A method and system for detecting abnormal high temperature of fan based on time series feature fusion

Abstract

This application proposes a method and system for detecting high-temperature anomalies in fans based on time series feature fusion. The system obtains the Scada data of the fan group and performs downsampling processing. Trend quantization processing replaces the boundary instantaneous value. Then, high-frequency noise is smoothed by moving average filtering to extract temperature characteristics and operating status characteristics. Physical mechanism rules are associated to perform mechanism modeling. The coupling characteristics of the Scada data are obtained by combining mechanism modeling or calculation. The coupling characteristics include the equipment-cooling temperature difference ratio TCR, the load-temperature gradient matching degree LTM, and the physical constraint conflict flag PCC. Different weights are assigned to the coupling characteristics based on the coupling strength to perform anomaly scoring and multi-level warning. This application can avoid the performance degradation of fans caused by historical dependence, accurately locate the root cause, reduce operation and maintenance troubleshooting costs, filter out false alarms caused by sensor noise or short-term load fluctuations, reduce the false alarm rate, and improve accuracy.

Description

Technical Field

[0001] The present application relates to the technical field of health management of wind turbine generator sets, and specifically to a method and system for detecting high temperature anomalies of wind turbines based on time series feature fusion. Background Art

[0002] Currently commonly used methods for detecting fan temperature anomalies include the single-threshold alarm method, the LSTM-based prediction method, and the machine learning model classification method. Among them, the single-threshold alarm method detects temperature anomalies by setting a fixed temperature threshold, the LSTM-based prediction method predicts the theoretical temperature through historical data and compares it with the actual temperature value to determine temperature anomalies, and the machine learning model classification method uses random forest or support vector machine (SVM) to perform binary classification on instantaneous temperature data.

[0003] However, these methods have limitations. First, the threshold alarm method can trigger false alarms when the temperature suddenly changes, causing the system to capture noise rather than actual temperature anomalies. Second, the LSTM-based prediction method, which judges a single time point, ignores the temporal inertial characteristics of temperature changes, such as the heating rate and accumulated heat. In addition, it lacks correlation with equipment industrial control signals concurrent with high temperatures, such as variable speed and hydraulic pressure, resulting in ineffective utilization of fault-derived features. Furthermore, after marking an anomaly, the above method requires manual review of the time series segment and cannot automatically output accurate start and end timestamps.

[0004] The above method relies on statistical algorithms and manipulation. The statistical features have no actual physical meaning, cannot adapt to sudden changes, have a high false alarm rate, and cannot guide maintenance. To address the above problems, this application proposes a fan high temperature anomaly detection method and system based on time series feature fusion. Summary of the Invention

[0005] This application proposes the following technical solutions to address one or more technical deficiencies in the above-mentioned prior art.

[0006] Based on the first aspect of this application, a method for detecting high temperature anomalies of a fan based on time series feature fusion is proposed, comprising:

[0007] S1: Obtain Scada data of the fan group and perform downsampling processing, process the boundary instantaneous values ​​in the Scada data using a trend quantization method, and then smooth the high-frequency noise through a moving average filter to extract the temperature characteristics and operating status characteristics of the Scada data;

[0008] S2: Dividing the Scada data into a generator temperature control module, a cooling system module, an electrical load module, and a mechanical state module, and associating the temperature characteristics and operating state characteristics of the Scada data with physical mechanism rules to perform mechanism modeling;

[0009] S3: combining mechanism modeling or calculation to obtain coupling characteristics of the Scada data, wherein the coupling characteristics include the equipment-cooling temperature difference ratio TCR, the load-temperature gradient matching degree LTM, and the physical constraint conflict flag PCC;

[0010] S4: assigning different weights to coupling features based on coupling strength to perform anomaly scoring, and performing multi-level warnings based on the anomaly scores. A yellow warning is issued when the anomaly score is greater than a preset basic threshold, and a red warning is issued when the anomaly score is greater than the preset basic threshold and the number of physical constraint conflict flags (PCC) that are 1 exceeds a preset number threshold.

[0011] The anomaly scoring formula is:

[0012] ,

[0013] Among them, TCR represents the equipment-cooling temperature difference ratio, LTM represents the load-temperature gradient matching, PCC represents the number of physical constraint conflict flags set to 1, Score represents the anomaly score, and Weight represents the different weights assigned to the coupling features.

[0014] Furthermore, the temperature characteristics include pitch drive temperature, ambient temperature, water-cooling outlet valve water temperature, water-cooling inlet valve water temperature, nacelle temperature, generator bearing temperature and hub temperature;

[0015] The operating status characteristics include pump status and fan status.

[0016] Furthermore, step S1 also includes filtering the Scada data whose temperature characteristics exceed the physical limit threshold, cleaning the Scada data with logical conflicts, replacing missing values ​​with the mean of the Scada data, and performing sliding window time series processing on the Scada data.

[0017] By detecting physically infeasible events and removing data that violates basic laws, we can extract physically credible, logically self-consistent, and temporally coherent information flows, providing high-quality input for subsequent analysis and improving its reliability.

