Track welding process information intelligent acquisition and analysis method based on Internet of Things technology

Abstract

The invention relates to the technical field of welding fault analysis, in particular to a rail welding process information intelligent collection and analysis method based on the Internet of Things technology, and the method comprises the steps: obtaining the data of each welding parameter in the rail welding process through an Internet of Things intelligent sensor group; according to the discrete degree of all modal component data in each welding parameter before each collection moment, the instantaneous interference complexity of each welding parameter at each collection moment is obtained in combination with the average level of the similarity degree between the modal components of the welding parameters, and then the credibility weight of each welding parameter at each collection moment is obtained; the method comprises the following steps: analyzing the interference removing singularity of each acquisition moment in the track welding process to obtain the interference removing singularity of each acquisition moment in the track welding process, analyzing the correlation between the interference removing singularity and each welding parameter in the track welding process to obtain the correlation fault significance of each acquisition moment in the track welding process, and judging the fault condition of the track welding equipment based on the correlation fault significance. The accuracy of intelligent analysis in the track welding process can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of welding failure analysis, and specifically to a method for intelligent collection and analysis of rail welding process information based on Internet of Things technology. Background Art

[0002] During the orbital welding process, the Internet of Things technology is used to intelligently collect orbital welding process information, and anomaly detection algorithms are used for analysis and processing. Abnormal faults of welding equipment during the welding process can be detected in real time, so that the welding equipment can be diagnosed and repaired in time, which can effectively avoid the occurrence of welding defects during the orbital welding process.

[0003] Currently, IoT technology is being applied to the welding field. Intelligent sensors on welding equipment collect data on the orbital welding process, and anomaly detection algorithms are used to analyze and process this information, enabling remote monitoring and management of the welding process. However, since the collection of orbital welding process information is easily interfered with by mechanical noise from the equipment, the collected orbital welding information can contain certain errors. Directly using this collected orbital welding information to detect abnormalities in welding equipment can easily lead to inaccurate detection of welding equipment faults, making it impossible to diagnose and repair the welding equipment in a timely manner, and thus making it impossible to ensure the quality of orbital welding. Summary of the Invention

[0004] In order to solve the above technical problems, this application provides an intelligent collection and analysis method for rail welding process information based on Internet of Things technology to solve the existing problems.

[0005] The intelligent collection and analysis method of rail welding process information based on Internet of Things technology in this application adopts the following technical solutions: One embodiment of the present application provides a method for intelligently collecting and analyzing rail welding process information based on Internet of Things technology, comprising the following steps: Obtain data on various welding parameters during rail welding through an IoT smart sensor group; The modal components of the data of each welding parameter within a preset time period before each acquisition moment are extracted. The instantaneous interference complexity of each welding parameter at each acquisition moment is obtained based on the discrete degree of instantaneous frequency and instantaneous amplitude of all modal components in each welding parameter before each acquisition moment, combined with the average level of similarity between the modal components of the welding parameters. Extracting singular values ​​from each welding parameter data within a preset time period before each acquisition moment, and obtaining the credibility weight of each welding parameter at each acquisition moment through the instantaneous interference complexity, so as to perform weighted analysis on the singular values ​​and obtain the interference-free singularity at each acquisition moment during the rail welding process; Analyze the correlation between the interference removal singularity and each welding parameter during the rail welding process, and obtain the associated fault significance at each acquisition moment during the rail welding process in combination with the interference removal singularity; Anomaly detection is performed on the associated fault significance at each acquisition moment to determine the fault condition of the rail welding equipment.

[0006] Preferably, the welding parameters include: welding current, welding voltage and welding temperature.

[0007] Preferably, the method for obtaining the modal components is: forming the data of the welding parameters within a preset time period before each acquisition moment into a welding parameter sequence at each acquisition moment, the welding parameter sequence including: a welding current sequence, a welding voltage sequence and a welding temperature sequence, performing modal decomposition on each welding parameter sequence to obtain the modal components of each welding parameter sequence.

