CN113211426B - Robot fault diagnosis method and device, computer equipment and storage medium - Google Patents
Robot fault diagnosis method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113211426B CN113211426B CN202011387150.4A CN202011387150A CN113211426B CN 113211426 B CN113211426 B CN 113211426B CN 202011387150 A CN202011387150 A CN 202011387150A CN 113211426 B CN113211426 B CN 113211426B
- Authority
- CN
- China
- Prior art keywords
- robot
- data
- torque
- beat
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1674—Programme controls characterised by safety, monitoring, diagnostic
Abstract
The application provides a robot fault diagnosis method, a device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring beat data of a robot to be tested in a preset time period, wherein the beat data comprises position data and torque data corresponding to each robot axis of the robot to be tested; determining target beat data corresponding to each robot axis according to the position data; acquiring torque data in the target beat data as target beat torque, and acquiring a torque similarity distance according to the target beat torque; and according to the torque similarity distance, carrying out fault diagnosis on the robot to be tested, and determining a fault robot axis of the robot to be tested. By adopting the method, the stability of the robot fault diagnosis can be improved, the accuracy of the robot fault diagnosis result can be improved, and the accurate detection of the abnormality of each axis of the robot can be realized.
Description
Technical Field
The application relates to the technical field of robots, in particular to a robot fault diagnosis method and device, computer equipment and a storage medium.
Background
With the rapid development of the robot technology, more and more robots are widely applied to various fields, such as industrial robots, and due to the characteristics of easiness in use, high intelligent level, high production efficiency and safety, easiness in management, remarkable economic benefit and the like, the robots can operate in high-risk environments, so that a plurality of traditional industrial devices are replaced.
However, the aging and fault problems of the existing industrial robot are very prominent, which brings great influence to the safety production and economic benefit of enterprises, and in order to further improve various performances of the industrial robot, the conventional robot fault diagnosis method usually monitors each axis of the robot in a circular operation mode, and the basic idea is that under a healthy state, due to the fact that data of different batches under repeated operation have certain similarity. Therefore, the fault detection can be realized by comparing the monitored batch data with the normal batch data. However, this technique is very susceptible to the influence of the change of the robot operation duration, the change of the environmental temperature, etc., and the stability is poor.
Therefore, the existing robot fault diagnosis method has the technical problem that the accuracy of the diagnosis result is not high due to low stability of the diagnosis technology.
Disclosure of Invention
Therefore, it is necessary to provide a robot fault diagnosis method, a robot fault diagnosis device, a computer device, and a storage medium for improving the stability of robot fault diagnosis and further improving the accuracy of the robot fault diagnosis result, so that a fault axis of a multi-axis robot can be timely discovered and processed.
In a first aspect, the present application provides a robot fault diagnosis method, including:
acquiring beat data of a robot to be tested in a preset time period, wherein the beat data comprises position data and torque data corresponding to each robot shaft of the robot to be tested;
determining target beat data corresponding to each robot axis according to the position data;
acquiring torque data in the target beat data as target beat torque, and acquiring a torque similarity distance according to the target beat torque;
and according to the torque similarity distance, carrying out fault diagnosis on the robot to be tested, and determining a fault robot axis of the robot to be tested.
In some embodiments of the present application, the beat data further includes velocity data corresponding to each of the robot axes, and before determining, according to the position data, target beat data corresponding to each of the robot axes, the method further includes:
screening target speed data corresponding to each robot axis according to the speed data, wherein the target speed data are speed data smaller than or equal to a preset speed threshold;
removing the target speed data in the speed data to obtain effective speed data corresponding to each robot axis;
and determining position data corresponding to the effective speed data as effective position data, wherein the effective position data is used for determining target beat data corresponding to each robot axis.
In some embodiments of the present application, the step of determining target beat data corresponding to each robot axis according to the position data includes:
acquiring a rising starting point position and a falling end point position of each robot shaft according to the change trend information of the position data in the preset time period, wherein the rising starting point position and the falling end point position are determined according to the position distance between two adjacent position data;
acquiring position data between the ascending starting position and the descending end position as target position data;
determining beat data corresponding to the target position data as target beat data of the robot to be tested, wherein the target beat data at least comprises one of the following data: position data, position deviation data, speed data, and torque data.
In some embodiments of the present application, the step of obtaining torque data in the target beat data as a target beat torque and obtaining a torque similarity distance according to the target beat torque includes:
acquiring torque data in the target beat data as target beat torque;
and calculating the distance between the target beat torque and the normal beat torque based on a dynamic time warping algorithm to obtain the torque similarity distance, wherein the normal beat torque is a preset beat torque.
In some embodiments of the present application, the step of acquiring torque data in the target beat data as a target beat torque and acquiring a torque similarity distance according to the target beat torque includes:
acquiring torque data in the target beat data as target beat torque;
calculating the distance between the target beat torque and each normal beat torque based on a dynamic time warping algorithm to obtain a similarity distance, wherein the normal beat torque is a preset beat torque;
and acquiring the average value of the similarity distances as the torque similarity distance.
In some embodiments of the present application, the step of performing fault diagnosis on the robot to be tested according to the torque similarity distance and determining a faulty robot axis of the robot to be tested includes:
if the torque similarity distance is larger than or equal to a preset distance threshold, generating a fault early warning signal;
when the signal quantity of the fault early warning signals reaches a preset quantity threshold value and each fault early warning signal is a continuous fault early warning signal, generating fault alarm signals;
and determining a fault robot shaft of the robot to be tested based on the fault alarm signal.
In some embodiments of the present application, the method further comprises:
obtaining a similarity distance ratio between the torque similarity distance and the distance threshold;
if the similarity distance ratio reaches a preset ratio condition, generating a fault alarm signal;
and determining a fault robot shaft of the robot to be tested based on the fault alarm signal.
