Fault detection method, fault prediction method, and electronic device

Abstract

An embodiment of the present invention discloses a fault detection method, a fault detection system, and an electronic device. The fault detection system includes multiple fault tree models and a mapping relationship between the fault tree models and seasons. The fault tree model includes an initial fault point and multiple branch fault points sorted by fault causal relationships. The method includes: obtaining the current season; when a fault is detected at the initial fault point, selecting a target fault tree model from the multiple fault tree models based on the mapping relationship and the current season; detecting the multiple branch fault points in the target fault tree model according to the fault causal relationship, and outputting a fault detection result, wherein the fault detection result includes the branch fault point where the fault occurs.

Description

Technical Field

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

[0002] With the advancement of communications technology, equipment integration has increased, enabling individual devices to possess robust data processing, exchange, and transmission capabilities. However, this has led to increased power consumption and heat generation, posing new challenges to the power and environmental monitoring systems in the equipment room. For example, during equipment operation, failures such as excessive heat in the equipment room can easily lead to reduced semiconductor device and battery life, increased dielectric loss in capacitors, accelerated aging of insulation materials, and potentially cause some equipment to reboot or freeze, compromising network security. Given the defining characteristics of 5G technology: high bandwidth, high reliability, low latency, and the ability to connect massive numbers of devices, a suitable equipment room temperature provides a suitable operating environment for 5G equipment, effectively ensuring its high reliability.

[0003] In the existing technology, when a high temperature is detected in the computer room, the computer room will issue a high temperature alarm, requiring manual on-site inspection and judgment and troubleshooting based on personal experience. However, manual on-site handling of abnormal conditions such as high temperature in the computer room relies heavily on personal experience, and the methods of diagnosing faults vary. Improper operation by personnel may lead to more serious consequences. In addition, on-site handling lacks theoretical support and is slow to handle. In addition, the changes in the seasons often affect the changes in computer room temperature, and the causes of faults such as high temperature in the computer room are different. This increases the difficulty of manual diagnosis of the root cause of the fault, making it impossible to conduct a systematic and targeted analysis of faults such as high temperature in the computer room, and thus unable to provide theoretical support for fault handling. Summary of the Invention

[0004] In view of this, an embodiment of the present invention provides a fault detection method, a fault prediction method, and an electronic device, which detects the root cause of the fault according to seasonal classification and the corresponding fault tree model, provides theoretical support for fault handling, and improves fault handling efficiency.

[0005] In a first aspect, an embodiment of the present invention provides a fault detection method applied to a fault detection system, wherein the fault detection system includes multiple fault tree models and mapping relationships between the fault tree models and seasons, wherein the fault tree models include an initial fault point and multiple branch fault points sorted by fault causal relationships. The method includes:

[0006] Get the current season;

[0007] When a fault is detected at the initial fault point, a target fault tree model is selected from the plurality of fault tree models based on the mapping relationship and the current season;

[0008] According to the fault causal relationship, multiple branch fault points in the target fault tree model are detected, and a fault detection result is output, wherein the fault detection result includes the branch fault point where the fault occurs.

[0009] In one possible implementation, the fault causal relationship includes multiple causal relationships sorted by priority, and detecting multiple branch fault points in the target fault tree model according to the fault causal relationship and outputting a fault detection result includes:

[0010] Taking the initial fault point as a causal relationship input, detecting the plurality of branch fault points of the first priority causal relationship to obtain the branch fault point where the fault occurs in the first priority causal relationship;

[0011] Taking the branch fault point where a fault occurs in the previous priority causal relationship as the causal relationship input, detecting multiple branch fault points of the next priority causal relationship to obtain the branch fault point where a fault occurs in the next priority causal relationship;

[0012] Determine whether the branch fault point where the fault occurs is the root cause of the fault, and output a fault detection result based on the determination result.

[0013] In one possible implementation, the multiple branch fault points include a computer room fault event and a first mains power supply, a second mains power supply, an automatic transfer switch, and a generator in a next-priority causal relationship with the computer room fault event. The branch fault point in the previous priority causal relationship where the fault occurs is used as a causal relationship input, and the multiple branch fault points in the next priority causal relationship are detected to obtain the branch fault point in the next priority causal relationship where the fault occurs, including:

[0014] If a power outage in the equipment room is detected, testing the first mains power supply, the second mains power supply, the automatic transfer switch, and the generator;

[0015] If it is detected that both the first mains power supply and the second mains power supply are out of power and the automatic transfer switch fails to switch, then the first mains power supply, the second mains power supply and the automatic transfer switch are faulty;

[0016] If it is detected that both the first mains power supply and the second mains power supply are out of power and the generator power supply fails, the first mains power supply, the second mains power supply and the generator fail.

[0017] In one possible implementation, obtaining the current season includes:

[0018] Get the collected current time and current device power;

[0019] A current season is determined based on the current time and the current device power.

[0020] In one possible implementation, the plurality of branch failure points include a first failure point and a plurality of second failure points in a priority causal relationship with the first failure point, and the method further includes:

[0021] When it is detected that the first fault point has not failed, detecting a plurality of the second fault points;

[0022] If a fault is detected at any of the second fault points, a fault change trend is output based on the second fault points that have not failed, and the fault change trend is used to predict the change trend of the first fault point when a fault occurs.

[0023] In one possible implementation, the fault change trend includes a first change trend, a second change trend, and a third change trend; the first fault point includes a power supply event in a computer room; the plurality of second fault points include a first mains power supply, a second mains power supply, an automatic transfer switch, and a generator; and outputting the fault change trend based on the second fault point that has not failed includes:

[0024] If the first mains fails, outputting the first change trend based on the second mains, the automatic transfer switch, and the generator, wherein the first change trend is used to indicate that if the second mains, the automatic transfer switch, and / or the generator fail, the computer room will be out of power;

[0025] If the second mains fails, outputting the second change trend based on the first mains, the automatic transfer switch, and the generator, wherein the second change trend is used to indicate that if the first mains, the automatic transfer switch, and / or the generator fail, the computer room will be out of power;

[0026] If the automatic transfer switch and / or the generator fails, the third change trend is output based on the first mains power and the second mains power, and the third change trend is used to indicate that if the first mains power and the second mains power fail, the computer room will be out of power.

