CN113211424B

CN113211424B - Fault detection and alarm method, device, server and storage medium

Info

Publication number: CN113211424B
Application number: CN202011446650.0A
Authority: CN
Inventors: 彭丰斌; 何军; 佘迎松; 王军; 傅益龙; 温昕; 贺政; 许跃修; 蒋沅均
Original assignee: Gechuang Dongzhi Shenzhen Technology Co ltd
Current assignee: Gechuang Dongzhi Shenzhen Technology Co ltd
Priority date: 2020-12-11
Filing date: 2020-12-11
Publication date: 2022-07-22
Anticipated expiration: 2040-12-11
Also published as: CN113211424A

Abstract

The application provides a fault detection warning method, a fault detection warning device, a server and a storage medium, which are applied to an industrial robot comprising a plurality of joint axes, and comprise the following steps: acquiring beat data corresponding to each joint axis in a beat; calculating a torque load effective value corresponding to each joint shaft in the plurality of joint shafts according to the beat data; judging whether the torque load effective value corresponding to each joint shaft reaches a preset alarm condition or not; and if the preset alarm condition is reached, generating an alarm corresponding to the torque load effective value. The method comprises the steps of obtaining beat data corresponding to each joint shaft in a beat, calculating a torque load effective value corresponding to each joint shaft by utilizing the beat data, and determining whether the joint shafts work normally or not by judging whether the torque load effective value exceeds a threshold value or not. Noise in beat data is removed, and stability of detection of each joint axis is improved.

Description

Fault detection and alarm method, device, server and storage medium

Technical Field

The application relates to the technical field of machinery, in particular to a fault detection and alarm method, a fault detection and alarm device, a server and a storage medium.

Background

With the rapid development of science and technology, industrial robots are widely used in modern factories. With the great increase of the demand of industrial robots, technologies of maintenance, fault detection, alarm and prediction and the like of industrial robots are becoming more and more important.

The fault detection and alarm of the industrial robot based on the torque load signal has the advantage of non-invasiveness, and the torque value can be obtained by reading a Programmable Logic Controller (PLC) Controller of the robot. Aiming at the problem of abrasion of each joint shaft of the robot, the joint shafts of the robot are monitored by a method of operating in a circulating mode in the prior art, and the basic idea is that under a healthy state, data of different batches (beats) under repeated operation have similarity. Therefore, the anomaly detection can be realized by comparing the monitoring data with the standard batch data. However, the existing method and technology are easily affected by robot load, beat action duration, environmental temperature change and the like, so that stability needs to be improved.

Disclosure of Invention

The application provides a fault detection and alarm method, and aims to solve the problems that fault detection in the prior art is excessively interfered by the outside, and is not high in stability and accuracy.

In one aspect, the present application provides a fault detection warning method applied to an industrial robot including a plurality of joint axes, the method including:

acquiring beat data corresponding to each joint axis in a beat;

calculating to obtain a torque load effective value corresponding to each joint shaft in the plurality of joint shafts according to the beat data;

judging whether the torque load effective value reaches a preset alarm condition or not;

and if the preset alarm condition is reached, generating an alarm corresponding to the torque load effective value.

Further, the acquiring beat data corresponding to each joint axis in the plurality of joint axes in a beat includes:

acquiring initial beat data;

determining the starting and ending time of a beat according to the initial beat data;

and determining beat data in different beats respectively corresponding to each joint axis in the initial beat data according to the start-stop time.

Further, the tempo data includes respective corresponding velocity data of each of the plurality of joint axes in one tempo;

the calculating to obtain the effective value of the torque load of each joint shaft in the plurality of joint shafts according to the beat data comprises the following steps:

according to the speed data, determining single beat data corresponding to each joint axis in the plurality of joint axes in the beat data;

and calculating to obtain the torque load effective value corresponding to each joint shaft in the plurality of joint shafts according to the single beat data.

Further, the calculating, according to the single beat data, a torque load effective value corresponding to each of the plurality of joint axes includes:

taking any joint axis in the plurality of joint axes as a target joint axis;

determining target single beat data corresponding to the target joint axis;

calculating an absolute mean value and a standard deviation of the target single beat data;

and determining the effective value of the torque load corresponding to the target joint axis according to the absolute mean value and the standard deviation of the target single beat data.

Further, after calculating the effective torque loading values corresponding to the plurality of joint axes according to the beat data, the method further includes:

acquiring first historical beat data corresponding to each joint shaft in the plurality of joint shafts in a first preset time period;

and respectively determining torque load early warning threshold values corresponding to the joint shafts in the joint shafts according to the first historical beat data corresponding to the joint shafts in the joint shafts.

