Switching failure prediction method, system and electronic device based on bayesian theory

Abstract

The application discloses a switch fault prediction method and system based on Bayesian theory and electronic equipment, and relates to the technical field of switch fault prediction, and the method comprises the following steps: judging whether a switch is faulty or not according to a driving current digital signal and a displacement digital signal of the switch during opening and closing, and obtaining a first judgment result, wherein the opening and closing comprises opening or closing; when the first judgment result is no, inputting the driving current digital signal and the displacement digital signal into a fault identification model based on Bayesian theory to perform fault prediction on the switch, and obtaining a predicted fault probability. Through the fault identification model based on Bayesian theory, the fault probability of the switch after each opening and closing can be accurately predicted.

Description

Technical Field

[0001] This invention relates to the field of switch fault prediction technology, and in particular to a switch fault prediction method, system and electronic device based on Bayesian theory. Background Technology

[0002] With the large-scale integration of high-proportion renewable energy sources such as photovoltaics and wind power, new power systems are rapidly developing. However, the intermittent and random nature of renewable energy generation presents new challenges to the safety and stability of power systems. In power transmission and distribution, high-voltage switchgear is a critical control and protection device. Ensuring its stable mechanical reliability is crucial for power system safety; its performance directly affects the stable operation of the power system. Therefore, higher demands are placed on fault detection and lifespan prediction of high-voltage circuit breakers. Traditional fault detection methods often rely on field experience and physical testing, which are not only inefficient but also unable to handle complex fault modes, creating numerous difficulties for current field operations. Therefore, developing an efficient and intelligent fault detection method and device has become an indispensable need.

[0003] To address this, scholars and engineers have conducted numerous studies. In the invention patent with publication number "CN111458629A" entitled "An Automatic Identification Method and Device for Mechanical Faults of High-Voltage Switches," fault identification is primarily achieved by collecting on-site current and sound signals and performing neural network learning. However, the use of sound signals is severely affected by interference from the on-site environment, greatly impacting the reliability of the identification results. In the invention patent with publication number "CN117493848A" entitled "A Method and Device for Identifying Faults of Rapid Repulsion Switches," fault identification is achieved by collecting on-site switch displacement, vibration, and current signals, combined with an intelligent algorithm model. However, there are numerous intelligent algorithm models, some of which are extremely inefficient and unsuitable for rapid on-site diagnosis. Summary of the Invention

[0004] The technical problem to be solved by this invention is to address the shortcomings of existing technologies. Specifically, it provides a switch fault prediction method, system, and electronic device based on Bayesian theory, as detailed below:

[0005] 1) In a first aspect, the present invention provides a switch fault prediction method based on Bayesian theory, the specific technical solution of which is as follows:

[0006] Based on the digital signals of the drive current and displacement of the switch during opening and closing, it is determined whether the switch has malfunctioned, and a first judgment result is obtained. Here, opening and closing includes opening or closing.

[0007] When the first judgment result is negative, the digital signal of the driving current and the digital signal of the displacement are input into the fault identification model based on Bayesian theory to predict the fault of the switch and obtain the predicted fault probability.

[0008] The beneficial effects of the switch fault prediction method based on Bayesian theory provided by this invention are as follows:

[0009] By using a fault identification model based on Bayesian theory, the probability of a switch failure after each opening and closing can be accurately predicted.

[0010] Based on the above scheme, the switch fault prediction method based on Bayesian theory of the present invention can be further improved as follows.

[0011] Furthermore, it also includes:

[0012] The predicted failure probability is input into a life prediction model based on Bayesian theory to predict the life of the switch.

[0013] Furthermore, the process of acquiring the digital signals of drive current and displacement during switch opening and closing includes:

[0014] Acquire the drive current signal of the control switch in the opening and closing control circuit to open and close the circuit, and acquire the displacement signal of the switch during opening and closing;

[0015] The drive current signal and displacement signal are processed by analog-to-digital conversion to obtain the digital drive current signal and the digital displacement signal.

[0016] Furthermore, based on the digital signals of the drive current and displacement during the opening and closing of the switch, it is determined whether a fault has occurred in the switch, resulting in a first judgment result, including:

[0017] The system determines whether the digital signal of the driving current is within the preset error range of the preset standard digital signal of the driving current, and obtains a second determination result. It also determines whether the digital signal of the displacement is within the preset error range of the preset standard digital signal of the displacement, and obtains a third determination result.

[0018] If the second judgment result is negative and / or the third judgment result is negative, then the switch is determined to be faulty, and the first judgment result is positive.

[0019] Furthermore, based on the digital signals of the drive current and displacement during the opening and closing of the switch, a first judgment result is obtained by determining whether the switch has malfunctioned. This also includes:

[0020] If both the second and third judgment results are yes, then the switch is determined to be not faulty, and the first judgment result is no.

