Portable data acquisition and analysis device for fault diagnosis of industrial equipment

Abstract

The invention discloses a portable data acquisition analysis device for fault diagnosis of industrial equipment, and relates to the technical field of data acquisition analyzers, the portable data acquisition analysis device comprises a data acquisition analyzer body, sliding grooves are symmetrically formed in the two sides of the data acquisition analyzer body, and the portable data acquisition analysis device further comprises a portable protection adjusting mechanism and an intelligent control system. According to the data acquisition analyzer, when the data acquisition analyzer is not used, the end part of the data acquisition analyzer body and each interface are protected by utilizing the protective vertical cover, so that the data acquisition analyzer body is prevented from being collided by an external environment, external dust is prevented from entering the interfaces, and the subsequent use of the data acquisition analyzer body is prevented from being influenced; when the protective vertical cover is used and opened, the protective vertical cover is used for supporting the data acquisition analyzer body, the data acquisition analyzer body is jacked up, and a space is reserved at the bottom of the data acquisition analyzer body, so that heat dissipation of the data acquisition analyzer body is facilitated, and deviation of a diagnosed data result caused by over-high operation of the data acquisition analyzer body is avoided.

Description

Technical Field

[0001] The invention relates to the technical field of data acquisition and analysis instruments, and in particular to a portable data acquisition and analysis device for industrial equipment fault diagnosis. Background Art

[0002] In the prior art, a data acquisition analyzer, also known as a data acquisition analyzer, is an instrument used to collect, process and display data from various measuring sensors. In the process of fault diagnosis of industrial motors, it is usually necessary to connect a detection wire between the data acquisition analyzer and the industrial motor, and one end of the wire connected to the industrial motor is usually provided with different sensors. By adsorbing the sensors to different monitoring node positions of the industrial motor, the fault diagnosis and analysis of the industrial motor is performed by using the monitoring of the sensors;

[0003] However, since a number of interfaces are usually provided on the data acquisition analyzer, and the existing data acquisition analyzers often lack effective protective structures, the data acquisition analyzer is easy to collide with objects in the external environment during carrying, making the data acquisition analyzer easy to be damaged when not in use. The interfaces are also easy to enter dust and moisture pollutants in the external environment, and then enter the analyzer through the interfaces, not only contaminating the interface contacts and causing poor contact, but also corroding and damaging the circuit boards and electronic components inside the analyzer, which not only reduces the service life of the analyzer, but also affects the accuracy and reliability of its measurement, causing troubles for subsequent data analysis and diagnosis;

[0004] In addition, during use, the existing digital acquisition analyzers have limited bottom space and poor heat dissipation. Long-term operation will cause the analyzer itself to overheat, thereby affecting the performance of its internal electronic components and ultimately reducing the accuracy of diagnostic data.

[0005] In view of this, the present invention proposes a portable data acquisition and analysis device for industrial equipment fault diagnosis to make up for and improve the deficiencies of the prior art. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides a portable data acquisition and analysis device for industrial equipment fault diagnosis to solve the corresponding technical problems raised in the above background technology.

[0007] To achieve the above purpose, the technical solution adopted by the present invention is: a portable data acquisition and analysis device for industrial equipment fault diagnosis, including a data acquisition and analysis instrument body, the two sides of the data acquisition and analysis instrument body are symmetrically provided with slide grooves, and also includes: a portable protection adjustment mechanism and an intelligent control system, and the portable protection adjustment mechanism is arranged on the data acquisition and analysis instrument body;

[0008] The intelligent control system includes a data acquisition unit, a data analysis unit, a fault assessment unit, a fault analysis unit and a sending unit;

[0009] The data acquisition unit is used to obtain the size data of the industrial motor to be diagnosed from the network database, and to establish a spatial model, to define a number of monitoring nodes on the spatial model, to obtain the status information at the monitoring nodes through the sensor group and to send it to the data analysis unit;

[0010] The data analysis unit includes an anomaly detection module and a fault location module. The anomaly detection module is used to obtain the status information at each monitoring node and output it as actual operation data. According to the standard operation data of the industrial motor to be diagnosed, the monitoring nodes that deviate from the standard operation data are analyzed and marked;

[0011] The fault location module is used to obtain monitoring nodes that deviate from standard operating data, combine the monitoring node layout in the space model, and determine the specific faulty components of the industrial motor through space mapping technology to preliminarily determine the location of the fault;

[0012] The fault assessment unit is used to obtain the fault location, connect the fault locations to form a fault area, establish a fault model using a regression analysis method, quantify the severity of the fault, and classify the fault severity into minor, medium and severe levels;

[0013] The fault analysis unit is used to obtain the severity of the quantitative fault, analyze the impact type caused by the fault location according to the severity of the quantitative fault and the location of the fault, evaluate the priority of maintenance, and generate a fault diagnosis report;

[0014] The sending unit is used to obtain the fault diagnosis report and send it to the user end.

[0015] Preferably, the portable protective adjustment mechanism includes protective vertical covers symmetrically arranged at the front and rear ends of the digital acquisition and analysis instrument body, and operating hand plates are symmetrically fixedly connected on both sides of the protective vertical covers. The operating hand plate is fixedly connected to a connecting column at one end away from the protective vertical covers, and the connecting column is slidably connected in a slide groove at one end away from the operating hand plate.

