Equipment fault diagnosis method and device, medical equipment and computer program product

Abstract

The invention relates to the technical field of equipment maintenance, and provides an equipment fault diagnosis method and device, medical equipment and a computer program product. The method comprises the following steps: acquiring prior probability data and likelihood probability data associated with to-be-diagnosed equipment; determining a target prior probability set according to the current diagnosis condition and the prior probability data; determining a target likelihood probability set according to the current abnormal phenomenon, the current diagnosis condition and the likelihood probability data; calculating a target posterior probability set according to the target prior probability set and the target likelihood probability set; and determining a fault diagnosis result of the to-be-diagnosed equipment according to the target posterior probability set. By adopting the method, the accuracy of the target posterior probability set obtained through calculation can be improved, so that a more accurate fault diagnosis result is obtained, and the time consumed for troubleshooting of equipment is shortened.

Description

Technical Field

[0001] The present application relates to the technical field of equipment maintenance, and in particular to an equipment fault diagnosis method, apparatus, medical equipment and computer program product. Background Art

[0002] As the structure and function of medical equipment become more and more complex, when abnormal phenomena occur in medical equipment, it is often difficult for on-site personnel to find the cause of the abnormal phenomenon in time and accurately locate the possible failure of the medical equipment. For example, although complex medical imaging equipment has multiple monitoring points set up inside the system, the problems reported through the monitoring points are often not real fault information, but just abnormal phenomena. For example, when the abnormal phenomenon of CRC check error is reported through the monitoring point, the corresponding real fault may be optical module failure, DDR failure or FPGA failure, etc. At present, on-site personnel can usually only follow the standard troubleshooting process to check the possible causes of the abnormal phenomenon one by one, which shows that there is a problem of long troubleshooting time. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a device fault diagnosis method, apparatus, medical device and computer program product, which can shorten the time spent on device fault troubleshooting.

[0004] A first aspect of an embodiment of the present application provides a device fault diagnosis method, comprising:

[0005] Acquiring prior probability data and likelihood probability data associated with the device to be diagnosed;

[0006] Determine a target prior probability set according to the current diagnostic condition and prior probability data of the device to be diagnosed;

[0007] Determine a target likelihood probability set according to the current abnormal phenomenon of the device to be diagnosed, the current diagnostic condition and the likelihood probability data;

[0008] Calculate the target posterior probability set according to the target prior probability set and the target likelihood probability set;

[0009] According to the target posterior probability set, the fault diagnosis result of the equipment to be diagnosed is determined.

[0010] The embodiment of the present application pre-creates and maintains the prior probability data and likelihood probability data associated with the device to be diagnosed. When a certain abnormal phenomenon occurs in the device to be diagnosed, the target prior probability set is first determined according to the current diagnostic conditions and the prior probability data, and the target likelihood probability set is determined according to the current abnormal phenomenon, the current diagnostic conditions and the likelihood probability data. Then, the target posterior probability set is calculated based on the target prior probability set and the target likelihood probability set. Finally, the fault diagnosis result of the device to be diagnosed is determined based on the target posterior probability set. In the above process, by searching for the target prior probability set and the target likelihood probability set that are adapted to the current diagnostic conditions from the prior probability data and the likelihood probability data, respectively, the accuracy of the calculated target posterior probability set can be improved, and then a more accurate fault diagnosis result can be obtained, thereby shortening the time-consuming troubleshooting of the equipment.

[0011] In one implementation of the embodiment of the present application, the prior probability data includes a plurality of initial prior probability sets corresponding to different diagnostic conditions; the likelihood probability data includes a plurality of initial likelihood probability sets corresponding to different diagnostic conditions; and according to the current diagnostic condition of the device to be diagnosed and the prior probability data, determining the target prior probability set includes:

[0012] Selecting an initial prior probability set corresponding to the current diagnosis condition from multiple initial prior probability sets as a target prior probability set;

[0013] According to the current abnormal phenomenon of the device to be diagnosed, the current diagnostic conditions and the likelihood probability data, the target likelihood probability set is determined, including:

[0014] Selecting an initial likelihood probability set corresponding to a current diagnostic condition from a plurality of initial likelihood probability sets;

[0015] From the initial likelihood probability set corresponding to the current diagnosis condition, the probability of occurrence of the current abnormal phenomenon when each fault of the device to be diagnosed occurs is selected as the target likelihood probability set.

[0016] In another implementation of the embodiment of the present application, the prior probability data includes multiple initial prior probability sets corresponding to different diagnostic conditions; the likelihood probability data includes multiple initial likelihood probability sets corresponding to different diagnostic conditions; and according to the current diagnostic condition of the device to be diagnosed and the prior probability data, determining the target prior probability set includes:

[0017] According to the current diagnostic conditions, determining the calculation weights of the multiple initial prior probability sets;

[0018] Perform weighted sum calculation on multiple initial prior probability sets according to their respective calculation weights to obtain a target prior probability set;

[0019] According to the current abnormal phenomenon of the device to be diagnosed, the current diagnostic conditions and the likelihood probability data, the target likelihood probability set is determined, including:

[0020] According to the current diagnostic conditions, determining the calculation weights of the multiple initial likelihood probability sets;

[0021] Perform weighted sum calculation on multiple initial likelihood probability sets according to their respective calculation weights to obtain a comprehensive likelihood probability set;

[0022] From the comprehensive likelihood probability set, the probability of occurrence of the current abnormal phenomenon when each fault of the equipment to be diagnosed occurs is selected as the target likelihood probability set.

[0023] In one implementation of the embodiment of the present application, after calculating the target posterior probability set according to the target prior probability set and the target likelihood probability set, it also includes:

[0024] After obtaining the actual fault result of the device to be diagnosed, the prior probability data and the likelihood probability data are updated according to the actual fault result;

[0025] According to the target posterior probability set and the actual fault result, the calculation weights of the multiple initial prior probability sets and the calculation weights of the multiple initial likelihood probability sets are updated.

[0026] In an implementation of an embodiment of the present application, the number of target prior probability sets, the number of target likelihood probability sets, and the number of target posterior probability sets are all multiple, and each target posterior probability set corresponds to a target prior probability set and a target likelihood probability set respectively; according to the target posterior probability set and the actual fault result, the calculation weights of the multiple initial prior probability sets and the calculation weights of the multiple initial likelihood probability sets are updated, including:

[0027] Determine the optimal posterior probability set that best matches the actual fault result from multiple target posterior probability sets;

[0028] Determining the target prior probability set corresponding to the optimal posterior probability set as the maximum prior probability set, and determining the target likelihood probability set corresponding to the optimal posterior probability set as the optimal likelihood probability set;

[0029] The calculation weight of the initial prior probability set associated with the highest prior probability set among the multiple initial prior probability sets is increased, and the calculation weight of the initial likelihood probability set associated with the optimal likelihood probability set among the multiple initial likelihood probability sets is increased.