[0018] Furthermore, the calculation formula of the equipment-cooling temperature difference ratio TCR is:

[0019] ,

[0020] Where TCR represents the equipment-cooling temperature difference ratio, Indicates the temperature of key equipment, Indicates the corresponding cooling medium temperature, Indicates a minimum value.

[0021] Furthermore, the calculation formula of the load-temperature gradient matching degree LTM is:

[0022] ,

[0023] Where LTM represents the load-temperature gradient matching, Indicates that the device is The temperature change within the window, Indicates the change in load power, Indicates a minimum value.

[0024] Furthermore, the physical constraint conflict flag PCC is defined based on the system physical mechanism rules, including:

[0025] If the generator front bearing temperature is higher than the preset front bearing temperature threshold, and the difference between the inner ring temperature and the outer ring temperature of the generator front bearing or the generator rear bearing exceeds the preset bearing temperature difference threshold, the physical constraint conflict flag PCC is 1;

[0026] If the water temperature at the water-cooling outlet valve is higher than the preset water-cooling temperature threshold, and the temperature difference between the water temperature at the water-cooling outlet valve and the water temperature at the water-cooling inlet valve exceeds the preset water-cooling temperature difference threshold, the cooling system efficiency decreases, and the physical constraint conflict flag PCC is 1;

[0027] If the ambient temperature is higher than the temperature threshold of the high temperature weather warning line, and the cabin temperature is higher than the preset forced ventilation failure threshold, then there is an ambient or cabin temperature anomaly, and the physical constraint conflict flag PCC is 1;

[0028] Otherwise, the physical constraint conflict flag PCC is 0.

[0029] Combined with physical conflict constraint identification (PCC), false warnings caused by sensor noise or short-term load fluctuations can be filtered out, reducing false alarm rates and guiding maintenance.

[0030] Furthermore, the Scada data is divided into a generator temperature control module, a cooling system module, an electrical load module and a mechanical status module, specifically:

[0031] The generator temperature control module includes the generator front bearing temperature, the generator rear bearing temperature, the generator front bearing inner ring temperature and the generator front bearing outer ring temperature;

[0032] The cooling system module includes the water temperature of the water cooling outlet valve, the water temperature of the water cooling inlet valve, the pump status and the fan status;

[0033] The electrical load module includes converter active power and generator speed;

[0034] The mechanical status module includes hydraulic system pressure and bearing vibration amplitude.

[0035] Furthermore, assigning different weights to coupling features based on the coupling strength includes:

[0036] If the current window triggers two or more physical mechanism rules, a high weight is assigned to the coupling feature;

[0037] If the current window triggers a physical mechanism rule, a medium weight is assigned to the coupling feature;

[0038] If the physical mechanism rule is not triggered in the current window, a low weight is assigned to the coupling feature.

[0039] By dynamically assigning weights to associate abnormality types with physical components, the troubleshooting costs for operations and maintenance personnel can be reduced.

[0040] Based on the second aspect of this application, a fan high temperature anomaly detection system based on time series feature fusion is proposed, comprising:

[0041] Data processing module: obtains the Scada data of the fan group and performs downsampling processing, processes the boundary instantaneous values ​​in the Scada data using the trend quantization method, and then smoothes the high-frequency noise through moving average filtering to extract the temperature characteristics and operating status characteristics of the Scada data;

[0042] Mechanism modeling module: divides the Scada data into a generator temperature control module, a cooling system module, an electrical load module, and a mechanical state module, and associates the temperature characteristics and operating state characteristics of the Scada data with physical mechanism rules to perform mechanism modeling;

[0043] Coupling module: Combined with mechanism modeling or calculation to obtain the coupling characteristics of the Scada data, the coupling characteristics include the equipment-cooling temperature difference ratio TCR, the load-temperature gradient matching degree LTM and the physical constraint conflict flag PCC;

[0044] Early warning module: assigns different weights to coupling features based on coupling strength to perform anomaly scoring, and issues multi-level early warnings based on the anomaly scores. A yellow warning is issued when the anomaly score is greater than a preset basic threshold, and a red warning is issued when the anomaly score is greater than a preset basic threshold and the number of physical constraint conflict flags (PCCs) that are 1 exceeds a preset threshold.

[0045] The anomaly scoring formula is:

[0046] ,

[0047] Among them, TCR represents the equipment-cooling temperature difference ratio, LTM represents the load-temperature gradient matching, PCC represents the number of physical constraint conflict flags set to 1, Score represents the anomaly score, and Weight represents the different weights assigned to the coupling features.

[0048] This application replaces the statistical model with physical mechanism rules and calculated coupling characteristics, which can directly reflect the physical coupling relationship between the equipment operating status and the cooling system, and improve the accuracy of the variable pitch drive overheating and cooling pump failure scenarios.

[0049] Based on the third aspect of the present application, a computer program product is further proposed, which has one or more computer programs thereon, and when the computer program is executed by a computer processor, implements any of the methods described above.

