Emergency recovery method and device based on industrial control host computer and electronic equipment

Abstract

The application belongs to the field of industrial control and provides an emergency recovery method and device based on an industrial control host computer and electronic equipment, the method comprising: obtaining running state data of the industrial control host computer; extracting abnormal running data in the running state data; based on the abnormal running data, diagnosing a fault of the industrial control host computer to obtain a fault type and a fault position; calling an emergency recovery strategy corresponding to the fault type and the fault position from an emergency plan tree diagram; and executing the emergency recovery strategy to perform emergency recovery on the industrial host computer. The scheme provided by the application can accurately diagnose the fault type and the fault position according to the abnormal running data and obtain the emergency recovery strategy by using the emergency plan tree diagram, can efficiently and accurately realize emergency recovery on the industrial control host computer, solves the problems of low efficiency and poor reliability of the traditional emergency recovery method depending on manual intervention, and achieves the beneficial effects of efficient and reliable emergency recovery.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial control, and in particular to an emergency recovery method and device based on an industrial control host computer and electronic equipment. BACKGROUND

[0002] The emergency recovery of a host computer is generally a process in which the host computer can quickly and effectively recover to a normal working state under certain faults or abnormal conditions. In the field of industrial control, the host computer is the control core part, and the efficiency of its emergency recovery will directly affect the control stability and safety of the control site.

[0003] In related technologies, the traditional emergency recovery method mainly relies on manual intervention, such as manually restarting the system, manually restoring backup data, and manually reinstalling the operating system. The manual intervention method not only requires high professional skills of the operator, but also consumes time and effort in manual recovery operations, making it difficult to deal with emergency situations.

[0004] Therefore, the traditional emergency recovery method relying on manual intervention has the problems of low efficiency and poor reliability. SUMMARY

[0005] The present application provides an emergency recovery method and device based on an industrial control host computer and electronic equipment to solve the defects of low efficiency and poor reliability of the traditional emergency recovery method relying on manual intervention.

[0006] In one aspect, the present application provides an emergency recovery method based on an industrial control host computer, which comprises:

[0007] Obtaining running state data of an industrial control host computer;

[0008] Extracting abnormal running data in the running state data;

[0009] Based on the abnormal running data, diagnosing the fault of the industrial control host computer to obtain a fault type and a fault location;

[0010] Retrieving an emergency recovery strategy corresponding to the fault type and the fault location from a pre-constructed emergency plan tree diagram; wherein the emergency plan tree diagram is established with the fault type, the fault location, and the emergency recovery strategy of the industrial host computer as nodes;

[0011] Executing the emergency recovery strategy to perform emergency recovery on the industrial host computer.

[0012] According to the emergency recovery method based on the industrial control host computer provided by the present application, the abnormal running data in the running state data is extracted, which comprises:

[0013] Compare each operation parameter in the operation state data with a parameter threshold corresponding to the operation parameter respectively to obtain a comparison result;

[0014] If the comparison result is that the operation parameter deviates from the parameter threshold for more than a preset time length, it is determined that the operation parameter is abnormal operation data, and the abnormal operation data is extracted.

[0015] According to the emergency recovery method based on the industrial control host computer provided by the application, the abnormal operation data is used to perform fault diagnosis on the industrial control host computer to obtain a fault type and a fault position, including:

[0016] The abnormal operation data is input into a pre-constructed fault diagnosis model to obtain a fault diagnosis result output by the fault diagnosis model; wherein, the fault diagnosis result is used to represent a root source position and a fault cause that cause the abnormal operation data to appear;

[0017] According to the root source position and the fault cause, a fault type and a fault position are determined.

[0018] According to the emergency recovery method based on the industrial control host computer provided by the application, the fault diagnosis model is obtained through the following process, including:

[0019] Obtain historical fault log data of the industrial control host computer;

[0020] Extract abnormal operation data samples, root source position samples and fault cause samples from the historical fault log data to establish a sample data set;

[0021] Establish a fault prediction network model based on a deep learning neural network architecture;

[0022] Train the fault prediction network model through the sample data set to obtain a fault diagnosis model.