[0030] In an implementation of the embodiment of the present application, the fault diagnosis result includes the fault troubleshooting sequence information of the device to be diagnosed; and the fault diagnosis result of the device to be diagnosed is determined according to the target posterior probability set, including:

[0031] Arrange the posterior probabilities contained in the target posterior probability set in order from large to small;

[0032] According to the arrangement order of each posterior probability, fault troubleshooting order information is generated.

[0033] In one implementation of the embodiment of the present application, the fault diagnosis result includes fault maintenance information of the device to be diagnosed; and the fault diagnosis result of the device to be diagnosed is determined according to the target posterior probability set, including:

[0034] Each posterior probability contained in the target posterior probability set is compared with the probability threshold value, and fault maintenance information is generated according to the comparison result.

[0035] A second aspect of an embodiment of the present application provides a device for diagnosing a fault in an equipment, comprising:

[0036] A data acquisition module, used to acquire prior probability data and likelihood probability data associated with the device to be diagnosed;

[0037] A priori probability determination module, used to determine a target priori probability set according to the current diagnostic condition of the device to be diagnosed and the priori probability data;

[0038] A likelihood probability determination module is used to determine a target likelihood probability set according to the current abnormal phenomenon of the device to be diagnosed, the current diagnostic conditions and the likelihood probability data;

[0039] A posterior probability calculation module, used to calculate a target posterior probability set based on a target prior probability set and a target likelihood probability set;

[0040] The fault diagnosis module is used to determine the fault diagnosis result of the device to be diagnosed according to the target posterior probability set.

[0041] A third aspect of an embodiment of the present application provides a medical device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the device fault diagnosis method provided in the first aspect of the embodiment of the present application is implemented.

[0042] A fourth aspect of the embodiments of the present application provides a computer program product. When the computer program product runs on a medical device, the medical device executes the device fault diagnosis method provided in the first aspect of the embodiments of the present application.

[0043] A fifth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the device fault diagnosis method provided in the first aspect of the embodiment of the present application is implemented.

[0044] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is a flow chart of a device fault diagnosis method provided by an embodiment of the present application;

[0046] Figure 2 It is a schematic diagram of the operation flow of the device fault diagnosis method provided by the embodiment of the present application in an actual application scenario;

[0047] Figure 3 It is a structural schematic diagram of a device fault diagnosis apparatus provided in an embodiment of the present application;

[0048] Figure 4 It is a schematic diagram of a medical device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures, technologies, etc. are proposed, so as to thoroughly understand the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details. In other cases, the detailed description of well-known systems, devices, circuits and methods is omitted to prevent unnecessary details from hindering the description of the present application. In addition, in the description of the present application specification and the attached claims, the terms "first", "second", "third" etc. are only used to distinguish the description, and cannot be interpreted as indicating or suggesting relative importance.

[0050] At present, the structures and functions of various medical devices such as medical imaging equipment are becoming more and more complex. When some abnormal phenomena occur in medical equipment, it is often only possible to manually check all possible causes of the abnormal phenomenon one by one to determine the possible faults of the equipment. This process is very dependent on the troubleshooting experience of the on-site personnel. If the on-site personnel are inexperienced or have not encountered similar faults, the troubleshooting will take a long time.

[0051] In view of the above technical problems, the embodiments of the present application provide a device fault diagnosis method, apparatus, medical device and computer program product, which can shorten the time of device fault troubleshooting by constructing a scientific and quantifiable fault analysis process. For more specific technical implementation details of the embodiments of the present application, please refer to the method embodiments described below.

[0052] It should be understood that the execution subjects of the various method embodiments of the present application are various types of electronic devices, such as medical devices, desktop computers, tablet computers, mobile phones, wearable devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, netbooks, personal digital assistants (PDA), medical imaging equipment, etc. The embodiments of the present application do not impose any restrictions on the specific type of the electronic device.

[0053] See also Figure 1 , shows a device fault diagnosis method provided by an embodiment of the present application, comprising:

[0054] 101. Obtaining prior probability data and likelihood probability data associated with the device to be diagnosed;

[0055] The device to be diagnosed refers to any type of electronic device that has some abnormal phenomenon and needs to be diagnosed to clarify the cause of the abnormal phenomenon and obtain the corresponding fault diagnosis results. For example, the device to be diagnosed can be a medical imaging device, a computer device or a CNC processing device, etc. The execution subject of each method embodiment of the present application can be the device to be diagnosed itself, or it can be any other electronic device that can obtain relevant probability data for analysis.

[0056] The embodiment of the present application pre-creates and maintains the prior probability data and likelihood probability data associated with the device to be diagnosed, wherein the prior probability data may include multiple initial prior probability sets corresponding to different diagnostic conditions, each initial prior probability set includes the probability of occurrence of each fault of the device to be diagnosed under the corresponding diagnostic conditions; the likelihood probability data may include multiple initial likelihood probability sets corresponding to different diagnostic conditions, each initial likelihood probability set includes the probability of occurrence of each abnormal phenomenon when each fault of the device to be diagnosed occurs under the corresponding diagnostic conditions. The embodiment of the present application does not impose any restrictions on the data storage format of the prior probability data and the likelihood probability data, and under normal circumstances, the data can be stored in a table format, in which case the prior probability data is a prior probability table, and the likelihood probability data is a likelihood probability table. In addition, the prior probability data can provide a corresponding description of the diagnostic conditions for each stored initial prior probability set, for example, each initial prior probability set can correspond to different diagnostic conditions such as time, scene or configuration. Similarly, the likelihood probability data can also provide a corresponding description of the diagnostic conditions for each stored initial likelihood probability set, for example, each initial likelihood probability set can correspond to different diagnostic conditions such as time, scene or configuration. For example, if the device to be diagnosed is a medical device, the probability of occurrence of various faults of the medical device under various conditions such as different times, different scenes or different configurations can be collected, such as the probability of fiber failure, the probability of optical module failure, the probability of DDR failure, the probability of lens damage, etc. Based on these probability data, the prior probability table of the medical device can be obtained. Similarly, the probability of occurrence of each abnormal phenomenon when each fault of the medical device occurs under various conditions such as different times, different scenes or different configurations can be collected, such as the probability of monitoring temperature exceeding the standard when DDR fails, the probability of monitoring voltage exceeding the standard when DDR fails, the probability of monitoring temperature exceeding the standard when optical module fails, etc. Based on these probability data, the likelihood probability table of the medical device can be obtained.