[0008] Preferably, the method for obtaining the instantaneous interference complexity of each welding parameter at each acquisition moment is: For the welding current in the welding parameters, the instantaneous interference complexity of the welding current at the tth acquisition moment is The calculation method is: ; Where, and are the standard deviations of the instantaneous frequency and instantaneous amplitude of all modal components in the welding current sequence at the tth acquisition moment, is the mean of the similarity between any two modal components in the welding current sequence at the tth acquisition moment, To avoid a constant with a zero denominator.

[0009] Preferably, the similarity between any two modal components is the cosine similarity between any two modal components.

[0010] Preferably, the credibility weight of each welding parameter at each acquisition moment is a normalized result of the inverse of the instantaneous interference complexity of each welding parameter at each acquisition moment.

[0011] Preferably, the method for obtaining the interference removal singularity at each acquisition moment during the orbital welding process is: ; Where, is the interference removal singularity at the tth acquisition moment during the rail welding process, 、 、 are the credibility weights of welding current, welding voltage and welding temperature at the tth acquisition moment, 、 、 are the singular values ​​of the welding current sequence, welding voltage sequence, and welding temperature sequence at the tth acquisition moment, respectively.

[0012] Preferably, the calculation method of the correlation fault significance at each acquisition moment in the track welding process is: ; Where, is the significance of the associated fault at the tth acquisition moment in the rail welding process, is the exponential normalization function, The average value of the absolute value of the covariance between the interference-removed singularity sequence at the t-th acquisition moment and the welding current sequence, welding voltage sequence, and welding temperature sequence is taken.

[0013] Preferably, the method for obtaining the interference-removed singularity sequence is: Normalized results of the interference removal singularity of all acquisition moments within a preset time period before each acquisition moment are arranged in chronological order to form an interference removal singularity sequence of each acquisition moment.

[0014] Preferably, the abnormal detection of the associated fault significance at each acquisition moment to determine the fault condition of the rail welding equipment further includes: The associated fault significance of the current acquisition moment and all previous historical acquisition moments in the rail welding process is input into the anomaly detection algorithm to obtain the abnormal moment in the rail welding process. If the current acquisition moment is an abnormal moment, the rail welding equipment has a fault; otherwise, the rail welding equipment has not a fault.

[0015] This application has at least the following beneficial effects: This application takes into account that when the welding parameters are interfered with by external noise to a high degree of complexity, the differences between the 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 the welding equipment; This application uses adaptive credibility weights for welding current, welding voltage, and welding temperature, and uses a weighted approach to measure the singularity characteristics after interference removal during the welding process. This method obtains the interference-free singularity at each acquisition moment, effectively reducing complex interference from external influences during the welding process and improving the accuracy of subsequent real-time detection of abnormal faults in welding equipment. This application accurately measures the significant characteristics of associated faults of welding equipment during the orbital welding process based on the interference removal singularity at each acquisition moment and the correlation characteristics between the interference removal singularity and welding parameters, reduces the adverse effects of complex interference from external environmental factors on abnormal fault detection, and improves the significance of associated faults of welding equipment during the orbital welding process, thereby utilizing the anomaly detection algorithm to more accurately detect abnormal faults in orbital welding equipment and issue early warnings through alarms, so that staff can diagnose and repair the welding equipment in a timely manner, thereby ensuring the quality of orbital welding. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 This is a flowchart of the steps of the intelligent collection and analysis method of rail welding process information based on Internet of Things technology provided in this application. DETAILED DESCRIPTION

[0018] To further illustrate the technical means and effectiveness of this application's implementation of the intended invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of the method for intelligently collecting and analyzing rail welding process information based on IoT technology proposed in this application. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0019] Unless otherwise defined, terms such as "comprises," "comprising," or any other variants thereof are intended to encompass non-exclusive inclusion, such that a circuit structure, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such article or device. In the absence of further restrictions, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the article or device comprising the element. In addition, the term "and\or" as used herein includes any and all combinations of one or more related listed items. All technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application pertains.