[0023] According to the emergency recovery method based on the industrial control host computer provided by the application, after obtaining the fault diagnosis model, the method further includes:

[0024] Obtain fault log update data of the industrial control host computer within a preset period;

[0025] Optimize model parameters of the fault diagnosis model based on the fault log update data.

[0026] According to the emergency recovery method based on the industrial control host computer provided by the application, the emergency recovery strategy is multiple, and the execution of the emergency recovery strategy includes:

[0027] The emergency recovery strategy with the highest execution level according to the preset priority is executed, and whether the fault at the current fault position is eliminated is judged, to obtain a judgment result;

[0028] If the judgment result is that the fault at the current fault position is not eliminated, the next level of emergency recovery strategy is executed until the judgment result is that the fault at the current fault position is eliminated.

[0029] According to the emergency recovery method based on the industrial control host computer provided by the application, after the emergency recovery strategy is executed to perform emergency recovery on the industrial host computer, the method further comprises:

[0030] Obtaining running state data of the industrial host computer after emergency recovery;

[0031] Comparing the running state data after emergency recovery with the running state data before emergency recovery and standard state data to obtain a comparison result;

[0032] According to the comparison result, the emergency recovery effect of the industrial host computer is evaluated to obtain an evaluation result.

[0033] According to the emergency recovery method based on the industrial control host computer provided by the application, after the evaluation result is obtained, the method further comprises:

[0034] According to the evaluation result, a state adjustment strategy is determined;

[0035] According to the state adjustment strategy, at least part of the running state data of the industrial host computer is adjusted.

[0036] In another aspect, the application also provides an emergency recovery device based on an industrial control host computer, comprising:

[0037] An obtaining module for obtaining running state data of an industrial control host computer;

[0038] An extracting module for extracting abnormal running data in the running state data;

[0039] A diagnosing module for diagnosing a fault of the industrial control host computer based on the abnormal running data to obtain a fault type and a fault position;

[0040] A calling module for calling an emergency recovery strategy corresponding to the fault type and the fault position from a pre-constructed emergency plan tree diagram; wherein the emergency plan tree diagram is established with the fault type, the fault position and the emergency recovery strategy of the industrial host computer as nodes;

[0041] An executing module for executing the emergency recovery strategy to perform emergency recovery on the industrial host computer.

[0042] In another aspect, the present application also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the industrial control host-based emergency recovery method according to any one of the above aspects when executing the program.

[0043] The industrial control host-based emergency recovery method, device and electronic device provided by the present application can automatically implement the emergency recovery process of the industrial control host, accurately diagnose the fault type and fault location according to the abnormal operation data, and accurately obtain the emergency recovery strategy by using the emergency plan tree diagram, thereby efficiently and accurately implementing the emergency recovery of the industrial control host, solving the problems of low efficiency and poor reliability of the traditional emergency recovery method relying on manual intervention, and achieving the beneficial effects of efficient and reliable emergency recovery. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0045] Figure 1 is a flowchart of the industrial control host-based emergency recovery method provided by the embodiments of the present application;

[0046] Figure 2 is a structural diagram of the industrial control host-based emergency recovery device provided by the embodiments of the present application;

[0047] Figure 3 is a structural diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0048] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0049] First, the relevant technical terms involved in this invention will be explained as follows:

[0050] Industrial control is accomplished by various automated systems, including program control, sensor feedback, and process monitoring. Industrial control has irreplaceable advantages in large power plants, aerospace, dam construction, industrial temperature control and heating, and ceramics.

[0051] A host computer is a computer that can directly issue control commands. It requires programming and has a dedicated development system. It usually displays various signal changes (such as hydraulic pressure, water level, temperature, etc.) on a screen. In the field of industrial control, industrial PCs, workstations, and touch screens are usually used as host computers for industrial control.

[0052] Host computer malfunctions include temporary files affecting processing speed, newly installed application software causing system lag, network failures, virus intrusion, network attacks, and other abnormal situations.

[0053] Emergency recovery refers to the ability to quickly restore the system to normal operation when a fault occurs, thereby reducing the downtime of the host computer.