In a second aspect, the present application provides a robot fault diagnosis device, the device comprising:
the data acquisition module is used for acquiring beat data of the robot to be detected in a preset time period, wherein the beat data comprises position data and torque data corresponding to each robot axis of the robot to be detected;
the data screening module is used for determining target beat data corresponding to each robot axis according to the position data;
the distance acquisition module is used for acquiring torque data in the target beat data as target beat torque and acquiring a torque similarity distance according to the target beat torque;
and the fault diagnosis module is used for carrying out fault diagnosis on the robot to be tested according to the torque similarity distance and determining a fault robot shaft of the robot to be tested.
In a third aspect, the present application further provides a server, including:
one or more processors;
a memory; and
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the robot fault diagnosis method.
In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, where the computer program is loaded by a processor to execute the steps in the robot fault diagnosis method.
According to the robot fault diagnosis method, the device, the computer equipment and the storage medium, the beat data of the robot to be detected in the preset time period is obtained, so that the position data is extracted, the target beat data in the beat data corresponding to each robot axis is screened out by using the position data, the torque similarity distance is obtained based on the torque data in the target beat data, and finally fault diagnosis of the robot to be detected by using the torque similarity distance is realized. The torque similarity distance obtained by the method is not data obtained by depending on the action duration of the robot, and is not influenced by the ambient temperature of the robot, so that the stability of fault diagnosis of the robot is stronger, and the accuracy of the obtained result is higher.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic view of a robot fault diagnosis method in an embodiment of the present application;
FIG. 2 is a schematic flow chart of a fault diagnosis method for a robot according to an embodiment of the present application;
FIG. 3 is a schematic view of an application interface of a robot fault diagnosis method in an embodiment of the present application;
fig. 4 is a beat data diagram of the robot fault diagnosis method in the embodiment of the present application;
FIG. 5 is a schematic flowchart of a robot fault diagnosis method according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of a robot fault diagnosis device in an embodiment of the present application;
fig. 7 is a schematic structural diagram of a computer device in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In the description of the present application, it is to be understood that the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or as implying that the number of indicated technical features is indicated. Thus, features defined as "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
In the description of the present application, the word "for example" is used to mean "serving as an example, instance, or illustration". Any embodiment described herein as "for example" is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for the purpose of explanation. It will be apparent to one of ordinary skill in the art that the present invention may be practiced without these specific details. In other instances, well-known structures and processes are not shown in detail to avoid obscuring the description of the invention with unnecessary detail. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
In the embodiment of the present application, it should be noted that, because the robot fault diagnosis method provided in the present application is executed in a computer device, processing objects of each computer device all exist in the form of data or information, such as distance, which is substantially distance information, it can be understood that, in the subsequent embodiments, if the size, the number, the position, and the like are mentioned, corresponding data exist, so that the computer device can process the data, and details are not described herein.
Embodiments of the present application provide a robot fault diagnosis method and apparatus, a computer device, and a storage medium, which are described in detail below.
Referring to fig. 1, fig. 1 is a schematic view of a robot fault diagnosis method provided in the present application, where the robot fault diagnosis method may be applied to a robot fault diagnosis system. The robot fault diagnosis system includes a terminal 100, a server 200, and a multi-axis robot 300. The terminal 100 may be a device that includes both receiving and transmitting hardware, i.e., a device having receiving and transmitting hardware capable of performing two-way communication over a two-way communication link. Such a device may include: a cellular or other communication device having a single line display or a multi-line display or a cellular or other communication device without a multi-line display. The terminal 100 may specifically be a desktop terminal or a mobile terminal, and the terminal 100 may also specifically be one of a mobile phone, a tablet computer, a notebook computer, and the like. The server 200 may be an independent server, or a server network or a server cluster composed of servers, which includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets, or a cloud server composed of a plurality of servers. Among them, the Cloud server is constituted by a large number of computers or web servers based on Cloud Computing (Cloud Computing). The multi-axis robot 300 may be specifically an industrial robot having a plurality of movable axes, such as a four-axis, a six-axis, or an eight-axis robot, and in practical applications, the multi-axis robot 300 may be an LUL (loader loading, unload) industrial robot.
Those skilled in the art will understand that the application environment shown in fig. 1 is only one application scenario applicable to the present application scheme, and does not constitute a limitation on the application scenario of the present application scheme, and that other application environments may further include more or less computer devices than those shown in fig. 1, for example, only 1 server 200 is shown in fig. 1, and it is understood that the robot fault diagnosis system may further include one or more other servers, which are not limited herein. In addition, as shown in fig. 1, the robot fault diagnosis system may further include a memory 400 for storing data, such as beat data.
It should be noted that the scenario diagram of the robot fault diagnosis system shown in fig. 1 is merely an example, and the robot fault diagnosis system and the scenario described in the embodiment of the present invention are for more clearly illustrating the technical solution of the embodiment of the present invention, and do not form a limitation on the technical solution provided in the embodiment of the present invention.
As shown in fig. 2, in one embodiment, a robot fault diagnosis method is provided. The embodiment mainly illustrates that the method is applied to the server 200 in fig. 1. Referring to fig. 2, the robot fault diagnosis method specifically includes steps S201 to S204, and specifically includes the following steps:
s201, acquiring beat data of the robot to be tested in a preset time period, wherein the beat data comprises position data and torque data corresponding to each robot axis of the robot to be tested.
The robot to be tested is a robot or an industrial robot which is currently diagnosed whether a fault exists or not, the robot comprises a plurality of robot shafts, and the robot shafts are movable positions of all joints of the robot.
