SMT production line equipment fault diagnosis method and system based on Internet of Things

Abstract

The invention discloses an SMT production line equipment fault diagnosis method and system based on the Internet of Things, and belongs to the technical field of fault diagnosis. Performing Internet of Things file compiling on the SMT production line equipment cluster, and establishing a fault event information base; the log end feeds back the trigger time node of each fault code, and adds source and trigger time node marks to the fault codes so as to establish a fault feature carrier model matrix; based on the matrix, generating a fault diagnosis matrix time flow, and analyzing and calculating a self-repairing state value of the equipment fault; according to the self-repairing state value, artificial diagnosis probability values of different triggering time nodes are calculated, and an artificial diagnosis time sequence list is generated. According to the method, cluster characteristics of SMT production line equipment, diversity of fault events and complexity of fault characteristics are comprehensively considered, scientific self-repairing state evaluation and manual diagnosis intervention strategy optimization are realized, so that intelligence and high efficiency of SMT production line equipment fault diagnosis are improved, and improvement of production efficiency and equipment reliability is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of fault diagnosis, and in particular to a method and system for diagnosing faults of SMT production line equipment based on the Internet of Things. Background Art

[0002] With the rapid development of Internet of Things technology, its application in the field of intelligent manufacturing is becoming more and more extensive, especially in the surface mount technology (SMT) production line, where Internet of Things technology makes it possible to efficiently diagnose and predict equipment failures. As a key link in the electronics manufacturing industry, the stability and reliability of SMT production line equipment are directly related to production efficiency and product quality. However, SMT production line equipment is of various types, the operation process is complex, and it is easily affected by multiple factors, resulting in frequent failures, which brings inconvenience and losses to production.

[0003] Traditional SMT production line equipment fault diagnosis methods mainly rely on manual inspections and empirical judgments. This method is not only time-consuming and labor-intensive, but also difficult to guarantee diagnostic efficiency and accuracy. Although the Internet of Things technology can collect real-time operating data of SMT production line equipment, including key information such as fault codes and trigger time nodes, the existing Internet of Things-based fault diagnosis methods still have some shortcomings. For example, in terms of fault feature extraction and fault model construction, there is a lack of effective methods targeting the characteristics of SMT production line equipment, making it difficult to accurately reflect the fault behavior and evolution laws of the equipment. In addition, in the fault diagnosis process, there is a lack of scientific basis for the evaluation of the equipment's self-repair capability and the selection of the timing for manual diagnosis intervention, resulting in a waste of diagnostic resources and low diagnostic efficiency. Summary of the invention

[0004] The purpose of the present invention is to provide an SMT production line equipment fault diagnosis method and system based on the Internet of Things to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] An SMT production line equipment fault diagnosis system based on the Internet of Things, the system comprises: an SMT production line equipment cluster storage module, a fault behavior feature processing module, a fault state analysis module and a manual diagnosis module;

[0007] The SMT production line equipment cluster storage library module is used to perform IoT archiving on the SMT production line equipment cluster and establish a fault event information library for the SMT production line equipment cluster;

[0008] The fault behavior feature processing module feeds back the triggering time node of each fault code through the log end, and adds a source tag and a triggering time node tag to the fault code, establishes a fault feature carrier model matrix through the triggering time node tag, and generates a fault feature carrier matrix of different triggering time nodes under each fault event;

[0009] The fault status analysis module generates a fault diagnosis matrix time flow based on the fault feature carrier matrix, and analyzes and calculates the self-repair status value of the SMT production line equipment fault;

[0010] The manual diagnosis module analyzes and calculates the manual diagnosis probability values ​​of different trigger time nodes based on the self-repair state value to generate a manual diagnosis time series list.

[0011] Further, the SMT production line equipment cluster storage library module includes a filing unit and an information library unit;

[0012] The filing unit is used to establish an Internet of Things filing of the SMT production line equipment cluster, and assign cluster attributes to each SMT production line equipment, wherein the cluster attributes include function attributes, installation location attributes, operation status attributes, performance specification attributes and number attributes of the SMT production line equipment, wherein each SMT production line equipment is uniformly numbered according to the production line chain sequence of the SMT production line equipment cluster to form the number attributes;

[0013] The information library unit is used to establish a fault event information library of the SMT production line equipment cluster, in which the fault event information library records the fault events of the SMT production line equipment cluster and the fault codes of each SMT production line equipment, and the fault codes carry the cluster attribute information of the SMT production line equipment.

