Method for avoiding loose plugging and switch for communication engineering

Abstract

The invention is applicable to the technical field of switches, and particularly relates to a method for avoiding loose plugging and a switch for communication engineering, and the method comprises the steps: obtaining historical fault interface signal data; dividing the historical fault interface signal data to obtain classified signal data; performing feature extraction according to the classified signal data to obtain classified signal features; and collecting real-time interface signals, carrying out feature extraction on the real-time interface signals to obtain real-time signal features, and judging whether each interface is loosened or not according to the real-time signal features and the classification signal features. According to the invention, waveform extraction is carried out according to historical fault interface signal data, corresponding waveform features of the interface in each state are determined, feature extraction is carried out on real-time transmission signals, and then feature comparison is carried out, so that the current state of each interface is determined, whether loosening exists is determined, and early warning is carried out in time before complete loosening. And the normal operation of equipment is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of switches, and particularly relates to a method for avoiding plugging looseness and a switch for communication engineering. Background Art

[0002] A switch is a network device for forwarding electrical (optical) signals. It can provide an exclusive electrical signal path for any two network nodes connected to the switch. The most common switch is an Ethernet switch. Other common ones include telephone voice switches, fiber optic switches, etc.

[0003] Switching is a general term for the technology that, according to the needs of information transmission between two communication ends, manually or automatically by equipment, sends the information to be transmitted to the corresponding route that meets the requirements. According to different working positions, switches can be divided into wide area network switches and local area network switches. The wide area network switch is a device that completes the information switching function in a communication engineering switch. It is applied at the data link layer. The switch has multiple ports, and each port has a bridging function and can be connected to a local area network or a high-performance server or workstation.

[0004] During the current use of the switch, multiple connectors are plugged into one switch at the same time. During long-term use, the connectors are inevitably loosened, and the loosening can only be detected after obvious abnormal phenomena occur, thus affecting the normal use of the device. Summary of the Invention

[0005] The purpose of the embodiment of the present invention is to provide a method for avoiding plugging looseness, aiming to solve the problem that in the prior art, the loosening can only be detected after obvious abnormal phenomena occur, affecting the normal use of the device.

[0006] The embodiment of the present invention is implemented as follows. A method for avoiding plugging looseness, the method includes:

[0007] Obtain historical fault interface signal data;

[0008] Divide the historical fault interface signal data to obtain classified signal data, where the classified signal data includes fault signal data, abnormal signal data, and normal signal data;

[0009] Extract features according to the classified signal data to obtain classified signal features, where the classified signal features at least include fault signal features, abnormal signal features, and normal signal features;

[0010] Collect real-time interface signals, extract features from the real-time interface signals to obtain real-time signal features, and determine whether each interface is loose according to the real-time signal features and the classified signal features.

[0011] Preferably, the step of dividing the historical fault interface signal data to obtain classified signal data specifically includes:

[0012] Identify the interface number in the historical fault interface signal data, and extract the interface signal data according to the interface number;

[0013] Determine the data division position according to the interface signal data corresponding to each interface number;

[0014] Divide the interface signal data according to the division position to obtain classified signal data.

[0015] Preferably, the step of extracting features from the classified signal data to obtain classified signal features specifically includes:

[0016] Represent the fault signal data, abnormal signal data, and normal signal data as waveform diagrams;

[0017] Classify the waveform diagrams according to the data type to obtain three types of waveform diagrams;

[0018] Extract features from all waveform diagrams of each type to obtain classified signal features.

[0019] Preferably, the step of collecting real-time interface signals, extracting features from the real-time interface signals to obtain real-time signal features, and determining whether each interface is loose according to the real-time signal features and classified signal features specifically includes:

[0020] Collect real-time interface signals and draw a real-time waveform diagram according to the real-time interface signals;

[0021] Extract features from the real-time waveform diagram to obtain real-time signal features;

[0022] Calculate the matching degree between the real-time signal features and all classified signal features, determine the interface status, and determine whether there is looseness according to the interface status.

