Intelligent fault diagnosis device and method with BIT capability

Abstract

The invention discloses an intelligent fault diagnosis device and method with BIT capability, and the method comprises the steps: enabling one or more tested devices to be connected to the intelligent fault diagnosis device, and enabling the one or more tested devices to be a field replaceable unit (LRU); a plurality of sensors are arranged at internal and external interfaces of each LRU, and collected data are transmitted to a central processing unit; analyzing the collected data by adopting a self-adaptive algorithm, and outputting a fault risk score A of the current system state; based on the fault risk score A, parameters of a fault prediction model lambda (t) are adjusted; and based on the fault risk score A and the fault prediction model lambda (t), obtaining an overall fault diagnosis index FD, and generating a fault diagnosis report. According to the invention, the fault diagnosis accuracy can be improved, the fault prediction capability can be enhanced, complex working conditions can be adapted, the maintenance cost and downtime can be reduced, and a real-time monitoring and feedback mechanism, expandability and compatibility and data-driven intelligent decision support can be realized.

Description

Technical Field

[0001] The present invention belongs to the field of computer system engineering, and particularly relates to an intelligent fault diagnosis device and method with BIT capabilities. Background Art

[0002] In modern aerospace, military, and high-tech fields, device monitoring and fault diagnosis based on Built-In Test (BIT) technology have been widely applied. The BIT system can monitor the operating status of a device in real time, identify potential faults, and issue alarms before a fault occurs by integrating sensors and self-test programs inside the device. The goal of this technology is to ensure the reliability and safety of the device, thereby reducing maintenance costs and downtime. However, the current BIT system still faces multiple technical challenges in practical applications, which limit its effectiveness and accuracy in fault diagnosis.

[0003] First of all, traditional BIT technology often relies on static thresholds to judge the health status of a device. This method may be effective in simple cases, but for complex and dynamically changing systems, static thresholds are prone to false alarms or missed alarms. For example, when a device operates under high load or extreme environments, its monitored parameters (such as temperature, current, and voltage) may naturally fluctuate rather than being caused by a fault. In this case, the judgment based on static thresholds may misjudge as a fault, resulting in unnecessary maintenance and repairs.

[0004] Secondly, the BIT system also has limitations in data processing and analysis capabilities. With the increase in the number of sensors and the accumulation of monitoring data, how to effectively process and analyze this data has become a key issue. Traditional fault diagnosis methods usually cannot make full use of real-time data for dynamic analysis, resulting in inaccurate diagnostic results. In addition, the lack of flexible data processing algorithms makes the system's response ability to sudden faults insufficient and unable to adjust the monitoring strategy in a timely manner.

[0005] Furthermore, the current BIT system often lacks intelligent fault prediction capabilities. Although some systems have fault detection functions, the prediction of potential faults is still insufficient. The probability of a fault occurring and the influencing factors are usually complex and variable. It is difficult to adapt to the changes in the device under different operating conditions by relying solely on historical fault records for prediction. Therefore, how to accurately estimate the fault occurrence rate and make dynamic adjustments based on the current device status is an urgent problem to be solved by the BIT system.

[0006] In addition, the fault diagnosis ability of the existing BIT system is often limited to single-parameter monitoring, lacking systematicness and comprehensiveness. For a complex system, the abnormality of a single parameter cannot fully reflect the health status of the device. At this time, how to comprehensively evaluate the overall health status of the device through multi-parameter fusion analysis has become an important direction for improving the accuracy of fault diagnosis. Summary of the Invention

[0007] In view of the defects existing in the above-mentioned prior art, the present invention provides an intelligent fault diagnosis method with BIT capability, including the following steps:

[0008] Step S101: Connect one or more devices under test to the intelligent fault diagnosis device, and the one or more devices under test are Line Replaceable Units (LRUs);

[0009] Step S103: Set a plurality of sensors inside each LRU and at its external interfaces, and transmit the collected data to the central processing unit of the intelligent fault diagnosis device;

[0010] Step S105: The central processing unit analyzes the collected data using an adaptive algorithm and outputs a fault risk score A of the current system state;

[0011] Step S107: Adjust the parameters of the fault prediction model λ(t) based on the fault risk score A;

[0012] Step S109: Obtain an overall fault diagnosis index F based on the fault risk score A and the fault prediction model λ(t) D and generate a fault diagnosis report.

[0013] Among them, in step S101, the test circuit is directly embedded in the LRU.

[0014] Among them, the sensors include current sensors, voltage sensors, and temperature sensors.