Further, the method further comprises:

acquiring second historical beat data corresponding to each joint shaft in the plurality of joint shafts in a second preset time period;

determining a plurality of beat windows in the second historical beat data according to a preset number of corresponding beat data of each beat window;

determining a plurality of linear regression models corresponding to the plurality of beat windows;

determining a predicted value of the torque load bearing an effective value in a next beat window based on the plurality of linear regression models.

Further, the determining a plurality of linear regression models corresponding to the plurality of beat windows includes:

respectively taking a beat window as a target beat window, and determining beat data in different beats respectively corresponding to each joint axis in the target beat window;

and calculating to obtain a linear regression model in the target beat window according to the beat data in different beats corresponding to each joint shaft.

Further, the determining whether the torque load effective value reaches a preset alarm condition includes:

judging whether the torque load effective value corresponding to each joint shaft exceeds an early warning threshold value or not;

and if the torque load effective value exceeds the early warning threshold, judging whether the torque load effective value reaches a preset warning condition.

In another aspect, the present application provides a fault detection warning device, the device including:

the acquisition module is used for acquiring beat data corresponding to each joint shaft in the plurality of joint shafts in a beat;

the calculation module is used for calculating to obtain a torque load effective value corresponding to each joint shaft in the plurality of joint shafts according to the beat data;

the judging module is used for judging whether the torque load effective value reaches a preset alarm condition or not;

and the warning module is used for generating a warning corresponding to the torque load effective value if the preset warning condition is met.

In another 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 fault detection alarm method as described in any one of the above.

In another aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, the computer program being loaded by a processor to perform the steps in the fault detection alarm method according to any one of the above.

The application provides a fault detection alarm method, which comprises the steps of obtaining beat data corresponding to each joint shaft in a beat, calculating to obtain a torque load effective value corresponding to each joint shaft by utilizing the beat data, and determining whether the joint shaft normally works or not by judging whether the torque load effective value exceeds a threshold value or not. The method and the device have the advantages that the effective value of the torque load is calculated, noise in the beat data is removed, influences such as robot load, beat action time length and environment temperature change are avoided, and stability of detection of all joint axes is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.

Fig. 1 is a schematic view of a scenario of a fault detection alarm system according to an embodiment of the present application;

fig. 2 is a schematic flowchart of an embodiment of a fault detection and alarm method provided in the embodiment of the present application;

fig. 3 is a schematic flowchart of an embodiment of obtaining beat data according to the present application;

fig. 4 is a schematic diagram of beat data provided in an embodiment of the present application;

FIG. 5 is a schematic flow chart illustrating an embodiment of calculating a torque loading root mean square value according to an embodiment of the present application;

FIG. 6 is a schematic flow chart illustrating another embodiment of calculating a torque loading root mean value according to an embodiment of the present application;

FIG. 7 is a flowchart illustrating an embodiment of obtaining a predicted value of a torque load holding effective value according to the present disclosure;

fig. 8 is a schematic flowchart of an embodiment of predicting a fault condition according to the present application;

fig. 9 is a schematic diagram of an embodiment of a fault detection apparatus provided in the present application;

fig. 10 shows a schematic structural diagram of a server according to 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 invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.

In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate orientations or positional relationships based on those shown in the drawings, merely for convenience of description and simplicity of description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention. Furthermore, 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 to implicitly indicate the number of technical features indicated. Thus, features defined as "first", "second", may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.

In this application, the word "exemplary" is used to mean "serving as an example, instance, or illustration. Any embodiment described herein as "exemplary" 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.

The embodiments of the present application provide a fault detection alarm method, device, server and storage medium, which are described in detail below.

As shown in fig. 1, a schematic view of a fault detection and alarm system provided in an embodiment of the present application is shown, where the fault detection and alarm system may include a plurality of industrial robots 100 and a server 200, the industrial robots 100 and the server 200 are connected, and a detection and alarm device is integrated in the server 200.

In the embodiment of the present invention, the server 200 is mainly configured to obtain beat data corresponding to each joint axis in a beat; calculating to obtain torque load effective values corresponding to the plurality of joint shafts according to the beat data; judging whether the torque load effective value reaches a preset alarm condition or not; and if the preset alarm condition is reached, generating an alarm corresponding to the torque load effective value.