[0027] In a second aspect, the present application further provides a fault prediction method, wherein the fault detection system includes a fault tree model, the fault tree model includes an initial fault point and multiple branch fault points sorted by fault causal relationship, the multiple branch fault points include a first fault point and multiple second fault points in a lower priority causal relationship than the first fault point, the method comprising:

[0028] When it is detected that the first fault point has not failed, detecting a plurality of the second fault points;

[0029] If a fault is detected at any of the second fault points, a fault change trend is output based on the second fault points that have not failed, and the fault change trend is used to predict the change trend of the first fault point when a fault occurs.

[0030] In a third aspect, the present application provides a fault detection system, comprising multiple fault tree models and a mapping relationship between the fault tree models and seasons, wherein the fault tree model comprises an initial fault point and multiple branch fault points sorted by fault causal relationship, and the system further comprises:

[0031] Collection module, used to obtain the current season;

[0032] a selection module, configured to select a target fault tree model from the plurality of fault tree models based on the mapping relationship and the current season when a fault occurs at the initial fault point;

[0033] An output module is used to detect the multiple branch fault points in the target fault tree model according to the fault causal relationship, and output a fault detection result, wherein the fault detection result includes the branch fault point where the fault occurs.

[0034] In a fourth aspect, an embodiment of the present invention provides an electronic device, including: a memory and a processor:

[0035] The memory is used to store computer programs;

[0036] The processor is configured to execute the computer program stored in the memory so as to enable the electronic device to perform the method according to the first aspect or the second aspect.

[0037] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, comprising a program or instructions. When the program or instructions are run on a computer, the method described in the first aspect or the second aspect is executed.

[0038] Compared with the existing technology, this technical solution has at least the following beneficial effects:

[0039] The fault detection method, fault detection system, and electronic device disclosed in the embodiments of the present invention can detect the root cause of a fault according to seasonal classification and the corresponding fault tree model, provide theoretical support for fault handling, and improve fault handling efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 is a schematic diagram of a fault detection method provided by Example 1 of the present invention;

[0042] Figure 2 1 is a flow chart of a fault detection method provided in Example 1 of the present invention;

[0043] Figure 3 This is a schematic diagram of the sequence of occurrence of fault events that cause high temperature in a computer room in spring in the fault detection method provided by Example 1 of the present invention;

[0044] Figure 4 This is a schematic diagram of the sequence of occurrence of fault events that cause high temperature in a computer room in summer in the fault detection method provided by Example 1 of the present invention;

[0045] Figure 5 This is a schematic diagram of the sequence of occurrence of fault events that cause high temperature in a computer room in autumn in the fault detection method provided by Example 1 of the present invention;

[0046] Figure 6 This is a schematic diagram of the sequence of occurrence of fault events that cause high temperature in a computer room in winter in the fault detection method provided by Example 1 of the present invention;

[0047] Figure 7 Schematic diagram of the Markov state transition model in the fault detection method provided in Example 1 of the present invention;

[0048] Figure 8 is a schematic diagram of a fault prediction method provided by Example 2 of the present invention;

[0049] Figure 9 It is a structural diagram of the fault detection system provided by Example 3 of the present invention.

[0050] Reference numerals:

[0051] 110 - acquisition module; 120 - selection module; 130 - output module. DETAILED DESCRIPTION

[0052] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0053] It should be understood that the embodiments described are only a portion of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative work are within the scope of protection of the present invention.

[0054] The fault detection methods in related technologies are mainly as follows:

[0055] Related technology 1 relies on manual experience to determine the root cause of faults such as high temperature in the computer room, which is not only inefficient but also poses a safety hazard.

[0056] Related technology 2 is to uniformly detect all fault points that may cause faults such as high temperature in the computer room, and then analyze the root cause of the fault. However, since there are many causes of faults such as high temperature in the computer room, the system is under great pressure, resulting in low fault handling efficiency. Moreover, the cause of the fault may be different in different seasons, and there is a phenomenon of incorrect or missed judgment of the root cause of the fault.

[0057] To this end, the present application provides a fault detection method, a fault prediction method and an electronic device, which detects the root cause of the fault (i.e., the root cause of the fault) according to seasonal classification and the corresponding fault tree model, provides theoretical support for fault handling, and improves fault handling efficiency.

[0058] Example 1

[0059] Embodiment 1 of the present invention proposes a fault detection method, such as Figure 1 and Figure 2 As shown, the method is applied to a fault detection system, which may include multiple fault tree models and a mapping relationship between the fault tree models and seasons. The fault tree model includes an initial fault point and multiple branch fault points sorted by fault causality, wherein the initial fault point is used to represent the fault event of the fault root cause to be analyzed, the branch fault point is used to represent the fault event that causes the initial fault point to fail, and the fault causality is used to represent the order of occurrence of the fault events that cause the initial fault point to fail.

[0060] Taking the initial fault point as an example of a computer room temperature event, if the computer room temperature is detected to be higher than the temperature threshold, it means that a fault has occurred at the initial fault point. Each branch fault point can be used to represent the fault event that caused the high temperature in the computer room, and the above fault causal relationship is determined according to the order in which the faults occurred.

[0061] Therefore, according to the order of occurrence of fault events that cause high temperature in the computer room, the fault causal relationship may include multiple causal relationships sorted by priority, such as a first priority causal relationship, a second priority causal relationship, a third priority causal relationship... and a last priority causal relationship, wherein the first priority causal relationship is used to represent one or more first priority fault events that directly cause high temperature in the computer room, and the first priority fault event is used as the input of the second priority causal relationship, and the second priority causal relationship is used to represent one or more second priority fault events that directly cause the first priority fault event to fail,..., and so on. The last priority causal relationship is used to represent one or more final priority fault events that directly cause the previous priority fault event to fail.

