Infrared thermal imager and intelligent fault diagnosis method based on multi-level thermal image analysis

Abstract

The application discloses an infrared thermal imager and an intelligent fault diagnosis method based on multi-level thermal image analysis, and relates to the technical field of infrared thermal imagers, comprising a multi-level temperature data acquisition module, an intelligent temperature data processing module and an intelligent fault diagnosis and early warning module. The application can obtain more comprehensive and accurate temperature information by simultaneously collecting surface layer, deep layer and transient temperature data of the monitored object, thereby improving monitoring accuracy. The intelligent temperature data processing module effectively fuses temperature data of different levels to generate more accurate comprehensive temperature maps, providing a reliable data basis for subsequent analysis. The intelligent fault diagnosis and early warning module automatically identifies and matches fault characteristics by establishing a fault mode model, reducing dependence on artificial experience and improving fault diagnosis efficiency and accuracy. It can monitor temperature changes in real time and warn potential faults, and through accurate fault diagnosis, more effective maintenance plans can be developed to reduce unnecessary downtime and maintenance costs.

Description

Technical Field

[0001] This invention relates to the field of infrared thermal imager technology, and in particular to an infrared thermal imager based on multi-level thermal image analysis and an intelligent fault diagnosis method. Background Technology

[0002] Infrared thermal imagers are increasingly used in equipment temperature monitoring and fault diagnosis. However, traditional infrared imaging data is mostly based on single-layer temperature data processing, making it difficult to obtain accurate temperature change information.

[0003] Meanwhile, most existing fault diagnosis methods rely on manual identification, which cannot meet the needs of real-time monitoring and automatic fault early warning. Therefore, high-precision infrared thermal imagers based on multi-level temperature data analysis and automated fault diagnosis have significant application value. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides an infrared thermal imager based on multi-level thermal imaging analysis and an intelligent fault diagnosis method. The technical solution adopted is as follows:

[0005] An infrared thermal imager based on multi-level thermal imaging analysis includes a multi-level temperature data acquisition module, an intelligent temperature data processing module, and an intelligent fault diagnosis and early warning module. The multi-level temperature data acquisition module includes a surface temperature acquisition unit, a deep temperature detection unit, and a transient temperature analysis unit. The surface temperature acquisition unit captures the surface temperature data of the monitored object using a high-resolution infrared sensor. The deep temperature detection unit acquires temperature data of the depths below the surface of the monitored object based on pulsed thermal excitation and thermal diffusion analysis technology. The data input terminal of the transient temperature analysis unit is communicatively connected to the data output terminals of the surface temperature acquisition unit and the deep temperature detection unit, respectively, to acquire surface temperature data and deep temperature data of the monitored object, analyze the rate of temperature rise or fall through time series analysis of temperature changes, and output transient temperature data.

[0006] The intelligent temperature data processing module is communicatively connected to the transient temperature analysis unit. It analyzes and integrates surface temperature data, deep temperature data, and transient temperature data through a multi-level data processing algorithm, outputs multi-level temperature data analysis results, and generates a comprehensive temperature map based on the multi-level temperature data analysis results.

[0007] The intelligent fault diagnosis and early warning module is connected to the intelligent temperature data processing module. It extracts fault-related temperature features from the multi-level temperature data analysis results. The temperature features include abrupt change points, abnormal temperature areas, and temperature difference fluctuations. It uses machine learning algorithms to establish a pattern model of known fault types to identify and match fault feature data. If a fault is successfully identified and matched, a fault alarm is triggered.

[0008] By employing the above technical solutions, and simultaneously acquiring surface, deep, and transient temperature data of the monitored object, more comprehensive and accurate temperature information can be obtained, improving monitoring accuracy. High-resolution infrared sensors ensure the resolution and detail of surface temperature data, aiding in the identification of minute temperature differences. Utilizing pulsed thermal excitation and thermal diffusion analysis techniques, the internal temperature conditions of the object can be detected, which is particularly important for diagnosing internal defects or faults. The intelligent temperature data processing module can quickly identify temperature anomalies by analyzing the rate of temperature change, providing crucial clues for fault diagnosis. It can effectively fuse temperature data from different levels to generate a more accurate comprehensive temperature map, providing a reliable data foundation for subsequent analysis.

[0009] The intelligent fault diagnosis and early warning module can automatically identify and match fault characteristics by establishing fault mode models, reducing reliance on human experience and improving the efficiency and accuracy of fault diagnosis.

