Network equipment predictive maintenance method and system based on situation awareness

Abstract

The invention belongs to the field of equipment safety monitoring, particularly relates to a network equipment predictive maintenance method and system based on situation awareness, and aims to solve the problems of low network safety and low oil and gas pipeline station maintenance accuracy in the prior art. The method comprises the following steps: for each type of target equipment, acquiring historical operation data and real-time operation data, and further constructing a situation awareness predictive maintenance model and a curve trend standard diagram; further obtaining an operation curve trend prediction map of the target equipment; performing situation awareness data behavior analysis to obtain predicted fault data of the target equipment; and updating the situation awareness predictive maintenance model and the curve trend standard diagram based on predictive fault data. According to the method, the situation awareness predictive maintenance model is independently constructed for each type of target equipment, the safety of the predictive maintenance model and the curve high network is continuously optimized along with long-time use, and the maintenance accuracy of the oil and gas pipeline station is improved.

Description

Background Art

[0002] Since the data collection method of oil and gas pipeline stations is that each equipment module sends data to the center, the intrusion of each equipment module will damage the data network of the center, and the analysis of a single data cannot make a holistic analysis of the network equipment and network security equipment of the entire station. Therefore, a predictive maintenance method for network equipment and network security equipment based on situational awareness is very necessary. Summary of the invention

[0003] In order to solve the above-mentioned problem in the prior art, that is, the prior art cannot perform an overall analysis of the network equipment and network security equipment of the entire station, so that the accuracy of network security and oil and gas pipeline station maintenance is insufficient, the present invention provides a network equipment predictive maintenance method based on situation awareness, the method comprising:

[0004] Step S100, for each target device, historical operation data and real-time operation data are obtained through the central situation awareness module, and a situation awareness predictive maintenance model and a curve trend standard diagram are constructed based on the historical operation data;

[0005] Step S200, obtaining an operation curve trend prediction diagram of the target equipment through the situation awareness predictive maintenance model;

[0006] Step S300, performing situation awareness data behavior analysis based on the curve trend prediction graph and the curve trend standard graph to obtain predicted fault data of the target device;

[0007] Step S400, uploading the predicted fault data to a situation awareness platform;

[0008] Step S500, the situation awareness platform updates the situation awareness predictive maintenance model and the curve trend standard diagram based on the predicted fault data to obtain a new situation awareness predictive maintenance model and a new curve trend standard diagram;

[0009] Step S600, using the new situation awareness predictive maintenance model and the new curve trend standard diagram, the real-time operation data is subjected to the method of steps S200 to S300 to obtain new predicted fault data and then select a predictive maintenance plan.

[0010] In some preferred implementations, the predicted fault data includes: a predicted value of a fault occurrence time, a predicted value of a fault occurrence period, a predicted value of a fault point, a predicted fault cause, and a predicted value of a fault location.

[0011] In some preferred embodiments, the situation awareness predictive maintenance model is obtained by:

[0012] Obtain historical operation data of the target device as training data;

[0013] Dividing the training data into a plurality of time periods;

[0014] Input the training data of the tth period into the situation awareness predictive maintenance model to be trained to obtain the predicted value of the training data of the t+1th period;

[0015] Calculate the loss function based on the predicted value of the training data in the t+1th period and the training data in the t+1th period in the training data;

[0016] The loss function is reduced by a stochastic gradient descent algorithm, and an alarm threshold is set to obtain a situation awareness predictive maintenance model.

[0017] In some preferred embodiments, the curve trend standard graph is obtained by:

[0018] Based on the historical operation data, the operation data curve that does not trigger the preset alarm threshold is fitted to obtain a curve trend standard graph.

[0019] In some preferred embodiments, the target equipment includes oil and gas pipeline field network equipment, network security equipment and oil and gas pipeline equipment.

[0020] In some preferred embodiments, the step S500 calculates a loss function based on the predicted fault data and the real-time operation data at the prediction time. If the loss function is greater than a set update threshold, the situation awareness predictive maintenance model parameters are adjusted to reduce the loss function, thereby obtaining a new situation awareness predictive maintenance model.

[0021] If the real-time operation data does not trigger the set alarm threshold, the real-time operation data is added to the historical operation data, and the curve trend standard graph is fitted to obtain a new curve trend standard graph.

