Monitoring system based on thermal imaging technology and part life prediction method

Abstract

The invention is suitable for the field of safety production, and provides a monitoring system based on a thermal imaging technology and a part service life prediction method. In the embodiment of the invention, for a production environment needing to be monitored, a thermal imaging information set containing coordinate information and coordinate temperature of equipment in the production environment is firstly collected, and then an infrared thermal image picture and an infrared thermal image video are determined through the thermal imaging information set; and carrying out temperature monitoring and error calibration on the areas corresponding to the devices in the pictures and the videos so as to determine the temperature states of the devices in the production environment in real time, and carrying out comparison and early warning on the temperature states and the early warning rules corresponding to the devices. According to the application, the monitoring temperature of the equipment can be corrected through the expert database module, and the corresponding early warning rule is set according to the difference of different equipment, so that the probability of false alarm and missing alarm is reduced.

Description

Technical Field

[0001] This application relates to the field of safe production, and in particular to a monitoring system based on thermal imaging technology and a method for predicting the lifespan of parts. Background Technology

[0002] In the field of safe production, thermal condition monitoring mainly relies on discrete temperature sensors and manual inspections. This approach has significant drawbacks, such as large monitoring blind spots and slow response times. Although infrared thermal imaging technology can achieve non-contact, full-area temperature monitoring, existing monitoring systems typically use fixed threshold alarm mechanisms, which are difficult to adapt to the differentiated temperature rise characteristics of different equipment components, easily leading to false alarms and missed alarms. Furthermore, during the operation and maintenance of various equipment in the production area, traditional methods for predicting equipment lifespan mainly rely on linear extrapolation based on equipment operating time or simple operating parameters. This extensive prediction mode lacks accuracy and cannot accurately reflect the actual wear and tear of the equipment. Summary of the Invention

[0003] In view of this, this application provides a monitoring system and a component life prediction method based on thermal imaging technology to solve the problems of different temperature rise characteristics of equipment components in the production environment, which easily lead to false alarms and missed alarms, and the inability to accurately predict the life of equipment in the production environment.

[0004] The first aspect of this application provides a monitoring system based on thermal imaging technology, the system including a thermal imaging module, an expert database module and a temperature monitoring module;

[0005] The thermal imaging module is used to collect thermal imaging information set of the target production environment through sensors, then convert the thermal imaging information set into infrared thermal images, and determine infrared thermal video through the infrared thermal images and the acquisition time in the thermal imaging information set. The thermal imaging information set includes the physical coordinates of each target device in the target production environment, the temperature value of the physical coordinates, and the acquisition time.

[0006] The expert database module is used to collect relevant information about each target device, determine the early warning rules for each target device through the relevant information, and perform error calibration on the temperature information determined by the temperature monitoring module. The relevant information includes historical data information, historical experience information, and functional parameters of the target device.

[0007] The temperature monitoring module is used to determine the monitoring area of ​​each target device in the infrared thermal image and infrared thermal video, and to monitor the monitoring area in real time to obtain the temperature information of the monitoring area. Then, the temperature information of each monitoring area after calibration by the expert library module is compared with the early warning rules of the corresponding target device, and an alarm is issued when it is determined that the temperature information meets the early warning rules.

[0008] Optionally, the error calibration of the temperature information determined by the temperature monitoring module includes:

[0009] A temperature calibration model containing a calibration table is constructed using the historical data information. The temperature information is then input into the temperature calibration model as an input parameter to obtain the temperature information after error calibration. The calibration table includes the positional relationship of the target device and the corresponding calibration values.

[0010] Optionally, the system also includes a dynamic display module;

[0011] The dynamic display module is used to determine the corresponding color temperature information through the temperature information, and then display each monitoring area, the color temperature information and the entity information of the target device in the monitoring area, so as to display the operating status of each target device through the color temperature information.

[0012] Optionally, the system further includes a component life prediction module, used to determine its predicted life based on relevant information of the target device and calibrated temperature information.

[0013] Optionally, the temperature information in the temperature monitoring module includes the maximum temperature, minimum temperature, average temperature, and variance statistics of the target device.