[0021] Furthermore, the drive current signal of the control switch in the opening and closing control circuit is collected, and the displacement signal of the switch during opening and closing is also collected, including:

[0022] The drive current signal for the control switch to open and close is acquired through the Rogowski coil, and the displacement signal of the switch during opening and closing is acquired through the displacement sensor.

[0023] Furthermore, the switch is a high-voltage switch.

[0024] 2) Secondly, the present invention also provides a switch fault prediction system based on Bayesian theory, the specific technical solution of which is as follows:

[0025] Includes a judgment module and a fault prediction module;

[0026] The judgment module is used to: determine whether the switch has malfunctioned based on the digital signals of the drive current and displacement when the switch is opened and closed, and obtain a first judgment result, wherein opening and closing includes opening or closing;

[0027] The fault prediction module is used to: when the first judgment result is negative, input the digital signal of the driving current and the digital signal of the displacement into the fault identification model based on Bayesian theory to predict the fault of the switch and obtain the predicted fault probability.

[0028] Based on the above scheme, the switch fault prediction system based on Bayesian theory of the present invention can be further improved as follows.

[0029] Furthermore, it also includes a life prediction module, which is used to: input the predicted failure probability into a life prediction model based on Bayesian theory to predict the life of the switch.

[0030] Furthermore, it also includes a digital signal acquisition module, which is used for:

[0031] Acquire the drive current signal of the control switch in the opening and closing control circuit to open and close the circuit, and acquire the displacement signal of the switch during opening and closing;

[0032] The drive current signal and displacement signal are processed by analog-to-digital conversion to obtain the digital drive current signal and the digital displacement signal.

[0033] Furthermore, the judgment module is specifically used for:

[0034] The system determines whether the digital signal of the driving current is within the preset error range of the preset standard digital signal of the driving current, and obtains a second determination result. It also determines whether the digital signal of the displacement is within the preset error range of the preset standard digital signal of the displacement, and obtains a third determination result.

[0035] If the second judgment result is negative and / or the third judgment result is negative, then the switch is determined to be faulty, and the first judgment result is positive.

[0036] Furthermore, the judgment module is also specifically used for:

[0037] If both the second and third judgment results are yes, then the switch is determined to be not faulty, and the first judgment result is no.

[0038] Furthermore, the digital signal acquisition module is also specifically used for:

[0039] The drive current signal for the control switch to open and close is acquired through the Rogowski coil, and the displacement signal of the switch during opening and closing is acquired through the displacement sensor.

[0040] Furthermore, the switch is a high-voltage switch.

[0041] 3) In a third aspect, the present invention also provides an electronic device, the electronic device including a processor coupled to a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor, so as to enable the electronic device to implement any of the above-mentioned switching fault prediction methods based on Bayesian theory.

[0042] 4) In a fourth aspect, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the above-mentioned switch fault prediction methods based on Bayesian theory.

[0043] It should be noted that the beneficial effects of the technical solutions of the second to fourth aspects of the present invention and their corresponding possible implementations can be found in the above description of the technical effects of the first aspect and its corresponding possible implementations, and will not be repeated here. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments of the present invention will be briefly introduced below:

[0045] Figure 1 This is a flowchart illustrating a switch fault prediction method based on Bayesian theory according to an embodiment of the present invention.

[0046] Figure 2 A schematic diagram of the envelope corresponding to the preset standard drive current digital signal;

[0047] Figure 3 This is a schematic diagram of the network structure of the first Bayesian network;

[0048] Figure 4This is a schematic diagram of a switch fault prediction system based on Bayesian theory according to an embodiment of the present invention.

[0049] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0050] The principles and features of the present invention are described below. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0051] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0052] like Figure 1 As shown in the figure, a switch fault prediction method based on Bayesian theory according to an embodiment of the present invention includes the following steps:

[0053] S1. Based on the digital signals of the driving current and displacement of the switch when it is open or closed, determine whether the switch has malfunctioned and obtain the first judgment result. Here, opening and closing includes opening or closing.

[0054] S2. When the first judgment result is negative, the digital signal of the driving current and the digital signal of the displacement are input into the fault identification model based on Bayesian theory to predict the fault of the switch and obtain the predicted fault probability.

[0055] Optionally, the above technical solution also includes:

[0056] S3. Input the predicted failure probability into the life prediction model based on Bayesian theory to predict the life of the switch.

[0057] Optionally, in the above technical solution, the process of acquiring the digital signals of the driving current and displacement during the opening and closing of the switch includes:

[0058] S010. Acquire the drive current signal of the control switch in the opening and closing control circuit to open and close the circuit, and acquire the displacement signal of the switch during opening and closing.

[0059] S011. Perform analog-to-digital conversion on the drive current signal and displacement signal to obtain the digital drive current signal and digital displacement signal.