[0016] Preferably, arc grooves are symmetrically provided on both sides of the data acquisition and analysis instrument body, a sliding guide column is slidably connected in the arc groove, a C-shaped rotating plate is fixedly connected to the sliding guide column, a double card groove is provided on the inner surface of the C-shaped rotating plate, a double card plate is fixedly connected to the outer surface of the connecting column, and the double card plate is adapted to the double card groove.

[0017] Preferably, positioning pins are symmetrically fixedly connected to the front operating hand panel, and pin holes are symmetrically opened on the rear operating hand panel, and the positioning pins are plugged into the pin holes.

[0018] As a preferred embodiment, the specific process of analyzing and marking the monitoring nodes that deviate from the standard operation data is as follows:

[0019] S101, comparing the standard operating data of the industrial motor to be diagnosed with the actual operating data X outputted by the status information at each monitoring node, wherein the actual operating data X includes the vibration amplitude X 1 , temperature value X 2 , current value X 3 , the operating coefficient W is calculated based on the actual operating data X, and the calculation formula is:

[0020] Where W is the operating coefficient, which is used to quantitatively evaluate the deviation between the state of the industrial motor in the actual operation process and the standard operating state;

[0021] X i1 is the ideal vibration amplitude, Xi2 is the ideal temperature value, and Xi3 is the ideal current value;

[0022] k 1 , k 2 , k 3 is the preset weight coefficient;

[0023] Combined with the obtained operating coefficient W, the monitoring nodes that deviate from the standard operating data are preliminarily identified and analyzed and marked as nodes to be analyzed;

[0024] S102, using the Z score method to convert the actual operation data X output by the node to be analyzed into a standardized measurement value Z relative to the average value, which represents the degree of deviation of the data of the monitoring node relative to the standard operation data, and the formula is:

[0025] Among them, μ is the average value of the actual operation data of all monitoring nodes, indicating the center position of the data set;

[0026] σ is the standard deviation of the actual operating data of all monitoring nodes, which is used to measure the degree of data dispersion;

[0027] According to the calculated Z score, the monitoring nodes whose data deviate from the normal range are judged. The positive or negative value of the Z score indicates the positive or negative deviation of the data point relative to the average value, and the absolute value of the Z score indicates the degree of deviation. The preset standard threshold is obtained. When the absolute value of the Z score is greater than the standard threshold, the data of the monitoring node is considered to be an outlier.

[0028] S103. Mark the position of the node to be analyzed according to the outlier detection result to obtain the outlier node.

[0029] As a preferred method, the specific process of preliminarily determining the fault location is as follows:

[0030] S201, establish a three-dimensional coordinate system, select the geometric center of the industrial motor as the origin, take the axial direction of the industrial motor as the Z axis, select two mutually perpendicular straight lines in a plane perpendicular to the axial direction as the X axis and the Y axis, determine the spatial positions of various components and nodes inside the industrial motor, divide the industrial motor into multiple nodes according to the design drawings and internal structure of the industrial motor, assign a unique identifier to each node, and determine its position coordinates in the coordinate system, store the position coordinates, identifiers and related attribute information of all nodes in a database, constitute a spatial model of the industrial motor, obtain the position and abnormal value of the abnormal node from the abnormal detection module, and match the node to be analyzed with the corresponding node in the spatial model;

[0031] S202, obtaining the position information of the abnormal node from the abnormality detection module, including the coordinates of the X-axis, Y-axis, and Z-axis and the abnormal value of the abnormal node, obtaining the position coordinates, unique identifier, and related attribute information of each node from the database, comparing the position coordinates of the abnormal node with the node coordinates in the spatial model, finding the spatial model node close to the coordinates of the abnormal node by calculating the spatial distance between the abnormal node and each node in the spatial model, and further comparing the attribute information of the abnormal node with the attribute information of the spatial model node on the basis of coordinate matching, confirming that the spatial model node is the corresponding position of the abnormal node inside the motor, mapping the abnormal node to the corresponding component in the spatial model, and determining the component that deviates significantly from the standard operation data according to the result of the spatial mapping;

[0032] S203: Based on the layout of the components in the space model and the connection relationship between them, preliminarily determine the specific location where the fault occurs.

[0033] As a preferred embodiment, the specific process of quantifying the severity of the fault is as follows:

[0034] S301, obtaining the specific location where the fault occurs, marking the location where the fault occurs in the spatial model to form a fault area, and extracting actual operation data X of the fault area;

[0035] S302, using polynomial regression method to establish a fault model, the formula is: Y = β 0 +β 1 X 1 +β 2 X 2 +......+β n X n +e;

[0036] Among them, Y is the target variable, indicating the severity of the fault;

[0037] X 1 , X 2 ,……X n is the independent variable, representing the fault characteristic data;

[0038] β 0 is the intercept term, which means that when all independent variables X 1 , X 2 ,……X n When both are 0, it is the baseline value of fault severity;

[0039] β 1 , β 2 , ... β n is the regression coefficient, which means that each independent variable X i The impact on the fault severity Y;

[0040] e is the error term, which represents the random error that cannot be explained by the model. It is usually assumed that e follows a normal distribution with a mean of 0;

[0041] S303, use historical fault data to train the model, and solve the regression coefficient by the least square method, the formula is:

