the current smart device in the current fault type based on the formula ZY=δ×(exp(MC / DMC)-1)×BZL; where δ is the amplitude adjustment coefficient, and the value range of δ is (0,1].

8. The intelligent device fault management system according to claim 1, characterized in that: The issuing of management instructions based on the fault factor includes: R1: extract the fault factor ZY corresponding to each fault type of the current smart device in turn, and determine whether the value of the fault factor ZY is greater than the factor threshold 1 set for the corresponding fault type; if yes, issue the fault type and management instruction 1; if no, jump to R2; wherein the factor threshold 1 is greater than the factor threshold 2; the management instruction includes management instruction 1, management instruction 2, and management instruction 3; R2: Determine whether the value of the fault factor ZY is less than the factor threshold 2 established for the corresponding fault type; if yes, issue fault type and management instruction 3; if no, issue fault type and management instruction 2.

9. The intelligent device fault management system according to claim 8, characterized in that: The pre-management of the smart device based on the management instruction includes: Receive management instructions. When receiving management instruction 1, mark the corresponding fault type as a high-probability fault and arrange personnel to conduct an immediate investigation; When management instruction 2 is received, the corresponding fault type is marked as a medium-probability fault, and the fault type is marked, and personnel are arranged to conduct a unified investigation; When management instruction three is received, the corresponding fault type is marked as a low-probability fault and monitoring continues.

10. A method for managing intelligent device faults, based on the intelligent device fault management system according to any one of claims 1 to 9, characterized in that: S1: Obtain the working time and basic information of smart devices; S2: Based on the basic information, similar devices are obtained, the fault information of similar devices is extracted, the fault information is preprocessed to obtain the standard fault probability of each fault type, and the working time and the standard fault probability are calculated to obtain the fault factor of each fault type of the current smart device; S3: issuing management instructions based on the fault factors, and pre-managing the smart devices based on the management instructions.

Images