Circuit board fault diagnosis system and method

Abstract

The invention specifically relates to a circuit board fault diagnosis system, and the system comprises a temperature collection module which is used for collecting a thermal radiation signal and a visible light signal of a circuit board, converting the thermal radiation signal of the circuit board into temperature distribution dot matrix data, and transmitting the temperature distribution dot matrix data and the visible light signal of the circuit board to a data processing module; and the data processing module is provided with a fault mode library of various models of circuit boards, and is used for analyzing the received visible light signals of the circuit boards, completing identification of the models of the circuit boards, processing the received temperature distribution dot matrix data of the circuit boards and completing fault diagnosis of the circuit boards. The invention further relates to a circuit board fault diagnosis method. According to the invention, the collected circuit board thermal radiation signals are processed and analyzed, comprehensive, efficient and accurate diagnosis of circuit board faults is realized, and the generalization performance and universality are high.

Description

Technical Field

[0001] The present invention relates to the technical field of circuit board status detection, and in particular to a circuit board fault diagnosis system and method. Background Art

[0002] Circuit boards are core components inside electronic and electrical devices. Whether their functions are normal or not has a direct impact on the functions and performance of the devices. Therefore, conducting circuit board fault diagnosis is a key link in equipment maintenance work.

[0003] The fault diagnosis of circuit boards by collecting thermal radiation signals from circuit boards with thermal imagers is increasingly being used in engineering practice. This method has the following advantages:

[0004] 1. Adopt non-contact detection method to avoid direct contact with the circuit board and cause damage to the circuit board;

[0005] 2. Circuit board fault diagnosis can be completed without being familiar with the working principle of the circuit board, which reduces the professional and technical requirements for maintenance personnel.

[0006] At present, the common method of diagnosing circuit board faults through thermal radiation or infrared signals is mainly to detect the temperature of specific components on the circuit board, and determine whether the components on the circuit board function normally by setting corresponding temperature thresholds or algorithms. This method mainly has the following problems:

[0007] 1. There are many types of circuit boards on the market, and there are a large number of components on the circuit boards. If the fault diagnosis of the circuit boards is carried out by temperature detection of each component, the workload is huge, and the scalability and versatility are very poor;

[0008] 2. Normally, when a single component on a circuit board fails, it will affect its associated upper circuits, lower circuits, power supplies and other circuits, causing abnormalities in the components in the associated circuits. At this time, if only a single component is analyzed, the efficiency and accuracy of the circuit board fault diagnosis work will be low.

[0009] Based on the above problems, it is very necessary to develop a circuit board fault diagnosis technology that can realize comprehensive, efficient and accurate diagnosis of circuit board faults and has strong scalability and versatility. Summary of the invention

[0010] The purpose of the present invention is to provide a circuit board fault diagnosis system and method, which can realize comprehensive, efficient and accurate diagnosis of circuit board faults by processing and analyzing the collected circuit board thermal radiation signals, and has strong scalability and versatility.

[0011] In order to achieve the above object, the present invention provides a circuit board fault diagnosis system, comprising:

[0012] The temperature acquisition module is used to acquire the thermal radiation signal and visible light signal of the circuit board; convert the thermal radiation signal of the circuit board into temperature distribution dot matrix data; and send the temperature distribution dot matrix data and visible light signal of the circuit board to the data processing module;

[0013] The data processing module is provided with a fault mode library of various types of circuit boards, which is used to analyze the visible light signal of the received circuit board to complete the identification of the circuit board model; process the temperature distribution dot matrix data of the received circuit board and complete the fault diagnosis of the circuit board.

[0014] In the present invention, the temperature acquisition module includes:

[0015] The infrared detector is used to collect the thermal radiation signal of the circuit board, convert the thermal radiation signal of the circuit board from an image to an analog signal and send it to the signal processing module;

[0016] A visible light camera, used to collect visible light signals from the circuit board and send them to the data processing module;

[0017] The signal processing module is connected to the data processing module via a data bus, and is used to convert the received thermal radiation signal of the circuit board into temperature distribution dot matrix data and send it to the data processing module via the data bus.