[0014] A second aspect of this application provides a method for predicting the lifespan of a component, the method comprising:

[0015] The thermal imaging information set of the target device is collected by the sensor, and then the thermal imaging information set is converted into infrared thermal images and / or infrared thermal videos.

[0016] The temperature information of the target device is determined by the infrared thermal image and / or infrared thermal video, and then the temperature information is calibrated based on the relevant information of the target device to obtain calibrated temperature information. The relevant information includes historical data information, historical experience information, and functional parameters of the target device.

[0017] The predicted lifespan of the target device is determined using the calibrated temperature information and the relevant information.

[0018] In the embodiments provided in this application, for production environments requiring monitoring, a thermal imaging information set containing the coordinates and temperatures of equipment within the production environment is first collected. Then, infrared thermal images and videos are determined using this information set. Next, temperature monitoring and error calibration are performed on the areas corresponding to each device in the images and videos to determine the temperature status of each device in the production environment in real time. Finally, this temperature status is compared with the corresponding early warning rules for each device to issue an early warning. This application utilizes an expert database module to set corresponding early warning rules based on the differences between different devices, thereby reducing the probability of false alarms and missed alarms.

[0019] Furthermore, this method can also accurately predict the service life of equipment by using historical data and functional parameters of each device in the expert database module, thereby enabling replacement when equipment ages and reducing the probability of accidents. Attached Figure Description

[0020] Figure 1 A system block diagram provided for embodiments of this application;

[0021] Figure 2 A flowchart illustrating the method provided in this application embodiment;

[0022] Figure 3 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0023] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0024] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0025] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0026] This application provides a monitoring system and a part life prediction method based on thermal imaging technology to improve the accuracy of locating abnormal temperature equipment in the production environment and reduce the probability of false alarms and missed alarms.

[0027] The technical solutions of this application will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0028] like Figure 1 The diagram shown is a system block diagram of a monitoring system based on thermal imaging technology provided in this application. The system includes a thermal imaging module, an expert database module, and a temperature monitoring module.

[0029] The functions and implementation process of each module are explained below:

[0030] Module 1, Thermal Imaging Module. This module is used to collect thermal imaging information sets of the target production environment through sensors, then convert the thermal imaging information sets into infrared thermal images, and determine infrared thermal video based on the acquisition time of the infrared thermal images and the thermal imaging information sets.

[0031] In this embodiment, the target equipment in the production environment can be transformers, cable terminals, control cabinets, control boxes, switches, relays, motor windings, etc. An image acquisition sensor can be placed near the target equipment to be monitored. Utilizing the principle of thermal infrared imaging, the sensor acquires a thermal imaging information set of the equipment. This thermal imaging information set includes the physical coordinates of each target equipment, the temperature value of the physical coordinates, and the acquisition time. Then, third-party tools such as FLIRTools or ThermaCAM Researcher are used to convert the physical coordinates (pixels) and the temperature value of the physical coordinates into infrared thermal images. Each pixel (coordinate point) in the image represents the temperature information of a tiny area on the device surface. By combining multiple infrared thermal images generated at different acquisition times (t) in chronological order, the aforementioned infrared thermal video can be obtained. This allows users to intuitively determine the temperature status of each device through images or videos.

[0032] Module Two, Expert Database Module. This module collects relevant information about each target device, determines early warning rules for each target device based on this information, and performs error calibration on the temperature information determined by the temperature monitoring module. The relevant information includes historical data, historical experience information, and functional parameters of the target devices.

[0033] This module primarily collects experimental, experiential, and knowledge information and stores it in a pre-built expert database. The expert database mainly includes temperature calibration models, color temperature models, and scheduling, early warning, and decision-making models established based on past operational experience in production environments. Because the temperature values ​​obtained by thermal infrared imaging equipment inherently have a measurement error of over 2%, and considering that some temperature measurement locations are inside the equipment where obstructions cause attenuation rather than direct surface measurement, temperature calibration models are created for the equipment parts and other objects to be measured in the production environment to improve measurement accuracy. This is achieved by establishing a temperature calibration table for the measured objects in the expert database, which can be used for calibration during temperature measurement. The establishment of the temperature calibration table should be based on experiments. This expert database must include label information and constraint rules for key equipment and information of concern marked in the production environment, as well as predictive models established based on production operation data, color temperature models, and alarm level classification rules.