[0023] Preferably, in the step of feature extraction, the signal is normalized. If the original signal is x(n) and the normalized signal is y(n), then the relationship between x(n) and y(n) is:

[0024]

[0025] where N is the length of the signal, max() is to find the maximum value of the vector, abc() is to find the absolute value, and the value range of y(n) is [-1, 1].

[0026] Preferably, if it is determined that the interface is loose, a warning message is sent in a timely manner.

[0027] Another object of the embodiments of the present invention is to provide a switch for communication engineering that avoids plugging looseness. The switch for communication engineering includes:

[0028] A data acquisition module, configured to acquire historical fault interface signal data;

[0029] A data classification module, configured to classify the historical fault interface signal data to obtain classified signal data, where the classified signal data includes fault signal data, abnormal signal data, and normal signal data;

[0030] A feature extraction module, configured to extract features according to the classified signal data to obtain classified signal features, where the classified signal features at least include fault signal features, abnormal signal features, and normal signal features;

[0031] An abnormal recognition module, configured to collect real-time interface signals, extract features from the real-time interface signals to obtain real-time signal features, and determine whether each interface is loose according to the real-time signal features and the classified signal features.

[0032] Preferably, the data classification module includes:

[0033] An interface data extraction unit, configured to identify the interface number in the historical fault interface signal data and extract the interface signal data according to the interface number;

[0034] A division position recognition unit, configured to determine the data division position according to the interface signal data corresponding to each interface number;

[0035] A data division unit, configured to divide the interface signal data according to the division position to obtain classified signal data.

[0036] Preferably, the feature extraction module includes:

[0037] A data conversion unit, configured to represent the fault signal data, abnormal signal data, and normal signal data in the form of waveform diagrams;

[0038] A waveform diagram classification unit, configured to classify the waveform diagrams according to the data type to obtain three types of waveform diagrams;

[0039] A waveform feature extraction unit, configured to extract features from all the waveform diagrams of each type to obtain classified signal features.

[0040] Preferably, the abnormal recognition module includes:

[0041] An implementation waveform diagram drawing unit, configured to collect real-time interface signals and draw real-time waveform diagrams according to the real-time interface signals;

[0042] A real-time feature extraction unit for extracting features from a real-time waveform diagram to obtain real-time signal features;

[0043] A feature matching calculation unit for calculating the matching degree between the real-time signal features and all classified signal features, determining the interface status, and judging whether there is looseness according to the interface status.

[0044] A method for avoiding plug-in looseness provided by an embodiment of the present invention detects an interface that has already had a looseness fault, thereby obtaining historical fault interface signal data, performs waveform extraction according to the historical fault interface signal data, determines the waveform features corresponding to the interface in each state, extracts features from the real-time transmission signal, and then performs feature comparison to determine the current state of each interface, judge whether there is looseness, and give an early warning in time before complete detachment, ensuring the normal operation of the device. Description of the Drawings

[0045] Figure 1 It is a flowchart of a method for avoiding plug-in looseness provided by an embodiment of the present invention;

[0046] Figure 2 It is a flowchart of the step of dividing historical fault interface signal data to obtain classified signal data provided by an embodiment of the present invention;

[0047] Figure 3 It is a flowchart of the step of extracting features from classified signal data to obtain classified signal features provided by an embodiment of the present invention;

[0048] Figure 4 It is a flowchart of the step of collecting real-time interface signals, extracting features from the real-time interface signals to obtain real-time signal features, and judging whether there is looseness in each interface according to the real-time signal features and the classified signal features provided by an embodiment of the present invention;

[0049] Figure 5 It is an architecture diagram of a switch for communication engineering for avoiding plug-in looseness provided by an embodiment of the present invention;

[0050] Figure 6 It is an architecture diagram of a data classification module provided by an embodiment of the present invention;

[0051] Figure 7 It is an architecture diagram of a feature extraction module provided by an embodiment of the present invention;

[0052] Figure 8 It is an architecture diagram of an anomaly recognition module provided by an embodiment of the present invention. Detailed Embodiments

[0053] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0054] It can be understood that the terms "first", "second", etc. used in the present application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of the present application, the first xx script may be referred to as the second xx script, and similarly, the second xx script may be referred to as the first xx script.

