Rail welding process information intelligent acquisition and analysis method based on internet of things technology
By acquiring welding parameters through an IoT sensor array and analyzing modal components and singular values, the problem of inaccurate detection caused by noise interference during track welding was solved, enabling highly accurate detection and timely repair of abnormal faults and ensuring welding quality.
Patent Information
- Application Number
- CN202510709622.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-29
- Publication Date
- 2026-02-10
- Estimated Expiration
- 2045-05-29
AI Technical Summary
During track welding, welding information collected by IoT technology is easily interfered with by mechanical noise from the equipment, leading to inaccurate detection of abnormal faults, inability to diagnose and repair them in a timely manner, and affecting welding quality.
Welding parameter data is acquired through IoT smart sensor arrays, modal components and singular values are extracted, instantaneous interference complexity and confidence weight are calculated, interference-free singularity analysis is performed, and anomaly detection is carried out by combining the significance of associated faults. Anomaly detection algorithms are used to determine welding equipment faults.
It improves the accuracy of abnormal fault detection in welding equipment, ensures the quality of track welding, enables timely diagnosis and repair of equipment, and reduces the impact of external noise interference.
Smart Images
Figure CN120654133B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of welding fault analysis technology, specifically to a method for intelligent acquisition and analysis of information on rail welding processes based on Internet of Things (IoT) technology. Background Technology
[0002] During the track welding process, IoT technology is used to intelligently collect information on the track welding process and analyze it using anomaly detection algorithms. This allows for real-time detection of abnormal faults in the welding equipment, enabling timely diagnosis and repair of the equipment and effectively preventing welding defects from occurring during track welding.
[0003] Currently, applying IoT technology to the welding field involves using smart sensors on welding equipment to collect data on the rail welding process and employing anomaly detection algorithms to analyze and process this information, enabling remote monitoring and management of the welding process. However, the collection of rail welding process information is susceptible to interference from mechanical noise from the equipment, leading to errors in the collected data. Directly using this collected information to detect equipment malfunctions can result in inaccurate fault detection, hindering timely diagnosis and repair, and ultimately compromising the quality of rail welding. Summary of the Invention
[0004] To address the aforementioned technical problems, this application provides a method for intelligent acquisition and analysis of information on the rail welding process based on Internet of Things (IoT) technology, thereby resolving the existing issues.
[0005] The intelligent acquisition and analysis method for rail welding process information based on Internet of Things technology in this application adopts the following technical solution:
[0006] One embodiment of this application provides a method for intelligent acquisition and analysis of rail welding process information based on Internet of Things (IoT) technology, including the following steps:
[0007] Data on various welding parameters during the rail welding process are acquired through an IoT-based smart sensor array.
[0008] The modal components of each welding parameter data within a preset time period before each acquisition time are extracted. Based on the dispersion of the instantaneous frequency and instantaneous amplitude of all modal components of each welding parameter before each acquisition time, and combined with the average level of similarity between the modal components of the welding parameter, the instantaneous interference complexity of each welding parameter at each acquisition time is obtained.
[0009] Singular values in each welding parameter data within a preset time period before each acquisition time are extracted, and the credibility weight of each welding parameter at each acquisition time is obtained through the instantaneous interference complexity, so as to perform weighted analysis on the singular values to obtain the interference-free singularity at each acquisition time during the track welding process.
[0010] The correlation between the interference removal singularity and each welding parameter during the track welding process is analyzed, and the associated fault significance at each acquisition time during the track welding process is obtained by combining the interference removal singularity.
[0011] Anomaly detection was performed on the significance of associated faults at each data acquisition time to determine the fault status of the track welding equipment.
[0012] Preferably, the welding parameters include: welding current, welding voltage, and welding temperature.
[0013] Preferably, the method for obtaining the modal components is as follows: the welding parameter data within a preset time period before each acquisition time are combined into a welding parameter sequence for each acquisition time. The welding parameter sequence includes: welding current sequence, welding voltage sequence and welding temperature sequence. Modal decomposition is performed on each welding parameter sequence to obtain the modal components of each welding parameter sequence.