[0010] The system can monitor temperature changes in real time and provide early warnings of potential faults, helping to take timely measures to prevent accidents. Accurate fault diagnosis allows for the development of more effective maintenance plans, reducing unnecessary downtime and maintenance costs.

[0011] Infrared thermal imagers based on multi-level thermal imaging analysis are suitable for temperature monitoring and fault diagnosis of various industrial equipment. They can be used to detect heat loss areas in buildings, optimize energy use, provide real-time temperature monitoring in high-risk environments, and enhance operational safety.

[0012] Optionally, it also includes a visualization multi-layer temperature image generation module, which includes a visualization data storage unit, a graphics processing unit, and a display. The visualization data storage unit is communicatively connected to the intelligent temperature data processing module to collect surface temperature data, deep temperature data, and transient temperature data. The graphics processing unit outputs multi-layer temperature image data, and the display is communicatively connected to the graphics processing unit.

[0013] By adopting the above technical solution, the graphics processing unit generates a comprehensive multi-layer temperature image by fusing temperature data at different levels, thereby achieving an intuitive display of temperature distribution.

[0014] Color coding and layered display function: Different temperature levels are displayed with different color codes, and the temperature distribution is shown through the changes in the depth of the image colors.

[0015] Color coding helps users quickly identify abnormal temperature areas, while the layered display function can show surface and deep temperature information separately, making it easier for users to observe the distribution and changes in temperature more clearly.

[0016] Zoom and focus viewing features: Users can zoom in and out of the temperature image and select the focus to observe temperature changes in a specific area.

[0017] Zoom and focus features help users examine detailed temperature changes in fault hotspots or potential risk areas, thereby more effectively locating the source of the fault and improving analysis efficiency.

[0018] Optionally, the surface temperature acquisition unit includes an infrared lens, an infrared sensor, and a sensor driving circuit. The infrared lens receives infrared radiation emitted by the monitored object, focuses the infrared radiation, and transmits it to the infrared sensor. The data output terminal of the infrared sensor is communicatively connected to the transient temperature analysis unit. The sensor driving circuit is communicatively connected to the infrared sensor and is used to control the working state of the infrared sensor.

[0019] By adopting the above technical solution, the infrared lens receives the infrared radiation emitted by the monitored object, focuses the infrared radiation and transmits it to the infrared sensor. The infrared sensor adopts a high-resolution infrared sensor to capture the temperature data of the surface of the monitored object in real time and generate a clear surface thermal map.

[0020] The surface temperature acquisition unit can quickly respond to changes in surface temperature, making it suitable for real-time monitoring of scenarios with high temperature differences or sudden temperature fluctuations. For example, when the surface temperature of mechanical equipment rises rapidly, this unit can detect the thermal change and generate an alarm.

[0021] Optionally, the deep temperature detection unit includes a laser pulse generator, a high-sensitivity thermocouple, and a signal amplification and filtering circuit. The laser pulse generator is used to thermally excite the monitored object. The high-sensitivity thermocouple is used to detect the temperature change of the monitored object after thermal excitation and is communicatively connected to the signal input terminal of the signal amplification and filtering circuit. The signal output terminal of the signal amplification and filtering circuit is communicatively connected to the transient temperature analysis unit.

[0022] By adopting the above technical solution, using pulsed thermal excitation and thermal diffusion analysis, a laser pulse generator is used to thermally excite the monitored object, and a high-sensitivity thermocouple is used to detect the temperature change of the monitored object after thermal excitation. Pulsed thermal excitation heats the surface layer through a short thermal pulse, detects the heat transfer process, and analyzes the deep temperature data.

[0023] The deep temperature detection unit can detect potential problems below the surface (such as hot spots caused by corrosion or cracks), making it particularly suitable for industrial equipment, building structures, and other similar applications. By analyzing the heat diffusion process, this unit can detect early-stage deep faults and provide early warnings of potential risks.

[0024] Optionally, the transient temperature analysis unit includes a high-speed multi-channel data acquisition card, a temperature data buffer, and a time series analysis processor. The data input terminal of the high-speed multi-channel data acquisition card is communicatively connected to the infrared sensor and the signal amplification and filtering circuit, respectively. The temperature data buffer is communicatively connected to the data output terminal of the high-speed multi-channel data acquisition card. The time series analysis processor is communicatively connected to the temperature data buffer. Based on the surface temperature data and deep temperature data of the monitored object, the time series analysis processor outputs transient temperature data through time series analysis of temperature changes.

[0025] By adopting the above technical solution, the time series analysis processor calculates the rate of temperature rise or fall through time series analysis of temperature changes, and identifies normal and abnormal temperature change patterns.

