Integrated equipment self-checking system and method based on OPS computer

Abstract

The invention discloses an integrated equipment self-checking system and method based on an OPS computer, and belongs to the technical field of integrated equipment self-checking. According to the method, operation data are transmitted to a cloud platform in real time through integrated equipment, a central detection host acquires the operation data of the integrated equipment, the operation data are classified, and the classified operation data are integrated and defined as a first-class curve and a second-class curve; performing preprocessing search on historical operation data of the integrated equipment, performing reference value calculation according to the second curve segment set, and generating historical operation reference data according to a reference value calculation result; extracting a fault feature set through historical operation reference data, and performing fault risk judgment on the integrated equipment by using real-time operation data of the integrated equipment; and performing early warning and prompting on the user according to the fault risk judgment. The data is screened, the calculated amount of the system is reduced, the equipment detection efficiency is improved, and the accuracy of an equipment fault detection result is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated equipment self-checking, and in particular to an integrated equipment self-checking system and method based on an OPS computer. Background Art

[0002] OPS computer is an open pluggable standard computer module. The computer part is made into a modular standard product. Through the pull-out design, the PC part and the LCD all-in-one computer can be easily and quickly separated to facilitate the repair, replacement, upgrade and replacement of computer components.

[0003] However, for fault detection of OPS computers, it is often necessary to disassemble the PC part of the computer, or an external auxiliary interface or equipment tool is needed to repair and eliminate OPS hardware-related faults, which requires a lot of manpower and material resources; manual repair of OPS hardware-related faults needs to rely on the experience and judgment of the maintenance personnel, which is easy to cause misjudgment and have an adverse impact on the subsequent work of the OPS computer, and the detection efficiency of manual repair equipment is not high.

[0004] Therefore, the present invention discloses an integrated equipment self-checking system and method based on OPS computer to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide an integrated equipment self-checking system and method based on an OPS computer to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an integrated equipment self-checking method based on an OPS computer, characterized in that the method comprises the following steps: S1: The integrated equipment is connected to the cloud platform through the network and transmits the operating data to the cloud platform in real time. The central detection host obtains the operating data of the integrated equipment from the cloud platform, classifies the operating data according to the hardware devices of the integrated equipment, and integrates the classified operating data to define Class I curves and Class II curves; S2: pre-processing the historical operation data of the integrated equipment to search and form a first curve segment set, extracting the first curve segment set to form a second curve segment set, calculating the reference value according to the second curve segment set, and generating historical operation reference data according to the reference value calculation result; S3: Extract the fault feature set through historical operation reference data, adjust the detection task scheduling of real-time operation data in real time according to the priority of equipment fault detection tasks, and use the real-time operation data of integrated equipment to determine the fault risk of integrated equipment; S4: Provide warnings and prompts to users based on fault risk assessment.

[0007] In step S1, the integrated devices connected to the cloud platform are grouped into a set IE={IE1, IE2, ..., IE n}, where n represents the total number of integrated devices, and the i-th integrated device is recorded as IE i , where i∈[1,n]; The operation data includes historical operation data and real-time operation data, and the historical operation data and real-time operation data both contain operation attribute value change curves, and the operation attribute value change curves include a central processing unit operation curve, an operation memory operation curve, a storage device operation curve, a processing unit operation curve, a network interface operation curve, and a power supply operation curve; The central processing unit operation curve, the operation memory operation curve, the storage device operation curve, the processing unit operation curve, the network interface operation curve and the power supply operation curve are curves showing the change of the values ​​of various operation attributes over time; The CPU operation curve includes a CPU temperature curve and a CPU utilization curve; the memory operation curve includes a memory utilization curve; the storage device operation curve includes a storage device read speed curve, a storage device write speed curve and a storage device remaining space curve; the processing unit operation curve includes a processing unit temperature curve and a processing unit utilization curve; the network interface operation curve includes a network interface delay curve, a network interface packet loss curve and a network interface transmission rate curve; the power supply operation curve includes a power supply power curve; In the present application, the central processing unit is the CPU of the OPS computer, the processing unit is the GPU of the OPS computer, and the storage device includes a hard disk; the central processing unit utilization, the running memory utilization, the storage device reading speed, the storage device writing speed, the storage device remaining space, the network interface delay, the network interface packet loss and the network interface transmission rate are obtained through the built-in detection tool of the OPS computer, the central processing unit temperature and the processing unit temperature are measured by sensors, the power supply voltage and current are measured by sensors, and the power supply power is calculated according to the power calculation formula; The central processing unit temperature curve, the central processing unit utilization curve, the running memory utilization curve, the processing unit temperature curve, the processing unit utilization curve, the network interface delay curve and the network interface packet loss curve are defined as first-class curves; the storage device read speed curve, the storage device write speed curve, the storage device remaining space curve, the network interface transmission rate curve and the power supply power curve are defined as second-class curves.