[0018] In the present invention, the data processing module processes the received temperature distribution dot matrix data of the circuit board and completes the fault diagnosis of the circuit board, including the following steps:

[0019] Step 1: cutting the temperature distribution dot matrix data of the circuit board into a plurality of first temperature analysis units, including the following steps:

[0020] The temperature distribution dot matrix data of the circuit board is uniformly cut into n pieces along the horizontal axis and m pieces along the vertical axis, and the temperature distribution dot matrix data of the circuit board is cut into first square array data consisting of n×m square data; n and m are both natural numbers;

[0021] Encode each block of data in the first block array data according to the row number and the column number and use it as a first temperature analysis unit;

[0022] Step 2: Calculate the first temperature characteristic vector matrix of the circuit board according to each piece of first temperature information in each first temperature analysis unit, including the following steps:

[0023] Collecting each piece of first temperature information in each first temperature analysis unit; the first temperature information includes a temperature value, a temperature rise value and a temperature rise rate;

[0024] Calculate the average value, maximum value and minimum value corresponding to each piece of first temperature information in each first temperature analysis unit to form a first temperature characteristic value of each first temperature analysis unit;

[0025] The first temperature characteristic values ​​of each first temperature analysis unit are saved in a vector matrix to form a first temperature characteristic vector matrix of the circuit board;

[0026] Step 3: calling a fault mode library of a circuit board of this model according to the model of the circuit board, wherein the fault mode library of the circuit board of this model contains a second temperature characteristic vector matrix of each fault mode circuit board of this model;

[0027] Performing similarity matching on the first temperature feature vector matrix and each second temperature feature vector matrix respectively, and selecting the second temperature feature vector matrix with the highest matching degree with the first temperature feature vector matrix;

[0028] The failure mode corresponding to the second temperature eigenvector matrix having the highest matching degree with the first temperature eigenvector matrix is ​​used as the failure mode of the circuit board.

[0029] In the present invention, the first temperature characteristic vector matrix and the second temperature characteristic vector are matched by similarity through a cosine similarity algorithm. The formula of the cosine similarity algorithm is as follows:

[0030]

[0031] Among them, a i is the i-th element in the first temperature vector matrix, b i is the i-th element in the second temperature vector matrix; cos(θ) is the cosine angle between the first temperature vector matrix and the second temperature vector matrix; the closer cos(θ) is to 1, the higher the similarity between the first temperature vector matrix and the second temperature vector matrix.

[0032] In the present invention, a failure mode library of a model of circuit board contains the second temperature characteristic vector matrix of each failure mode circuit board of the model; the second temperature characteristic vector matrix of a failure mode circuit board of a model is obtained by the following steps:

[0033] The temperature acquisition module acquires the thermal radiation signal of the circuit board of the model and the fault mode; converts the thermal radiation signal of the circuit board of the model and the fault mode into temperature distribution dot matrix data and sends it to the data processing module;

[0034] The data processing module processes the received temperature distribution dot matrix data of the circuit board of the model and the fault mode to form a second temperature characteristic vector matrix of the circuit board of the model and the fault mode.

[0035] In the present invention, the data processing module processes the received temperature distribution dot matrix data of a model and a fault mode circuit board to form a second temperature characteristic vector matrix of the model and the fault mode circuit board, including the following steps:

[0036] Step 1: cutting the temperature distribution dot matrix data of the model and the fault mode circuit board into a plurality of second temperature analysis units, including the following steps:

[0037] The temperature distribution dot matrix data of the circuit board of the model and the fault mode is uniformly cut into n pieces along the horizontal axis and m pieces along the vertical axis, and the temperature distribution dot matrix data of the circuit board of the model and the fault mode is cut into a second square array data composed of n×m square data; n and m are both natural numbers;

[0038] Encoding each block of data in the second block array data according to the row number and the column number and using it as a second temperature analysis unit;

[0039] Step 2: Calculate the second temperature characteristic vector matrix of the circuit board of the model and the fault mode according to each piece of second temperature information in each second temperature analysis unit, including the following steps:

[0040] Collecting each piece of second temperature information in each second temperature analysis unit; the second temperature information includes a temperature value, a temperature rise value and a temperature rise rate;

[0041] Calculate the average value, maximum value and minimum value corresponding to each piece of second temperature information in each second temperature analysis unit to form a second temperature characteristic value of each second temperature analysis unit;

[0042] The second temperature characteristic values ​​of each second temperature analysis unit are saved in a vector matrix format to form a second temperature characteristic vector matrix of the circuit board of this model and this fault mode.