The preset time period refers to a time period for acquiring beat data, for example, 30 minutes, 1 hour, and the like. It is understood that the preset time period in this embodiment may be a time period accumulated by taking the current computer time as a starting time, or a time period defined by a preset starting time and a preset stopping time.
The beat data refers to servo data generated during the process that the robot uses the mechanical arm to load the substrate glass from a specific position, and the robot goes through a series of actions and finishes unloading the substrate glass from another specified position, and the servo data includes but is not limited to the torque, the speed, the position deviation and the like of each robot axis servo motor. The servo means to operate in accordance with a request of a control signal; the torque is a moment which causes a rotation effect or a torsional deformation of an object and is equal to the product of the force and the moment arm, and the torque value (torque load value and torque) referred to in the embodiment of the application is provided by detection of a Programmable Logic Controller (PLC) Controller loaded on the robot 300; the speed is the running speed of the servo motor, the position deviation is equivalent to the position error, and the speed depends on the actual position of each robot axis in the moving process and the normal position determined through a plurality of experiments.
Specifically, before the server 200 obtains beat data of the robot to be tested in the prediction time period, a worker managing the robot 300 may set related parameters through a designated application running on the terminal 100, that is, set an initial parameter that will enable the robot to be tested to complete beat actions in the preset time period, and the setting interface may refer to fig. 3. In one embodiment, the setting interface shown in fig. 3 includes settings related to a start command (start command), an end command (end command), and the like of the Robot 300 (Robot 1) in a prediction period. It can be understood that before the staff sets the parameters, the staff first needs to open the designated application loaded on the terminal 100, the interface after the designated application is opened can be presented in the interactive interface of the terminal 100, after the staff obtains and views the application interface, the staff can input the relevant parameters through the interactive interface or external devices such as a mouse, a keyboard and the like, after the parameters are submitted, the terminal 100 stores and transmits the relevant parameters to the server 200, so that the server 200 controls the robot to be tested to operate based on the parameters, and further controls the robot to be tested to complete one or more beat actions as required, and then feeds back the corresponding beat data to the server 200, that is, the beat data includes the position data and the torque data corresponding to each robot axis. The beat data obtained corresponding to the interface shown in fig. 3 is shown in fig. 4, and each row has specific meanings: date, time (e.g., 2020-07-04 22); shaft 1 torque, shaft 1 empty (for space occupying, meaningless), shaft 2 torque, shaft 2 empty \8230, shaft 8 torque, shaft 8 empty.
More specifically, the terminal 100 may or may not store the parameters submitted by the staff according to the actual application requirements, and if the parameters need to be stored, the parameters are stored as historical parameters, and the staff may query the historical parameters in real time.
And S202, determining target beat data corresponding to each robot axis according to the position data.
The Position data refers to positions of the axes of each robot at corresponding time points, and may be represented by "Position data (PosP)" in practical application, where the unit is pulse and belongs to a motor encoder unit.
Specifically, after the server 200 acquires beat data of the robot to be tested in a preset time period, position data in the beat data may be extracted. Because the position data at this time corresponds to the position data at each of the multiple time points in the preset time period, the currently obtained position data may be regarded as a sequence, and the server 200 may perform list analysis on the position sequence, or may perform drawing analysis on the position sequence, to further determine the target beat data corresponding to each robot axis, that is, to screen out the target beat data in the beat data. The target beat data determination step involved in the present embodiment will be described in detail below.
In one embodiment, the tempo data further includes velocity data corresponding to each robot axis, and before this step, the method further includes: screening target speed data corresponding to each robot axis according to the speed data, wherein the target speed data are speed data smaller than or equal to a preset speed threshold; removing the target speed data in the speed data to obtain effective speed data corresponding to each robot axis; and determining position data corresponding to the effective speed data as effective position data, wherein the effective position data is used for determining target beat data corresponding to each robot axis.
The speed data is the operating speed of each robot axis servomotor, and may be expressed by "Velocity (VelP)" in practical application, where the unit is pulse/sec, and belongs to a motor encoder unit, for example, 3,5, 7, and the like.
The preset speed threshold is a critical value of a high-low speed boundary set according to an actual service requirement, for example, 3,5, 7, and the like.
Specifically, after the server 200 acquires the beat data of the robot to be tested, the beat data needs to be analyzed so as to screen out target beat data that can be used for subsequent analysis, but before the screening, the beat data needs to be preprocessed, that is, the target speed data in the beat data and other beat data corresponding to the target speed are cleaned, that is, low-rotation-speed data such as waiting for taking a film are removed according to the speed data to acquire effective speed data, and then effective position data corresponding to the effective speed data is acquired. Therefore, the determining of the target beat data corresponding to each robot axis according to the position data in the above embodiments may actually be determining the target beat data corresponding to each robot axis according to the valid position data. By adopting the data preprocessing method provided by the embodiment to preprocess the beat data, the effectiveness of the beat data can be higher, and the accuracy of the fault diagnosis result of the robot is further influenced to be higher.
In one embodiment, this step includes: acquiring a rising starting point position and a falling end point position of each robot shaft according to the change trend information of the position data in the preset time period, wherein the rising starting point position and the falling end point position are determined according to the position distance between two adjacent position data; acquiring position data between the ascending starting position and the descending end position as target position data; determining beat data corresponding to the target position data as target beat data of the robot to be tested, wherein the target beat data at least comprises one of the following data: position data, position deviation data, speed data, and torque data.
The change trend information may be change trend information presented on the basis of a mapping table of the position data, that is, a graph expressed in a planar rectangular coordinate system, where an X-axis of the planar rectangular coordinate system is time in a preset time period, and a Y-axis of the planar rectangular coordinate system is position data in the preset time period.