[0062] In this embodiment, if a fault event does not have a next priority causal relationship, the fault event can be considered as a root cause fault event (used to indicate the root cause of the fault), and each final priority fault event in the last priority causal relationship is a root cause fault event.

[0063] Taking into account the influence of seasonal factors, multiple fault tree models are established by season based on the fault events that cause high temperature in the computer room and the order of occurrence of the fault events. For example, the multiple fault tree models include a first fault tree model, a second fault tree model, a third fault tree model, and a fourth fault tree model. The mapping relationship between each fault tree model and the season may include: the first fault tree model corresponds to spring, the second fault tree model corresponds to summer, the third fault tree model corresponds to autumn, and the fourth fault tree model corresponds to winter.

[0064] Figures 3 to 6 Schematic diagram of the sequence of fault events that lead to high temperature in the computer room in spring, summer, autumn and winter, respectively, where rectangular boxes represent fault events that are not the root cause of the fault, and circular boxes represent fault events that are the root cause of the fault. Taking spring as an example, the sequence of fault events that lead to high temperature in the computer room may include, but is not limited to, strong winds in spring, which can easily cause poles to fall and break, or lines to fall off, causing the mains power (such as the first mains power and the second mains power) to be cut off, resulting in the air conditioner being unable to start, thereby causing the temperature in the computer room to rise (i.e., high temperature in the computer room). Alternatively, the temperature in spring is lower, but the density of cabinets is high. If they are not placed properly, it will lead to poor ventilation and heat accumulation, which can also cause the temperature in the computer room to rise. After the power outage in the computer room, the communication equipment continues to work due to the continuous power supply of the battery, but all air conditioners will stop running and the temperature in the computer room will rise rapidly.

[0065] Considering that the computer room is connected to two different mains power lines (such as the first mains power line and the second mains power line), the first mains power line and the second mains power line serve as hot backup for each other. When both mains power lines fail, a generator is required to power the computer room. The automatic transfer switch (ATS) automatically switches the power supply to the generator after detecting a mains power outage. If the automatic transfer switch detects a chip failure before the two mains power lines fail, it will not automatically switch. Even if the generator starts successfully, it will not be able to power the computer room, causing the computer room air conditioner to fail to start, which in turn causes the computer room temperature to rise. If the automatic transfer switch detects a chip failure after the two mains power lines fail, the automatic transfer switch has already automatically switched, the generator is in power supply, the computer room is not powered off, the air conditioner is not affected, and the computer room temperature remains within a reasonable temperature range.

[0066] For example, in the sequence of fault events that lead to high temperatures in the computer room in spring, the fault events that directly lead to high temperatures in the computer room may include but are not limited to the air conditioner not starting, insufficient air conditioning cooling, the air conditioner temperature setting is too high, poor ventilation, etc. The fault events that directly lead to the air conditioner not starting may include but are not limited to power outages in the computer room, circuit breaker tripping, etc. The fault events that directly lead to insufficient air conditioning cooling may include but are not limited to excessive dust accumulation on the filter, fan failure, insufficient refrigerant, insufficient cooling capacity estimation, evaporator fouling, etc. The fault events that directly lead to insufficient refrigerant may include but are not limited to blockage of the refrigerant pipeline, leakage of the refrigerant pipeline, etc. The fault events that directly lead to the circuit breaker tripping may include but are not limited to air conditioner overload, circuit breaker undervoltage, etc.

[0067] In this embodiment, the fault events that directly lead to power outage in the machine room may include but are not limited to the first mains power outage, the second mains power outage, the failure of the automatic transfer switch to switch, the power supply failure of the generator (or diesel engine, etc.). The fault events that directly lead to the first mains power outage or the second mains power outage may include but are not limited to the pole breaking and the like. The fault events that directly lead to the failure of the automatic transfer switch to switch may include but are not limited to manual switch switching, switch failure or damage, etc. The fault events that directly lead to the generator power supply failure may include but are not limited to the generator failure to start, circuit breaker failure, generator failure, etc. The fault events that directly lead to the generator failure to start may include but are not limited to insufficient starter motor power, starter motor failure, starter motor fuse burnout, low lubricating oil pressure, low diesel level, etc. The fault events that directly lead to circuit breaker failure may include but are not limited to spring energy storage failure, transmission mechanism failure, trip coil burnout, poor connector contact, etc. The fault events that directly lead to generator failure may include generator short circuit, generator overload or generator undervoltage, etc.

[0068] It should be pointed out that among the above-mentioned fault events, the fault events that can be considered as the root causes of the fault include temperature setting too high, poor ventilation, excessive dust accumulation on the filter, fan failure, refrigerant pipeline blockage, refrigerant pipeline leakage, insufficient cooling capacity estimation, evaporator fouling, air conditioner overload, circuit breaker undervoltage, broken rod, manual switch conversion, switch failure or damage, insufficient power in the starter motor, starter motor failure, starter motor fuse burnt, low lubricating oil pressure, low diesel level, spring energy storage failure, transmission mechanism failure, trip coil burnt, poor connector contact, generator short circuit, generator overload or generator undervoltage, etc.

[0069] Therefore, a first fault tree model can be established based on the order of the fault events that caused high temperatures in the computer room during spring. In this first fault tree model, the initial fault point is the high temperature event in the computer room. With the initial fault point as the causal relationship input, multiple branch fault points in the first priority causal relationship (such as the first priority branch fault point) can include, but are not limited to, air conditioning startup events (such as air conditioning failure to start, resulting in high temperatures in the computer room), air conditioning cooling events (such as air conditioning failure or insufficient cooling, resulting in high temperatures in the computer room), air conditioning temperature setting events (such as temperature settings that are too high, resulting in high temperatures in the computer room), and ventilation events (such as poor ventilation, resulting in high temperatures in the computer room).