[0014] Further, the fault behavior feature processing module includes a feature marking unit and a feature recording unit;

[0015] The feature marking unit is used to count all SMT production line devices that generate fault codes in each fault event, and to feed back the triggering time node of each fault code through the log end, to add a source mark to the fault code, and to add a triggering time node mark to the source mark based on the triggering time node of the fault code;

[0016] The feature recording unit is used to establish a fault feature carrier model matrix, the column number of the fault feature carrier model matrix is ​​the number of the SMT production line equipment, and the row number of the fault feature carrier model matrix is ​​the type number of the fault code; it is used to map all trigger time node marks of the same trigger time node in the same fault event into the fault feature carrier model matrix to generate a fault feature carrier matrix under different trigger time nodes.

[0017] Further, the fault status analysis module includes a fault diagnosis matrix time flow unit and a self-repair status analysis unit;

[0018] The fault diagnosis matrix time flow unit is used to coordinate all fault feature carrier matrices generated in each fault event and generate a fault diagnosis matrix time flow;

[0019] The self-repair state analysis unit analyzes the self-repair state value of the SMT production line equipment fault based on the fault diagnosis matrix time flow.

[0020] Furthermore, the manual diagnosis module includes a manual diagnosis analysis unit and a manual diagnosis push unit;

[0021] The artificial diagnosis analysis unit is used to generate a fault diagnosis time series and calculate the artificial diagnosis probability values ​​at different trigger time nodes;

[0022] The manual diagnosis push unit is used to arrange the trigger time nodes in descending order of the manual diagnosis probability values, and generate a manual diagnosis time series list, and send it to the staff port.

[0023] A method for diagnosing faults of SMT production line equipment based on the Internet of Things, the method comprising the following steps:

[0024] Step S1: perform IoT archiving on the SMT production line equipment cluster and establish a fault event information database for the SMT production line equipment cluster;

[0025] Step S2: Feedback the triggering time node of each fault code through the log end, and add a source tag and a triggering time node tag to the fault code. Through the triggering time node tag, a fault feature carrier model matrix is ​​established to generate a fault feature carrier matrix of different triggering time nodes under each fault event;

[0026] Step S3: Based on the fault feature carrier matrix, generate the fault diagnosis matrix time flow, and analyze and calculate the self-repair state value of the SMT production line equipment fault;

[0027] Step S4: Based on the self-repair state value, analyze and calculate the manual diagnosis probability values ​​of different trigger time nodes to generate a manual diagnosis time series list.

[0028] Furthermore, the specific implementation process of step S1 includes:

[0029] Establishing an IoT file for the SMT production line equipment cluster, and assigning cluster attributes to each SMT production line equipment, wherein the cluster attributes include the function attributes, installation location attributes, operation status attributes, performance specification attributes, and number attributes of the SMT production line equipment, wherein each SMT production line equipment is uniformly numbered according to the production line chain sequence of the SMT production line equipment cluster to form the number attributes;

[0030] A fault event information library of the SMT production line equipment cluster is established, in which the fault event information library records the fault events of the SMT production line equipment cluster and the fault codes of each SMT production line equipment, and the fault codes carry the cluster attribute information of the SMT production line equipment.

[0031] Furthermore, the specific implementation process of step S2 includes:

[0032] In each fault event, all SMT production line devices that generate fault codes are counted, and the triggering time nodes of each fault code are fed back through the log terminal; a source tag is added to the fault code, recorded as F a |L e , where F a Indicates the ath fault code, L e represents the e-th SMT production line equipment; based on the trigger time node of the fault code, a trigger time node tag is added to the source tag, which is recorded as t i (F a |L e ), where t i Indicates the i-th trigger time node;

[0033] Based on the trigger time node mark, a fault feature carrier model matrix is ​​established, wherein the column number of the fault feature carrier model matrix is ​​the number of the SMT production line equipment, and the row number of the fault feature carrier model matrix is ​​the type number of the fault code; all the trigger time node marks of the same trigger time node in the x-th fault event are mapped to the fault feature carrier model matrix. During the mapping process, if there is a trigger time node mark t i (F a |L e ), then let the matrix element in the ath row and eth column of the fault feature carrier model matrix be 1. If there is no trigger time node marker t i (F a |L e ), then let the matrix element in the ath row and the eth column of the fault feature carrier model matrix be 0, and the trigger time node t is obtained. i The fault feature carrier matrix under i ).