Since the graph drawn according to the position data at least includes one peak, and one peak usually represents one beat, the rising start point position and the falling end point position mentioned in the above steps are the rising start point position and the falling end point position of the peak, and after determining the two positions, the coordinates (x, y) corresponding to each position can be obtained.
Specifically, after the server 200 acquires the beat data of the robot to be tested, the position data in the beat data may be extracted so as to acquire change trend information presented by using a graph drawn by the position data, and further, the position distance between two adjacent position data in the change trend information is analyzed, that is, the difference between the Y-axis positions of the two adjacent position data is calculated, if the difference reaches a preset distance threshold, it may be determined that the first position data meeting the threshold condition is a rising start position, and the last position data meeting the threshold condition is a falling end position.
For example, the trend information includes 6 coordinate points, each corresponding to one piece of position data, including: (0, 0), (1, 0), (2, 1), (3, 5), (4, 1), (5, 0), the 6 coordinate points can be located in one peak by analysis, the rising start point position should be (1, 0) and the falling end point position should be (5, 0).
More specifically, as will be understood from the explanation of the above example, after the server 200 analyzes the position data and determines the rising start point position and the falling end point position therein, it is possible to acquire each position data between the rising start point position and the falling end point position as the target position data, i.e., the position data represented by the above coordinate points (2, 1), (3, 5), (4, 1). Meanwhile, target beat data, that is, beat data corresponding to the x-axis time point in each target position data, needs to be determined based on the target position data.
And S203, acquiring torque data in the target beat data as target beat torque, and acquiring a torque similarity distance according to the target beat torque.
The torque similarity distance is a concept related to application of a Dynamic Time Warping (DTW) method, and specifically, for a distance between two torques, a smaller distance represents a higher similarity between the two torques.
Specifically, the torque similarity distance obtaining step related in this embodiment needs to be actually obtained based on DTW algorithm analysis, and the DWT algorithm is a method for measuring similarity between two discrete time sequences, and is mainly characterized in that under the condition that the sequence lengths are different or the x-axis cannot be completely aligned, a time warping function meeting a certain condition is used to describe a time correspondence relationship between the two discrete time sequences, and the time correspondence relationship is not affected by beat action time of the robot.
More specifically, the torque similarity distance is obtained based on the DWT algorithm by analyzing the target beat torque as a discrete time series (the time series is a common representation form of data in the field of digital signal processing) simultaneously with another discrete time series, and measuring the similarity between the two time series by using the sum of the distances between all similar points to obtain the torque similarity distance.
For example, (1) assume that two discrete data to be matched are a = { a (1), a (2), \8230;, a (m) } and B = { B (1), B (2), \8230;, B (n) }, where the element with subscript 1 is the start of the sequence and the elements with subscripts m, n are the end of the a sequence, B sequence, respectively; (2) In order to align the two sequences A and B, a method of "dynamic programming" is adopted, firstly, an m x n matrix is constructed for storing the distance between the point to point of the two sequences (generally, the Euclidean distance can be used), and the smaller the distance, the higher the similarity between the two points is; (3) The part is the core of the DTW algorithm, the matrix is regarded as a grid, the purpose of the algorithm can be summarized as finding an optimal path passing through the grid of the matrix, and the grid point passing through the path is a point pair formed by aligning two discrete sequences; (4) After finding the optimal Path, the DTW algorithm defines a normalized Path Distance (Warp Path Distance), and measures the similarity between two time series by using the sum of distances between all similar points. Finally, an accumulation distance dist is defined, namely, the distances calculated by all the previous points are accumulated when the two sequences A and B are matched from the point (0, 0), every time one point is reached, after the end point (n, m) is reached, the accumulation distance describes the overall similarity degree of the sequences A and B, the A or B is set as the target beat torque, and the similarity distance between the target beat torque and the other beat torque is analyzed, so that the torque similarity distance can be obtained. The torque similarity distance acquisition step involved in the present embodiment will be described in detail below.
In one embodiment, this step comprises: acquiring torque data in the target beat data as target beat torque; and calculating the distance between the target beat torque and the normal beat torque based on a dynamic time warping algorithm to obtain the torque similarity distance, wherein the normal beat torque is a preset beat torque.
The normal beat torque is the beat torque of each selected robot shaft in a normal state after the robot to be tested is repeatedly tested.
Specifically, based on the above description of the embodiments, it can be known that the torque similarity distance needs to be obtained by means of a dynamic time rule algorithm. Therefore, the server 200 may use the target beat torque and the normal beat torque as two discrete time sequences, and solve the overall similarity based on the DTW algorithm, so as to obtain the torque similarity distance.
In one embodiment, this step includes: acquiring torque data in the target beat data as target beat torque; calculating the distance between the target beat torque and each normal beat torque based on a dynamic time warping algorithm to obtain a similarity distance, wherein the normal beat torque is a preset beat torque; and acquiring the average value of the similarity distances as the torque similarity distance.
Specifically, what is different from the previous embodiment in this embodiment is that: calculating the current beat torque tor [ i]With several normal beat torques tor [1]、tor[2]、……tor[n]Mean value W of the similarity distance of i ＝(W i1 +W i2 +……+W in ) And/n, while the previous embodiment described: calculating the torque of the current beat tor [ i [ ]]With a normal beat torque tor [0 ]](e.g., a tempo produced by an industrial robot under normal operation [0 ]]) Similarity distance W of i0 . The character "i" indicates a beat, normal beat torques respectively corresponding to the robot axes of the robot to be tested exist, and when the server 200 performs fault diagnosis on the robot to be tested, the torque similarity distance corresponding to each robot axis can be respectively calculated so as to judge whether the robot axis is in a beat state or notThere is a fault anomaly. It can be understood that, by using the torque similarity distance obtaining method in the present embodiment, compared with the torque similarity distance obtaining method described in the previous embodiment, the robustness of the calculation result is better, and the influence on random interference is small, so that the accuracy of the robot fault diagnosis result can be further improved.