[0034] The following explains some common models in this module:

[0035] The temperature measurement calibration model is used to calibrate the detected temperature to the actual temperature. The calibration method is based on a calibration table established after a preset experiment. The calibration table includes the target device, its internal and external locations, and the corresponding calibration values.

[0036] The color temperature model corresponds to the detected and calibrated color temperature data (color temperature meter), which is used to determine temperature anomalies.

[0037] Labeling models are established based on experience and experiments to classify monitoring areas or monitoring objects.

[0038] The empirical rule model specifies the types of temperature information (mean, current measured value, maximum and minimum values, variance) and the number of outliers that different devices need to detect, and establishes preconditions. It also determines the triggering content (such as temperature exceeding x degrees, outliers exceeding y) corresponding to abnormal events of different devices and establishes postconditions.

[0039] The grading rule model is used to set different thresholds for postconditions to obtain different triggering levels. Different triggering levels correspond to different alarm levels, and each alarm level corresponds to different flashing and ringing patterns.

[0040] Each model is built based on corresponding historical data. Taking the temperature measurement calibration model as an example, the model's construction process is as follows:

[0041] First, experiments are conducted according to various scenarios in the production environment to obtain experimental data (i.e., the historical data information mentioned above). This experimental data records the detection temperature of the target device determined by the thermal imaging information set under different scenarios and the corresponding relationship between the target device. For example, in scenario A, when the detection temperature inside the motor bearing of the device is x℃, it is calibrated to x'℃.

[0042] The experimental data is then preprocessed and features extracted to obtain feature vectors for model training.

[0043] The above feature vectors are divided into training set (60-80%), validation set (10-20%), and test set (10-20%).

[0044] A deep learning model, such as CNN (for images), RNN / LSTM (for sequences), or Transformer (for NLP), is constructed. This model is then trained, tested, and validated using the aforementioned training, validation, and test sets to obtain a temperature calibration model incorporating the calibration table. By inputting temperature information as an input parameter into this model, the error-calibrated temperature information can be obtained.

[0045] This module also needs to set corresponding early warning rules for each device based on its historical information (such as historical operating data). For example, if the historical operating data determines that the temperature information of device A is a maximum of 150℃ and a minimum of 40℃, the early warning rule is that the temperature is between the minimum and maximum values. If the historical operating data determines that the maximum temperature of device B is 350℃ and the minimum of 150℃, the early warning rule is that the temperature is between the minimum and maximum values. Furthermore, if some empirical information determines that the temperature change within 3 seconds cannot exceed 100℃, then the warning rule for device B also needs to include the condition that the temperature change within 3 seconds cannot exceed 100℃.

[0046] Module 3, Temperature Monitoring Module. This module is used to determine the monitoring area of ​​each target device in the infrared thermal image and infrared thermal video, and to monitor the monitoring area in real time to obtain the temperature information of the monitoring area. Then, it compares the temperature information of each monitoring area with the warning rules of the corresponding target device, and issues an alarm when the temperature information meets the warning rules.

[0047] In this embodiment, several temperature parameters to be monitored need to be preset, such as maximum value, minimum value, and amplitude of change. Then, the temperature information of each device is compared with the warning information determined by the expert database module. Taking devices A and B as examples, during actual monitoring, infrared thermal images are obtained through the thermal imaging module. or video Then, based on the physical coordinates of devices A and B, from or Determine the monitoring area of ​​the device. Then, based on the image... or video The temperature readings determine whether the temperature of device A is between 40℃ and 150℃. If it exceeds 150℃ or falls below 40℃, corresponding alarm prompts are issued. For device B, the temperature not only needs to be between 150℃ and 350℃, but also requires video monitoring. The amplitude of temperature change within 3 seconds should be determined, and an alarm should be issued when the temperature rises or falls by more than 100°C within 3 seconds.

[0048] In another embodiment, the temperature information mentioned above includes the maximum temperature, minimum temperature, average temperature, and variance statistics of the target device.