[0034] Furthermore, the specific implementation process of step S3 includes:

[0035] Coordinate all fault feature carrier matrices generated in the xth fault event and generate a fault diagnosis matrix time stream, denoted as H x = {R(t i )|i∈[1,I]}, where I represents the total number of trigger time nodes included in the fixed diagnosis cycle;

[0036] Based on the time flow of the fault diagnosis matrix, the self-repair status value of the SMT production line equipment fault is analyzed. The analysis process is as follows:

[0037]

[0038] In the formula, CR(t i →t i ) means that if the trigger time node t i The column correlation matrix at rest, CR(t i →t i+1 ) indicates that the trigger time node t i Flow to the trigger time node t i+1 The column correlation matrix generated when i+1 ) represents the trigger time node t i+1 The fault feature carrier matrix under , T is the transposed symbol of the matrix;

[0039] Set the summation function f[·] to sum all matrix elements in the column correlation matrix and calculate the sum at the trigger time node t i+1 The self-repair status value of SMT production line equipment failure

[0040] In the above method, the column correlation is the correlation between SMT production line equipment caused by fault behavior. This correlation is used to express the fault propagation behavior of the SMT production line equipment cluster. It is foreseeable that since the collaborative process of the SMT production line equipment cluster is interactive, dynamic and continuous, the self-repair ability of the SMT production line equipment affects the fault triggering behavior of its downstream equipment. The column correlation matrix under the time flow can show the impact of this self-repair ability, and then, a column correlation matrix is ​​generated when the trigger time node is stationary and a column correlation matrix is ​​generated when the trigger time node flows; the self-repair state value is the embodiment of the self-repair fault capability of the SMT production line equipment. The larger the self-repair state value, the greater the fault propagation trend of the SMT production line equipment cluster, and then the smaller the self-repair fault capability of the SMT production line equipment.

[0041] Furthermore, the specific implementation process of step S4 includes:

[0042] A self-repair state threshold is preset. If the self-repair state value is greater than or equal to the self-repair state threshold, the trigger time node corresponding to the self-repair state value is filtered out, all the trigger time nodes filtered out in the x-th fault event are counted, and the fault diagnosis time series is generated, which is recorded as K x ={t i {i∈[1,I};

[0043] Based on the fault diagnosis time series, calculate the trigger time node t i The artificial diagnosis probability value P(t i )=

[0044]

[0045] In the formula, if the trigger time node t i Exists in the fault diagnosis time series K x In the above example, let g[if:t i ∈K x ]=1, if the trigger time node t i Does not exist in the fault diagnosis time series K x In the above example, let g[if:t i ∈K x ]=0, y represents the total number of fault events;

[0046] The trigger time nodes are arranged in descending order according to the manual diagnosis probability values, and a manual diagnosis time series list is generated and sent to the staff port.

[0047] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in the SMT production line equipment fault diagnosis method and system based on the Internet of Things provided by the present invention, the SMT production line equipment cluster is archived by the Internet of Things to establish a fault event information library; the log end feeds back the trigger time node of each fault code, and adds the source and trigger time node mark to the fault code to establish a fault feature carrier model matrix; based on the matrix, a fault diagnosis matrix time flow is generated to analyze and calculate the self-repair state value of the equipment fault; according to the self-repair state value, the manual diagnosis probability value of different trigger time nodes is calculated to generate a manual diagnosis time series list. The present invention comprehensively considers the cluster characteristics of the SMT production line equipment, the diversity of fault events and the complexity of fault characteristics, and realizes scientific self-repair state evaluation and optimization of manual diagnosis intervention strategies to improve the intelligence and efficiency of SMT production line equipment fault diagnosis, which is conducive to the improvement of production efficiency and equipment reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0049] Figure 1 It is a schematic diagram of the steps of a method for diagnosing SMT production line equipment faults based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] In the first embodiment of the present invention, a SMT production line equipment fault diagnosis system based on the Internet of Things is provided, the system comprising: an SMT production line equipment cluster storage module, a fault behavior feature processing module, a fault state analysis module and a manual diagnosis module;