[0015] Among them, in step S105, the following formula is used to calculate the fault risk score A of the current system state:

[0016] where M is the number of samples, w j is the weight of the jth sample, and f j (X) is the prediction function of the jth sample based on the input X.

[0017] Among them, in step S107, the following formula is used to obtain the failure rate λ(t) of the fault prediction model,

[0018] λ(t) = (α + k·A)·e -(β-m·A)t+γ, where α represents the initial failure rate; k is an adjustment coefficient used to control the influence degree of the output A of the adaptive algorithm on the initial failure rate α; β is a decay factor representing the decline rate of the failure rate over time; m is an adjustment coefficient used to control the influence degree of the output A of the adaptive algorithm on the decay factor β; γ is the minimum failure rate, indicating that in any case, the failure probability of the system will not be lower than this value.

[0019] Among them, in the step S109, the following formula is used to obtain the overall fault diagnosis index F D ,

[0020] Among them, S i (t) is the sensor data of the i-th circuit at time t; D(t) represents the total monitoring data at time t; N represents the number of devices under test; T represents the total monitoring time period, indicating the duration of data acquisition; λ(t) represents the failure rate; w i represents the importance weight of the i-th device; γ(D(t)) is a normalization function used to handle the influence of the total monitoring data D(t); F D ∈[0, 1], 0 indicates the possibility of no failure occurrence, 1 indicates the certainty of failure occurrence, and the system is in a complete failure state.

[0021] Among them, the fault diagnosis report in the step S109 includes the fault type, fault location, and recommended handling measures for subsequent maintenance

[0022] Among them, the fault diagnosis report can display the fault information in real time and provide query and recording functions through the display interface of the display screen of the intelligent fault diagnosis device for the quick response of the operator.

[0023] Among them, the intelligent fault diagnosis device isolates the detected fault information to the field replaceable unit LRU for subsequent maintenance and replacement.

[0024] The present invention also proposes an intelligent fault diagnosis device with BIT capability, including

[0025] A functional chassis for connecting one or more devices under test to the intelligent fault diagnosis device, and the one or more devices under test are field replaceable units LRU;

[0026] Sensors are used to be arranged inside each LRU and at the external interfaces, and transmit the collected data to the central processing unit of the intelligent fault diagnosis device;

[0027] The central processing unit is used to analyze the collected data by using an adaptive algorithm and output a fault risk score A of the current system state;

[0028] The central processing unit is also used to adjust the parameters of the fault prediction model λ(t) based on the fault risk score A; and to obtain the overall fault diagnosis index FD and generate a fault diagnosis report based on the fault risk score A and the fault prediction model λ(t).

[0029] A display screen, which is used to provide a display interface for querying and displaying;

[0030] A UPS unit, which is used to provide an uninterruptible power supply.

[0031] Compared with the prior art, the present invention has the following advantages:

[0032] By introducing an adaptive algorithm, the present invention can analyze and adjust the fault risk score A in real time, reflecting the real-time health status of the device. Compared with the traditional static threshold method, this dynamic adjustment mechanism significantly improves the accuracy of fault diagnosis and reduces the occurrence of false alarms and missed alarms.

[0033] By using the output of the adaptive algorithm as the input of the fault prediction model, the parameters of the fault occurrence rate (such as the initial fault occurrence rate α and the decay factor β) can be dynamically adjusted. This method makes the prediction of the fault occurrence probability more accurate, can identify potential faults in advance, and thus provides a reliable basis for maintenance decisions.

[0034] Traditional fault diagnosis methods often have difficulty adapting to the changes of devices under complex working conditions. The present invention can comprehensively evaluate the overall health status of the device by real-time monitoring of various operating parameters (such as temperature, voltage and current) and combining with an adaptive algorithm. This method of multi-parameter fusion analysis effectively improves the adaptability of the system and ensures fault identification and prediction under different operating conditions.

[0035] Through accurate fault prediction, enterprises can achieve preventive maintenance, avoiding unnecessary repairs and shutdowns. This not only reduces the maintenance cost, but also improves the operating efficiency of the device, extends the service life of the device, and ensures the continuity and stability of production activities.

[0036] It can dynamically adjust the fault diagnosis strategy according to the operating state of the device and environmental changes. This flexibility enables the system to quickly respond to sudden faults and improves the robustness and reliability of the overall system.

[0037] It has good scalability and can adapt to different types and scales of devices. Whether in the aerospace, military or other high-tech fields, it can be customized and applied according to specific requirements, enhancing the compatibility and flexibility of the system.