[0057] As an example, the fault set of the device to be diagnosed can be recorded as {A1, A2, A3...Am}, which includes m types of faults, such as fiber failure, optical module failure and DDR failure; the abnormal phenomenon set can be recorded as {B1, B2, B3...Bn}, which includes n types of abnormal phenomena, such as CRC check error, monitoring temperature exceeding the standard and monitoring voltage exceeding the standard. Each initial prior probability set can be recorded as X={P(A1), P(A2), P(A3)...P(Am)}, where P(A1) represents the probability of occurrence of fault A1, and so on; X corresponds to a diagnostic condition (such as a specified time, scene or configuration), and the prior probability data includes multiple initial prior probability sets corresponding to different diagnostic conditions, which can be recorded as {X1, X2, X3...}, where the size of each prior probability recorded in different initial prior probability sets can be different. Similarly, each initial likelihood probability set can be recorded as Y = {P(B1|A1), P(B1|A2)…P(B1|An), P(B2|A1), P(B2|A2)…P(B2|An)…P(Bn|A1), P(Bn|A2)…P(Bn|An)}, where P(B1|A1) represents the probability of occurrence of abnormal phenomenon B1 when fault A1 occurs, that is, the probability of abnormal phenomenon B1 occurring under the condition that fault A1 occurs, and so on; Y corresponds to a diagnostic condition (such as a specified time, scene or configuration), and the likelihood probability data includes multiple initial likelihood probability sets corresponding to different diagnostic conditions, which can be recorded as {Y1, Y2, Y3…}, where the sizes of the likelihood probabilities recorded in different initial likelihood probability sets can be different.

[0058] Under normal circumstances, the prior probability data and likelihood probability data can be obtained by statistical analysis based on the historical fault records of the device to be diagnosed, the historical fault records of a large number of other devices of the same type as the device to be diagnosed, and / or the common equipment fault records in the industry where the device to be diagnosed is located. For example, some probability data can be obtained through the historical data of the equipment manufacturer. These probability data may include probability data for all types of equipment, probability data for equipment produced only in the last three years, probability data for a specified fiber brand, general probability data for the industry, and probability data after certain specific events, etc. Among them, specific events refer to events that obviously affect the probability, such as revision events for quality issues, material switching events, or supplier replacement events, etc.

[0059] In the absence of sufficient data, approximate probability data can also be obtained through principle analysis and manual evaluation as prior probability data and likelihood probability data. For example, if the technician has a deep understanding of the working principle of the device to be diagnosed, he can predict the various possible faults of the device to be diagnosed and the probability of each fault through principle analysis and manual evaluation, thereby obtaining prior probability data; similarly, he can predict the probability of various abnormal phenomena when a certain fault occurs in the device to be diagnosed through principle analysis and manual evaluation, thereby obtaining likelihood probability data.

[0060] When certain abnormal phenomena occur in the equipment to be diagnosed, by obtaining appropriate prior probability data and likelihood probability data for calculation and analysis, a more accurate and quantitative fault diagnosis result can be obtained. For the specific calculation and analysis process, please refer to the following.

[0061] 102. Determine a target prior probability set according to the current diagnostic condition and prior probability data of the device to be diagnosed;

[0062] After obtaining the prior probability data, the first method is to select a suitable initial prior probability set from the multiple initial prior probability sets contained in the prior probability data according to the current diagnostic conditions of the device to be diagnosed as the target prior probability set to be used. The target prior probability set contains the probability of occurrence of each fault of the device to be diagnosed under the current diagnostic conditions. The second method is to assign calculation weights according to the current diagnostic conditions, perform weighted sum calculations on the multiple initial prior probability sets contained in the prior probability data, and obtain a comprehensive prior probability set as the target prior probability set to be used. The following describes these two methods in detail:

[0063] In one implementation of the embodiment of the present application, the prior probability data includes a plurality of initial prior probability sets corresponding to different diagnostic conditions; the likelihood probability data includes a plurality of initial likelihood probability sets corresponding to different diagnostic conditions; and according to the current diagnostic condition of the device to be diagnosed and the prior probability data, determining the target prior probability set includes:

[0064] From the multiple initial prior probability sets, an initial prior probability set corresponding to the current diagnosis condition is selected as the target prior probability set.

[0065] This method first determines the current diagnostic conditions of the device to be diagnosed, such as the time of the current diagnosis, the brand of the device, the scene configuration, and the events that affect the probability. Then, from the multiple initial prior probability sets contained in the prior probability data, select the initial prior probability set corresponding to the current diagnostic conditions as the target prior probability set. The number of target prior probability sets obtained here can be one or more. For example, assuming that the multiple initial prior probability sets are {X1, X2, X3}, where X2 corresponds to the current diagnostic conditions, then select X2 from {X1, X2, X3} as the target prior probability set. This method can obtain more accurate prior probabilities by selecting the initial prior probability set corresponding to the current diagnostic conditions, thereby improving the accuracy of calculating the posterior probability in the subsequent process.

[0066] In another implementation of the embodiment of the present application, a target prior probability set is determined according to the current diagnostic condition and prior probability data of the device to be diagnosed, including:

[0067] (1) Determine the calculation weights of multiple initial prior probability sets according to the current diagnostic conditions;

[0068] (2) Multiple initial prior probability sets are weighted and summed according to their respective calculation weights to obtain a target prior probability set.

[0069] After determining the current diagnostic condition of the device to be diagnosed, this method allocates calculation weights to the multiple initial prior probability sets contained in the prior probability data according to the current diagnostic condition, and then performs weighted summation calculation on the multiple initial prior probability sets according to their respective calculation weights to obtain a comprehensive prior probability set as the target prior probability set. For example, assuming that the multiple initial prior probability sets are {X1, X2, X3}, where X1 = {P(A1)1, P(A2)1, P(A3)1…P(Am)1}, X2 = {P(A1)2, P(A2)2, P(A3)2…P(Am)2}, X3 = {P(A1)3, P(A2)3, P(A3)3…P(Am)3}, the prior probability of X2 is determined according to the current diagnostic condition. To be more accurate, the calculation weights of X1, X2, and X3 can be set to 0.2, 0.6, and 0.2, respectively, so that the target prior probability set X=0.2*X1+0.6*X2+0.2*X3={P(A1), P(A2), P(A3)…P(Am)}, where P(A1)=0.2*P(A1)1+0.6*P(A1)2+0.2*P(A1)3, and so on. By setting it in this way, the calculation weights of each initial prior probability set can be reasonably allocated according to the current diagnostic conditions, so as to calculate a more reasonable comprehensive prior probability set, which can also improve the accuracy of calculating the posterior probability in the subsequent process.