[0026] The transient temperature analysis unit identifies sudden temperature changes, such as rapid heating caused by motor overload or drastic temperature fluctuations caused by chemical reactions, by calculating the rate of temperature change. Transient temperature data, combined with surface and deep temperature data, provides a time-dimensional reference for accurate diagnosis.

[0027] Optionally, the intelligent temperature data processing module includes a data storage device, a data processor, and a graphics processor. The data storage device is communicatively connected to the time series analysis processor, and the data processor and the graphics processor are communicatively connected to the data storage device, respectively.

[0028] By employing the above technical solutions, the intelligent temperature data processing module uses a multi-level data processing algorithm to intelligently analyze and fuse temperature data from different levels, generating a high-precision comprehensive temperature map. The multi-level temperature separation algorithm separates surface, deep, and transient temperature data into layers, extracting temperature features at different depths and times. This algorithm effectively extracts and separates temperature data from each layer, ensuring that temperature information from each layer is not confused. For example, the algorithm can separate surface temperature changes caused by deep faults, avoiding misjudgments. Based on the thermal diffusion data from the deep temperature detection unit, the thermal diffusivity coefficient is calculated to analyze the rate of temperature transfer within the monitored object. The thermal diffusivity coefficient helps determine the diffusion trend and speed of temperature; for example, a sharp increase in the thermal diffusivity coefficient within a certain range may indicate deep-seated temperature anomalies or material problems. This function is particularly suitable for monitoring internal temperature changes in power equipment and industrial machinery. Finally, the surface, deep, and transient temperature data are intelligently synthesized to generate a comprehensive temperature map that integrates different temperature information. The data synthesis unit effectively fuses multi-layer temperature data, resulting in a comprehensive temperature map that includes both surface details and deep temperature change information, making it suitable for high-precision monitoring in complex environments.

[0029] Optionally, the intelligent fault diagnosis and early warning module includes an AI processor, an early warning signal output interface, and a communication interface, wherein the AI ​​processor is communicatively connected to the data storage, the early warning signal output interface, and the communication interface, respectively.

[0030] By adopting the above technical solution and analyzing multi-level temperature data, fault-related temperature characteristics are extracted, including abrupt change points, abnormal temperature areas, and temperature fluctuations.

[0031] The fault feature extraction unit identifies abnormal temperature change points, such as sudden temperature rises or abnormal heat diffusion rates, based on the temperature characteristics of multi-level data, providing effective preliminary data for fault mode identification.

[0032] By using machine learning algorithms such as support vector machines (SVM) and neural networks, pattern models of known fault types are established to identify and match fault feature data.

[0033] The fault mode recognition unit can quickly determine the fault type based on a machine learning model, automatically identifying whether it is a common fault (such as temperature rise caused by short circuits, mechanical friction, etc.), thus improving diagnostic speed. The unit's fault mode library can be learned and updated using historical data, further improving the accuracy and generalization ability of the recognition.

[0034] Based on the identified fault modes and characteristics, the early warning triggering unit sets multiple early warning levels, including prompts, warnings, and emergency alarms.

[0035] When the early warning triggering unit identifies potential fault characteristics, it triggers an alarm signal of the corresponding level and can be connected to a remote monitoring system or a smartphone APP to realize real-time push of fault information, ensuring that users can take timely countermeasures.

[0036] The fault diagnosis method based on multi-level thermal imaging analysis uses an infrared thermal imager based on multi-level thermal imaging analysis to diagnose faults in the monitored object, including the following steps:

[0037] Step 1: The time series analysis processor outputs transient temperature data by analyzing the surface temperature data and deep temperature data of temperature changes over time.

[0038] Step 2: The AI ​​processor analyzes the temperature characteristics of each layer of transient temperature data;

[0039] Step 3: The AI ​​processor calculates the thermal diffusivity and analyzes the rate of temperature transfer in the monitored object.

[0040] Step 4: The AI ​​processor extracts the fault characteristics of the monitored object based on the temperature characteristics and thermal diffusivity of each layer;

[0041] Step 5: Use machine learning algorithms to perform pattern recognition on the fault features, and match the extracted fault features with a known fault pattern database to output the fault pattern results.

[0042] Step 6: Based on the fault mode identification results, output the preset warning action command through the warning signal output interface and the communication interface.