[0070] Among the multiple branch fault points of the first priority causal relationship, with the air conditioner startup event as the causal relationship input, the multiple branch fault points in the second priority causal relationship (such as the second priority branch fault point) may include but are not limited to computer room power supply events (such as power outage in the computer room resulting in the air conditioner not starting), circuit breaker tripping events (such as circuit breaker tripping resulting in the air conditioner not starting), etc.

[0071] In the third priority causal relationship, with the computer room power supply event as the causal relationship input, multiple branch fault points in the third priority causal relationship (such as the third priority branch fault point) may include but are not limited to the first mains (such as the first mains power outage event), the second mains (such as the second mains power outage event), the automatic transfer switch (such as the automatic transfer switch failure event), the generator (such as the generator failure event), etc.

[0072] By analogy, in the first fault tree model, the branch fault points belonging to the root cause of the fault can be used to represent the root cause fault events corresponding to the above root causes of the fault, such as temperature setting too high, poor ventilation, excessive dust accumulation on the filter, fan failure, refrigerant pipeline blockage, refrigerant pipeline leakage, insufficient cooling capacity estimation, evaporator fouling, air conditioner overload, circuit breaker undervoltage, broken rod, manual switch conversion, switch failure or damage, insufficient power in the starter motor, starter motor failure, starter motor fuse burnt, low lubricating oil pressure, low diesel level, spring energy storage failure, transmission mechanism failure, trip coil burnt, poor connector contact, generator short circuit, generator overload or generator undervoltage and other fault events.

[0073] Given the high temperatures and rainfall in summer, transformers located outdoors are vulnerable to lightning strikes if their lightning protection fails, causing transformer overload or short circuits. This can lead to power outages in the computer room, air conditioning shutdowns, and increased room temperatures. Increased air conditioning loads in the summer, coupled with a drop in grid voltage, can cause the computer room's air conditioning circuit breaker to trip due to undervoltage, preventing the air conditioner from starting and causing room temperatures to rise. Computer room temperatures are generally kept within the maximum allowable range in summer. Higher temperatures increase the amount of heat dissipated by equipment, increasing the air's ability to absorb moisture and reducing its insulation properties. This can easily cause insulation breakdown, leading to equipment short circuits and, in turn, increased room temperatures.

[0074] Therefore, for example, in the order of occurrence of fault events that lead to high temperature in the computer room in summer, the fault events that directly lead to high temperature in the computer room may include but are not limited to the air conditioner not starting, insufficient air conditioner cooling, too high air conditioner temperature setting, large equipment heat dissipation, etc. The fault events that directly lead to the air conditioner not starting may include but are not limited to power outage in the computer room, circuit breaker tripping, etc. The fault events that directly lead to circuit breaker tripping may include but are not limited to air conditioner short circuit, circuit breaker overload, circuit breaker undervoltage, etc. The fault events that directly lead to power outage in the computer room may include but are not limited to the first mains power outage, the second mains power outage, automatic transfer switch conversion failure, generator power supply failure, transformer failure, etc. The fault events that directly lead to transformer failure may include but are not limited to transformer overload, transformer short circuit, lightning protection device failure, etc. Among them, the fault events that lead to the first mains power outage, the second mains power outage, automatic transfer switch conversion failure and generator failure are the same as the order of occurrence of the corresponding fault events in the spring mentioned above, and will not be repeated here.

[0075] Similarly, a second fault tree model can be established according to the order of occurrence of fault events that cause high temperature in the computer room in summer. The specific principle can be referred to the first fault tree model mentioned above and will not be repeated here.

[0076] Accordingly, given the fall's drop in temperature and the widening difference between day and night, while the room's temperature is more comfortable, small animals take advantage of this opportunity to enter the room in preparation for winter. If the room's seals are not tight during this period, air conditioning can leak, causing the room's temperature to rise. When small animals enter the air conditioner's outdoor unit, they block the fan, affecting the compressor's heat dissipation and causing it to operate inefficiently. This in turn reduces the air conditioner's cooling capacity, causing the room's temperature to rise.

[0077] For example, in the order of failure events that lead to high temperatures in the computer room in autumn, the failure events that directly lead to high temperatures in the computer room may include, but are not limited to, air conditioning failure, insufficient air conditioning cooling, inadequate sealing of the computer room, air conditioning temperature setting too high, and blockage of the air conditioning outdoor unit. The failure events that lead to air conditioning failure or insufficient air conditioning cooling follow the same order as the corresponding failure events in spring, and will not be repeated here.

[0078] Similarly, according to the order of occurrence of fault events that lead to high temperature in the computer room in autumn, a third fault tree model can be established. The specific principle can refer to the first fault tree model mentioned above and will not be repeated here.

[0079] To ensure normal equipment operation, air conditioning or additional heat sources (such as heaters) are often used to maintain low winter temperatures. High-powered heat sources can also cause the entire equipment room to heat up. Furthermore, a malfunction in the temperature measurement device or a disturbance in the transmission line can cause false alarms or high-temperature alarms.

[0080] Since the outside temperature is lower in winter, air conditioning is generally not required. Therefore, in the sequence of fault events that lead to high temperature in the computer room in winter, the fault events that directly lead to high temperature in the computer room may include but are not limited to failure of the temperature measuring device, excessive power of the heat source, too high temperature setting, false alarms, etc.

[0081] Similarly, according to the order of occurrence of fault events that lead to high temperature in the computer room in winter, a fourth fault tree model can be established. The specific principle can refer to the first fault tree model mentioned above and will not be repeated here.

[0082] Therefore, when a high temperature is detected in the computer room (for example, a high temperature alarm is issued when the computer room temperature is higher than the temperature threshold), the corresponding fault tree model can be traversed according to the season to quickly locate the root cause of the fault, providing theoretical support for subsequent fault handling.

[0083] like Figure 1 As shown, the fault detection method provided in this embodiment may include:

[0084] S101. Get the current season.

[0085] In this embodiment, the seasons may include spring, summer, autumn and winter. Optionally, in step S101, the current season may be determined by acquiring the current time.