[0070] 103. Determine a target likelihood probability set according to the current abnormal phenomenon of the device to be diagnosed, the current diagnostic condition, and the likelihood probability data;

[0071] After obtaining the likelihood probability data, two methods can also be used to select a suitable initial likelihood probability set from multiple initial likelihood probability sets contained in the likelihood probability data, and determine the target likelihood probability set. The target likelihood probability set contains the probability of occurrence of the current abnormal phenomenon when each fault of the device to be diagnosed occurs under the current diagnostic conditions. Since the initial likelihood probability set contains the probability of occurrence of each abnormal phenomenon when each fault of the device to be diagnosed occurs, and only the likelihood probability corresponding to the abnormal phenomenon currently occurring in the device to be diagnosed needs to be used in fault diagnosis, after selecting a suitable initial likelihood probability set, the probability of occurrence of the current abnormal phenomenon when each fault of the device to be diagnosed occurs can be extracted from it as the target likelihood probability set to be used. The following describes these two methods in detail:

[0072] In one implementation of the embodiment of the present application, the prior probability data includes a plurality of initial prior probability sets corresponding to different diagnostic conditions; the likelihood probability data includes a plurality of initial likelihood probability sets corresponding to different diagnostic conditions; and according to the current abnormal phenomenon of the device to be diagnosed, the current diagnostic condition and the likelihood probability data, the target likelihood probability set is determined, including:

[0073] (1) selecting an initial likelihood probability set corresponding to the current diagnostic condition from multiple initial likelihood probability sets;

[0074] (2) From the initial likelihood probability set corresponding to the current diagnostic conditions, the probability of occurrence of the current abnormal phenomenon when each fault of the equipment to be diagnosed occurs is selected as the target likelihood probability set.

[0075] This method first determines the current diagnostic condition of the device to be diagnosed, and selects the initial likelihood probability set corresponding to the current diagnostic condition from the multiple initial likelihood probability sets contained in the likelihood probability data as the preliminary likelihood probability set. The number of preliminary likelihood probability sets obtained here can be one or more. Since the preliminary likelihood probability set contains the probability of occurrence of each abnormal phenomenon when each fault of the device to be diagnosed occurs, it is necessary to filter out the probability of occurrence of the current abnormal phenomenon when each fault of the device to be diagnosed occurs from the preliminary likelihood probability set as the target likelihood probability set. For example, assuming that the multiple initial likelihood probability sets are {Y1, Y2, Y3}, where Y2 corresponds to the current diagnostic condition, then select Y2 from {Y1, Y2, Y3} as the preliminary likelihood probability set, and then filter out the part of the likelihood probability corresponding to the current abnormal phenomenon from Y2 to form the target likelihood probability set. For example, assuming that Y2 = {P(B1|A1), P(B1|A2)…P(B1|An), P(B2|A1), P(B2|A2)…P(B2|An)…P(Bn|A1), P(Bn|A2)…P(Bn|An)}, and the current abnormal phenomenon is B1, then the likelihood probability corresponding to B1 is selected from Y2, that is, {P(B1|A1), P(B1|A2)…P(B1|An)}, as the target likelihood probability set. This method can obtain a more accurate likelihood probability by selecting the initial likelihood probability set corresponding to the current diagnostic condition, thereby improving the accuracy of calculating the posterior probability in the subsequent process.

[0076] In another implementation of the embodiment of the present application, a target likelihood probability set is determined according to the current abnormal phenomenon of the device to be diagnosed, the current diagnostic condition, and the likelihood probability data, including:

[0077] (1) Determine the calculation weights of multiple initial likelihood probability sets according to the current diagnostic conditions;

[0078] (2) performing weighted sum calculation on multiple initial likelihood probability sets according to their respective calculation weights to obtain a comprehensive likelihood probability set;

[0079] (3) From the comprehensive likelihood probability set, select the probability of occurrence of the current abnormal phenomenon when each fault of the equipment to be diagnosed occurs as the target likelihood probability set.

[0080] After determining the current diagnostic condition of the device to be diagnosed, this method allocates the calculation weights of the multiple initial likelihood probability sets contained in the likelihood probability data according to the current diagnostic condition, and then performs weighted sum calculation on the multiple initial likelihood probability sets according to their respective calculation weights to obtain a comprehensive likelihood probability set. Since the comprehensive likelihood probability set also contains the probability of occurrence of each abnormal phenomenon when each fault of the device to be diagnosed occurs, it is necessary to filter out the probability of occurrence of the current abnormal phenomenon when each fault of the device to be diagnosed occurs from the comprehensive likelihood probability set as the target likelihood probability set. For example, suppose that multiple initial likelihood probability sets are {Y1, Y2, Y3}, where Y1 = {P(B1|A1)1, P(B1|A2)1…P(B1|An)1, P(B2|A1)1, P(B2|A2)1…P(B2|An)1…P(Bn|A1)1, P(Bn|A2)1…P(Bn|An)1}, and Y2 = {P(B1|A1) 2, P(B1∣A2)2…P(B1∣An)2, P(B2∣A1)2, P(B2∣A2)2…P(B2∣An)2…P(Bn∣A1)2, P(Bn∣A 2)2…P(Bn∣An)2}, Y3={P(B1∣A1)3, P(B1∣A2)3…P(B1∣An)3, P(B2∣A1)3, P(B2∣A2)3… P(B2|An)3…P(Bn|A1)3, P(Bn|A2)3…P(Bn|An)3}, according to the current diagnostic conditions, it is more accurate to determine the likelihood probability of Y2. Then, the calculation weights of Y1, Y2, and Y3 can be set to 0.2, 0.6, and 0.2 respectively. In this way, the comprehensive likelihood probability set Y=0.2*Y1+0.6*Y2+0.2*Y3={P(B ={P(B1|A1), P(B1|A2)…P(B1|An), P(B2|A1), P(B2|A2)…P(B2|An)…P(Bn|A1), P(Bn|A2)…P(Bn|An)}, where P(B1|A1)=0.2*P(B1|A1)1+0.6*P(B1|A1)2+0.2*P(B1|A1)3, and so on. Assuming that the current abnormal phenomenon is B1, the part of the likelihood probability corresponding to B1 is selected from the comprehensive likelihood probability set Y, that is, {P(B1|A1), P(B1|A2)…P(B1|An)}, as the target likelihood probability set. By setting in this way, the calculation weights of each initial likelihood probability set can be reasonably allocated according to the current diagnostic conditions, so as to calculate a more reasonable comprehensive likelihood probability set, which can also improve the accuracy of calculating the posterior probability in the subsequent process.