[0020] The specific scheme of the method for intelligent collection and analysis of rail welding process information based on Internet of Things technology provided by this application is described in detail below with reference to the accompanying drawings.

[0021] An embodiment of the present application provides an intelligent collection and analysis method for rail welding process information based on Internet of Things technology. For details, please refer to Figure 1 , including the following steps: Step 1: Obtain data on various welding parameters during the orbital welding process through the IoT smart sensor group.

[0022] Rail welding is performed using industrially manufactured rail welding equipment, which consists of a welding machine, base, travel wheels, stepper motor, gears, grinding wheels, support frame, and other components. Using IoT technology, an intelligent sensor group is installed on the rail welding equipment to collect data on various welding parameters during the rail welding process. In this embodiment, the intelligent sensor group includes a current sensor, a voltage sensor, and a temperature sensor. Welding parameters include welding current, welding voltage, and welding problems. The intelligent sensor group collects welding parameter data in real time during the rail welding process, with a sampling frequency of 100 Hz.

[0023] In the process of manufacturing orbital welding equipment, the Internet of Things technology is applied to the welding equipment. Through smart sensors and communication equipment, the operating status, welding parameters and other information of the welding equipment can be transmitted to the cloud server in real time. The operator processes the real-time welding parameter information on the terminal device and promptly discovers abnormal faults of the welding equipment.

[0024] Therefore, the welding current, welding voltage and welding temperature during the orbital welding process are collected in real time by the intelligent sensor group on the manufactured orbital 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 to eliminate the interference of different dimensions of data on subsequent analysis and processing.

[0025] Furthermore, in this embodiment, the normalized welding parameter data obtained before each acquisition moment are stored in chronological order, and the welding parameter sequences of each acquisition moment are obtained in sequence, including: welding current sequence, welding voltage sequence and welding temperature sequence. Among them, the normalization processing method can be other normalization methods such as exponential normalization or range normalization. This embodiment adopts the exponential normalization method for normalization processing.

[0026] It should be noted that in order to avoid the problem of large amount of calculation caused by excessive data, in this embodiment, the data of welding parameters within a preset time before each collection moment are combined into a welding parameter sequence for each collection moment. The preset time in this embodiment is 5 seconds.

[0027] Step 2: Extract the modal components of the data of each welding parameter before each acquisition moment. According to the discrete degree of instantaneous frequency and instantaneous amplitude of all modal components in each welding parameter before each acquisition moment, combined with the average level of similarity between the modal components of the welding parameters, the instantaneous interference complexity of each welding parameter at each acquisition moment is obtained.

[0028] Because the collection of track welding process information is susceptible to interference from mechanical noise from the equipment, this information can contain errors. Existing technologies do not fully consider the interference characteristics of welding information when analyzing and processing welding process information, resulting in inaccurate detection of welding equipment anomalies and faults. Therefore, it is necessary to analyze the interference characteristics of welding information to improve the accuracy of welding equipment anomaly and fault detection.

[0029] Taking the welding current sequence as an example, in this embodiment, the welding current sequence is input into the HHT Hilbert-Huang Transform (HHT Hilbert-Huang Transform), and the HHT Hilbert-Huang Transform is used to obtain the various modal components of the welding current sequence, and the instantaneous frequency and instantaneous amplitude of each modal component are calculated. Among them, the HHT Hilbert-Huang Transform is a well-known technology and is not described in detail.

[0030] Generally speaking, 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 more complex the external interference to the welding current is, and the more likely it is to affect the authenticity of the orbital welding information. At this time, the credibility of abnormal faults in the welding current is lower.

[0031] 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.

[0032] Through the above analysis, the instantaneous interference complexity of the welding current at each acquisition moment is calculated: ; Where, is the instantaneous interference complexity of the welding current at the tth acquisition moment, and are the standard deviations of the instantaneous frequency and instantaneous amplitude of all modal components in the welding current sequence at the tth acquisition moment, is the mean of the similarity between any two modal components in the welding current sequence at the tth acquisition moment, To avoid the constant with a denominator of zero, the value in the range of (0.001, 0.01) is used. The value of is 0.001.

