Fault probability calculation method and device, fault probability prediction method and device, electronic equipment and storage medium

Abstract

The invention provides a fault probability calculation method and device, a fault probability prediction method and device, electronic equipment and a storage medium, and relates to the technical field of fault detection.The fault probability calculation method comprises the steps that target working data is acquired, first Gini impurity is calculated, second Gini impurity is selected from the first Gini impurity, and the first Gini impurity and the second Gini impurity are calculated; selecting a target working parameter from the plurality of working parameters based on the second Gini impurity; and determining a fault probability corresponding to the target timestamp based on the target working parameter. According to the invention, the technical problems of low robustness of a fault prediction model and low accuracy of fault prediction in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault detection, and in particular to a fault probability calculation and prediction method, device, electronic equipment and storage medium. Background Art

[0002] In the related technologies, for fault prediction, machine learning models, deep learning models or fuzzy systems can be used specifically. In the above models, the collected data is used as a basis, the collected data is analyzed and processed, and the implicit information therein is discovered to predict the failure of the equipment.

[0003] However, due to the complexity of the fault prediction algorithm, the fault prediction model has poor robustness and can only process single data. It is unable to analyze the equipment failure based on multimodal data, which affects the accuracy of fault prediction.

[0004] In summary, with respect to fault prediction, the robustness of the fault prediction model in the prior art and the accuracy of fault prediction need to be improved. Summary of the invention

[0005] In view of this, an object of the present invention is to provide a fault probability calculation, prediction method, device, electronic device and storage medium to alleviate the technical problems of low robustness of fault prediction models and low accuracy of fault prediction in the prior art.

[0006] In a first aspect, an embodiment of the present invention provides a method for calculating a failure probability, which is applied to a server and calculates the failure probability corresponding to a target timestamp in the following manner: Acquire target working data, where the target working data is working data corresponding to a target timestamp, and the target working data includes a plurality of working parameters; Calculating a first Gini impurity, where the first Gini impurity includes: a Gini impurity corresponding to each working parameter in the target working data; Selecting a second Gini impurity from the first Gini impurity, and selecting a target operating parameter from the plurality of operating parameters based on the second Gini impurity; Based on the target operating parameters, determining the failure probability corresponding to the target timestamp, wherein there is a mapping relationship between the operating parameters and the failure probability, and the second Gini coefficient is the minimum value of the first Gini coefficients, Work data for the target.

[0007] In the embodiment provided in the present application, the Gini impurity is used as an indicator to determine the prediction probability of each timestamp for the acquired multimodal working parameters, which simplifies the fault prediction model and improves the robustness of the fault model. At the same time, when predicting faults, the influence of multiple working parameters on the fault probability is considered, thereby improving the accuracy of fault prediction.

[0008] One possible way is that the target working data includes: temperature data, humidity data, vibration data, flow data, pressure data, voltage data, current data, and rotation speed corresponding to the target timestamp.

[0009] One possible way is to calculate the Gini impurity corresponding to each working parameter using the following formula: ; is the working parameter; Working parameters The corresponding Gini impurity.

[0010] In a second aspect, an embodiment of the present application provides a fault prediction method, which is applied to a server, wherein the server is used to predict faults of a target device. Acquire target device prediction data, the target device prediction data including: a plurality of first working data and target device operation and maintenance data, the plurality of first working data being first working data corresponding to a plurality of timestamps, one first working data corresponding to one timestamp; Calculating the failure probability corresponding to each time stamp in the plurality of first working data; Determine a decay curve based on the target device operation and maintenance data and the failure probability corresponding to each timestamp; Setting a fault threshold, and predicting a failure time of a target device based on the fault threshold and a decay curve; Sending a target device failure prediction result, wherein the target device failure prediction result includes: a failure time of the target device.

[0011] In one possible manner, the method further comprises: If the failure probability corresponding to any of the failure probabilities corresponding to each time stamp is greater than a failure threshold, the target device failure prediction result further includes: failure prompt information, and the failure prompt information is used to prompt that a failure occurs on the target device.

[0012] In one possible manner, the method further comprises: The fault threshold is adjusted based on the target device operation and maintenance data.