[0022] In some preferred embodiments, the method for obtaining the curve trend standard graph further includes:

[0023] Divide historical operation data into multiple types of fault history data according to fault causes, fault locations and fault points;

[0024] The historical fault data of the same type are fitted to obtain a standard fault curve trend diagram.

[0025] In some preferred embodiments, the method further comprises, based on historical operation data, dividing the difference between the curve data of the fault and the standard curve trend graph into a plurality of intervals, and using the critical points of the intervals as balance points.

[0026] Another aspect of the present invention provides a network equipment predictive maintenance system based on situation awareness, the system comprising:

[0027] The prediction model building and curve trend determination module is configured to obtain historical operation data and real-time operation data for each target device through the central situation awareness module, and build a situation awareness predictive maintenance model and a curve trend standard diagram based on the historical operation data;

[0028] An operation curve prediction module is configured to obtain an operation curve trend prediction diagram of a target device based on real-time operation data through the situation awareness predictive maintenance model;

[0029] A predicted fault data acquisition module, configured to perform situation awareness data behavior analysis based on the curve trend prediction graph and the curve trend standard graph to acquire predicted fault data of the target device;

[0030] A data uploading module, configured to upload the predicted fault data to a situation awareness platform;

[0031] A prediction model and trend graph updating module, configured for the situation awareness platform to update the situation awareness predictive maintenance model and the curve trend standard graph based on the predicted fault data, and obtain a new situation awareness predictive maintenance model and a new curve trend standard graph;

[0032] The predictive maintenance scheme acquisition module is configured to perform the functions of the operation curve prediction module and the predicted fault data acquisition module on the real-time operation data through the new situation awareness predictive maintenance model and the new curve trend standard diagram, obtain new predicted fault data and then select a predictive maintenance scheme.

[0033] Beneficial effects of the present invention:

[0034] (1) The present invention constructs a situational awareness predictive maintenance model for each target device and continuously optimizes the predictive maintenance model and curve over a long period of time, so as to timely push maintenance information through intelligent detection technology, improve network security, and improve the accuracy of oil and gas pipeline station maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0036] Figure 1 It is a flow chart of a method for predictive maintenance of network equipment based on situation awareness in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0038] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0039] In order to more clearly illustrate the network equipment predictive maintenance method based on situation awareness of the present invention, the following is combined with Figure 1 Each step in the embodiment of the present invention is described in detail.

[0040] The network equipment predictive maintenance method based on situation awareness according to the first embodiment of the present invention includes steps S100 to S600, and each step is described in detail as follows:

[0041] In this embodiment, the transmission mode of the original network is changed, and the original equipment collection module is changed from sending data to collecting data by the center, so as to collect real-time and historical operation data of oil and gas pipeline station network equipment, network security equipment and other equipment. The historical data includes all operation data of the corresponding equipment from the initial working time to before the failure occurs.

[0042] Step S100, for each target device, historical operation data and real-time operation data are obtained through the central situation awareness module, and a situation awareness predictive maintenance model and a curve trend standard diagram are constructed based on the historical operation data;

[0043] In this embodiment, the target equipment includes oil and gas pipeline field network equipment, network security equipment and oil and gas pipeline equipment.

[0044] In this embodiment, the situation awareness predictive maintenance model is obtained by:

[0045] Obtain historical operation data of the target device as training data;

[0046] Dividing the training data into a plurality of time periods;

[0047] Input the training data of the tth period into the situation awareness predictive maintenance model to be trained to obtain the predicted value of the training data of the t+1th period;

[0048] Calculate the loss function based on the predicted value of the training data in the t+1th period and the training data in the t+1th period in the training data;

[0049] The loss function is reduced by a stochastic gradient descent algorithm, and an alarm threshold is set to obtain a situation awareness predictive maintenance model.

[0050] The alarm threshold is the safety threshold of the equipment used for predictive maintenance determined by the historical data of the pattern. The alarm threshold is used to indicate the value range of the data when the network equipment and network security equipment are sub-healthy. The lower limit of the alarm threshold is the lower limit of the predictive maintenance of the network equipment and network security equipment, and the upper limit of the alarm threshold is the upper limit of the predictive maintenance of the network equipment and network security equipment.

[0051] In this embodiment, the curve trend standard graph is obtained by:

[0052] Based on the historical operation data, the operation data curve that does not trigger the preset alarm threshold is fitted to obtain a curve trend standard graph.

