Abnormality identification method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application disclose an abnormality identification method and device, electronic equipment and storage medium; by obtaining the running state parameters of multiple fans in a fan system; based on the running state parameters, determining the first group deviation of the fan; based on the first group deviation of the fan, calculating the deviation rate of change corresponding to the fan; based on the deviation rate of change, identifying the target fan with abnormality in the multiple fans, and generating the early warning prompt information for the target fan. In this way, by determining the first group deviation of each fan according to the running state parameters of multiple fans in the fan system, and calculating the deviation rate of change of each fan according to the first group deviation of the fan, the target fan with abnormality or potential abnormality can be identified in the multiple fans according to the deviation rate of change, and early warning is performed, so that the fan with abnormality or potential abnormality in the fan system can be identified in time, and the fan abnormality identification efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and specifically to an anomaly identification method, apparatus, electronic device, and storage medium. Background Technology

[0002] In existing multi-fan cooling systems, fan operation status is typically monitored using threshold-based alarms, such as triggering an alarm when the fan speed falls below a set threshold or stops completely. However, this anomaly detection method only triggers an alarm after the fan performance has significantly degraded or failed, failing to promptly identify fans that are abnormal or potentially abnormal, resulting in low anomaly detection efficiency. Summary of the Invention

[0003] This application provides an anomaly identification method, apparatus, electronic device, and storage medium, which can promptly identify fans in a fan system that have anomalies or potential anomalies, effectively improving the efficiency of fan anomaly identification.

[0004] This application provides an anomaly identification method, including: Obtain the operating status parameters of multiple fans in the fan system; Based on the operating status parameters, the first group deviation of the fans is determined; Based on the first group deviation of the fan, calculate the deviation change rate corresponding to the fan; Based on the deviation change rate, a target fan with an abnormality is identified among the plurality of fans, and a warning message is generated for the target fan.

[0005] Accordingly, embodiments of this application also provide an anomaly identification device, including: The acquisition unit is used to acquire the operating status parameters of multiple fans in the fan system; A determining unit is configured to determine the first group deviation of the fans based on the operating state parameters; The calculation unit is used to calculate the rate of change of deviation of the fan based on the first group deviation of the fan; The identification unit is used to identify a target fan with an abnormality among the plurality of fans based on the deviation change rate, and to generate a warning message for the target fan.

[0006] In one embodiment, a determining unit is configured to: Feature extraction is performed on the operating status parameters to obtain the operating feature information of the fan; Based on the operational characteristic information, calculate the average operational characteristic information of the multiple fans; Calculate the statistical difference between the operational characteristic information and the average operational characteristic information; Based on the difference statistics and the average operating characteristic information, the first group deviation of the fan is calculated.

[0007] In one embodiment, the computing unit is used for: Calculate the difference between the first group deviation of the fan at the current moment and the first group deviation at the previous moment to obtain the deviation difference value; Based on the deviation difference and the time difference between the current time and the previous time, the deviation change rate corresponding to the fan is calculated.

[0008] In one embodiment, the operating status parameters have multiple parameter types; the determining unit is used for: Based on the operating status parameters, calculate the second group deviation corresponding to each parameter type; The second group deviation corresponding to multiple parameter types is fused to obtain the first group deviation of the fan.

[0009] In one embodiment, the identification unit is used for: Based on the deviation change rate, fans that meet the preset abnormal conditions are identified among the multiple fans and determined as target fans with abnormalities. The preset abnormal conditions include the deviation rate of change being greater than a preset rate of change threshold and the duration being greater than a preset duration threshold.

[0010] In one embodiment, the identification unit is used for: The health of the fan is calculated based on the deviation change rate and the deviation of the first group; Based on the health status, identify the target fan among the plurality of fans that is abnormal, and the level of abnormality for the target fan; Based on the anomaly level, a warning message is generated for the target fan.

[0011] In one embodiment, the identification unit is used for: Based on the deviation change rate and the operating status parameters, the performance degradation trend analysis of the fan is performed by the target recognition model to obtain the performance degradation probability. Based on the performance degradation probability, a target fan with potential anomalies is identified among the plurality of fans.

[0012] Furthermore, embodiments of this application also provide an electronic device, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of any of the anomaly identification methods provided in embodiments of this application.

[0013] Furthermore, embodiments of this application also provide a computer-readable storage medium including a computer program, which, when run on an electronic device, causes the electronic device to perform the steps of any of the anomaly identification methods provided in embodiments of this application.

[0014] Furthermore, embodiments of this application also provide a computer program product, including a computer program stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, causing the electronic device to perform the steps of any of the anomaly identification methods provided in embodiments of this application.