And S204, performing fault diagnosis on the robot to be tested according to the torque similarity distance, and determining a fault robot axis of the robot to be tested.
Specifically, a threshold value is required to be preset for fault diagnosis of the robot to be tested according to the torque similarity distance, and whether the current torque similarity distance is out of range is judged by using the threshold value, so that fault diagnosis of the robot to be tested can be realized, and a robot axis corresponding to the torque similarity distance exceeding the threshold value is judged as a fault robot axis. In practical applications, after determining that the axis of the robot is faulty, the server 200 may generate a warning signal, where the warning signal may trigger a warning light associated in advance to light up, or trigger a warning player associated in advance to sound, so as to prompt a worker to process the faulty axis of the robot in time, and ensure the working safety of the robot to be tested. The faulty robot axis determination step involved in the present embodiment will be described in detail below.
In one embodiment, this step includes: if the torque similarity distance is larger than or equal to a preset distance threshold, generating a fault early warning signal; generating fault alarm signals when the signal quantity of the fault early warning signals reaches a preset quantity threshold value and each fault early warning signal is a continuous fault early warning signal; and determining a fault robot shaft of the robot to be tested based on the fault alarm signal.
The distance threshold value is a fault judgment critical value obtained by statistical analysis of historical fault information of the robot, and if the torque similarity distance exceeds the threshold value, the robot shaft corresponding to the robot to be tested can be judged to have a fault, and the robot shaft can be determined to be a fault robot shaft.
Wherein the quantity threshold is a critical value between pre-alarm and alarm, which is set based on actual service requirements.
Specifically, after the server 200 analyzes and obtains the torque similarity distance of each robot axis, it may further determine a preset distance threshold corresponding to each robot axis, compare the distance threshold with the torque similarity distance, and if the torque similarity distance is greater than or equal to the distance threshold, generate a fault warning signal corresponding to the robot axis. In addition, if the torque similarity distance of the same robot axis continuously exceeds (or matches) the distance threshold value to reach a preset number threshold value, for example, the torque similarity distance exceeds (or matches) the distance threshold value continuously three times, a fault alarm signal of the robot axis can be generated. It is understood that both the fault warning signal and the fault warning signal can be generated and then sent to the terminal 100 by the server 200, and the signal at this time can be prompted by a specific application loaded on the terminal 100, for example, a pop-up window prompt lamp; or may be displayed on the staff member by the terminal 100 via an external device, such as an indicator light, a player, etc.
More specifically, since the present application proposes that there are two signals, namely, a fault alarm signal and a fault pre-warning signal, when both of the two signals need to be displayed on the display screen by the indicator light or the player, the signals can be preset to be distinguished in different forms, for example, a yellow indicator light is turned on to represent the fault pre-warning signal, and a red indicator light is turned on to represent the fault alarm signal; for another example, sound a is an alarm signal indicating a fault, and sound B is an alarm signal indicating a fault.
In one embodiment, this step comprises: obtaining a similarity distance ratio between the torque similarity distance and the distance threshold; if the similarity distance ratio reaches a preset ratio condition, generating a fault alarm signal; and determining a fault robot shaft of the robot to be tested based on the fault alarm signal.
Wherein, the ratio condition refers to the ratio of the torque similarity distance to the similarity distance between the distance thresholds, and reaches a preset multiple value, for example, 1.2, 1.6, etc.
Specifically, the previous embodiment has described the generation mechanism of the fault warning signal and the fault warning signal in detail, but in this embodiment, a generation mechanism of the fault warning signal is additionally provided, which is different from the previous embodiment in that the fault warning signal in this embodiment does not need to be compared with the quantity threshold, but when the torque similarity distance exceeds (or matches) the distance threshold for the first time, the similarity distance ratio between the torque similarity distance and the distance threshold is calculated, and if the torque similarity distance is a preset multiple of the distance threshold, the fault warning signal can be directly generated, so as to determine that the robot axis corresponding to the fault warning signal is the faulty robot axis.
For example, if the current resulting torque similarity distance of server 200 is 1.2 times the distance threshold, server 200 may generate a fault alarm signal.
According to the robot fault diagnosis method, the position data in the beat data are extracted by obtaining the beat data of the robot to be detected in the preset time period, so that the target beat data in the beat data corresponding to each robot axis is screened out by using the position data, the torque similarity distance is obtained based on the torque data in the target beat data, and finally fault diagnosis of the robot to be detected by using the torque similarity distance is realized. The torque similarity distance obtained by the method is not data obtained by depending on the action time of the robot and is not influenced by the ambient temperature of the robot, so that the stability of fault diagnosis of the robot is higher, and the accuracy of the obtained result is higher.
In order to enable those skilled in the art to fully understand the robot fault diagnosis scheme provided by the present application, the present application further provides an application scenario applying the robot fault diagnosis method described above. Specifically, the application of the robot fault diagnosis method in the application scenario will be described as follows with reference to fig. 5:
as shown in fig. 5, a complete embodiment provided by the present application mainly includes four steps: (1) The data preprocessing of the beat data, namely screening out the low-speed data and the corresponding beat data; (2) Motion segmentation of the beat data, namely determining target beat data corresponding to each robot axis according to the position data; (3) Calculating the torque similarity distance of the beat data, namely acquiring the torque similarity distance according to the target beat torque; (4) And (4) fault diagnosis, namely performing fault diagnosis on the robot to be tested according to the torque similarity distance, and determining a fault robot axis of the robot to be tested.