[0052] The SMT production line equipment cluster storage library module is used to perform IoT archiving on the SMT production line equipment cluster and establish a fault event information library for the SMT production line equipment cluster;

[0053] Wherein, the SMT production line equipment cluster storage library module includes a filing unit and an information library unit;

[0054] The filing unit is used to establish an Internet of Things filing of the SMT production line equipment cluster, and assign cluster attributes to each SMT production line equipment, wherein the cluster attributes include function attributes, installation location attributes, operation status attributes, performance specification attributes and number attributes of the SMT production line equipment, wherein each SMT production line equipment is uniformly numbered according to the production line chain sequence of the SMT production line equipment cluster to form the number attributes;

[0055] The information library unit is used to establish a fault event information library of the SMT production line equipment cluster, in which the fault event information library records the fault events of the SMT production line equipment cluster and the fault codes of each SMT production line equipment, and the fault codes carry the cluster attribute information of the SMT production line equipment.

[0056] The fault behavior feature processing module feeds back the triggering time node of each fault code through the log end, and adds a source tag and a triggering time node tag to the fault code, establishes a fault feature carrier model matrix through the triggering time node tag, and generates a fault feature carrier matrix of different triggering time nodes under each fault event;

[0057] Wherein, the fault behavior feature processing module includes a feature marking unit and a feature recording unit;

[0058] The feature marking unit is used to count all SMT production line devices that generate fault codes in each fault event, and to feed back the triggering time node of each fault code through the log end, to add a source mark to the fault code, and to add a triggering time node mark to the source mark based on the triggering time node of the fault code;

[0059] The feature recording unit is used to establish a fault feature carrier model matrix, the column number of the fault feature carrier model matrix is ​​the number of the SMT production line equipment, and the row number of the fault feature carrier model matrix is ​​the type number of the fault code; it is used to map all trigger time node marks of the same trigger time node in the same fault event into the fault feature carrier model matrix to generate a fault feature carrier matrix under different trigger time nodes.

[0060] The fault status analysis module generates a fault diagnosis matrix time flow based on the fault feature carrier matrix, and analyzes and calculates the self-repair status value of the SMT production line equipment fault;

[0061] Wherein, the fault state analysis module includes a fault diagnosis matrix time flow unit and a self-repair state analysis unit;

[0062] The fault diagnosis matrix time flow unit is used to coordinate all fault feature carrier matrices generated in each fault event and generate a fault diagnosis matrix time flow;

[0063] The self-repair state analysis unit analyzes the self-repair state value of the SMT production line equipment fault based on the fault diagnosis matrix time flow.

[0064] The manual diagnosis module analyzes and calculates the manual diagnosis probability values ​​of different trigger time nodes based on the self-repair state value to generate a manual diagnosis time series list;

[0065] Wherein, the manual diagnosis module includes a manual diagnosis analysis unit and a manual diagnosis push unit;

[0066] The artificial diagnosis analysis unit is used to generate a fault diagnosis time series and calculate the artificial diagnosis probability values ​​at different trigger time nodes;

[0067] The manual diagnosis push unit is used to arrange the trigger time nodes in descending order of the manual diagnosis probability values, and generate a manual diagnosis time series list, and send it to the staff port.

[0068] See also Figure 1 In the second embodiment, a method for diagnosing SMT production line equipment faults based on the Internet of Things is provided, which is applied to the first embodiment, and the method includes the following steps:

[0069] Step S1: perform IoT archiving on the SMT production line equipment cluster and establish a fault event information database for the SMT production line equipment cluster;

[0070] Exemplarily, an IoT file of an SMT production line equipment cluster is established, and cluster attributes are assigned to each SMT production line equipment, wherein the cluster attributes include function attributes, installation location attributes, operation status attributes, performance specification attributes, and number attributes of the SMT production line equipment, wherein each SMT production line equipment is uniformly numbered according to the production line chain sequence of the SMT production line equipment cluster to form the number attributes;

[0071] A fault event information library of the SMT production line equipment cluster is established, in which the fault event information library records the fault events of the SMT production line equipment cluster and the fault codes of each SMT production line equipment, and the fault codes carry the cluster attribute information of the SMT production line equipment.