[0050] The technical effect of this application is that: this application performs high-precision anomaly detection through physical mechanism rules, directly reflects the physical coupling relationship between the equipment operating status and the cooling system through coupling characteristics, and directly associates the anomaly type and physical components through dynamic weight distribution. It can avoid the performance degradation of the fan caused by historical dependence, achieve accurate positioning of the root cause, reduce operation and maintenance investigation costs, filter out false alarms caused by sensor noise or short-term load fluctuations, reduce the false alarm rate, and improve accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Other features, objects and advantages of the present application will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings.

[0052] Figure 1 This is a flowchart of a method for detecting high temperature anomalies of a fan based on time series feature fusion according to an embodiment of the present application.

[0053] Figure 2 This is a module diagram of a fan high temperature anomaly detection system based on time series feature fusion provided according to an embodiment of the present application.

[0054] Figure 3 It is a structural diagram of a computer system suitable for implementing the electronic device of the embodiment of the present application. DETAILED DESCRIPTION

[0055] The present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the relevant invention and are not intended to limit the invention. It should also be noted that, for ease of description, only portions relevant to the relevant invention are shown in the accompanying drawings.

[0056] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0057] Figure 1 A method for detecting abnormal high temperature of a fan based on time series feature fusion is shown, comprising:

[0058] S1: Obtain Scada data of the fan group and perform downsampling processing, process the boundary instantaneous values ​​in the Scada data using a trend quantization method, and then smooth the high-frequency noise through a moving average filter to extract the temperature characteristics and operating status characteristics of the Scada data;

[0059] S2: Dividing the Scada data into a generator temperature control module, a cooling system module, an electrical load module, and a mechanical state module, and associating the temperature characteristics and operating state characteristics of the Scada data with physical mechanism rules to perform mechanism modeling;

[0060] S3: combining mechanism modeling or calculation to obtain coupling characteristics of the Scada data, wherein the coupling characteristics include the equipment-cooling temperature difference ratio TCR, the load-temperature gradient matching degree LTM, and the physical constraint conflict flag PCC;

[0061] S4: assigning different weights to coupling features based on coupling strength to perform anomaly scoring, and performing multi-level warnings based on the anomaly scores. A yellow warning is issued when the anomaly score is greater than a preset basic threshold, and a red warning is issued when the anomaly score is greater than the preset basic threshold and the number of physical constraint conflict flags (PCC) that are 1 exceeds a preset number threshold.

[0062] The anomaly scoring formula is:

[0063] ,

[0064] Among them, TCR represents the equipment-cooling temperature difference ratio, LTM represents the load-temperature gradient matching, PCC represents the number of physical constraint conflict flags set to 1, Score represents the anomaly score, and Weight represents the different weights assigned to the coupling features.

[0065] It should be noted that the temperature characteristics include pitch drive temperature, ambient temperature, water-cooling outlet valve water temperature, water-cooling inlet valve water temperature, nacelle temperature, generator bearing temperature and hub temperature;

[0066] The operating status characteristics include pump status and fan status.

[0067] It should be noted that step S1 also includes filtering the Scada data whose temperature characteristics exceed the physical limit threshold, cleaning the Scada data with logical conflicts, replacing missing values ​​with the mean of the Scada data, and performing sliding window time series processing on the Scada data.

[0068] It should be noted that the calculation formula of the equipment-cooling temperature difference ratio TCR is:

[0069] ,

[0070] Where TCR represents the equipment-cooling temperature difference ratio, Indicates the temperature of key equipment, Indicates the corresponding cooling medium temperature, Indicates a minimum value.

[0071] It should be noted that the calculation formula of the load-temperature gradient matching degree LTM is:

[0072] ,

[0073] Where LTM represents the load-temperature gradient matching, Indicates that the device is The temperature change within the window, Indicates the change in load power, Indicates a minimum value.

[0074] It should be noted that when the load-temperature gradient matching degree LTM>0.5, the temperature rises too quickly, exceeding the load expectation, triggering the physical mechanism rule; the device-cooling temperature difference ratio TCR suddenly increases by more than twice or rises for three consecutive windows, and the heat dissipation efficiency decreases, triggering the physical mechanism rule.

[0075] It should be noted that the physical constraint conflict flag PCC is defined based on the system physical mechanism rules, including:

[0076] If the generator front bearing temperature is higher than the preset front bearing temperature threshold, and the difference between the inner ring temperature and the outer ring temperature of the generator front bearing or the generator rear bearing exceeds the preset bearing temperature difference threshold, the physical constraint conflict flag PCC is 1;

[0077] If the water temperature at the water-cooling outlet valve is higher than the preset water-cooling temperature threshold, and the temperature difference between the water temperature at the water-cooling outlet valve and the water temperature at the water-cooling inlet valve exceeds the preset water-cooling temperature difference threshold, the cooling system efficiency decreases, and the physical constraint conflict flag PCC is 1;

[0078] If the ambient temperature is higher than the temperature threshold of the high temperature weather warning line, and the cabin temperature is higher than the preset forced ventilation failure threshold, then there is an ambient or cabin temperature anomaly, and the physical constraint conflict flag PCC is 1;

[0079] Otherwise, the physical constraint conflict flag PCC is 0.