In this embodiment of the present invention, the server 200 may be an independent server, or may be a server network or a server cluster composed of servers, for example, the server 200 described in this embodiment of the present invention includes, but is not limited to, a computer, a network host, a single network server, multiple network server sets, or a cloud server composed of multiple servers. Among them, the Cloud server is constituted by a large number of computers or web servers based on Cloud Computing (Cloud Computing). In the embodiment of the present invention, the server and the industrial robot may implement communication through any communication manner, including, but not limited to, mobile communication based on 3rd Generation Partnership Project (3 GPP), Long Term Evolution (LTE), Worldwide Interoperability for Microwave Access (WiMAX), or computer network communication based on TCP/IP Protocol Suite (TCP/IP), User Datagram Protocol (UDP), and the like.

It will be appreciated that an industrial robot 100 as used in embodiments of the present invention may comprise devices that include both receiving and transmitting hardware, i.e. devices having receiving and transmitting hardware capable of performing two-way communication over a two-way communication link. The method specifically comprises the following steps: 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.

It will be understood by those skilled in the art that the application environment shown in fig. 1 is only one application scenario related to the present invention, and does not constitute a limitation on the application scenario of the present invention, and that other application environments may further include more or less servers than those shown in fig. 1, or a network connection relationship of servers, for example, only 1 server and 2 industrial robots are shown in fig. 1, and it will be understood that the fault detection and alarm system may further include one or more other servers, or/and one or more fault detection and alarm devices connected to a network of servers, and is not limited herein.

In addition, as shown in fig. 1, the fault detection and alarm system may further include a memory 300 for storing data, such as beat data generated when the industrial robot works, and the like.

It should be noted that the scene schematic diagram of the fault detection alarm system shown in fig. 1 is merely an example, and the fault detection alarm system and the scene described in the embodiment of the present invention are for more clearly explaining 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.

Some of the terms referred to in this application are described below:

torque: a special moment that causes the object to rotate. The torque of the engine is the torque output by the engine from the crankshaft. Under the condition of fixed power, the engine speed and the engine speed are in inverse proportion, the higher the speed and the lower the torque, and the higher the speed and the torque are, the load capacity of the automobile in a certain range is reflected. The external torque is called torque or external couple torque, and the internal torque is called internal couple torque or torque.

An industrial robot: industrial robots (industrial robots) are multi-joint manipulators or multi-degree-of-freedom machine devices widely used in the industrial field, have certain automaticity, and can realize various industrial processing and manufacturing functions by depending on the own power energy and control capability. Industrial robots are widely used in various industrial fields such as electronics, logistics, and chemical industry. Generally, an industrial robot consists of three major parts, six subsystems: the three parts are a mechanical part, a sensing part and a control part; the six subsystems can be divided into a mechanical structure system, a driving system, a sensing system, a robot-environment interaction system, a man-machine interaction system and a control system.

PLC: a Programmable Logic Controller (PLC), a digital operation Controller with a microprocessor for automatic control, which can load control instructions into a memory at any time for storage and execution. The programmable controller consists of functional units such as a CPU, an instruction and data memory, an input/output interface, a power supply, a digital-analog converter and the like.

As shown in fig. 2, which is a schematic flow chart of an embodiment of a fault detection and alarm method in the embodiment of the present application, the fault detection and alarm method includes:

21. beat data corresponding to each joint axis in a beat is acquired.

In an embodiment of the application, the industrial robot may comprise a plurality of joint axes, different joint axes being interconnected to achieve various different functions.

In the embodiment of the application, beat data corresponding to a plurality of joint axes in the industrial robot within one beat can be acquired. Where the tempo is the time required for the industrial robot to complete a certain action, i.e. in an embodiment of the application the tempo is a unit of time. The beat data is the motion data of a plurality of joint axes in the industrial robot in different beats corresponding to each joint axis in a time period corresponding to one beat; the tempo data may include data information such as torque load, speed, and positional deviation of each joint axis of the servo motor corresponding to each joint axis.

In the above embodiment, one joint axis corresponds to one piece of beat data, a plurality of joint axes correspond to a plurality of pieces of beat data, and the piece of beat data is a plurality of pieces of beat data.

22. And calculating to obtain the torque load effective value corresponding to each joint shaft in the plurality of joint shafts according to the beat data.

Specifically, in the embodiment of the present application, the torque loading effective value may be used to determine the working condition of each joint shaft.

23. And judging whether the torque load effective value reaches a preset alarm condition or not.

Specifically, in the embodiment of the present application, the number of the joint shafts is plural, and each joint shaft corresponds to one torque loading effective value. And because different joint shafts actually perform different actions and the abrasion among different parts in the joint shafts is different, each joint shaft corresponds to a torque load effective value and also corresponds to different alarm conditions.