[0013] In a third aspect, an embodiment of the present application provides a fault prediction method, which is applied to a programmable controller, wherein the programmable controller is applied to perform fault prediction on a target device, wherein the programmable controller is respectively connected to the server of the second aspect and to multiple sensors for communication, and the multiple sensors communicate and collect: multiple second working data and target device operation and maintenance raw data, wherein the multiple second working data are second working data corresponding to multiple timestamps, one second working data corresponds to one timestamp, and each second working data includes multiple working parameters, including: Generate target device prediction data, the target device prediction data including: a plurality of first working data and target device operation and maintenance data, the target device operation and maintenance data is generated by processing the target device operation and maintenance original data, the plurality of first working data is a part of the processed second working data, the plurality of first working data is the first working data corresponding to a plurality of timestamps, and one first working data corresponds to one timestamp; Sending the target device prediction data to the server; A target device failure prediction result sent by the server is received, where the target device failure prediction result includes: a failure time of the target device, and the target device failure prediction result is generated based on the target device prediction data.

[0014] In one possible manner, the target device fault prediction result further includes: fault prompt information, and the method further includes: In response to the fault prompt information, generating a maintenance suggestion for the target device based on the target device operation and maintenance data and the plurality of second working data; and / or In response to the fault prompt information, prompt information is generated.

[0015] In one possible manner, the prompt information includes: one of the first prompt information or the second prompt information; The first prompt information is used to prompt that the target device needs maintenance; The second prompt information is used to prompt that the target device needs to be replaced.

[0016] In a fourth aspect, an embodiment of the present application provides a failure probability calculation device, which is applied to a server, including: A first acquisition module: used to acquire target working data, wherein the target working data is working data corresponding to a target timestamp, and the target working data includes a plurality of working parameters; A first calculation module: used for calculating a first Gini impurity based on the target working data, where the first Gini impurity includes: a Gini impurity corresponding to each working parameter in the first working data; A selection module: configured to select a second Gini impurity from the first Gini impurity, and select a target operating parameter from the plurality of operating parameters based on the second Gini impurity; A determination module is used to determine the failure probability corresponding to the target timestamp based on the target working parameter, wherein there is a mapping relationship between the working parameter and the failure probability, and the second Gini coefficient is the minimum value of the first Gini coefficient. Work data for the target.

[0017] In a fifth aspect, an embodiment of the present application provides a fault prediction device, which is applied to a server, and the server is used to predict faults of a target device. A second acquisition module: acquiring target device prediction data, wherein the target device prediction data includes: a plurality of first working data and target device operation and maintenance data, wherein the plurality of first working data are first working data corresponding to a plurality of timestamps, and one first working data corresponds to one timestamp; A second calculation module: used to calculate the failure probability corresponding to each first working data in the plurality of first working data by using the method described in the first aspect; A second determination module: used to determine a decay curve based on the target equipment operation and maintenance data and the failure probability corresponding to each first working data; Prediction module: used to set a fault threshold and predict the failure time of the target device based on the fault threshold and the decay curve; The first sending module is used to send a target device failure prediction result, wherein the target device failure prediction result includes: a failure time of the target device.

[0018] In a sixth aspect, an embodiment of the present application provides a fault prediction device, which is applied to a programmable controller, and the programmable controller is applied to predict faults of a target device. The programmable controller is respectively connected to a server and a plurality of sensors for communication, and the plurality of sensors communicate and collect: a plurality of second working data and target device operation and maintenance raw data, wherein the plurality of second working data are second working data corresponding to multiple timestamps, and one second working data corresponds to one timestamp, including: A generating module: used to generate target device prediction data, wherein the target device prediction data includes: a plurality of first working data and target device operation and maintenance data, wherein the target device operation and maintenance data is generated by processing the target device operation and maintenance original data, and the plurality of first working data is a part of the plurality of second working data after processing; A second sending module: used for sending the target device prediction data to the server; Receiving module: used for receiving the target device failure prediction result sent by the server, the target device failure prediction result includes: the failure time of the target device, and the target device failure prediction result is generated based on the target device prediction data.

[0019] In a seventh aspect, an embodiment of the present application provides an electronic device, including: at least one processor; and at least one memory in communication with the processor, wherein: The memory stores program instructions that can be executed by the processor, and the processor can call the program instructions to execute the methods described in the first to third aspects.

[0020] In an eighth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions enable the computer to execute the method described in the first to third aspects.

[0021] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0022] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 A flow chart of a fault prediction method provided by an embodiment of the present invention; Figure 2 Another fault prediction method flow chart provided by the embodiment of the present invention Figure 3 A structural diagram of a failure probability calculation device provided by an embodiment of the present invention; Figure 4 A structural diagram of another fault probability calculation device provided by an embodiment of the present invention; Figure 5 A structural diagram of another fault probability calculation device provided by an embodiment of the present invention; Figure 6 This is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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.