[0081] 104. Calculate a target posterior probability set according to the target prior probability set and the target likelihood probability set;

[0082] After determining the target prior probability set and the target likelihood probability set, the corresponding posterior probability can be calculated based on the target prior probability set and the target likelihood probability set, which is recorded as the target posterior probability set, which contains the probability of occurrence of each fault of the equipment to be diagnosed when the current abnormal phenomenon occurs. The specific calculation process can be combined with the Bayesian formula and the total probability formula.

[0083] As an example, assume that the fault set of the device to be diagnosed is {A1, A2, A3…Am}, the abnormal phenomenon set is {B1, B2, B3…Bn}, the current abnormal phenomenon observed from the monitoring point of the device to be diagnosed is B1, the target prior probability set is {P(A1), P(A2), P(A3)…P(Am)}, the target likelihood probability set is {P(B1|A1), P(B1|A2)…P(B1|An)}, and the target posterior probability set to be calculated is {P(A1|B1), P(A2|B1)…P(Am|B1)}. Taking P(A1|B1) as an example, the following calculation can be performed by combining the Bayesian formula and the total probability formula:

[0084] P(A1∣B1)=(P(B1∣A1)*P(A1)) / (P(B1∣A1)*P(A1)+P(B1∣A2)*P(A2)+…P(B1∣Am)*P(Am)).

[0085] According to the same calculation method of P(A1|B1), P(A2|B1), P(A3|B1)…P(Am|B1) can be calculated respectively, so as to obtain the target posterior probability set {P(A1|B1), P(A2|B1)…P(Am|B1)}. Among them, P(A1|B1) represents the probability of occurrence of fault A1 when abnormal phenomenon B1 occurs. If P(A1|B1) is high, it means that the cause of abnormal phenomenon B1 is likely to be fault A1, and fault A1 should be checked first, and so on.

[0086] The abnormal phenomenon that occurs can be a single abnormal phenomenon or multiple abnormal phenomena. Among them, the posterior probability of a single abnormal phenomenon can be obtained by the calculation formula of P(A1|B1) above. As for multiple abnormal phenomena, multiple phenomena can be used to replace a single phenomenon in the calculation formula of P(A1|B1) above for calculation. For example, assuming that abnormal phenomena B1 and B2 occur at the same time, B1B2 is used to replace B1 in the above calculation formula to calculate the corresponding posterior probability {P(A1|B1B2), P(A2|B1B2)…P(Am|B1B2)}. Compared with the posterior probability calculated based on a single abnormal phenomenon, the posterior probability calculated using multiple abnormal phenomena is more accurate. For example, the probability of P(A1|B1) may not be high, which means that it is impossible to clearly know whether the cause of the fault is A1 based only on the occurrence of abnormal phenomenon B1, while the probability of P(A1|B1B2) may be very high, which means that when abnormal phenomena B1 and B2 occur at the same time, it can be basically determined that the cause of the fault is A1.

[0087] In one implementation of the embodiment of the present application, after calculating the target posterior probability set according to the target prior probability set and the target likelihood probability set, it also includes:

[0088] (1) After obtaining the actual fault result of the device to be diagnosed, the prior probability data and the likelihood probability data are updated according to the actual fault result;

[0089] (2) According to the target posterior probability set and the actual fault result, the calculation weights of the multiple initial prior probability sets and the calculation weights of the multiple initial likelihood probability sets are updated.

[0090] The target posterior probability set records the probability of various faults of the equipment to be diagnosed under the condition of the current abnormal phenomenon. By analyzing the probability of various faults, the on-site personnel can prioritize the faults with higher probability, effectively shorten the troubleshooting time, and finally obtain the actual fault results of the equipment to be diagnosed. After obtaining the actual fault results of the equipment to be diagnosed, the prior probability data and likelihood probability data can be updated according to the actual fault results. For example, assuming that the actual fault result is fault A1, the probability of fault A1 and the likelihood probability related to A1 will change, so the maintained prior probability data and likelihood probability data are updated according to the change. Through this setting, in the process of multiple fault diagnosis of the equipment to be diagnosed, the prior probability data and likelihood probability data will be continuously updated in real time to improve the accuracy of these probability data. In addition, the target posterior probability set can be compared with the actual fault result. According to the comparison result, it can be known whether the calculation result of the target posterior probability set is accurate, and then it can be inferred whether the target prior probability set and target likelihood probability set used are accurate. The calculation weights of multiple initial prior probability sets in the prior probability data can be updated, and the calculation weights of multiple initial likelihood probability sets in the likelihood probability data can be updated.

[0091] In an implementation of an embodiment of the present application, the number of target prior probability sets, the number of target likelihood probability sets, and the number of target posterior probability sets are all multiple, and each target posterior probability set corresponds to a target prior probability set and a target likelihood probability set respectively; according to the target posterior probability set and the actual fault result, the calculation weights of the multiple initial prior probability sets and the calculation weights of the multiple initial likelihood probability sets are updated, including:

[0092] (1) Determine the optimal posterior probability set that best matches the actual fault result from multiple target posterior probability sets;

[0093] (2) determining the target prior probability set corresponding to the optimal posterior probability set as the highest prior probability set, and determining the target likelihood probability set corresponding to the optimal posterior probability set as the optimal likelihood probability set;

[0094] (3) Increasing the calculation weight of the initial prior probability set associated with the highest prior probability set among multiple initial prior probability sets, and increasing the calculation weight of the initial likelihood probability set associated with the optimal likelihood probability set among multiple initial likelihood probability sets.