[0042] Among them, Y i is the actual fault severity of the i-th sample;

[0043] is the predicted fault severity of the i-th sample, and its calculation formula is:

[0044]

[0045] By solving the minimum value of the objective function, the regression coefficient β can be obtained 0 , β 1 , β 2 , ... β n The optimal value of

[0046] S304: Input the characteristic data of the current fault area into the trained fault model, calculate the value of the fault severity Y according to the fault model, and classify the fault severity into the following levels according to the calculated Y value:

[0047] Slight: Y≤Y 1 ;

[0048] Medium: Y 1 <Y≤Y 2 ;

[0049] Severe: Y>Y 2 ;

[0050] Among them, Y1 and Y 2 It is a threshold set based on historical data or domain knowledge;

[0051] S305, using the historical fault data set to verify the accuracy of the fault model, if the model error is within an acceptable range, the model is considered valid and the fault model is obtained;

[0052] S306 , substituting the actual operation data X of the current fault area into the fault model, calculating the value of the fault severity Y, and comparing the calculated Y value with the thresholds according to the preset fault level classification standard to obtain the quantified fault severity.

[0053] As a preferred embodiment, the specific process of generating a fault diagnosis report is as follows:

[0054] S401, obtaining the fault location, obtaining the overall structure of the industrial motor and the functions of each component, analyzing the impact caused by the fault location, and dividing the impact into three categories: vibration damage, thermal damage, and electrical damage. Based on the impact classification result, combined with a comprehensive evaluation of the severity level of the quantitative fault, the vibration damage, thermal damage, and electrical damage are further divided into severity levels;

[0055] S402, according to different types of faults and their severity, obtain preset weights of vibration damage, thermal damage, and electrical damage, adjust the vibration damage score, thermal damage score, and electrical damage score according to the weights, add up the scores to get a total score, and determine the maintenance priority according to the total score. The higher the score, the greater the impact of the fault on the motor operation system, and the maintenance is given priority;

[0056] S403, obtaining maintenance priorities and generating a fault diagnosis report, and formulating a maintenance plan according to the maintenance priorities, including maintenance methods, required conditions, maintenance time, and maintenance personnel.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] (1) By setting up a portable protective adjustment mechanism, the protective cover can be used to protect the end of the digital acquisition analyzer body and various interfaces when not in use, so as to prevent the external environment from causing bumps on the digital acquisition analyzer body and external dust from entering the interfaces, thereby affecting the subsequent use of the digital acquisition analyzer body. The movable design of the protective cover, combined with the movement of the connecting column and the synchronous rotation and positioning of the C-shaped rotating plate, can support the digital acquisition analyzer body when the protective cover is opened, lift the digital acquisition analyzer body and reserve space at the bottom, so as to facilitate the heat dissipation of the digital acquisition analyzer body and avoid the digital acquisition analyzer body running too high and causing deviations in the diagnostic data results.

[0059] (2) By obtaining the detection nodes that deviate from the standard operating data, analyzing the abnormal value data of the monitoring nodes and obtaining the abnormal nodes, combined with the spatial model of the industrial motor, the abnormal nodes are mapped to the corresponding components in the spatial model to obtain the specific location of the fault. Combined with the fault model, the severity of the fault is quantified. By comprehensively considering the fault type, the score is adjusted according to the weight of each fault type, the maintenance priority is determined, and a fault diagnosis report is generated and sent to the user end, thereby improving the efficiency and accuracy of fault diagnosis and facilitating users to take maintenance measures in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a schematic diagram of the overall structure of a preferred embodiment of the present invention;

[0061] Figure 2 This is a schematic diagram of the protective cover shown in the present invention being opened;

[0062] Figure 3 It is a schematic diagram of the split structure of the C-shaped rotating plate and the connecting column shown in the present invention;

[0063] Figure 4 It is a schematic diagram of the structure of the intelligent control system shown in the present invention.

[0064] The numbers in the figure are:

[0065] 1. Data acquisition analyzer body; 2. Slideway; 3. Arc groove;

[0066] 4. Portable protective adjustment mechanism; 401. Protective cover; 402. Operating hand plate; 403. Connecting column; 404. Double card plate; 405. Positioning pin; 406. Pin hole; 407. C-shaped rotating plate; 408. Double card slot; 409. Sliding guide column. DETAILED DESCRIPTION

[0067] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] Embodiment 1 of the present invention:

[0069] Please refer to Figures 1 to 3 As shown, a portable data acquisition and analysis device for industrial equipment fault diagnosis includes a data acquisition and analysis instrument body 1, and slide grooves 2 are symmetrically opened on both sides of the data acquisition and analysis instrument body 1, and also includes: a portable protection adjustment mechanism 4 and an intelligent control system, and the portable protection adjustment mechanism 4 is arranged on the data acquisition and analysis instrument body 1;

[0070] The portable protective adjustment mechanism 4 includes a protective stand 401 symmetrically arranged at the front and rear ends of the data acquisition and analysis instrument body 1, and operating hand plates 402 are symmetrically fixedly connected to both sides of the protective stand 401, and one end of the operating hand plate 402 away from the protective stand 401 is fixedly connected to a connecting column 403, and one end of the connecting column 403 away from the operating hand plate 402 is slidably connected to the slide groove 2;