[0043] Optionally, the formula for calculating the transient temperature data in step 1 is:

[0044] ;

[0045] in This is the transient temperature component, where t is time and x is location. This is the temperature data after applying a low-pass filter;

[0046] The formula for calculating the thermal diffusivity in step 3 is:

[0047] ;

[0048] in It is the thermal diffusivity. It is the change in temperature. It is a change over time;

[0049] In step 4, the formula for fault feature extraction is:

[0050] ;

[0051] Where G is the temperature gradient. and These are the partial derivatives of temperature in the x and y directions, respectively.

[0052] Optionally, the core formula of the machine algorithm in step 5 is:

[0053] ;

[0054] in These are Lagrange multipliers, where n is the number of samples. It is the class label of the i-th sample. It is a kernel function used to calculate the kernel values ​​of two sample points. and The inner product between them.

[0055] In summary, the present invention has at least one of the following beneficial technical effects:

[0056] This invention provides an infrared thermal imager and intelligent fault diagnosis method based on multi-level thermal imaging analysis. By simultaneously acquiring surface, deep, and transient temperature data of the monitored object, it can obtain more comprehensive and accurate temperature information, improving monitoring accuracy. A high-resolution infrared sensor ensures the resolution and detail of surface temperature data, helping to identify minute temperature differences. Pulsed thermal excitation and thermal diffusion analysis techniques are used to detect the internal temperature conditions of the object.

[0057] The intelligent temperature data processing module can effectively integrate temperature data from different levels to generate a more accurate comprehensive temperature map, providing a reliable data foundation for subsequent analysis.

[0058] The intelligent fault diagnosis and early warning module automatically identifies and matches fault characteristics by establishing a fault mode model, reducing reliance on human experience and improving the efficiency and accuracy of fault diagnosis.

[0059] The ability to monitor temperature changes in real time and provide early warnings of potential faults helps to take timely measures to prevent accidents. Accurate fault diagnosis allows for the development of more effective maintenance plans, reducing unnecessary downtime and maintenance costs.

[0060] Infrared thermal imagers based on multi-level thermal imaging analysis are suitable for temperature monitoring and fault diagnosis of various industrial equipment. They can be used to detect heat loss areas in buildings, optimize energy use, provide real-time temperature monitoring in high-risk environments, and enhance operational safety. Attached Figure Description

[0061] Figure 1 This is a schematic diagram of the electrical component connection principle of the infrared thermal imager based on multi-level thermal image analysis according to the present invention.

[0062] Figure 2 This is a flowchart illustrating the fault diagnosis method based on multi-level thermal imaging analysis of the present invention.

[0063] Figure labeling: 1. Temperature data acquisition module; 11. Surface temperature acquisition unit; 111. Infrared lens; 112. Infrared sensor; 113. Sensor driving circuit; 12. Deep temperature detection unit; 121. Laser pulse generator; 122. High-sensitivity thermocouple; 123. Signal amplification and filtering circuit; 13. Transient temperature analysis unit; 131. High-speed multi-channel data acquisition card; 132. Temperature data buffer; 133. Time series analysis processor; 2. Intelligent temperature data processing module; 21. Data storage; 22. Data processor; 23. Graphics processor; 3. Intelligent fault diagnosis and early warning module; 31. AI processor; 32. Early warning signal output interface; 33. Communication interface; 4. Visualized multi-layer temperature image generation module; 41. Visualized data storage; 42. Graphics processing unit; 43. Display. Detailed Implementation

[0064] The present invention will be further described in detail below with reference to the accompanying drawings.

[0065] This invention discloses an infrared thermal imager and an intelligent fault diagnosis method based on multi-level thermal imaging analysis.

[0066] Reference Figure 1 and Figure 2 Example 1: An infrared thermal imager based on multi-level thermal imaging analysis includes a multi-level temperature data acquisition module 1, an intelligent temperature data processing module 2, and an intelligent fault diagnosis and early warning module 3. The multi-level temperature data acquisition module 1 includes a surface temperature acquisition unit 11, a deep temperature detection unit 12, and a transient temperature analysis unit 13. The surface temperature acquisition unit 11 captures the surface temperature data of the monitored object through a high-resolution infrared sensor. The deep temperature detection unit 12 acquires the temperature data of the deep layers below the surface of the monitored object based on pulse thermal excitation and thermal diffusion analysis technology. The data input terminal of the transient temperature analysis unit 13 is communicatively connected to the data output terminals of the surface temperature acquisition unit 11 and the deep temperature detection unit 12, respectively, to acquire the surface temperature data and deep temperature data of the monitored object, analyze the rate of temperature rise or fall through time series analysis of temperature changes, and output transient temperature data.