[0060] Optionally, in S1, based on the digital signals of the drive current and displacement during the opening and closing of the switch, it is determined whether a fault has occurred in the switch, and a first determination result is obtained, including:

[0061] S10. Determine whether the digital signal of the driving current is within the preset error range of the preset standard digital signal of the driving current, and obtain the second determination result. Also determine whether the digital signal of the displacement is within the preset error range of the preset standard digital signal of the displacement, and obtain the third determination result.

[0062] S11. When the second judgment result is negative and / or the third judgment result is negative, the switch is determined to be faulty, and the first judgment result is positive.

[0063] Optionally, in S1, determining whether a switch malfunction has occurred based on the digital signals of the drive current and displacement during the opening and closing of the switch, and obtaining a first determination result, further includes:

[0064] S12. When both the second and third judgment results are yes, it is determined that the switch is not faulty and the first judgment result is no.

[0065] Optionally, in S010, the drive current signal of the control switch in the opening and closing control circuit is collected, and the displacement signal of the switch during opening and closing is collected, including:

[0066] S0100: The drive current signal of the control switch for opening and closing is acquired through the Rogowski coil, and the displacement signal of the switch during opening and closing is acquired through the displacement sensor.

[0067] Optionally, in the above technical solution, the switch is a high-voltage switch.

[0068] Taking a high-voltage switch as an example, the present invention will be further explained and described, specifically including the following steps:

[0069] S101. The drive current signal for closing the high-voltage switch is acquired through the Rogowski coil, and the displacement signal of the high-voltage switch when closing is acquired through the displacement sensor. Both the drive current signal and the displacement signal are analog signals.

[0070] S102. Perform analog-to-digital conversion on the drive current signal and displacement signal to obtain the digital drive current signal and digital displacement signal.

[0071] S103. Obtain the first judgment result, specifically:

[0072] The second judgment result is obtained by determining whether the digital drive current signal is within the preset error range of the preset standard digital drive current signal, and the third judgment result is obtained by determining whether the digital displacement signal is within the preset error range of the preset standard digital displacement signal. Then:

[0073] 1) If the second judgment result is negative and / or the third judgment result is negative, then the high-voltage switch is determined to be faulty, and the first judgment result is positive;

[0074] 2) When both the second and third judgment results are yes, it is determined that the high-voltage switch has not malfunctioned, and the first judgment result is no.

[0075] The process of acquiring the preset standard drive current digital signal and the preset standard displacement digital signal is as follows:

[0076] After confirming that the high-voltage switch and its corresponding opening and closing control circuit are both in normal working condition, the opening and closing control circuit sends a drive current to control the high-voltage switch to close. The drive current signal used by the opening and closing control circuit to control the high-voltage switch to close is collected through the Rogowski coil and used as the standard drive current signal. The displacement signal of the high-voltage switch when it is closed is collected through the displacement sensor and used as the standard displacement signal. The standard drive current signal and the standard displacement signal are converted from analog to digital to obtain the preset standard drive current digital signal and the preset standard displacement digital signal.

[0077] Among them, the driving current signal is: the curve data of the driving current used to control the closing of the high-voltage switch as a function of time. In this curve data, the horizontal axis is time and the vertical axis is driving current. The time when the driving current is generated is taken as the start time and the time when the driving current decreases to 0 is taken as the end time.

[0078] The displacement signal is a curve showing the displacement of the moving contact of the high-voltage switch as a function of time when the switch is closed. In this curve, the horizontal axis represents time, and the vertical axis represents the displacement of the moving contact. The moment when the driving current is generated is taken as the start time, and the moment when the driving current decreases to 0 is taken as the end time.

[0079] The process of obtaining the preset error range of the preset standard drive current digital signal includes:

[0080] According to the preset drive current error value of the preset standard drive current digital signal, the curve corresponding to the preset standard drive current digital signal is offset. Specifically, the preset drive current error value is added to the drive current at each moment in the preset standard drive current digital signal to obtain the upper limit offset curve corresponding to the preset standard drive current digital signal. The preset drive current error value is subtracted from the drive current at each moment in the preset standard drive current digital signal to obtain the lower limit offset curve corresponding to the preset standard drive current digital signal. The range between the upper limit offset curve and the lower limit offset curve is the preset error range of the preset standard drive current digital signal.

[0081] In this system, the horizontal axis of the preset standard drive current digital signal represents time, and the vertical axis represents drive current. The moment when the drive current is generated is taken as the start time, and the moment when the drive current decreases to 0 is taken as the end time.