[0086] Considering that the power usage of the equipment in the computer room varies in different seasons, for example, the power usage of the equipment in the computer room decreases in the order of summer, spring, autumn and winter. Preferably, to improve the accuracy of the current season, step S101 may include:

[0087] S201, obtaining the collected current time and current device power;

[0088] S202: Determine the current season based on the current time and the current device power.

[0089] In this embodiment, the current device power can be used to represent the sum of the current power usage of all devices in the computer room. The computer room may include one or more devices, such as communication equipment (such as 5G equipment, etc.) or auxiliary equipment that assists the normal operation of communication equipment, such as air conditioners, generators, heat sources, etc.

[0090] Specifically, the fault detection system may include a mapping relationship between seasons and power ranges, such as spring corresponding to the first power range, summer corresponding to the second power range, autumn corresponding to the third power range, and winter corresponding to the fourth power range. Each power range can be obtained based on the actual power statistics of the equipment in the computer room in each season. Taking into account the climate differences between different regions, the seasons in some areas may be delayed by about one to two months. For example, in temperate regions, spring is around February, March, and April, summer is around May, June, and July, autumn is around August, September, and October, and winter is around November, December, and January. Therefore, if the current time is spring and the current device power is within the first power range, the current season is spring. If the current time is summer and the current device power is within the second power range, the current season is summer. If the current time is autumn and the current device power is within the third power range, the current season is autumn. If the current time is winter and the current device power is within the fourth power range, the current season is winter.

[0091] S102: When a fault is detected at the initial fault point, a target fault tree model is selected from the plurality of fault tree models based on a mapping relationship between the fault tree model and the season and the current season.

[0092] That is to say, if the current season is spring, the target fault tree model is the first fault tree model, if the current season is summer, the target fault tree model is the second fault tree model, if the current season is autumn, the target fault tree model is the third fault tree model, and if the current season is winter, the target fault tree model is the third fault tree model.

[0093] S103 : Detect the plurality of branch fault points in the target fault tree model according to the fault causal relationship, and output a fault detection result, wherein the fault detection result includes the branch fault point where the fault occurs.

[0094] That is to say, according to the order of occurrence of fault events that cause high temperature in the computer room in the current season, multiple branch fault points in the target fault tree model are traversed and the fault detection results are output, which not only improves the fault detection efficiency but also provides theoretical support for subsequent fault processing.

[0095] It should be noted that the fault detection system can also include multiple sensors. The aforementioned initial fault point and each branch fault point can be equipped with corresponding sensors to detect in real time whether a fault has occurred at the corresponding fault point. For example, a temperature sensor can be used to detect whether the computer room temperature is above a temperature threshold. If the temperature is above the temperature threshold, it indicates a fault in the computer room, such as outputting a high temperature alarm signal.

[0096] In one possible implementation, step S103 may include:

[0097] S301: Using the initial fault point as a causal relationship input, detecting multiple branch fault points of a first priority causal relationship to obtain a branch fault point where a fault occurs in the first priority causal relationship;

[0098] S302: Using a branch fault point where a fault occurs in a previous priority causal relationship as a causal relationship input, detecting multiple branch fault points in a next priority causal relationship to obtain a branch fault point where a fault occurs in the next priority causal relationship;

[0099] S303: Determine whether the branch fault point where the fault occurs is the root cause of the fault, and output a fault detection result based on the determination result.

[0100] That is, the fault detection result can be used to indicate the branch fault point where the fault occurs and is the root cause of the fault.

[0101] Taking spring as an example, referring to the first fault tree model above, high temperature in the computer room is designated as fault event A, air conditioner failure as fault event B1, insufficient air conditioner cooling as fault event B2, computer room power outage as fault event C1, circuit breaker tripping as fault event C2, and insufficient refrigerant as fault event C3. The first mains outage is designated as fault event D1, the second mains outage as fault event D2, automatic line switch failure as fault event D3, and generator power failure as fault event D4. Generator failure is designated as fault event E1, circuit breaker failure as fault event E2, and generator failure as fault event E3. Fault event A is the initial fault point, with fault event A as the causal relationship input. Fault events B1 and B2 are the first-priority branch fault points. Fault event B1 is the causal relationship input, with fault events C1 and C2 as the second-priority branch fault points. Fault event B2 is the causal relationship input, with fault event C3 as the second-priority branch fault point. Taking fault event C1 as the causal relationship input, fault events D1, D2, D3, and D4 are the third priority branch fault points. Taking fault event D4 as the causal relationship input, fault events E1, E2, and E3 are the fourth priority branch fault points.

[0102] The first fault tree model is traversed in order of priority. When a high temperature is detected in the computer room, the air conditioner is checked to see if it is not started and if the air conditioner is not cooling enough. If the air conditioner is not started, the computer room is checked to see if there is a power outage and if the circuit breaker has tripped. If a power outage is detected in the computer room, the first mains power outage, the second mains power outage, the automatic transfer switch failure, and the generator power supply failure are checked, and so on, until the branch fault point that causes the fault is detected.

[0103] In one possible implementation, step S302 may include:

[0104] S401: If a power outage in the computer room is detected, test the first mains power supply, the second mains power supply, the automatic transfer switch, and the generator;

[0105] S402: If it is detected that both the first mains power supply and the second mains power supply are out of power and the automatic transfer switch fails to switch, the first mains power supply, the second mains power supply and the automatic transfer switch are faulty;

[0106] S403: If it is detected that both the first mains power supply and the second mains power supply are out of power, and the generator power supply fails, then the first mains power supply, the second mains power supply, and the generator fail.

[0107] Considering that the computer room is connected to the primary and secondary mains, which serve as hot backups for each other, if both the primary and secondary mains fail, the automatic transfer switch switches power to the generator. Therefore, if both the primary and secondary mains fail and the automatic transfer switch fails, or if both the primary and secondary mains fail and the generator fails, the computer room will experience a power outage.

[0108] Similarly, if the current season is summer, autumn or winter, the corresponding fault tree model can be traversed to locate the root cause of the fault, which will not be repeated here.