24. And if the preset alarm condition is reached, generating an alarm corresponding to the torque load effective value.

The torque load effective value corresponding to each joint shaft can be compared with a preset alarm condition, if the torque load effective value reaches the preset alarm condition, it is indicated that the torque of the current joint shaft is in an abnormal working state, and an alarm corresponding to the torque is required to be generated so as to remind an operator to process.

In the embodiment of the application, the alarm conditions corresponding to different joint shafts can be different, so that the alarms can be of various types, operators can conveniently and directly judge the failed joint shaft according to the alarms, and the rapid positioning of the failed joint shaft is realized.

The application provides a fault detection and alarm method, which comprises the steps of obtaining beat data corresponding to each joint shaft in a beat, calculating to obtain a torque load effective value corresponding to each joint shaft by utilizing the beat data, and determining whether the joint shafts work normally or not by judging whether the torque load effective value exceeds a threshold value or not. The method and the device have the advantages that the effective value of the torque load is calculated, noise in the beat data is removed, influences such as robot load, beat action time length and environment temperature change are avoided, and stability of detection of all joint axes is improved.

In an embodiment of the present application, as shown in fig. 3, a flowchart illustrating an embodiment of obtaining beat data provided in the embodiment of the present application, where obtaining beat data corresponding to each joint axis in a beat may include:

31. initial beat data is acquired.

32. And determining the start-stop time of one beat according to the initial beat data.

33. And determining beat data in different beats corresponding to each joint axis in the initial beat data according to the start-stop time.

Specifically, in the embodiment of the present application, the data generated by the joint axes is massive, so that the PLC can obtain the initial beat data corresponding to each joint axis in real time, and the initial beat data of the joint axes can be servo data generated by the industrial robot starting with loading the substrate glass from one specific position and ending with unloading the substrate glass to another specific position through a series of actions.

Each time an industrial robot performs an action, a beat data file is generated, and may generally include beat data generated by performing a certain action on all joint axes for a period of time. The length of the time corresponding to the beat can be determined according to the time required by the plurality of joint axes to complete a specific action. In one particular embodiment of the present application, one beat is typically 30-40 seconds.

Since the PLC records real-time data, it is also necessary to determine beat data of all joint axes in one beat among all data recorded by the PLC. Namely, the beat data recorded by the PLC needs to be screened to determine the start and end times of the beat, and only the single beat data of a series of motions of the joint axis between the start and end of the beat is retained.

In the embodiment of the application, the initial beat data corresponding to a plurality of joint axes can be directly obtained by using a PLC, and the initial beat data is real-time data. In the data recorded by the PLC, the first row typically records the position corresponding to each axis, and the resulting positional deviation of each axis with respect to the previous second position; and simultaneously, the information such as the speed, the torque and the like corresponding to each shaft is recorded.

The data in each row usually includes beat data such as positions, position deviations, speeds, torques and the like corresponding to all joint axes at a certain time, and the data in different rows are beat data corresponding to all joint axes at different times. In fig. 4, the data in different rows are sorted in chronological order, and usually, after beat data of all joint axes at the current time is recorded, beat data corresponding to all joint axes at the next second is recorded. And beat data corresponding to each joint axis among the data recorded by the PLC is usually stored at a frequency of milliseconds.

In the embodiment of the application, the beat data corresponding to each joint axis can be obtained through screening according to the initial beat data corresponding to each joint axis. Since one beat is generally 30 to 40 seconds, data belonging to one beat among all data recorded by the PLC is also required.

In the embodiment of the present application, an industrial robot is generally used to move the display panel in the preparation process, so that one cycle may be the whole process from the beginning of taking a sheet to the end of putting the sheet by the industrial robot. And the time corresponding to the beat is the time required by the whole process from the start of taking the film to the end of putting the film by the industrial robot. Since each motion of the joint axis is recorded in the PLC, the PLC can be used to directly determine the time corresponding to each motion of the industrial robot, so as to determine the time of one beat.

As shown in fig. 4, an embodiment of the beat data provided for the embodiment of the present application is schematically illustrated, where "Start GET 2" may represent that the current industrial robot starts to take a picture, that is, the action in one beat starts; and "End GET 2" may represent the End of the current industrial robot taking a slice. And "Start PUT 12" may represent that the current industrial robot starts playing; and "End PUT 12" may represent that the current industrial robot finishes playing, i.e. the motion in one beat ends.