[0008] According to the specific attribute characteristics of various hardware in the integrated device, the CPU temperature value, CPU utilization value, running memory utilization value, processing unit temperature value, processing unit utilization value, network interface delay value and network interface packet loss value often reach regional maximum values ​​before failure; storage device read speed value, storage device write speed value, storage device remaining space value, network interface transmission rate value and power supply power value often reach regional minimum values ​​before failure; the above different attribute curves are classified into different curve groups, which is conducive to subsequent analysis and calculation; According to the above scheme, in step S2, a historical operation attribute value change curve in the historical operation data corresponds to a historical operation attribute value change curve function, and within the same detection cycle, the integrated device IE i The derivative of each historical operation attribute value change curve function is obtained, and the curve function obtained after the derivative is recorded as the historical operation attribute value change rate curve function; Find the moment when the historical operation attribute value change rate is zero in the historical operation attribute value change rate curve function, and in the corresponding historical operation attribute value change curve, take the moment when the historical operation attribute value change rate is zero as the center, intercept the curve segment of the system preset time length to form a first curve segment set; the curve segment does not include the case where the historical operation attribute value is always zero; the system preset time length of each historical operation attribute value change curve is different; When an integrated device fails, various attribute values ​​often reach regional extreme values. The historical operation data is derived to form a historical operation attribute value change rate curve function. The moment when the historical operation attribute value change rate is zero in the historical operation attribute value change rate curve function can be found effectively to find the time when the integrated device fails, thereby improving the accuracy of the equipment fault detection results. The operation attribute value change trends of each operation attribute value change curve are different. According to different operation attribute value change curves, the system intercepts curve segments with different system preset time lengths, thereby further improving the accuracy of the equipment fault detection results. If any two curve segments have overlapping parts, the curve segments with overlapping parts will be integrated; if any two curve segments do not have overlapping parts, they will be sorted according to the time sequence; Extract the curve segments in the first curve segment set, where the historical operation attribute value is a regional maximum value when the historical operation attribute value change rate is zero; the regional maximum value is the case where the historical operation attribute value change rate is greater than zero before the moment when the historical operation attribute value change rate is zero, and the historical operation attribute value change rate is less than zero after the moment when the historical operation attribute value change rate is zero; the extracted curve segments are combined into a second curve segment set CS of a class of curves a i ={CSa （i，1） , C.S. a （i，2） ,…,CS a （i，Ma）}, where Ma is the total number of curve segments of the a-th type of first-class curve, and the j-th curve segment of the a-th type of first-class curve is denoted as CS a （i，j） , where j∈[1,Ma]; Extract the curve segments in the second curve segment set, where the historical operation attribute value is a regional minimum value when the historical operation attribute value change rate is zero, and the regional minimum value is the case where the historical operation attribute value change rate is less than zero before the moment when the historical operation attribute value change rate is zero, and the historical operation attribute value change rate is greater than zero after the moment when the historical operation attribute value change rate is zero; the extracted curve segments are combined into the second curve segment set CS of the second type of curve b i ={CS b （i，1） , C.S. b （i，2） ,…,CS b （i，Mb）}, where Mb is the total number of curve segments of the b-th type II curve, and the j-th curve segment of the b-th type II curve is denoted as CS b （i，j） , where j∈[1,Mb]; For integrated equipment IE i Calculate the reference value of historical operation data, including the total reference value RVA of a type of curve i The specific calculation formula is as follows: RVA i =∑\s\do 3(a=1)A [α a ×(∑\s\do 3(j=1)Ma RCS a （i，j） / Ma)]; Where A represents the total number of the first curves, α a represents the weight of the a-th type I curve, RCS a Represents the curve segment CS a （i，j） The average value of the historical operating attribute values; Total reference value RVB of the second type curve i The specific calculation formula is as follows: RVB i =∑\s\do 3(b=1)B [α b ×(∑\s\do 3(j=1)Mb RCS b （i，j） / Mb)]; Where B represents the total number of second curves, α b Represents the weight of the b-th type II curve, RCS b Represents the curve segment CS b （i，j） The average value of the historical operating attribute values; Set the total reference value threshold of the first type of curve to β1, and set the total reference value threshold of the second type of curve to β2; The historical operation data whose total reference value of the first-class curve is greater than or equal to the threshold β1, or whose total reference value of the second-class curve is less than or equal to the threshold β2 are defined as the historical operation reference data.

[0009] According to the above calculation of reference value and setting of threshold, a part of historical operation data is retained to form historical operation reference data, which can effectively screen out data with high reference value, reduce data with low reference value or even no reference value, reduce the amount of calculation of the system, and improve equipment detection efficiency.

[0010] According to the above scheme, in step S3, the reference value of each type of curve of the integrated equipment that has failed is extracted from the historical operation reference data to form a type of curve failure reference value set; the reference value of each type of curve is compared to form a type of curve failure feature value set; the type of curve failure feature value set includes the minimum reference value of each type of curve; Extract the reference value of each type of Class II curve of the integrated equipment that has experienced a fault from the historical operation reference data to form a Class II curve fault reference value set; compare the reference value of each type of Class II curve to form a Class II curve fault characteristic value set; the Class II curve fault characteristic value set includes the maximum value of the reference value of each type of Class II curve; The first type of curve fault characteristic value set and the second type of curve fault characteristic value set are combined to form a fault characteristic parameter set; Fault features are extracted for integrated equipment that has experienced faults, and the regional extreme values ​​of the reference value of each curve are used as elements of the fault feature set to improve the accuracy of equipment fault detection results.