[0080] It should be noted that the Scada data is divided into a generator temperature control module, a cooling system module, an electrical load module and a mechanical status module, specifically:

[0081] The generator temperature control module includes the generator front bearing temperature, the generator rear bearing temperature, the generator front bearing inner ring temperature and the generator front bearing outer ring temperature;

[0082] The cooling system module includes the water temperature of the water cooling outlet valve, the water temperature of the water cooling inlet valve, the pump status and the fan status;

[0083] The electrical load module includes converter active power and generator speed;

[0084] The mechanical status module includes hydraulic system pressure and bearing vibration amplitude.

[0085] It should be noted that assigning different weights to coupling features based on the coupling strength includes:

[0086] If the current window triggers two or more physical mechanism rules, a high weight is assigned to the coupling feature;

[0087] If the current window triggers a physical mechanism rule, a medium weight is assigned to the coupling feature;

[0088] If the physical mechanism rule is not triggered in the current window, a low weight is assigned to the coupling feature.

[0089] It should be noted that the core equipment includes a pitch drive and a generator bearing. The triggering of two physical mechanism rules includes a sudden increase in the equipment-cooling temperature difference ratio TCR and a physical constraint conflict flag PCC greater than or equal to 1. The triggering of one physical mechanism rule means that one of the equipment-cooling temperature difference ratio TCR, the load-temperature gradient matching degree LTM and the physical constraint conflict flag PCC is triggered.

[0090] It should be noted that the values ​​of the high weight, medium weight and low weight decrease in sequence and are configured according to the site conditions and actual needs.

[0091] It should be noted that this application, based on a real-time health assessment method for the thermodynamic characteristics of industrial equipment, innovatively proposes a two-dimensional coupled analysis model combining the equipment-cooling temperature difference ratio (TCR) and the load-temperature gradient matching degree. The equipment-cooling temperature difference ratio (TCR) continuously quantifies the heat dissipation efficiency degradation characteristics by comparing the temperature gradient distribution at key nodes in the heat exchange system. The load-temperature gradient matching degree (LTM) constructs a time-domain criterion for the non-steady-state temperature rise trend based on the dynamic process detection of temperature change dynamics.

[0092] The two parameters work together to study the evolution law of thermal load of the core components of wind turbine rotating machinery. By extending the time-frequency dimension of the observation continuity window period, the early signs of thermal anomalies of the equipment are captured without the intervention of prediction algorithms. Compared with the traditional thermal failure warning technology based on prediction models, this application significantly improves the reliability and timeliness of temperature-related fault warning by relying on the time series intrinsic analysis of SCADA data. It can provide early warning according to the characteristics of the event sequence when an abnormality is about to occur, and provides an innovative technical path based on forward monitoring for the preventive maintenance of the temperature of the core components of wind turbines, which is a significant improvement.

[0093] It should be noted that this application replaces the statistical model with the coupling characteristics obtained through physical mechanism rules and calculations, which can directly reflect the physical coupling relationship between the equipment operating status and the cooling system, improve the accuracy of the variable pitch drive overheating and cooling pump failure scenarios, and use the coupling characteristics to predict the decline in heat dissipation efficiency in advance before the temperature reaches the absolute threshold, thereby avoiding fault escalation.

[0094] It should be noted that by detecting physically infeasible events and removing data that violates basic laws, we can extract physically credible, logically self-consistent, and temporally coherent information flows, providing high-quality input for subsequent analysis and improving the reliability of subsequent analysis.

[0095] It should be noted that by dynamically allocating weights to associate abnormality types with physical components, the root cause can be accurately located, which can reduce the troubleshooting costs for operation and maintenance personnel.

[0096] It should be noted that by defining coupling characteristics, the physical nature of the equipment's heat dissipation efficiency and the load temperature rise relationship can be directly mapped, and the status of the mechanical and electrical systems can be traced, solving the problem that the statistical characteristics of traditional methods have no actual physical meaning; the dynamic window mechanism improves the sensitivity to transient anomalies and can avoid the response delay of fixed windows to emergencies.

[0097] It should be noted that the physical mechanism rules include:

[0098] In the generator temperature control module, the generator temperature is positively correlated with the generator speed. When the generator is hot, the lubricating oil becomes thinner, the friction decreases, and the generator speed increases. When the generator temperature drops, the lubricating oil becomes thicker, the friction increases, and the generator speed decreases.

[0099] In the cooling system module, when the generator temperature rises, the water temperature of the water cooling outlet valve rises and the pump and fan are activated;

[0100] In the electrical load module, when the converter active power or generator speed is too high, the temperature of key components that are closely related to the cooling system efficiency can be controlled;

[0101] In the mechanical status module, the bearing temperature is inversely proportional to the bearing vibration amplitude, and the heat dissipation efficiency decreases when the hydraulic system pressure is abnormal.