[0072] Step S2: Feedback the triggering time node of each fault code through the log end, and add a source tag and a triggering time node tag to the fault code. Through the triggering time node tag, a fault feature carrier model matrix is ​​established to generate a fault feature carrier matrix of different triggering time nodes under each fault event;

[0073] For example, in each fault event, all SMT production line devices that generate fault codes are counted, and the triggering time node of each fault code is fed back through the log terminal; a source tag is added to the fault code, recorded as F a |L e , where F a Indicates the ath fault code, L e represents the e-th SMT production line equipment; based on the trigger time node of the fault code, a trigger time node tag is added to the source tag, which is recorded as t i (F a |L e ), where t i Indicates the i-th trigger time node;

[0074] Based on the trigger time node mark, a fault feature carrier model matrix is ​​established, wherein the column number of the fault feature carrier model matrix is ​​the number of the SMT production line equipment, and the row number of the fault feature carrier model matrix is ​​the type number of the fault code; all the trigger time node marks of the same trigger time node in the x-th fault event are mapped to the fault feature carrier model matrix. During the mapping process, if there is a trigger time node mark t i (F a |L e ), then let the matrix element in the ath row and eth column of the fault feature carrier model matrix be 1. If there is no trigger time node marker t i (F a |Le ), then let the matrix element in the ath row and the eth column of the fault feature carrier model matrix be 0, and the trigger time node t is obtained. i The fault feature carrier matrix under i ).

[0075] Step S3: Based on the fault feature carrier matrix, generate the fault diagnosis matrix time flow, and analyze and calculate the self-repair state value of the SMT production line equipment fault;

[0076] Exemplarily, all fault feature carrier matrices generated in the xth fault event are coordinated to generate a fault diagnosis matrix time stream, denoted as H x = {R(t i )|i∈[1,I]}, where I represents the total number of trigger time nodes included in the fixed diagnosis cycle;

[0077] Based on the time flow of the fault diagnosis matrix, the self-repair status value of the SMT production line equipment fault is analyzed. The analysis process is as follows:

[0078]

[0079] In the formula, CR(t i →t i ) means that if the trigger time node t i The column correlation matrix at rest, CR(t i →t i+1 ) indicates that the trigger time node t i Flow to the trigger time node t i+1 The column correlation matrix generated when i+1 ) represents the trigger time node t i+1 The fault feature carrier matrix under , T is the transposed symbol of the matrix;

[0080] Set the summation function f[·] to sum all matrix elements in the column correlation matrix and calculate the sum at the trigger time node t i+1 The self-repair status value of SMT production line equipment failure

[0081] Step S4: Based on the self-repair state value, analyze and calculate the manual diagnosis probability values ​​of different trigger time nodes to generate a manual diagnosis time series list;

[0082] Exemplarily, a self-repair state threshold is preset. If the self-repair state value is greater than or equal to the self-repair state threshold, the trigger time node corresponding to the self-repair state value is screened out, all the trigger time nodes screened out in the x-th fault event are counted, and a fault diagnosis time series is generated, which is recorded as K x ={t i |i∈[1,I};

[0083] Based on the fault diagnosis time series, calculate the trigger time node t i The probability of manual diagnosis

[0084] In the formula, if the trigger time node t i Exists in the fault diagnosis time series K x In the above example, let g[if:t i ∈K x ]=1, if the trigger time node t i Does not exist in the fault diagnosis time series K x In the above example, let g[if:t i ∈K x ]=0, y represents the total number of fault events;

[0085] The trigger time nodes are arranged in descending order according to the manual diagnosis probability values, and a manual diagnosis time series list is generated and sent to the staff port.