[0014] Preferably, the method for obtaining the instantaneous interference complexity of each welding parameter at each acquisition time is as follows:
[0015] For the welding current in the welding parameters, the instantaneous disturbance complexity of the welding current at the t-th acquisition time is... The calculation method is as follows:
[0016] ;
[0017] In the formula, and , respectively, represent the instantaneous frequency and standard deviation of the instantaneous amplitude of all modal components in the welding current sequence at the t-th acquisition time. Let be the mean of the similarity between any two modal components in the welding current sequence at time t. To avoid constants with a denominator of zero.
[0018] Preferably, the similarity between any two modal components is the cosine similarity between any two modal components.
[0019] Preferably, the confidence weight of each welding parameter at each acquisition time is the normalized result of the reciprocal of the instantaneous interference complexity of each welding parameter at each acquisition time.
[0020] Preferably, the method for obtaining the interference-free singularity at each acquisition time during the track welding process is as follows:
[0021] ;
[0022] In the formula, Let be the noise-removing singularity at the t-th acquisition time during the track welding process. , , These represent the confidence weights for welding current, welding voltage, and welding temperature at the t-th acquisition time. , , These are the singular values of the welding current sequence, welding voltage sequence, and welding temperature sequence at the t-th acquisition time, respectively.
[0023] Preferably, the method for calculating the significance of associated faults at each acquisition time point during the track welding process is as follows:
[0024] ;
[0025] In the formula, Let be the significance of the associated fault at the t-th acquisition time during the track welding process. For exponential normalization function, The average value of the absolute covariance between the interference-free singularity sequence at the t-th acquisition time and the welding current sequence, welding voltage sequence, and welding temperature sequence is taken.
[0026] Preferably, the method for obtaining the interference-free singularity sequence is as follows:
[0027] The normalized results of the de-interference singularities of all acquisition times within the preset time period before each acquisition time are arranged in chronological order to form the de-interference singularity sequence of each acquisition time.
[0028] Preferably, the step of performing anomaly detection on the correlation fault significance at each acquisition time to determine the fault status of the track welding equipment further includes:
[0029] The correlation significance of the current acquisition time and all previous historical acquisition times during the track welding process is input into the anomaly detection algorithm to obtain the abnormal moments in the track welding process. If the current acquisition time is an abnormal moment, the track welding equipment has malfunctioned; otherwise, the track welding equipment has not malfunctioned.
[0030] This application has at least the following beneficial effects:
[0031] This application takes into account that when the welding parameters are subject to a high degree of external noise interference, the differences between various modal components are large and the instantaneous frequency and instantaneous amplitude are more complex. Therefore, based on the analysis of each modal component and its instantaneous frequency and instantaneous amplitude, the instantaneous interference complexity corresponding to each acquisition moment is accurately measured to improve the accuracy of subsequent abnormal fault detection on welding equipment.
[0032] This application uses adaptive welding current, welding voltage, and welding temperature confidence weights, and employs a weighted method to measure the singularity characteristics after removing interference during the welding process, obtaining the interference-free singularity at each acquisition time. This effectively reduces the complex interference from external influences during the welding process and improves the accuracy of subsequent real-time detection of abnormal faults in welding equipment.
[0033] This application accurately measures the significant characteristics of associated faults in welding equipment during track welding by combining the de-interference singularity at each acquisition time with the correlation characteristics between the de-interference singularity and welding parameters. This reduces the adverse effects of complex interference from external environmental factors on abnormal fault detection, improves the significance of associated faults in welding equipment during track welding, and thus uses anomaly detection algorithms to more accurately detect abnormal faults in track welding equipment. An alarm is then used to issue early warnings, enabling staff to diagnose and repair the welding equipment in a timely manner, thereby ensuring the quality of track welding. Attached Figure Description
[0034] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0035] Figure 1 A flowchart illustrating the steps of the intelligent acquisition and analysis method for track welding process information based on Internet of Things technology provided in this application. Detailed Implementation
[0036] To further illustrate the technical means and effects adopted by this application to achieve the intended inventive objective, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the intelligent acquisition and analysis method for rail welding process information based on Internet of Things technology proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.