[0102] In a specific embodiment, for abnormal generator front bearing temperature, the system makes the following judgment: During window period 1 (08:00:00-08:00:30), the Scada data is shown in Table 1. The front bearing temperature of the key equipment generator rises from an initial 30°C to 34°C, with a temperature change of 4°C and an average of 32°C. The corresponding cooling medium temperature (average water-cooled outlet valve temperature) is 28°C, with a minimum value of 0.01. The converter active power change is 100 kW.

[0103] Calculate the coupling characteristics of Scada data, the equipment-cooling temperature difference ratio TCR = 32 / (28+0.01) = 1.14, according to the linear regression slope formula The calculated linear regression slope is 0.14°C / s, with no obvious sudden increase, which is consistent with the steady-state temperature rise;

[0104] Load-temperature gradient matching LTM=4 / 100=0.04;

[0105] The average temperature of the generator front bearing is 32°C, which is lower than the preset bearing temperature threshold of 45°C. The temperature difference between the inner and outer rings of the generator front bearing is 15°C, which is lower than the preset bearing temperature difference threshold of 20°C. The physical constraint conflict flag PCC = 0.

[0106] The average water temperature at the water-cooling outlet valve is 28°C, which is lower than the preset water-cooling temperature threshold of 40°C. The temperature difference between the water-cooling outlet valve temperature and the water-cooling inlet valve temperature is 6°C, which is higher than the preset water-cooling temperature difference threshold of 5°C. The physical constraint conflict flag PCC = 0.

[0107] The average ambient temperature is 25°C, the high temperature warning threshold is 35°C, the cabin temperature is 35°C, the forced ventilation failure threshold is 50°C, and the ambient and cabin temperatures are lower than the preset thresholds, then the physical constraint conflict flag PCC = 0;

[0108] The physical mechanism rule is not triggered in the current window, and the weight assigned to the coupling feature is 0.1. The anomaly score of window period 1 is 0.1×(1.14+0.04+0)=0.118;

[0109] Table 1: Scada data for window period 1

[0110]

[0111] The generator Scada data for window period 2 (08:00:10-08:00:40) is shown in Table 2. The temperature of the key equipment generator rose from the initial 34°C to 61°C, with a temperature change of 27°C and an average of 47.5°C. The corresponding cooling medium temperature (average water-cooled outlet valve temperature) had an average of 41°C, a minimum of 0.01, and a power change of 100 kW.

[0112] Calculating the coupling characteristics of the Scada data, the device-cooling temperature difference ratio (TCR) was 47.5 / (41+0.01) = 1.16, which represents a 1.02-fold increase relative to window period 1. This is less than twice the preset increase threshold, and the physical mechanism rule was not triggered.

[0113] The load-temperature gradient matching degree LTM = 27 / 100 ≈ 0.27, which is less than the preset warning threshold of 0.5 and does not trigger the physical mechanism rule;

[0114] The average temperature of the generator front bearing is 47.5°C, which is higher than the preset front bearing temperature threshold of 45°C. The temperature difference between the inner and outer rings of the generator front bearing is 25°C, which is higher than the preset bearing temperature difference threshold of 20°C. The physical constraint conflict flag PCC = 1.

[0115] The average water temperature at the water cooling outlet valve is 41°C, which is higher than the preset water cooling temperature threshold of 40°C. The temperature difference between the water cooling outlet valve temperature and the water cooling inlet valve temperature is 13°C, which is higher than the preset water cooling temperature difference threshold of 5°C. The physical constraint conflict flag PCC = 1.

[0116] The average ambient temperature is 25°C, the high temperature warning threshold is 35°C, the cabin temperature is 35°C, the forced ventilation failure threshold is 50°C, and the ambient and cabin temperatures are lower than the preset thresholds, then the physical constraint conflict flag PCC = 0;

[0117] The current window triggers only one physical mechanism rule, the weight assigned to the coupling feature is 0.3, and the anomaly score is 0.3×(1.16+0.27+2)=1.029;

[0118] Table 2: Scada data for window period 2

[0119]

[0120] In window period 3 (08:00:20-08:00:50), the Scada data are shown in Table 3. The temperature of the key equipment generator rose from the initial 42°C to 72°C, with a temperature change of 30°C and an average of 57°C. The corresponding cooling medium temperature (water-cooled outlet valve water temperature) had an average of 45°C, a minimum of 0.01, and a power change of 30KW.

[0121] Calculating the coupling characteristics of the Scada data, the device-cooling temperature difference ratio TCR = 57 / (45+0.01) = 1.27, which increased by 1.09 times compared to window period 2. However, after three consecutive windows of increase, the heat dissipation efficiency decreased, triggering the physical mechanism rules;

[0122] Load-temperature gradient matching LTM=30 / 30=1>0.5, triggering the physical mechanism rule;

[0123] The generator front bearing temperature is 57°C, which is higher than the preset front bearing temperature threshold of 45°C. The temperature difference between the inner and outer rings of the generator front bearing is 25°C, which is higher than the preset bearing temperature difference threshold of 20°C. The physical constraint conflict flag PCC = 1.