[0043] In the present invention, the data processing module is also provided with a normal mode library of each type of circuit board; the normal mode library of a type of circuit board contains the third temperature characteristic vector matrix of the normal mode circuit board of this type;

[0044] The circuit board fault diagnosis system also includes a display module; the display module is used to display the fault mode of the circuit board and the first temperature characteristic value of each first temperature analysis unit of the circuit board; the first temperature analysis unit with the first abnormal first temperature characteristic value is highlighted in the first color, and the first temperature analysis unit with the second abnormal first temperature characteristic value is highlighted in the second color;

[0045] The data processing module is also used to compare the first temperature characteristic vector matrix of the circuit board with the third temperature characteristic vector matrix of the normal mode circuit board of the corresponding model; when the difference between the first temperature characteristic vector matrix element and the corresponding third temperature characteristic vector matrix element exceeds the set upper limit value, it is judged that the first temperature characteristic value of the first temperature analysis unit corresponding to the circuit board is first abnormal; when the difference between the first temperature characteristic vector matrix element and the corresponding third temperature characteristic vector matrix element exceeds the set lower limit value, it is judged that the first temperature characteristic value of the first temperature analysis unit corresponding to the circuit board is second abnormal.

[0046] In the present invention, the third temperature characteristic vector matrix of a normal mode circuit board of a model is obtained by the following steps:

[0047] The temperature acquisition module acquires the thermal radiation signal of the normal mode circuit board of this model; converts the thermal radiation signal of the normal mode circuit board of this model into temperature distribution dot matrix data and sends it to the data processing module;

[0048] The data processing module processes the received temperature distribution dot matrix data of the normal mode circuit board of this model to form a third temperature characteristic vector matrix of the normal mode circuit board of this model.

[0049] In the present invention, the data processing module processes the received temperature distribution dot matrix data of a normal mode circuit board of a model to form a third temperature characteristic vector matrix of the normal mode circuit board of the model, including the following steps:

[0050] Step 1: cutting the temperature distribution dot matrix data of the normal mode circuit board of the model into a plurality of third temperature analysis units, comprising the following steps:

[0051] The temperature distribution dot matrix data of the normal mode circuit board of this model is uniformly cut into n pieces along the horizontal axis and m pieces along the vertical axis, and the temperature distribution dot matrix data of the normal mode circuit board of this model is cut into third block array data composed of n×m block data; n and m are both natural numbers;

[0052] Encode each block of data in the third block array data according to the row number and the column number and use it as a third temperature analysis unit;

[0053] Step 2: Calculate the third temperature characteristic vector matrix of the normal mode circuit board of this model according to each piece of third temperature information in each third temperature analysis unit, including the following steps:

[0054] Collecting each piece of third temperature information in each third temperature analysis unit; the third temperature information includes a temperature value, a temperature rise value and a temperature rise rate;

[0055] Calculate the average value, maximum value and minimum value corresponding to each piece of third temperature information in each third temperature analysis unit to form a third temperature characteristic value of each third temperature analysis unit;

[0056] The third temperature characteristic values ​​of each third temperature analysis unit are saved in a vector matrix format to form a third temperature characteristic vector matrix of the normal mode circuit board of this model.

[0057] In the present invention, the temperature acquisition module is also used to collect visible light signals of various types of circuit boards and send them to the data processing module;

[0058] The data processing module is also used to store the received visible light signals of the circuit boards of various models;

[0059] The data processing module analyzes the received visible light signal of the circuit board to complete the identification of the circuit board model, including the following steps:

[0060] The visible light signal of the circuit board is matched with the visible light signals of the circuit boards of various models, and the model corresponding to the matched visible light signal is the model of the circuit board.

[0061] In order to achieve the above object, the present invention also provides a circuit board fault diagnosis method, using the above circuit board fault diagnosis system, comprising the following steps:

[0062] S1. System self-check: After the system is powered on, the status of each module inside the system is checked; if the status is normal, the next step of the workflow is entered; if an abnormality occurs, the system stops working and an alarm is issued;

[0063] S2, system startup: each module in the system starts working;

[0064] S3, data acquisition: the temperature acquisition module acquires the thermal radiation signal and visible light signal of the circuit board; converts the thermal radiation signal of the circuit board into temperature distribution dot matrix data; and sends the temperature distribution dot matrix data and visible light signal of the circuit board to the data processing module;

[0065] S4, data processing: the data processing module analyzes the visible light signal of the received circuit board to identify the model of the circuit board; processes the received temperature distribution dot matrix data of the circuit board and completes the fault diagnosis of the circuit board; determines whether the circuit board has a first temperature analysis unit with an abnormal first temperature characteristic value;

[0066] S5, data display: the display module displays the fault mode of the circuit board, displays the first temperature characteristic value of each first temperature analysis unit of the circuit board; and highlights the first temperature analysis unit with abnormal first temperature characteristic value;

[0067] S6. Determine whether it is necessary to continue collecting and analyzing the temperature of the circuit board. If necessary, return to S3; if not, end.