[0055] Switching is a general term for the technology that, according to the needs of information transmission between two communication ends, manually or automatically by equipment, sends the information to be transmitted to the corresponding route that meets the requirements. According to the different working positions, switches can be divided into wide area network switches and local area network switches. A wide area network switch is a device that completes the information switching function in a communication engineering switch. It is applied at the data link layer. A switch has multiple ports, and each port has a bridging function and can be connected to a local area network or a high-performance server or workstation. During the current use of switches, multiple connectors are plugged into a single switch at the same time. During long-term use, the connectors are inevitably loosened, and the loosening can only be detected after obvious abnormal phenomena occur, thus affecting the normal use of the equipment.

[0056] The present invention detects the interfaces that have already had loosening faults, thereby obtaining historical fault interface signal data, extracts waveforms based on the historical fault interface signal data, determines the waveform characteristics corresponding to the interfaces in various states, extracts characteristics from the real-time transmission signals, and then performs characteristic comparison to determine the current states of the interfaces, determines whether there is loosening, and gives an early warning in time before complete detachment, ensuring the normal operation of the equipment.

[0057] As Figure 1 shown, it is a flowchart of a method for avoiding plugging loosening provided by an embodiment of the present invention. The method includes:

[0058] S100, obtain historical fault interface signal data.

[0059] In this step, historical fault interface signal data is obtained. The historical fault interface signal data is the signal data transmitted by the interface that currently has a fault during the historical process. The signal data can be the signal strength, that is, the signal strength during the transmission process is recorded to obtain the signal data. For example, if interface A fails and cannot be used at time B, then the signal strength data received by interface A is traced back to obtain the historical fault interface signal data. During the entire process of the interface becoming loose, it must include a non-loose stage, a virtual connection stage, and a loose stage.

[0060] S200. Divide the historical fault interface signal data to obtain classified signal data. The classified signal data includes fault signal data, abnormal signal data, and normal signal data.

[0061] In this step, divide the historical fault interface signal data. Since during the process of the interface having a fault, it goes through at least three stages, and the data corresponding to each stage is different. For example, during the non-loose stage, the data transmission is stable and the signal strength is within the preset range. During the virtual connection stage, signal strength fluctuations will occur, and occasionally the signal strength will exceed the preset range. During the loose stage, the signal strength will be lower than the setting, resulting in ineffective signal transmission. Therefore, based on this, the historical fault interface signal data is divided into fault signal data, abnormal signal data, and normal signal data, which respectively correspond to the three stages of the non-loose stage, the virtual connection stage, and the loose stage.

[0062] S300. Extract features from the classified signal data to obtain classified signal features. The classified signal features at least include fault signal features, abnormal signal features, and normal signal features.

[0063] In this step, extract features from the classified signal data. After completing the classification of the data, there are three types of data corresponding to the fault signal data, abnormal signal data, and normal signal data. Then, represent them with a waveform diagram, and then extract the waveform features to obtain the fault signal features, abnormal signal features, and normal signal features. The fault signal features, abnormal signal features, and normal signal features respectively correspond to the three types of data of the fault signal data, abnormal signal data, and normal signal data.

[0064] S400. Collect real-time interface signals, extract features from the real-time interface signals to obtain real-time signal features, and determine whether each interface is loose based on the real-time signal features and the classified signal features.

[0065] In this step, real-time interface signals are collected. During use, in order to analyze the loosening conditions of each interface, the signal transmission intensity of each interface is recorded to obtain real-time interface signals. Then, according to the same signal feature extraction method, feature extraction is performed to obtain real-time signal features. The real-time signal features are used to characterize the state of the signal transmission intensity of each interface. The real-time signal features are compared with the classified signal features to determine the current stage of each interface, and determine whether it is in the non-loosening stage, the virtual connection stage, or the loosening stage. When it is determined that the interface is in the virtual connection stage or the loosening stage, a warning message needs to be sent to relevant personnel to notify them to repair the interface.

[0066] As Figure 2 shown, as a preferred embodiment of the present invention, the step of dividing the historical fault interface signal data to obtain classified signal data specifically includes:

[0067] S201, identify the interface number in the historical fault interface signal data, and extract the interface signal data according to the interface number.