[0033] The more complex the instantaneous interference of the welding current caused by external influences, the lower the credibility of the abnormal fault of the welding current. When measuring the abnormal fault characteristics of the manufactured welding equipment, the weight at this time should be reduced, thereby improving the accuracy of abnormal fault detection on the manufactured welding equipment.

[0034] Similarly, the above method of this embodiment is used to analyze the welding voltage sequence and the welding temperature sequence respectively, and the instantaneous interference complexity of the welding voltage and the welding temperature at each acquisition moment is obtained respectively.

[0035] Step 3: Extract the singular values ​​in the welding parameter data before each acquisition moment, and obtain the credibility weight of each welding parameter at each acquisition moment through the instantaneous interference complexity, so as to perform weighted analysis on the singular values ​​to obtain the interference-free singularity at each acquisition moment in the rail welding process.

[0036] Furthermore, SVD singular value decomposition (SVD) is performed on the welding current sequence, welding voltage sequence, and welding temperature sequence at each acquisition moment. The singular values ​​of the welding current sequence, welding voltage sequence, and welding temperature sequence at each acquisition moment are obtained using the SVD singular value decomposition algorithm. The larger the singular value, the higher the singularity characteristic of the corresponding welding parameter data, and the more likely the welding equipment manufactured at this time is to experience abnormal failures. The SVD singular value decomposition is a well-known technology and is not described in detail here.

[0037] In order to more accurately measure the singularity characteristics of the orbital welding process, the inverse of the instantaneous interference complexity of the welding current, welding voltage, and welding temperature at each acquisition moment is exponentially normalized, and the credibility weights of the welding current, welding voltage, and welding temperature at each acquisition moment are obtained in turn. The smaller the credibility weight, the greater the complex interference characteristics of the corresponding welding parameters affected by external factors, and the greater the interference in analyzing the singularity in the orbital welding process. Therefore, the smaller the credibility weight is set, the lower the proportion of singularity caused by complex interference of external factors is, and the accuracy of measuring the singularity in the orbital welding process is improved.

[0038] Through the above analysis, the interference removal singularity at each acquisition moment in the track welding process is calculated: ; Where, is the interference removal singularity at the tth acquisition moment during the rail welding process, 、 、 are the credibility weights of welding current, welding voltage and welding temperature at the tth acquisition moment, 、 、 are the singular values ​​of the welding current sequence, welding voltage sequence, and welding temperature sequence at the tth acquisition moment, respectively.

[0039] In this embodiment, the credibility weights of the welding current, welding voltage and welding temperature are adaptively set, and the singularity characteristics after interference removal in the welding process are measured by weighted summation to obtain the interference-free singularity at each acquisition moment. This can significantly reduce the complex interference of external influences in the welding process and improve the accuracy of subsequent real-time detection of abnormal faults of the welding equipment, so that the welding equipment can be diagnosed and repaired in a timely manner, and the quality of orbital welding can be ensured.

[0040] Step 4: Analyze the correlation between the interference removal singularity and each welding parameter during the orbital welding process, and combine the interference removal singularity to obtain the associated fault significance at each acquisition moment during the orbital welding process.

[0041] Under normal circumstances, the orbital welding process is relatively stable, and the manufactured orbital welding equipment does not have abnormal faults. However, if the welding equipment has abnormal faults, the welding current, welding voltage and welding temperature will all produce characteristic changes related to abnormal characteristics. The greater the singularity after interference removal, the more it can reflect that the welding equipment has abnormal faults. The welding equipment should be diagnosed and repaired in time to ensure the quality of orbital welding.

[0042] Furthermore, in this embodiment, the interference removal singularity at each acquisition moment is subjected to exponential normalization. For each acquisition moment, the normalized results of the interference removal singularity at all acquisition moments within 5 seconds before each acquisition moment are arranged in chronological order to form a interference removal singularity sequence at each acquisition moment.