[0071] Both sides of the data acquisition and analysis instrument body 1 are symmetrically provided with arc grooves 3, and a sliding guide column 409 is slidably connected in the arc groove 3. Both ends of the arc groove 3 are provided with card slots, and a card plug is fixedly provided on the sliding guide column 409, and the card plug is adapted to the card slot. Initially, the card plug is connected to one of the card slots, and a C-shaped rotating plate 407 is fixedly connected to the sliding guide column 409, and a double card slot 408 is provided on the inner surface of the C-shaped rotating plate 407. A double card plate 404 is fixedly connected to the outer surface of the connecting column 403, and the double card plate 404 is adapted to the double card slot 408;

[0072] The front operating hand plate 402 is symmetrically fixedly connected with positioning pins 405 , and the rear operating hand plate 402 is symmetrically provided with pin holes 406 , and the positioning pins 405 are plugged into the pin holes 406 .

[0073] The following is the working process of the portable protection adjustment mechanism 4:

[0074] It should be noted that in the initial state, when the data acquisition and analysis instrument body 1 is not in use, the state of the data acquisition and analysis instrument body 1 is as follows: Figure 1 As shown, when the data acquisition and analysis instrument body 1 is in use, the state of the data acquisition and analysis instrument body 1 is as follows Figure 2 As shown;

[0075] like Figures 1 to 3 As shown, when the data acquisition and analysis instrument body 1 is used, since the data acquisition and analysis instrument body 1 is symmetrically covered with protective vertical covers 401 on both sides, and the protective vertical covers 401 are connected to the data acquisition and analysis instrument body 1 in a movable connection mode, that is, slide grooves 2 are symmetrically provided on both sides of the data acquisition and analysis instrument body 1, and operating hand plates 402 are symmetrically fixedly provided on both sides of the protective vertical covers 401, and the ends of the two operating hand plates 402 on the same data acquisition and analysis instrument body 1 away from the data acquisition and analysis instrument body 1 are fixedly provided with connecting columns 403, and the connecting columns 403 are slidably arranged in the slide grooves 2, so that the protective vertical covers 401 can be movably connected to the data acquisition and analysis instrument body 1, combined with Figure 3It can be seen that two operating hand plates 402 are respectively arranged on both sides of the data acquisition and analysis instrument body 1. In the initial state, the facing surfaces of the two adjacent operating hand plates 402 on the same side are respectively provided with positioning pins 405 and pin holes 406, and the positioning pins 405 and pin holes 406 on the same side are adapted. Initially, the positioning pins 405 are inserted into the pin holes 406, and the two adjacent operating hand plates 402 are connected to form an integral structure. There is a gap between the operating hand plates 402 and the data acquisition and analysis instrument body 1 due to the design of the connecting column 403. Therefore, when the staff carries the data acquisition and analysis instrument body 1, the two mutually connected operating hand plates 402 can be used to lift the data acquisition and analysis instrument body 1, so as to facilitate carrying. The operating hand plates 402 structures connected to each other are arranged on both sides of the data acquisition and analysis instrument body 1. Therefore, when the staff carries it, there is no need to deliberately find the handle side, thereby saving the time of taking the data acquisition and analysis instrument body 1, and it can be more convenient in operation.

[0076] like Figures 1 to 3 As shown, a double clamping plate 404 is fixedly arranged on the outer surface of the connecting column 403, and arc grooves 3 (combined with Figure 2 It can be seen that the arc groove 3 is arranged at the outer sides of both ends of the slide groove 2. When the connecting column 403 slides to the end position of the slide groove 2, it moves close to the arc groove 3, and a sliding guide column 409 is slidingly arranged in the arc groove 3, and a C-shaped rotating plate 407 is arranged on the sliding guide column 409. When the staff uses the data acquisition analyzer body 1 to diagnose the fault of the industrial motor, first, the two adjacent clamped operating hand plates 402 can be disconnected by controlling the operating hand plate 402 to separate them, and the operating hand plate 402 can be disconnected by the setting of the connecting column 403 and the slide groove 2. The two operating hand plates 402 on the same side move in opposite directions. When the connecting column 403 slides to the end of the slide groove 2, it will contact the C-shaped rotating plate 407. Since the inner surface of the C-shaped rotating plate 407 is provided with a double card groove 408, and the double card groove 408 is adapted to the double card plate 404 on the outer surface of the connecting column 403, when the connecting column 403 contacts the C-shaped rotating plate 407, the double card plate 404 moves synchronously and is inserted into the double card groove 408. At this time, the staff can rotate the operating hand plate 402 to change the state of the protective cover 401 from Figure 1 Change to Figure 2At this time, the protection cover 401 is provided to support the data acquisition analyzer body 1, so that space is reserved at the bottom of the data acquisition analyzer body 1, so as to facilitate the heat dissipation of the data acquisition analyzer body 1 during the subsequent operation. The arc groove 3 is provided with a card slot at both ends, and a card plug is fixedly provided on the sliding guide column 409, and the card plug is adapted to the card slot. Initially, the card plug is connected to one of the card slots. After rotation, the card plug can be connected to another card slot, and the rotation angle of the C-shaped rotating plate 407 is limited, thereby limiting the position of the protection cover 401, so that the protection cover 401 can be more stable when supporting the data acquisition analyzer body 1;