[0011] Prioritize the faults of the integrated equipment, and adjust the detection task scheduling of the real-time operation data in real time according to the priority of the equipment fault detection task. Give priority to finding the operation attribute values ​​contained in the equipment fault detection tasks with high priority, calculate the reference value of the operation attribute value change curve in the real-time operation data of the integrated equipment, and compare it with the fault feature values ​​corresponding to the fault feature set. If the reference value of one of the first-class curves is greater than or equal to the corresponding fault feature value, or the reference value of one of the second-class curves is less than or equal to the corresponding fault feature value, it is determined that the integrated equipment has a failure risk.

[0012] According to the priority of equipment fault detection tasks, the detection task scheduling of real-time operation data is adjusted in real time to improve the overall detection efficiency.

[0013] According to the above scheme, in step S4, if there is an integrated device with a risk of failure, the user is warned and the specific hardware device with the risk of failure is prompted. If there is no risk of failure in the integrated device, no warning or prompting is performed.

[0014] Another aspect of the present application provides an integrated device self-checking system based on an OPS computer, the system is applied to the above-mentioned integrated device self-checking method based on an OPS computer, and is characterized in that the system includes an integrated device, a cloud platform and a central detection host; The cloud platform is used to receive the operation data of the integrated device and transmit the operation data of the integrated device to the central detection host; The central detection host includes a data classification and integration module, a reference value analysis and calculation module, a fault feature extraction and determination module, and an early warning prompt module; The data classification and integration module is used to classify and integrate the operating data according to the hardware equipment of the integrated equipment, and define it as Class I curves and Class II curves; the reference value analysis and calculation module is used to pre-process and search the historical operating data of the integrated equipment, and calculate the reference value of the historical operating data after pre-processing and searching; the fault feature extraction and judgment module is used to extract the fault feature set, and use the real-time operating data of the integrated equipment to judge the fault risk of the integrated equipment; the early warning and prompt module warns and prompts the user according to the fault risk judgment.

[0015] According to the above solution, the data classification and integration module includes a data classification unit and a data integration unit; The data classification unit is used to classify the operation data into historical operation data and real-time operation data, and classify the operation attribute value change curves contained in the historical operation data and the real-time operation data into a central processing unit operation curve, an operation memory operation curve, a storage device operation curve, a processing unit operation curve, a network interface operation curve and a power supply operation curve; The CPU operation curve includes a CPU temperature curve and a CPU utilization curve; the memory operation curve includes a memory utilization curve; the storage device operation curve includes a storage device read speed curve, a storage device write speed curve and a storage device remaining space curve; the processing unit operation curve includes a processing unit temperature curve and a processing unit utilization curve; the network interface operation curve includes a network interface delay curve, a network interface packet loss curve and a network interface transmission rate curve; the power supply operation curve includes a power supply power curve; The data integration unit is used to define the central processing unit temperature curve, the central processing unit utilization curve, the running memory utilization curve, the processing unit temperature curve, the processing unit utilization curve, the network interface delay curve and the network interface packet loss curve as a first type of curve; the storage device read speed curve, the storage device write speed curve, the storage device remaining space curve, the network interface transmission rate curve and the power supply power curve are defined as a second type of curve.

[0016] According to the above scheme, the reference value analysis and calculation module includes a reference value analysis search unit and a reference value calculation unit; The reference value analysis and search unit is used to analyze the integrated device IE in the same detection cycle. i The derivative of each historical operation attribute value change curve function is obtained, and the curve function obtained after the derivative is recorded as the historical operation attribute value change rate curve function; the moment when the historical operation attribute value change rate is zero in the historical operation attribute value change rate curve function is found, and in the corresponding historical operation attribute value change curve, the moment when the historical operation attribute value change rate is zero is taken as the center, and the curve segment of the system preset time length is intercepted to form a first curve segment set; the curve segment whose historical operation attribute value is a regional extreme value when the historical operation attribute value change rate is zero is extracted from the first curve segment set, and the extracted curve segments are formed into a second curve segment set; The reference value calculation unit is used to calculate the reference value of the historical operation data after pre-processing and searching.

[0017] According to the above scheme, the fault feature extraction and determination module includes a fault feature extraction unit and a fault risk determination module; The fault feature extraction unit is used to form a type I curve fault feature value set and a type II curve fault feature value set, and integrate the type I curve fault feature value set and the type II curve fault feature value set to form a fault feature parameter set; The fault risk determination module is used to calculate the reference value of the real-time operation data of the integrated equipment, and compare it with the fault feature values ​​corresponding to the fault feature set to determine the fault risk of the integrated equipment.

[0018] According to the above solution, the early warning prompt module is used to warn users of integrated devices that have failure risks, and to prompt specific hardware devices that have failure risks.