[0068] In this step, the interface number in the historical fault interface signal data is identified. To facilitate the distinction of each interface, a unique number is set for each interface in the same switch, and the numbers corresponding to the interfaces between different switches can be repeated. Data extraction is performed according to the number to obtain the interface signal data, that is, all the data of one interface is grouped together.

[0069] S202, determine the data division position according to the interface signal data corresponding to each interface number.

[0070] In this step, the data division position is determined according to the interface signal data corresponding to each interface number. Two division positions need to be determined for dividing the non-loosening stage, the virtual connection stage, and the loosening stage. By calculating the change value of the signal intensity, when its instantaneous change value exceeds the preset value, the first division moment is determined, and the first division position is determined according to the first division moment. Then, when it is determined that the time when the signal intensity value continuously is lower than the preset value exceeds the preset time, the second division moment is determined, and the second division position is determined according to the second division moment.

[0071] S203, divide the interface signal data according to the division position to obtain classified signal data.

[0072] In this step, the interface signal data is divided according to the division position. The normal signal data is divided from the interface signal data according to the first division position, and then the remaining part of the interface signal data is divided into fault signal data and abnormal signal data through the second division position, that is, the classified signal data is obtained.

[0073] AsFigure 3 As shown in the figure, as a preferred embodiment of the present invention, the step of extracting features from the classification signal data to obtain classification signal features specifically includes:

[0074] S301, representing the fault signal data, abnormal signal data, and normal signal data in the form of waveform diagrams.

[0075] In this step, the fault signal data, abnormal signal data, and normal signal data are read in sequence, a two-dimensional coordinate system is constructed, with time as the horizontal axis and the signal intensity value as the vertical axis, so as to draw waveform diagrams and obtain multiple waveform diagrams.

[0076] S302, classifying the waveform diagrams according to the data type to obtain three types of waveform diagrams.

[0077] In this step, the waveform diagrams are classified according to the data type, that is, the waveform diagrams obtained from the fault signal data are classified into one category, the waveform diagrams obtained from the abnormal signal data are classified into one category, and the waveform diagrams of the normal signal data are classified into one category, thereby obtaining three types of waveform diagrams.

[0078] S303, extracting features from all the waveform diagrams of each type to obtain classification signal features.

[0079] In this step, features are extracted from all the waveform diagrams of each type. Since the number of waveform diagrams in the same category is large, the common features are extracted to obtain classification signal features, which include fault signal features, abnormal signal features, and normal signal features.

[0080] As Figure 4 shown, as a preferred embodiment of the present invention, the step of collecting real-time interface signals, extracting features from the real-time interface signals to obtain real-time signal features, and determining whether each interface is loose according to the real-time signal features and classification signal features specifically includes:

[0081] S401, collecting real-time interface signals and drawing real-time waveform diagrams according to the real-time interface signals.

[0082] In this step, real-time interface signals are collected, the real-time transmission signal intensity of each interface is recorded, thereby forming real-time interface signals corresponding to each interface. Similarly, a two-dimensional coordinate system is constructed, with time as the horizontal axis and the signal intensity value as the vertical axis, and the real-time waveform diagram is drawn.

[0083] S402, extracting features from the real-time waveform diagram to obtain real-time signal features.

[0084] S403. Calculate the matching degree between the real-time signal features and all classified signal features, determine the interface status, and determine whether there is looseness according to the interface status.

[0085] In this step, feature extraction is performed in the same way to obtain real-time signal features. The real-time signal features actually include multiple feature values. The status of the current interface is determined by determining the range of the feature value distribution. For example, if 10% of the feature values in the real-time signal features match the normal signal features, 20% match the fault signal features, and 70% match the abnormal signal features, it can be regarded as a virtual connection state. At this time, there is a risk of loosening, and a warning message is sent.

[0086] In the step of feature extraction, the signal is normalized. If the original signal is x(n) and the normalized signal is y(n), the relationship between x(n) and y(n) is:

[0087]

[0088] where N is the length of the signal, max() is used to find the maximum value of the vector, abc() is used to find the absolute value, and the value range of y(n) is [-1, 1].