[0077] By setting up a portable protective adjustment mechanism 4, when not in use, the protective stand 401 provided can be used to protect the end of the digital acquisition and analyzer body 1 and various interfaces, so as to prevent the external environment from causing bumps on the digital acquisition and analyzer body 1, and external dust from entering the interfaces, thereby affecting the subsequent use of the digital acquisition and analyzer body 1. The movable design of the protective stand 401, in conjunction with the movement of the connecting column 403 and the synchronous rotation positioning of the C-shaped rotating plate 407, can support the digital acquisition and analyzer body 1 when the protective stand 401 is opened for use, lift up the digital acquisition and analyzer body 1 and reserve space at its bottom, thereby facilitating the heat dissipation of the digital acquisition and analyzer body 1 and preventing the digital acquisition and analyzer body 1 from running too high and causing deviations in the diagnostic data results.

[0078] Embodiment 2 of the present invention:

[0079] Please refer to Figure 4 As shown, a portable data acquisition and analysis device for industrial equipment fault diagnosis also includes: an intelligent control system;

[0080] The intelligent control system includes a data acquisition unit, a data analysis unit, a fault assessment unit, a fault analysis unit and a sending unit;

[0081] The data acquisition unit is used to obtain the dimension data of the industrial motor to be diagnosed from the network database, and to establish a spatial model, to define a number of monitoring nodes on the spatial model, to obtain the status information at the monitoring nodes through the sensor group and to send it to the data analysis unit;

[0082] The data analysis unit includes an anomaly detection module and a fault location module. The anomaly detection module is used to obtain the status information at each monitoring node and output it as actual operation data. According to the standard operation data of the industrial motor to be diagnosed, the monitoring nodes that deviate from the standard operation data are analyzed and marked;

[0083] The fault location module is used to obtain monitoring nodes that deviate from standard operating data, and determine the specific faulty components of the industrial motor through spatial mapping technology in combination with the monitoring node layout in the spatial model, and preliminarily determine the location of the fault;

[0084] The fault assessment unit is used to obtain the fault location, connect the fault locations to form a fault area, establish a fault model using a regression analysis method, quantify the severity of the fault, and classify the fault severity into minor, medium, and severe levels;

[0085] The fault analysis unit is used to obtain the severity of the quantitative fault, analyze the impact type caused by the fault location according to the severity of the quantitative fault and the location of the fault, evaluate the priority of maintenance, and generate a fault diagnosis report;

[0086] The sending unit is used to obtain the fault diagnosis report and send it to the user end;

[0087] The specific process of analyzing and marking monitoring nodes that deviate from standard operating data is as follows:

[0088] S101, comparing the standard operating data of the industrial motor to be diagnosed with the actual operating data X outputted by the status information at each monitoring node, where the actual operating data X includes the vibration amplitude X 1 , temperature value X 2 , current value X 3 , the operating coefficient W is calculated based on the actual operating data X, and the calculation formula is:

[0089]

[0090] Where W is the operating coefficient, which is used to quantitatively evaluate the deviation between the state of the industrial motor in the actual operation process and the standard operating state;

[0091] X i1 is the ideal vibration amplitude, Xi2 is the ideal temperature value, and Xi3 is the ideal current value;

[0092] k 1 , k 2 , k 3 is the preset weight coefficient;

[0093] Combined with the obtained operating coefficient W, the monitoring nodes that deviate from the standard operating data are preliminarily identified and analyzed and marked as nodes to be analyzed;

[0094] S102, using the Z score method to convert the actual operation data X output by the node to be analyzed into a standardized measurement value Z relative to the average value, which represents the degree of deviation of the data of the monitoring node relative to the standard operation data, and the formula is:

[0095] Among them, μ is the average value of the actual operation data of all monitoring nodes, indicating the center position of the data set;

[0096] σ is the standard deviation of the actual operating data of all monitoring nodes, which is used to measure the degree of data dispersion;

[0097] According to the calculated Z score, the monitoring nodes whose data deviate from the normal range are judged. The positive or negative value of the Z score indicates the positive or negative deviation of the data point relative to the average value, and the absolute value of the Z score indicates the degree of deviation. The preset standard threshold is obtained. When the absolute value of the Z score is greater than the standard threshold, the data of the monitoring node is considered to be an outlier.

[0098] S103, marking the position of the node to be analyzed according to the outlier detection result, and obtaining the outlier node;

[0099] The specific process of initially determining the fault location is as follows:

[0100] S201, establish a three-dimensional coordinate system, select the geometric center of the industrial motor as the origin, take the axial direction of the industrial motor as the Z axis, select two mutually perpendicular straight lines in a plane perpendicular to the axial direction as the X axis and the Y axis, determine the spatial positions of various components and nodes inside the industrial motor, divide the industrial motor into multiple nodes according to the design drawings and internal structure of the industrial motor, assign a unique identifier to each node, and determine its position coordinates in the coordinate system, store the position coordinates, identifiers and related attribute information of all nodes in a database, constitute a spatial model of the industrial motor, obtain the position and abnormal value of the abnormal node from the abnormal detection module, and match the node to be analyzed with the corresponding node in the spatial model;