[0026] In the related technologies, for fault prediction, machine learning models, deep learning models or fuzzy systems can be used specifically. In the above models, the collected data is used as a basis, the collected data is analyzed and processed, and the implicit information therein is discovered to predict the failure of the equipment.

[0027] However, due to the complexity of the fault prediction algorithm, the fault prediction model has poor robustness and can only process single data. It is unable to analyze the equipment failure based on multimodal data, which affects the accuracy of fault prediction.

[0028] In summary, with respect to fault prediction, the robustness of the fault prediction model in the prior art and the accuracy of fault prediction need to be improved.

[0029] Based on this, the embodiments of the present invention provide a method, device, electronic device and storage medium for calculating and predicting fault probability, which can improve the robustness of the fault prediction model and the accuracy of fault prediction.

[0030] Before introducing the embodiments provided in this application, the data involved in this application are first described: Timestamp: It refers to a way of recording time, usually used to record the time of occurrence of an event or the creation and modification time of a file. To facilitate understanding of this embodiment, a method for calculating a failure probability disclosed in an embodiment of the present invention is first introduced in detail.

[0031] In the embodiments adopted by the present application, a method for calculating the probability of failure is first disclosed. The method is applied to the server. For the calculation of the probability of failure at any moment, that is, for the target timestamp, first, the target working data is required to be the working data corresponding to the target timestamp. To simplify the description, in all the embodiments of the present application, the target working data is defined as the working data corresponding to the target timestamp. At the same time, the target working data includes multiple working parameters.

[0032] For the target working data, specifically, the target timestamp may correspond to a variety of temperature data, humidity data, vibration data, flow data, pressure data, voltage data, current data, and rotational speed. Personnel in this field can set the target working parameters as needed based on the actual equipment. No limitation is made here. Through the above steps, the server obtains the multimodal working parameters corresponding to the timestamp.

[0033] Then, after the target working data is obtained, the Gini impurity corresponding to each working parameter in the target working data is calculated. Similarly, for the convenience of description, the Gini impurity corresponding to each working parameter in the target working data is defined as the first Gini impurity.

[0034] Gini impurity is an indicator used to evaluate the degree of impurity of a data set. It plays an important role in machine learning, especially in building decision trees and random forests. The lower the Gini impurity, the lower the impurity of the data, and the higher the purity of the child nodes in the random forest.

[0035] It is known to those skilled in the art that in order to calculate the Gini impurity, in some embodiments, the data needs to be processed, specifically including data cleaning and normalization. In other words, in the embodiments provided in this application, For working parameters.

[0036] Finally, based on the target working parameters, the failure probability corresponding to the target timestamp is determined.

[0037] Specifically, there is a mapping relationship between working parameters and failure probabilities. Once the target working parameters are determined, the failure probability corresponding to the target working parameters, that is, the failure probability corresponding to the target timestamp, can be determined using the index principle.

[0038] In the embodiment provided in the present application, the Gini impurity is used as an indicator to determine the prediction probability of each timestamp for the acquired multimodal working parameters, which simplifies the fault prediction model and improves the robustness of the fault model. At the same time, when predicting faults, the influence of multiple working parameters on the fault probability is considered, thereby improving the accuracy of fault prediction.

[0039] Based on the above embodiment, the Gini impurity can be calculated by the following formula: ; is the working parameter; Working parameters The corresponding Gini impurity.

[0040] The following is a specific example: Exemplarily, the selected target working data includes temperature parameters and vibration parameters, and the normalized temperature and vibration corresponding to each timestamp are shown in Table 1: Table 1: Normalized temperature and vibration corresponding to each timestamp

[0041] By timestamp For example, the Gini impurity corresponding to the temperature parameter is: ; The Gini impurity corresponding to the vibration parameter is: ; Due to the timestamp In the case of 0.8, the Gini impurity of the temperature parameter is relatively low, so the temperature is selected as the target working parameter. When the temperature parameter is 0.8, the failure probability of the equipment is 0.2, so the timestamp The corresponding failure probability is 0.2.

[0042] Based on the above embodiments, the present application provides a fault prediction method, in which the server is used to perform fault prediction on a target device.