[0054] The following is combined Figures 1 to 3 This invention describes in detail the emergency recovery method, device, and electronic equipment based on an industrial control host computer provided in the embodiments of the present invention.

[0055] Figure 1 This is a flowchart illustrating the emergency recovery method based on an industrial control host computer provided in an embodiment of the present invention.

[0056] like Figure 1 As shown in the embodiment of the present invention, the emergency recovery method based on an industrial control host computer can be executed by an electronic device with data transmission and reception and data processing functions. The method mainly includes the following steps:

[0057] Step 110: Obtain the operating status data of the industrial control host computer.

[0058] In this embodiment, the operating status data of the industrial host computer can characterize the real-time working status of the industrial host computer. For example, the operating status data may include information such as CPU utilization, memory utilization, and network connection status.

[0059] Step 120: Extract abnormal running data from the running status data.

[0060] It can be understood that the abnormal operation data can be data deviating from normal values or normal states in the operation state data. In actual application, each operation parameter in the operation state data can be compared with normal values or normal states to determine and extract the abnormal operation data.

[0061] Step 130: Based on the abnormal operation data, fault diagnosis is performed on the industrial control host computer to obtain a fault type and a fault position.

[0062] In this embodiment, the fault type and the fault position of the industrial control host computer can be diagnosed by analyzing the abnormal operation data. In actual application, the abnormal operation data can be one or multiple, and therefore the fault type and the fault position can also be one or multiple. For example, the fault type can be a hardware fault and a software fault.

[0063] Step 140: An emergency recovery strategy corresponding to the fault type and the fault position is called from a pre-constructed emergency plan tree diagram. The emergency plan tree diagram is established with the fault type, the fault position and the emergency recovery strategy of the industrial host computer as nodes.

[0064] In this embodiment, the emergency plan tree diagram is established with the fault type, the fault position and the emergency recovery strategy of the industrial host computer as nodes, and can clearly record the correspondence between the fault and the emergency recovery strategy.

[0065] For different fault types and fault positions, different emergency recovery strategies can be used for processing. For example, for virus infection, an antivirus software can be used for automatic cleaning; for system crash, a pre-set recovery script can be used for automatic repair; for software fault, a backup data recovery or a system reinstallation can be used for automatic recovery; for hardware fault, the connection state of a hardware interface can be detected to determine whether the related hardware is damaged, and if necessary, the related hardware can be replaced for automatic recovery.

[0066] Step 150: The emergency recovery strategy is executed to perform emergency recovery on the industrial host computer.

[0067] The scheme provided in this embodiment can automatically realize fault diagnosis and emergency recovery of the industrial host computer, and compared with the manual intervention mode, the efficiency and reliability of the emergency recovery are effectively improved.

[0068] In an embodiment, the abnormal operation data in the operation state data is extracted, and specifically includes:

[0069] First, each operation parameter in the operation state data is compared with a parameter threshold corresponding to the operation parameter to obtain a comparison result.

[0070] For example, the CPU usage rate can be compared with the corresponding parameter threshold to determine whether the CPU usage rate is higher than the corresponding parameter threshold and the case exceeds the preset time length, to obtain a comparison result. For another example, the memory usage rate can be compared with the corresponding parameter threshold to determine whether the memory usage rate is lower than the corresponding parameter threshold and the case exceeds the preset time length, to obtain a comparison result.

[0071] Then, if the comparison result is that the running parameter deviates from the parameter threshold for more than the preset time length, it is determined that the running parameter is abnormal running data, and the abnormal running data is extracted.

[0072] In actual application, the parameter threshold and the preset time length can be reasonably set according to the actual application scene requirement. For example, for an application scene with high safety factor requirement, the preset time length can be set a little shorter.

[0073] In an embodiment, based on the abnormal running data, fault diagnosis is performed on the industrial control host computer to obtain a fault type and a fault location, specifically including:

[0074] First, the abnormal running data is input into a pre-constructed fault diagnosis model to obtain a fault diagnosis result output by the fault diagnosis model; wherein the fault diagnosis result is used to represent a root location and a fault cause that cause the abnormal running data to appear.