[0101] S202, obtaining the position information of the abnormal node from the abnormality detection module, including the coordinates of the X-axis, Y-axis, and Z-axis and the abnormal value of the abnormal node, obtaining the position coordinates, unique identifier, and related attribute information of each node from the database, comparing the position coordinates of the abnormal node with the node coordinates in the spatial model, finding the spatial model node close to the coordinates of the abnormal node by calculating the spatial distance between the abnormal node and each node in the spatial model, and further comparing the attribute information of the abnormal node with the attribute information of the spatial model node on the basis of coordinate matching, confirming that the spatial model node is the corresponding position of the abnormal node inside the motor, mapping the abnormal node to the corresponding component in the spatial model, and determining the component that deviates significantly from the standard operation data according to the result of the spatial mapping;

[0102] S203, preliminarily determine the specific location where the fault occurs based on the layout of the components in the space model and the connection relationship between them;

[0103] The specific process of quantifying the severity of a fault is as follows:

[0104] S301, obtaining the specific location where the fault occurs, marking the location where the fault occurs in the spatial model to form a fault area, and extracting actual operation data X of the fault area;

[0105] S302, using polynomial regression method to establish a fault model, the formula is: Y = β 0 +β 1 X 1 +β 2 X 2 +......+β n X n +e;

[0106] Among them, Y is the target variable, indicating the severity of the fault;

[0107] X 1 , X 2 ,……X n is the independent variable, representing the fault characteristic data;

[0108] β 0 is the intercept term, which means that when all independent variables X 1 , X 2 ,……X n When both are 0, it is the baseline value of fault severity;

[0109] β 1 , β 2 , ... β n is the regression coefficient, which means that each independent variable X i The impact on the fault severity Y;

[0110] e is the error term, which represents the random error that cannot be explained by the model. It is usually assumed that e follows a normal distribution with a mean of 0;

[0111] S303, use historical fault data to train the model, and solve the regression coefficient by the least square method, the formula is:

[0112] Among them, Y i is the actual fault severity of the i-th sample;

[0113] is the predicted fault severity of the i-th sample, and its calculation formula is:

[0114]

[0115] By solving the minimum value of the objective function, the regression coefficient β can be obtained 0 , β 1, β 2 , ... β n The optimal value of

[0116] S304: Input the characteristic data of the current fault area into the trained fault model, calculate the value of the fault severity Y according to the fault model, and classify the fault severity into the following levels according to the calculated Y value:

[0117] Slight: Y≤Y 1 ;

[0118] Medium: Y 1 <Y≤Y 2 ;

[0119] Severe: Y>Y 2 ;

[0120] Among them, Y 1 and Y 2 It is a threshold set based on historical data or domain knowledge;

[0121] S305, using the historical fault data set to verify the accuracy of the fault model, if the model error is within an acceptable range, the model is considered valid and the fault model is obtained;

[0122] S306, substituting the actual operation data X of the current fault area into the fault model, calculating the value of the fault severity Y, and comparing the calculated Y value with the thresholds according to the preset fault level classification standard to obtain the severity of the quantitative fault;

[0123] The specific process of generating a fault diagnosis report is as follows:

[0124] S401, obtaining the fault location, obtaining the overall structure of the industrial motor and the functions of each component, analyzing the impact caused by the fault location, and dividing the impact into three categories: vibration damage, thermal damage, and electrical damage. Based on the impact classification result, combined with a comprehensive evaluation of the severity level of the quantitative fault, the vibration damage, thermal damage, and electrical damage are further divided into severity levels;

[0125] S402, according to different types of faults and their severity, obtain preset weights of vibration damage, thermal damage, and electrical damage, adjust the vibration damage score, thermal damage score, and electrical damage score according to the weights, add up the scores to get a total score, and determine the maintenance priority according to the total score. The higher the score, the greater the impact of the fault on the motor operation system, and the maintenance is given priority;

[0126] S403, obtaining maintenance priorities and generating a fault diagnosis report, and formulating a maintenance plan according to the maintenance priorities, including maintenance methods, required conditions, maintenance time, and maintenance personnel.

[0127] By obtaining the detection nodes that deviate from the standard operating data, analyzing the abnormal value data of the monitoring nodes and obtaining the abnormal nodes, combined with the spatial model of the industrial motor, the abnormal nodes are mapped to the corresponding components in the spatial model to obtain the specific location of the fault. Combined with the fault model, the severity of the fault is quantified. By comprehensively considering the fault type, the score is adjusted according to the weight of each fault type, the maintenance priority is determined, and a fault diagnosis report is generated and sent to the user end, thereby improving the efficiency and accuracy of fault diagnosis and facilitating users to take maintenance measures in a timely manner.

[0128] By setting up the intelligent control system and combining the forage wetting auxiliary mechanism 5, the spraying frequency of the water mist can be automatically adjusted according to the forage wetting state requirements, so as to ensure that the forage is wetted to a moderate degree, neither too wet to cause adhesion nor too dry to cause difficulty in crushing. Compared with the continuous and fixed spraying method, the waste of water resources can be reduced. At the same time, the heat generated by the wet forage during the crushing process is also less, which helps to reduce energy consumption.