[0019] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: different attribute curves are classified into different curve groups according to the specific attribute characteristics of various hardware in the integrated device, which is conducive to analysis and calculation; when an integrated device fails, various attribute values ​​often reach regional extreme values, and the historical operation data is derived to form a historical operation attribute value change rate curve function, which can effectively find the time when the integrated device fails, and improve the accuracy of the equipment fault detection result; the operation attribute value change trends of each operation attribute value change curve are different, and according to different operation attribute value change curves, the system intercepts curve segments with different system preset time lengths, further improving the accuracy of the equipment fault detection result; the reference value is calculated and a threshold is set, and a part of the historical operation data is retained to form historical operation reference data, which can effectively filter data, reduce the system's calculation amount, and improve equipment detection efficiency; fault feature extraction is performed on the integrated equipment that has failed, and the regional extreme value of the reference value of each curve is used as a fault feature set element to improve the accuracy of the equipment fault detection result. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of an integrated equipment self-checking system and method based on an OPS computer of the present invention; Figure 2 It is a structural schematic diagram of an integrated equipment self-checking system and method based on an OPS computer of the present invention. DETAILED DESCRIPTION

[0021] 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.

[0022] See also Figure 1 , an integrated equipment self-checking method based on OPS computer, characterized in that the method comprises the following steps: S1: The integrated equipment is connected to the cloud platform through the network and transmits the operating data to the cloud platform in real time. The central detection host obtains the operating data of the integrated equipment from the cloud platform, classifies the operating data according to the hardware devices of the integrated equipment, and integrates the classified operating data to define Class I curves and Class II curves; In step S1, the integrated devices connected to the cloud platform are grouped into a set IE={IE1, IE2, ..., IE n}, where n represents the total number of integrated devices, and the i-th integrated device is recorded as IE i , where i∈[1,n]; The operation data includes historical operation data and real-time operation data, and the historical operation data and real-time operation data both contain operation attribute value change curves, and the operation attribute value change curves include a central processing unit operation curve, an operation memory operation curve, a storage device operation curve, a processing unit operation curve, a network interface operation curve, and a power supply operation curve; The central processing unit operation curve, the operation memory operation curve, the storage device operation curve, the processing unit operation curve, the network interface operation curve and the power supply operation curve are curves showing the change of the values ​​of various operation attributes over time; The CPU operation curve includes a CPU temperature curve and a CPU utilization curve; the memory operation curve includes a memory utilization curve; the storage device operation curve includes a storage device read speed curve, a storage device write speed curve and a storage device remaining space curve; the processing unit operation curve includes a processing unit temperature curve and a processing unit utilization curve; the network interface operation curve includes a network interface delay curve, a network interface packet loss curve and a network interface transmission rate curve; the power supply operation curve includes a power supply power curve; The central processing unit temperature curve, the central processing unit utilization curve, the running memory utilization curve, the processing unit temperature curve, the processing unit utilization curve, the network interface delay curve and the network interface packet loss curve are defined as first-class curves; the storage device read speed curve, the storage device write speed curve, the storage device remaining space curve, the network interface transmission rate curve and the power supply power curve are defined as second-class curves.

[0023] S2: pre-processing the historical operation data of the integrated equipment to search and form a first curve segment set, extracting the first curve segment set to form a second curve segment set, calculating the reference value according to the second curve segment set, and generating historical operation reference data according to the reference value calculation result; In step S2, a historical operation attribute value change curve in the historical operation data corresponds to a historical operation attribute value change curve function. In the same detection cycle, the integrated device IE i The derivative of each historical operation attribute value change curve function is obtained, and the curve function obtained after the derivative is recorded as the historical operation attribute value change rate curve function; Find the moment when the historical operation attribute value change rate is zero in the historical operation attribute value change rate curve function, and in the corresponding historical operation attribute value change curve, take the moment when the historical operation attribute value change rate is zero as the center, intercept the curve segment of the system preset time length to form a first curve segment set; the curve segment does not include the case where the historical operation attribute value is always zero; the system preset time length of each historical operation attribute value change curve is different; If any two curve segments have overlapping parts, the curve segments with overlapping parts will be integrated; if any two curve segments do not have overlapping parts, they will be sorted according to the time sequence; In this embodiment, the CPU temperature change rate curve has a CPU temperature change rate of zero at moments t=10s and t=10.5s; and the system preset time length for capturing the CPU temperature change rate curve is 0.8s. For moment t=10s, it is necessary to capture the curve segment from t=9.6s to t=10.4s in the CPU temperature curve; for moment t=10.5s, it is necessary to capture the curve segment from t=10.1s to t=10.9s in the CPU temperature curve. There is an overlap between the above two curve segments, and the two curve segments with the overlap are integrated to form a curve segment from t=9.6s to t=10.9s.