[0068] Beneficial technical effects of the present invention:

[0069] The circuit board fault diagnosis system and method of the present invention extracts the global temperature characteristics of circuit boards of different models, and through quantitative modeling and analysis of the temperature characteristics of circuit boards of different models, the concept of components is weakened, and the promotion and versatility are strong; through the method of cutting and zoning the temperature distribution of the circuit board, typical temperature characteristics are screened, non-typical temperature characteristics are eliminated, unnecessary information is filtered out, and data analysis efficiency and accuracy are improved; the circuit board fault mode is directly located, which greatly improves the circuit board maintenance efficiency; the global temperature characteristics of the circuit board are intuitively displayed, and the temperature abnormality area is marked to help the staff intuitively understand the circuit board status. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 A schematic diagram of the structure of an embodiment of a circuit board fault diagnosis system of the present invention;

[0071] Figure 2 This is a schematic diagram of normal identification of temperature characteristics of the circuit board temperature analysis unit;

[0072] Figure 3 This is a schematic diagram of abnormal identification of temperature characteristics of the circuit board temperature analysis unit;

[0073] Figure 4 The following is a flowchart of an embodiment of the circuit board fault diagnosis system of the present invention. DETAILED DESCRIPTION

[0074] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of the application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", "third", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0075] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0076] The technical solution of the present invention is clearly and completely described below in conjunction with the accompanying drawings and specific embodiments.

[0077] refer to Figure 1 , shows a schematic structural diagram of an embodiment of a circuit board fault diagnosis system, the circuit board fault diagnosis system comprising:

[0078] The temperature acquisition module is used to acquire the thermal radiation signal and visible light signal of the circuit board; convert the thermal radiation signal of the circuit board into temperature distribution dot matrix data; and send the temperature distribution dot matrix data and visible light signal of the circuit board to the data processing module;

[0079] The data processing module is provided with a fault mode library of various types of circuit boards, which is used to analyze the visible light signal of the received circuit board to complete the identification of the circuit board model; process the temperature distribution dot matrix data of the received circuit board and complete the fault diagnosis of the circuit board.

[0080] In this embodiment, the temperature acquisition module includes:

[0081] The infrared detector is used to collect the thermal radiation signal of the circuit board, convert the thermal radiation signal of the circuit board from an image to an analog signal and send it to the signal processing module;

[0082] A visible light camera, used to collect visible light signals from the circuit board and send them to the data processing module;

[0083] The signal processing module is connected to the data processing module via a data bus, and is used to convert the received thermal radiation signal of the circuit board into temperature distribution dot matrix data and send it to the data processing module via the data bus.

[0084] The data processing module receives a large amount of temperature distribution dot matrix data of the circuit board, with a resolution of 640*480, and calculates that the number of temperature pixels is 307200, with a size of 17 microns. In this embodiment, the data processing module processes the received temperature distribution dot matrix data of the circuit board and completes the fault diagnosis of the circuit board, including the following steps:

[0085] Step 1: cutting the temperature distribution dot matrix data of the circuit board into a plurality of first temperature analysis units, including the following steps:

[0086] The temperature distribution dot matrix data of the circuit board is evenly cut into 10 parts along the horizontal axis, and each row is named according to Arabic numerals 1-10; the temperature distribution dot matrix data of the circuit board is evenly cut into 10 parts along the vertical axis, and each column is named according to the English letters AJ; finally, the temperature distribution dot matrix data of the circuit board is evenly cut into 10 parts along the vertical axis, and the temperature distribution dot matrix data of the circuit board is evenly cut into 10 parts. The first square array data consisting of 10×10 square data;

[0087] Encode each block of data in the first block array data according to the row number and the column number and use it as a first temperature analysis unit; each first temperature analysis unit contains a plurality of temperature pixel points;

[0088] Step 2: Calculate the first temperature characteristic vector matrix of the circuit board according to each piece of first temperature information in each first temperature analysis unit, including the following steps:

[0089] Collecting each piece of first temperature information in each first temperature analysis unit; the first temperature information includes a temperature value, a temperature rise value and a temperature rise rate;

[0090] Calculate the average value, maximum value and minimum value corresponding to each piece of first temperature information in each first temperature analysis unit to form a first temperature characteristic value of each first temperature analysis unit;