That is, in the embodiment of the present application, the start motion and the end motion of a beat can be directly determined by using data recorded by the PLC, and then the start time and the end time of a beat are determined, so as to determine beat data corresponding to all joint axes in a beat.

In the beat data shown in fig. 4, the start and end times of a beat are recorded in units of seconds, but in other embodiments of the present application, the start and end times of a beat may be recorded in units of milliseconds, so that the accuracy of the time corresponding to the beat is improved, thereby improving the accuracy of the beat data.

Fig. 5 is a schematic flow chart of an embodiment of calculating a torque loading effective value according to an embodiment of the present application. In an embodiment of the present application, the tempo data corresponding to each joint axis further includes speed data of each joint axis in a tempo. Calculating a torque loading effective value corresponding to each of the plurality of joint axes according to the beat data may include:

51. and determining single beat data corresponding to each joint axis in the plurality of joint axes in the beat data according to the speed data.

52. And calculating to obtain the torque load effective value corresponding to each joint shaft in the plurality of joint shafts according to the single beat data.

After the start-stop time of a beat and the beat data in different beats corresponding to each joint axis in a beat are determined, the beat data needs to be processed again to obtain actual beat data.

Since the speed of the joint axis is generally slow during a period of time between the start and the end of a beat, the joint axis is not in a normal working state. Therefore, in order to improve the effectiveness of the beat data, the beat data may be filtered again according to the respective speeds corresponding to the respective joint axes, so as to obtain the actual beat data.

Specifically, it may be determined whether a speed corresponding to each of the plurality of joint axes is within a preset speed range; if so, keeping beat data corresponding to the speed within a preset speed range; if not, the beat data corresponding to the speed which is not in the preset speed range is not reserved.

That is, in the embodiment of the present application, only part of data in one beat is retained according to the respective velocities corresponding to each joint axis, and beat data corresponding to velocities not within the preset velocity range is not retained. In general, in the beat data of the joint axis, the low speed corresponds to the process that the joint axis is just started or finishes the action stop, and at this time, the joint axis cannot be in the normal working state; therefore, beat data corresponding to the speed which is not within the preset speed range can be removed, and the accuracy of the beat data is improved.

In an embodiment of the application, the velocity of the joint axis may be generally expressed as the rotational speed of the servo motor in the joint axis, typically Xpulse/sec, i.e. the velocity per second is Xpulse, where impulse is the unit of rotational speed. The velocity data recorded by the PLC has positive values and negative values, and the positive values and the negative values only represent the difference of the joint axis directions.

In a specific embodiment of the present application, 1pulse/sec may be used as a low rotation speed standard, and beat data of a joint axis corresponding to a speed with an absolute value of less than or equal to 1pulse/sec is not retained.

After part of the initial beat data is removed, beat data corresponding to each joint axis can be obtained, and a torque load effective value corresponding to each joint axis is calculated according to the beat data corresponding to each joint axis.

It should be noted that, in the above embodiment, the speed range corresponding to each joint axis may be different, and the speed range corresponding to each joint axis may be determined according to actual conditions.

In the embodiment of the present application, there are a plurality of joint axes, and a plurality of pieces of beat data corresponding to the joint axes are also provided, and any of the plurality of joint axes may be used as a target joint axis. As shown in fig. 6, a schematic flowchart of another embodiment of calculating a torque loading effective value provided by the embodiment of the present application may include:

61. and determining target single-beat data corresponding to the target joint axis.

62. The absolute mean and standard deviation of the target single beat data are calculated.

63. And determining the torque load effective value corresponding to the target joint axis according to the absolute mean value and the standard deviation of the target single beat data.

In the embodiment of the application, the effective value of the torque load corresponding to each joint shaft is different; therefore, the torque load effective value corresponding to each joint axis can be calculated by using any joint axis among the plurality of joint axes as the target joint axis.

Specifically, the absolute mean and the standard deviation corresponding to the target joint axis may be calculated according to the beat data corresponding to the target joint axis. In the embodiment of the application, when the absolute mean and the standard deviation corresponding to the target joint axis are calculated, the torque load corresponding to the target joint axis in one beat is only substituted, and the torque load can be directly obtained by using the PLC.

Since one beat is usually 30-40 seconds, the torque loads corresponding to the target joint axis in different time within one beat are also multiple, and the absolute mean value and the standard deviation of the multiple torque loads can be respectively calculated according to the multiple torque loads so as to calculate the effective value of the torque load corresponding to the target joint axis.