[0024] Extract the curve segments in the first curve segment set, where the historical operation attribute value is a regional maximum value when the historical operation attribute value change rate is zero; the regional maximum value is the case where the historical operation attribute value change rate is greater than zero before the moment when the historical operation attribute value change rate is zero, and the historical operation attribute value change rate is less than zero after the moment when the historical operation attribute value change rate is zero; the extracted curve segments are combined into a second curve segment set CS of a class of curves a i ={CS a （i，1） , C.S. a （i，2） ,…,CS a （i，Ma）}, where Ma is the total number of curve segments of the a-th type of first-class curve, and the j-th curve segment of the a-th type of first-class curve is denoted as CS a （i，j） , where j∈[1,Ma]; Extract the curve segments in the second curve segment set, where the historical operation attribute value is a regional minimum value when the historical operation attribute value change rate is zero, and the regional minimum value is the case where the historical operation attribute value change rate is less than zero before the moment when the historical operation attribute value change rate is zero, and the historical operation attribute value change rate is greater than zero after the moment when the historical operation attribute value change rate is zero; the extracted curve segments are combined into the second curve segment set CS of the second type of curve b i ={CS b （i，1） , C.S. b （i，2） ,…,CS b （i，Mb）}, where Mb is the total number of curve segments of the b-th type II curve, and the j-th curve segment of the b-th type II curve is denoted as CS b （i，j） , where j∈[1,Mb]; For integrated equipment IE i Calculate the reference value of historical operation data, including the total reference value RVA of a type of curve i The specific calculation formula is as follows: RVA i =∑\s\do 3(a=1)A [α a ×(∑\s\do 3(j=1)Ma RCS a （i，j） / Ma)]; Where A represents the total number of the first curves, α a represents the weight of the a-th type I curve, RCS a Represents the curve segment CS a（i，j） The average value of the historical operating attribute values; Total reference value RVB of the second type curve i The specific calculation formula is as follows: RVB i =∑\s\do 3(b=1)B [α b ×(∑\s\do 3(j=1)Mb RCS b （i，j） / Mb)]; Where B represents the total number of second curves, α b Represents the weight of the b-th type II curve, RCS b Represents the curve segment CS b （i，j） The average value of the historical operating attribute values; Set the total reference value threshold of the first type of curve to β1, and set the total reference value threshold of the second type of curve to β2; The historical operation data whose total reference value of the first-class curve is greater than or equal to the threshold β1, or whose total reference value of the second-class curve is less than or equal to the threshold β2 are defined as the historical operation reference data.

[0025] In this embodiment, for the integrated device IE i , the first curve selects the CPU utilization curve and the running memory utilization curve; The curve function corresponding to the curve segment where the CPU utilization curve has a maximum value is Y=-(t-1) 2 +6, t∈[0.6, 1.4], RCS 1 =(∫\s\do 3(0.6)1.4-(t-1) 2 +6) / (1.4-0.6)=6, The curve function corresponding to the curve segment where the running memory utilization curve has a maximum value is Y=-(t-2) 2 +6, t∈[1.6, 2.4], RCS 2 =(∫\s\do 3(1.6)2.4-(t-2) 2 +6) / (2.4-1.6)=6, α1 is 0.5, α2 is 0.6, then RVA i =α1×RCS 1 +α2×RCS 2 =0.5×6+0.5×6=6, Set the total reference value threshold of a type of curve to 5, then the integrated device IE iThe total reference value of the first type of curve is greater than the total reference value threshold of the first type of curve, retain the above CPU utilization curve and running memory utilization curve, and convert the integrated device IE i The CPU utilization data and running memory utilization data are defined as historical running reference data.

[0026] S3: Extract the fault feature set through historical operation reference data, adjust the detection task scheduling of real-time operation data in real time according to the priority of equipment fault detection tasks, and use the real-time operation data of integrated equipment to determine the fault risk of integrated equipment; In step S3, the reference value of each type of curve of the integrated equipment that has experienced a fault is extracted from the historical operation reference data to form a type of curve fault reference value set; the reference value of each type of curve is compared to form a type of curve fault characteristic value set; the type of curve fault characteristic value set includes the minimum reference value of each type of curve; Extract the reference value of each type of Class II curve of the integrated equipment that has experienced a fault from the historical operation reference data to form a Class II curve fault reference value set; compare the reference value of each type of Class II curve to form a Class II curve fault characteristic value set; the Class II curve fault characteristic value set includes the maximum value of the reference value of each type of Class II curve; The first type of curve fault characteristic value set and the second type of curve fault characteristic value set are combined to form a fault characteristic parameter set; Prioritize the faults of the integrated equipment, adjust the detection task scheduling of the real-time operation data in real time according to the priority of the equipment fault detection task, calculate the reference value of the real-time operation data of the integrated equipment, and compare it with the fault feature values ​​corresponding to the fault feature set. If the reference value of one of the first-class curves is greater than or equal to the corresponding fault feature value, or the reference value of one of the second-class curves is less than or equal to the corresponding fault feature value, it is determined that the integrated equipment has a fault risk.

[0027] In this embodiment, the faults of the integrated devices are prioritized, the CPU fault is set to priority 1, and the running memory fault is set to priority 2; priority 1 is higher than priority 2, so when multiple integrated devices are simultaneously detected for faults, the reference value calculation of the CPU temperature curve and the CPU utilization curve in the integrated device is given priority, and compared with the fault feature values ​​corresponding to the fault feature set, after the calculation and comparison of the CPU temperature curve and the CPU utilization curve of all the integrated devices are completed, the reference value calculation and comparison operation are performed on the running memory utilization curve.

[0028] In this embodiment, a type of curve includes a central processing unit temperature curve, a central processing unit utilization curve, a running memory utilization curve, a processing unit temperature curve, a processing unit utilization curve, a network interface delay curve and a network interface packet loss curve. If the reference value of one of the type-one curves is greater than or equal to the corresponding fault characteristic value, it is determined that the integrated device is at risk of failure.