[0049] This embodiment includes multiple different temperature parameters. The expert database module can set various early warning rules based on the above temperature information. Details are as follows:

[0050] 1) Monitoring of extreme values ​​in the temperature measurement area. For example, ,in, For relative to The measured temperature information is the temperature information after calibration by the temperature measurement calibration model of the expert database, T min T is the minimum permissible temperature value for the production environment monitoring area. max This refers to the maximum permissible temperature value in the production environment monitoring area.

[0051] 2) Monitoring the average temperature across the measurement area. For example, T min ≤µ≤T max ,in,

[0052] M and N are the maximum coordinates of the temperature measurement points in the monitoring area.

[0053] 3) Statistical monitoring of variance in the temperature measurement area. For example, σ t 2 ≤T max ,in,

[0054] μ tLet μ be a mean function of time, representing the average temperature of different image frames in the monitoring area; t represents the sequence of different images over time; and N is the maximum frame sequence value. .

[0055] This embodiment allows for further expansion of the temperature information monitored in the temperature monitoring module, enabling the expert database module to set more detailed early warning rules for each device, thereby further reducing the probability of false alarms and missed alarms for abnormal device temperatures.

[0056] This concludes the process. Figure 1 Functional descriptions of each module.

[0057] In the above embodiments, for production environments requiring monitoring, a thermal imaging information set containing the coordinates and temperatures of equipment within the production environment is first collected. Then, infrared thermal images and videos are determined using this information set. Next, temperature monitoring and error calibration are performed on the areas corresponding to each device in the images and videos to determine the temperature status of each device in the production environment in real time. Finally, this temperature status is compared with the corresponding early warning rules for each device to issue an early warning. This application utilizes an expert database module to set corresponding early warning rules based on the differences between different devices, thereby reducing the probability of false alarms and missed alarms.

[0058] In another embodiment, the system further includes a dynamic display module, which is used to determine the corresponding color temperature information through the temperature information, and then display each monitoring area, the color temperature information and the entity information of the target device in the monitoring area, so as to display the operating status of each target device through the color temperature information.

[0059] In this embodiment, the color temperature information includes multiple different color temperature values, each corresponding to a different temperature range. For example, blue represents the low temperature range (0℃-40℃), green represents the normal temperature range (40℃-100℃), and red represents the high temperature range (100℃-300℃). Different shades reflect the specific location of the temperature within each range, allowing users to directly estimate the approximate temperature of the device through the color temperature information.

[0060] In another embodiment, the system further includes a component life prediction module, which is used to determine the predicted life of the target device based on relevant information of the target device and calibrated temperature information.

[0061] Taking deep groove ball bearings as an example, the life prediction process for this equipment is as follows:

[0062] Determine the reliability correction factor, material factor, operating condition factor, effective service factor, and basic rated service life of the deep groove ball bearing that needs to be predicted, and then use the formula...

[0063] The predicted life of the deep groove ball bearing is determined, where α1 is the reliability correction factor, α2 is the material factor, α3 is the operating condition factor, α4 is the effective service life factor, and L... 10 This is the basic rated life.

[0064] In this embodiment, the reliability correction factor α1 is selected based on the reliability S, and a fixed value can be set by referring to a table. The material factor α2 can be determined by the oxygen content of the deep groove ball bearing material. For example, when the oxygen content of the material is 20~30ppm, α2 can be taken as 1.5~3. The effective service life factor α4 can be determined by the reliability and damage area of ​​the deep groove ball bearing. For example, if the reliability S of the deep groove ball bearing is 90% and the fatigue damage area is 1mm... 2 In this case, α4 can be taken as 1.

[0065] For the working condition coefficient α3, it can be obtained through the formula... Determine, where α 3K α is the load factor. 3L α is the lubrication coefficient. 3M This is the skewness coefficient.