[0089] As Figure 5 shown, a switch for communication engineering to avoid plugging looseness provided by an embodiment of the present invention. The switch for communication engineering includes:

[0090] A data acquisition module 100 for acquiring historical fault interface signal data.

[0091] In this switch, the data acquisition module 100 acquires historical fault interface signal data. The historical fault interface signal data is the signal data transmitted by the interface that currently has a fault during the historical process. The signal data can be the signal strength, that is, the signal strength during the transmission process is recorded to obtain the signal data. For example, if interface A fails and cannot be used at time B, the signal strength data received by interface A is traced back to obtain the historical fault interface signal data. During the entire process of the interface becoming loose, it must include a non-loose stage, a virtual connection stage, and a loose stage.

[0092] A data classification module 200 for classifying the historical fault interface signal data to obtain classified signal data. The classified signal data includes fault signal data, abnormal signal data, and normal signal data.

[0093] In this switch, the data classification module 200 divides the historical fault interface signal data. Since during the process of interface failure, it goes through at least three stages, and the data corresponding to each stage is different. For example, during the non-loosening stage, data transmission is stable and the signal strength is within the preset range. During the virtual connection stage, signal strength fluctuations occur, and occasionally the signal strength exceeds the preset range. During the loosening stage, the signal strength will be lower than the setting, resulting in ineffective signal transmission. Therefore, the historical fault interface signal data is divided accordingly into fault signal data, abnormal signal data, and normal signal data, which respectively correspond to the three stages of non-loosening stage, virtual connection stage, and loosening stage.

[0094] The feature extraction module 300 is used to extract features from the classified signal data to obtain classified signal features, and the classified signal features at least include fault signal features, abnormal signal features, and normal signal features.

[0095] In this switch, the feature extraction module 300 extracts features according to the classified signal data. After the data classification is completed, there are three types of data corresponding to the fault signal data, abnormal signal data, and normal signal data. Then, a waveform diagram is used to represent it, and then waveform features are extracted to obtain the fault signal features, abnormal signal features, and normal signal features. The fault signal features, abnormal signal features, and normal signal features respectively correspond to the three types of data of the fault signal data, abnormal signal data, and normal signal data.

[0096] The abnormality recognition module 400 is used to collect real-time interface signals, extract features from the real-time interface signals to obtain real-time signal features, and determine whether each interface is loose according to the real-time signal features and the classified signal features.

[0097] In this switch, the abnormality recognition module 400 collects real-time interface signals. During use, in order to analyze the loosening situation of each interface, the signal transmission strength of each interface is recorded to obtain real-time interface signals, and then feature extraction is performed according to the same signal feature extraction method to obtain real-time signal features. The real-time signal features are used to characterize the state of the signal transmission strength of each interface. The real-time signal features are compared with the classified signal features to determine the current stage of each interface, and determine whether it is in the non-loosening stage, virtual connection stage, or loosening stage. When it is determined that the interface is in the virtual connection stage or loosening stage, a warning message needs to be sent to relevant personnel to notify them to repair the interface.

[0098] As Figure 6 shown, as a preferred embodiment of the present invention, the data classification module 200 includes:

[0099] The interface data extraction unit 201 is used to identify the interface number in the historical fault interface signal data and extract the interface signal data according to the interface number.

[0100] In this module, the interface data extraction unit 201 identifies the interface number in the historical fault interface signal data. To facilitate the distinction of each interface, a unique number is set for each interface in the same switch, and the numbers corresponding to the interfaces between different switches can be repeated. Data extraction is performed according to the number to obtain the interface signal data, that is, all the data of one interface are grouped together.

[0101] The division position identification unit 202 is used to determine the data division position according to the interface signal data corresponding to each interface number.

[0102] In this module, the division position identification unit 202 determines the data division position according to the interface signal data corresponding to each interface number. Two division positions need to be determined for the non-loosening stage, virtual connection stage, and loosening stage. By calculating the change value of the signal strength, when its instantaneous change value exceeds the preset value, the first division moment is determined, and the first division position is determined according to the first division moment. Then, when the time for which the signal strength value continuously remains lower than the preset value exceeds the preset time, the second division moment is determined, and the second division position is determined according to the second division moment.