[0043] Among them, the interference-free singularity sequence reflects the characteristic changes of the singularity after removing the interference of external influences during the orbital welding process. The stronger the correlation between the characteristic changes of the singularity during the orbital welding process and the welding current, welding voltage and welding temperature, the more significant it is that an abnormal fault has occurred in the orbital welding equipment at this time.

[0044] Therefore, the correlation between the interference-removed singularity sequence and the welding current sequence, welding voltage sequence, and welding temperature sequence at each acquisition moment is calculated respectively. The correlation degree can be measured by the Pearson correlation coefficient, covariance, or grey relational degree. In this embodiment, the covariance is selected to measure the correlation degree.

[0045] Through the above analysis, the correlation fault significance of each acquisition moment in the rail welding process is calculated: ; Where, is the significance of the associated fault at the tth acquisition moment in the rail welding process, is the exponential normalization function, The average value of the absolute value of the covariance between the interference-removed singularity sequence at the t-th acquisition moment and the welding current sequence, welding voltage sequence, and welding temperature sequence is taken.

[0046] It can be understood that the significance of associated faults reflects the significant characteristics of associated faults in welding equipment during orbital welding. If the singularity characteristics after interference removal in the welding process are greater, and the correlation between the characteristic changes of the singularity in the orbital welding process and the welding current, welding voltage and welding temperature is higher, it can more significantly indicate that an associated abnormal fault has occurred in the orbital welding equipment at this time.

[0047] Step 5: Perform anomaly detection on the associated fault significance at each acquisition moment to determine the fault condition of the rail welding equipment.

[0048] Through the above process of this embodiment, the significance of associated faults at different acquisition moments during the welding process can be obtained, so as to avoid the inaccurate detection of abnormal faults of the rail welding equipment caused by complex interference from external environmental factors during the rail welding process, thereby improving the accuracy of abnormal fault detection of the rail welding equipment.

[0049] At the same time, as the track welding time progresses, if the welding equipment at the current moment experiences an abnormal fault, the fault feature significance characteristics will show a large outlier phenomenon. Therefore, in order to more accurately detect abnormal faults of the welding equipment in real time during the welding process, the associated fault significance of 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 anomaly detection algorithm (Histogram-based Outlier Score) or the LOF anomaly detection algorithm (Local Outlier Factor). In this embodiment, the HBOS anomaly detection algorithm is used for anomaly detection and is used to obtain abnormal moments during the track welding process. The HBOS anomaly detection algorithm is a well-known technology and will not be described in detail.

[0050] If the current acquisition moment is an abnormal moment in the rail welding process, it is judged that the rail welding equipment has an abnormal fault at this time, and an alarm is issued through the rail welding equipment. The staff is required to diagnose and repair the welding equipment in time; if the current acquisition moment is not an abnormal moment in the rail welding process, it is judged that the rail welding equipment is operating normally at this time, and the rail welding can continue, which can effectively ensure the quality of the rail welding.

[0051] It is understood that references to "one embodiment" or "some embodiments" in the present specification mean that one or more embodiments of the present application include a particular feature, structure, or characteristic described in conjunction with that embodiment. Thus, if "in one embodiment," "in some embodiments," "in other embodiments," or "in other embodiments" appear in different places in this specification, they do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and their variations all mean "including but not limited to," unless otherwise specifically emphasized.

[0052] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above description is of a specific embodiment of this specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-tasking and parallel processing are also possible or may be advantageous. At the same time, the size of the sequence number of each step in the embodiment does not mean the 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.

[0053] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. The intelligent collection and analysis method of rail welding process information based on Internet of Things technology is characterized by: The following steps are involved: Obtain data on various welding parameters during rail welding through an IoT smart sensor group; The modal components of the data of each welding parameter within a preset time period before each acquisition moment are extracted. The instantaneous interference complexity of each welding parameter at each acquisition moment is obtained based on the discrete degree of instantaneous frequency and instantaneous amplitude of all modal components in each welding parameter before each acquisition moment, combined with the average level of similarity between the modal components of the welding parameters. Extracting singular values ​​from each welding parameter data within a preset time period before each acquisition moment, and obtaining the credibility weight of each welding parameter at each acquisition moment through the instantaneous interference complexity, so as to perform weighted analysis on the singular values ​​and obtain the interference-free singularity at each acquisition moment during the rail welding process; Analyze the correlation between the interference removal singularity and each welding parameter during the rail welding process, and obtain the associated fault significance at each acquisition moment during the rail welding process in combination with the interference removal singularity; Anomaly detection is performed on the associated fault significance at each acquisition moment to determine the fault condition of the rail welding equipment.