[0109] In one possible implementation, the plurality of branch failure points include a first failure point and a plurality of second failure points in a priority causal relationship with the first failure point. The method may further include:

[0110] S501: When it is detected that the first fault point is not faulty, detect multiple second fault points;

[0111] S502: If any of the second fault points is detected to have a fault, output a fault change trend based on the second fault points that have not failed, where the fault change trend is used to predict a change trend of a fault occurring at the first fault point.

[0112] In this embodiment, the fault detection system may also include a Markov state transition model, which is modeled using "hot spare gate" and "priority AND gate" according to the order of occurrence of the fault events to obtain a Markov state transition model. The Markov state transition model can be used to predict the changing trend of the fault occurring at the first fault point.

[0113] Preferably, if Figure 7 As shown in the figure, based on the occurrence sequence of the fault events that lead to the power outage in the computer room, a Markov state transition model of the power outage in the computer room can be established, and based on the Markov state transition model, the fault change trend of the power outage in the computer room can be predicted. In the Markov state transition model of the power outage in the computer room, 0 represents normal, 1 represents fault, Indicates the first mains failure; B indicates the second mains failure; Indicates that the automatic transfer switch is faulty. Indicates a generator power failure.

[0114] For example, in the Markov state transition model, the first fault point is a computer room failure event, and the multiple second fault points are the first mains power, the second mains power, the automatic transfer switch, and the generator. If a failure is detected in any of the first mains power, the second mains power, the automatic transfer switch, or the generator, the Markov state transition model is used to predict the failure change trend of the computer room, so as to eliminate hidden dangers in a timely manner according to the failure change trend, avoid failure in the computer room, and improve the timeliness of fault handling.

[0115] Preferably, the fault change trend may include a first change trend, a second change trend, and a third change trend. Step S502 may include:

[0116] S601: If the first mains fails, outputting the first change trend based on the second mains, the automatic transfer switch, and the generator, where the first change trend indicates that if the second mains, the automatic transfer switch, and / or the generator fail, the computer room will experience a power outage.

[0117] S602: If the second mains fails, outputting a second change trend based on the first mains, the automatic transfer switch, and the generator, where the second change trend indicates that if the first mains, the automatic transfer switch, and / or the generator fail, the computer room will experience a power outage.

[0118] S603. If the automatic transfer switch and / or the generator fails, the third change trend is output based on the first mains power and the second mains power, and the third change trend is used to indicate that if the first mains power and the second mains power fail, the computer room will be out of power.

[0119] In step S601, when the computer room is not experiencing a power outage, if a power outage of the first mains is detected, the second mains, the automatic transfer switch, and the generator are inspected. If the second mains, the automatic transfer switch, and the generator are all detected to be normal, the first change trend is that if the second mains, the automatic transfer switch, or the generator fails, a power outage will occur in the computer room. Therefore, the relevant staff must give priority to checking and ensuring that the second mains, the automatic transfer switch, and the generator are normal to avoid a power outage in the computer room. If a power outage of the second mains is detected, the first change trend is that if the automatic transfer switch or the generator fails, a power outage will occur in the computer room. Therefore, the relevant staff must give priority to checking and ensuring that the automatic transfer switch or the generator are normal to avoid a power outage in the computer room. If a power outage of the second mains is detected, the first change trend is that if the automatic transfer switch or the generator fails, a power outage will occur in the computer room. Therefore, the relevant staff must give priority to checking and ensuring that the automatic transfer switch or the generator are normal to avoid a power outage in the computer room.

[0120] Similarly, in step S602, when the computer room is not experiencing a power outage, if a power outage of the second mains is detected, the first mains, the automatic transfer switch, and the generator are inspected. If the first mains, the automatic transfer switch, and the generator are all detected to be normal, the second change trend is that if the first mains, the automatic transfer switch, or the generator fails, a power outage will occur in the computer room. Therefore, the relevant staff must give priority to checking and ensuring that the first mains, the automatic transfer switch, and the generator are normal to avoid a power outage in the computer room. If a power outage of the first mains is detected, the second change trend is that if the automatic transfer switch or the generator fails, a power outage will occur in the computer room. Therefore, the relevant staff must give priority to checking and ensuring that the automatic transfer switch or the generator are normal to avoid a power outage in the computer room. If a power outage of the automatic transfer switch or the generator is detected, the second change trend is that if the first mains fails, a power outage will occur in the computer room. Therefore, the relevant staff must give priority to checking and ensuring that the first mains is normal to avoid a power outage in the computer room.

[0121] Similarly, in step S603, when the power outage in the computer room is not detected, if a fault in the automatic transfer switch or generator is detected, the first mains and the second mains are tested. If both the first mains and the second mains are detected to be normal, the third change trend is that if both the first mains and the second mains are out of power, the computer room will be out of power. Therefore, the relevant staff must give priority to checking and ensuring that the first mains and the second mains are normal to avoid a power outage in the computer room. If a power outage in the first mains is detected, the third change trend is that if the second mains is out of power, the computer room will be out of power. Therefore, the relevant staff must give priority to checking and ensuring that the automatic transfer switch or generator is normal to avoid a power outage in the computer room. If a fault in the automatic transfer switch or generator is detected, the third change trend is that if the first mains is out of power, the computer room will be out of power. Therefore, the relevant staff must give priority to checking and ensuring that the first mains is normal to avoid a power outage in the computer room.

[0122] It is understood that some or all of the steps or operations in the above embodiments are merely examples, and the present application embodiments may also perform other operations or variations of various operations. In addition, the various steps may be performed in a different order than those presented in the above embodiments, and it is possible that not all of the operations in the above embodiments need to be performed.

[0123] Example 2

[0124] like Figure 8 FIG. 1 is a schematic diagram of an embodiment of the fault prediction method of the present application. Figure 8 As shown, the above fault prediction method may include:

[0125] S701: When it is detected that the first fault point is not faulty, detect multiple second fault points;

[0126] S702: If any of the second fault points is detected to have a fault, output a fault change trend based on the second fault points that have not failed, where the fault change trend is used to predict a change trend of a fault occurring at the first fault point.