[0095] According to the content described above, it can be known that multiple different target prior probability sets and multiple different target likelihood probability sets can be obtained by using different probability selection methods. These target prior probability sets are paired with target likelihood probability sets one by one, and multiple different target posterior probability sets can be calculated. For example, assuming that there are n target prior probability sets and n target likelihood probability sets, n target posterior probability sets can be calculated. After obtaining the actual fault result of the device to be diagnosed, each target posterior probability set is compared with the actual fault result, so as to determine a target posterior probability set that best matches the actual fault result, which is recorded as the optimal posterior probability set. For example, assuming that the three target posterior probability sets are Z1, Z2 and Z3, respectively, according to the actual fault result, it is confirmed that fault A1 has occurred, the current abnormal phenomenon is B1, and the posterior probability P(A1|B1) contained in Z2 is the largest, then Z2 can be determined as the optimal posterior probability set that best matches the actual fault result. After determining the optimal a priori probability set, the target prior probability set corresponding to the optimal a priori probability set is determined as the highest a priori probability set, and the target likelihood probability set corresponding to the optimal a priori probability set is determined as the optimal likelihood probability set, that is, the optimal a priori probability set is calculated based on the highest a priori probability set and the optimal likelihood probability set. Based on this, it can be known that the posterior probability calculated using the highest a priori probability set and the optimal likelihood probability set is closest to the actual fault result, so it can be considered that the highest a priori probability set and the optimal likelihood probability set have a higher accuracy. Therefore, the calculation weight of the initial prior probability set related to the highest a priori probability set among multiple initial prior probability sets can be increased, and the calculation weight of the initial likelihood probability set related to the optimal likelihood probability set among multiple initial likelihood probability sets can be increased. Among them, the initial prior probability set related to the highest priority probability set can be the highest priority probability set itself, or other initial prior probability sets used to calculate the highest priority probability set; the initial likelihood probability set related to the optimal likelihood probability set can be the optimal likelihood probability set itself, or other initial likelihood probability sets used to calculate the optimal likelihood probability set. By setting in this way, the initial prior probability set and initial likelihood probability set with higher accuracy can be selected and used to a greater extent, thereby improving the accuracy of calculating the posterior probability in the subsequent fault diagnosis process.

[0096] 105. Determine the fault diagnosis result of the device to be diagnosed according to the target posterior probability set.

[0097] After the target posterior probability set is calculated, the fault diagnosis result of the device to be diagnosed can be determined and displayed. Specifically, the target posterior probability set records the probability of various faults of the device to be diagnosed under the condition of the current abnormal phenomenon. By analyzing the various posterior probabilities recorded in the target posterior probability set, a reasonable troubleshooting sequence and a reasonable maintenance plan can be formulated. For example, assuming that the device to be diagnosed is a medical device, and the abnormal phenomenon currently occurring in the medical device is that the monitoring temperature exceeds the standard, the calculated target posterior probability set contains the probability of various faults of the medical device under the condition of the monitoring temperature exceeding the standard, such as the probability of optical fiber failure when the monitoring temperature exceeds the standard, the probability of optical module failure when the monitoring temperature exceeds the standard, the probability of memory damage when the monitoring temperature exceeds the standard, etc. Based on these probability data, it can be known which fault of the current medical device has the highest probability of occurrence, so as to formulate the most reasonable troubleshooting sequence and maintenance plan.

[0098] In an implementation of the embodiment of the present application, the fault diagnosis result includes the fault troubleshooting sequence information of the device to be diagnosed; and the fault diagnosis result of the device to be diagnosed is determined according to the target posterior probability set, including:

[0099] (1) Arrange the posterior probabilities contained in the target posterior probability set in order from large to small;

[0100] (2) Generate troubleshooting sequence information based on the order of the posterior probabilities.

[0101] The posterior probabilities contained in the target posterior probability set can be arranged in order from large to small, the most likely cause of the fault can be analyzed, and the specific value of this possibility can be quantified. According to the arrangement order of each posterior probability, the troubleshooting sequence information can be generated. For example, assuming that the sorted posterior probabilities are: P(A2|B1)>P(A3|B1)>P(A1|B1), it means that in the case of abnormal event B1, the probability of fault A2 occurring is the highest, the probability of fault A3 occurring is in the middle, and the probability of fault A1 occurring is the lowest. Based on this, the troubleshooting sequence information of "first troubleshoot fault A2, then troubleshoot fault A3, and finally troubleshoot fault A1" can be generated. Under the guidance of the troubleshooting sequence information, on-site personnel can give priority to troubleshooting faults with a higher probability of occurrence, thereby speeding up the speed of troubleshooting the actual fault and shortening the time spent on equipment troubleshooting.

[0102] In one implementation of the embodiment of the present application, the fault diagnosis result includes fault maintenance information of the device to be diagnosed; and the fault diagnosis result of the device to be diagnosed is determined according to the target posterior probability set, including:

[0103] Each posterior probability contained in the target posterior probability set is compared with the probability threshold value, and fault maintenance information is generated according to the comparison result.

[0104] Each posterior probability contained in the target posterior probability set can be obtained, and these posterior probabilities can be compared with the preset probability threshold values, and the corresponding fault maintenance information can be generated according to the comparison results. For example, the probability threshold values ​​80% and 10% can be set. When a certain posterior probability P(A2|B1)>80%, it can be considered that the A2 fault is about to occur, and the fault maintenance information of repairing or replacing the equipment and components related to the A2 fault is generated. When a certain posterior probability P(A1|B1)<10%, it can be considered that the occurrence of the B1 phenomenon may have a certain correlation with the A1 fault, but the possibility of the A1 fault is not high, and more abnormal phenomena can be monitored. Some abnormal phenomena may not affect the normal use of the equipment to be diagnosed, such as the equipment voltage has a trend of decreasing, the optical power has a trend of decreasing, etc. Whether the corresponding equipment and components need to be repaired immediately for such abnormal phenomena needs to be comprehensively considered in terms of cost and user experience. In actual operation, the above probability threshold values ​​can be reasonably set according to cost and user opinions, so as to achieve a balance between cost saving and risk avoidance. In addition, the definition of abnormal phenomena can also be set according to the degree, such as a 3%, 5%, 10% reduction in optical power, etc. This makes it easier to monitor the health status of the entire device and make good judgments for equipment maintenance.

[0105] As an example, Figure 2 It is a schematic diagram of the operation flow of the device fault diagnosis method provided in an embodiment of the present application in an actual application scenario.

[0106] exist Figure 2In the , by combing the root causes of the faults and monitoring the abnormal phenomenon set, a prior probability table and a likelihood probability table can be created and maintained, wherein the prior probability table contains multiple initial prior probability sets corresponding to different times, scenarios or configurations, and the likelihood probability table contains multiple initial likelihood probability sets corresponding to different times, scenarios or configurations. When diagnosing the equipment, you can select the appropriate prior probability from the prior probability table and the appropriate likelihood probability from the likelihood probability table according to the historical situation and the current problem. Then, based on the Bayesian formula, the selected prior probability and likelihood probability are combined for calculation to obtain the corresponding posterior probability. According to the posterior probability, it can be judged whether the current abnormal phenomenon will affect the normal use of the equipment. If it affects the use, the cause of the fault can be analyzed according to the calculated posterior probability, and the corresponding maintenance plan can be arranged. If it does not affect the use, it can be judged whether maintenance is needed in advance and a maintenance plan can be formulated based on the cost and user experience. In addition, after calculating the posterior probability, we can compare it with the actual fault results and analyze which prior probability and likelihood probability can be used to calculate the posterior probability that is closer to the actual situation, and then update the selection strategy of the prior probability and likelihood probability. Specifically, we can increase the calculation weight of the corresponding prior probability and likelihood probability when calculating the comprehensive probability data. At the same time, update the probability data of the prior probability table and the likelihood probability table according to the actual fault results.