[0129] By obtaining the actual moisture content data of the forage to be processed, the humidification difference is calculated in combination with the ideal moisture content data of the forage to be processed, and a wetting efficiency model is established according to the linear regression method, the preset processing parameters of the forage wetting auxiliary mechanism 5 are combined with the humidification difference to calculate the actual processing parameters of the forage wetting auxiliary mechanism 5, and the bidirectional synchronous motor 506 is controlled to access the circuit, so that the piston rod 514 can reciprocate and suck inside the lower end of the T-shaped connecting tube 512, and the forage inside the feed hopper 3 is atomized and sprayed with water, so as to increase the wetting degree of the forage, improve the wetting accuracy of the forage, and optimize the processing efficiency and quality.

[0130] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technical personnel in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0131] The above formulas are all dimensionless and numerical calculations. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0132] In the two embodiments provided in the present application, it should be understood that the disclosed devices and systems can be implemented in other ways; for example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed; another point, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, the indirect coupling or communication connection of devices or modules can be electrical, mechanical or other forms;

[0133] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A portable data acquisition and analysis device for industrial equipment fault diagnosis, comprising a data acquisition and analysis instrument body (1), wherein two sides of the data acquisition and analysis instrument body (1) are symmetrically provided with slide grooves (2), characterized in that: It also includes: a portable protection adjustment mechanism (4) and an intelligent control system, and the portable protection adjustment mechanism (4) is arranged on the data acquisition and analysis instrument body (1); The intelligent control system includes a data acquisition unit, a data analysis unit, a fault assessment unit, a fault analysis unit and a sending unit; The data acquisition unit is used to obtain the size data of the industrial motor to be diagnosed from the network database, and to establish a spatial model, to define a number of monitoring nodes on the spatial model, to obtain the status information at the monitoring nodes through the sensor group and to send it to the data analysis unit; The data analysis unit includes an anomaly detection module and a fault location module. The anomaly detection module is used to obtain the status information at each monitoring node and output it as actual operation data. According to the standard operation data of the industrial motor to be diagnosed, the monitoring nodes that deviate from the standard operation data are analyzed and marked; The fault location module is used to obtain monitoring nodes that deviate from standard operating data, combine the monitoring node layout in the space model, and determine the specific faulty components of the industrial motor through space mapping technology to preliminarily determine the location of the fault; The fault assessment unit is used to obtain the fault location, connect the fault locations to form a fault area, establish a fault model using a regression analysis method, quantify the severity of the fault, and classify the fault severity into minor, medium and severe levels; The fault analysis unit is used to obtain the severity of the quantitative fault, analyze the impact type caused by the fault location according to the severity of the quantitative fault and the location of the fault, evaluate the priority of maintenance, and generate a fault diagnosis report; The sending unit is used to obtain the fault diagnosis report and send it to the user end.

2. A portable data acquisition and analysis device for industrial equipment fault diagnosis according to claim 1, characterized in that: The portable protective adjustment mechanism (4) comprises a protective stand (401) symmetrically arranged at the front and rear ends of the data acquisition and analysis instrument body (1); operating hand plates (402) are symmetrically fixedly connected to both sides of the protective stand (401); one end of the operating hand plate (402) away from the protective stand (401) is fixedly connected to a connecting column (403); and one end of the connecting column (403) away from the operating hand plate (402) is slidably connected to the slide groove (2).

3. A portable data acquisition and analysis device for industrial equipment fault diagnosis according to claim 2, characterized in that: Both sides of the data acquisition and analysis instrument body (1) are symmetrically provided with arc grooves (3), a sliding guide column (409) is slidably connected in the arc groove (3), a C-shaped rotating plate (407) is fixedly connected to the sliding guide column (409), a double card groove (408) is provided on the inner surface of the C-shaped rotating plate (407), a double card plate (404) is fixedly connected to the outer surface of the connecting column (403), and the double card plate (404) is adapted to the double card groove (408).

4. A portable data acquisition and analysis device for industrial equipment fault diagnosis according to claim 2, characterized in that: The front end of the operating hand plate (402) is symmetrically fixedly connected with a positioning pin (405), and the rear end of the operating hand plate (402) is symmetrically provided with a pin hole (406), and the positioning pin (405) is plugged into the pin hole (406).

5. A portable data acquisition and analysis device for industrial equipment fault diagnosis according to claim 1, characterized in that: The specific process of analyzing and marking monitoring nodes that deviate from standard operating data is as follows: S101. Compare the standard operating data of the industrial motor to be diagnosed with the actual operating data X output by the status information at each monitoring node, wherein the actual operating data X includes the vibration amplitude X1, the temperature value X2, and the current value X3. Calculate the operating coefficient W according to the actual operating data X. The calculation formula is: Where W is the operating coefficient, which is used to quantitatively evaluate the deviation between the state of the industrial motor in the actual operation process and the standard operating state; X i1 is the ideal vibration amplitude, Xi2 is the ideal temperature value, and Xi3 is the ideal current value; k1, k2, k3 are preset weight coefficients; Combined with the obtained operating coefficient W, the monitoring nodes that deviate from the standard operating data are preliminarily identified and analyzed and marked as nodes to be analyzed; S102, using the Z score method to convert the actual operation data X output by the node to be analyzed into a standardized measurement value Z relative to the average value, which represents the degree of deviation of the data of the monitoring node relative to the standard operation data, and the formula is: Among them, μ is the average value of the actual operation data of all monitoring nodes, indicating the center position of the data set; σ is the standard deviation of the actual operating data of all monitoring nodes, which is used to measure the degree of data dispersion; According to the calculated Z score, the monitoring nodes whose data deviate from the normal range are judged. The positive or negative value of the Z score indicates the positive or negative deviation of the data point relative to the average value, and the absolute value of the Z score indicates the degree of deviation. The preset standard threshold is obtained. When the absolute value of the Z score is greater than the standard threshold, the data of the monitoring node is considered to be an outlier. S103. Mark the position of the node to be analyzed according to the outlier detection result to obtain the outlier node.