[0124] The average water temperature at the water-cooling outlet valve is 45°C, which is higher than the preset water-cooling temperature threshold of 40°C. The temperature difference between the water-cooling outlet valve temperature and the water-cooling inlet valve temperature is 7°C, which is higher than the preset water-cooling temperature difference threshold of 5°C. The physical constraint conflict flag PCC = 1.

[0125] The average ambient temperature is 36°C, the high temperature warning threshold is 35°C, the cabin temperature is 55°C, and the forced ventilation failure threshold is 50°C. If both the ambient temperature and the cabin temperature are higher than the preset thresholds, the physical constraint conflict flag PCC = 1.

[0126] The current window triggers the three physical mechanism rules of the core device, assigns a weight of 0.6 to the coupling feature, and the anomaly score is 0.6×(1.27+1+3)=3.162;

[0127] Table 3: Scada data for window period 3

[0128]

[0129] Assume that the preset baseline threshold is 4, and the anomaly score within the three window periods is 4.309, which is greater than the preset baseline threshold and the number threshold of 3 where the preset physical constraint conflict flag PCC is 1, triggering a red alert.

[0130] Reference below Figure 2 , Figure 2A fan high temperature anomaly detection system based on time series feature fusion is shown, which includes a data processing module a, a mechanism modeling module b, a coupling module c and an early warning module d.

[0131] In a specific embodiment, the data processing module a is configured to: obtain the Scada data of the fan group for downsampling processing, process the boundary instantaneous values ​​in the Scada data through a trend quantification method, and then smooth the high-frequency noise through a moving average filter to extract the temperature characteristics and operating status characteristics of the Scada data.

[0132] In a specific embodiment, the mechanism modeling module b is configured to: divide the Scada data into a generator temperature control module, a cooling system module, an electrical load module and a mechanical state module, and associate the temperature characteristics and operating state characteristics of the Scada data with physical mechanism rules to perform mechanism modeling.

[0133] In a specific embodiment, the coupling module c is configured to: combine mechanism modeling or calculation to obtain the coupling characteristics of the Scada data, wherein the coupling characteristics include the equipment-cooling temperature difference ratio TCR, the load-temperature gradient matching degree LTM and the physical constraint conflict mark PCC.

[0134] In a specific embodiment, the early warning module d is configured to: assign different weights to the coupling features based on the coupling strength to perform anomaly scoring, and perform multi-level early warning based on the anomaly score. When the anomaly score is greater than a preset basic threshold, a yellow early warning is performed; when the anomaly score is greater than the preset basic threshold and the number of the physical constraint conflict flag PCC is 1 exceeds a preset number threshold, a red early warning is performed;

[0135] The anomaly scoring formula is:

[0136] ,

[0137] Among them, TCR represents the equipment-cooling temperature difference ratio, LTM represents the load-temperature gradient matching, PCC represents the number of physical constraint conflict flags set to 1, Score represents the anomaly score, and Weight represents the different weights assigned to the coupling features.

[0138] It should be noted that the present application performs high-precision anomaly detection through physical mechanism rules, directly reflects the physical coupling relationship between the equipment operating status and the cooling system through coupling characteristics, and directly associates the anomaly type and physical components through dynamic weight distribution. It can avoid the performance degradation of the fan caused by historical dependence, accurately locate the root cause, reduce operation and maintenance investigation costs, filter out false alarms caused by sensor noise or short-term load fluctuations, reduce the false alarm rate, and improve accuracy.

[0139] It should be noted that the window length and threshold benchmark of this application are adjusted according to the real-time working conditions, which can avoid performance degradation caused by historical dependence, reversely locate the specific fault location through weight combination, and directly map the anomaly to the operation and maintenance action.

[0140] It should be noted that this application, based on a real-time health assessment method for the thermodynamic characteristics of industrial equipment, innovatively proposes a two-dimensional coupled analysis model combining the equipment-cooling temperature difference ratio (TCR) and the load-temperature gradient matching degree. The equipment-cooling temperature difference ratio (TCR) continuously quantifies the heat dissipation efficiency degradation characteristics by comparing the temperature gradient distribution at key nodes in the heat exchange system. The load-temperature gradient matching degree (LTM) constructs a time-domain criterion for the non-steady-state temperature rise trend based on the dynamic process detection of temperature change dynamics.

[0141] The two parameters work together to study the evolution law of thermal load of the core components of wind turbine rotating machinery. By extending the time-frequency dimension of the observation continuity window period, the early signs of thermal anomalies of the equipment are captured without the intervention of prediction algorithms. Compared with the traditional thermal failure warning technology based on prediction models, this application significantly improves the reliability and timeliness of temperature-related fault warning by relying on the time series intrinsic analysis of SCADA data. It can provide early warning according to the characteristics of the event sequence when an abnormality is about to occur, and provides an innovative technical path based on forward monitoring for the preventive maintenance of the temperature of the core components of wind turbines. This is one of the innovations of this application.