[0107] The embodiment of the present application pre-creates and maintains the prior probability data and likelihood probability data associated with the device to be diagnosed. When a certain abnormal phenomenon occurs in the device to be diagnosed, the target prior probability set is first determined according to the current diagnostic conditions and the prior probability data, and the target likelihood probability set is determined according to the current abnormal phenomenon, the current diagnostic conditions and the likelihood probability data. Then, the target posterior probability set is calculated based on the target prior probability set and the target likelihood probability set. Finally, the fault diagnosis result of the device to be diagnosed is determined based on the target posterior probability set. In the above process, by searching for the target prior probability set and the target likelihood probability set that are adapted to the current diagnostic conditions from the prior probability data and the likelihood probability data, respectively, the accuracy of the calculated target posterior probability set can be improved, and then a more accurate fault diagnosis result can be obtained, thereby shortening the time-consuming troubleshooting of the equipment.

[0108] In summary, the embodiments of the present application provide a quantifiable fault diagnosis method, which can shorten the time spent on equipment fault troubleshooting and formulate a reasonable equipment maintenance plan.

[0109] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0110] A device fault diagnosis method is mainly described above, and a device fault diagnosis apparatus will be described below.

[0111] See also Figure 3 , an equipment fault diagnosis device provided in an embodiment of the present application includes:

[0112] The data acquisition module 301 is used to acquire the prior probability data and likelihood probability data associated with the device to be diagnosed;

[0113] A priori probability determination module 302 is used to determine a target priori probability set according to the current diagnosis condition of the device to be diagnosed and the priori probability data;

[0114] The likelihood probability determination module 303 is used to determine a target likelihood probability set according to the current abnormal phenomenon of the device to be diagnosed, the current diagnostic condition and the likelihood probability data;

[0115] The posterior probability calculation module 304 is used to calculate the target posterior probability set according to the target prior probability set and the target likelihood probability set;

[0116] The fault diagnosis module 305 is used to determine the fault diagnosis result of the device to be diagnosed according to the target posterior probability set.

[0117] In one implementation of the embodiment of the present application, the prior probability data includes a plurality of initial prior probability sets corresponding to different diagnostic conditions; the likelihood probability data includes a plurality of initial likelihood probability sets corresponding to different diagnostic conditions; and the prior probability determination module includes:

[0118] A priori probability selection unit, used to select an initial priori probability set corresponding to the current diagnosis condition from multiple initial priori probability sets as a target priori probability set;

[0119] The likelihood probability determination module includes:

[0120] A first likelihood probability selection unit, used to select an initial likelihood probability set corresponding to a current diagnosis condition from a plurality of initial likelihood probability sets;

[0121] The second likelihood probability selection unit is used to select the probability of occurrence of the current abnormal phenomenon when each fault of the device to be diagnosed occurs from the initial likelihood probability set corresponding to the current diagnosis condition as the target likelihood probability set.

[0122] In another implementation of the embodiment of the present application, the prior probability data includes a plurality of initial prior probability sets corresponding to different diagnostic conditions; the likelihood probability data includes a plurality of initial likelihood probability sets corresponding to different diagnostic conditions; and the prior probability determination module includes:

[0123] A first calculation weight determination unit, used to determine the calculation weights of each of the multiple initial prior probability sets according to the current diagnosis condition;

[0124] A priori probability calculation unit, used to perform weighted sum calculation on multiple initial priori probability sets according to their respective calculation weights to obtain a target priori probability set;

[0125] The likelihood probability determination module includes:

[0126] A second calculation weight determination unit, used to determine the calculation weights of the multiple initial likelihood probability sets according to the current diagnosis condition;

[0127] A likelihood probability calculation unit is used to perform weighted sum calculation on multiple initial likelihood probability sets according to their respective calculation weights to obtain a comprehensive likelihood probability set;

[0128] The third likelihood probability selection unit is used to select the occurrence probability of the current abnormal phenomenon when each fault of the device to be diagnosed occurs from the comprehensive likelihood probability set as the target likelihood probability set.

[0129] In one implementation of the embodiment of the present application, the device fault diagnosis apparatus further includes:

[0130] A probability data updating unit, used to update the prior probability data and the likelihood probability data according to the actual fault result after obtaining the actual fault result of the device to be diagnosed;

[0131] The calculation weight updating unit is used to update the calculation weights of the multiple initial prior probability sets and the calculation weights of the multiple initial likelihood probability sets according to the target posterior probability set and the actual fault result.

[0132] In an implementation of an embodiment of the present application, the number of target prior probability sets, the number of target likelihood probability sets, and the number of target posterior probability sets are all multiple, and each target posterior probability set corresponds to a target prior probability set and a target likelihood probability set respectively; the calculation weight update unit includes:

[0133] A first optimal probability determination subunit, used to determine an optimal posterior probability set that best matches the actual fault result from multiple target posterior probability sets;

[0134] A second optimal probability determination subunit, configured to determine a target priori probability set corresponding to the optimal a posteriori probability set as a maximum priori probability set, and to determine a target likelihood probability set corresponding to the optimal a posteriori probability set as an optimal likelihood probability set;

[0135] The calculation weight increasing subunit is used to increase the calculation weight of the initial prior probability set related to the highest prior probability set among multiple initial prior probability sets, and to increase the calculation weight of the initial likelihood probability set related to the optimal likelihood probability set among multiple initial likelihood probability sets.

[0136] In one implementation of the embodiment of the present application, the fault diagnosis result includes fault troubleshooting sequence information of the device to be diagnosed; the fault diagnosis module includes:

[0137] A posterior probability sorting unit, used to sort the posterior probabilities contained in the target posterior probability set in descending order;

[0138] The troubleshooting information generating unit is used to generate fault troubleshooting sequence information according to the arrangement sequence of each posterior probability.

[0139] In one implementation of the embodiment of the present application, the fault diagnosis result includes fault maintenance information of the device to be diagnosed; the fault diagnosis module includes:

[0140] The maintenance information generating unit is used to compare each posterior probability contained in the target posterior probability set with the probability threshold value, and generate fault maintenance information according to the comparison result.