[0053] In this embodiment, the method for obtaining the curve trend standard graph further includes:

[0054] Divide historical operation data into multiple types of fault history data according to fault causes, fault locations and fault points;

[0055] The historical fault data of the same type are fitted to obtain a standard fault curve trend diagram.

[0056] Step S200, obtaining an operation curve trend prediction diagram of the target equipment through the situation awareness predictive maintenance model;

[0057] Step S300, performing situation awareness data behavior analysis based on the curve trend prediction graph and the curve trend standard graph to obtain predicted fault data of the target device;

[0058] In this embodiment, the predicted fault data includes: a predicted value of a fault occurrence time, a predicted value of a fault occurrence period, a predicted value of a fault point, a predicted fault cause, and a predicted value of a fault location.

[0059] Step S400, uploading the predicted fault data to a situation awareness platform;

[0060] Step S500, the situation awareness platform updates the situation awareness predictive maintenance model and the curve trend standard diagram based on the predicted fault data to obtain a new situation awareness predictive maintenance model and a new curve trend standard diagram;

[0061] In this embodiment, the step S500 specifically includes: calculating a loss function based on the predicted fault data and the real-time operation data at the prediction time, and if the loss function is greater than a set update threshold, adjusting the situation awareness predictive maintenance model parameters to reduce the loss function, thereby obtaining a new situation awareness predictive maintenance model;

[0062] If the real-time operation data does not trigger the set alarm threshold, the real-time operation data is added to the historical operation data, and the curve trend standard graph is fitted to obtain a new curve trend standard graph.

[0063] Step S600, through the new situational awareness predictive maintenance model and the new curve trend standard graph, the real-time operation data is subjected to the method of step S200 to step S300 to obtain new predicted fault data and then select a predictive maintenance plan. This embodiment obtains the time point, fault point, fault cause and location that may require maintenance from the new predicted fault data, and transmits them to the situational awareness platform for storage, analysis and calculation, and then selects a predictive maintenance plan. In addition, the remaining life of the equipment can also be determined based on the new predicted fault data.

[0064] In this embodiment, the operation module is also used to display the work order list, perform work order handling operations, and track the work order handling process and results until a closed loop is formed after maintenance is completed or faults are eliminated.

[0065] In this embodiment, the method further includes dividing the difference between the curve data of the fault and the standard curve trend graph into a plurality of intervals based on the historical operation data, and using the critical points of the intervals as the balance points.

[0066] Although the various steps in the above embodiment are described in the above-mentioned order, those skilled in the art can understand that in order to achieve the effect of this embodiment, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in a reverse order. These simple changes are within the scope of protection of the present invention.

[0067] A network equipment predictive maintenance system based on situational awareness according to a second embodiment of the present invention comprises:

[0068] The prediction model building and curve trend determination module is configured to obtain historical operation data and real-time operation data for each target device through the central situation awareness module, and build a situation awareness predictive maintenance model and a curve trend standard diagram based on the historical operation data;

[0069] An operation curve prediction module is configured to obtain an operation curve trend prediction diagram of a target device based on real-time operation data through the situation awareness predictive maintenance model;

[0070] A predicted fault data acquisition module, configured to perform situation awareness data behavior analysis based on the curve trend prediction graph and the curve trend standard graph to acquire predicted fault data of the target device;

[0071] A data uploading module, configured to upload the predicted fault data to a situation awareness platform;

[0072] A prediction model and trend graph updating module, configured for the situation awareness platform to update the situation awareness predictive maintenance model and the curve trend standard graph based on the predicted fault data, and obtain a new situation awareness predictive maintenance model and a new curve trend standard graph;

[0073] The predictive maintenance scheme acquisition module is configured to perform the functions of the operation curve prediction module and the predicted fault data acquisition module on the real-time operation data through the new situation awareness predictive maintenance model and the new curve trend standard diagram, obtain new predicted fault data and then select a predictive maintenance scheme.

[0074] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0075] It should be noted that the situational awareness-based network equipment predictive maintenance system provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiment can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.

[0076] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related instructions of the storage device and processing device described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0077] Those skilled in the art should be able to appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0078] The terms "first", "second", etc. are used to distinguish similar objects rather than to describe or indicate a particular order or sequence.

[0079] The term "comprise" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus / device.