[0082] The second judgment result is obtained by determining whether the digital signal of the driving current is within the preset error range of the preset standard digital signal of the driving current. The specific implementation method is as follows:

[0083] 1) First implementation method:

[0084] After obtaining the digital drive current signal, the system first determines whether the duration between the start and end times in the digital drive current signal is equal to the duration between the start and end times of the preset standard digital drive current signal. If not, the second determination result is directly set to "no". If yes, the system continues to determine whether the drive current at each moment in the digital drive current signal is within the corresponding preset error range. If yes, the second determination result is "yes". If the drive current at any moment is not within the corresponding preset error range, the second determination result is "no". The preset error range for each moment can be obtained from the preset error range of the preset standard digital drive current signal.

[0085] like Figure 2 As shown, the upper limit offset curve and the lower limit offset curve corresponding to the preset standard drive current digital signal are used as two envelopes. Then, the starting and ending data points of the upper limit offset curve and the lower limit offset curve corresponding to the preset standard drive current digital signal are connected by straight lines to form two envelopes, as shown below. Figure 2 As shown by the dashed line, the four envelope lines form an envelope. When the digital signal of the driving current is completely within the envelope, it is determined that the driving current at each moment in the digital signal of the driving current is within the corresponding preset error range, and the second judgment result is yes. When the digital signal of the driving current is not completely within the envelope, it is determined that the driving current at at least one moment is not within the corresponding preset error range, and the second judgment result is no.

[0086] 2) Second implementation method:

[0087] After obtaining the digital drive current signal, first determine whether the duration between the start and end times in the digital drive current signal is equal to the duration between the start and end times of the preset standard digital drive current signal. If not, directly determine the second determination result as negative. If yes, divide the digital drive current signal into N equal segments, with the duration Δt of each segment being:

[0088]

[0089] Where t represents the duration between the start time t0 and the end time t1 of the digital drive current signal.

[0090] The upper and lower offset curves corresponding to the preset standard drive current digital signal are divided into N equal segments. Each segment of the drive current digital signal is denoted as a drive current digital sub-signal. Each segment of the upper and lower offset curves corresponding to the preset standard drive current digital signal is denoted as an upper offset sub-curve and a lower offset sub-curve, respectively. Then, each drive current digital sub-signal is compared to see if it is within the error range between the corresponding upper and lower offset sub-curves. If any drive current digital sub-signal is not within the error range between the corresponding upper and lower offset sub-curves, the second judgment result is negative. If each drive current digital sub-signal is within the error range between the corresponding upper and lower offset sub-curves, the second judgment result is positive.

[0091] Specifically, the upper and lower offset sub-curves corresponding to any digital sub-signal of the driving current are used as two envelopes. The starting and ending data points of the upper and lower offset sub-curves are then connected by straight lines to form two envelopes. The four envelopes together form an envelope. It is determined that the digital sub-signal of the driving current is completely within this envelope, and a judgment result is obtained. Each digital sub-signal of the driving current is traversed to obtain N fourth judgment results. When all N fourth judgment results are yes, the second judgment result is yes. When one of the N fourth judgment results is no, the second judgment result is no.

[0092] In this system, the horizontal axis of the preset standard displacement digital signal represents time, and the vertical axis represents displacement. The moment when the driving current is generated is taken as the start time, and the moment when the driving current decreases to 0 is taken as the end time.

[0093] The third judgment result is obtained by determining whether the displacement digital signal is within the preset error range of the preset standard displacement digital signal. The specific implementation method is as follows:

[0094] 1) First implementation method:

[0095] After obtaining the displacement digital signal, the system first determines whether the duration between the start and end times in the displacement digital signal is equal to the duration between the start and end times of the preset standard displacement digital signal. If not, the third determination result is directly set to "no". If yes, the system continues to determine whether the displacement at each moment in the displacement digital signal is within the corresponding preset error range. If yes, the third determination result is "yes". If the displacement at any moment is not within the corresponding preset error range, the third determination result is "no". The preset error range for each moment can be obtained from the preset error range of the preset standard displacement digital signal.

[0096] The upper limit offset curve and the lower limit offset curve corresponding to the preset standard displacement digital signal are used as two envelopes. The starting and ending data points of the upper limit offset curve and the lower limit offset curve corresponding to the preset standard displacement digital signal are connected by straight lines to form two envelopes. The four envelopes are combined to form an envelope. When the displacement digital signal is completely within the envelope, it is determined that the displacement at each moment in the displacement digital signal is within the corresponding preset error range, and the third judgment result is yes. When the displacement digital signal is not completely within the envelope, it is determined that the displacement at at least one moment is not within the corresponding preset error range, and the third judgment result is no.

[0097] 2) Second implementation method:

[0098] First, determine if the duration between the start and end times in the digital displacement signal is equal to the duration between the start and end times of the preset standard digital displacement signal. If not, directly determine the third judgment result as negative. If yes, continue to divide the digital displacement signal into n equal segments, each segment having a duration Δt. ′ for:

[0099]

[0100] Among them, t ′ Indicates: the start time t0 of the displacement digital signal ′ The termination time t1 of the displacement digital signal ′ The duration between them.