[0075] In this embodiment, the fault diagnosis model can be obtained by training a deep learning neural network model with a large amount of sample data. In actual application, the model training can be performed in a supervised training manner. The input of the fault diagnosis model is the abnormal running data, and the output is the fault diagnosis result, which can be a phrase describing the root location and the fault cause, for example, "host computer mainboard is damaged", wherein the root location is the mainboard and the fault cause is the mainboard damage.

[0076] Then, the fault type and the fault location are determined according to the root location and the fault cause.

[0077] For example, the fault cause can be virus infection, system crash, and hardware failure, etc. It can be understood that according to the root location and the fault cause of the fault, the fault type and the fault location can be further determined. Still taking the root location as the mainboard and the fault cause as the mainboard damage as an example, it can be determined that the fault type is hardware failure and the fault location is the host computer mainboard.

[0078] In an embodiment, the fault diagnosis model is obtained by the following process, specifically including:

[0079] First, historical fault log data of the industrial control host computer is obtained.

[0080] Since the fault-related log data of the industrial control host computer will be stored in the memory for a certain period of time, the stored fault-related log data can be called out to obtain historical fault log data.

[0081] In some embodiments, since there may be some abnormal data points with large numerical deviations in the historical fault log data, in actual application, after obtaining the historical fault log data, the historical fault log data can be preprocessed, such as data screening and data cleaning, to improve the accuracy of the subsequent sample data set.

[0082] Secondly, abnormal running data samples, root location samples and fault cause samples are extracted from the historical fault log data to establish a sample data set.

[0083] In this embodiment, the sample data set contains multiple groups of sample data, and each group of sample data includes abnormal running data samples, root location samples and fault cause samples.

[0084] Thirdly, a fault prediction network model is established based on a deep learning neural network.

[0085] In this embodiment, the fault prediction network model adopts a deep learning neural network model as the basic architecture, and after further training, it will have more accurate fault diagnosis capability.

[0086] Fourthly, the fault prediction network model is trained through the sample data set to obtain a fault diagnosis model.

[0087] The sample data set can realize supervised training of the fault prediction network model. During the training process, the model parameters are continuously optimized, and finally, after the training termination condition is reached, a fault diagnosis model with better model parameters can be obtained.

[0088] In an embodiment, after obtaining the fault diagnosis model, the above method can further include:

[0089] Firstly, the fault log update data of the industrial control host computer within a preset period is obtained.

[0090] Since the industrial control host computer will continuously generate new fault-related log data during operation, the fault log update data within a certain preset period can be obtained regularly in the future, for example, the fault log update data within the nearest one week can be obtained every week.

[0091] Then, based on the fault log update data, the model parameters of the fault diagnosis model are optimized.

[0092] The fault diagnosis model is periodically updated by newly obtained fault log update data, so that the problem of insufficient prediction accuracy of the fault diagnosis model trained by only historical fault log data can be avoided, the prediction accuracy of the fault diagnosis model is improved, and the accuracy of the fault diagnosis result is ensured.

[0093] In an embodiment, the emergency recovery strategy is multiple, and the emergency recovery strategy is executed, specifically including:

[0094] The emergency recovery strategy with the highest execution priority is executed, and it is determined whether the fault at the current fault position is eliminated, to obtain a determination result.

[0095] If the determination result is that the fault at the current fault position is not eliminated, the next level of emergency recovery strategy is executed until the determination result is that the fault at the current fault position is eliminated.

[0096] It can be understood that for the fault occurring at the same fault position, due to different fault degrees, a single emergency recovery strategy may not be able to ensure that the fault is completely solved, therefore, the embodiment can set multiple emergency recovery strategies, for example, when a system crash fault occurs, emergency recovery strategies such as restarting the service and repairing the system configuration can be used.