[0029] S4: Provide warnings and prompts to users based on fault risk assessment.

[0030] In step S4, if there is an integrated device with a risk of failure, the user is warned and the specific hardware device with the risk of failure is prompted. If there is no risk of failure in the integrated device, no warning or prompting is performed.

[0031] See also Figure 2 , the present invention provides a technical solution: an integrated equipment self-checking system based on OPS computer, characterized in that the system includes an integrated device, a cloud platform and a central detection host; The cloud platform is used to receive the operation data of the integrated device and transmit the operation data of the integrated device to the central detection host; The central detection host includes a data classification and integration module, a reference value analysis and calculation module, a fault feature extraction and determination module, and an early warning prompt module; The data classification and integration module is used to classify and integrate the operating data according to the hardware equipment of the integrated equipment, and define it as Class I curves and Class II curves; the reference value analysis and calculation module is used to pre-process and search the historical operating data of the integrated equipment, and calculate the reference value of the historical operating data after pre-processing and searching; the fault feature extraction and judgment module is used to extract the fault feature set, and use the real-time operating data of the integrated equipment to judge the fault risk of the integrated equipment; the early warning and prompt module warns and prompts the user according to the fault risk judgment.

[0032] The data classification and integration module includes a data classification unit and a data integration unit; The data classification unit is used to classify the operation data into historical operation data and real-time operation data, and classify the operation attribute value change curves contained in the historical operation data and the real-time operation data into a central processing unit operation curve, an operation memory operation curve, a storage device operation curve, a processing unit operation curve, a network interface operation curve and a power supply operation curve; The CPU operation curve includes a CPU temperature curve and a CPU utilization curve; the memory operation curve includes a memory utilization curve; the storage device operation curve includes a storage device read speed curve, a storage device write speed curve and a storage device remaining space curve; the processing unit operation curve includes a processing unit temperature curve and a processing unit utilization curve; the network interface operation curve includes a network interface delay curve, a network interface packet loss curve and a network interface transmission rate curve; the power supply operation curve includes a power supply power curve; The data integration unit is used to define the central processing unit temperature curve, the central processing unit utilization curve, the running memory utilization curve, the processing unit temperature curve, the processing unit utilization curve, the network interface delay curve and the network interface packet loss curve as a first type of curve; the storage device read speed curve, the storage device write speed curve, the storage device remaining space curve, the network interface transmission rate curve and the power supply power curve are defined as a second type of curve.

[0033] The reference value analysis and calculation module includes a reference value analysis search unit and a reference value calculation unit; The reference value analysis and search unit is used to analyze the integrated device IE in the same detection cycle. i The derivative of each historical operation attribute value change curve function is obtained, and the curve function obtained after the derivative is recorded as the historical operation attribute value change rate curve function; the moment when the historical operation attribute value change rate is zero in the historical operation attribute value change rate curve function is found, and in the corresponding historical operation attribute value change curve, the moment when the historical operation attribute value change rate is zero is taken as the center, and the curve segment of the system preset time length is intercepted to form a first curve segment set; the curve segment whose historical operation attribute value is a regional extreme value when the historical operation attribute value change rate is zero is extracted from the first curve segment set, and the extracted curve segments are formed into a second curve segment set; The reference value calculation unit is used to calculate the reference value of the historical operation data after pre-processing and searching.

[0034] The fault feature extraction and determination module includes a fault feature extraction unit and a fault risk determination module; The fault feature extraction unit is used to form a type I curve fault feature value set and a type II curve fault feature value set, and integrate the type I curve fault feature value set and the type II curve fault feature value set to form a fault feature parameter set; The fault risk determination module is used to calculate the reference value of the real-time operation data of the integrated equipment, and compare it with the fault feature values ​​corresponding to the fault feature set to determine the fault risk of the integrated equipment.

[0035] The early warning prompt module is used to warn users of integrated devices with failure risks and to prompt specific hardware devices with failure risks. It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0036] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An integrated equipment self-checking method based on OPS computer, characterized in that: The method comprises the following steps: S1: The integrated equipment is connected to the cloud platform through the network and transmits the operating data to the cloud platform in real time. The central detection host obtains the operating data of the integrated equipment from the cloud platform, classifies the operating data according to the hardware devices of the integrated equipment, and integrates the classified operating data to define Class I curves and Class II curves; S2: pre-processing the historical operation data of the integrated equipment to search and form a first curve segment set, extracting the first curve segment set to form a second curve segment set, calculating the reference value according to the second curve segment set, and generating historical operation reference data according to the reference value calculation result; S3: Extract the fault feature set through historical operation reference data, adjust the detection task scheduling of real-time operation data in real time according to the priority of equipment fault detection tasks, and use the real-time operation data of integrated equipment to determine the fault risk of integrated equipment; S4: Provide warnings and prompts to users based on fault risk assessment.