[0101] The upper and lower offset curves corresponding to the preset standard displacement digital signal are divided into n equal segments. Each segment of the displacement digital signal is denoted as a displacement digital sub-signal. Each segment of the upper and lower offset curves corresponding to the preset standard displacement digital signal is denoted as the upper offset sub-curve and the lower offset sub-curve, respectively. Then, each displacement digital sub-signal is compared to see if it is within the error range between the corresponding upper and lower offset sub-curves. If any displacement digital sub-signal is not within the error range between the corresponding upper and lower offset sub-curves, the third judgment result is negative. If each displacement digital sub-signal is within the error range between the corresponding upper and lower offset sub-curves, the third judgment result is positive.

[0102] Specifically, the upper and lower offset sub-curves corresponding to any displacement digital sub-signal are used as two envelopes. The starting and ending data points of the upper and lower offset sub-curves are then connected by straight lines to form two envelopes. The four envelopes together form an envelope. It is determined that the displacement digital sub-signal is completely within this envelope, and the judgment result is obtained. Each displacement digital sub-signal is traversed to obtain n fifth judgment results. When all n fifth judgment results are yes, the third judgment result is yes. When one of the n fifth judgment results is no, the third judgment result is no.

[0103] S104. Obtain the fault identification model based on Bayesian theory, specifically:

[0104] First, a Bayesian network is constructed. For ease of distinction, this Bayesian network is referred to as the first Bayesian network, and the components or parameters in the first Bayesian network are called Bayesian nodes. Based on the relationships between different Bayesian nodes, and by investigating historical data (historical digital signals of drive current, historical digital signals of displacement, and historical faults of high-voltage switches), a suitable topology can be constructed as the first Bayesian network, such as... Figure 3 As shown, T represents a fault, and N1, N2, N3, X1, X2, X3, and X4 are all Bayesian nodes. N1 represents a fault in the energy storage unit, N2 represents a fault in the drive unit, N3 represents a fault in the motion unit, X1 represents a fault in the energy storage capacitor, X2 represents a fault in the opening and closing coil, X3 represents a fault in the repulsion disk, and X4 represents a fault in the transmission rod. N1 includes X1, N2 includes X2, and N3 includes both X3 and X4.

[0105] Then, based on the historical digital signals of driving current, displacement, and faults of the high-voltage switch, the constructed first Bayesian network is trained, and the probabilities of each Bayesian node are gradually adjusted. After training, a fault identification model based on Bayesian theory is obtained. The fault identification model based on Bayesian theory can be used to predict faults based on the real-time digital signals of driving current and displacement. Moreover, the fault identification model based on Bayesian theory can be iteratively trained based on newly obtained digital signals of current, displacement, and faults, which can ensure the accuracy of fault prediction of the fault identification model based on Bayesian theory.

[0106] The fault prediction logic of the fault identification model based on Bayesian theory is as follows:

[0107]

[0108] According to Bayesian theory, the algorithm should be divided into three parts: obtaining the failure probability of the basic node (prior probability), the influence of a certain condition on the failure probability (likelihood), and failure probability prediction (posterior probability). Specifically:

[0109] 1) Prior probability: Establish a Bayesian network, based on past equipment operation experience and data, and let the event of component failure, such as opening and closing coil failure, relay failure, etc., be X. i .

[0110] 2) Likelihood: Each influencing factor, such as usage time, maintenance frequency, etc., is represented by Yi. Factors with different degrees of influence are evaluated.

[0111] 3) Posterior probability: Based on the failure to operate defect, associate the failure event X. i Fault prediction is performed based on the probability of occurrence of influencing factor Yi.

[0112] S105. When the first judgment result is negative, the digital signal of the driving current and the digital signal of the displacement are input into the fault identification model based on Bayesian theory to predict the fault of the high-voltage switch and obtain the predicted fault probability. Then, S106 is executed. When the first judgment result is positive, it indicates that the high-voltage switch has issued a fault and a fault reminder can be issued to remind the high-voltage switch to be replaced or repaired to avoid further losses.

[0113] S106. Input the predicted failure probability into the life prediction model based on Bayesian theory to predict the life of the switch.

[0114] First, a Bayesian network is constructed. For ease of distinction, this constructed Bayesian network is referred to as the second Bayesian network, and the components or parameters in the second Bayesian network are called Bayesian nodes. Based on the relationships between different Bayesian nodes, and by investigating historical data (historical fault probabilities of high-voltage switches and the corresponding actual lifespan of high-voltage switches), a suitable topology can be constructed as the second Bayesian network. Then, based on the historical fault probabilities of high-voltage switches and the corresponding actual lifespan of high-voltage switches, the constructed second Bayesian network is trained. By gradually adjusting the probabilities of each Bayesian node, the algorithm can be optimized. After training, a lifespan prediction model based on Bayesian theory is obtained. This lifespan prediction model can be used to predict faults based on real-time obtained digital signals of drive current and displacement. Furthermore, iterative training can be performed on the lifespan prediction model based on Bayesian theory based on newly obtained digital signals of current and displacement, ensuring the accuracy of fault prediction.