[0097] In actual application, the priorities of the multiple emergency recovery strategies can be set in advance, and in the emergency recovery link, each emergency recovery strategy is executed according to the preset priorities one by one, and after each emergency recovery strategy is executed, it is determined whether the fault at the current fault position is eliminated, if the fault is eliminated, the next level of emergency recovery strategy does not need to be executed, if the fault is not eliminated, the next level of emergency recovery strategy needs to be executed until the fault is eliminated.

[0098] If after all the emergency recovery strategies are executed, it is still determined that the fault at the current fault position is not eliminated, a warning prompt can be issued to request the management personnel to intervene in time to ensure that the fault is handled in time.

[0099] In an embodiment, after the emergency recovery strategy is executed to perform emergency recovery on the industrial host computer, the above method can further include:

[0100] Firstly, the running state data of the industrial host computer after the emergency recovery is obtained.

[0101] In this step, the running parameters that were previously abnormal need to be obtained in the running state data, so that the comparison result is more obvious subsequently.

[0102] Secondly, the running state data after the emergency recovery is compared with the running state data before the emergency recovery and the standard state data, to obtain a comparison result.

[0103] In this step, for numerical running parameters such as memory usage, numerical comparison can be performed, and the numerical difference can be taken as the comparison result. For state running parameters such as network connection state, the change of the state can be taken as the comparison result.

[0104] In the third step, the emergency recovery effect of the industrial host computer is evaluated according to the comparison result, and an evaluation result is obtained.

[0105] In this embodiment, the evaluation process is mainly for numerical running parameters. Specifically, a plurality of correction ranges corresponding to each type of running parameter can be pre-set, and then it is determined that the comparison result, i.e., the numerical difference, of the current running parameter is in which correction range, and then the evaluation result of the emergency recovery effect can be determined.

[0106] In some embodiments, the evaluation result can be evaluation description such as excellent, good, and poor, and different correction ranges correspond to different evaluation descriptions.

[0107] In actual applications, the related log data when the industrial host computer fails during operation can be backed up. Specifically, the backup can be implemented in a periodic backup, incremental backup, or differential backup manner. Specifically, in the periodic backup manner, the related log data when the industrial host computer fails can be backed up periodically (such as daily, weekly, or monthly); in the incremental backup manner, only the log data changed since the last backup can be backed up to reduce backup time and storage space; and in the differential backup manner, the log data changed since the last full backup can be backed up.

[0108] By backing up the related log data when the industrial host computer fails during operation, the risk of loss of key data that cannot be recovered in the case of software failure can be reduced, and the backup data can be used as data basis for subsequent optimization and update of the fault diagnosis model and the emergency plan tree diagram.

[0109] In an embodiment, after the evaluation result is obtained, the above method can further include:

[0110] According to the evaluation result, a state adjustment strategy is determined.

[0111] According to the state adjustment strategy, at least part of the running state data of the industrial host computer is adjusted.

[0112] In this embodiment, if the evaluation result is not good, the recovery strategy will be automatically adjusted according to the actual situation according to the state adjustment strategy, such as increasing memory, upgrading hardware, etc., until a satisfactory recovery effect is achieved.

[0113] In some embodiments, part of the types of evaluation results can be set as poor evaluation effect, such as setting the type of "poor" as poor evaluation effect, so that when the evaluation result is poor, the state adjustment strategy can be determined according to the correction range of the level corresponding to "poor" and the comparison result, and specifically, the optimal value in the correction range of the level corresponding to "poor" can be set, and the process of adjusting the numerical difference corresponding to the comparison result to the optimal value can be set as the state adjustment strategy.

[0114] In practical applications, after emergency recovery, the industrial control host computer can be regularly inspected to check whether the key information such as hardware devices and system configurations is normal, for example, whether the settings of the IP address, port number, subnet mask and the like of the industrial control host computer are correct, to ensure normal operation.

[0115] In summary, the emergency recovery method based on the industrial control host computer provided by the embodiments of the present application has at least the following advantages compared with the traditional manual intervention emergency recovery scheme:

[0116] First, the recovery speed is fast, and through fault diagnosis and emergency recovery strategy, the emergency recovery program can be started quickly when a fault occurs, greatly shortening the recovery time.