[0141] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the device fault diagnosis method represented by any of the above embodiments is implemented.

[0142] An embodiment of the present application also provides a computer program product. When the computer program product is run on a medical device, the medical device executes a device fault diagnosis method as represented by any of the above embodiments.

[0143] Figure 4 Schematic diagram of a medical device provided by an embodiment of the present application. Figure 4 As shown, the medical device 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the embodiments of the above-mentioned device fault diagnosis method are implemented, for example Figure 1 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 3 Functions of modules 301 to 305 are shown.

[0144] The computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 42 in the medical device 4.

[0145] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0146] The memory 41 may be an internal storage unit of the medical device 4, such as a hard disk or memory of the medical device 4. The memory 41 may also be an external storage device of the medical device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the medical device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the medical device 4. The memory 41 is used to store the computer program and other programs and data required by the medical device 4. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0147] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0148] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0149] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0150] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0151] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as 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 an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0152] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0153] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0154] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0155] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A device fault diagnosis method, characterized in that: include: Acquiring prior probability data and likelihood probability data associated with the device to be diagnosed; Determining a target priori probability set according to the current diagnostic condition of the device to be diagnosed and the priori probability data; Determining a target likelihood probability set according to the current abnormal phenomenon of the device to be diagnosed, the current diagnostic condition, and the likelihood probability data; Calculating a target posterior probability set according to the target prior probability set and the target likelihood probability set; A fault diagnosis result of the device to be diagnosed is determined according to the target posterior probability set.

2. The method according to claim 1, characterized in that The prior probability data includes a plurality of initial prior probability sets corresponding to different diagnostic conditions; the likelihood probability data includes a plurality of initial likelihood probability sets corresponding to different diagnostic conditions; and the determining of the target prior probability set according to the current diagnostic condition of the device to be diagnosed and the prior probability data includes: Selecting, from the multiple initial prior probability sets, an initial prior probability set corresponding to the current diagnosis condition as the target prior probability set; The determining of a target likelihood probability set according to the current abnormal phenomenon of the device to be diagnosed, the current diagnostic condition and the likelihood probability data includes: Selecting an initial likelihood probability set corresponding to the current diagnosis condition from the multiple initial likelihood probability sets; From the initial likelihood probability set corresponding to the current diagnostic condition, the probability of occurrence of the current abnormal phenomenon when each fault of the device to be diagnosed occurs is selected as the target likelihood probability set.

3. The method according to claim 1, characterized in that The prior probability data includes a plurality of initial prior probability sets corresponding to different diagnostic conditions; the likelihood probability data includes a plurality of initial likelihood probability sets corresponding to different diagnostic conditions; and the determining of the target prior probability set according to the current diagnostic condition of the device to be diagnosed and the prior probability data includes: Determining, according to the current diagnostic condition, a calculation weight of each of the plurality of initial prior probability sets; Performing weighted sum calculation on the multiple initial prior probability sets according to their respective calculation weights to obtain the target prior probability set; The determining of a target likelihood probability set according to the current abnormal phenomenon of the device to be diagnosed, the current diagnostic condition and the likelihood probability data includes: Determining, according to the current diagnostic condition, a calculation weight of each of the plurality of initial likelihood probability sets; Performing weighted sum calculation on the multiple initial likelihood probability sets according to their respective calculation weights to obtain a comprehensive likelihood probability set; From the comprehensive likelihood probability set, the probability of occurrence of the current abnormal phenomenon when each fault of the device to be diagnosed occurs is selected as the target likelihood probability set.

4. The method according to claim 3, characterized in that After calculating the target posterior probability set according to the target prior probability set and the target likelihood probability set, the method further includes: After obtaining the actual fault result of the device to be diagnosed, updating the prior probability data and the likelihood probability data according to the actual fault result; According to the target posterior probability set and the actual fault result, the calculation weights of the multiple initial prior probability sets and the calculation weights of the multiple initial likelihood probability sets are updated.

5. The method according to claim 4, characterized in that The number of the target prior probability sets, the number of the target likelihood probability sets, and the number of the target posterior probability sets are all multiple, and each of the target posterior probability sets corresponds to one target prior probability set and one target likelihood probability set respectively; updating the respective calculation weights of the multiple initial prior probability sets and the respective calculation weights of the multiple initial likelihood probability sets according to the target posterior probability set and the actual fault result, comprises: Determining an optimal posterior probability set that best matches the actual fault result from the multiple target posterior probability sets; Determining the target a priori probability set corresponding to the optimal a priori probability set as the highest a priori probability set, and determining the target likelihood probability set corresponding to the optimal a priori probability set as the optimal likelihood probability set; The calculation weight of the initial prior probability set associated with the highest prior probability set among the multiple initial prior probability sets is increased, and the calculation weight of the initial likelihood probability set associated with the optimal likelihood probability set among the multiple initial likelihood probability sets is increased.

6. The method according to any one of claims 1 to 5, characterized in that: The fault diagnosis result includes the fault troubleshooting sequence information of the device to be diagnosed; and determining the fault diagnosis result of the device to be diagnosed according to the target posterior probability set includes: Arrange the posterior probabilities contained in the target posterior probability set in order from large to small; The troubleshooting sequence information is generated according to the arrangement order of the respective posterior probabilities.

7. The method according to any one of claims 1 to 5, characterized in that: The fault diagnosis result includes the fault maintenance information of the device to be diagnosed; and determining the fault diagnosis result of the device to be diagnosed according to the target posterior probability set includes: Each posterior probability included in the target posterior probability set is compared with a probability threshold value, and the fault maintenance information is generated according to the comparison result.

8. A device for diagnosing equipment faults, characterized in that: include: A data acquisition module, used to acquire prior probability data and likelihood probability data associated with the device to be diagnosed; A priori probability determination module, used to determine a target priori probability set according to the current diagnosis condition of the device to be diagnosed and the priori probability data; A likelihood probability determination module, used to determine a target likelihood probability set according to the current abnormal phenomenon of the device to be diagnosed, the current diagnostic condition and the likelihood probability data; A posterior probability calculation module, used to calculate a target posterior probability set based on the target prior probability set and the target likelihood probability set; The fault diagnosis module is used to determine the fault diagnosis result of the device to be diagnosed according to the target posterior probability set.

9. A medical device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the device fault diagnosis method according to any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that When the computer program product is run on a medical device, the medical device is enabled to execute the device fault diagnosis method according to any one of claims 1 to 7.

Images