[0086] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0087] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for diagnosing SMT production line equipment faults based on the Internet of Things, characterized in that: The method comprises the following steps: Step S1: perform IoT archiving on the SMT production line equipment cluster and establish a fault event information database for the SMT production line equipment cluster; Step S2: Feedback the triggering time node of each fault code through the log end, and add a source tag and a triggering time node tag to the fault code. Through the triggering time node tag, a fault feature carrier model matrix is ​​established to generate a fault feature carrier matrix of different triggering time nodes under each fault event; Step S3: Based on the fault feature carrier matrix, generate the fault diagnosis matrix time flow, and analyze and calculate the self-repair state value of the SMT production line equipment fault; Step S4: Based on the self-repair state value, analyze and calculate the manual diagnosis probability values ​​of different trigger time nodes to generate a manual diagnosis time series list.

2. According to the method for diagnosing faults of SMT production line equipment based on the Internet of Things in claim 1, it is characterized in that: The specific implementation process of step S1 includes: Establishing an IoT file for the SMT production line equipment cluster, and assigning cluster attributes to each SMT production line equipment, wherein the cluster attributes include the function attributes, installation location attributes, operation status attributes, performance specification attributes, and number attributes of the SMT production line equipment, wherein each SMT production line equipment is uniformly numbered according to the production line chain sequence of the SMT production line equipment cluster to form the number attributes; A fault event information library of the SMT production line equipment cluster is established, in which the fault event information library records the fault events of the SMT production line equipment cluster and the fault codes of each SMT production line equipment, and the fault codes carry the cluster attribute information of the SMT production line equipment.

3. The method for diagnosing faults of SMT production line equipment based on the Internet of Things according to claim 1, characterized in that: The specific implementation process of step S2 includes: In each fault event, all SMT production line devices that generate fault codes are counted, and the triggering time nodes of each fault code are fed back through the log terminal; a source tag is added to the fault code, recorded as F a |L e , where F a Indicates the ath fault code, L e represents the e-th SMT production line equipment; based on the trigger time node of the fault code, a trigger time node tag is added to the source tag, which is recorded as t i (F a |L e ), where t i Indicates the i-th trigger time node; Based on the trigger time node mark, a fault feature carrier model matrix is ​​established, wherein the column number of the fault feature carrier model matrix is ​​the number of the SMT production line equipment, and the row number of the fault feature carrier model matrix is ​​the type number of the fault code; all the trigger time node marks of the same trigger time node in the x-th fault event are mapped to the fault feature carrier model matrix. During the mapping process, if there is a trigger time node mark t i (F a |L e ), then let the matrix element in the ath row and eth column of the fault feature carrier model matrix be 1. If there is no trigger time node marker t i (F a |L e ), then let the matrix element in the ath row and the eth column of the fault feature carrier model matrix be 0, and the trigger time node t is obtained. i The fault feature carrier matrix under i ).

4. The method for diagnosing faults of SMT production line equipment based on the Internet of Things according to claim 3 is characterized in that: The specific implementation process of step S3 includes: Coordinate all fault feature carrier matrices generated in the xth fault event and generate a fault diagnosis matrix time stream, denoted as H x = {R(t i )|i∈[1,I]}, where I represents the total number of trigger time nodes included in the fixed diagnosis cycle; Based on the time flow of the fault diagnosis matrix, the self-repair status value of the SMT production line equipment fault is analyzed. The analysis process is as follows: In the formula, CR(t i →t i ) means that if the trigger time node t i The column correlation matrix at rest, CR(t i →t i+1 ) indicates that the trigger time node t i Flow to the trigger time node t i+1 The column correlation matrix generated when i+1 ) represents the trigger time node t i+1 The fault feature carrier matrix under , T is the transposed symbol of the matrix; Set the summation function f[·] to sum all matrix elements in the column correlation matrix and calculate the sum at the trigger time node t i+1 The self-repair status value of SMT production line equipment failure 5. The method for diagnosing faults of SMT production line equipment based on the Internet of Things according to claim 4 is characterized in that: The specific implementation process of step S4 includes: A self-repair state threshold is preset. If the self-repair state value is greater than or equal to the self-repair state threshold, the trigger time node corresponding to the self-repair state value is filtered out, and all the trigger time nodes filtered out in the x-th fault event are counted, and a fault diagnosis time series is generated, which is recorded as K x ={t i |i∈[1,I}; Based on the fault diagnosis time series, calculate the trigger time node t i The probability of manual diagnosis In the formula, if the trigger time node t i Exists in the fault diagnosis time series K x In the above example, let g[if:t i ∈K x ]=1, if the trigger time node t i Does not exist in the fault diagnosis time series K x In the above example, let g[if:t i ∈K x ]=0, y represents the total number of fault events; The trigger time nodes are arranged in descending order according to the manual diagnosis probability values, and a manual diagnosis time series list is generated and sent to the staff port.