[0066] Load factor α 3K Then it can be done Calculation. Among them, This refers to the radial force acting on the deep groove ball bearing. This represents the axial force acting on the deep groove ball bearing; K is the viscosity. , The kinematic viscosity of the lubricating oil at the operating temperature. Based on the average diameter of the deep groove ball bearing and rotational speed The required viscosity (mm) for sufficient lubrication can be found in the chart. 2 / s), (mm), where d is the inner diameter of the deep groove ball bearing and D is the outer diameter of the deep groove ball bearing. After calculating the value of X above, when X > 2.13, then α 3K =0.690 (load area is 180°); when X < 2.13, then α 3K The load area (greater than 180°) can be selected using a chart.

[0067] For the lubrication coefficient α 3L This coefficient is related to the viscosity K value of the deep groove ball bearing, and α can be obtained by referring to a lubrication coefficient chart determined by viscosity. 3L value.

[0068] And for the skewness coefficient α 3MWhen the inclination of the bearing axis of the deep groove ball bearing is less than 0.0005 radians, its impact on the bearing life can be ignored. 3M Take 1.

[0069] For the basic rated life L 10 It can be done through formula Obtained. In this formula, The temperature coefficient is determined by using the temperature information from the temperature calibration model calibrated by the expert database to determine the actual maximum temperature value of the deep groove ball bearing. This actual maximum temperature value can then be used to find the corresponding temperature coefficient in the temperature coefficient table. C is the basic rated dynamic load (N); P is the equivalent dynamic load (N); ε is the life exponent, which can be taken as 3 for deep groove ball bearings. The bearing speed is (r / min).

[0070] The equivalent dynamic load P can be calculated using the following formula: ,in, The load condition factor can be obtained by querying a table stored in the expert database; Radial load (N); X represents the axial load; X represents the radial dynamic load factor; and Y represents the axial dynamic load factor. These can be determined using the device's functional parameters from the expert database module.

[0071] For example, the radial load of the deep groove ball bearing 6310 is determined by the bearing parameters of the deep groove ball bearing. =5500N, axial load =2700N, bearing speed =1250 r / min. Slight impacts will occur during operation, therefore the kinematic viscosity of the lubricating oil is set at the operating temperature. =20mm 2 / s, with a design reliability of 90%, and the bearing operates in an extremely clean environment. > T max At 95℃, the bearing is in an abnormal operating temperature range. From the above, we can calculate: .

[0072] Consult relevant documents in the expert database, such as bearing catalogs or mechanical design manuals, to determine the basic rated dynamic load of the part as C = 61800 N. Then, use the formula... Calculate the basic rated life L of the bearing. 10 =4748h. Since the bearing's rated life reliability is 90%, α1=1. However, under normal circumstances, the oxygen content of the material is 20~30ppm, so α2=1.5 is selected. Deep groove ball bearing 6310 =50mm, =110mm, , =1250 r / min, which can be obtained by consulting the lubrication viscosity chart in the expert database. , ,

[0073] α can be found by referring to the chart. 3K =0.8. When the bearing axis tilt is less than 0.0005 radians, α can be taken as 0.8. 3M =1, K=1.429, referring to the viscosity-lubrication coefficient chart, we can take α. 3L =1.5, bearing fatigue life with a reliability of 90%, fatigue damage area is 6mm. 2 We can take α4=1, therefore, the predicted life of the deep groove ball bearing is: =1×1.5×(0.8+1+1.5)×1×1.5×4748=35253.9h. If the monitored bearing is within the predicted lifespan, the system is operating normally; if the monitored bearing is nearing its predicted lifespan, such as 0.95L=33491.205h, a warning message indicating an abnormality in the motor bearing will be given.

[0074] This concludes the description of each module in this application. The functions of the system described above will now be explained through several specific scenarios.

[0075] Scenario 1: Digital twin thermal imaging monitoring system for power distribution room in production environment.

[0076] In this scenario, the power distribution room is identified as the monitoring target. Electrical components in the power distribution cabinet age, and continued operation of these aging components often leads to overheating and eventual damage, affecting the normal operation of the power distribution room. Therefore, this embodiment uses the entire power distribution cabinet as the monitoring target.

[0077] The first step is to label the distribution cabinet. Label the constructed 3D model of the distribution cabinet to identify its information. Labeling information includes, but is not limited to, equipment number, equipment type, start date of use, last maintenance date, responsible person, and contact number.