[0115] In the above embodiments, the "digital signal of driving current and digital signal of displacement obtained when the high-voltage switch is closed" is used as an example for illustration. The implementation logic of the fault prediction process and life prediction process of the high-voltage switch when it is opened is the same as in the above embodiments, and will not be repeated here.

[0116] In the above embodiments, although the steps are numbered S1, S2, etc., they are only specific embodiments given by the present invention. Those skilled in the art can adjust the execution order of S1, S2, etc. according to the actual situation, which is also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0117] like Figure 4 As shown, a switch fault prediction system 200 based on Bayesian theory according to an embodiment of the present invention includes a judgment module 201 and a fault prediction module 202.

[0118] The judgment module 201 is used to: determine whether the switch has malfunctioned based on the digital signal of the drive current and the digital signal of the displacement when the switch is opened or closed, and obtain a first judgment result, wherein opening and closing includes opening or closing.

[0119] The fault prediction module 202 is used to: when the first judgment result is negative, input the digital signal of the driving current and the digital signal of the displacement into the fault identification model based on Bayesian theory to perform fault prediction on the switch and obtain the predicted fault probability.

[0120] Optionally, the above technical solution also includes a life prediction module, which is used to: input the predicted failure probability into a life prediction model based on Bayesian theory to predict the life of the switch.

[0121] Optionally, the above technical solution further includes a digital signal acquisition module, which is used for:

[0122] Acquire the drive current signal of the control switch in the opening and closing control circuit to open and close the circuit, and acquire the displacement signal of the switch during opening and closing;

[0123] The drive current signal and displacement signal are processed by analog-to-digital conversion to obtain the digital drive current signal and the digital displacement signal.

[0124] Optionally, in the above technical solution, the judgment module 201 is specifically used for:

[0125] The system determines whether the digital signal of the driving current is within the preset error range of the preset standard digital signal of the driving current, and obtains a second determination result. It also determines whether the digital signal of the displacement is within the preset error range of the preset standard digital signal of the displacement, and obtains a third determination result.

[0126] If the second judgment result is negative and / or the third judgment result is negative, then the switch is determined to be faulty, and the first judgment result is positive.

[0127] Optionally, in the above technical solution, the judgment module 201 is further specifically used for:

[0128] If both the second and third judgment results are yes, then the switch is determined to be not faulty, and the first judgment result is no.

[0129] Optionally, in the above technical solution, the digital signal acquisition module is further specifically used for:

[0130] The drive current signal for the control switch to open and close is acquired through the Rogowski coil, and the displacement signal of the switch during opening and closing is acquired through the displacement sensor.

[0131] Optionally, in the above technical solution, the switch is a high-voltage switch.

[0132] It should be noted that the beneficial effects of the switch fault prediction system 200 based on Bayesian theory provided in the above embodiments are the same as those of the switch fault prediction method based on Bayesian theory, and will not be repeated here. Furthermore, the system provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to the actual situation to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process is detailed in the method embodiments, and will not be repeated here.

[0133] The switch fault prediction system based on Bayesian theory of the present invention can be a computer program (including program code) running on a computer device. For example, the switch fault prediction system based on Bayesian theory of the present invention is an application software that can be used to execute the corresponding steps in the switch fault prediction method based on Bayesian theory of the present invention.

[0134] In some embodiments, the Bayesian theory-based switch fault prediction system of the present invention can be implemented in a combination of hardware and software. As an example, the Bayesian theory-based switch fault prediction system of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the Bayesian theory-based switch fault prediction method of the present invention. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0135] The modules described in the embodiments of this invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0136] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-mentioned switching fault prediction methods based on Bayesian theory. That is, an electronic device according to an embodiment of the present invention may include, but is not limited to: a processor and a memory; the memory is used to store the computer program; the processor is used to execute the switching fault prediction method based on Bayesian theory shown in any embodiment of the present invention by calling the computer program.

[0137] In one alternative embodiment, an electronic device is provided, such as Figure 5 As shown, Figure 5 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0138] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0139] Bus 4002 may include a path for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus 4002 is represented by only one thick line, but this does not mean that there is only one bus or one type of bus.

[0140] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0141] The memory 4003 stores the application code (computer program) for executing the present invention, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0142] Among them, electronic devices can also be terminal devices. A terminal device can be any terminal device that can install applications and access web pages through applications, including at least one of smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, smart TVs, and smart in-vehicle devices.