[0015] This application embodiment acquires the operating status parameters of multiple fans in a fan system; determines the first group deviation degree of the fans based on the operating status parameters; calculates the deviation change rate of each fan based on the first group deviation degree; and identifies the target fan with an anomaly among the multiple fans based on the deviation change rate, and generates a warning message for the target fan. Thus, by determining the first group deviation degree of each fan based on the operating status parameters of multiple fans in the fan system, and calculating the deviation change rate of each fan based on the first group deviation degree, it is possible to identify target fans with anomalies or potential anomalies among the multiple fans based on the deviation change rate, and issue warning messages. This enables timely identification of fans with anomalies or potential anomalies in the fan system, thereby effectively improving the efficiency of fan anomaly identification. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram illustrating an implementation scenario of an anomaly identification method provided in this application embodiment; Figure 2 This is a flowchart illustrating an anomaly identification method provided in an embodiment of this application; Figure 3This is a schematic diagram of the fan system distribution for an anomaly identification method provided in this application embodiment; Figure 4 This is a schematic diagram of the anomaly detection device provided in the embodiments of this application; Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] Furthermore, in the description of the embodiments of this application, the terms "first," "second," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0020] In some multi-fan cooling systems, fan operation status is typically monitored using threshold-based alarms. For example, an alarm is triggered when the fan speed falls below a set threshold or stops completely. However, this anomaly detection method only triggers an alarm after the fan performance has significantly deteriorated or failed. It struggles to promptly identify the gradual performance degradation caused by aging, bearing wear, or load changes, and cannot identify existing or potential anomalies before a significant fan failure occurs, resulting in low anomaly detection efficiency.

[0021] To address the aforementioned technical issues, this application provides an anomaly identification method. By determining the first group deviation of each fan based on the operating status parameters of multiple fans in a fan system, and calculating the deviation change rate of each fan based on the first group deviation, the method can identify target fans with anomalies or potential anomalies among multiple fans and issue early warnings. This enables timely identification of fans with anomalies or potential anomalies in the fan system, effectively improving the efficiency of fan anomaly identification.

[0022] This application provides an anomaly identification method, apparatus, electronic device, and storage medium. The anomaly identification apparatus can be integrated into an electronic device, which may be a server, a terminal, or other similar device.

[0023] The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The terminal can include, but is not limited to, lighting fixtures, smart projection devices, mobile phones, computers, smart voice interaction devices, smart home appliances, vehicle terminals, and aircraft. The terminal and server can be directly or indirectly connected via wired or wireless communication; this application does not impose any restrictions on this connection.

[0024] Please see Figure 1 Taking the integration of anomaly detection devices into electronic devices as an example, Figure 1 This is a schematic diagram of an implementation scenario of the anomaly identification method provided in this application. The electronic device can be a terminal, which can acquire the operating status parameters of multiple fans in the fan system; determine the first group deviation degree of the fans based on the operating status parameters; calculate the deviation change rate of the fans based on the first group deviation degree of the fans; identify the target fan with an anomaly among the multiple fans based on the deviation change rate, and generate a warning message for the target fan.

[0025] It should be noted that, Figure 1 The illustrated scenario of the anomaly detection method is merely an example. The implementation environment of the anomaly detection method described in this application is intended to more clearly illustrate the technical solutions of this application and does not constitute a limitation on the technical solutions provided in this application. Those skilled in the art will recognize that, with the evolution of anomaly detection and the emergence of new business scenarios, the technical solutions provided in this application are equally applicable to similar technical problems.

[0026] The solutions provided in this application are specifically illustrated through the following embodiments. It should be noted that the order of description of the following embodiments is not intended to limit the preferred order of the embodiments.

[0027] This embodiment will be described from the perspective of an anomaly detection device, which can be integrated into an electronic device, such as a server or a terminal, and this application does not impose any restrictions on it.

[0028] Please see Figure 2 , Figure 2 This is a flowchart illustrating the anomaly identification method provided in an embodiment of this application. The anomaly identification method includes: In step 101, the operating status parameters of multiple fans in the fan system are obtained.

[0029] The fan system may include multiple fans operating in parallel. For example, it can be a multi-fan parallel cooling system, such as a cooling system for lighting equipment, power supply equipment, communication equipment, and industrial control equipment. The operating status parameters can be parameters indicating the operating status of the multiple fans, such as the actual fan speed, current, and ambient temperature.

[0030] In one embodiment, the operating status parameters of multiple fans can be collected periodically, thereby obtaining time series data composed of multiple operating status parameters based on multiple collection cycles.

[0031] Optionally, the multiple fans may include fans for blowing air and fans for suction air, or all of them may be fans for blowing air or all of them may be fans for suction air. The specific fan type and fan layout can be set according to actual needs, and this application does not limit them.

[0032] In one embodiment, it is assumed that the fan system may include eight fans, including four blowing fans for blowing air and four suction fans for suction air.

[0033] For example, please refer to Figure 3 , Figure 3 This is a schematic diagram of the fan system distribution of an anomaly identification method provided in this application embodiment. The fan system may include four suction fans (F1-F4) arranged on the front side and four blowing fans (F1-F4) arranged on the rear side, etc.

[0034] In step 102, the first group deviation of the fans is determined based on the operating status parameters.

[0035] The first group deviation can be information indicating the degree of deviation between the fan and multiple fans.

[0036] There are several ways to determine the first group deviation of fans based on operating status parameters. For example, features can be extracted from the operating status parameters to obtain the operating feature information of the fans; the average operating feature information of multiple fans can be calculated based on the operating feature information; the difference statistics between the operating feature information and the average operating feature information can be calculated; and the first group deviation of fans can be calculated based on the difference statistics and the average operating feature information.

[0037] The operating characteristic information can be information characterizing the operating status of the fan. The average operating characteristic information can be information characterizing the average operating status of multiple fans. The difference statistics can be information indicating the difference between the operating characteristic information of each fan and the average operating characteristic information.