[0043] It should be noted that the target device is the device for which fault prediction is required. Assuming that fault prediction is required for a motor, the target device corresponds to the motor. Figure 1 In the embodiment provided in this application, the following steps are specifically included: S101: Obtain target device prediction data.

[0044] The target device prediction data is data used to predict faults of the target device. The target device is the device corresponding to the device to be pre-fault predicted. The target device prediction data includes: multiple first working data and target device operation and maintenance data. One first working data corresponds to a timestamp. In other words, in order to realize the fault prediction of the target device, it is necessary to obtain the first working data and target device operation and maintenance data corresponding to multiple timestamps. The target device operation and maintenance data specifically includes the start and stop time of the target device, historical maintenance data, etc. For the first working data, it may specifically include temperature data, humidity data, vibration data, flow data, pressure data, voltage data, current data, and rotation speed corresponding to the target device at each timestamp.

[0045] S102: Calculate the failure probability corresponding to each time stamp in the plurality of first working data.

[0046] Regarding the method of calculating the failure probability, the failure probability of each timestamp may be calculated by referring to the method of the aforementioned embodiment, which will not be described in detail here.

[0047] S103: Determine a decay curve based on the target device operation and maintenance data and the failure probability corresponding to each timestamp.

[0048] After obtaining the failure probability of each timestamp, the decay curve can be fitted in combination with the target equipment operation and maintenance data. Specifically, the decay curve represents the relationship between the failure probability and time. The failure probability corresponding to each moment can be determined through the decay curve.

[0049] S104: Setting a fault threshold, and predicting the failure time of the target device based on the fault threshold and the decay curve.

[0050] After fitting the decay curve, set the fault threshold. For the fault threshold, that is, the minimum value allowed for the corresponding fault probability, use the decay curve to determine the time when the fault probability reaches the fault threshold, and then predict the fault of the target device.

[0051] S105: Sending the target device failure prediction result.

[0052] Specifically, the target device failure prediction result includes: the failure time of the target device.

[0053] In this embodiment, the Gini impurity is used as an indicator to determine the prediction probability of each timestamp for the acquired multimodal working parameters, which simplifies the fault prediction model and improves the robustness of the fault model. At the same time, when predicting faults, the influence of multiple working parameters on the fault probability is considered, thereby improving the accuracy of fault prediction.

[0054] In some embodiments, in order to provide real-time alarm for the target device, if the failure probability corresponding to any of the failure probabilities corresponding to each timestamp is greater than the failure threshold, the target device failure prediction result includes: failure prompt information, which is used to prompt that the target device has a failure.

[0055] Through the above method, the lower computer of the server can obtain the fault prompt information and inform the equipment management personnel based on the above fault prompt information.

[0056] In some embodiments, the fault threshold is adaptively adjusted using the operation and maintenance data of the equipment to be predicted, that is, the fault threshold is adjusted based on the operation and maintenance data of the target equipment. For example, when the number of maintenance times of the target equipment is greater than a certain threshold, the fault threshold will be more adaptable. The technical personnel in this field can set the adjustment method of the fault threshold by themselves, and it is not limited here.

[0057] Reference Figure 2On the basis of the foregoing embodiments, the present application also provides a fault prediction method, which is applied to a programmable controller. The programmable controller is applied to perform fault prediction on a target device. The programmable controller is respectively connected to a server and to multiple sensors for communication. The multiple sensors communicate and collect: multiple second working data and target device operation and maintenance original data. The multiple second working data are second working data corresponding to multiple timestamps. One second working data corresponds to one timestamp, and each second working data includes multiple working parameters.

[0058] Specifically, the programmable controller provided in the present application is specifically used to obtain data collected by the sensor and process the data collected by the sensor.

[0059] In this embodiment, the second working data corresponds to the working parameters of the target device. Different from the first working data, the second working data is directly sent from the sensor to the programmable controller, and the first working data is the data processed by the second working data. The processing method specifically includes data screening and / or data cleaning and / or normalization processing.

[0060] In this embodiment, the following steps are specifically included: S201: Generate target device prediction data.

[0061] Specifically, the programmable controller can generate a target prediction device in the following manner: first, the aforementioned multiple second working data are screened and / or data cleaned and / or normalized, and the processed multiple second working data are screened to obtain multiple first working data, that is, the first working data corresponding to multiple timestamps.

[0062] At the same time, the original operation and maintenance data of the target device is processed, that is, the operation and maintenance data of the target device is obtained, and the plurality of first working data and the operation and maintenance data of the target device are integrated, that is, the target device data is generated.