In this embodiment, position data in the beat data is extracted by obtaining the beat data of the robot to be detected in a preset time period, so that target beat data in the beat data corresponding to each robot axis is screened out by using the position data, and a torque similarity distance is obtained based on torque data in the target beat data, thereby finally realizing fault diagnosis of the robot to be detected by using the torque similarity distance. The torque similarity distance obtained by the method is not data obtained by depending on the action time of the robot and is not influenced by the ambient temperature of the robot, so that the stability of fault diagnosis of the robot is higher, and the accuracy of the obtained result is higher.
In order to better implement the robot fault diagnosis method in the embodiment of the present application, based on the robot fault diagnosis method, the embodiment of the present application further provides a robot fault diagnosis apparatus, as shown in fig. 6, where the robot fault diagnosis apparatus 600 includes:
the data acquisition module 610 is configured to acquire beat data of a robot to be tested in a preset time period, where the beat data includes position data and torque data corresponding to each robot axis of the robot to be tested;
a data filtering module 620, configured to determine, according to the position data, target beat data corresponding to each robot axis;
a distance obtaining module 630, configured to obtain torque data in the target beat data as a target beat torque, and obtain a torque similarity distance according to the target beat torque;
and the fault diagnosis module 640 is configured to perform fault diagnosis on the robot to be tested according to the torque similarity distance, and determine a fault robot axis of the robot to be tested.
In some embodiments of the present application, the beat data further includes speed data corresponding to each robot axis, and the robot fault diagnosis device 600 further includes a data preprocessing module, configured to screen out target speed data corresponding to each robot axis according to the speed data, where the target speed data is speed data smaller than or equal to a preset speed threshold; removing the target speed data in the speed data to obtain effective speed data corresponding to each robot axis; and determining position data corresponding to the effective speed data as effective position data, wherein the effective position data is used for determining target beat data corresponding to each robot axis.
In some embodiments of the present application, the data filtering module 620 is further configured to obtain a rising start position and a falling end position of each robot axis according to variation trend information of the position data in the preset time period, where the rising start position and the falling end position are determined according to a position distance between two adjacent position data; acquiring position data between the ascending starting position and the descending end position as target position data; determining beat data corresponding to the target position data as target beat data of the robot to be tested, wherein the target beat data at least comprises one of the following data: position data, position deviation data, speed data, and torque data.
In some embodiments of the present application, the distance obtaining module 630 is further configured to obtain torque data in the target beat data as a target beat torque; and calculating the distance between the target beat torque and a normal beat torque based on a dynamic time warping algorithm to obtain the torque similarity distance, wherein the normal beat torque is a preset beat torque.
In some embodiments of the present application, the distance obtaining module 630 is further configured to obtain torque data in the target beat data as a target beat torque; calculating the distance between the target beat torque and each normal beat torque based on a dynamic time warping algorithm to obtain a similarity distance, wherein the normal beat torque is a preset beat torque; and acquiring the average value of the similarity distances as the torque similarity distance.
In some embodiments of the present application, the fault diagnosis module 640 is further configured to generate a fault warning signal if the torque similarity distance is greater than or equal to a preset distance threshold; when the signal quantity of the fault early warning signals reaches a preset quantity threshold value and each fault early warning signal is a continuous fault early warning signal, generating fault alarm signals; and determining a fault robot shaft of the robot to be tested based on the fault alarm signal.
In some embodiments of the present application, the fault diagnosis module 640 is further configured to obtain a similarity distance ratio between the torque similarity distance and the distance threshold; if the similarity distance ratio reaches a preset ratio condition, generating a fault alarm signal; and determining a fault robot shaft of the robot to be tested based on the fault alarm signal.
In the above embodiment, the position data in the beat data is extracted by obtaining the beat data of the robot to be detected in the preset time period, so that the position data is used to screen out the target beat data in the beat data corresponding to each robot axis, and the torque similarity distance is obtained based on the torque data in the target beat data, thereby finally realizing the fault diagnosis of the robot to be detected by using the torque similarity distance. Because the torque similarity distance is not data obtained by depending on the action time of the robot and is not influenced by the ambient temperature of the robot, the stability of the fault diagnosis of the robot is stronger, and the accuracy of the obtained result is higher.
In some embodiments of the present application, the robot fault diagnosis apparatus 600 may be implemented in the form of a computer program that is executable on a computer device such as the one shown in fig. 7. The memory of the computer device may store various program modules constituting the robot fault diagnosis apparatus 600, such as a data acquisition module 610, a data filtering module 620, a distance acquisition module 630, and a fault diagnosis module 640 shown in fig. 6. The computer program constituted by the respective program modules causes the processor to execute the steps in the robot failure diagnosis method of the respective embodiments of the present application described in the present specification.
For example, the computer device shown in fig. 7 may execute step S201 by the data acquisition module 610 in the robot malfunction diagnosis apparatus 600 shown in fig. 6. The computer device may perform step S202 through the data filtering module 620. The computer device may perform step S203 through the distance acquisition module 630. The computer device may perform step S204 through the fault diagnosis module 640. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The network interface of the computer device is used for communicating with an external computer device through a network connection. The computer program is executed by a processor to implement a robot fault diagnosis method.
It will be appreciated by those skilled in the art that the configuration shown in fig. 7 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In some embodiments of the present application, there is provided a computer device comprising one or more processors; a memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to perform the steps of the robot fault diagnosis method described above. Here, the steps of the robot fault diagnosis method may be the steps of the robot fault diagnosis method of each of the above embodiments.