[0091] The first temperature characteristic values ​​of each first temperature analysis unit are saved in a vector matrix to form a first temperature characteristic vector matrix of the circuit board;

[0092] Step 3: calling a fault mode library of a circuit board of this model according to the model of the circuit board, wherein the fault mode library of the circuit board of this model contains a second temperature characteristic vector matrix of each fault mode circuit board of this model;

[0093] Performing similarity matching on the first temperature feature vector matrix and each second temperature feature vector matrix respectively, and selecting the second temperature feature vector matrix with the highest matching degree with the first temperature feature vector matrix;

[0094] The failure mode corresponding to the second temperature eigenvector matrix having the highest matching degree with the first temperature eigenvector matrix is ​​used as the failure mode of the circuit board.

[0095] In this embodiment, the first temperature feature vector matrix and the second temperature feature vector are matched by similarity using a cosine similarity algorithm. The formula of the cosine similarity algorithm is as follows:

[0096]

[0097] Among them, a i is the i-th element in the first temperature vector matrix, bi is the i-th element in the second temperature vector matrix; cos(θ) is the cosine angle between the first temperature vector matrix and the second temperature vector matrix; the closer cos(θ) is to 1, the higher the similarity between the first temperature vector matrix and the second temperature vector matrix.

[0098] In this embodiment, the failure mode library of a model of circuit board contains the second temperature characteristic vector matrix of each failure mode circuit board of the model; the second temperature characteristic vector matrix of a model of a failure mode circuit board is obtained by the following steps:

[0099] The temperature acquisition module acquires the thermal radiation signal of the circuit board of the model and the fault mode; converts the thermal radiation signal of the circuit board of the model and the fault mode into temperature distribution dot matrix data and sends it to the data processing module;

[0100] The data processing module processes the received temperature distribution dot matrix data of the circuit board of the model and the fault mode to form a second temperature characteristic vector matrix of the circuit board of the model and the fault mode.

[0101] In this embodiment, the infrared detector collects the thermal radiation signal of a circuit board of one model and one fault mode at a time, converts the thermal radiation signal of the circuit board of the model and the fault mode from an image to an analog signal and sends it to the signal processing module;

[0102] The signal processing module converts the received thermal radiation signal of the circuit board of the model and the fault mode into temperature distribution dot matrix data and sends the data to the data processing module through the data bus;

[0103] The data processing module processes the received temperature distribution dot matrix data of the circuit board of the model and the fault mode to form a second temperature characteristic vector matrix of the circuit board of the model and the fault mode.

[0104] In this embodiment, the data processing module processes the received temperature distribution dot matrix data of a model and a fault mode circuit board to form a second temperature characteristic vector matrix of the model and the fault mode circuit board, including the following steps:

[0105] Step 1: cutting the temperature distribution dot matrix data of the model and the fault mode circuit board into a plurality of second temperature analysis units, including the following steps:

[0106] The temperature distribution dot matrix data of the circuit board of this model and this fault mode is evenly cut into 10 parts along the horizontal axis, and each row is named according to Arabic numerals 1-10; the temperature distribution dot matrix data of the circuit board of this model and this fault mode is evenly cut into 10 parts along the vertical axis, and each column is named according to the English letters AJ; finally, the temperature distribution dot matrix data of the circuit board of this model and this fault mode is cut into a second square array data composed of 10×10 square data;

[0107] Encoding each block of data in the second block array data according to the row number and the column number and using it as a second temperature analysis unit;

[0108] Step 2: Calculate the second temperature characteristic vector matrix of the circuit board of the model and the fault mode according to each piece of second temperature information in each second temperature analysis unit, including the following steps:

[0109] Collecting each piece of second temperature information in each second temperature analysis unit; the second temperature information includes a temperature value, a temperature rise value and a temperature rise rate;

[0110] Calculate the average value, maximum value and minimum value corresponding to each piece of second temperature information in each second temperature analysis unit to form a second temperature characteristic value of each second temperature analysis unit;

[0111] The second temperature characteristic values ​​of each second temperature analysis unit are saved in a vector matrix format to form a second temperature characteristic vector matrix of the circuit board of this model and this fault mode.