[0063] It can be seen that the target device prediction data includes: multiple first working data and target device operation and maintenance data, the target device operation and maintenance data is generated by processing the target device operation and maintenance original data, and the multiple first working data are part of the processed second working data.

[0064] S202: Send target device prediction data to the server.

[0065] S203: Receive the target device failure prediction result sent by the server.

[0066] In this embodiment, the target device failure prediction result includes: the failure time of the target device, and the target device failure prediction result is generated based on the target device prediction data.

[0067] Regarding the calculation method of the target device failure prediction, please refer to the aforementioned S101 to S105 for details, which will not be elaborated here.

[0068] In some embodiments, the target device fault prediction result further includes: fault prompt information. In some scenarios, the programmable controller generates a maintenance suggestion for the target device based on the target device operation and maintenance data and the plurality of second working data in response to the fault prompt information.

[0069] In this scenario, the programmable controller displays maintenance recommendations for the target equipment.

[0070] In another part of the scenarios, the programmable controller generates a maintenance suggestion for the target device in response to the fault prompt information based on the target device operation and maintenance data and multiple second work data, and generates prompt information at the same time.

[0071] In this scenario, the programmable controller displays prompt information of the target device and maintenance suggestions of the target device.

[0072] In another part of the scenarios, the programmable controller generates prompt information in response to fault prompt information.

[0073] In this scenario, the programmable controller displays prompt information of the target device.

[0074] With respect to the aforementioned prompt information, the prompt information is one of the first prompt information or the second prompt information. The first prompt information is used to prompt that the target device needs maintenance, and the second prompt information is used to prompt that the target device needs replacement.

[0075] Reference Figure 3 , an embodiment of the present application provides a failure probability calculation device, applied to a server, comprising: A first acquisition module: used to acquire target working data, wherein the target working data is working data corresponding to a target timestamp, and the target working data includes a plurality of working parameters; A first calculation module: used for calculating a first Gini impurity based on the target working data, where the first Gini impurity includes: a Gini impurity corresponding to each working parameter in the first working data; A selection module: configured to select a second Gini impurity from the first Gini impurity, and select a target operating parameter from the plurality of operating parameters based on the second Gini impurity; A determination module is used to determine the failure probability corresponding to the target timestamp based on the target working parameter, wherein there is a mapping relationship between the working parameter and the failure probability, and the second Gini coefficient is the minimum value of the first Gini coefficient. Work data for the target.

[0076] Reference Figure 4The embodiment of the present application provides a fault prediction device, which is applied to a server, and the server is used to predict faults of a target device. A second acquisition module: acquiring target device prediction data, wherein the target device prediction data includes: a plurality of first working data and target device operation and maintenance data, wherein the plurality of first working data are first working data corresponding to a plurality of timestamps, and one first working data corresponds to one timestamp; A second calculation module: used to calculate the failure probability corresponding to each first working data in the plurality of first working data; A second determination module: used to determine a decay curve based on the target equipment operation and maintenance data and the failure probability corresponding to each first working data; Prediction module: used to set a fault threshold and predict the failure time of the target device based on the fault threshold and the decay curve; The first sending module is used to send a target device failure prediction result, wherein the target device failure prediction result includes: a failure time of the target device.

[0077] Reference Figure 5 The embodiment of the present application provides a fault prediction device, which is applied to a programmable controller, and the programmable controller is applied to predict faults of a target device. The programmable controller is respectively connected to a server and a plurality of sensors for communication, and the plurality of sensors communicate and collect: a plurality of second working data and target device operation and maintenance raw data, wherein the plurality of second working data are second working data corresponding to multiple timestamps, and one second working data corresponds to one timestamp, including: A generating module: used to generate target device prediction data, wherein the target device prediction data includes: a plurality of first working data and target device operation and maintenance data, wherein the target device operation and maintenance data is generated by processing the target device operation and maintenance original data, and the plurality of first working data is a part of the plurality of second working data after processing; A second sending module: used for sending the target device prediction data to the server; Receiving module: used for receiving the target device failure prediction result sent by the server, the target device failure prediction result includes: the failure time of the target device, and the target device failure prediction result is generated based on the target device prediction data.

[0078] Unless otherwise specifically stated, the relative steps, numerical expressions and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present invention.