[0038] Therefore, based on the collected operating status parameters, an operating feature vector can be constructed for each fan. This operating feature vector characterizes the fan's operating status at the current moment and serves as the basis for subsequent anomaly prediction and analysis. Then, based on the operating feature vectors of multiple fans in the same fan system, the average operating characteristic or benchmark operating model of the fan group can be calculated to characterize the group behavior benchmark of the multi-fan system under normal conditions. Next, the operating feature vectors of each fan can be compared with the group behavior benchmark to calculate the degree of deviation of the individual fan relative to the group, obtaining the first group deviation degree of the fans. When the group deviation degree of a certain fan continues to increase, it can be determined that the fan has a potential abnormal trend.

[0039] There are several ways to extract features from operating status parameters to obtain the operating characteristic information of a fan. For example, when there is only one operating status parameter, the operating status parameter can be determined as the operating characteristic information of the fan; for instance, the fan speed can be determined as the operating characteristic information of the fan. When there are multiple operating status parameters, the multiple operating status parameters of each fan can be weighted and summed according to the weight set for each type of operating status parameter to obtain the operating characteristic information of each fan.

[0040] Among them, there are several ways to calculate the difference statistics between the operating characteristic information and the average operating characteristic information. Based on the difference statistics and the average operating characteristic information, the first group deviation of the fans can be calculated. For example, the difference between the operating characteristic information and the average operating characteristic information can be calculated to obtain the difference statistics, and the ratio of the difference statistics of each fan to the average operating characteristic information can be calculated to obtain the first group deviation of the fans.

[0041] In one embodiment, the actual speed of each fan can be obtained from the operating status parameters, and the actual speed of each fan can be determined as the operating characteristic information of that fan. Next, the average speed of the actual speeds of multiple fans can be calculated to obtain the average operating characteristic information of the multiple fans. Then, the absolute value of the speed difference between the actual speed of each fan and the average speed can be calculated, and the ratio of the absolute value of the speed difference of each fan to the average speed can be calculated to obtain the first group deviation of each fan.

[0042] For example, the first group deviation of each fan can be calculated using the following formula based on the actual fan speed and the average speed: Di = |RPMi RPMavg| / RPMavg; Where Di can be represented as the first group deviation of the fans, RPMi can be represented as the actual speed of the i-th fan, and RPMavg can be represented as the average speed of the remaining fans within the same time window.

[0043] In one embodiment, the operating status parameters can have multiple parameter types, and the first group deviation of the fan can be determined based on the group deviation of the fan under the operating status parameters of multiple parameter types.

[0044] For example, there are several ways to determine the first group deviation of the fan based on the operating status parameters. For instance, the second group deviation corresponding to each parameter type can be calculated based on the operating status parameters; the second group deviations corresponding to multiple parameter types can be fused to obtain the first group deviation of the fan.

[0045] There are multiple ways to calculate the second group deviation for each parameter type based on the operating status parameters. For example, assuming that the operating status parameters include three parameter types: actual fan speed, current, and ambient temperature, then the second group deviation for the actual fan speed type, the second group deviation for the current type, and the second group deviation for the ambient temperature type can be calculated.

[0046] For example, for a current type, the current of each fan is obtained from the operating status parameters, and the current of each fan is determined as the operating characteristic information of that fan. Next, the average current of multiple fans can be calculated to obtain the average operating characteristic information of multiple fans. Then, the absolute value of the current difference between each fan's current and the average current can be calculated, as well as the ratio of the absolute value of the current difference of each fan to the average current, to obtain the second group deviation of each fan under the current parameter type.

[0047] For the ambient temperature type, the ambient temperature of each fan is obtained from the operating status parameters, and the ambient temperature of each fan is determined as the operating characteristic information of that fan. Next, the average ambient temperature of multiple fans can be calculated to obtain the average operating characteristic information of multiple fans. Then, the absolute value of the temperature difference between the ambient temperature of each fan and the average temperature can be calculated, and the ratio of the absolute value of the temperature difference of each fan to the average temperature can be calculated to obtain the second group deviation of each fan under the ambient temperature parameter type.

[0048] After calculating the second group deviation for each parameter type based on the operating status parameters, the second group deviations for multiple parameter types can be fused to obtain the first group deviation of the fan. There are several ways to fuse the second group deviations for multiple parameter types to obtain the first group deviation of the fan. For example, the statistical distribution of the second group deviations for multiple parameter types can be calculated to obtain the first group deviation of the fan.

[0049] The statistical distribution value can be information indicating the statistical distribution of the deviation of multiple second groups, such as the mean, median, mode, etc. of the deviation of multiple second groups.

[0050] Optionally, there are several ways to fuse the second group deviations corresponding to multiple parameter types to obtain the first group deviation of the fan. For example, a weight can be set for each parameter type, and the second group deviations corresponding to multiple parameter types can be weighted and summed according to the weights to obtain the first group deviation of the fan.

[0051] In step 103, the deviation change rate of the corresponding fan is calculated based on the first group deviation of the fan.

[0052] The deviation change rate can be used to describe the change in the deviation of the first group of fans over a period of time.

[0053] There are several ways to calculate the rate of change of the fan's deviation based on the first group deviation of the fan. For example, the difference between the first group deviation of the fan at the current moment and the first group deviation at the previous moment can be calculated to obtain the deviation difference. Based on the deviation difference and the time difference between the current moment and the previous moment, the rate of change of the fan's deviation can be calculated.