[0143] It should be noted that, Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0144] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the above-mentioned switch fault prediction methods based on Bayesian theory.

[0145] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0146] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform any of the aforementioned Bayesian theory-based switching fault prediction methods.

[0147] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0148] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0149] The computer-readable storage medium provided in this invention can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0150] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0151] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0152] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.

[0153] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this invention can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0154] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A switch fault prediction method based on Bayesian theory, characterized in that, include: Based on the digital signals of the driving current and displacement of the switch during opening and closing, it is determined whether the switch has malfunctioned, and a first judgment result is obtained, wherein opening and closing includes opening or closing. When the first judgment result is negative, the digital signal of the driving current and the digital signal of the displacement are input into the fault identification model based on Bayesian theory to perform fault prediction on the switch and obtain the predicted fault probability. Based on the digital signals of the drive current and displacement during the opening and closing of the switch, a first judgment result is obtained to determine whether the switch has malfunctioned, including: A second judgment result is obtained by determining whether the driving current digital signal is within the preset error range of the preset standard driving current digital signal, and a third judgment result is obtained by determining whether the displacement digital signal is within the preset error range of the preset standard displacement digital signal. When the second judgment result is negative and / or the third judgment result is negative, the switch is determined to be faulty, and the first judgment result is positive. Specifically, determining whether the digital signal of the driving current is within the preset error range of the preset standard digital signal of the driving current to obtain the second determination result can be implemented in either the first or the second manner: The first implementation method is as follows: After obtaining the digital signal of the driving current, firstly determine whether the duration between the start time and the end time in the digital signal of the driving current is equal to the duration between the start time and the end time of the preset standard digital signal of the driving current. If not, directly determine the second judgment result as negative. If yes, continue to determine whether the driving current at each moment in the digital signal of the driving current is within the corresponding preset error range. If yes, the second judgment result is positive. If the driving current at any moment is not within the corresponding preset error range, the second judgment result is negative. The upper limit offset curve and the lower limit offset curve corresponding to the preset standard drive current digital signal are used as two envelopes. Then, the starting data points and ending data points of the upper limit offset curve and the lower limit offset curve corresponding to the preset standard drive current digital signal are connected by straight lines to form two envelopes. The four envelopes are combined to form an envelope. When the drive current digital signal is completely within the envelope, it is determined that the drive current at each moment in the drive current digital signal is within the corresponding preset error range, and the second judgment result is yes. When the drive current digital signal is not completely within the envelope, it is determined that the drive current at at least one moment is not within the corresponding preset error range, and the second judgment result is no. The second implementation method: After obtaining the digital driving current signal, first determine whether the duration between the start and end times in the digital driving current signal is equal to the duration between the start and end times of the preset standard digital driving current signal. If not, directly determine the second judgment result as negative; if yes, divide the digital driving current signal into equal parts. Each segment has a duration of [duration]. The upper and lower offset curves corresponding to the preset standard drive current digital signal are equally divided into... Each segment of the driving current digital signal is denoted as a driving current digital sub-signal. Each segment of the upper limit offset curve and lower limit offset curve corresponding to the preset standard driving current digital signal is denoted as an upper limit offset sub-curve and a lower limit offset sub-curve, respectively. Then, each driving current digital sub-signal is compared to see if it is within the error range between the corresponding upper limit offset sub-curve and lower limit offset sub-curve. If any driving current digital sub-signal is not within the error range between the corresponding upper limit offset sub-curve and lower limit offset curve, the second judgment result is negative. If each driving current digital sub-signal is within the error range between the corresponding upper limit offset sub-curve and lower limit offset curve, the second judgment result is positive. Specifically, the upper and lower offset sub-curves corresponding to any given digital sub-signal of the driving current are used as two envelopes. The starting and ending data points of these two curves are then connected by straight lines to form two envelopes. These four envelopes together form a single envelope. The result is determined by identifying if the digital sub-signal of the driving current is completely within this envelope. This process is repeated for each digital sub-signal of the driving current. The fourth judgment result, when When all four fourth judgments are true, then the second judgment is true. If any of the fourth judgment results is negative, then the second judgment result is negative.

2. The switch fault prediction method based on Bayesian theory according to claim 1, characterized in that, Also includes: The predicted failure probability is input into a lifetime prediction model based on Bayesian theory to predict the lifetime of the switch.

3. A switch fault prediction method based on Bayesian theory according to claim 1 or 2, characterized in that, The process of acquiring the digital signals of drive current and displacement during switch opening and closing includes: The drive current signal of the opening and closing control circuit that controls the switch to open and close is collected, and the displacement signal of the switch during opening and closing is also collected. The driving current signal and the displacement signal are subjected to analog-to-digital conversion to obtain the driving current digital signal and the displacement digital signal.