[0079] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0080] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the system, method and computer program product according to multiple embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0081] Figure 6 A block diagram of an exemplary electronic device suitable for implementing an exemplary embodiment of the present invention is shown. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0082] like Figure 6 As shown, the electronic device is in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: one or more processors 410, a memory 430, and a communication bus 440 connecting different system components (including the memory 430 and the processor 410).

[0083] The communication bus 440 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnection (PCI) bus.

[0084] Electronic devices typically include a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, removable and non-removable media.

[0085] The memory 430 may include a computer system readable medium in the form of a volatile memory, such as a random access memory (RAM) and / or a cache memory. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. The memory 430 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of each embodiment of the present invention.

[0086] A program / utility having a set (at least one) of program modules may be stored in the memory 430, such program modules including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules generally perform the functions and / or methods of the embodiments described in the embodiments of the present invention.

[0087] The processor 410 executes various functional applications and data processing by running the programs stored in the memory 430, such as implementing the embodiments of the present invention. Figure 1~Figure 2 The method provided by the illustrated embodiment.

[0088] An embodiment of the present invention provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions enable the computer to execute an embodiment of the present invention. Figure 1~Figure 2 The method provided by the illustrated embodiment.

[0089] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ReadOnly Memory; hereinafter referred to as: ROM), an erasable programmable read-only memory (Erasable Programmable ReadOnly Memory; hereinafter referred to as: EPROM) or flash memory, optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0090] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0091] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0092] Computer program codes for performing the operations of the embodiments of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0093] The above describes specific embodiments of the present invention. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0094] In the description of the embodiments of the present invention, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiments of the present invention. In the embodiments of the present invention, the schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in the embodiments of the present invention and the features of the different embodiments or examples, without contradiction.

[0095] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the embodiments of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0096] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred implementation of the embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0097] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0098] It should be noted that the terminals involved in the embodiments of the present invention may include but are not limited to personal computers (Personal Computer; hereinafter referred to as: PC), personal digital assistants (Personal Digital Assistant; hereinafter referred to as: PDA), wireless handheld devices, tablet computers (Tablet Computer), mobile phones, MP3 players, MP4 players, etc.

[0099] In the several embodiments provided in the embodiments of the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0100] In addition, each functional unit in each embodiment of the present invention may be integrated into one processor, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0101] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (Processor) to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk and other media that can store program codes.

[0102] The above description is only a preferred embodiment of the embodiment of the present invention and is not intended to limit the embodiment of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiment of the present invention should be included in the scope of protection of the embodiment of the present invention.

Claims

1. A method for calculating failure probability, applied to a server, characterized in that: For the target timestamp, the failure probability corresponding to the target timestamp is calculated as follows: Acquire target working data, where the target working data is working data corresponding to a target timestamp, and the target working data includes a plurality of working parameters; Calculating a first Gini impurity, where the first Gini impurity includes: a Gini impurity corresponding to each working parameter in the target working data; Selecting a second Gini impurity from the first Gini impurity, and selecting a target operating parameter from the plurality of operating parameters based on the second Gini impurity; Based on the target operating parameter, determining the failure probability corresponding to the target timestamp, wherein there is a mapping relationship between each operating parameter and the failure probability, and the second Gini coefficient is the minimum value of the first Gini coefficients, For working parameters.

2. The method according to claim 1, characterized in that The target working data includes: temperature data, humidity data, vibration data, flow data, pressure data, voltage data, current data, and rotation speed corresponding to the target timestamp.

3. The method according to claim 1 or 2, characterized in that: The Gini impurity corresponding to each working parameter is calculated using the following formula: ； is the working parameter; Working parameters The corresponding Gini impurity.

4. A fault prediction method, applied to a server, wherein the server is used to predict faults of a target device, characterized in that: Acquire target device prediction data, the target device prediction data including: a plurality of first working data and target device operation and maintenance data, the plurality of first working data being first working data corresponding to a plurality of timestamps, one first working data corresponding to one timestamp; Calculate the failure probability corresponding to each timestamp in the plurality of first working data using the method described in any one of claims 1 to 3; Determine a decay curve based on the target device operation and maintenance data and the failure probability corresponding to each timestamp; Setting a fault threshold, and predicting a failure time of a target device based on the fault threshold and a decay curve; Sending a target device failure prediction result, wherein the target device failure prediction result includes: a failure time of the target device.

5. The method according to claim 4, characterized in that The method further comprises: If the failure probability corresponding to any of the failure probabilities corresponding to each time stamp is greater than a failure threshold, the target device failure prediction result further includes: failure prompt information, and the failure prompt information is used to prompt that a failure occurs on the target device.