6. A portable data acquisition and analysis device for industrial equipment fault diagnosis according to claim 5, characterized in that: The specific process of initially determining the fault location is as follows: S201, establish a three-dimensional coordinate system, select the geometric center of the industrial motor as the origin, take the axial direction of the industrial motor as the Z axis, select two mutually perpendicular straight lines in a plane perpendicular to the axial direction as the X axis and the Y axis, determine the spatial positions of various components and nodes inside the industrial motor, divide the industrial motor into multiple nodes according to the design drawings and internal structure of the industrial motor, assign a unique identifier to each node, and determine its position coordinates in the coordinate system, store the position coordinates, identifiers and related attribute information of all nodes in a database, constitute a spatial model of the industrial motor, obtain the position and abnormal value of the abnormal node from the abnormal detection module, and match the node to be analyzed with the corresponding node in the spatial model; S202, obtaining the position information of the abnormal node from the abnormality detection module, including the coordinates of the X-axis, Y-axis, and Z-axis and the abnormal value of the abnormal node, obtaining the position coordinates, unique identifier, and related attribute information of each node from the database, comparing the position coordinates of the abnormal node with the node coordinates in the spatial model, finding the spatial model node close to the coordinates of the abnormal node by calculating the spatial distance between the abnormal node and each node in the spatial model, and further comparing the attribute information of the abnormal node with the attribute information of the spatial model node on the basis of coordinate matching, confirming that the spatial model node is the corresponding position of the abnormal node inside the motor, mapping the abnormal node to the corresponding component in the spatial model, and determining the component that deviates significantly from the standard operation data according to the result of the spatial mapping; S203: Based on the layout of the components in the space model and the connection relationship between them, preliminarily determine the specific location where the fault occurs.

7. A portable data acquisition and analysis device for industrial equipment fault diagnosis according to claim 6, characterized in that: The specific process of quantifying the severity of a fault is as follows: S301, obtaining the specific location where the fault occurs, marking the location where the fault occurs in the spatial model to form a fault area, and extracting actual operation data X of the fault area; S302, using polynomial regression method to establish a fault model, the formula is: Y = β0 + β1X1 + β2X2 + ... + β n X n +e; Among them, Y is the target variable, indicating the severity of the fault; X1, X2, ...X n is the independent variable, representing the fault characteristic data; β0 is the intercept term, which means that when all independent variables X1, X2, ... n When both are 0, it is the baseline value of fault severity; β1, β2, ... β n is the regression coefficient, which means that each independent variable X i The impact on the fault severity Y; e is the error term, which represents the random error that cannot be explained by the model. It is usually assumed that e follows a normal distribution with a mean of 0; S303, use historical fault data to train the model, and solve the regression coefficient by the least square method, the formula is: Among them, Y i is the actual fault severity of the i-th sample; is the predicted fault severity of the i-th sample, and its calculation formula is: By solving the minimum value of the objective function, we can get the regression coefficients β0, β1, β2, ... β n The optimal value of S304: Input the characteristic data of the current fault area into the trained fault model, calculate the value of the fault severity Y according to the fault model, and classify the fault severity into the following levels according to the calculated Y value: Mild: Y≤Y1; Medium: Y1 <Y≤Y2; Severe: Y>Y2; Among them, Y1 and Y2 are thresholds set based on historical data or domain knowledge; S305, using the historical fault data set to verify the accuracy of the fault model, if the model error is within an acceptable range, the model is considered valid and the fault model is obtained; S306 , substituting the actual operation data X of the current fault area into the fault model, calculating the value of the fault severity Y, and comparing the calculated Y value with the thresholds according to the preset fault level classification standard to obtain the quantified fault severity.

8. A portable data acquisition and analysis device for industrial equipment fault diagnosis according to claim 7, characterized in that: The specific process of generating a fault diagnosis report is as follows: S401, obtaining the fault location, obtaining the overall structure of the industrial motor and the functions of each component, analyzing the impact caused by the fault location, and dividing the impact into three categories: vibration damage, thermal damage, and electrical damage. Based on the impact classification result, combined with a comprehensive evaluation of the severity level of the quantitative fault, the vibration damage, thermal damage, and electrical damage are further divided into severity levels; S402, according to different types of faults and their severity, obtain preset weights of vibration damage, thermal damage, and electrical damage, adjust the vibration damage score, thermal damage score, and electrical damage score according to the weights, add up the scores to get a total score, and determine the maintenance priority according to the total score. The higher the score, the greater the impact of the fault on the motor operation system, and the maintenance is given priority; S403, obtaining maintenance priorities and generating a fault diagnosis report, and formulating a maintenance plan according to the maintenance priorities, including maintenance methods, required conditions, maintenance time, and maintenance personnel.

Images