[0067] The intelligent temperature data processing module 2 is connected to the transient temperature analysis unit 13. It analyzes and integrates surface temperature data, deep temperature data and transient temperature data through multi-level data processing algorithms, outputs multi-level temperature data analysis results, and generates a comprehensive temperature map based on the multi-level temperature data analysis results.

[0068] The intelligent fault diagnosis and early warning module 3 communicates with the intelligent temperature data processing module 2. It extracts fault-related temperature features from the multi-level temperature data analysis results. The temperature features include abrupt change points, abnormal temperature areas, and temperature difference fluctuations. It uses machine learning algorithms to establish a pattern model of known fault types to identify and match fault feature data. If a fault is successfully identified and matched, a fault alarm is triggered.

[0069] By simultaneously acquiring surface, deep, and transient temperature data of the monitored object, more comprehensive and accurate temperature information can be obtained, improving monitoring accuracy. High-resolution infrared sensors ensure the resolution and detail of surface temperature data, helping to identify minute temperature differences. Utilizing pulsed thermal excitation and thermal diffusion analysis techniques, the internal temperature conditions of the object can be detected, which is particularly important for diagnosing internal defects or faults. The intelligent temperature data processing module 2 can quickly identify temperature anomalies by analyzing the rate of temperature change, providing crucial clues for fault diagnosis. It can effectively fuse temperature data from different levels to generate a more accurate comprehensive temperature map, providing a reliable data foundation for subsequent analysis.

[0070] The intelligent fault diagnosis and early warning module 3 can automatically identify and match fault characteristics by establishing a fault mode model, reducing reliance on human experience and improving the efficiency and accuracy of fault diagnosis.

[0071] The system can monitor temperature changes in real time and provide early warnings of potential faults, helping to take timely measures to prevent accidents. Accurate fault diagnosis allows for the development of more effective maintenance plans, reducing unnecessary downtime and maintenance costs.

[0072] Infrared thermal imagers based on multi-level thermal imaging analysis are suitable for temperature monitoring and fault diagnosis of various industrial equipment. They can be used to detect heat loss areas in buildings, optimize energy use, provide real-time temperature monitoring in high-risk environments, and enhance operational safety.

[0073] Example 2 also includes a visualization multi-layer temperature image generation module 4. The visualization multi-layer temperature image generation module 4 includes a visualization data storage 41, a graphics processing unit 42, and a display 43. The visualization data storage 41 is communicatively connected to the intelligent temperature data processing module 2 to collect surface temperature data, deep temperature data, and transient temperature data. The graphics processing unit 42 outputs multi-layer temperature image data, and the display 43 is communicatively connected to the graphics processing unit 42.

[0074] The graphics processing unit 42 generates a comprehensive multi-layer temperature image by fusing temperature data at different levels, thereby achieving an intuitive display of temperature distribution.

[0075] Color coding and layered display function: Different temperature levels are displayed with different color codes, and the temperature distribution is shown through the changes in the depth of the image colors.

[0076] Color coding helps users quickly identify abnormal temperature areas, while the layered display function can show surface and deep temperature information separately, making it easier for users to observe the distribution and changes in temperature more clearly.

[0077] Zoom and focus viewing features: Users can zoom in and out of the temperature image and select the focus to observe temperature changes in a specific area.

[0078] Zoom and focus features help users examine detailed temperature changes in fault hotspots or potential risk areas, thereby more effectively locating the source of the fault and improving analysis efficiency.

[0079] Example 3: The surface temperature acquisition unit 11 includes an infrared lens 111, an infrared sensor 112, and a sensor driving circuit 113. The infrared lens 111 receives the infrared radiation emitted by the monitored object, focuses the infrared radiation, and transmits it to the infrared sensor 112. The data output terminal of the infrared sensor 112 is communicatively connected to the transient temperature analysis unit 13. The sensor driving circuit 113 is communicatively connected to the infrared sensor 112 and is used to control the working state of the infrared sensor 112.

[0080] Infrared lens 111 receives infrared radiation emitted by the monitored object, focuses the infrared radiation and transmits it to infrared sensor 112. Infrared sensor 112 uses a high-resolution infrared sensor to capture the temperature data of the surface of the monitored object in real time and generate a clear surface thermal map.

[0081] The surface temperature acquisition unit can quickly respond to changes in surface temperature, making it suitable for real-time monitoring of scenarios with high temperature differences or sudden temperature fluctuations. For example, when the surface temperature of mechanical equipment rises rapidly, this unit can detect the thermal change and generate an alarm.