[0112] In this embodiment, the data processing module is further provided with a normal mode library of each type of circuit board; the normal mode library of a type of circuit board contains the third temperature characteristic vector matrix of the normal mode circuit board of that type;

[0113] The circuit board fault diagnosis system also includes a display module; the display module is used to display the fault mode of the circuit board and the first temperature characteristic value of each first temperature analysis unit of the circuit board; the first temperature analysis unit with the first abnormal first temperature characteristic value is highlighted in the first color, and the first temperature analysis unit with the second abnormal first temperature characteristic value is highlighted in the second color;

[0114] The data processing module is also used to compare the first temperature characteristic vector matrix of the circuit board with the third temperature characteristic vector matrix of the normal mode circuit board of the corresponding model; when the difference between the first temperature characteristic vector matrix element and the corresponding third temperature characteristic vector matrix element exceeds the set upper limit value, it is judged that the first temperature characteristic value of the first temperature analysis unit corresponding to the circuit board is first abnormal; when the difference between the first temperature characteristic vector matrix element and the corresponding third temperature characteristic vector matrix element exceeds the set lower limit value, it is judged that the first temperature characteristic value of the first temperature analysis unit corresponding to the circuit board is second abnormal.

[0115] like Figure 2 As shown, the first row displays the maximum temperature value in the first temperature analysis unit of the circuit board, and the second row displays the maximum temperature rise value in the first temperature analysis unit of the circuit board; Figure 3 As shown, the temperature value of the temperature analysis unit 7F is obviously higher than the normal state, and the analysis unit is highlighted in red; the temperature value of the temperature analysis unit 5E is obviously higher than the normal state, and the analysis unit is highlighted in yellow.

[0116] In this embodiment, the third temperature characteristic vector matrix of a normal mode circuit board of a model is obtained by the following steps:

[0117] The temperature acquisition module acquires the thermal radiation signal of the normal mode circuit board of this model; converts the thermal radiation signal of the normal mode circuit board of this model into temperature distribution dot matrix data and sends it to the data processing module;

[0118] The data processing module processes the received temperature distribution dot matrix data of the normal mode circuit board of this model to form a third temperature characteristic vector matrix of the normal mode circuit board of this model.

[0119] In this embodiment, the infrared detector collects the thermal radiation signal of one model of normal mode circuit board at a time, converts the thermal radiation signal of the model of normal mode circuit board from an image to an analog signal and sends it to the signal processing module;

[0120] The signal processing module converts the received thermal radiation signal of the normal mode circuit board of this model into temperature distribution dot matrix data and sends it to the data processing module through the data bus;

[0121] The data processing module processes the received temperature distribution dot matrix data of the normal mode circuit board of this model to form a third temperature characteristic vector matrix of the normal mode circuit board of this model.

[0122] In this embodiment, the data processing module processes the received temperature distribution dot matrix data of a model of normal mode circuit board to form a third temperature characteristic vector matrix of the model of normal mode circuit board, including the following steps:

[0123] Step 1: cutting the temperature distribution dot matrix data of the normal mode circuit board of the model into a plurality of third temperature analysis units, comprising the following steps:

[0124] The temperature distribution dot matrix data of the normal mode circuit board of this model is evenly cut into 10 parts along the horizontal axis, and each row is named according to Arabic numerals 1-10; the temperature distribution dot matrix data of the normal mode circuit board of this model is evenly cut into 10 parts along the vertical axis, and each column is named according to the English letters AJ; finally, the temperature distribution dot matrix data of the normal mode circuit board of this model is cut into a third block array data composed of 10×10 block data;

[0125] Encode each block of data in the third block array data according to the row number and the column number and use it as a third temperature analysis unit;

[0126] Step 2: Calculate the third temperature characteristic vector matrix of the normal mode circuit board of this model according to each piece of third temperature information in each third temperature analysis unit, including the following steps:

[0127] Collecting each piece of third temperature information in each third temperature analysis unit; the third temperature information includes a temperature value, a temperature rise value and a temperature rise rate;

[0128] Calculate the average value, maximum value and minimum value corresponding to each piece of third temperature information in each third temperature analysis unit to form a third temperature characteristic value of each third temperature analysis unit;

[0129] The third temperature characteristic values ​​of each third temperature analysis unit are saved in a vector matrix format to form a third temperature characteristic vector matrix of the normal mode circuit board of this model.

[0130] In this embodiment, the temperature acquisition module is also used to collect visible light signals of various types of circuit boards and send them to the data processing module;

[0131] The data processing module is also used to store the received visible light signals of the circuit boards of various models;

[0132] The data processing module analyzes the received visible light signal of the circuit board to complete the identification of the circuit board model, including the following steps:

[0133] The visible light signal of the circuit board is matched with the visible light signals of the circuit boards of various models, and the model corresponding to the matched visible light signal is the model of the circuit board.