[0103] The data division unit 203 is used to divide the interface signal data according to the division position to obtain classified signal data.

[0104] In this module, the data division unit 203 determines the data division position according to the interface signal data corresponding to each interface number. Two division positions need to be determined for the non-loosening stage, virtual connection stage, and loosening stage. By calculating the change value of the signal strength, when its instantaneous change value exceeds the preset value, the first division moment is determined, and the first division position is determined according to the first division moment. Then, when the time for which the signal strength value continuously remains lower than the preset value exceeds the preset time, the second division moment is determined, and the second division position is determined according to the second division moment.

[0105] As Figure 7 shown, as a preferred embodiment of the present invention, the feature extraction module 300 includes:

[0106] The data conversion unit 301 is used to represent the fault signal data, abnormal signal data, and normal signal data in the form of waveform diagrams.

[0107] In this module, the data conversion unit 301 sequentially reads the fault signal data, abnormal signal data, and normal signal data, constructs a two-dimensional coordinate system with time as the horizontal axis and the signal strength value as the vertical axis, and thus draws waveform diagrams to obtain multiple waveform diagrams.

[0108] The waveform graph classification unit 302 is used to classify waveform graphs according to data types, obtaining three types of waveform graphs.

[0109] In this module, the waveform graph classification unit 302 classifies waveform graphs according to data types, that is, the waveform graphs obtained from fault signal data are classified into one category, the waveform graphs obtained from abnormal signal data are classified into one category, and the waveform graphs of normal signal data are classified into one category, thereby obtaining three types of waveform graphs.

[0110] The waveform feature extraction unit 303 is used to extract features from all waveform graphs of each type, obtaining classification signal features.

[0111] In this module, the waveform feature extraction unit 303 extracts features from all waveform graphs of each type. Since the number of waveform graphs in the same category is large, by extracting their common features, classification signal features are obtained, and the classification signal features include fault signal features, abnormal signal features, and normal signal features.

[0112] As Figure 8 shown, as a preferred embodiment of the present invention, the abnormal recognition module 400 includes:

[0113] The implementation waveform graph drawing unit 401 is used to collect real-time interface signals and draw real-time waveform graphs according to the real-time interface signals.

[0114] In this module, the implementation waveform graph drawing unit 401 collects real-time interface signals, records the real-time transmission signal intensity of each interface, thereby forming real-time interface signals corresponding to each interface. Similarly, a two-dimensional coordinate system is constructed, with time as the horizontal axis and signal intensity values as the vertical axis, and the real-time waveform graph is drawn.

[0115] The real-time feature extraction unit 402 is used to extract features from the real-time waveform graph, obtaining real-time signal features.

[0116] The feature matching calculation unit 403 is used to calculate the matching degree between the real-time signal features and all classification signal features, determine the interface status, and determine whether there is looseness according to the interface status.

[0117] In this module, feature extraction is performed in the same way to obtain real-time signal features. The real-time signal features actually contain multiple feature values. By determining the range of the distribution of feature values, the status of the current interface is determined. For example, if 10% of the feature values in the real-time signal features match the normal signal features, 20% match the fault signal features, and 70% match the abnormal signal features, it can be regarded as a virtual connection state, and at this time there is a risk of loosening, and a warning message is issued;

[0118] In the step of feature extraction, the signal is normalized. If the original signal is x(n) and the normalized signal is y(n), then the relationship between x(n) and y(n) is as follows:

[0119]

[0120] where N is the length of the signal, max() is used to find the maximum value of the vector, abc() is used to find the absolute value, and the value range of y(n) is [-1, 1].

[0121] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0122] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0123] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as falling within the scope described in this specification.

[0124] The above-described embodiments merely represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

[0125] The foregoing is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for avoiding plugging looseness, characterized in that, The method includes: Obtaining historical fault interface signal data; Dividing the historical fault interface signal data to obtain classified signal data, where the classified signal data includes fault signal data, abnormal signal data, and normal signal data; Performing feature extraction based on the classified signal data to obtain classified signal features, where the classified signal features at least include fault signal features, abnormal signal features, and normal signal features; Collecting real-time interface signals, performing feature extraction on the real-time interface signals to obtain real-time signal features, and determining whether each interface is loose based on the real-time signal features and the classified signal features.