[0117] Second, the operation is simple, the emergency recovery method provided by the embodiment uses automation technology, reduces the need for manual intervention, makes the recovery process more simple, and reduces the operation difficulty and labor cost.

[0118] Third, the recovery effect is stable, through functions such as fault diagnosis and positioning, recovery effect evaluation and optimization, the stability of the recovery process and the reliability of the recovery effect are ensured.

[0119] Fourth, the safety is high, through the way of regular inspection, the preventive maintenance function can be provided, the industrial control host computer is regularly inspected, maintained and upgraded, the probability of fault occurrence is effectively reduced, and the safety of the industrial control process is improved.

[0120] Fifth, the adaptability is strong, the corresponding emergency recovery strategy can be used to realize emergency recovery according to different fault types and fault positions, and the adaptability is strong.

[0121] Sixth, the business continuity is guaranteed, the emergency recovery can be quickly realized when a fault occurs, the business continuity is ensured, and the influence of the fault on the industrial production is reduced.

[0122] Based on the same general inventive concept, the application also protects an emergency recovery device based on an industrial control host computer. The emergency recovery device based on an industrial control host computer provided by the application is described below, and the emergency recovery device based on an industrial control host computer described below can be mutually corresponding with reference to the emergency recovery method based on an industrial control host computer described above.

[0123] Figure 2 FIG. 1 is a structural schematic diagram of the emergency recovery device based on an industrial control host computer provided by an embodiment of the application.

[0124] As shown in FIG. 1, the emergency recovery device based on an industrial control host computer provided by an embodiment of the application specifically comprises: Figure 2

[0125] An acquisition module 210 is configured to acquire running state data of the industrial control host computer.

[0126] An extraction module 220 is configured to extract abnormal running data from the running state data.

[0127] A diagnosis module 230 is configured to perform fault diagnosis on the industrial control host computer based on the abnormal running data, to obtain a fault type and a fault location.

[0128] A calling module 240 is configured to call an emergency recovery strategy corresponding to the fault type and the fault location from a pre-constructed emergency plan tree diagram; wherein the emergency plan tree diagram is established with the fault type, the fault location and the emergency recovery strategy of the industrial control host computer as nodes.

[0129] An execution module 250 is configured to execute the emergency recovery strategy to perform emergency recovery on the industrial control host computer.

[0130] In an embodiment, the extraction module 220 is specifically configured to:

[0131] compare each running parameter in the running state data with a parameter threshold corresponding to the running parameter respectively to obtain a comparison result;

[0132] if the comparison result is that the running parameter deviates from the parameter threshold for more than a preset time length, determine that the running parameter is abnormal running data, and extract the abnormal running data.

[0133] In an embodiment, the diagnosis module 230 is specifically configured to:

[0134] input the abnormal running data into a pre-constructed fault diagnosis model to obtain a fault diagnosis result output by the fault diagnosis model; wherein the fault diagnosis result is used to represent a root location and a fault cause that cause the abnormal running data to appear;

[0135] determine the fault type and the fault location according to the root location and the fault cause.​

[0136] In an embodiment, the fault diagnosis model is obtained by the following process, comprising:

[0137] acquiring historical fault log data of the industrial control host computer;

[0138] extracting abnormal operation data samples, root location samples and fault cause samples from the historical fault log data, and establishing a sample data set;

[0139] establishing a fault prediction network model based on a deep learning neural network framework;

[0140] training the fault prediction network model through the sample data set to obtain the fault diagnosis model.

[0141] In an embodiment, the above-mentioned emergency recovery device based on the industrial control host computer can further comprise:

[0142] an optimization module configured to acquire fault log update data of the industrial control host computer within a preset period, and optimize model parameters of the fault diagnosis model based on the fault log update data.

[0143] In an embodiment, the emergency recovery strategy can be multiple, and the execution module is specifically configured to:

[0144] execute the emergency recovery strategy with the highest priority according to a preset priority execution level, and determine whether the fault at the current fault location is eliminated to obtain a determination result;

[0145] if the determination result is that the fault at the current fault location is not eliminated, execute the next level of emergency recovery strategy until the determination result is that the fault at the current fault location is eliminated.