[0054] Here, the "previous time" can be the starting point of the current time window, and the "current time" can be the ending point of the current time window. The current time and the previous time can constitute a time window. The deviation difference can be the difference between the first group deviation at the current time and the first group deviation at the previous time. The time difference can be the difference between the current time and the previous time.

[0055] There are several ways to calculate the fan's deviation change rate based on the deviation difference and the time difference between the current and previous moments. For example, the following formula can be used to calculate the fan's deviation change rate based on the deviation difference and the time difference between the current and previous moments: Ki = (Di(t2) Di(t1)) / (t2 t1); Where Ki can be represented as the rate of change of deviation in the i-th time window, Di(t1) can be represented as the deviation of the first group at time t1, and Di(t2) can be represented as the deviation of the first group at time t2. t1 can be represented as the start time of the i-th time window, t2 can be represented as the end time of the i-th time window, and t1 is the time before t2.

[0056] In this way, the first group deviation degree Di of the fan can be linearly trended over multiple consecutive time windows to obtain the change of the fan's deviation degree from the group over time. Based on the rate of change of deviation degree and duration, the development trend of fan performance degradation can be predicted, thereby specifically extracting and identifying abnormal risks before the fan triggers the fault threshold, effectively improving the efficiency of fan anomaly identification.

[0057] In step 104, based on the deviation change rate, a target fan with an abnormality is identified among multiple fans, and a warning message is generated for the target fan.

[0058] The target fan can be one of multiple fans that is malfunctioning. The warning message can be used to provide an alert regarding the malfunction of the target fan.

[0059] There are several ways to identify an abnormal target fan among multiple fans based on the deviation change rate. For example, the fan that meets the preset abnormal conditions can be identified among multiple fans based on the deviation change rate and determined as the target fan with abnormality. The preset abnormal conditions include a deviation change rate greater than a preset change rate threshold and a duration greater than a preset duration threshold.

[0060] The preset abnormal condition can be a condition used to determine if a target fan is abnormal. The preset rate of change threshold can be a threshold for the rate of change of deviation; when the rate of change of deviation of the fan is greater than this threshold, it indicates that the fan may have an abnormal development trend. The specific value of the preset rate of change threshold can be set according to actual conditions, and this embodiment does not limit it. The duration can be the duration for which the rate of change of deviation of the fan calculated in multiple consecutive time windows is continuously greater than the preset rate of change threshold. The preset duration threshold can be a preset duration threshold; when the duration corresponding to the fan is greater than this threshold, it indicates that the fan has an abnormal development trend. The specific value of the preset duration threshold can be set according to actual conditions, and this embodiment does not limit it.

[0061] For example, when the deviation rate Ki of a fan is detected to be greater than a preset rate of change threshold (Kth) for multiple consecutive time windows, and the duration exceeds a preset duration threshold (Tth), it can be determined that the fan has an abnormal development trend and the fan can be identified as a target fan with an abnormality.

[0062] Therefore, by detecting the rate of change of the fan's deviation over multiple consecutive time windows, identifying fans that meet preset abnormal conditions as target fans with abnormalities, and generating early warning information for the target fans, it is possible to trigger abnormal fan warnings even when the fan speed is still within the normal operating range, thereby enabling early warning of potential fan failures and improving the efficiency of fan abnormality identification.

[0063] Optionally, there are several ways to identify the target fan with abnormality among multiple fans and generate warning information for the target fan based on the deviation change rate. For example, the health of the fan can be calculated based on the deviation change rate and the deviation of the first group; based on the health, the target fan with abnormality among multiple fans and the abnormality level of the target fan can be determined; and based on the abnormality level, warning information for the target fan can be generated.

[0064] The health rating can be information describing the fan's health status or degree, reflecting its current health level and remaining reliable operating capacity. The anomaly level indicates the severity of the anomaly in the target fan.

[0065] There are several ways to calculate the health of a fan based on the deviation change rate and the first group deviation. For example, one can obtain the first weight corresponding to the first group deviation of the fan and the second weight corresponding to the deviation change rate, and then perform a weighted summation of the deviation change rate and the first group deviation based on the first weight and the second weight, and calculate the fan's health based on the weighted summation result.

[0066] The first weight can be the weight corresponding to the deviation of the first group, and the second weight can be the weight corresponding to the rate of change of deviation.

[0067] For example, the fan's health Hi=1 (α×Di+β×Ki).

[0068] Here, Hi can represent the health status of the i-th fan. α can represent the first weight, and β can represent the second weight. α and β can be weighting coefficients, satisfying the condition α + β = 1. The value of Hi can range from 0 to 1. The closer Hi is to 1, the healthier the fan; the closer Hi is to 0, the less healthy the fan.

[0069] Optionally, the specific values ​​of α and β can be preset based on the operating experience of the fan, or can be adaptively determined based on historical data during the initial operation phase of the system. This embodiment of the application does not limit these values. For example, based on experience in industrial production, the value of α can be set to be between 0.6 and 0.8, and the value of β can be set to be between 0.4 and 0.2.

[0070] After calculating the health degree of the fan based on the deviation change rate and the first group deviation degree, the target fan with anomalies among multiple fans and the anomaly level of the target fan can be determined according to the health degree. Among them, there are various ways to determine the target fan with anomalies among multiple fans and the anomaly level of the target fan according to the health degree. For example, a fan with a health degree lower than a preset health degree threshold can be determined as the target fan with anomalies, and the anomaly level of the target fan can be determined according to the health degree range in which the health degree of the fan is located.