2. The method for intelligent collection and analysis of rail welding process information based on Internet of Things technology according to claim 1, characterized in that: The welding parameters include welding current, welding voltage and welding temperature.

3. The method for intelligent collection and analysis of rail welding process information based on Internet of Things technology according to claim 1 is characterized in that: The method for obtaining the modal components is as follows: the data of the welding parameters within a preset time period before each acquisition moment are combined into a welding parameter sequence at each acquisition moment, the welding parameter sequence including a welding current sequence, a welding voltage sequence, and a welding temperature sequence; each welding parameter sequence is modally decomposed to obtain the modal components of each welding parameter sequence.

4. The method for intelligent collection and analysis of rail welding process information based on Internet of Things technology according to claim 3 is characterized in that: The method for obtaining the instantaneous interference complexity of each welding parameter at each acquisition moment is: For the welding current in the welding parameters, the instantaneous interference complexity of the welding current at the tth acquisition moment is The calculation method is: ； Where, and are the standard deviations of the instantaneous frequency and instantaneous amplitude of all modal components in the welding current sequence at the tth acquisition moment, is the mean of the similarity between any two modal components in the welding current sequence at the tth acquisition moment, To avoid a constant with a zero denominator.

5. The method for intelligent collection and analysis of rail welding process information based on Internet of Things technology according to claim 4 is characterized in that: The similarity between any two modal components is the cosine similarity between any two modal components.

6. The method for intelligent collection and analysis of rail welding process information based on Internet of Things technology according to claim 1, characterized in that: The credibility weight of each welding parameter at each acquisition moment is a normalized result of the inverse of the instantaneous interference complexity of each welding parameter at each acquisition moment.

7. The method for intelligent collection and analysis of rail welding process information based on Internet of Things technology according to claim 3 is characterized in that: The method for obtaining the interference-free singularity at each acquisition moment during the track welding process is as follows: ； Where, is the interference removal singularity at the tth acquisition moment during the rail welding process, 、 、 are the credibility weights of welding current, welding voltage and welding temperature at the tth acquisition moment, 、 、 are the singular values ​​of the welding current sequence, welding voltage sequence, and welding temperature sequence at the tth acquisition moment, respectively.

8. The method for intelligent collection and analysis of rail welding process information based on Internet of Things technology according to claim 3 is characterized in that: The calculation method of the correlation fault significance at each acquisition moment in the track welding process is: ； Where, is the significance of the associated fault at the tth acquisition moment in the rail welding process, is the exponential normalization function, The average value of the absolute value of the covariance between the interference-removed singularity sequence at the t-th acquisition moment and the welding current sequence, welding voltage sequence, and welding temperature sequence is taken.

9. The method for intelligent collection and analysis of rail welding process information based on Internet of Things technology according to claim 1, characterized in that: The method for obtaining the interference-removed singularity sequence is: Normalized results of the interference removal singularity of all acquisition moments within a preset time period before each acquisition moment are arranged in chronological order to form an interference removal singularity sequence of each acquisition moment.

10. The method for intelligent collection and analysis of rail welding process information based on Internet of Things technology according to claim 1, characterized in that: The abnormal detection of the associated fault significance at each acquisition moment to determine the fault condition of the rail welding equipment further includes: The associated fault significance of the current acquisition moment and all previous historical acquisition moments in the rail welding process is input into the anomaly detection algorithm to obtain the abnormal moment in the rail welding process. If the current acquisition moment is an abnormal moment, the rail welding equipment has a fault; otherwise, the rail welding equipment has not a fault.

Images