[0038] Through in-depth fusion analysis of historical data and real-time data, the present invention can provide data-driven intelligent decision-making support for equipment management personnel. This data-based decision-making mechanism can improve the scientificity and effectiveness of maintenance strategies and help enterprises optimize resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] By referring to the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present disclosure will become readily understood. In the drawings, several embodiments of the present disclosure are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0040] Figure 1 is a flowchart showing an intelligent fault diagnosis method with BIT capability according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0042] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the", and "said" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. "Plurality" generally includes at least two.

[0043] It should be understood that although the terms first, second, third, etc. may be used in the embodiments of the present invention to describe..., these... should not be limited to these terms. These terms are only used to distinguish.... For example, without departing from the scope of the embodiments of the present invention, the first... may also be referred to as the second..., and similarly, the second... may also be referred to as the first....

[0044] It should be understood that the term " / and" used herein is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after.

[0045] Depending on the context, as used herein, the terms "if" and "when" may be interpreted as "when", "while", "in response to determining", or "in response to detecting". Similarly, depending on the context, the phrases "if determined" or "if detecting (stated condition or event)" may be interpreted as "when determined", "in response to determining", "when detecting (stated condition or event)", or "in response to detecting (stated condition or event)".

[0046] It should also be noted that the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the commodity or device comprising said element.

[0047] The optional embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0048] BIT (Built-In Test), also known as built-in test, refers to integrating the test function into the device so that the device can perform self-test and fault diagnosis autonomously. The observability of BIT means that when a fault occurs, the system can effectively monitor, identify, and report fault information to ensure that the fault can be located to a specific functional unit (LRU, Line Replaceable Unit).

[0049] Embodiment 1

[0050] As Figure 1 shown, the present invention discloses an intelligent fault diagnosis method with BIT capability, including the following steps:

[0051] Step S101: Connect one or more devices to be tested to the intelligent fault diagnosis device, and the one or more devices to be tested are line replaceable units (LRUs) on-site.

[0052] Step S103: Set a plurality of sensors inside each LRU and at the external interfaces, and transmit the collected data to the central processing unit of the intelligent fault diagnosis device.

[0053] Step S105: The central processing unit analyzes the collected data using an adaptive algorithm and outputs a fault risk score A of the current system state.

[0054] Step S107: Based on the fault risk score A, adjust the parameters of the fault prediction model λ(t).

[0055] Step S109: Based on the failure risk score A and the failure prediction model λ(t), obtain the overall failure diagnosis index F D , and generate a failure diagnosis report.

[0056] Embodiment 2:

[0057] An intelligent failure diagnosis method with BIT ability proposed by the present invention includes the following steps:

[0058] Step S101: Connect one or more devices under test to the intelligent failure diagnosis device, and the one or more devices under test are Line Replaceable Units (LRUs);

[0059] Step S103: Set a plurality of sensors inside each LRU and at the external interfaces, and transmit the collected data to the central processing unit of the intelligent failure diagnosis device;

[0060] Step S105: The central processing unit analyzes the collected data using an adaptive algorithm and outputs the failure risk score A of the current system state;

[0061] Step S107: Based on the failure risk score A, adjust the parameters of the failure prediction model λ(t);

[0062] Step S109: Based on the failure risk score A and the failure prediction model λ(t), obtain the overall failure diagnosis index F D , and generate a failure diagnosis report.

[0063] Among them, in step S101, the test circuit is directly embedded in the LRU.

[0064] Among them, the sensors include current sensors, voltage sensors, and temperature sensors.

[0065] Among them, in step S105, the following formula is used to calculate the failure risk score A of the current system state:

[0066] Among them, M is the number of samples, w j is the weight of the jth sample, and f j (X) is the prediction function of the jth sample based on the input X.

[0067] The value of A can represent the current failure risk degree of the system. The higher this score, the greater the possibility of failure. Through this score, the system can determine whether immediate maintenance or replacement measures are required.

[0068] The function f j (X) is a feature function based on the input X. Taking three sensors (temperature T, voltage V, and current I) as an example, the feature function f is definedj (X).

[0069] Assume that a feature function will be defined for each sensor, and linear combinations and non - linear terms are used to reflect the influence of the sensor. It can be expressed as:

[0070]

[0071] Then the final f(x) is expressed as:

[0072] where the parameters (a 1 , a 2 , a 3 , b 1 , b 2 , b 3 ) of these functions can be trained and optimized according to historical data to improve the accuracy of the model.