[0146] In an embodiment, the above-mentioned emergency recovery device based on the industrial control host computer can further comprise:

[0147] an evaluation module configured to acquire operation state data of the industrial host computer after the emergency recovery, compare the operation state data after the emergency recovery with the operation state data before the emergency recovery and standard state data to obtain a comparison result, and evaluate the emergency recovery effect of the industrial host computer according to the comparison result to obtain an evaluation result.

[0148] In an embodiment, the above-mentioned emergency recovery device based on the industrial control host computer can further comprise:

[0149] an adjustment module configured to determine a state adjustment strategy according to the evaluation result, and adjust at least part of the operation state data of the industrial host computer according to the state adjustment strategy.

[0150] In summary, the emergency recovery device based on an industrial control host computer provided in this embodiment of the invention can quickly and accurately perform emergency recovery when a fault occurs, effectively reducing the impact of the fault on industrial production and ensuring business continuity.

[0151] Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention.

[0152] like Figure 3 As shown, the electronic device may include a processor 310, a communication interface 320, a memory 330, and a communication bus 340. The processor 310, communication interface 320, and memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute an emergency recovery method based on an industrial control host computer. This method includes: acquiring the operating status data of the industrial control host computer; extracting abnormal operating data from the operating status data; performing fault diagnosis on the industrial control host computer based on the abnormal operating data to obtain the fault type and fault location; retrieving an emergency recovery strategy corresponding to the fault type and fault location from a pre-constructed emergency plan tree diagram; wherein the emergency plan tree diagram is established with the fault type, fault location, and emergency recovery strategy of the industrial host computer as nodes; and executing the emergency recovery strategy to perform emergency recovery on the industrial host computer.

[0153] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0154] In another aspect, the present application also provides a computer program product comprising a computer program, the computer program being stored in a non-transitory computer-readable storage medium, and the computer program being executable by a processor to enable a computer to perform the industrial control host computer-based emergency recovery method provided by the above method, which comprises: acquiring running state data of an industrial control host computer; extracting abnormal running data in the running state data; performing fault diagnosis on the industrial control host computer based on the abnormal running data to obtain a fault type and a fault location; retrieving an emergency recovery strategy corresponding to the fault type and the fault location from a pre-constructed emergency plan tree diagram; wherein the emergency plan tree diagram is established with the fault type, the fault location and the emergency recovery strategy of the industrial host computer as nodes; and executing the emergency recovery strategy to perform emergency recovery on the industrial host computer.

[0155] In another aspect, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the industrial control host computer-based emergency recovery method provided by the above method, which comprises: acquiring running state data of an industrial control host computer; extracting abnormal running data in the running state data; performing fault diagnosis on the industrial control host computer based on the abnormal running data to obtain a fault type and a fault location; retrieving an emergency recovery strategy corresponding to the fault type and the fault location from a pre-constructed emergency plan tree diagram; wherein the emergency plan tree diagram is established with the fault type, the fault location and the emergency recovery strategy of the industrial host computer as nodes; and executing the emergency recovery strategy to perform emergency recovery on the industrial host computer.

[0156] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e., they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0157] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus necessary general hardware platforms, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in terms of the contribution to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in the various embodiments or some parts of the embodiments.