Specifically, the absolute mean of the single beat data corresponding to the target joint axis may be divided by the standard deviation, that is: mean (abs (X))/std (abs (X))), where X is the torque load value in the beat data for the target joint axis. That is, when calculating the torque load effective value, only the torque load value in the tempo data is substituted into the formula calculation.

The torque load effective value corresponding to each joint shaft can be calculated according to the calculation method, and whether the joint shaft is in fault or not is judged.

In an embodiment of the present application, determining whether the torque loading effective value reaches the preset alarm condition may be divided into multiple steps, which may include: judging whether the torque load effective value corresponding to each joint shaft exceeds an early warning threshold value or not; and if the effective value of the torque load exceeds the early warning threshold value, judging whether the effective value of the torque load reaches a preset warning condition.

That is, in the embodiment of the present application, it is not enough to determine whether the effective value of the torque load exceeds the warning threshold, and it is also necessary to determine whether the effective value of the torque load reaches the warning condition. If the torque load effective value exceeds the early warning threshold value due to external factors at a certain moment, but the torque load effective value is recovered to be normal in the next beat and does not reach the preset warning condition, no warning is generated.

Therefore, it is also necessary to determine the respective early warning thresholds for the different joint axes. In the embodiment of the present application, the early warning thresholds corresponding to different joint axes may be the same or different.

Specifically, after the torque load effective value corresponding to each of the plurality of joint axes is obtained through calculation, the fault detection and alarm method may further include:

acquiring first historical beat data corresponding to each joint shaft in a plurality of joint shafts within a first preset time period; and respectively determining the torque load early warning threshold value corresponding to each joint shaft in the plurality of joint shafts according to the historical beat data corresponding to each joint shaft in the plurality of joint shafts.

If the torque load effective value of the joint shaft exceeds the early warning threshold, whether the current torque load effective value reaches the preset warning condition or not can be judged again. If the preset alarm condition is reached, an alarm corresponding to the current torque load effective value can be generated.

Specifically, in the embodiment of the present application, the torque load warning threshold value of each joint axis may be determined based on historical fault analysis for each joint axis. For example, based on the analysis of the first historical beat data of each joint axis in the first preset time period, when the torque load effective value of the joint axis is lower than the preset value, an alarm is generated.

Specifically, the torque load early warning threshold may be 4.8, that is, when the effective torque load value of the joint shaft is lower than 4.8, the current effective torque load value has reached the early warning threshold. At the moment, whether the current torque load effective value is continuously lower than 4.8 for three times or not and whether an alarm condition that the current torque load effective value is continuously lower than an early warning threshold value for three times is achieved or not can be judged; if yes, directly generating an alarm corresponding to the current torque load effective value.

In other embodiments of the present application, the preset alarm condition may also be that whether the current torque load effective value is lower than 80% of the early warning threshold, if yes, the alarm is directly given without determining whether the current torque load effective value is lower than the early warning threshold continuously three times.

Specifically, taking the early warning threshold value of the torque load as 4.8 as an example, if the current effective value of the torque load is lower than 80% of 4.8, that is, lower than 3.84; and directly generating an alarm corresponding to the current torque load effective value at the moment, and not judging whether the current torque load effective value is lower than 4.8 continuously for three times.

In other embodiments of the present application, the effective value of the torque beat of each joint axis may also be predicted according to the linear regression model, so as to predict the fault condition of each joint axis, and generate an alarm in advance.

As shown in fig. 7, an embodiment of a flowchart for obtaining a predicted value of the effective value of the torque load is provided in this application, and in some embodiments of the application, obtaining the predicted value of the effective value of the torque load may include:

71. and acquiring second historical beat data corresponding to each joint shaft in the plurality of joint shafts in a second preset time period.

72. And determining a plurality of beat windows in the second historical beat data according to the preset number of beat data corresponding to each beat window.

73. A plurality of linear regression models corresponding to the plurality of beat windows is determined.

74. And determining a predicted value of the torque load with the effective value in the next beat window according to a plurality of linear regression models.

Specifically, in the embodiment of the present application, a linear regression model about a torque load effective value may be determined by using second historical beat data corresponding to a joint axis in a second preset time period; to determine a predicted value of the torque load holding effective value according to the linear regression model.

First, second historical beat data corresponding to each joint axis in the plurality of joint axes within a second preset time period can be obtained; and dividing the second historical beat data into different beat windows according to preset beat data, wherein each beat window comprises a plurality of beats and historical beat data corresponding to the plurality of beats.

One beat window corresponds to one linear regression model, and the number of beat windows can be multiple, so that the number of linear regression models is also multiple.