[0037] Unless otherwise defined, terms such as “comprising,” “including,” or any other variations thereof are intended to cover a non-exclusive inclusion, such that a circuit structure, article, or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the article or device that includes said element. Furthermore, the term “and / or” as used herein includes any and all combinations of one or more of the associated listed items. All technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.
[0038] The following description, in conjunction with the accompanying drawings, details the specific scheme of the intelligent acquisition and analysis method for track welding process information based on Internet of Things technology provided in this application.
[0039] This application provides an embodiment of an intelligent acquisition and analysis method for rail welding process information based on Internet of Things (IoT) technology. For details, please refer to [link to specific examples]. Figure 1 This includes the following steps:
[0040] Step 1: Acquire data on various welding parameters during the track welding process using an IoT smart sensor array.
[0041] The track is welded using industrially manufactured track welding equipment. This equipment consists of components such as a welding machine, base, wheels, stepper motor, gears, grinding wheels, and support frame. An intelligent sensor array is installed on the track welding equipment using Internet of Things (IoT) technology to collect data on various welding parameters during the welding process. In this embodiment, the intelligent sensor array includes current sensors, voltage sensors, and temperature sensors. The welding parameters include welding current, welding voltage, and welding conditions. The intelligent sensor array collects welding parameter data in real time during the track welding process, with a sampling frequency of 100Hz.
[0042] In the process of manufacturing rail welding equipment, the Internet of Things (IoT) technology is applied to the welding equipment. Through smart sensors and communication devices, information such as the operating status and welding parameters of the welding equipment can be transmitted to the cloud server in real time. Operators can then process the real-time welding parameter information on the terminal equipment and promptly detect abnormal faults in the welding equipment.
[0043] Therefore, the welding current, welding voltage, and welding temperature during the track welding process are collected in real time by the intelligent sensor group on the manufactured track welding equipment, and the welding current, welding voltage, and welding temperature before each collection moment are obtained in the cloud server. In this embodiment, preferably, the welding current, welding voltage, and welding temperature are normalized respectively in order to eliminate the interference of different data dimensions on subsequent analysis and processing.
[0044] Furthermore, in this embodiment, the normalized welding parameter data obtained before each acquisition time are stored in chronological order to obtain the welding parameter sequence for each acquisition time, including: welding current sequence, welding voltage sequence, and welding temperature sequence. The normalization method can be exponential normalization or range normalization, or other normalization methods. In this embodiment, exponential normalization is used for normalization.
[0045] It should be noted that, in order to avoid the problem of excessive computation due to excessive data volume, in this embodiment, the welding parameter data within a preset time period before each acquisition time are combined into a welding parameter sequence for each acquisition time. In this embodiment, the preset time period is 5 seconds.
[0046] Step 2: Extract the modal components of the welding parameters data before each acquisition time. Based on the dispersion of the instantaneous frequency and instantaneous amplitude of all modal components of each welding parameter before each acquisition time, and combined with the average level of similarity between the modal components of the welding parameters, obtain the instantaneous interference complexity of each welding parameter at each acquisition time.
[0047] Because the acquisition of track welding process information is easily affected by mechanical noise from the equipment, it can lead to errors in the collected track welding information. Current technologies do not fully consider the interference characteristics in the welding process information when analyzing and processing it, resulting in inaccurate detection of welding equipment malfunctions. Therefore, it is necessary to analyze the interference characteristics in the welding information to improve the accuracy of welding equipment malfunction detection.
[0048] Taking the welding current sequence as an example, in this embodiment, the welding current sequence is input into the HHT Hilbert-Huang Transform, and the HHT Hilbert-Huang Transform is used to obtain each modal component of the welding current sequence, and the instantaneous frequency and instantaneous amplitude of each modal component are calculated. The HHT Hilbert-Huang Transform is a well-known technology and will not be described in detail.
[0049] Generally, the lower the similarity between the modal components of the welding current sequence, and the greater the difference in instantaneous frequency and instantaneous amplitude between the modal components, the higher the complexity of the welding current being affected by external interference, and the more likely it is to affect the authenticity of the track welding information. In this case, the credibility of the abnormal faults in the welding current is lower.