[0127] Specifically, the fault prediction method can be applied to a fault detection system, wherein the fault detection system includes a fault tree model, wherein the fault tree model includes an initial fault point and multiple branch fault points sorted by fault causal relationship, wherein the multiple branch fault points include a first fault point and multiple second fault points in a priority causal relationship below the first fault point. The fault tree model can refer to the above Figure 1 The specific content or principle of the fault tree model in the method embodiment, step S701 and step S702 can refer to the above Figure 1 The specific content or principle of step S501 and step S502 in the method embodiment will not be repeated here.

[0128] It is understood that some or all of the steps or operations in the above embodiments are merely examples, and the present application embodiments may also perform other operations or variations of various operations. In addition, the various steps may be performed in a different order than those presented in the above embodiments, and it is possible that not all of the operations in the above embodiments need to be performed.

[0129] Example 3

[0130] like Figure 9 As shown, in embodiment 3 of the present invention, a fault detection system 100 is disclosed. The fault detection system 100 includes multiple fault tree models and mapping relationships between the fault tree models and seasons. The fault tree model includes an initial fault point and multiple branch fault points sorted by fault causal relationships. The system 100 also includes:

[0131] Acquisition module 110, used to obtain the current season;

[0132] A selection module 120 is configured to select a target fault tree model from the plurality of fault tree models based on the mapping relationship and the current season when a fault occurs at the initial fault point;

[0133] The output module 130 is configured to detect the plurality of branch fault points in the target fault tree model according to the fault causal relationship, and output a fault detection result, wherein the fault detection result includes the branch fault point where the fault occurs.

[0134] In one possible implementation, the fault causal relationship includes multiple causal relationships sorted by priority, and the output module 130 is further configured to:

[0135] Taking the initial fault point as a causal relationship input, detecting the plurality of branch fault points of the first priority causal relationship to obtain the branch fault point where the fault occurs in the first priority causal relationship;

[0136] Taking the branch fault point where a fault occurs in the previous priority causal relationship as the causal relationship input, detecting multiple branch fault points of the next priority causal relationship to obtain the branch fault point where a fault occurs in the next priority causal relationship;

[0137] Determine whether the branch fault point where the fault occurs is the root cause of the fault, and output a fault detection result based on the determination result.

[0138] In one possible implementation, the plurality of branch fault points include a computer room fault event and a first mains power supply, a second mains power supply, an automatic transfer switch, and a generator that are in a priority causal relationship with the computer room fault event. The output module 130 is further configured to:

[0139] If a power outage in the equipment room is detected, testing the first mains power supply, the second mains power supply, the automatic transfer switch, and the generator;

[0140] If it is detected that both the first mains power supply and the second mains power supply are out of power and the automatic transfer switch fails to switch, then the first mains power supply, the second mains power supply and the automatic transfer switch are faulty;

[0141] If it is detected that both the first mains power supply and the second mains power supply are out of power and the generator power supply fails, the first mains power supply, the second mains power supply and the generator fail.

[0142] In one possible implementation, the acquisition module 110 is further configured to:

[0143] Get the collected current time and current device power;

[0144] A current season is determined based on the current time and the current device power.

[0145] In one possible implementation, the multiple branch fault points include a first fault point and multiple second fault points in a priority causal relationship with the first fault point, and the fault detection system 100 is further configured to:

[0146] When it is detected that the first fault point has not failed, detecting a plurality of the second fault points;

[0147] If a fault is detected at any of the second fault points, a fault change trend is output based on the second fault points that have not failed, and the fault change trend is used to predict the change trend of the first fault point when a fault occurs.

[0148] In one possible implementation, the fault change trend includes a first change trend, a second change trend, and a third change trend; the first fault point includes a power supply event in a computer room; the plurality of second fault points include a first mains power supply, a second mains power supply, an automatic transfer switch, and a generator; and the fault detection system 100 is further configured to:

[0149] If the first mains fails, outputting the first change trend based on the second mains, the automatic transfer switch, and the generator, wherein the first change trend is used to indicate that if the second mains, the automatic transfer switch, and / or the generator fail, the computer room will be out of power;

[0150] If the second mains fails, outputting the second change trend based on the first mains, the automatic transfer switch, and the generator, wherein the second change trend is used to indicate that if the first mains, the automatic transfer switch, and / or the generator fail, the computer room will be out of power;

[0151] If the automatic transfer switch and / or the generator fails, the third change trend is output based on the first mains power and the second mains power, and the third change trend is used to indicate that if the first mains power and the second mains power fail, the computer room will be out of power.

[0152] It is understandable that Figure 9 The fault detection system 100 provided in the embodiment shown can be used to implement the present application Figure 1 or Figure 8 The technical solution of the method embodiment shown, its implementation principle and technical effects can be further referred to the relevant description in the method embodiment.

[0153] It should be understood that the above Figure 9 The division of the various modules of the fault detection system 100 shown is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. Moreover, these modules can all be implemented in the form of software called through processing elements; they can also all be implemented in the form of hardware; some modules can also be implemented in the form of software called through processing elements, and some modules can be implemented in the form of hardware. For example, the output module can be a separately established processing element, or it can be integrated into a chip of an electronic device. The implementation of other modules is similar. In addition, these modules can all or partly be integrated together, or they can be implemented independently. During the implementation process, each step of the above method or each of the above modules can be completed by the hardware integrated logic circuit in the processor element or the instructions in the form of software.

[0154] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, these modules may be integrated together to implement a system-on-a-chip (SOC).

[0155] Example 4

[0156] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor:

[0157] memory for storing computer programs;

[0158] The processor is configured to execute the computer program stored in the memory so as to enable the electronic device to execute the method of embodiment 1 or embodiment 2.

[0159] The processor and the memory can communicate with each other through an internal connection path to transmit control and / or data signals. The memory is used to store computer programs, and the processor is used to call and execute the computer programs from the memory.