In an embodiment of the present application, determining a plurality of linear regression models corresponding to a plurality of beat windows may include:

and respectively taking one beat window as a target beat window, and determining the beat data in different beats respectively corresponding to each joint axis in the target beat window. And calculating to obtain a linear regression model in a target beat window according to beat data in different beats corresponding to each joint axis.

In an embodiment of the application, a plurality of linear models about effective values of torque loads are determined by using historical beat data; a variation law of the torque load effective value can be determined according to a plurality of linear regression models to predict the torque load effective value.

In a specific embodiment of the present application, six beats may be taken as one beat window, i.e., one beat window includes six beats. Acquiring beat data in different beats corresponding to each joint axis in the time of six adjacent continuous beats; according to the beat data, effective values of torque beats of all joint shafts in different beats can be determined; the effective value of the torque beat corresponding to each joint shaft is six. And a linear regression model can be determined according to six different effective values of the torque beat.

In the above embodiment, six beats are divided into beats 1-6, and a linear regression model is determined according to the effective value of the torque beats in the beats 1-6; and continuously taking six adjacent and continuous beats, namely the beats 2-7, as a beat window, and then determining the effective torque beat value of each joint axis in the beats 2-7 to obtain a linear regression model corresponding to the beats 2-7. Wherein the parameters in the regression model may be determined using a least squares method.

On the basis of the above embodiment, a plurality of linear regression models can be obtained, and the number of the linear regression models is the same as the number of the beat windows. And according to the plurality of linear regression models, the change trend of the effective value of the torque beat can be determined, so that the effective value of the torque beat in the subsequent beat can be predicted, and early warning is achieved.

In the embodiment of the present application, the number of beats in one beat window is usually between 5 and 10, and the greater the number of beats, the more beat data is acquired, and the obtained linear regression model is also about accurate. However, when the joint axis is in fault, the effective value of the torque beat corresponding to the joint axis changes suddenly, which greatly affects the parameters in the linear regression model, so the number of beats in one beat window cannot be too large. Typically, the beats in a beat window are six to ten.

It should be noted that, in the embodiment of the present application, the beat data corresponding to different joint axes are different, and the torque beat effective values, the early warning threshold values, and the warning conditions corresponding to different joint axes may be the same or different; can be set according to actual conditions. When the fault condition of a certain joint axis is judged, the fault condition is judged independently and is not related to other joint axes.

As shown in fig. 8, a specific embodiment of a fault detection and alarm method provided in the embodiment of the present application is shown, in fig. 8, when starting fault detection, it is necessary to first acquire initial beat data of a joint axis and preprocess the initial beat data. In which, the preprocessing may be to determine the start and end time of a beat, and to retain a part of the initial beat data located in the beat. And dividing the initial beat data without reserving the initial beat data corresponding to the low speed to obtain the beat data.

After the beat data is obtained, the effective value of the torque load can be calculated according to the beat data; and judging whether the joint shaft is in fault according to the effective value of the torque load. The method comprises the steps of judging whether a torque load effective value exceeds an early warning threshold value or not, and judging whether the torque load effective value reaches a preset warning condition or not if the torque load effective value exceeds the early warning threshold value; if yes, directly giving an alarm.

In the above embodiment, a piecewise linear regression model of the effective value of the torque meter can be generated by using the historical meter data to perform fault prediction.

In order to better implement the fault detection and alarm method in the embodiment of the present application, on the basis of the fault detection and alarm method, an embodiment of the present application further provides a fault detection and alarm device, as shown in fig. 9, which is a schematic diagram of an embodiment of the fault detection device provided in the embodiment of the present application, where the fault detection and alarm device 900 includes:

an obtaining module 901, configured to obtain beat data corresponding to the joint axes in a beat;

the calculating module 902 is configured to calculate, according to the beat data, a torque load effective value corresponding to each joint axis of the multiple joint axes;

a judging module 903, configured to judge whether the torque loading effective value reaches a preset alarm condition

And an alarm module 904, configured to generate an alarm corresponding to the torque load effective value if the preset alarm condition is met.

The application provides a fault detection alarm device, which is characterized in that beat data corresponding to each joint shaft in a beat are obtained, a torque load effective value corresponding to each joint shaft is obtained through calculation by utilizing the beat data, and whether the joint shaft works normally is determined by judging whether the torque load effective value exceeds a threshold value or not. This application has got rid of the noise in the beat data through calculating the moment of torsion load rms value, has avoided influence such as long and ambient temperature change of robot load, beat action, has improved the stability to each joint axis detection.