[0050] Furthermore, the similarity between any two modal components of the welding current sequence is calculated. The similarity can be measured by cosine similarity or Jaccard similarity coefficient. In this embodiment, cosine similarity is used to measure the similarity. The greater the similarity, the more similar the changes between the two modal components are.
[0051] Based on the above analysis, the instantaneous interference complexity of the welding current at each acquisition moment is calculated:
[0052] ;
[0053] In the formula, Let be the instantaneous interference complexity of the welding current at the t-th acquisition time. and , respectively, represent the instantaneous frequency and standard deviation of the instantaneous amplitude of all modal components in the welding current sequence at the t-th acquisition time. Let be the mean of the similarity between any two modal components in the welding current sequence at time t. To avoid constants with a denominator of zero, this embodiment uses values within the range of (0.001, 0.01). The value is 0.001.
[0054] The more complex the instantaneous interference of the welding current from external factors, the lower the reliability of the abnormal faults in the welding current. When measuring the abnormal fault characteristics of the manufactured welding equipment, the weight of this should be reduced to improve the accuracy of abnormal fault detection on the manufactured welding equipment.
[0055] Similarly, the welding voltage sequence and welding temperature sequence are analyzed using the method described in this embodiment to obtain the instantaneous interference complexity of welding voltage and welding temperature at each acquisition time.
[0056] Step 3: Extract the singular values from the welding parameter data before each acquisition time, and obtain the confidence weight of each welding parameter at each acquisition time through the instantaneous interference complexity, so as to perform weighted analysis on the singular values to obtain the interference-free singularity at each acquisition time during the track welding process.
[0057] Furthermore, SVD (Singular Value Decomposition) is performed on the welding current sequence, welding voltage sequence, and welding temperature sequence at each acquisition time. The SVD algorithm is used to obtain the singular values of the welding current sequence, welding voltage sequence, and welding temperature sequence at each acquisition time. The larger the singular value, the higher the singularity of the corresponding welding parameter data. The welding equipment manufactured under such conditions is more prone to abnormal failures. SVD is a well-known technique and will not be elaborated further.
[0058] To more accurately measure singularity characteristics during track welding, the inverse of the instantaneous interference complexity of welding current, welding voltage, and welding temperature at each acquisition moment was exponentially normalized to obtain the reliability weights for welding current, welding voltage, and welding temperature at each acquisition moment. The smaller the reliability weight, the greater the complex interference characteristics of the corresponding welding parameters under external influencing factors, and the greater the interference in the analysis of singularities during track welding. Therefore, setting a smaller reliability weight reduces the proportion of singularities generated by complex interference from external influencing factors, thereby improving the accuracy of measuring singularities during track welding.
[0059] Based on the above analysis, the noise-removing singularity at each acquisition time point during the track welding process is calculated:
[0060] ;
[0061] In the formula, Let be the noise-removing singularity at the t-th acquisition time during the track welding process. , , These represent the confidence weights for welding current, welding voltage, and welding temperature at the t-th acquisition time. , , These are the singular values of the welding current sequence, welding voltage sequence, and welding temperature sequence at the t-th acquisition time, respectively.
[0062] In this embodiment, by adaptively setting the confidence weights of welding current, welding voltage, and welding temperature, and using a weighted summation method to measure the singularity characteristics after removing interference during the welding process, the interference-free singularity at each acquisition time is obtained. This can significantly reduce the complex interference from external influences during the welding process and improve the accuracy of real-time detection of abnormal faults in the welding equipment. This enables timely diagnosis and repair of the welding equipment and ensures the quality of track welding.
[0063] Step 4: Analyze the correlation between the interference removal singularity and each welding parameter during the track welding process, and combine the interference removal singularity to obtain the associated fault significance at each acquisition time during the track welding process.
[0064] Under normal circumstances, the rail welding process is relatively stable, and the manufactured rail welding equipment does not experience any abnormal malfunctions. However, if the welding equipment malfunctions, the welding current, welding voltage, and welding temperature will all exhibit abnormal characteristic changes. The greater the singularity after interference removal, the more it indicates that the welding equipment has malfunctioned. The welding equipment should be diagnosed and repaired in a timely manner to ensure the quality of the rail welding.