In some embodiments of the present application, a computer-readable storage medium is provided, which stores a computer program, which is loaded by a processor, so that the processor executes the steps of the robot fault diagnosis method described above. Here, the steps of the robot fault diagnosis method may be the steps of the robot fault diagnosis method of each of the above embodiments.
The robot fault diagnosis method, the robot fault diagnosis device, the computer equipment and the storage medium provided by the embodiments of the present application are described in detail above, and a specific example is applied in the present application to explain the principle and the implementation of the present invention, and the description of the embodiments above is only used to help understanding the method and the core idea of the present invention; meanwhile, for those skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed, and in summary, the content of the present specification should not be construed as limiting the present invention.
Claims (8)
1. A method of diagnosing a fault in a robot, the method comprising:
acquiring beat data of a robot to be tested in a preset time period, wherein the beat data refers to servo data generated when the robot to be tested uses a mechanical arm, the servo data comprises speed data, position data and torque data of a servo motor of each robot shaft of the robot to be tested, and the speed data is the running speed of the servo motor;
screening target speed data corresponding to each robot axis according to the speed data, wherein the target speed data are speed data smaller than or equal to a preset speed threshold value, and the preset speed threshold value is a critical value of a high-speed and low-speed boundary;
eliminating the target speed data in the speed data to remove the low-rotation-speed data of each robot shaft so as to obtain effective speed data corresponding to each robot shaft;
determining position data corresponding to the effective speed data as effective position data, wherein the effective position data is used for determining target beat data corresponding to each robot axis;
acquiring a rising starting point position and a falling end point position of each robot shaft according to the change trend information of the effective position data in the preset time period, wherein the rising starting point position and the falling end point position are determined according to the position distance between two adjacent position data;
acquiring effective position data between the ascending starting position and the descending end position as target position data;
determining beat data corresponding to the target position data, wherein the beat data is used as target beat data corresponding to each robot axis of the robot to be tested;
acquiring torque data in the target beat data as a target beat torque, and acquiring a torque similarity distance according to the target beat torque and a normal beat torque based on a dynamic time warping algorithm when the length of a discrete time sequence of the target beat torque is not consistent with the length of a discrete time sequence of the normal beat torque, wherein the normal beat torque is a preset beat torque, and the length of the discrete time sequence of the target beat torque corresponds to the beat action duration of the target beat torque;
and according to the torque similarity distance, carrying out fault diagnosis on the robot to be tested, and determining a fault robot axis of the robot to be tested.
2. The robot fault diagnosis method according to claim 1, wherein the step of obtaining a torque similarity distance from the target beat torque and the normal beat torque based on a dynamic time warping algorithm comprises:
and calculating the distance between the target beat torque and the normal beat torque based on a dynamic time warping algorithm to obtain the torque similarity distance.
3. The robot fault diagnosis method according to claim 1, wherein the step of obtaining a torque similarity distance from the target beat torque and the normal beat torque based on a dynamic time warping algorithm comprises:
calculating the distance between the target beat torque and each normal beat torque based on a dynamic time warping algorithm to obtain a similarity distance;
and acquiring the average value of the similarity distances as the torque similarity distance.
4. The robot fault diagnosis method according to claim 1, wherein the step of performing fault diagnosis on the robot under test and determining a faulty robot axis of the robot under test based on the torque similarity distance includes:
if the torque similarity distance is larger than or equal to a preset distance threshold, generating a fault early warning signal;
generating fault alarm signals when the signal quantity of the fault early warning signals reaches a preset quantity threshold value and each fault early warning signal is a continuous fault early warning signal;
and determining a fault robot shaft of the robot to be tested based on the fault alarm signal.
5. The robot fault diagnosis method according to claim 4, characterized in that the method further comprises:
obtaining a similarity distance ratio between the torque similarity distance and the distance threshold;
if the similarity distance ratio reaches a preset ratio condition, generating a fault alarm signal;
and determining a fault robot shaft of the robot to be tested based on the fault alarm signal.
6. A robot malfunction diagnosis apparatus, characterized in that the apparatus comprises:
the data acquisition module is used for acquiring beat data of the robot to be tested in a preset time period, wherein the beat data refers to servo data generated when the robot to be tested uses a mechanical arm, the servo data comprises speed data, position data and torque data of a servo motor of each robot shaft of the robot to be tested, and the speed data is the running speed of the servo motor;
the data screening module is used for screening target speed data corresponding to each robot axis according to the speed data, wherein the target speed data is speed data smaller than or equal to a preset speed threshold value, and the preset speed threshold value is a critical value of a high-speed and low-speed boundary; eliminating the target speed data in the speed data to remove the low-rotation-speed data of each robot shaft so as to obtain effective speed data corresponding to each robot shaft; determining position data corresponding to the effective speed data as effective position data, wherein the effective position data is used for determining target beat data corresponding to each robot axis; acquiring a rising starting point position and a falling end point position of each robot axis according to the change trend information of the effective position data in the preset time period, wherein the rising starting point position and the falling end point position are determined according to the position distance between two adjacent position data; acquiring effective position data between the ascending starting position and the descending end position as target position data; determining beat data corresponding to the target position data as target beat data corresponding to each robot axis of the robot to be tested;
a distance obtaining module, configured to obtain torque data in the target beat data as a target beat torque, and obtain a torque similarity distance according to the target beat torque and a normal beat torque based on a dynamic time warping algorithm when a length of a discrete time sequence of the target beat torque is not consistent with a length of a discrete time sequence of the normal beat torque, where the normal beat torque is a preset beat torque, and the length of the discrete time sequence of the target beat torque corresponds to a beat action duration of the target beat torque;
and the fault diagnosis module is used for carrying out fault diagnosis on the robot to be tested according to the torque similarity distance and determining a fault robot shaft of the robot to be tested.