[0082] Example 4: The deep temperature detection unit 12 includes a laser pulse generator 121, a high-sensitivity thermocouple 122, and a signal amplification and filtering circuit 123. The laser pulse generator 121 is used to thermally excite the monitored object. The high-sensitivity thermocouple 122 is used to detect the temperature change of the monitored object after thermal excitation and is communicatively connected to the signal input terminal of the signal amplification and filtering circuit 123. The signal output terminal of the signal amplification and filtering circuit 123 is communicatively connected to the transient temperature analysis unit 13.

[0083] Using pulsed thermal excitation and thermal diffusion analysis techniques, a laser pulse generator 121 is used to thermally excite the monitored object, and a high-sensitivity thermocouple 122 is used to detect the temperature change of the monitored object after thermal excitation. Pulsed thermal excitation heats the surface layer through a short thermal pulse, detects the heat transfer process, and analyzes the deep temperature data.

[0084] The deep temperature detection unit 12 can detect potential hazards below the surface (such as hot spots caused by corrosion or cracks), making it particularly suitable for industrial equipment, building structures, and other similar applications. By analyzing the heat diffusion process, this unit can detect early-stage deep faults and provide early warnings of potential risks.

[0085] Example 5: The transient temperature analysis unit 13 includes a high-speed multi-channel data acquisition card 131, a temperature data buffer 132, and a time series analysis processor 133. The data input terminal of the high-speed multi-channel data acquisition card 131 is communicatively connected to the infrared sensor 112 and the signal amplification and filtering circuit 123, respectively. The temperature data buffer 132 is communicatively connected to the data output terminal of the high-speed multi-channel data acquisition card 131. The time series analysis processor 133 is communicatively connected to the temperature data buffer 132. Based on the surface temperature data and deep temperature data of the monitored object, the time series analysis processor 133 outputs transient temperature data through time series analysis of temperature changes.

[0086] The time series analysis processor 133 calculates the rate of temperature rise or fall by performing time series analysis on temperature changes, and identifies normal and abnormal temperature change patterns.

[0087] The transient temperature analysis unit 13 identifies sudden temperature changes, such as rapid heating caused by motor overload or drastic temperature fluctuations caused by chemical reactions, by calculating the rate of temperature change. The transient temperature data, combined with surface and deep temperature data, provides a time-dimensional reference for accurate diagnosis.

[0088] Example 6: The intelligent temperature data processing module 2 includes a data storage 21, a data processor 22, and a graphics processor 23. The data storage 21 is communicatively connected to the time series analysis processor 133, and the data processor 22 and the graphics processor 23 are communicatively connected to the data storage 21, respectively.

[0089] The intelligent temperature data processing module 2 uses a multi-level data processing algorithm to intelligently analyze and fuse temperature data from different levels, generating a high-precision comprehensive temperature map. The multi-layer temperature separation algorithm separates surface, deep, and transient temperature data into layers, extracting temperature features at different depths and times. This algorithm effectively extracts and separates temperature data from each layer, ensuring that temperature information from each layer is not confused. For example, the algorithm can separate surface temperature changes caused by deep faults, avoiding misjudgments. Based on the thermal diffusion data from the deep temperature detection unit, the thermal diffusivity coefficient is calculated to analyze the rate of temperature transfer within the monitored object. The thermal diffusivity coefficient helps determine the diffusion trend and speed of temperature; for example, a sharp increase in the thermal diffusivity coefficient within a certain range may indicate deep-seated temperature anomalies or material problems. This function is particularly suitable for monitoring internal temperature changes in power equipment and industrial machinery. The surface, deep, and transient temperature data are intelligently synthesized to generate a comprehensive temperature map that integrates different temperature information. The data synthesis unit effectively fuses multi-layer temperature data, resulting in a comprehensive temperature map that includes both surface details and deep temperature change information, making it suitable for high-precision monitoring in complex environments.

[0090] Example 7: The intelligent fault diagnosis and early warning module 3 includes an AI processor 31, an early warning signal output interface 32, and a communication interface 33. The AI ​​processor 31 is communicatively connected to the data storage 21, the early warning signal output interface 32, and the communication interface 33, respectively.

[0091] By analyzing multi-level temperature data, fault-related temperature features are extracted, including abrupt change points, abnormal temperature regions, and temperature fluctuations.

[0092] The fault feature extraction unit identifies abnormal temperature change points, such as sudden temperature rises or abnormal heat diffusion rates, based on the temperature characteristics of multi-level data, providing effective preliminary data for fault mode identification.

[0093] By using machine learning algorithms such as support vector machines (SVM) and neural networks, pattern models of known fault types are established to identify and match fault feature data.