[0158] Finally, it should be noted that the above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the same; although the present application has been described in detail with reference to the foregoing examples, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An industrial control host computer-based emergency recovery method, characterized by, Comprising: acquiring running state data of an industrial control host computer; extracting abnormal running data in the running state data; inputting the abnormal running data into a pre-constructed fault diagnosis model to obtain a fault diagnosis result output by the fault diagnosis model; wherein the fault diagnosis result is used to represent a root location and a fault cause that cause the abnormal running data to appear, and the fault diagnosis model is obtained through the following process, comprising: acquiring historical fault log data of the industrial control host computer; extracting abnormal running data samples, root location samples and fault cause samples from the historical fault log data to establish a sample data set; establishing a fault prediction network model based on a deep learning neural network as a basic framework; training the fault prediction network model through the sample data set to obtain the fault diagnosis model; acquiring fault log update data of the industrial control host computer within a preset period; optimizing model parameters of the fault diagnosis model based on the fault log update data; determining a fault type and a fault location according to the root location and the fault cause; retrieving an emergency recovery strategy corresponding to the fault type and the fault location from a pre-constructed emergency plan tree diagram; wherein the emergency recovery strategy is multiple, and the emergency plan tree diagram is established with the fault type, the fault location and the emergency recovery strategy as nodes; executing the emergency recovery strategy with the highest priority according to a preset priority execution level, and judging whether the fault at the current fault location is eliminated to obtain a judgment result; if the judgment result is that the fault at the current fault location is not eliminated, executing the next level of emergency recovery strategy until the judgment result is that the fault at the current fault location is eliminated, so as to perform emergency recovery on the industrial host computer; acquiring running state data of the industrial host computer after emergency recovery; comparing the running state data after emergency recovery with the running state data before emergency recovery and standard state data to obtain a comparison result; evaluating the emergency recovery effect of the industrial host computer according to the comparison result to obtain an evaluation result; when the evaluation result is poor, setting an optimal value in a correction range corresponding to the level of poor, and adjusting a numerical difference corresponding to the comparison result to the optimal value as a state adjustment strategy; adjusting at least part of the running state data of the industrial host computer according to the state adjustment strategy.

2. The industrial control host computer based emergency recovery method according to claim 1, characterized in that, The extraction of the abnormal running data in the running state data comprises: comparing each running parameter in the running state data with a parameter threshold value corresponding to the running parameter respectively to obtain a comparison result; if the comparison result is that the running parameter deviates from the parameter threshold value for more than a preset time length, it is determined that the running parameter is abnormal running data, and the abnormal running data is extracted.

3. An emergency recovery device based on an industrial control host computer, characterized by Comprising: an acquisition module configured to acquire running state data of an industrial control host computer; an extraction module configured to extract abnormal running data in the running state data; The diagnostic module is configured to input the abnormal operation data into a pre-constructed fault diagnosis model to obtain a fault diagnosis result output by the fault diagnosis model; wherein the fault diagnosis result is used to represent a root location and a fault cause that cause the abnormal operation data to appear, and the fault diagnosis model is obtained through the following process, including: obtaining historical fault log data of the industrial control host computer; extracting abnormal operation data samples, root location samples, and fault cause samples from the historical fault log data to establish a sample data set; establishing a fault prediction network model based on a deep learning neural network as a basic framework; training the fault prediction network model through the sample data set to obtain the fault diagnosis model; obtaining fault log update data of the industrial control host computer within a preset period; optimizing model parameters of the fault diagnosis model based on the fault log update data; determining a fault type and a fault location according to the root location and the fault cause; The calling module is configured to call an emergency recovery strategy corresponding to the fault type and the fault location from a pre-constructed emergency plan tree diagram; wherein the emergency recovery strategy is multiple, and the emergency plan tree diagram is established with the fault type, the fault location, and the emergency recovery strategy as nodes; The execution module is configured to execute an emergency recovery strategy with the highest priority according to a preset priority execution level, and determine whether the fault at the current fault location is eliminated to obtain a determination result; if the determination result is that the fault at the current fault location is not eliminated, a next-level emergency recovery strategy is executed until the determination result is that the fault at the current fault location is eliminated, so as to perform emergency recovery on the industrial host computer. The device is also configured to: obtain operation state data of the industrial host computer after emergency recovery; compare the operation state data after emergency recovery with operation state data before emergency recovery and standard state data to obtain a comparison result; evaluate the emergency recovery effect of the industrial host computer according to the comparison result to obtain an evaluation result; when the evaluation result is poor, set an optimal value in a correction range corresponding to the level of the poor, adjust a numerical difference corresponding to the comparison result to the optimal value as a state adjustment strategy; and adjust at least part of the operation state data of the industrial host computer according to the state adjustment strategy.

4. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the industrial control host computer-based emergency recovery method of claim 1 or 2 when executing the program.

Images