[0073] Among them, in step S107, the following formula is used to obtain the failure incidence rate λ(t) of the failure prediction model, which represents the failure probability at time t. It reflects the possibility of the system failing at a specific time point.

[0074] λ(t)=(α + k·A)·e -(β-m·A)t +γ, where α represents the initial failure incidence rate, which represents the basic failure incidence rate of the system when there are no other influencing factors. It is usually obtained through historical data analysis. Specifically, it can be calculated by counting the number of failures in the past fault records per unit time; k represents the adjustment coefficient, which is used to control the influence degree of the adaptive algorithm output A on the initial failure incidence rate α. It can be determined through experiments or optimization algorithms and is usually adjusted based on historical fault data to ensure the accuracy of the model in different situations; β is the attenuation factor, which represents the decline rate of the failure incidence rate over time. A higher β value means that the failure incidence rate drops rapidly. It can be obtained by fitting historical fault data, usually using regression analysis or maximum likelihood estimation methods for fitting; m is the adjustment coefficient, which is used to control the influence degree of the adaptive algorithm output A on the attenuation factor β. Similar to k, it can be determined by analyzing historical data and experimental results to ensure the reasonable response of the system under different conditions; γ is the minimum failure incidence rate, which represents that in any case, the failure probability of the system will not be lower than this value. It can be regarded as the benchmark failure rate of the system. It is usually obtained by analyzing historical data, calculating the failure incidence rate in the optimal state, or determined through theoretical derivation.

[0075] For example, collect the historical failure data of the system, including the time, type, and frequency of failures. Through statistical analysis, calculate the average number of failures per unit time to obtain α. Through experiments, observe the influence of different A values on the failure rate, and use optimization algorithms (such as grid search or genetic algorithms) to determine the optimal values of the adjustment coefficients k and m. Through regression analysis of historical data, fit the value of β, usually using statistical software or self-written programs for analysis. Calculate the lowest failure probability under the best conditions to obtain γ.

[0076] Among them, in step S109, the following formula is used to obtain the overall fault diagnosis index F D ,

[0077] Among them, S i (t) is the sensor data of the i-th circuit at time t; D(t) represents the total monitoring data at time t; N represents the number of devices under test; T represents the total monitoring time period, indicating the duration of data acquisition; λ(t) represents the failure rate; w i represents the importance weight of the i-th device; γ(D(t)) represents a normalization function used to handle the influence of the total monitoring data D(t); F D ∈[0, 1], 0 indicates the possibility of no failure, 1 indicates the certainty of failure, and the system is in a complete failure state.

[0078] Among them, the fault diagnosis report in step S109 includes the fault type, fault location, and recommended handling measures for subsequent maintenance

[0079] Among them, the fault diagnosis report can display the fault information in real time and provide query and recording functions through the display interface of the display screen of the intelligent fault diagnosis device for the quick response of the operator.

[0080] Design a user-friendly interface that can clearly display the fault information, diagnosis results, and recommended handling measures to help the operator take action quickly. It should have the functions of recording and querying fault information for maintenance personnel to analyze historical fault data and optimize subsequent testing and maintenance strategies.

[0081] Among them, the intelligent fault diagnosis device isolates the detected fault information to the on-site replaceable unit LRU for subsequent maintenance and replacement.

[0082] Embodiment III.

[0083] The present invention also proposes an intelligent fault diagnosis device with BIT capability, including:

[0084] A functional chassis for connecting one or more devices under test to an intelligent fault diagnosis device, where the one or more devices under test are line replaceable units (LRUs).

[0085] Sensors for being disposed inside each LRU and at external interfaces, and for transmitting the collected data to a central processing unit of the intelligent fault diagnosis device.

[0086] A central processing unit for analyzing the collected data using an adaptive algorithm and outputting a fault risk score A of the current system state.

[0087] The central processing unit is further configured to adjust parameters of a fault prediction model λ(t) based on the fault risk score A; and to obtain an overall fault diagnosis index FD and generate a fault diagnosis report based on the fault risk score A and the fault prediction model λ(t).

[0088] A display screen for providing a display interface for querying and displaying.

[0089] A UPS unit for providing an uninterruptible power supply.

[0090] Embodiment 4

[0091] The present disclosure provides a non - volatile computer storage medium storing computer - executable instructions that can execute the method steps as described in the above embodiments.

[0092] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which computer-readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and this computer-readable signal medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0093] The above-mentioned computer-readable medium can be included in the above-mentioned electronic device; or it can exist separately and not be assembled into the electronic device.