6. The method according to claim 4 or 5, characterized in that: The method further comprises: The fault threshold is adjusted based on the target device operation and maintenance data.

7. A fault prediction method, characterized in that: Applied to a programmable controller, the programmable controller is applied to predict faults of a target device, the programmable controller is respectively connected to the server according to any one of claims 4 to 6 and to multiple sensors for communication, the multiple sensors communicate and collect: multiple second working data and target device operation and maintenance raw data, the multiple second working data are second working data corresponding to multiple timestamps, one second working data corresponds to one timestamp, including: Generate target device prediction data, the target device prediction data includes: a plurality of first working data and target device operation and maintenance data, the target device operation and maintenance data is generated by processing the target device operation and maintenance original data, the plurality of first working data is a part of the plurality of second working data after processing; Sending the target device prediction data to the server; A target device failure prediction result sent by the server is received, where the target device failure prediction result includes: a failure time of the target device, and the target device failure prediction result is generated based on the target device prediction data.

8. The method according to claim 7, characterized in that The target device fault prediction result further includes: fault prompt information, and the method further includes: In response to the fault prompt information, generating a maintenance suggestion for the target device based on the target device operation and maintenance data and the plurality of second working data; and / or In response to the fault prompt information, prompt information is generated.

9. The method according to claim 8, characterized in that The prompt information includes: one of the first prompt information or the second prompt information; The first prompt information is used to prompt that the target device needs maintenance; The second prompt information is used to prompt that the target device needs to be replaced.

10. A failure probability calculation device, applied to a server, characterized in that: include: A first acquisition module: used to acquire target working data, wherein the target working data is working data corresponding to a target timestamp, and the target working data includes a plurality of working parameters; A first calculation module: used for calculating a first Gini impurity based on the target working data, where the first Gini impurity includes: a Gini impurity corresponding to each working parameter in the first working data; A selection module: configured to select a second Gini impurity from the first Gini impurity, and select a target operating parameter from the plurality of operating parameters based on the second Gini impurity; A determination module is used to determine the failure probability corresponding to the target timestamp based on the target working parameter, wherein there is a mapping relationship between each working parameter and the failure probability, and the second Gini coefficient is the minimum value of the first Gini coefficients. For working parameters.

11. A fault prediction device, applied to a server, wherein the server is used to predict faults of a target device, characterized in that: A second acquisition module: acquiring target device prediction data, wherein the target device prediction data includes: a plurality of first working data and target device operation and maintenance data, wherein the plurality of first working data are first working data corresponding to a plurality of timestamps, and one first working data corresponds to one timestamp; A second calculation module: used for calculating the failure probability corresponding to each first working data in the plurality of first working data by using the method according to any one of claims 1 to 3; A second determination module: used to determine a decay curve based on the target equipment operation and maintenance data and the failure probability corresponding to each first working data; Prediction module: used to set a fault threshold and predict the failure time of the target device based on the fault threshold and the decay curve; The first sending module is used to send a target device failure prediction result, wherein the target device failure prediction result includes: a failure time of the target device.

12. A fault prediction device, characterized in that: Applied to a programmable controller, the programmable controller is used to predict the fault of a target device, the programmable controller is respectively connected to a server and a plurality of sensors for communication, and the plurality of sensors communicate and collect: a plurality of second working data and target device operation and maintenance raw data, the plurality of second working data are second working data corresponding to multiple timestamps, one second working data corresponds to one timestamp, including: A generating module: used to generate target device prediction data, wherein the target device prediction data includes: a plurality of first working data and target device operation and maintenance data, wherein the target device operation and maintenance data is generated by processing the target device operation and maintenance original data, and the plurality of first working data is a part of the plurality of second working data after processing; A second sending module: used for sending the target device prediction data to the server; Receiving module: used for receiving the target device failure prediction result sent by the server, the target device failure prediction result includes: the failure time of the target device, and the target device failure prediction result is generated based on the target device prediction data.

13. An electronic device, characterized in that: include: at least one processor; as well as at least one memory in communication with the processor, wherein: The memory stores program instructions executable by the processor, and the processor can execute the method according to any one of claims 1 to 3, 4 to 6, or 7 to 9 by calling the program instructions.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which enable the computer to execute the method according to any one of claims 1 to 3 or 4 to 6 or 7 to 9.

Images