[0094] The fault mode recognition unit can quickly determine the fault type based on a machine learning model, automatically identifying whether it is a common fault (such as temperature rise caused by short circuits, mechanical friction, etc.), thus improving diagnostic speed. The unit's fault mode library can be learned and updated using historical data, further improving the accuracy and generalization ability of the recognition.

[0095] Based on the identified fault modes and characteristics, the early warning triggering unit sets multiple early warning levels, including prompts, warnings, and emergency alarms.

[0096] When the early warning triggering unit identifies potential fault characteristics, it triggers an alarm signal of the corresponding level and can be connected to a remote monitoring system or a smartphone APP to realize real-time push of fault information, ensuring that users can take timely countermeasures.

[0097] Example 8: A fault diagnosis method based on multi-level thermal imaging analysis, which uses an infrared thermal imager based on multi-level thermal imaging analysis to diagnose faults in the monitored object, includes the following steps:

[0098] Step 1: The time series analysis processor 133 outputs transient temperature data by analyzing the surface temperature data and deep temperature data of the temperature change over time.

[0099] Step 2: AI processor 31 analyzes the temperature characteristics of each layer of transient temperature data;

[0100] Step 3: The AI ​​processor 31 calculates the thermal diffusivity and analyzes the rate of temperature transfer in the monitored object.

[0101] Step 4: The AI ​​processor 31 extracts the fault characteristics of the monitored object based on the temperature characteristics and thermal diffusivity of each layer;

[0102] Step 5: Use machine learning algorithms to perform pattern recognition on the fault features, and match the extracted fault features with a known fault pattern database to output the fault pattern results.

[0103] Step 6: Based on the fault mode identification results, output the preset warning action command through the warning signal output interface 32 and the communication interface 33.

[0104] Example 9, the formula for calculating transient temperature data in step 1 is:

[0105] ;

[0106] in This is the transient temperature component, where t is time and x is location. This is the temperature data after applying a low-pass filter;

[0107] The formula for calculating the thermal diffusivity in step 3 is:

[0108] ;

[0109] in It is the thermal diffusivity. It is the change in temperature. It is a change over time;

[0110] In step 4, the formula for fault feature extraction is:

[0111] ;

[0112] Where G is the temperature gradient. and These are the partial derivatives of temperature in the x and y directions, respectively.

[0113] In Example 10, the core formula of the machine algorithm in step 5 is:

[0114] ;

[0115] in These are Lagrange multipliers, where n is the number of samples. It is the class label of the i-th sample. It is a kernel function used to calculate the kernel values ​​of two sample points. and The inner product between them.

[0116] The above are all preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

1. An infrared thermal imager based on multi-level thermal image analysis, characterized in that: The system includes a multi-level temperature data acquisition module (1), an intelligent temperature data processing module (2), and an intelligent fault diagnosis and early warning module (3). The multi-level temperature data acquisition module (1) includes a surface temperature acquisition unit (11), a deep temperature detection unit (12), and a transient temperature analysis unit (13). The surface temperature acquisition unit (11) captures the surface temperature data of the monitored object through a high-resolution infrared sensor. The deep temperature detection unit (12) acquires the temperature data of the deep layers below the surface of the monitored object based on pulse thermal excitation and thermal diffusion analysis technology. The data input terminal of the transient temperature analysis unit (13) is connected to the data output terminals of the surface temperature acquisition unit (11) and the deep temperature detection unit (12) respectively, and collects the surface temperature data and deep temperature data of the monitored object. Through time series analysis of temperature changes, the rate of temperature rise or fall is analyzed, and transient temperature data is output. The intelligent temperature data processing module (2) is connected to the transient temperature analysis unit (13) and analyzes and integrates surface temperature data, deep temperature data and transient temperature data through a multi-level data processing algorithm, outputs multi-level temperature data analysis results, and generates a comprehensive temperature map based on the multi-level temperature data analysis results. The intelligent fault diagnosis and early warning module (3) is connected to the intelligent temperature data processing module (2) to extract fault-related temperature features from the multi-level temperature data analysis results. The temperature features include abrupt change points, abnormal temperature areas and temperature difference fluctuations. The machine learning algorithm is used to establish a pattern model of known fault types to identify and match fault feature data. If there is a fault that is successfully identified and matched, a fault alarm is triggered. Fault diagnosis of monitored objects using infrared thermal imagers based on multi-level thermal image analysis includes the following steps: Step 1: The time series analysis processor (133) outputs transient temperature data by analyzing the surface temperature data and deep temperature data of the temperature change over time. Step 2, the AI ​​processor (31) analyzes the temperature characteristics of each layer of transient temperature data; Step 3, the AI ​​processor (31) calculates the thermal diffusivity and analyzes the rate of temperature transfer in the monitored object; Step 4, the AI ​​processor (31) extracts the fault characteristics of the monitored object based on the temperature characteristics and thermal diffusivity of each layer; Step 5: Use machine learning algorithms to perform pattern recognition on the fault features, and match the extracted fault features with a known fault pattern database to output the fault pattern results. Step 6: Based on the fault mode identification results, output the preset warning action command through the warning signal output interface (32) and the communication interface (33).