[0065] Furthermore, in this embodiment, the de-interference singularity at each acquisition time is subjected to exponential normalization. For each acquisition time, the normalized results of the de-interference singularity of all acquisition times within 5 seconds before each acquisition time are arranged in chronological order to form the de-interference singularity sequence of each acquisition time.
[0066] Among them, the noise-removed singularity sequence reflects the characteristic changes of singularity after removing external interference during the track welding process. The stronger the correlation between the characteristic changes of singularity during the track welding process and the welding current, welding voltage, and welding temperature, the more significantly it indicates that the track welding equipment has experienced an abnormal malfunction.
[0067] Therefore, the correlation between the interference-free singularity sequence and the welding current sequence, welding voltage sequence, and welding temperature sequence at each acquisition time is calculated. The correlation can be measured by Pearson correlation coefficient, covariance, or grey relational degree. In this embodiment, covariance is selected to measure the correlation.
[0068] Based on the above analysis, the significance of associated faults at each acquisition time point during the track welding process is calculated:
[0069] ;
[0070] In the formula, Let be the significance of the associated fault at the t-th acquisition time during the track welding process. For exponential normalization function, The average value of the absolute covariance between the interference-free singularity sequence at the t-th acquisition time and the welding current sequence, welding voltage sequence, and welding temperature sequence is taken.
[0071] Understandably, the significance of associated faults reflects the significant characteristics of associated faults in the welding equipment during the track welding process. If the singularity characteristics after interference removal are greater during the welding process, and the correlation between the changes in singularity characteristics and welding current, welding voltage, and welding temperature during the track welding process is higher, it can more significantly indicate that associated abnormal faults have occurred in the track welding equipment.
[0072] Step 5: Perform anomaly detection on the significance of associated faults at each acquisition time to determine the fault status of the track welding equipment.
[0073] The above process in this embodiment can obtain the significance of associated faults at different acquisition times during the welding process, so as to avoid the situation where the detection of abnormal faults in track welding equipment is inaccurate due to complex interference from external environmental factors during track welding, and improve the accuracy of abnormal fault detection of track welding equipment.
[0074] Meanwhile, as the track welding time progresses, if an abnormal fault occurs in the welding equipment at the current moment, the fault characteristic saliency will exhibit a significant outlier. Therefore, in order to more accurately detect abnormal faults in the welding equipment in real time during the welding process, the correlation fault saliency between the current acquisition moment and all previous historical acquisition moments during the track welding process is input into the anomaly detection algorithm. The anomaly detection algorithm can be the HBOS (Histogram-based Outlier Score) or the LOF (Local Outlier Factor) anomaly detection algorithm. In this embodiment, the HBOS anomaly detection algorithm is used for anomaly detection. The HBOS anomaly detection algorithm is used to obtain the abnormal moment in the track welding process. The HBOS anomaly detection algorithm is a well-known technology and will not be described in detail.
[0075] If the current data acquisition time falls within an abnormal moment in the track welding process, it is determined that the track welding equipment has malfunctioned, and an alarm will be triggered on the equipment, requiring staff to promptly diagnose and repair the welding equipment. If the current data acquisition time does not fall within an abnormal moment in the track welding process, it is determined that the track welding equipment is operating normally and welding can continue, effectively ensuring the quality of the track welding.
[0076] It is understood that references to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include the specific features, structures, or characteristics described in connection with that embodiment. Therefore, the appearance of phrases such as "in one embodiment," "in some embodiments," "in other embodiments," or "in still other embodiments" in different parts of this specification does not necessarily refer to the same embodiment, but rather means "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.
[0077] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous. Moreover, the sequence numbers of the steps in the embodiments do not imply a specific order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments in this specification.
[0078] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.