[0071] For example, assume that the anomaly levels include two levels, which are level-1 anomaly and level-2 anomaly respectively. When the fan is in a level-1 anomaly, it can indicate that the fan has a minor anomaly. When the fan is in a level-2 anomaly, it can indicate that the fan has a serious anomaly.

[0072] For example, when the health degree Hi of the fan ≥ H1, it can indicate that the fan is in a normal operating state; when the health degree Hi of the fan is in the first health degree range [H2, H1], it can indicate that the fan has a minor anomaly, determine that the fan belongs to a level-1 anomaly, and an early warning prompt message corresponding to the level-1 anomaly can be output; when the health degree Hi of the fan < H2, it can indicate that the fan has a serious anomaly, determine that the fan belongs to a level-2 anomaly, and an early warning prompt message corresponding to the level-2 anomaly can be output.

[0073] Among them, H1 and H2 can be preset health degree thresholds, and H1 > H2.

[0074] Optionally, the anomaly levels can also be divided into more levels according to actual needs. For example, they can be divided into three anomaly levels or four anomaly levels, etc. The specific level division can be set according to actual business needs, and the embodiments of the present application do not limit this here.

[0075] Optionally, the anomaly risk of the fan can be graded according to the anomaly trend prediction result and health degree index of the fan, and an early warning prompt message corresponding to the corresponding level can be output. Among them, different anomaly levels can correspond to different anomaly severity levels as well as early warning and maintenance suggestions.

[0076] For example, there are various ways to generate an early warning prompt message for the target fan based on the anomaly level. For example, for a level-1 anomaly, the fan belonging to the level-1 anomaly can be marked as the target fan with anomalies, and its data collection frequency can be increased to more accurately capture the anomaly trend of the fan, so that the fan with anomaly risk among multiple fans can be identified in a timely and accurate manner. For a level-2 anomaly, an audible and visual alarm for the fan belonging to the level-2 anomaly can be triggered, so that relevant staff can repair or replace the abnormal fan to maintain the working ability of the fan system, etc.

[0077] Therefore, this application embodiment can identify the trend of fan performance degradation in advance through anomaly prediction and graded early warning, thereby avoiding system overheating or protection shutdown caused by sudden fan failure, ensuring the stable working state of the fan system, and thus improving the efficiency of fan anomaly identification.

[0078] In one embodiment, the deviation change rate of the fan can be calculated over multiple consecutive time windows, and a linear trend analysis can be performed on the deviation change rate. When a fan meeting a preset abnormality condition is identified among multiple fans based on the deviation change rate, the fan meeting the preset abnormality condition can be identified as a target fan with an abnormality or an abnormal development trend, and an early warning can be issued. Simultaneously, the fan health can be calculated based on the deviation change rate and a first group deviation rate. Based on the health rate, the target fan with an abnormality among multiple fans and its abnormality level can be determined. Based on the abnormality level, an early warning message for the target fan can be generated. Therefore, this embodiment of the application, by analyzing the development trend of the fan deviation change rate, can identify abnormal risks among multiple fans before the fans trigger relevant fault thresholds, achieving early warning of potential fan faults. Furthermore, by calculating the fan health based on the deviation change rate and the first group deviation rate, and by accurately identifying and classifying the abnormalities of multiple fans based on their health, the efficiency of fan abnormality early warning can be further improved.

[0079] Optionally, there are several other ways to identify a target fan with anomalies among multiple fans based on the deviation change rate. For example, the performance degradation trend analysis of the fan can be performed using a target identification model based on the deviation change rate and operating status parameters to obtain the performance degradation probability; and the target fan with potential anomalies can be identified among multiple fans based on the performance degradation probability.

[0080] The target recognition model can be an artificial intelligence model used to identify the probability of fan performance degradation, such as a well-trained large-scale deep learning model. This performance degradation probability can be information indicating the likelihood of fan performance degradation.

[0081] There are several ways to identify a target fan with potential anomalies among multiple fans based on the probability of performance degradation. For example, a fan with a performance degradation probability greater than a preset probability threshold can be identified as a target fan with potential anomalies.

[0082] In one embodiment, operating status parameters such as the actual speed, current, and ambient temperature of each fan in the fan system can be collected periodically, and a group behavior benchmark can be established based on the historically collected operating status parameters. When the speed change trend of a certain fan deviates significantly from that of the other fans, and the duration of the deviation exceeds a preset duration threshold, it can be determined that the fan has a performance degradation trend, identify it as a target fan with an anomaly, and output a first-level warning message. When the deviation further intensifies, a higher-level warning message can be output to prompt maintenance personnel to check or replace the fan in advance.

[0083] Therefore, this application provides a method for anomaly prediction and graded early warning in multi-fan systems. By performing trend analysis and group comparison of fan operating status parameters, it can identify fan performance degradation trends in advance based on group deviation and changes in deviation, effectively avoiding false alarms caused by changes in system load or environment, and reducing the risk of sudden fan system failures. Simultaneously, based on health indicators and a graded early warning mechanism, relevant maintenance personnel can intuitively understand the degree of fan anomalies, thereby achieving accurate identification and predictive maintenance. It also supports adaptive updates of the relevant identification model, is applicable to scenarios involving long-term fan operation and performance changes, and enables intelligent management of operational risks in multi-fan systems without adding additional hardware.

[0084] As described above, this embodiment of the application obtains the operating status parameters of multiple fans in a fan system; determines the first group deviation of the fans based on the operating status parameters; calculates the deviation change rate of each fan based on the first group deviation; identifies the target fan with anomalies among the multiple fans based on the deviation change rate, and generates a warning message for the target fan. Therefore, by determining the first group deviation of each fan based on the operating status parameters of multiple fans in the fan system, and calculating the deviation change rate of each fan based on the first group deviation, it is possible to identify target fans with anomalies or potential anomalies among the multiple fans based on the deviation change rate, and issue warning messages. This enables timely identification of fans with anomalies or potential anomalies in the fan system, thereby effectively improving the efficiency of fan anomaly identification.

[0085] To better implement the above methods, embodiments of the present invention also provide an anomaly identification device, which can be integrated into an electronic device, which can be a terminal.

[0086] For example, such as Figure 4 The diagram shown is a structural schematic of an anomaly identification device provided in an embodiment of this application. The anomaly identification device may include an acquisition unit 201, a determination unit 202, a calculation unit 203, and an identification unit 204, as follows: The acquisition unit 201 is used to acquire the operating status parameters of multiple fans in the fan system; The determining unit 202 is used to determine the first group deviation of the fans based on the operating status parameters; The calculation unit 203 is used to calculate the deviation change rate of the fan based on the first group deviation of the fan; The identification unit 204 is used to identify a target fan with an abnormality among the plurality of fans based on the deviation change rate, and to generate a warning message for the target fan.

[0087] In one embodiment, the determining unit 202 is configured to: Feature extraction is performed on the operating status parameters to obtain the operating characteristic information of the fan; Calculate the average operating characteristic information of multiple fans based on the operating characteristic information; Calculate the statistical difference between operational characteristic information and average operational characteristic information; Based on the difference statistics and average operating characteristics, the first group deviation of the fans is calculated.

[0088] In one embodiment, the computing unit 203 is used for: Calculate the difference between the first group deviation of the fan at the current moment and the first group deviation at the previous moment to obtain the deviation difference value; Based on the deviation difference and the time difference between the current time and the previous time, the deviation change rate corresponding to the fan is calculated.

[0089] In one embodiment, the operating status parameters have multiple parameter types; the determining unit 202 is used for: Based on the operating status parameters, calculate the second group deviation corresponding to each parameter type; The second group deviation corresponding to multiple parameter types is fused to obtain the first group deviation of the fan.

[0090] In one embodiment, the identification unit 204 is used for: Based on the deviation change rate, fans that meet the preset abnormal conditions are identified among the multiple fans and determined as target fans with abnormalities. The preset abnormal conditions include the deviation rate of change being greater than a preset rate of change threshold and the duration being greater than a preset duration threshold.

[0091] In one embodiment, the identification unit 204 is used for: The health of the fan is calculated based on the deviation change rate and the deviation of the first group; Based on the health status, identify the target fan among the plurality of fans that is abnormal, and the level of abnormality for the target fan; Based on the anomaly level, a warning message is generated for the target fan.

[0092] In one embodiment, the identification unit 204 is used for: Based on the deviation change rate and the operating status parameters, the performance degradation trend analysis of the fan is performed by the target recognition model to obtain the performance degradation probability. Based on the performance degradation probability, a target fan with potential anomalies is identified among the plurality of fans.

[0093] As described above, this embodiment of the application acquires the operating status parameters of multiple fans in the fan system through the acquisition unit 201; the determination unit 202 determines the first group deviation degree of the fans based on the operating status parameters; the calculation unit 203 calculates the deviation change rate of the corresponding fan based on the first group deviation degree of the fans; and the identification unit 204 identifies the target fan with an abnormality among the multiple fans based on the deviation change rate, and generates a warning message for the target fan. Therefore, by determining the first group deviation degree of each fan based on the operating status parameters of multiple fans in the fan system, and calculating the deviation change rate of each fan based on the first group deviation degree of the fans, the system can identify target fans with abnormalities or potential abnormalities among the multiple fans based on the deviation change rate of the fans, and issue warning messages. This enables timely identification of fans with abnormalities or potential abnormalities in the fan system, thereby effectively improving the efficiency of fan anomaly identification.

[0094] Accordingly, this application also provides an electronic device, which can be a terminal, such as a smartphone, tablet computer, laptop computer, touch screen, game console, personal computer (PC), personal digital assistant (PDA), or other terminal device. Alternatively, the electronic device can be a server.

[0095] like Figure 5 As shown, Figure 5This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 300 includes a processor 301 with one or more processing cores, a memory 302 with one or more computer-readable storage media, and a computer program stored in the memory 302 and executable on the processor. The processor 301 and the memory 302 are electrically connected. Those skilled in the art will understand that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0096] The processor 301 is the control center of the electronic device 300. It connects various parts of the electronic device 300 through various interfaces and lines. By running or loading software programs and / or units stored in the memory 302, and calling data stored in the memory 302, it executes various functions of the electronic device 300 and processes data. The processor 301 may be a CPU, GPU, network processor (NP), etc., and can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0097] In this embodiment, the processor 301 in the electronic device 300 loads the instructions corresponding to the processes of one or more applications into the memory 302 according to the following steps, and the processor 301 runs the applications stored in the memory 302 to realize various functions, such as: Obtain the operating status parameters of multiple fans in the fan system; Based on the operating status parameters, determine the first group deviation of the fans; Based on the first group deviation of the fans, calculate the deviation change rate of the corresponding fans; Based on the deviation change rate, the system identifies the target fan with abnormality among multiple fans and generates a warning message for the target fan.

[0098] This solution acquires the operating status parameters of multiple fans in a fan system; based on these parameters, it determines the first group deviation of the fans; based on this first group deviation, it calculates the deviation change rate for each fan; and based on this deviation change rate, it identifies the target fan with an anomaly among the multiple fans and generates an early warning message for that target fan. In this way, by determining the first group deviation of each fan based on its operating status parameters and calculating the deviation change rate for each fan, the solution can identify target fans with anomalies or potential anomalies among the multiple fans and issue early warnings. This allows for timely identification of fans with anomalies or potential anomalies in the fan system, effectively improving the efficiency of fan anomaly identification.

[0099] Furthermore, the various functions implemented by running the application stored in memory 302 can also be found in the description of the foregoing embodiments, and will not be repeated here.

[0100] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0101] Optional, such as Figure 5 As shown, the electronic device 300 also includes: a touch display screen 303, a radio frequency circuit 304, an audio circuit 305, an input unit 306, and a power supply 307. The processor 301 is electrically connected to the touch display screen 303, the radio frequency circuit 304, the audio circuit 305, the input unit 306, and the power supply 307. Those skilled in the art will understand that... Figure 5 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0102] The touch display screen 303 can be used to display a graphical user interface (GUI) and receive operation commands generated by the user interacting with the GUI. The touch display screen 303 may include a display panel and a touch panel. The display panel can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the electronic device. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. Optionally, the display panel can be configured using a liquid crystal display (LCD), organic light-emitting diode (OLED), or other similar technologies. The touch panel can be used to collect touch operations performed by the user on or near it (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel), generate corresponding operation commands, and execute the corresponding program according to the operation commands. Optionally, the touch panel may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch location and the signal generated by the touch operation, transmitting the signal to the touch controller. The touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 301. It can also receive and execute commands from the processor 301. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it transmits the information to the processor 301 to determine the type of touch event. Subsequently, the processor 301 provides corresponding visual output on the display panel based on the type of touch event. In this embodiment, the touch panel and the display panel can be integrated into the touch display screen 303 to achieve input and output functions. However, in some embodiments, the touch panel and the touch display screen 303 can be implemented as two independent components to achieve input and output functions. That is, the touch display screen 303 can also be used as part of the input unit 306 to achieve input functions.

[0103] The radio frequency circuit 304 can be used to transmit and receive radio frequency signals to establish wireless communication with network devices or other electronic devices, and to transmit and receive signals with network devices or other electronic devices.

[0104] Audio circuitry 305 can be used to provide an audio interface between a user and an electronic device via a speaker and a microphone. Audio circuitry 305 converts received audio data into electrical signals, transmits them to the speaker, and the speaker converts them into sound signals for output. Conversely, the microphone converts collected sound signals into electrical signals, which are then received by audio circuitry 305, converted back into audio data, and then processed by processor 301 before being transmitted via radio frequency circuitry 304 to, for example, another electronic device, or output to memory 302 for further processing. Audio circuitry 305 may also include an earphone jack to facilitate communication between peripheral headphones and electronic devices.

[0105] The input unit 306 can be used to receive input target video and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0106] Power supply 307 is used to supply power to various components of electronic device 300. Optionally, power supply 307 can be logically connected to processor 301 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. Power supply 307 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0107] although Figure 5 As not shown in the diagram, the electronic device 300 may also include a camera, sensor, wireless fidelity module, Bluetooth module, etc., which will not be described in detail here.

[0108] In the above embodiments, the descriptions of each embodiment have different focuses. Parts not described in detail in a particular embodiment can be found in the relevant descriptions of other embodiments. It should be noted that the electronic device provided in this application's embodiments belongs to the same concept as the anomaly identification method described in the above embodiments, and its specific implementation process is detailed in the above method embodiments, and will not be repeated here.

[0109] As can be seen from the above, the electronic device provided in this application embodiment can obtain the operating status parameters of multiple fans in a fan system; determine the first group deviation degree of the fans based on the operating status parameters; calculate the deviation change rate of the corresponding fan based on the first group deviation degree of the fans; identify the target fan with an abnormality among multiple fans based on the deviation change rate, and generate a warning message for the target fan. Therefore, by determining the first group deviation degree of each fan based on the operating status parameters of multiple fans in the fan system, and calculating the deviation change rate of each fan based on the first group deviation degree of the fans, the device can identify the target fan with an abnormality or potential abnormality among multiple fans based on the deviation change rate of the fans, and provide a warning message. This enables timely identification of fans with abnormalities or potential abnormalities in the fan system, thereby effectively improving the efficiency of fan anomaly identification.

[0110] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0111] Therefore, embodiments of this application provide a computer-readable storage medium, including a computer program, which, when run on an electronic device, causes the electronic device to execute any of the anomaly detection methods provided in embodiments of this application. For example, the computer program can execute the steps of the following anomaly detection method: Obtain the operating status parameters of multiple fans in the fan system; Based on the operating status parameters, determine the first group deviation of the fans; Based on the first group deviation of the fans, calculate the deviation change rate of the corresponding fans; Based on the deviation change rate, the system identifies the target fan with abnormality among multiple fans and generates a warning message for the target fan.

[0112] This solution acquires the operating status parameters of multiple fans in a fan system; based on these parameters, it determines the first group deviation of the fans; based on this first group deviation, it calculates the deviation change rate for each fan; and based on this deviation change rate, it identifies the target fan with an anomaly among the multiple fans and generates an early warning message for that target fan. In this way, by determining the first group deviation of each fan based on its operating status parameters and calculating the deviation change rate for each fan, the solution can identify target fans with anomalies or potential anomalies among the multiple fans and issue early warnings. This allows for timely identification of fans with anomalies or potential anomalies in the fan system, effectively improving the efficiency of fan anomaly identification.

[0113] Furthermore, the detailed steps of the above method can be found in the description of the foregoing embodiments, and will not be repeated here.

[0114] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0115] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0116] Since the computer program stored in the computer-readable storage medium can execute any of the anomaly identification methods provided in the embodiments of this application, it can achieve the beneficial effects that any of the anomaly identification methods provided in the embodiments of this application can achieve, as detailed in the preceding embodiments, and will not be repeated here.

[0117] According to one aspect of this application, a computer program product is also provided, comprising a computer program stored in a computer-readable storage medium; when a processor of an electronic device reads the computer program from the computer-readable storage medium, the processor executes the computer program, causing the electronic device to perform the methods provided in various optional implementations of the above embodiments.

[0118] In the above embodiments of the anomaly detection device, computer-readable storage medium, electronic device, and computer program product, the descriptions of each embodiment have different focuses. Parts not described in detail in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes and beneficial effects of the anomaly detection device, computer-readable storage medium, computer program product, electronic device, and their corresponding units described above can be referred to the description of the anomaly detection method in the above embodiments, and will not be repeated here.

[0119] The above provides a detailed description of an anomaly identification method, apparatus, electronic device, computer-readable storage medium, and computer program product provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An anomaly identification method, characterized in that, include: Obtain the operating status parameters of multiple fans in the fan system; Based on the operating status parameters, the first group deviation of the fans is determined; Based on the first group deviation of the fan, calculate the deviation change rate corresponding to the fan; Based on the deviation change rate, a target fan with an abnormality is identified among the plurality of fans, and a warning message is generated for the target fan.

2. The anomaly identification method as described in claim 1, characterized in that, Determining the first group deviation of the fans based on the operating status parameters includes: Feature extraction is performed on the operating status parameters to obtain the operating feature information of the fan; Based on the operational characteristic information, calculate the average operational characteristic information of the multiple fans; Calculate the statistical difference between the operational characteristic information and the average operational characteristic information; Based on the difference statistics and the average operating characteristic information, the first group deviation of the fan is calculated.

3. The anomaly identification method as described in claim 1, characterized in that, The step of calculating the deviation change rate corresponding to the fan based on the first group deviation of the fan includes: Calculate the difference between the first group deviation of the fan at the current moment and the first group deviation at the previous moment to obtain the deviation difference value; Based on the deviation difference and the time difference between the current time and the previous time, the deviation change rate corresponding to the fan is calculated.

4. The anomaly identification method as described in claim 1, characterized in that, The operating status parameters have various parameter types; Determining the first group deviation of the fans based on the operating status parameters includes: Based on the operating status parameters, calculate the second group deviation corresponding to each parameter type; The second group deviation corresponding to multiple parameter types is fused to obtain the first group deviation of the fan.

5. The anomaly identification method according to any one of claims 1 to 4, characterized in that, The step of identifying the abnormal target fan among the plurality of fans based on the deviation change rate includes: Based on the deviation change rate, fans that meet the preset abnormal conditions are identified among the multiple fans and determined as target fans with abnormalities. The preset abnormal conditions include the deviation rate of change being greater than a preset rate of change threshold and the duration being greater than a preset duration threshold.

6. The anomaly identification method according to any one of claims 1 to 4, characterized in that, The step of identifying a target fan exhibiting an anomaly among the plurality of fans based on the deviation change rate, and generating a warning message for the target fan, includes: The health of the fan is calculated based on the deviation change rate and the deviation of the first group; Based on the health status, identify the target fan among the plurality of fans that is abnormal, and the level of abnormality for the target fan; Based on the anomaly level, a warning message is generated for the target fan.

7. The anomaly identification method according to any one of claims 1 to 4, characterized in that, The step of identifying the abnormal target fan among the plurality of fans based on the deviation change rate includes: Based on the deviation change rate and the operating status parameters, the performance degradation trend analysis of the fan is performed by the target recognition model to obtain the performance degradation probability. Based on the performance degradation probability, a target fan with potential anomalies is identified among the plurality of fans.

8. An anomaly detection device, characterized in that, include: The acquisition unit is used to acquire the operating status parameters of multiple fans in the fan system; A determining unit is configured to determine the first group deviation of the fans based on the operating state parameters; The calculation unit is used to calculate the rate of change of deviation of the fan based on the first group deviation of the fan; The identification unit is used to identify a target fan with an abnormality among the plurality of fans based on the deviation change rate, and to generate a warning message for the target fan.

9. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the anomaly identification method according to any one of claims 1 to 7.

10. A storage medium, characterized in that, The device includes a computer program that, when run on an electronic device, causes the electronic device to perform the steps of the anomaly identification method according to any one of claims 1 to 7.

Images