2. The integrated equipment self-checking method based on OPS computer according to claim 1 is characterized in that: In step S1, the integrated devices connected to the cloud platform are grouped into a set IE={IE1, IE2, ..., IE n }, where n represents the total number of integrated devices, and the i-th integrated device is recorded as IE i , where i∈[1,n]; The operation data includes historical operation data and real-time operation data, and the historical operation data and real-time operation data both contain operation attribute value change curves, and the operation attribute value change curves include a central processing unit operation curve, an operation memory operation curve, a storage device operation curve, a processing unit operation curve, a network interface operation curve, and a power supply operation curve; The central processing unit operation curve, the operation memory operation curve, the storage device operation curve, the processing unit operation curve, the network interface operation curve and the power supply operation curve are curves showing the change of the values ​​of various operation attributes over time; The CPU operation curve includes a CPU temperature curve and a CPU utilization curve; the memory operation curve includes a memory utilization curve; the storage device operation curve includes a storage device read speed curve, a storage device write speed curve and a storage device remaining space curve; the processing unit operation curve includes a processing unit temperature curve and a processing unit utilization curve; the network interface operation curve includes a network interface delay curve, a network interface packet loss curve and a network interface transmission rate curve; the power supply operation curve includes a power supply power curve; The central processing unit temperature curve, the central processing unit utilization curve, the running memory utilization curve, the processing unit temperature curve, the processing unit utilization curve, the network interface delay curve and the network interface packet loss curve are defined as first-class curves; the storage device read speed curve, the storage device write speed curve, the storage device remaining space curve, the network interface transmission rate curve and the power supply power curve are defined as second-class curves.

3. The integrated equipment self-checking method based on OPS computer according to claim 2 is characterized in that: In step S2, a historical operation attribute value change curve in the historical operation data corresponds to a historical operation attribute value change curve function. In the same detection cycle, the integrated device IE i The derivative of each historical operation attribute value change curve function is obtained, and the curve function obtained after the derivative is recorded as the historical operation attribute value change rate curve function; Find the moment when the historical operation attribute value change rate is zero in the historical operation attribute value change rate curve function, and in the corresponding historical operation attribute value change curve, take the moment when the historical operation attribute value change rate is zero as the center, intercept the curve segment of the system preset time length to form a first curve segment set; the curve segment does not include the case where the historical operation attribute value is always zero; the system preset time length of each historical operation attribute value change curve is different; If any two curve segments have overlapping parts, the curve segments with overlapping parts will be integrated; if any two curve segments do not have overlapping parts, they will be sorted according to the time sequence; Extract the curve segments in the first curve segment set, where the historical operation attribute value is a regional maximum value when the historical operation attribute value change rate is zero; the regional maximum value is the case where the historical operation attribute value change rate is greater than zero before the moment when the historical operation attribute value change rate is zero, and the historical operation attribute value change rate is less than zero after the moment when the historical operation attribute value change rate is zero; the extracted curve segments are combined into a second curve segment set CS of a class of curves a i ={CS a （i，1） , C.S. a （i，2） ,…,CS a （i，Ma） }, where Ma is the total number of curve segments of the a-th type of first-class curve, and the j-th curve segment of the a-th type of first-class curve is denoted as CS a （i，j） , where j∈[1,Ma]; Extract the curve segments in the second curve segment set, where the historical operation attribute value is a regional minimum value when the historical operation attribute value change rate is zero, and the regional minimum value is the case where the historical operation attribute value change rate is less than zero before the moment when the historical operation attribute value change rate is zero, and the historical operation attribute value change rate is greater than zero after the moment when the historical operation attribute value change rate is zero; the extracted curve segments are combined into the second curve segment set CS of the second type of curve b i ={CS b （i，1） , C.S. b （i，2） ,…,CS b （i，Mb） }, where Mb is the total number of curve segments of the b-th type II curve, and the j-th curve segment of the b-th type II curve is denoted as CS b （i，j） , where j∈[1,Mb]; For integrated equipment IE i Calculate the reference value of historical operation data, including the total reference value RVA of a type of curve i The specific calculation formula is as follows: RVA i =∑\s\do 3(a=1)A [α a ×(∑\s\do 3(j=1)Ma RCS a （i，j） / Ma)]; Where A represents the total number of the first curve, α a represents the weight of the a-th type I curve, RCS a Represents the curve segment CS a （i，j） The average value of the historical operating attribute values; Total reference value RVB of the second type curve i The specific calculation formula is as follows: RVB i =∑\s\do 3(b=1)B [α b ×(∑\s\do 3(j=1)Mb RCS b （i，j） / Mb)]; Where B represents the total number of second curves, α b Represents the weight of the b-th type II curve, RCS b Represents the curve segment CS b （i，j） The average value of the historical operating attribute values; Set the total reference value threshold of the first type of curve to β1, and set the total reference value threshold of the second type of curve to β2; The historical operation data whose total reference value of the first-class curve is greater than or equal to the threshold β1, or whose total reference value of the second-class curve is less than or equal to the threshold β2 are defined as the historical operation reference data.