2. The method for avoiding plugging looseness according to claim 1, characterized in that, The step of dividing the historical fault interface signal data to obtain classified signal data specifically includes: Identifying the interface numbers in the historical fault interface signal data, and extracting the interface signal data according to the interface numbers; Determining the data division positions based on the interface signal data corresponding to each interface number; Dividing the interface signal data according to the division positions to obtain classified signal data.

3. The method for avoiding plugging looseness according to claim 1, characterized in that, The step of performing feature extraction based on the classified signal data to obtain classified signal features specifically includes: Representing the fault signal data, abnormal signal data, and normal signal data as waveform diagrams; Classifying the waveform diagrams according to the data types to obtain three types of waveform diagrams; Performing feature extraction on all the waveform diagrams of each type to obtain classified signal features.

4. The method for avoiding plugging looseness according to claim 1, characterized in that, The step of collecting real-time interface signals, performing feature extraction on the real-time interface signals to obtain real-time signal features, and determining whether each interface is loose based on the real-time signal features and the classified signal features specifically includes: Collecting real-time interface signals and drawing a real-time waveform diagram according to the real-time interface signals; Performing feature extraction on the real-time waveform diagram to obtain real-time signal features; Calculating the matching degrees of the real-time signal features and all the classified signal features, determining the interface states, and determining whether there is looseness based on the interface states.

5. The method for avoiding plugging looseness according to claim 1, characterized in that, In the step of performing feature extraction, the signal is normalized. If the original signal is x(n) and the normalized signal is y(n), the relationship between x(n) and y(n) is: Where N is the length of the signal, max() is to find the maximum value of the vector, abc() is to find the absolute value, and the value range of y(n) is [-1, 1].

6. The method for avoiding plugging looseness according to claim 1, wherein If it is determined that an interface is loose, a warning message is sent in a timely manner.

7. A switch for communication engineering that avoids plugging loosening, characterized in that, The switch for communication engineering includes: A data acquisition module for obtaining historical fault interface signal data; A data classification module for dividing the historical fault interface signal data to obtain classified signal data, where the classified signal data includes fault signal data, abnormal signal data, and normal signal data; A feature extraction module for performing feature extraction based on the classified signal data to obtain classified signal features, where the classified signal features at least include fault signal features, abnormal signal features, and normal signal features; An abnormality identification module for collecting real-time interface signals, performing feature extraction on the real-time interface signals to obtain real-time signal features, and determining whether each interface is loose based on the real-time signal features and the classified signal features.

8. The switch for communication engineering to avoid plugging looseness according to claim 7, characterized in that, The data classification module includes: An interface data extraction unit, which is used to identify the interface number in the historical fault interface signal data and extract the interface signal data according to the interface number; A division position recognition unit, which is used to determine the data division position according to the interface signal data corresponding to each interface number; A data division unit, which is used to divide the interface signal data according to the division position to obtain classified signal data.

9. The switch for communication engineering to avoid plugging looseness according to claim 7, characterized in that, The feature extraction module includes: A data conversion unit, which is used to represent the fault signal data, abnormal signal data and normal signal data in the form of waveform diagrams; A waveform diagram classification unit, which is used to classify the waveform diagrams according to the data type to obtain three types of waveform diagrams; A waveform feature extraction unit, which is used to extract features from all waveform diagrams under each type to obtain classified signal features.

10. The switch for communication engineering to avoid plugging looseness according to claim 7, characterized in that, The abnormality recognition module includes: An implementation waveform diagram drawing unit, which is used to collect real-time interface signals and draw real-time waveform diagrams according to the real-time interface signals; A real-time feature extraction unit, which is used to extract features from the real-time waveform diagrams to obtain real-time signal features; A feature matching calculation unit, which is used to calculate the matching degree between the real-time signal features and all classified signal features, determine the interface state, and determine whether there is looseness according to the interface state.

Images