[0134] See also Figure 4 The present invention also provides a circuit board fault diagnosis method, using the above circuit board fault diagnosis system, comprising the following steps:

[0135] S1. System self-check: After the system is powered on, the status of each module inside the system is checked; if the status is normal, the next step of the workflow is entered; if an abnormality occurs, the system stops working and an alarm is issued;

[0136] S2, system startup: each module in the system starts working;

[0137] S3, data acquisition: the temperature acquisition module acquires the thermal radiation signal and visible light signal of the circuit board; converts the thermal radiation signal of the circuit board into temperature distribution dot matrix data; and sends the temperature distribution dot matrix data and visible light signal of the circuit board to the data processing module;

[0138] S4, data processing: the data processing module analyzes the visible light signal of the received circuit board to identify the model of the circuit board; processes the received temperature distribution dot matrix data of the circuit board and completes the fault diagnosis of the circuit board; determines whether the circuit board has a first temperature analysis unit with an abnormal first temperature characteristic value;

[0139] S5, data display: the display module displays the fault mode of the circuit board, displays the first temperature characteristic value of each first temperature analysis unit of the circuit board; and highlights the first temperature analysis unit with abnormal first temperature characteristic value;

[0140] S6. Determine whether it is necessary to continue collecting and analyzing the temperature of the circuit board. If necessary, return to S3; if not, end.

[0141] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A circuit board fault diagnosis system, characterized in that: include: Temperature acquisition module, used to collect thermal radiation signals and visible light signals of the circuit board; Convert the thermal radiation signal of the circuit board into temperature distribution dot matrix data; send the temperature distribution dot matrix data and visible light signal of the circuit board to the data processing module; The data processing module is provided with a fault mode library of various types of circuit boards, which is used to analyze the visible light signal of the received circuit board to complete the identification of the circuit board model; process the temperature distribution dot matrix data of the received circuit board and complete the fault diagnosis of the circuit board.

2. The circuit board fault diagnosis system according to claim 1, characterized in that: The temperature acquisition module includes: The infrared detector is used to collect the thermal radiation signal of the circuit board, convert the thermal radiation signal of the circuit board from an image to an analog signal and send it to the signal processing module; A visible light camera, used to collect visible light signals from the circuit board and send them to the data processing module; The signal processing module is connected to the data processing module via a data bus, and is used to convert the received thermal radiation signal of the circuit board into temperature distribution dot matrix data and send it to the data processing module via the data bus.

3. The circuit board fault diagnosis system according to claim 1, characterized in that: The data processing module processes the received temperature distribution dot matrix data of the circuit board and completes the fault diagnosis of the circuit board, including the following steps: Step 1, cutting the temperature distribution dot matrix data of the circuit board into a plurality of first temperature analysis units; Step 2: Calculate the first temperature characteristic vector matrix of the circuit board according to each piece of first temperature information in each first temperature analysis unit; Step 3: calling a fault mode library of a circuit board of this model according to the model of the circuit board, wherein the fault mode library of the circuit board of this model contains a second temperature characteristic vector matrix of each fault mode circuit board of this model; Performing similarity matching on the first temperature feature vector matrix and each second temperature feature vector matrix respectively, and selecting the second temperature feature vector matrix with the highest matching degree with the first temperature feature vector matrix; The failure mode corresponding to the second temperature eigenvector matrix having the highest matching degree with the first temperature eigenvector matrix is ​​used as the failure mode of the circuit board.

4. The circuit board fault diagnosis system according to claim 3, characterized in that: The first temperature feature vector matrix and the second temperature feature vector are matched by similarity using the cosine similarity algorithm. The formula of the cosine similarity algorithm is as follows: Among them, a i is the i-th element in the first temperature vector matrix, b i is the i-th element in the second temperature vector matrix; cos(θ) is the cosine angle between the first temperature vector matrix and the second temperature vector matrix; the closer cos(θ) is to 1, the higher the similarity between the first temperature vector matrix and the second temperature vector matrix.