[0078] The second step is to place the thermal imaging equipment. Depending on the attributes to be monitored, the thermal imaging equipment can be placed directly above and opposite the distribution cabinet to monitor more components within the cabinet.

[0079] The third step is to set up the monitoring area. This embodiment primarily aims to monitor the operating status of the power distribution cabinet. Before an abnormality occurs, the power distribution cabinet often exhibits abnormal component temperatures. Therefore, the entire power distribution cabinet can be set as the monitoring area. The highest temperature can be used as the monitoring condition within the area. To increase monitoring accuracy, multiple monitoring points can be used within the monitoring area, for example, five points with the highest temperature.

[0080] The fourth step is to query and access the expert database. Based on the calibrated distribution cabinet information and the collected temperature values ​​of the monitoring area, the expert database is queried to provide the monitoring results. If the monitored distribution cabinet has a temperature value within the monitoring area... The system is operating normally if no more than 5 monitoring points have temperatures exceeding 150℃; if the monitored distribution cabinet has a temperature value within the monitored area... If more than 5 points reach 150℃, the expert database will issue a warning message indicating an abnormality in the distribution cabinet.

[0081] Finally, the display will be presented. If the distribution cabinet is operating normally, the display system only needs to display the information normally; if the expert database provides warning information, the display system should provide different levels of display based on the warning level. The display is not limited to flashing warning signs of different colors or alarm sounds at different intervals.

[0082] Scenario 2: Digital Twin Thermal Imaging Monitoring System for Motor Windings in a Production Environment. This scenario identifies the motor windings in the production environment as the monitoring object. A common form of motor failure is the burning out of the motor windings due to overheating. Therefore, this embodiment can use the motor windings as the monitoring object.

[0083] The first step is to calibrate the motor windings. Label the constructed 3D model of the motor windings to identify their information. This labeling includes, but is not limited to, winding number, winding type, start date, last maintenance date, responsible person, and contact number.

[0084] The second step is to place the thermal imaging equipment. Depending on the properties being monitored, the thermal imaging equipment can be placed directly above and opposite the winding axis to monitor the overall temperature of the winding.

[0085] The third step is to set up the monitoring area. This embodiment primarily aims to monitor the winding's operating status. Before an abnormality occurs, the winding temperature often rises; therefore, the entire winding can be set as the monitoring area. Average temperature monitoring can be used as the condition for this area.

[0086] The fourth step is to query and access the expert database. Based on the calibrated winding information and the average temperature of the monitored area, the expert database is consulted to provide the monitoring results. If the average temperature µ of the monitored winding after temperature measurement and calibration in the monitored area is less than 80℃, the system is operating normally; if the average temperature µ of the monitored winding after temperature measurement and calibration in the monitored area is greater than 80℃, the expert database will issue a warning message indicating an abnormality in the motor winding.

[0087] Finally, the display is performed. If the motor windings are operating normally, the display system only needs to identify the motor windings according to the color temperature information based on the average temperature of the monitored area. If the expert database provides warning information, the display system should provide different levels of warning information for the motor windings. The display is not limited to flashing warning signs of different colors or alarm sounds at different intervals.

[0088] This concludes the usage instructions for the above scenarios in various systems.

[0089] This application also provides a method for predicting the lifespan of a component, such as... Figure 2 As shown, the process of this method is as follows:

[0090] Step S201: Collect thermal imaging information set of the target device through sensors, and then convert the thermal imaging information set into infrared thermal images and / or infrared thermal videos.

[0091] Step S202: Determine the temperature information of the target device through the infrared thermal image and / or infrared thermal video, and then calibrate the temperature information based on the relevant information of the target device to obtain calibrated temperature information.

[0092] Step S203: Determine the predicted lifespan of the target device using the calibrated temperature information and the relevant information.

[0093] In this embodiment, the lifespan of most production equipment can be estimated using temperature information and corresponding related information, taking deep groove ball bearings as an example.

[0094] It can be done through formula Determine the dynamic load P of the target device, wherein, For load condition factor, For radial load, X is the axial load, and Y is the radial dynamic load factor.