[0094] The computer program code for performing the operations of the present disclosure can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages - such as Java, Smalltalk, C++, and also include 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, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or, it can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0095] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that, in some alternative implementations, the functions denoted in the blocks may occur in a different order than that denoted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0096] The units involved in the embodiments described in the present disclosure can be implemented in software or in hardware. Among them, the name of the unit does not, in some cases, constitute a limitation on the unit itself.

[0097] The preferred embodiments of the present invention are described above to make the spirit of the present invention clearer and easier to understand, and are not intended to limit the present invention. Any modifications, substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection defined by the claims appended to the present invention.

Claims

1. An intelligent fault diagnosis method with BIT capability, characterized in that: The following steps are involved: Step S101, connecting one or more tested devices to an intelligent fault diagnosis device, wherein the one or more tested devices are field replaceable units (LRUs); Step S103, multiple sensors are arranged inside each LRU and at the external interface, and the collected data are transmitted to the central processing unit of the intelligent fault diagnosis device; Step S105, the central processing unit uses an adaptive algorithm to analyze the collected data and outputs a fault risk score A of the current system state; Step S107: adjusting the parameters of the fault prediction model λ(t) based on the fault risk score A; Step S109: Based on the fault risk score A and the fault prediction model λ(t), obtain the overall fault diagnosis index F D , generate a fault diagnosis report.

2. The method according to claim 1, characterized in that: In the step S101 , the test circuit is directly embedded in the LRU.

3. The method according to claim 1, characterized in that: The sensors include a current sensor, a voltage sensor and a temperature sensor.

4. The method according to claim 1, characterized in that: In step S105, the following formula is used to calculate the fault risk score A of the current system state: Where M is the number of samples, w j is the weight of the jth sample, f i (X) is the prediction function based on the j-th sample of input X.

5. The method according to claim 1, characterized in that: In step S107, the following formula is used to obtain the failure occurrence rate λ(t) of the failure prediction model: λ(t)=(α+k·A)·e -(β-m·A)t+γ , where α represents the initial fault rate; k represents the adjustment coefficient, which is used to control the influence of the adaptive algorithm output A on the initial fault rate α; β is the attenuation factor, which represents the rate of decrease of the fault rate over time; m is the adjustment coefficient, which is used to control the influence of the adaptive algorithm output A on the attenuation factor β; γ is the minimum fault rate, which means that under any circumstances, the probability of failure of the system will not be lower than this value.

6. The method according to claim 5, characterized in that In step S109, the overall fault diagnosis index F is obtained by using the following formula: D , Among them, S i (t) is the sensor data of the ith circuit at time t; D(t) represents the total monitoring data at time t; N represents the number of devices under test; T represents the total monitoring time period, which represents the duration of data collection; λ(t) represents the fault occurrence rate; w i represents the importance weight of the i-th device; γ(D(t)) represents the normalization function, which is used to process the influence of the total monitoring data D(t); F D ∈[0, 1], 0 means there is no possibility of failure, 1 means the certainty of failure, and the system is in a state of complete failure.

7. The method according to claim 1, characterized in that: The fault diagnosis report in step S109 includes the fault type, fault location and suggested treatment measures to facilitate subsequent maintenance.

8. The method according to claims 1 to 7, characterized in that: The fault diagnosis report can display fault information in real time, and provide query and recording functions through the display interface of the display screen of the intelligent fault diagnosis device to facilitate rapid response by operators.

9. The method according to claims 1 to 7, characterized in that: The intelligent fault diagnosis device isolates the detected fault information to the field replaceable unit LRU to facilitate subsequent maintenance and replacement.

10. An intelligent fault diagnosis device with BIT capability, comprising: A function plug-in box, which is used to connect one or more tested devices to the intelligent fault diagnosis device, wherein the one or more tested devices are field replaceable units (LRUs); A sensor, which is arranged inside each LRU and at an external interface, and transmits the collected data to a central processing unit of the intelligent fault diagnosis device; A central processing unit, which is used to analyze the collected data using an adaptive algorithm and output a fault risk score A of the current system state; The central processing unit is further used to adjust the parameters of the fault prediction model λ(t) based on the fault risk score A; and to obtain the overall fault diagnosis index FD based on the fault risk score A and the fault prediction model λ(t), and to generate a fault diagnosis report; A display screen, which is used to provide a display interface for query and display; UPS unit, which is used to provide uninterruptible power supply.

Images