7. A computer device, characterized in that the computer device comprises:
one or more processors;
a memory; and
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the robot fault diagnosis method of any of claims 1 to 5.
8. A computer-readable storage medium, having stored thereon a computer program which is loaded by a processor to perform the steps in the robot fault diagnosis method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011387150.4A CN113211426B (en) | 2020-12-02 | 2020-12-02 | Robot fault diagnosis method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011387150.4A CN113211426B (en) | 2020-12-02 | 2020-12-02 | Robot fault diagnosis method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113211426A CN113211426A (en) | 2021-08-06 |
| CN113211426B true CN113211426B (en) | 2023-02-28 |
Family
ID=77085833
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011387150.4A Active CN113211426B (en) | 2020-12-02 | 2020-12-02 | Robot fault diagnosis method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113211426B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114323718B (en) * | 2021-12-14 | 2023-12-15 | 合肥欣奕华智能机器股份有限公司 | Robot fault prediction method and device |
| CN114418042B (en) * | 2021-12-30 | 2022-07-22 | 智昌科技集团股份有限公司 | Industrial robot operation trend diagnosis method based on cluster analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104697799A (en) * | 2015-03-10 | 2015-06-10 | 无锡惠科电工高新技术有限公司 | Automatic load increase testing system and testing method for engine |
| CN105247430A (en) * | 2013-05-29 | 2016-01-13 | 日本电产三协株式会社 | Data processing device and data processing method |
| CN105892405A (en) * | 2015-02-17 | 2016-08-24 | 日本电产三协株式会社 | Action record management system, management device and action record management method |
| CN106020116A (en) * | 2015-03-24 | 2016-10-12 | 发那科株式会社 | Robot controller capable of performing fault diagnosis of robot |
| JP2020071624A (en) * | 2018-10-30 | 2020-05-07 | 国立研究開発法人宇宙航空研究開発機構 | Abnormality diagnosing apparatus, abnormality diagnosing method and program |
| CN111489517A (en) * | 2019-01-25 | 2020-08-04 | 富士康精密电子（太原）有限公司 | Screw locking abnormity warning method and device, computer device and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11789437B2 (en) * | 2018-07-24 | 2023-10-17 | Canon Kabushiki Kaisha | Processing apparatus and processing method for processing portion |
-
2020
- 2020-12-02 CN CN202011387150.4A patent/CN113211426B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105247430A (en) * | 2013-05-29 | 2016-01-13 | 日本电产三协株式会社 | Data processing device and data processing method |
| CN105892405A (en) * | 2015-02-17 | 2016-08-24 | 日本电产三协株式会社 | Action record management system, management device and action record management method |
| CN104697799A (en) * | 2015-03-10 | 2015-06-10 | 无锡惠科电工高新技术有限公司 | Automatic load increase testing system and testing method for engine |
| CN106020116A (en) * | 2015-03-24 | 2016-10-12 | 发那科株式会社 | Robot controller capable of performing fault diagnosis of robot |
| JP2020071624A (en) * | 2018-10-30 | 2020-05-07 | 国立研究開発法人宇宙航空研究開発機構 | Abnormality diagnosing apparatus, abnormality diagnosing method and program |
| CN111489517A (en) * | 2019-01-25 | 2020-08-04 | 富士康精密电子（太原）有限公司 | Screw locking abnormity warning method and device, computer device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113211426A (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113211426B (en) | Robot fault diagnosis method and device, computer equipment and storage medium | |
| US10585774B2 (en) | Detection of misbehaving components for large scale distributed systems | |
| US10223403B2 (en) | Anomaly detection system and method | |
| CN107253196B (en) | Mechanical arm collision detection method, device, equipment and storage medium | |
| EP2911025B1 (en) | Initiated test health management system and method | |
| US7313502B2 (en) | System and method to combine and weight multiple sensors with overlapping sensing range to create a measurement system utilized in a high integrity or safety environment | |
| US10503146B2 (en) | Control system, control device, and control method | |
| CN111459700A (en) | Method and apparatus for diagnosing device failure, diagnostic device, and storage medium | |
| US20070021890A1 (en) | Malfunction condition judgment apparatus, control method, automobile and program method | |
| CN104518924A (en) | Automatic testing and result comparison method and system | |
| US20200184373A1 (en) | Recurrent Gaussian Mixture Model For Sensor State Estimation In Condition Monitoring | |
| JP2019144931A (en) | Abnormality monitoring apparatus, abnormality monitoring method, and abnormality monitoring program | |
| CN114800486B (en) | Industrial robot fault diagnosis method and system based on statistical characteristics | |
| WO2020152741A1 (en) | Abnormality cause estimation device, abnormality cause estimation method, and program | |
| CN115437339A (en) | Remote diagnosis method and device, electronic equipment and storage medium | |
| CN110806730A (en) | Big data operation and maintenance platform, server and storage medium | |
| CN115769235A (en) | Method and system for providing an alert related to the accuracy of a training function | |
| CN109990803B (en) | Method and device for detecting system abnormity and method and device for sensor processing | |
| CN111027679A (en) | Abnormal data detection method and system | |
| CN115375039A (en) | Industrial equipment fault prediction method and device, electronic equipment and storage medium | |
| US11353860B2 (en) | Data analysis device, system, method, and recording medium storing program | |
| JP2019145079A (en) | Abnormality monitoring apparatus, abnormality monitoring method, and abnormality monitoring program | |
| CN113177077B (en) | Abnormal event determination method and device for automatic driving and electronic equipment | |
| Lyu et al. | A Novel Fault Diagnosis Method Based on Feature Fusion and Model Agnostic Meta-Learning | |
| CN115438452B (en) | Reliable transmission detection method for time sequence network signals |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |