Temperature anomaly early warning method and device, electronic equipment and storage medium

Abstract

The present disclosure discloses a temperature anomaly early warning method and device, an electronic device and a storage medium. According to the present application, the bearing tile temperature monitoring data and the working condition parameters of at least two hydroelectric generating units are integrated, the comparable data set is constructed through working condition alignment to establish the statistical benchmark of the group tile temperature distribution, the limitations of single machine historical data analysis or fixed threshold monitoring are broken through, the early statistical significant deviation of the target unit tile temperature relative to the group can be accurately captured, and therefore, the technical problem that the existing monitoring method relies on the SCADA system fixed threshold alarm, the single machine historical data analysis, and it is difficult to realize the early warning of the bearing tile temperature anomaly can be solved. The technical effects of realizing the early identification and early warning of the bearing tile temperature anomaly, checking the potential faults such as wear and cooling failure in advance, guaranteeing the operation stability of the hydroelectric generating unit, and prolonging the service life of the equipment are achieved.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a method and apparatus for early warning of temperature anomalies, an electronic device, and a storage medium. Background Technology

[0002] As the core energy conversion equipment in hydropower energy systems, the bearing system of hydro-turbine generator sets directly affects the stability and lifespan of the entire unit. With the continuous growth of my country's installed hydropower capacity, current technology for monitoring bearing temperature mainly relies on real-time monitoring and threshold alarms from SCADA systems. Specifically, this technology system covers the entire process from data acquisition to threshold determination, including key aspects such as fixed threshold setting, single-unit historical data analysis, and physical model prediction. Bearing temperature, as a core parameter reflecting lubrication status, load characteristics, and assembly precision, often indicates potential faults such as wear and cooling failure due to abnormal changes; however, existing methods struggle to provide early warnings. Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, and storage medium for early warning of temperature anomalies.

[0004] According to a first aspect of this disclosure, a method for early warning of temperature anomalies is provided, comprising:

[0005] Obtain bearing temperature monitoring data and corresponding operating parameters for at least two hydropower units during operation; Based on the operating parameters, the bearing bearing temperature monitoring data of the multiple units are aligned to ensure that the data of each unit under comparable operating conditions constitute a comparable dataset. Based on the comparable dataset, a statistical benchmark reflecting the population's watton distribution is determined; Based on the statistical benchmark, determine whether the bearing temperature of the target unit deviates significantly from the group bearing temperature distribution, and trigger an abnormal warning when the determination is yes.

[0006] Optionally, the step of aligning the bearing bearing temperature monitoring data of the multiple units according to operating conditions includes: The validity of the bearing bearing temperature monitoring data is verified, and invalid data points are removed. Based on the operating parameters, the operating status of the units is divided into operating condition ranges, and the operating data of different units that are divided into the same operating condition parameter range are classified into the same comparable dataset.

[0007] Optionally, the step of dividing the unit's operating status into operating condition intervals based on the operating condition parameters includes: Based on the multi-dimensional operating parameters consisting of active power and head, cluster analysis is used to divide the operating range of the unit into multiple operating condition intervals.

[0008] Optionally, the statistical benchmark includes measures of central tendency and dispersion of the comparable datasets.

[0009] Optionally, determining whether the bearing temperature of the target unit shows a statistically significant deviation based on the statistical benchmark includes: Based on the central tendency measure and the dispersion measure, the normal fluctuation range of the var temperature is determined; Determine whether the bearing temperature of the target unit exceeds the normal fluctuation range.

[0010] Optionally, determining whether the bearing temperature of the target unit deviates statistically significantly from the group bearing temperature distribution further includes: When it is determined that the bearing temperature of the target unit deviates, further analysis is conducted to determine whether the deviation is caused by common factors affecting all units or by specific factors affecting only the target unit. If the cause is determined to be specific factors, an abnormality warning will be triggered for the target unit.

[0011] According to a second aspect of this disclosure, a temperature anomaly early warning device is provided, comprising: The acquisition unit is also used to acquire bearing temperature monitoring data and corresponding operating parameters of at least two hydropower units during operation; The processing unit is also used to perform operating condition alignment processing on the bearing bearing temperature monitoring data of the multiple units based on the operating condition parameters, so that the data of each unit under comparable operating conditions constitute a comparable dataset. The determining unit is also used to determine a statistical benchmark reflecting the population's watt-hour distribution based on the comparable dataset; The judgment unit is also used to determine, based on the statistical benchmark, whether the bearing temperature of the target unit deviates significantly from the group bearing temperature distribution, and to trigger an abnormal warning when the determination is yes.

[0012] Optionally, the processing unit is further configured to: The validity of the bearing bearing temperature monitoring data is verified, and invalid data points are removed. Based on the operating parameters, the operating status of the units is divided into operating condition ranges, and the operating data of different units that are divided into the same operating condition parameter range are classified into the same comparable dataset.

[0013] Optionally, the processing unit is further configured to: Based on the multi-dimensional operating parameters consisting of active power and head, cluster analysis is used to divide the operating range of the unit into multiple operating condition intervals.

[0014] Optionally, the determining unit is further configured to: include the statistical benchmark as a measure of central tendency and a measure of dispersion of the comparable datasets.

[0015] Optionally, the determining unit is further configured to: Based on the central tendency measure and the dispersion measure, the normal fluctuation range of the var temperature is determined; Determine whether the bearing temperature of the target unit exceeds the normal fluctuation range.

[0016] Optionally, the determining unit is further configured to: When it is determined that the bearing temperature of the target unit deviates, further analysis is conducted to determine whether the deviation is caused by common factors affecting all units or by specific factors affecting only the target unit. If the cause is determined to be specific factors, an abnormality warning will be triggered for the target unit.

[0017] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0018] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0019] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0020] The temperature anomaly early warning method, device, electronic equipment, and storage medium disclosed herein, through integrating bearing bearing temperature monitoring data and operating parameters from at least two hydropower units, and constructing a comparable dataset by aligning operating conditions to establish a statistical benchmark for the group bearing temperature distribution, overcomes the limitations of single-unit historical data analysis or fixed threshold monitoring. It can accurately capture early statistically significant deviations of the target unit's bearing temperature relative to the group. Therefore, it can solve the technical problem that existing monitoring methods rely on fixed threshold alarms of SCADA systems and single-unit historical data analysis, making it difficult to achieve early warning of bearing bearing temperature anomalies. It achieves the technical effects of early identification and early warning of bearing bearing temperature anomalies, early detection of potential faults such as wear and cooling failure, ensuring the operational stability of hydropower generator units, and extending equipment service life.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0022] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 A schematic flowchart illustrating a method for early warning of temperature anomalies provided in an embodiment of this disclosure; Figure 2 A schematic diagram of the structure of a temperature anomaly early warning device provided in an embodiment of this disclosure; Figure 3 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0023] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0024] The following description, with reference to the accompanying drawings, outlines an embodiment of a temperature anomaly early warning method, apparatus, electronic device, and storage medium.

[0025] Figure 1 This is a schematic flowchart illustrating a method for early warning of temperature anomalies provided in an embodiment of this disclosure.

[0026] like Figure 1 As shown, the method includes the following steps: Step 101: Obtain bearing temperature monitoring data and corresponding operating parameters for at least two hydropower units during operation; Hydropower units of the same model refer to multiple units within the same hydropower station with similar structures and thermodynamic characteristics, configured for ease of manufacturing, installation, operation, maintenance, and main wiring design. These units operate under the same hydraulic conditions, ambient temperature, water quality, and other external environmental factors, making their operating data naturally comparable. Bearing temperature monitoring data covers the real-time temperature data of the unit's upper guide bearing, lower guide bearing, water guide bearing, and thrust bearing. This data directly reflects the bearing's lubrication status, load condition, and assembly precision, serving as the core basis for determining whether there are any abnormalities in the bearing. Abnormal fluctuations in bearing temperature often indicate potential faults such as wear, poor lubrication, or cooling failure.

[0027] The corresponding operating parameters mainly include active power and head. Water temperature, operating load, and other relevant parameters can also be included according to actual monitoring needs. These operating parameters are important factors affecting the normal changes in bearing pad temperature. The normal fluctuation range of unit pad temperature varies under different operating conditions, therefore, synchronous data collection is necessary to ensure the accuracy of subsequent analysis. Data acquisition is achieved through the SCADA (Supervisory Control and Data Acquisition) system deployed at the hydropower station. This system has the function of real-time monitoring of unit operating status and can continuously and stably acquire bearing pad temperature monitoring data and operating parameters. During the acquisition process, the continuity and integrity of the data must be ensured, and invalid data caused by communication anomalies, transient interference, etc., must be initially filtered out. This provides high-quality and reliable basic data support for subsequent horizontal comparison based on group data, dynamic threshold calculation, and anomaly early warning.

[0028] Step 102: Based on the operating condition parameters, perform operating condition alignment processing on the bearing bearing temperature monitoring data of the multiple units so that the data of each unit under comparable operating conditions constitute a comparable dataset. Operating parameters are key indicators reflecting the unit's operating status. Under different operating conditions, the unit's load, energy conversion efficiency, and other parameters vary, resulting in different normal fluctuation ranges in bearing pad temperature. Directly comparing bearing pad temperature data under different operating conditions can lead to misjudgments due to these differences, making it impossible to accurately identify true anomalies. When performing operating condition alignment based on the acquired operating parameters, the collected bearing pad temperature monitoring data must first be preprocessed to remove invalid data generated by factors such as communication anomalies and transient electromagnetic interference, ensuring the authenticity and reliability of the data used for alignment.

[0029] Subsequently, based on the specific numerical range of the operating parameters, the entire operating state of the unit is divided into several clearly defined operating condition intervals. Each operating condition interval corresponds to a specific combination of operating parameters, representing a stable operating state of the unit. For each unit, its operating condition interval is determined based on its real-time operating parameters. At the same time, the bearing temperature data within the same operating condition interval is matched from the monitoring data of other units. If some units are not currently within a certain operating condition interval, the valid bearing temperature data from the most recent time when they were within that operating condition interval is extracted from their historical operating data.

[0030] This process allows for the collection of bearing temperature data from all units under each operating condition within each operating range. These data are unaffected by differences in operating conditions and only reflect the bearing operating status of the unit itself, thus forming a comparable dataset that can be directly compared horizontally. This provides a unified basis for subsequent accurate analysis of whether the bearing temperature of the unit is abnormal.

[0031] Step 103: Based on the comparable dataset, determine the statistical benchmark that reflects the population's watton distribution; The comparable dataset, after being aligned with operating conditions, aggregates effective bearing temperature data of all units under the same operating conditions. These data come from units of the same model with similar structures, similar thermodynamic characteristics, and operating in the same external environment. Essentially, they are independent samples from the same healthy population, and their distribution pattern approximately follows a normal distribution, which can truly present the overall characteristics of the group bearing temperature under normal operating conditions.

[0032] The core components of a statistical benchmark include the sample mean and the sample standard deviation. The sample mean reflects the central tendency of the bearing temperature of the group, representing the normal average level of bearing temperature under the same operating conditions. The sample standard deviation reflects the dispersion of the bearing temperature of the group, characterizing the reasonable fluctuation range of the bearing temperature of each unit relative to the average level under normal operating conditions. When determining the statistical benchmark, it is necessary to make full use of all valid data in the comparable dataset to ensure that the bearing temperature information of the same type of bearing in each unit is covered, and to avoid benchmark distortion due to missing or incomplete data.

[0033] By statistically calculating all turbine temperature data in the comparable dataset, the obtained sample mean and sample standard deviation can comprehensively capture the distribution characteristics of the group's turbine temperature. This reflects both the common patterns of units of the same model under the same operating conditions and the reasonable differences between individual units. This statistical benchmark is not fixed but dynamically adjusted as the comparable dataset is updated. When the operating conditions of the units change, a new statistical benchmark is generated for the new comparable dataset, ensuring that the benchmark always adapts to the current operating state. This effectively overcomes the shortcomings of traditional fixed benchmarks that cannot adapt to fluctuations in operating conditions, laying a solid foundation for accurately determining whether the turbine temperature of a single unit deviates from the normal range of the group.

[0034] Step 104: Based on the statistical benchmark, determine whether the bearing temperature of the target unit deviates significantly from the group bearing temperature distribution, and trigger an abnormal warning when the determination is yes.

[0035] The target unit refers to any one of at least two units that requires abnormal bearing temperature detection. Its bearing temperature data has been aligned with previous operating conditions, making it suitable for horizontal comparison with group data. The statistical benchmark, as the core reference reflecting the normal operating status of the group bearing temperature, condenses the concentration trend and reasonable fluctuation characteristics of bearing temperatures of multiple units under the same operating conditions. It provides an objective standard that fits the actual operating conditions for judging whether the bearing temperature of a single unit is abnormal, completely eliminating the reliance on fixed thresholds or historical data of a single unit in traditional judgment methods.

[0036] The core logic of the judgment process is not to compare the absolute value of bearing temperature, but to focus on the statistical deviation of the target unit's bearing temperature from the distribution of the group's bearing temperature. This allows for the precise capture of specific faults affecting only a single unit, effectively filtering out overall group bearing temperature drift caused by systemic factors such as changes in ambient temperature. Specifically, by quantifying the deviation of the target unit's bearing temperature from the sample mean in the statistical benchmark, and comparing this deviation with the normal fluctuation range of the group's bearing temperature, it is determined whether there is a statistically significant deviation. The normal fluctuation range of the group's bearing temperature is derived based on the statistical benchmark and can fully accommodate reasonable individual differences among units of the same model under the same operating conditions, ensuring the scientific validity and reliability of the judgment results.

[0037] If the bearing temperature of the target unit exceeds the normal fluctuation range mentioned above, it indicates a statistically significant deviation from the overall bearing temperature distribution. This deviation is not a random, reasonable fluctuation, but is highly likely due to potential problems such as bearing wear, poor lubrication, abnormal assembly precision, or cooling system failure. In this case, the system will immediately trigger an anomaly warning, sending a notification to operation and maintenance personnel containing key information such as the target unit number and the type of abnormal bearing, helping them quickly pinpoint the core issue. This judgment and warning mode is highly sensitive to early, gradually changing bearing temperature anomalies, enabling maintenance personnel to intervene promptly in the early stages of a fault, preventing further deterioration and serious accidents such as bearing burnout or shaft seizure. This significantly reduces economic losses caused by unplanned downtime and effectively ensures the safety and stability of large and medium-sized hydropower units.

[0038] In some embodiments, the process of aligning the bearing bearing temperature monitoring data of the multiple units includes: The validity of the bearing bearing temperature monitoring data is verified, and invalid data points are removed. Based on the operating parameters, the operating status of the units is divided into operating condition ranges, and the operating data of different units that are divided into the same operating condition parameter range are classified into the same comparable dataset.

[0039] When aligning bearing bearing temperature monitoring data from multiple generating units, the first step is to perform validity verification. This is a fundamental prerequisite for ensuring the accuracy of subsequent data comparisons. During the acquisition and transmission of bearing bearing temperature monitoring data, invalid data points may arise due to factors such as communication link interruptions, momentary electromagnetic interference from equipment, or temporary sensor malfunctions. Such data cannot accurately reflect the actual operating status of the unit's bearings, and directly incorporating it into the analysis would severely impact the alignment of operating conditions and the reliability of subsequent anomaly assessments.

[0040] The validity verification process uses preset data rationality rules to screen each collected bearing pad temperature data point, eliminating invalid data that exceeds the normal physical range, exhibits abnormal fluctuations, or shows no continuous change. This ensures that the retained monitoring data objectively and accurately represents the temperature state of the bearing during operation, providing a high-quality data foundation for operating condition alignment processing. After validity verification, the unit's operating status is divided into operating condition intervals based on the acquired operating condition parameters. Operating condition parameters directly determine the unit's load level, energy conversion efficiency, and bearing stress. The normal fluctuation patterns of bearing pad temperature differ significantly under different operating conditions. Therefore, based on the numerical distribution range of core operating condition parameters such as active power and head, the entire operating range of the unit needs to be divided into several clearly defined operating condition intervals. Each operating condition interval corresponds to a specific set of operating condition parameters, representing a stable operating mode of the unit. After completing the operating condition interval division, the bearing pad temperature monitoring data of different units are categorized according to their corresponding operating condition parameter ranges. All operating data within the same operating condition parameter range, regardless of which unit they originate from, are grouped into the same comparable dataset.

[0041] This classification method effectively eliminates the interference of different operating conditions on bearing bearing temperature data, ensuring that all data in the same comparable dataset have the same operating background. This guarantees that the bearing bearing temperature data of at least two units can be compared horizontally under a unified operating condition benchmark, laying a solid foundation for the subsequent construction of a statistical benchmark reflecting the distribution of bearing temperature in the group and for accurate identification of anomalies.

[0042] In some embodiments, dividing the operating state of the unit into operating condition intervals based on the operating condition parameters includes: Based on the multi-dimensional operating parameters consisting of active power and head, cluster analysis is used to divide the operating range of the unit into multiple operating condition intervals.

[0043] Operating condition ranges are divided based on multi-dimensional operating parameters consisting of active power and head. The core of this approach is to leverage the synergistic characterization of these two key parameters and the objective grouping capabilities of cluster analysis to achieve accurate classification of the unit's operating status. Active power directly reflects the unit's load level, and the load magnitude directly alters the bearing's stress and friction, thus affecting the normal fluctuation range of bearing temperature. Head, on the other hand, directly reflects the hydropower station's hydraulic conditions. Under different heads, the driving effect and impact force of water flow on the unit vary, which also affects the bearing system and causes changes in bearing temperature.

[0044] The combined multidimensional operating parameters can comprehensively and accurately capture the core characteristics of the unit's operating status, providing the most accurate basis for dividing operating condition intervals. Cluster analysis, as an unsupervised data grouping technique, does not require preset fixed interval boundaries and can automatically identify the natural distribution patterns of data in the multidimensional operating parameter space. During the division process, the active power and head data generated during the operation of each unit are used as analysis samples. By calculating the similarity of multidimensional parameters between different samples, operating data with highly similar characteristics are aggregated into the same category, and each category is an independent operating condition interval.

[0045] This classification method can adapt to the actual distribution of unit operating data, effectively avoiding the subjectivity and limitations brought about by manually setting interval boundaries, and ensuring that units within each operating condition interval are under similar load levels and hydraulic conditions. Multiple operating condition intervals divided through cluster analysis can clearly distinguish different operating scenarios, allowing units within the same interval to have a consistent operating condition background. This ensures that the subsequently collected bearing bearing temperature data has strong comparability, providing a scientific and solid foundation for building a reliable group statistical benchmark and accurately identifying bearing temperature anomalies.

[0046] In some embodiments, the statistical benchmark includes a measure of central tendency and a measure of dispersion of the comparable datasets.

[0047] Central tendency and dispersion measures in statistical benchmarks are core indicators for characterizing the overall distribution characteristics of comparable datasets. Their combined effect provides a comprehensive and objective group reference for determining whether the bearing temperature of a target unit is abnormal. The central tendency measure reflects the average bearing temperature of at least two units under the same operating conditions. It is a core distillation of the normal operating status of the group's bearing temperature, accurately capturing the common temperature characteristics exhibited by units of the same model due to similar structures and thermodynamic characteristics. Since units of the same model operate in the same external environment, facing similar hydraulic conditions and loads, their bearing temperature data approximately follow a normal distribution under the same operating conditions. The central tendency measure precisely corresponds to the center of this distribution, intuitively presenting the typical range of bearing temperature values ​​under healthy conditions, providing a core reference point for determining whether the bearing temperature of a single unit deviates from the normal level of the group.

[0048] The dispersion measure characterizes the range of fluctuation of temperature data for each turbine in a comparable dataset relative to a central tendency measure. It quantifies the reasonable temperature differences between units of the same model caused by minor differences in manufacturing and assembly, slight variations in operational wear, and other factors. This range of fluctuation is not random or disordered, but rather a statistical regularity formed based on a large amount of operational data from healthy units. It can effectively encompass normal differences between individual units while excluding interference from extreme outliers. The existence of the dispersion measure ensures that the statistical benchmark is no longer a single fixed value, but rather has a reasonable range of flexibility, avoiding misjudgments caused by an excessive pursuit of data consistency, and ensuring the scientific rigor and flexibility of subsequent anomaly assessments.

[0049] The measures of central tendency and dispersion are complementary and indispensable, together forming a complete statistical benchmark. The measure of central tendency determines the core range of the group's bearing temperature, while the measure of dispersion defines the reasonable boundaries of this core range. The combination of the two reflects both the common patterns of bearing temperature among units of the same model and respects the reasonable differences among individual units. This statistical benchmark can dynamically adapt to changes in the operating conditions of the units. When the operating conditions change, the comparable dataset is updated accordingly, and the measures of central tendency and dispersion are adjusted synchronously, always maintaining a high degree of adaptability to the current operating status. This provides a stable, reliable, and realistic group reference standard for subsequent judgment of bearing temperature anomalies in target units through statistical deviation, effectively supporting the accuracy and sensitivity of anomaly early warning.

[0050] In some embodiments, determining whether the bearing temperature of the target unit deviates significantly from the statistical benchmark includes: Based on the central tendency measure and the dispersion measure, the normal fluctuation range of the var temperature is determined; Determine whether the bearing temperature of the target unit exceeds the normal fluctuation range.

[0051] Determining the normal fluctuation range of bearing temperature based on central tendency and dispersion measures is a crucial step in transforming abstract statistical benchmarks into concrete judgment criteria, providing an operational quantitative basis for accurately identifying anomalies. Central tendency, as the core reference benchmark for group bearing temperatures, intuitively reflects the average level of bearing bearing temperatures of at least two units under the same operating conditions, serving as the central anchor point for defining the normal fluctuation range. Dispersion measures quantify the dispersion of data within the group bearing temperatures relative to this average level, clearly presenting the reasonable temperature differences between healthy units caused by minor manufacturing and assembly variations, slight differences in operational wear, and other factors. The normal fluctuation range constructed by combining these two measures firmly relies on the statistical characteristic that bearing temperatures of units of the same model approximately follow a normal distribution, while also closely reflecting actual operating scenarios. It effectively encompasses normal differences between individual units while accurately excluding unreasonable extreme fluctuations, ensuring the scientific and practical nature of the range definition.

[0052] After determining the normal fluctuation range, the bearing temperature of the target unit is compared with the range to determine statistically significant deviations. The bearing temperature data of the target unit has been aligned with previous operating conditions, providing a basis for horizontal comparison with the group data. The reasonableness of its bearing temperature values ​​needs to be referenced to the normal fluctuation range of the group. If the bearing temperature of the target unit falls within the normal fluctuation range, it indicates that its temperature change conforms to the group's operating pattern, and the deviation from the central tendency measure is within a reasonable range, with no statistically significant deviation, indicating that the bearing is operating normally. If the bearing temperature of the target unit exceeds the normal fluctuation range, whether above the upper limit or below the lower limit, it indicates that its temperature change deviates from the statistical scope of normal group operation, constituting a statistically significant deviation. This deviation is not a random, reasonable fluctuation, but is likely due to potential problems such as bearing wear, poor lubrication, cooling system failure, or abnormal temperature measuring equipment. This judgment method can accurately capture these specific anomalies, providing a reliable basis for triggering anomaly warnings and timely maintenance intervention, effectively improving the accuracy and targeting of anomaly identification.

[0053] In some embodiments, determining whether the bearing temperature of the target unit deviates statistically significantly from the group bearing temperature distribution further includes: When it is determined that the bearing temperature of the target unit deviates, further analysis is conducted to determine whether the deviation is caused by common factors affecting all units or by specific factors affecting only the target unit. If the cause is determined to be specific factors, an abnormality warning will be triggered for the target unit.

[0054] When a statistically significant deviation is observed in the bearing bearing temperature of a target unit relative to the overall bearing temperature distribution, further analysis of the causes of this deviation is crucial for ensuring the accuracy of early warnings. The core objective is to distinguish between systemic common effects and individual specific faults, avoiding unnecessary maintenance interventions or overlooking genuine hidden dangers due to misjudgments. Units of the same model, due to their similar structures, thermodynamic characteristics, and location within the same hydropower station and external environment, face consistent external factors such as hydraulic conditions, ambient temperature, and water quality. These factors are common to all units, causing synchronous drift in bearing temperatures across all units. This drift is a normal adaptive change at the group level, not caused by a fault in a single unit. Triggering an early warning for such deviations would result in invalid false alarms.

[0055] Factors that specifically affect the target unit are mostly due to local problems within the unit itself, such as bearing assembly precision deviations, partial failures in the lubrication system, excessive bearing wear, and blockages in the cooling circuit. These factors will not affect other units, but will only cause the bearing temperature of the target unit to deviate from the normal distribution range of the group, which is a fault signal that needs to be dealt with in a timely manner.

[0056] During the analysis, the statistical characteristics of the group's tile temperature distribution need to be used for identification. If the tile temperature of the target unit deviates while the tile temperatures of other units of the same model also show similar amplitudes and directions of change, it indicates that the deviation is caused by common factors, and there is no need to trigger an anomaly warning for the target unit. If only the target unit shows a significant deviation in tile temperature, while the tile temperatures of other units remain within the normal fluctuation range, and the deviation exceeds the range of changes that common factors might cause, then it can be determined that the deviation is caused by specific factors. In this case, triggering an anomaly warning for the target unit can accurately pinpoint the individual with potential faults, ensuring that maintenance resources are focused on the units that truly require intervention. This hierarchical judgment mechanism effectively filters out the interference of common factors, making anomaly warnings more targeted and reliable. It avoids the false alarms and missed alarms caused by the lack of differentiation of causes in traditional warning methods, and helps maintenance personnel quickly locate specific faults in individual units, providing precise guidance for timely maintenance measures and preventing the escalation of faults, further ensuring the stability and safety of the operation of large and medium-sized hydropower units.

[0057] Corresponding to the aforementioned method for early warning of temperature anomalies, this invention also proposes a device for early warning of temperature anomalies. Since the device embodiments of this invention correspond to the method embodiments described above, details not disclosed in the device embodiments can be referred to in the method embodiments, and will not be repeated here.

[0058] Figure 2 This is a schematic diagram of the structure of a temperature anomaly early warning device provided in an embodiment of this disclosure, as shown below. Figure 2 As shown, it includes: The acquisition unit 21 is also used to acquire bearing temperature monitoring data and corresponding operating parameters of at least two hydropower units during operation; The processing unit 22 is also used to perform operating condition alignment processing on the bearing bearing temperature monitoring data of the multiple units based on the operating condition parameters, so that the data of each unit under comparable operating conditions constitute a comparable dataset. The determining unit 23 is also used to determine a statistical benchmark reflecting the population's wattage distribution based on the comparable dataset; The judgment unit 24 is also used to determine, based on the statistical benchmark, whether the bearing temperature of the target unit deviates significantly from the group bearing temperature distribution, and to trigger an abnormal warning when the determination is yes.

[0059] Furthermore, in one possible implementation of this disclosure, the processing unit 22 is further configured to: The validity of the bearing bearing temperature monitoring data is verified, and invalid data points are removed. Based on the operating parameters, the operating status of the units is divided into operating condition ranges, and the operating data of different units that are divided into the same operating condition parameter range are classified into the same comparable dataset.

[0060] Furthermore, in one possible implementation of this disclosure, the processing unit 22 is further configured to: Based on the multi-dimensional operating parameters consisting of active power and head, cluster analysis is used to divide the operating range of the unit into multiple operating condition intervals.

[0061] Furthermore, in one possible implementation of this disclosure embodiment, the determining unit 23 is further configured to: the statistical benchmark includes a measure of central tendency and a measure of dispersion of the comparable dataset.

[0062] Furthermore, in one possible implementation of this disclosure, the determining unit 24 is further configured to: Based on the central tendency measure and the dispersion measure, the normal fluctuation range of the var temperature is determined; Determine whether the bearing temperature of the target unit exceeds the normal fluctuation range.

[0063] Furthermore, in one possible implementation of this disclosure, the determining unit 24 is further configured to: When it is determined that the bearing temperature of the target unit deviates, further analysis is conducted to determine whether the deviation is caused by common factors affecting all units or by specific factors affecting only the target unit. If the cause is determined to be specific factors, an abnormality warning will be triggered for the target unit.

[0064] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of the embodiments of this disclosure, and the principle is the same. Therefore, the embodiments of this disclosure are not limited thereto.

[0065] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0066] Figure 3 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0067] like Figure 3As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. I / O (Input / Output) interface 405 is also connected to bus 404.

[0068] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0069] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as a method for early warning of temperature anomalies. For example, in some embodiments, the method for early warning of temperature anomalies may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the aforementioned temperature anomaly warning method by any other suitable means (e.g., by means of firmware).

[0070] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0071] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0072] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0073] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0074] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0075] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0076] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0077] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0078] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for early warning of temperature anomalies, characterized in that, include: Obtain bearing temperature monitoring data and corresponding operating parameters for at least two hydropower units during operation; Based on the operating parameters, the bearing bearing temperature monitoring data of the multiple units are aligned to ensure that the data of each unit under comparable operating conditions constitute a comparable dataset. Based on the comparable dataset, a statistical benchmark reflecting the population's watton distribution is determined; Based on the statistical benchmark, determine whether the bearing temperature of the target unit deviates significantly from the group bearing temperature distribution, and trigger an abnormal warning when the determination is yes.

2. The method according to claim 1, characterized in that, The process of aligning the bearing bearing temperature monitoring data of the multiple units with operating conditions includes: The validity of the bearing bearing temperature monitoring data is verified, and invalid data points are removed. Based on the operating parameters, the operating status of the units is divided into operating condition ranges, and the operating data of different units that are divided into the same operating condition parameter range are classified into the same comparable dataset.

3. The method according to claim 2, characterized in that, The process of dividing the unit's operating status into operating condition intervals based on the operating condition parameters includes: Based on the multi-dimensional operating parameters consisting of active power and head, cluster analysis is used to divide the operating range of the unit into multiple operating condition intervals.

4. The method according to claim 1, characterized in that, The statistical benchmark includes measures of central tendency and dispersion of the comparable datasets.

5. The method according to claim 4, characterized in that, The step of determining whether the bearing temperature of the target unit shows a statistically significant deviation based on the statistical benchmark includes: Based on the central tendency measure and the dispersion measure, the normal fluctuation range of the var temperature is determined; Determine whether the bearing temperature of the target unit exceeds the normal fluctuation range.

6. The method according to claim 1, characterized in that, The determination of whether the bearing bearing temperature of the target unit deviates statistically significantly from the group bearing temperature distribution also includes: When it is determined that the bearing temperature of the target unit deviates, further analysis is conducted to determine whether the deviation is caused by common factors affecting all units or by specific factors affecting only the target unit. If the cause is determined to be specific factors, an abnormality warning will be triggered for the target unit.

7. A temperature anomaly early warning device, characterized in that, include: The acquisition unit is also used to acquire bearing temperature monitoring data and corresponding operating parameters of at least two hydropower units during operation; The processing unit is also used to perform operating condition alignment processing on the bearing bearing temperature monitoring data of the multiple units based on the operating condition parameters, so that the data of each unit under comparable operating conditions constitute a comparable dataset. The determining unit is also used to determine a statistical benchmark reflecting the population's watt-hour distribution based on the comparable dataset; The judgment unit is also used to determine, based on the statistical benchmark, whether the bearing temperature of the target unit deviates significantly from the group bearing temperature distribution, and to trigger an abnormal warning when the determination is yes.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images