Claims
1. A method for intelligent acquisition and analysis of information on rail welding process based on Internet of Things (IoT) technology, characterized in that: Includes the following steps: Data on various welding parameters during the rail welding process are acquired through an IoT-based smart sensor array. The modal components of each welding parameter data within a preset time period before each acquisition time are extracted. Based on the dispersion of the instantaneous frequency and instantaneous amplitude of all modal components of each welding parameter before each acquisition time, and combined with the average level of similarity between the modal components of the welding parameter, the instantaneous interference complexity of each welding parameter at each acquisition time is obtained. Singular values in each welding parameter data within a preset time period before each acquisition time are extracted, and the credibility weight of each welding parameter at each acquisition time is obtained through the instantaneous interference complexity, so as to perform weighted analysis on the singular values to obtain the interference-free singularity at each acquisition time during the track welding process. The correlation between the interference removal singularity and each welding parameter during the track welding process is analyzed, and the associated fault significance at each acquisition time during the track welding process is obtained by combining the interference removal singularity. Anomaly detection was performed on the significance of associated faults at each data acquisition time to determine the fault status of the track welding equipment; The method for obtaining the instantaneous interference complexity of each welding parameter at each acquisition time is as follows: For the welding current in the welding parameters, the instantaneous disturbance complexity of the welding current at the t-th acquisition time is... The calculation method is as follows: ； In the formula, and , respectively, represent the instantaneous frequency and standard deviation of the instantaneous amplitude of all modal components in the welding current sequence at the t-th acquisition time. Let be the mean of the similarity between any two modal components in the welding current sequence at time t. To avoid constants with a denominator of zero; The confidence weight of each welding parameter at each acquisition time is the normalized result of the reciprocal of the instantaneous interference complexity of each welding parameter at each acquisition time. The method for obtaining the interference-free singularity at each acquisition time during the track welding process is as follows: ； In the formula, Let be the noise-removing singularity at the t-th acquisition time during the track welding process. , , These represent the confidence weights for welding current, welding voltage, and welding temperature at the t-th acquisition time. , , Do not include the singular values of the welding current sequence, welding voltage sequence, and welding temperature sequence at the t-th acquisition time; The method for calculating the significance of associated faults at each acquisition time during the track welding process is as follows: ； In the formula, Let be the significance of the associated fault at the t-th acquisition time during the track welding process. For exponential normalization function, The average value of the absolute covariance between the interference-free singularity sequence at the t-th acquisition time and the welding current sequence, welding voltage sequence, and welding temperature sequence is taken.
2. The intelligent acquisition and analysis method for track welding process information based on Internet of Things technology as described in claim 1, characterized in that, The welding parameters include: welding current, welding voltage, and welding temperature.
3. The intelligent acquisition and analysis method for track welding process information based on Internet of Things technology as described in claim 1, characterized in that, The method for obtaining the modal components is as follows: the welding parameter data within a preset time period before each acquisition time are combined into a welding parameter sequence for each acquisition time. The welding parameter sequence includes: welding current sequence, welding voltage sequence and welding temperature sequence. Modal decomposition is performed on each welding parameter sequence to obtain the modal components of each welding parameter sequence.
4. The intelligent acquisition and analysis method for rail welding process information based on Internet of Things technology as described in claim 1, characterized in that, The similarity between any two modal components is the cosine similarity between any two modal components.
5. The intelligent acquisition and analysis method for rail welding process information based on Internet of Things technology as described in claim 1, characterized in that, The method for obtaining the interference-removed singularity sequence is as follows: The normalized results of the de-interference singularities of all acquisition times within the preset time period before each acquisition time are arranged in chronological order to form the de-interference singularity sequence of each acquisition time.
6. The intelligent acquisition and analysis method for track welding process information based on Internet of Things technology as described in claim 1, characterized in that, The method of performing anomaly detection on the correlation fault significance at each data acquisition time to determine the fault status of the track welding equipment further includes: The correlation significance of the current acquisition time and all previous historical acquisition times during the track welding process is input into the anomaly detection algorithm to obtain the abnormal moments in the track welding process. If the current acquisition time is an abnormal moment, the track welding equipment has malfunctioned; otherwise, the track welding equipment has not malfunctioned.
Citation Information
Patent Citations
GIS disconnecting link operation state judgment method and system and computer readable storage medium
CN115453336A
Urban flood control toughness critical state identification method and system considering multiple pressure coupling
CN119226782A