[0080] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A network equipment predictive maintenance method based on situational awareness, characterized in that: The method comprises: Step S100, for each target device, historical operation data and real-time operation data are obtained through the central situation awareness module, and a situation awareness predictive maintenance model and a curve trend standard diagram are constructed based on the historical operation data; Step S200, obtaining an operation curve trend prediction diagram of the target equipment through the situation awareness predictive maintenance model; Step S300, performing situation awareness data behavior analysis based on the curve trend prediction graph and the curve trend standard graph to obtain predicted fault data of the target device; Step S400, uploading the predicted fault data to a situation awareness platform; Step S500, the situation awareness platform updates the situation awareness predictive maintenance model and the curve trend standard diagram based on the predicted fault data to obtain a new situation awareness predictive maintenance model and a new curve trend standard diagram; Step S600, using the new situation awareness predictive maintenance model and the new curve trend standard diagram, the real-time operation data is subjected to the method of steps S200 to S300 to obtain new predicted fault data and then select a predictive maintenance plan.

2. The network equipment predictive maintenance method based on situational awareness according to claim 1 is characterized in that: The predicted fault data includes: a predicted value of a fault occurrence time, a predicted value of a fault occurrence period, a predicted value of a fault point, a predicted fault cause and a predicted value of a fault location.

3. The network equipment predictive maintenance method based on situational awareness according to claim 1 is characterized in that: The situation awareness predictive maintenance model is obtained by: Obtain historical operation data of the target device as training data; Dividing the training data into a plurality of time periods; Input the training data of the tth period into the situation awareness predictive maintenance model to be trained to obtain the predicted value of the training data of the t+1th period; Calculate the loss function based on the predicted value of the training data in the t+1th period and the training data in the t+1th period in the training data; The loss function is reduced by a stochastic gradient descent algorithm, and an alarm threshold is set to obtain a situation awareness predictive maintenance model.

4. The network equipment predictive maintenance method based on situational awareness according to claim 1, characterized in that: The curve trend standard graph is obtained by: Based on the historical operation data, the operation data curve that does not trigger the preset alarm threshold is fitted to obtain a curve trend standard graph.

5. The network equipment predictive maintenance method based on situational awareness according to claim 1, characterized in that: The target equipment includes oil and gas pipeline field network equipment, network security equipment and oil and gas pipeline equipment.

6. The network equipment predictive maintenance method based on situational awareness according to claim 1, characterized in that: The step S500 specifically includes: calculating a loss function based on the predicted fault data and the real-time operation data at the prediction time, and if the loss function is greater than a set update threshold, adjusting the situation awareness predictive maintenance model parameters to reduce the loss function, thereby obtaining a new situation awareness predictive maintenance model; If the real-time operation data does not trigger the set alarm threshold, the real-time operation data is added to the historical operation data, and the curve trend standard graph is fitted to obtain a new curve trend standard graph.

7. The network equipment predictive maintenance method based on situational awareness according to claim 1, characterized in that: The method for obtaining the curve trend standard graph further includes: Divide historical operation data into multiple types of fault history data according to fault causes, fault locations and fault points; The historical fault data of the same type are fitted to obtain a standard fault curve trend diagram.

8. The network equipment predictive maintenance method based on situational awareness according to claim 1, characterized in that: The method further includes dividing the difference between the curve data of the fault and the standard curve trend diagram into a plurality of intervals based on the historical operation data, and using the critical points of the intervals as the balance points.

9. A network equipment predictive maintenance system based on situational awareness, characterized in that: The system comprises: The prediction model building and curve trend determination module is configured to obtain historical operation data and real-time operation data for each target device through the central situation awareness module, and build a situation awareness predictive maintenance model and a curve trend standard diagram based on the historical operation data; An operation curve prediction module is configured to obtain an operation curve trend prediction diagram of a target device based on real-time operation data through the situation awareness predictive maintenance model; A predicted fault data acquisition module, configured to perform situation awareness data behavior analysis based on the curve trend prediction graph and the curve trend standard graph to acquire predicted fault data of the target device; A data uploading module, configured to upload the predicted fault data to a situation awareness platform; A prediction model and trend graph updating module, configured for the situation awareness platform to update the situation awareness predictive maintenance model and the curve trend standard graph based on the predicted fault data, and obtain a new situation awareness predictive maintenance model and a new curve trend standard graph; The predictive maintenance scheme acquisition module is configured to perform the functions of the operation curve prediction module and the predicted fault data acquisition module on the real-time operation data through the new situation awareness predictive maintenance model and the new curve trend standard diagram, obtain new predicted fault data and then select a predictive maintenance scheme.

Images