[0142] Reference below Figure 3 , which shows a structural diagram of a computer system suitable for implementing an electronic device of an embodiment of the present application. Figure 3 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0143] like Figure 3 As shown, the computer system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 302 or programs loaded from a storage unit 308 into a random access memory (RAM) 303. Various programs and data required for system operation are also stored in RAM 303. CPU 301, ROM 302, and RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0144] The following components are connected to the I / O interface 305: an input section 306 including a keyboard, mouse, and the like; an output section 307 including devices such as a liquid crystal display (LCD) and speakers; a storage section 308 including devices such as a hard disk; and a communication section 309 including a network interface card such as a LAN card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the media can be installed in the storage section 308 as needed.

[0145] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for executing the method illustrated in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via the communication portion 309 and / or installed from removable media 311. When executed by the central processing unit (CPU) 301, the computer program performs the functions defined in the methods of this application. It should be noted that the computer-readable storage medium of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this application, a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such a propagated data signal may take various forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0146] Computer program code for performing the operations of the present application can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0147] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0148] The modules described in the embodiments of the present application may be implemented by software or hardware.

[0149] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains Scada data of the wind turbine group and performs downsampling processing, processes the boundary instantaneous values ​​in the Scada data using a trend quantification method, and then smoothes high-frequency noise using a moving average filter to extract the temperature characteristics and operating status characteristics of the Scada data; divides the Scada data into a generator temperature control module, a cooling system module, an electrical load module, and a mechanical status module, and associates the temperature characteristics and operating status characteristics of the Scada data with physical mechanism rules to perform mechanism modeling. Combined with mechanism modeling or calculation, coupling characteristics of the Scada data are obtained, wherein the coupling characteristics include a device-cooling temperature difference ratio (TCR), a load-temperature gradient matching degree (LTM), and a physical constraint conflict flag (PCC); assigns different weights to the coupling characteristics based on the coupling strength to perform anomaly scoring, and performs multi-level warnings based on the anomaly scores. When the anomaly score is greater than a preset basic threshold, a yellow warning is issued. When the anomaly score is greater than the preset basic threshold and the number of physical constraint conflict flags (PCC) that are 1 exceeds a preset number threshold, a red warning is issued.

[0150] Finally, it should be noted that the above description is merely a preferred embodiment of this application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention herein is not limited to technical solutions formed by specific combinations of the aforementioned technical features. It also encompasses other technical solutions formed by any combination of the aforementioned technical features or their equivalents, without departing from the aforementioned inventive concept. For example, a technical solution formed by replacing the aforementioned features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for detecting high temperature anomalies of a fan based on time series feature fusion, characterized in that: include: S1: Obtain Scada data of the fan group and perform downsampling processing, process the boundary instantaneous values ​​in the Scada data using a trend quantization method, and then smooth the high-frequency noise through a moving average filter to extract the temperature characteristics and operating status characteristics of the Scada data; S2: Dividing the Scada data into a generator temperature control module, a cooling system module, an electrical load module, and a mechanical state module, and associating the temperature characteristics and operating state characteristics of the Scada data with physical mechanism rules to perform mechanism modeling; S3: combining mechanism modeling or calculation to obtain coupling characteristics of the Scada data, wherein the coupling characteristics include the equipment-cooling temperature difference ratio TCR, the load-temperature gradient matching degree LTM, and the physical constraint conflict flag PCC; S4: assigning different weights to coupling features based on coupling strength to perform anomaly scoring, and performing multi-level warnings based on the anomaly scores. A yellow warning is issued when the anomaly score is greater than a preset basic threshold, and a red warning is issued when the anomaly score is greater than the preset basic threshold and the number of physical constraint conflict flags (PCC) that are 1 exceeds a preset number threshold. The anomaly scoring formula is: Among them, TCR represents the equipment-cooling temperature difference ratio, LTM represents the load-temperature gradient matching degree, PCC represents the number of physical constraint conflict flags set to 1, Score represents the anomaly score, and Weight represents the different weights assigned to the coupling features; The calculation formula of the equipment-cooling temperature difference ratio TCR is: Where TCR represents the equipment-cooling temperature difference ratio, T device Indicates the temperature of key equipment, T cooling represents the corresponding cooling medium temperature, ∈ represents the minimum value; The calculation formula of the load-temperature gradient matching degree LTM is: Where LTM represents the load-temperature gradient matching, ΔT j Indicates the temperature change of the device within the j window, P load Represents the load power change, ∈ represents the minimum value; Defining the physical constraint conflict flag PCC based on the system physical mechanism rules includes: If the generator front bearing temperature is higher than the preset front bearing temperature threshold, and the difference between the inner ring temperature and the outer ring temperature of the generator front bearing or the generator rear bearing exceeds the preset bearing temperature difference threshold, the physical constraint conflict flag PCC is 1; If the water temperature at the water-cooling outlet valve is higher than the preset water-cooling temperature threshold, and the temperature difference between the water temperature at the water-cooling outlet valve and the water temperature at the water-cooling inlet valve exceeds the preset water-cooling temperature difference threshold, the cooling system efficiency decreases, and the physical constraint conflict flag PCC is 1; If the ambient temperature is higher than the temperature threshold of the high temperature weather warning line, and the cabin temperature is higher than the preset forced ventilation failure threshold, then there is an ambient or cabin temperature anomaly, and the physical constraint conflict flag PCC is 1; Otherwise, the physical constraint conflict flag PCC is 0.