6. An SMT production line equipment fault diagnosis system based on the Internet of Things, executing an SMT production line equipment fault diagnosis method based on the Internet of Things as described in any one of claims 1-5, characterized in that: The system includes: an SMT production line equipment cluster storage module, a fault behavior feature processing module, a fault state analysis module and a manual diagnosis module; The SMT production line equipment cluster storage library module is used to perform IoT archiving on the SMT production line equipment cluster and establish a fault event information library for the SMT production line equipment cluster; The fault behavior feature processing module feeds back the triggering time node of each fault code through the log end, and adds a source tag and a triggering time node tag to the fault code, establishes a fault feature carrier model matrix through the triggering time node tag, and generates a fault feature carrier matrix of different triggering time nodes under each fault event; The fault status analysis module generates a fault diagnosis matrix time flow based on the fault feature carrier matrix, and analyzes and calculates the self-repair status value of the SMT production line equipment fault; The manual diagnosis module analyzes and calculates the manual diagnosis probability values ​​of different trigger time nodes based on the self-repair state value to generate a manual diagnosis time series list.

7. The SMT production line equipment fault diagnosis system based on the Internet of Things according to claim 6 is characterized in that: The SMT production line equipment cluster storage library module includes a filing unit and an information library unit; The filing unit is used to establish an Internet of Things filing of the SMT production line equipment cluster, and assign cluster attributes to each SMT production line equipment, wherein the cluster attributes include function attributes, installation location attributes, operation status attributes, performance specification attributes and number attributes of the SMT production line equipment, wherein each SMT production line equipment is uniformly numbered according to the production line chain sequence of the SMT production line equipment cluster to form the number attributes; The information library unit is used to establish a fault event information library of the SMT production line equipment cluster, in which the fault event information library records the fault events of the SMT production line equipment cluster and the fault codes of each SMT production line equipment, and the fault codes carry the cluster attribute information of the SMT production line equipment.

8. The SMT production line equipment fault diagnosis system based on the Internet of Things according to claim 6 is characterized in that: The fault behavior feature processing module includes a feature marking unit and a feature recording unit; The feature marking unit is used to count all SMT production line devices that generate fault codes in each fault event, and to feed back the triggering time node of each fault code through the log end, to add a source mark to the fault code, and to add a triggering time node mark to the source mark based on the triggering time node of the fault code; The feature recording unit is used to establish a fault feature carrier model matrix, wherein the column number of the fault feature carrier model matrix is ​​the serial number of the SMT production line equipment, and the row number of the fault feature carrier model matrix is ​​the type number of the fault code; It is used to map all trigger time node labels of the same trigger time node in the same fault event into the fault feature carrier model matrix to generate a fault feature carrier matrix under different trigger time nodes.

9. The SMT production line equipment fault diagnosis system based on the Internet of Things according to claim 6 is characterized in that: The fault state analysis module includes a fault diagnosis matrix time flow unit and a self-repair state analysis unit; The fault diagnosis matrix time flow unit is used to coordinate all fault feature carrier matrices generated in each fault event and generate a fault diagnosis matrix time flow; The self-repair state analysis unit analyzes the self-repair state value of the SMT production line equipment fault based on the fault diagnosis matrix time flow.

10. The SMT production line equipment fault diagnosis system based on the Internet of Things according to claim 6, characterized in that: The manual diagnosis module includes a manual diagnosis analysis unit and a manual diagnosis push unit; The artificial diagnosis analysis unit is used to generate a fault diagnosis time series and calculate the artificial diagnosis probability values ​​at different trigger time nodes; The manual diagnosis push unit is used to arrange the trigger time nodes in descending order of the manual diagnosis probability values, and generate a manual diagnosis time series list, and send it to the staff port.

Images