2. The infrared thermal imager based on multi-level thermal imaging analysis according to claim 1, characterized in that: It also includes a visualization multi-layer temperature image generation module (4), which includes a visualization data storage (41), a graphics processing unit (42) and a display (43). The visualization data storage (41) is connected to the intelligent temperature data processing module (2) to collect surface temperature data, deep temperature data and transient temperature data. The graphics processing unit (42) outputs multi-layer temperature image data. The display (43) is connected to the graphics processing unit (42).

3. The infrared thermal imager based on multi-level thermal image analysis according to claim 2, characterized in that: The surface temperature acquisition unit (11) includes an infrared lens (111), an infrared sensor (112), and a sensor driving circuit (113). The infrared lens (111) receives infrared radiation emitted by the monitored object, focuses the infrared radiation, and transmits it to the infrared sensor (112). The data output terminal of the infrared sensor (112) is communicatively connected to the transient temperature analysis unit (13). The sensor driving circuit (113) is communicatively connected to the infrared sensor (112) and is used to control the working state of the infrared sensor (112).

4. The infrared thermal imager based on multi-level thermal imaging analysis according to claim 3, characterized in that: The deep temperature detection unit (12) includes a laser pulse generator (121), a high-sensitivity thermocouple (122), and a signal amplification and filtering circuit (123). The laser pulse generator (121) is used to thermally excite the monitored object. The high-sensitivity thermocouple (122) is used to detect the temperature change of the monitored object after thermal excitation and is communicatively connected to the signal input terminal of the signal amplification and filtering circuit (123). The signal output terminal of the signal amplification and filtering circuit (123) is communicatively connected to the transient temperature analysis unit (13).

5. The infrared thermal imager based on multi-level thermal imaging analysis according to claim 4, characterized in that: The transient temperature analysis unit (13) includes a high-speed multi-channel data acquisition card (131), a temperature data buffer (132), and a time series analysis processor (133). The data input terminal of the high-speed multi-channel data acquisition card (131) is connected to the infrared sensor (112) and the signal amplification and filtering circuit (123) respectively. The temperature data buffer (132) is connected to the data output terminal of the high-speed multi-channel data acquisition card (131). The time series analysis processor (133) is connected to the temperature data buffer (132). The time series analysis processor (133) outputs transient temperature data based on the surface temperature data and deep temperature data of the monitored object surface through time series analysis of temperature changes.

6. The infrared thermal imager based on multi-level thermal imaging analysis according to claim 5, characterized in that: The intelligent temperature data processing module (2) includes a data storage (21), a data processor (22) and a graphics processor (23). The data storage (21) is communicatively connected to the time series analysis processor (133), and the data processor (22) and the graphics processor (23) are communicatively connected to the data storage (21) respectively.

7. The infrared thermal imager based on multi-level thermal imaging analysis according to claim 6, characterized in that: The intelligent fault diagnosis and early warning module (3) includes an AI processor (31), an early warning signal output interface (32), and a communication interface (33). The AI ​​processor (31) is connected to the data storage (21), the early warning signal output interface (32), and the communication interface (33) respectively.

8. The infrared thermal imager based on multi-level thermal imaging analysis according to claim 7, characterized in that: The formula for calculating transient temperature data in step 1 is: ； in This is the transient temperature component, where t is time and x is location. This is the temperature data after applying a low-pass filter; The formula for calculating the thermal diffusivity in step 3 is: ； in It is the thermal diffusivity. It is the change in temperature. It is a change over time; In step 4, the formula for fault feature extraction is: ； Where G is the temperature gradient. and These are the partial derivatives of temperature in the x and y directions, respectively.

9. The infrared thermal imager based on multi-level thermal imaging analysis according to claim 8, characterized in that: The core formula of the machine algorithm in step 5 is: ； in These are Lagrange multipliers, where n is the number of samples. It is the class label of the i-th sample. It is a kernel function used to calculate the kernel values ​​of two sample points. and The inner product between them.

Images