4. The switch fault prediction method based on Bayesian theory according to claim 1, characterized in that, Based on the digital signals of the drive current and displacement during the opening and closing of the switch, a first judgment result is obtained by determining whether the switch has malfunctioned. The method also includes: When both the second and third judgment results are yes, it is determined that the switch is not faulty, and the first judgment result is no.

5. The switch fault prediction method based on Bayesian theory according to claim 3, characterized in that, The drive current signal that controls the opening and closing of the switch in the opening and closing control circuit is collected, and the displacement signal of the switch during opening and closing is also collected, including: The drive current signal that controls the opening and closing of the switch is acquired through the Rogowski coil, and the displacement signal of the switch during opening and closing is acquired through the displacement sensor.

6. A switch fault prediction method based on Bayesian theory according to claim 1 or 2, characterized in that, The switch is a high-voltage switch.

7. A switch fault prediction system based on Bayesian theory, characterized in that, Includes a judgment module and a fault prediction module; The judgment module is used to: determine whether the switch has malfunctioned based on the digital signal of the driving current and the digital signal of the displacement when the switch is opened and closed, and obtain a first judgment result, wherein opening and closing includes opening or closing. The fault prediction module is used to: when the first judgment result is negative, input the driving current digital signal and the displacement digital signal into a fault identification model based on Bayesian theory to perform fault prediction on the switch and obtain the predicted fault probability. The judgment module is specifically used for: The system determines whether the digital signal of the driving current is within the preset error range of the preset standard digital signal of the driving current, and obtains a second determination result. It also determines whether the digital signal of the displacement is within the preset error range of the preset standard digital signal of the displacement, and obtains a third determination result. If the second judgment result is negative and / or the third judgment result is negative, then the switch is determined to be faulty, and the first judgment result is positive. Specifically, determining whether the digital signal of the driving current is within the preset error range of the preset standard digital signal of the driving current to obtain the second determination result can be implemented in either the first or the second manner: The first implementation method is as follows: After obtaining the digital signal of the driving current, firstly determine whether the duration between the start time and the end time in the digital signal of the driving current is equal to the duration between the start time and the end time of the preset standard digital signal of the driving current. If not, directly determine the second judgment result as negative. If yes, continue to determine whether the driving current at each moment in the digital signal of the driving current is within the corresponding preset error range. If yes, the second judgment result is positive. If the driving current at any moment is not within the corresponding preset error range, the second judgment result is negative. The upper limit offset curve and the lower limit offset curve corresponding to the preset standard drive current digital signal are used as two envelopes. Then, the starting data points and ending data points of the upper limit offset curve and the lower limit offset curve corresponding to the preset standard drive current digital signal are connected by straight lines to form two envelopes. The four envelopes are combined to form an envelope. When the drive current digital signal is completely within the envelope, it is determined that the drive current at each moment in the drive current digital signal is within the corresponding preset error range, and the second judgment result is yes. When the drive current digital signal is not completely within the envelope, it is determined that the drive current at at least one moment is not within the corresponding preset error range, and the second judgment result is no. The second implementation method: After obtaining the digital driving current signal, first determine whether the duration between the start and end times in the digital driving current signal is equal to the duration between the start and end times of the preset standard digital driving current signal. If not, directly determine the second judgment result as negative; if yes, divide the digital driving current signal into equal parts. Each segment has a duration of [duration]. The upper and lower offset curves corresponding to the preset standard drive current digital signal are equally divided into... Each segment of the driving current digital signal is denoted as a driving current digital sub-signal. Each segment of the upper limit offset curve and lower limit offset curve corresponding to the preset standard driving current digital signal is denoted as an upper limit offset sub-curve and a lower limit offset sub-curve, respectively. Then, each driving current digital sub-signal is compared to see if it is within the error range between the corresponding upper limit offset sub-curve and lower limit offset sub-curve. If any driving current digital sub-signal is not within the error range between the corresponding upper limit offset sub-curve and lower limit offset curve, the second judgment result is negative. If each driving current digital sub-signal is within the error range between the corresponding upper limit offset sub-curve and lower limit offset curve, the second judgment result is positive. Specifically, the upper and lower offset sub-curves corresponding to any given digital sub-signal of the driving current are used as two envelopes. The starting and ending data points of these two curves are then connected by straight lines to form two envelopes. These four envelopes together form a single envelope. The result is determined by identifying if the digital sub-signal of the driving current is completely within this envelope. This process is repeated for each digital sub-signal of the driving current. The fourth judgment result, when When all four fourth judgments are true, then the second judgment is true. If any of the fourth judgment results is negative, then the second judgment result is negative.

8. An electronic device, characterized in that, The invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a switch fault prediction method based on Bayesian theory as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements a switch fault prediction method based on Bayesian theory as described in any one of claims 1 to 6.

Images