2. The method according to claim 1, characterized in that The temperature characteristics include pitch drive temperature, ambient temperature, water-cooling outlet valve water temperature, water-cooling inlet valve water temperature, nacelle temperature, generator bearing temperature and hub temperature; The operating status characteristics include pump status and fan status.

3. The method according to claim 1, characterized in that Step S1 also includes filtering the Scada data whose temperature characteristics exceed the physical limit threshold, cleaning the Scada data with logical conflicts, replacing missing values ​​with the mean of the Scada data, and performing sliding window time series processing on the Scada data.

4. The method according to claim 1, wherein The Scada data is divided into a generator temperature control module, a cooling system module, an electrical load module and a mechanical status module, specifically: The generator temperature control module includes the generator front bearing temperature, the generator rear bearing temperature, the generator front bearing inner ring temperature and the generator front bearing outer ring temperature; The cooling system module includes the water temperature of the water cooling outlet valve, the water temperature of the water cooling inlet valve, the pump status and the fan status; The electrical load module includes converter active power and generator speed; The mechanical status module includes hydraulic system pressure and bearing vibration amplitude.

5. The method according to claim 1, wherein Assigning different weights to coupling features based on the coupling strength includes: If the current window triggers two or more physical mechanism rules, a high weight is assigned to the coupling feature; If the current window triggers a physical mechanism rule, a medium weight is assigned to the coupling feature; If the physical mechanism rule is not triggered in the current window, a low weight is assigned to the coupling feature.

6. A fan high temperature anomaly detection system based on time series feature fusion, characterized in that: include: Data processing module: obtains the Scada data of the fan group and performs downsampling processing, processes the boundary instantaneous values ​​in the Scada data using the trend quantization method, and then smoothes the high-frequency noise through moving average filtering to extract the temperature characteristics and operating status characteristics of the Scada data; Mechanism modeling module: divides the Scada data into a generator temperature control module, a cooling system module, an electrical load module, and a mechanical state module, and associates the temperature characteristics and operating state characteristics of the Scada data with physical mechanism rules to perform mechanism modeling; Coupling module: Combined with mechanism modeling or calculation to obtain the coupling characteristics of the Scada data, the coupling characteristics include the equipment-cooling temperature difference ratio TCR, the load-temperature gradient matching degree LTM and the physical constraint conflict flag PCC; Early warning module: assigns different weights to coupling features based on coupling strength to perform anomaly scoring, and issues multi-level early warnings based on the anomaly scores. A yellow warning is issued when the anomaly score is greater than a preset basic threshold, and a red warning is issued when the anomaly score is greater than a preset basic threshold and the number of physical constraint conflict flags (PCCs) that are 1 exceeds a preset threshold. The anomaly scoring formula is: Among them, TCR represents the equipment-cooling temperature difference ratio, LTM represents the load-temperature gradient matching degree, PCC represents the number of physical constraint conflict flags set to 1, Score represents the anomaly score, and Weight represents the different weights assigned to the coupling features; The calculation formula of the equipment-cooling temperature difference ratio TCR is: Where TCR represents the equipment-cooling temperature difference ratio, T device Indicates the temperature of key equipment, T cooling represents the corresponding cooling medium temperature, ∈ represents the minimum value; The calculation formula of the load-temperature gradient matching degree LTM is: Where LTM represents the load-temperature gradient matching, ΔT j Indicates the temperature change of the device within the j window, P load Represents the load power change, ∈ represents the minimum value; Defining the physical constraint conflict flag PCC based on the system physical mechanism rules includes: If the generator front bearing temperature is higher than the preset front bearing temperature threshold, and the difference between the inner ring temperature and the outer ring temperature of the generator front bearing or the generator rear bearing exceeds the preset bearing temperature difference threshold, the physical constraint conflict flag PCC is 1; If the water temperature at the water-cooling outlet valve is higher than the preset water-cooling temperature threshold, and the temperature difference between the water temperature at the water-cooling outlet valve and the water temperature at the water-cooling inlet valve exceeds the preset water-cooling temperature difference threshold, the cooling system efficiency decreases, and the physical constraint conflict flag PCC is 1; If the ambient temperature is higher than the temperature threshold of the high temperature weather warning line, and the cabin temperature is higher than the preset forced ventilation failure threshold, then there is an ambient or cabin temperature anomaly, and the physical constraint conflict flag PCC is 1; Otherwise, the physical constraint conflict flag PCC is 0.

7. A computer program product having one or more computer programs thereon, characterized in that: When the computer program is executed by a computer processor, the method according to any one of claims 1 to 5 is implemented.

Images