4. The integrated equipment self-checking method based on OPS computer according to claim 3 is characterized in that: In step S3, the reference value of each type of curve of the integrated equipment that has experienced a fault is extracted from the historical operation reference data to form a type of curve fault reference value set; the reference value of each type of curve is compared to form a type of curve fault characteristic value set; The first-class curve fault characteristic value set includes the minimum reference value of each first-class curve; Extract the reference value of each type of Class II curve of the integrated equipment that has experienced a fault from the historical operation reference data to form a Class II curve fault reference value set; compare the reference value of each type of Class II curve to form a Class II curve fault characteristic value set; The two-type curve fault characteristic value set includes the maximum reference value of each type of two-type curve; The first type of curve fault characteristic value set and the second type of curve fault characteristic value set are combined to form a fault characteristic parameter set; Prioritize the faults of the integrated equipment, adjust the detection task scheduling of the real-time operation data in real time according to the priority of the equipment fault detection task, calculate the reference value of the real-time operation data of the integrated equipment, and compare it with the fault feature values ​​corresponding to the fault feature set. If the reference value of one of the first-class curves is greater than or equal to the corresponding fault feature value, or the reference value of one of the second-class curves is less than or equal to the corresponding fault feature value, it is determined that the integrated equipment has a fault risk.

5. The integrated equipment self-checking method based on OPS computer according to claim 4 is characterized in that: In step S4, if there is an integrated device with a risk of failure, the user is warned and the specific hardware device with the risk of failure is prompted. If there is no risk of failure in the integrated device, no warning or prompting is performed.

6. An integrated equipment self-checking system based on an OPS computer, the system is applied to implement an integrated equipment self-checking method based on an OPS computer as described in any one of claims 1 to 5, characterized in that: The system includes integrated equipment, cloud platform and central detection host; The cloud platform is used to receive the operation data of the integrated device and transmit the operation data of the integrated device to the central detection host; The central detection host includes a data classification and integration module, a reference value analysis and calculation module, a fault feature extraction and determination module, and an early warning prompt module; The data classification and integration module is used to classify and integrate the operation data according to the hardware devices of the integrated device, and define them as Class I curves and Class II curves; The reference value analysis and calculation module is used to pre-process and search the historical operation data of the integrated equipment, and to calculate the reference value of the historical operation data after pre-processing and searching; the fault feature extraction and determination module is used to extract the fault feature set, and to determine the fault risk of the integrated equipment using the real-time operation data of the integrated equipment; The early warning and prompting module warns and prompts the user according to the fault risk determination.

7. The integrated equipment self-checking system based on OPS computer according to claim 6 is characterized in that: The data classification and integration module includes a data classification unit and a data integration unit; The data classification unit is used to classify the operation data into historical operation data and real-time operation data, and classify the operation attribute value change curves contained in the historical operation data and the real-time operation data into a central processing unit operation curve, an operation memory operation curve, a storage device operation curve, a processing unit operation curve, a network interface operation curve and a power supply operation curve; The CPU operation curve includes a CPU temperature curve and a CPU utilization curve; the memory operation curve includes a memory utilization curve; the storage device operation curve includes a storage device read speed curve, a storage device write speed curve and a storage device remaining space curve; the processing unit operation curve includes a processing unit temperature curve and a processing unit utilization curve; the network interface operation curve includes a network interface delay curve, a network interface packet loss curve and a network interface transmission rate curve; the power supply operation curve includes a power supply power curve; The data integration unit is used to define the central processing unit temperature curve, the central processing unit utilization curve, the running memory utilization curve, the processing unit temperature curve, the processing unit utilization curve, the network interface delay curve and the network interface packet loss curve as a first type of curve; the storage device read speed curve, the storage device write speed curve, the storage device remaining space curve, the network interface transmission rate curve and the power supply power curve are defined as a second type of curve.

8. The integrated equipment self-checking system based on OPS computer according to claim 6 is characterized in that: The reference value analysis and calculation module includes a reference value analysis search unit and a reference value calculation unit; The reference value analysis and search unit is used to analyze the integrated device IE in the same detection cycle. i The derivative of each historical operation attribute value change curve function is obtained, and the curve function obtained after the derivative is recorded as the historical operation attribute value change rate curve function; the moment when the historical operation attribute value change rate is zero in the historical operation attribute value change rate curve function is found, and in the corresponding historical operation attribute value change curve, the moment when the historical operation attribute value change rate is zero is taken as the center, and the curve segment of the system preset time length is intercepted to form a first curve segment set; the curve segment whose historical operation attribute value is a regional extreme value when the historical operation attribute value change rate is zero is extracted from the first curve segment set, and the extracted curve segments are formed into a second curve segment set; The reference value calculation unit is used to calculate the reference value of the historical operation data after pre-processing and searching.

9. The integrated equipment self-checking system based on OPS computer according to claim 6 is characterized in that: The fault feature extraction and determination module includes a fault feature extraction unit and a fault risk determination module; The fault feature extraction unit is used to form a type I curve fault feature value set and a type II curve fault feature value set, and integrate the type I curve fault feature value set and the type II curve fault feature value set to form a fault feature parameter set; The fault risk determination module is used to calculate the reference value of the real-time operation data of the integrated equipment, and compare it with the fault feature values ​​corresponding to the fault feature set to determine the fault risk of the integrated equipment.

10. The integrated equipment self-checking system based on OPS computer according to claim 6 is characterized in that: The early warning prompt module is used to warn users of integrated devices with failure risks and to prompt specific hardware devices with failure risks.

Images