[0095] Then through the formula Determine the basic rated life L of the target equipment. 10 ,in, The temperature coefficient of the target device is determined by calibrated temperature information, C is the basic rated dynamic load of the target device, P is the equivalent dynamic load of the target device, ε is the life index of the target device, and n is the rotational speed of the target device.

[0096] Finally, the formula is used. Determine the predicted lifespan L of the target equipment. Wherein, α1 is the reliability correction coefficient, α2 is the material coefficient, α3 is the operating condition coefficient, and α4 is the effective service life coefficient.

[0097] This concludes the process. Figure 2 The process is shown below.

[0098] In this embodiment, the lifespan of equipment in the production environment is accurately predicted, thereby enabling replacement when equipment ages, which reduces the probability of accidents.

[0099] The above embodiments of the present invention provide a monitoring system based on thermal imaging technology, and based on this system, a method for predicting the lifespan of components. Through the above method and apparatus, not only are the problems of difficulty in accurately locating temperature anomalies and the differentiated temperature rise characteristics of different equipment components, which easily lead to false alarms and missed alarms, in the operation and maintenance of production environments solved, but the lifespan of equipment can also be accurately predicted using temperature information within the production environment. This allows for timely replacement of equipment as it ages, reducing the probability of accidents.

[0100] This embodiment also discloses a computer device, such as... Figure 3 As shown, the computer device includes a processor and a memory, the memory storing at least one instruction, which is loaded and executed by the processor to implement the method on the monitoring system based on thermal imaging technology described above.

[0101] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A monitoring system based on thermal imaging technology, characterized in that, The system includes a thermal imaging module, an expert database module, and a temperature monitoring module; The thermal imaging module is used to collect thermal imaging information set of the target production environment through sensors, then convert the thermal imaging information set into infrared thermal images, and determine infrared thermal video through the infrared thermal images and the acquisition time in the thermal imaging information set. The thermal imaging information set includes the physical coordinates of each target device in the target production environment, the temperature value of the physical coordinates, and the acquisition time. The expert database module is used to collect relevant information about each target device, determine the early warning rules for each target device through the relevant information, and perform error calibration on the temperature information determined by the temperature monitoring module. The relevant information includes historical data information, historical experience information, and functional parameters of the target device. The temperature monitoring module is used to determine the monitoring area of ​​each target device in the infrared thermal image and infrared thermal video, and to monitor the monitoring area in real time to obtain the temperature information of the monitoring area. Then, the temperature information of each monitoring area after calibration by the expert library module is compared with the early warning rules of the corresponding target device, and an alarm is issued when it is determined that the temperature information meets the early warning rules.

2. The system according to claim 1, characterized in that, The error calibration of the temperature information determined by the temperature monitoring module includes: A temperature calibration model containing a calibration table is constructed using the historical data information. The temperature information is then input into the temperature calibration model as an input parameter to obtain the temperature information after error calibration. The calibration table includes the positional relationship of the target device and the corresponding calibration values.

3. The system according to claim 1, characterized in that, The system also includes a dynamic display module; The dynamic display module is used to determine the corresponding color temperature information through the temperature information, and then display each monitoring area, the color temperature information and the entity information of the target device in the monitoring area, so as to display the operating status of each target device through the color temperature information.

4. The system according to claim 1, characterized in that, The system also includes a component life prediction module, which is used to determine the predicted life of the target device based on relevant information of the target device and calibrated temperature information.

5. The system according to claim 1, characterized in that, The temperature information in the temperature monitoring module includes the maximum temperature, minimum temperature, average temperature, and variance statistics of the target device.

6. A method for predicting the lifespan of a component, characterized in that, The method includes: The thermal imaging information set of the target device is collected by the sensor, and then the thermal imaging information set is converted into infrared thermal images and / or infrared thermal videos. The temperature information of the target device is determined by the infrared thermal image and / or infrared thermal video, and then the temperature information is calibrated based on the relevant information of the target device to obtain calibrated temperature information. The relevant information includes historical data information, historical experience information, and functional parameters of the target device. The predicted lifespan of the target device is determined using the calibrated temperature information and the relevant information.

Images