[0160] The above-mentioned memory can be a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer.

[0161] Example 5

[0162] Embodiment 5 of the present invention provides a computer-readable storage medium, including a program or instruction. When the program or instruction runs on a computer, the method of embodiment 1 or embodiment 2 is executed.

[0163] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode to another website, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0164] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A fault detection method, applied to a fault detection system, characterized in that: The fault detection system includes multiple fault tree models and mapping relationships between the fault tree models and seasons. The fault tree models include an initial fault point and multiple branch fault points sorted by fault causal relationships. The method includes: Get the current season; When a fault is detected at the initial fault point, a target fault tree model is selected from the plurality of fault tree models based on the mapping relationship and the current season; According to the fault causal relationship, the plurality of branch fault points in the target fault tree model are detected, and a fault detection result is output, wherein the fault detection result includes the branch fault point where the fault occurs; The fault causal relationship includes a plurality of causal relationships sorted by priority. The detecting of the plurality of branch fault points in the target fault tree model according to the fault causal relationship and outputting a fault detection result include: Taking the initial fault point as a causal relationship input, detecting the plurality of branch fault points of the first priority causal relationship to obtain the branch fault point where the fault occurs in the first priority causal relationship; Taking the branch fault point where a fault occurs in the previous priority causal relationship as the causal relationship input, detecting multiple branch fault points of the next priority causal relationship to obtain the branch fault point where a fault occurs in the next priority causal relationship; Determine whether the branch fault point where the fault occurs is the root cause of the fault, and output a fault detection result based on the determination result; The plurality of branch fault points include a first fault point and a plurality of second fault points in a priority causal relationship below the first fault point, and the method further includes: When it is detected that the first fault point has not failed, detecting a plurality of the second fault points; If a fault is detected at any of the second fault points, a fault change trend is output based on the second fault points that have not failed, and the fault change trend is used to predict the change trend of the first fault point when a fault occurs; The plurality of branch fault points include a computer room power supply event and a first mains power supply, a second mains power supply, an automatic transfer switch and a generator that are in a priority causal relationship with the computer room power supply event.

2. The fault detection method according to claim 1, characterized in that: The branch fault point where a fault occurs in the previous priority causal relationship is used as the causal relationship input, and multiple branch fault points of the next priority causal relationship are detected to obtain the branch fault point where a fault occurs in the next priority causal relationship, including: If a power outage in the equipment room is detected, testing the first mains power supply, the second mains power supply, the automatic transfer switch, and the generator; If it is detected that both the first mains power supply and the second mains power supply are out of power and the automatic transfer switch fails to switch, then the first mains power supply, the second mains power supply and the automatic transfer switch are faulty; If it is detected that both the first mains power supply and the second mains power supply are out of power and the generator power supply fails, the first mains power supply, the second mains power supply and the generator fail.

3. The fault detection method according to claim 1, characterized in that: Obtaining the current season includes: Get the collected current time and current device power; A current season is determined based on the current time and the current device power.

4. The fault detection method according to claim 1, characterized in that: The fault change trend includes a first change trend, a second change trend, and a third change trend. The first fault point includes a power supply event in a computer room. The plurality of second fault points include a first mains power supply, a second mains power supply, an automatic transfer switch, and a generator. Outputting the fault change trend based on the second fault point that has not failed includes: If the first mains fails, outputting the first change trend based on the second mains, the automatic transfer switch, and the generator, wherein the first change trend is used to indicate that if the second mains, the automatic transfer switch, and / or the generator fail, the computer room will be out of power; If the second mains fails, outputting the second change trend based on the first mains, the automatic transfer switch, and the generator, wherein the second change trend is used to indicate that if the first mains, the automatic transfer switch, and / or the generator fail, the computer room will be out of power; If the automatic transfer switch and / or the generator fails, the third change trend is output based on the first mains power and the second mains power, and the third change trend is used to indicate that if the first mains power and the second mains power fail, the computer room will be out of power.

5. A fault detection system, characterized in that: The fault detection system includes multiple fault tree models and mapping relationships between the fault tree models and seasons. The fault tree models include an initial fault point and multiple branch fault points sorted by fault causal relationships. The system also includes: Collection module, used to obtain the current season; a selection module, configured to select a target fault tree model from the plurality of fault tree models based on the mapping relationship and the current season when a fault occurs at the initial fault point; an output module, configured to detect the plurality of branch fault points in the target fault tree model according to the fault causal relationship, and output a fault detection result, wherein the fault detection result includes the branch fault point where the fault occurs; The fault causal relationship includes a plurality of causal relationships sorted by priority, and the output module is further configured to use the initial fault point as a causal relationship input, detect the plurality of branch fault points of the first priority causal relationship, and obtain the branch fault point where the fault occurs in the first priority causal relationship; Taking the branch fault point where a fault occurs in the previous priority causal relationship as the causal relationship input, detecting multiple branch fault points of the next priority causal relationship to obtain the branch fault point where a fault occurs in the next priority causal relationship; Determine whether the branch fault point where the fault occurs is the root cause of the fault, and output a fault detection result based on the determination result; The plurality of branch fault points include a first fault point and a plurality of second fault points in a priority causal relationship with the first fault point, and the output module is further configured to detect the plurality of second fault points when it is detected that the first fault point has not failed; If a fault is detected at any of the second fault points, a fault change trend is output based on the second fault points that have not failed, and the fault change trend is used to predict the change trend of the first fault point when a fault occurs; The plurality of branch fault points include a computer room power supply event and a first mains power supply, a second mains power supply, an automatic transfer switch and a generator that are in a priority causal relationship with the computer room power supply event.

6. An electronic device, characterized in that: include: Memory and processor: The memory is used to store computer programs; The processor is configured to execute the computer program stored in the memory, so as to enable the electronic device to perform the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The method comprises a program or an instruction, and when the program or the instruction is run on a computer, the method according to any one of claims 1 to 4 is executed.

Images