5. In the present invention, the circuit board fault diagnosis system according to claim 3 is characterized in that: The failure mode library of a model of circuit board contains the second temperature characteristic vector matrix of each failure mode circuit board of the model; the second temperature characteristic vector matrix of a failure mode circuit board of a model is obtained by the following steps: The temperature acquisition module acquires the thermal radiation signal of the circuit board of the model and the fault mode; converts the thermal radiation signal of the circuit board of the model and the fault mode into temperature distribution dot matrix data and sends it to the data processing module; The data processing module processes the received temperature distribution dot matrix data of the circuit board of the model and the fault mode to form a second temperature characteristic vector matrix of the circuit board of the model and the fault mode.

6. The circuit board fault diagnosis system according to claim 3, characterized in that: The data processing module is also provided with a normal mode library of each model of circuit board; the normal mode library of a model of circuit board contains the third temperature characteristic vector matrix of the normal mode circuit board of this model; The circuit board fault diagnosis system also includes a display module; the display module is used to display the fault mode of the circuit board and the first temperature characteristic value of each first temperature analysis unit of the circuit board; and highlight the first temperature analysis unit with abnormal first temperature characteristic value; The data processing module is also used to compare the first temperature characteristic vector matrix of the circuit board with the third temperature characteristic vector matrix of the normal mode circuit board of the corresponding model; when the difference between the first temperature characteristic vector matrix element and the corresponding third temperature characteristic vector matrix element exceeds a set value, it is judged that the first temperature characteristic value of the first temperature analysis unit corresponding to the circuit board is abnormal.

7. The circuit board fault diagnosis system according to claim 6, characterized in that: The third temperature eigenvector matrix of a normal mode circuit board is obtained by the following steps: The temperature acquisition module acquires the thermal radiation signal of the normal mode circuit board of this model; converts the thermal radiation signal of the normal mode circuit board of this model into temperature distribution dot matrix data and sends it to the data processing module; The data processing module processes the received temperature distribution dot matrix data of the normal mode circuit board of this model to form a third temperature characteristic vector matrix of the normal mode circuit board of this model.

8. The circuit board fault diagnosis system according to claim 7, characterized in that: The data processing module processes the received temperature distribution dot matrix data of a model and a fault mode circuit board to form a second temperature characteristic vector matrix of the model and the fault mode circuit board, including the following steps: Cutting the temperature distribution dot matrix data of the circuit board of the model and the failure mode into a plurality of second temperature analysis units; Calculate the second temperature characteristic vector matrix of the circuit board of the model and the fault mode according to each piece of second temperature information in each second temperature analysis unit; The data processing module processes the received temperature distribution dot matrix data of a normal mode circuit board of a model to form a third temperature characteristic vector matrix of the normal mode circuit board of the model, including the following steps: Cutting the temperature distribution dot matrix data of the normal mode circuit board of the model into a plurality of third temperature analysis units; According to each piece of third temperature information in each third temperature analysis unit, a third temperature characteristic vector matrix of the normal mode circuit board of this model is calculated.

9. The circuit board fault diagnosis system according to claim 1, characterized in that: The temperature acquisition module is also used to collect visible light signals from various types of circuit boards and send them to the data processing module; The data processing module is also used to store the received visible light signals of the circuit boards of various models; The data processing module analyzes the received visible light signal of the circuit board to complete the identification of the circuit board model, including the following steps: The visible light signal of the circuit board is matched with the visible light signals of the circuit boards of various models, and the model corresponding to the matched visible light signal is the model of the circuit board.

10. A circuit board fault diagnosis method, characterized in that: The circuit board fault diagnosis system according to any one of claims 1 to 9 comprises the following steps: S1. System self-check: After the system is powered on, the status of each module inside the system is checked; if the status is normal, the next step of the workflow is entered; if an abnormality occurs, the system stops working and an alarm is issued; S2, system startup: each module in the system starts working; S3, data acquisition: the temperature acquisition module acquires the thermal radiation signal and visible light signal of the circuit board; converts the thermal radiation signal of the circuit board into temperature distribution dot matrix data; and sends the temperature distribution dot matrix data and visible light signal of the circuit board to the data processing module; S4, data processing: the data processing module analyzes the visible light signal of the received circuit board to identify the model of the circuit board; processes the received temperature distribution dot matrix data of the circuit board and completes the fault diagnosis of the circuit board; determines whether the circuit board has a first temperature analysis unit with an abnormal first temperature characteristic value; S5, data display: the display module displays the fault mode of the circuit board and the first temperature characteristic value of each first temperature analysis unit of the circuit board; Highlight the first temperature analysis unit with abnormal first temperature characteristic value in color; S6. Determine whether it is necessary to continue collecting and analyzing the temperature of the circuit board. If necessary, return to S3; if not, end.

Images