The present application further provides a server, which integrates any one of the failure detection and alarm devices provided in the embodiments of the present application, as shown in fig. 10, which shows a schematic structural diagram of the server related to the embodiments of the present application, specifically:

the server may include components such as a processor 1001 of one or more processing cores, memory 1002 of one or more computer-readable storage media, a power source 1003, and an input unit 1004. Those skilled in the art will appreciate that the server architecture shown in FIG. 10 is not meant to be limiting, and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. Wherein:

the processor 1001 is a control center of the server, connects various parts of the entire server with various interfaces and lines, performs various functions of the server and processes data by running or executing software programs and/or modules stored in the memory 1002 and calling data stored in the memory 1002, thereby performing overall monitoring of the server. Optionally, processor 1001 may include one or more processing cores; preferably, the processor 1001 may integrate an application processor, which mainly handles an operating system, a user interface, application programs, etc., and a modem processor, which mainly handles wireless communication. It will be appreciated that the modem processor described above may not be integrated into processor 1001.

The memory 1002 may be used to store software programs and modules, and the processor 1001 executes various functional applications and data processing by operating the software programs and modules stored in the memory 1002. The memory 1002 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the server, and the like. Further, the memory 1002 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 1002 may also include a memory controller to provide the processor 1001 access to the memory 1002.

The server further includes a power source 1003 for supplying power to each component, and preferably, the power source 1003 may be logically connected to the processor 1001 through a power management system, so as to implement functions of managing charging, discharging, and power consumption through the power management system. The power source 1003 may also include any component including one or more of a dc or ac power source, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.

The server may further include an input unit 1004, and the input unit 1004 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

Although not shown, the server may further include a display unit and the like, which will not be described in detail herein. Specifically, in this embodiment, the processor 1001 in the server loads the executable file corresponding to the process of one or more application programs into the memory 1002 according to the following instructions, and the processor 1001 runs the application programs stored in the memory 1002, thereby implementing various functions as follows:

acquiring beat data corresponding to each joint shaft in a beat; calculating to obtain torque load effective values corresponding to the plurality of joint shafts according to the beat data; judging whether the torque load effective value reaches a preset alarm condition or not; and if the preset alarm condition is reached, generating an alarm corresponding to the torque load effective value.

The present application also provides a computer-readable storage medium, which may include: read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disks, and the like. The storage medium stores a computer program, which is loaded by the processor to perform the steps of any one of the fault detection and alarm methods provided in the embodiments of the present application. For example, the computer program may be loaded by a processor to perform the steps of:

acquiring beat data corresponding to each joint axis in a beat; calculating to obtain torque load effective values corresponding to the plurality of joint shafts according to the beat data; judging whether the torque load effective value reaches a preset alarm condition or not; and if the preset alarm condition is met, generating an alarm corresponding to the torque load effective value.

It should be noted that, since the method in the embodiment of the present application is executed in an electronic device, processing objects of each electronic device exist in the form of data or information, for example, time, which is substantially time information, and it can be understood that, if size, number, position, and the like are mentioned in subsequent embodiments, corresponding data exist so that the electronic device performs processing, which is not described herein again specifically.

The fault detection and alarm method, device, server and storage medium provided in the embodiments of the present application are described in detail above, and specific examples are applied herein to explain the principle and implementation manner of the present invention, and the description of the above embodiments is only used to help understanding the method and core ideas 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

1. A fault detection warning method, characterized by being applied to an industrial robot including a plurality of joint axes, the method comprising:

acquiring beat data corresponding to each joint axis in the plurality of joint axes in a beat, wherein the beat data comprises speed data corresponding to each joint axis in the plurality of joint axes in the beat;

according to the speed data, single beat data corresponding to each joint axis in the plurality of joint axes is determined in the beat data, wherein the single beat data is a torque load value corresponding to the corresponding joint axis in a single beat;

taking any joint axis in the plurality of joint axes as a target joint axis;

determining single beat data corresponding to the target joint axis;

calculating the absolute mean value and standard deviation of the single beat data corresponding to the target joint axis;

determining a torque load effective value corresponding to the target joint axis according to the absolute mean value and the standard deviation of the target single beat data corresponding to the target joint axis so as to obtain the torque load effective values corresponding to each joint axis in the plurality of joint axes;

if the preset alarm condition is met, generating an alarm corresponding to the torque load effective value;

acquiring second historical beat data corresponding to each joint shaft in the plurality of joint shafts within a second preset time period;

sequentially taking a plurality of adjacent continuous beats with preset number as a beat window in a plurality of beats contained in the second historical beat data so as to divide the second historical beat data into a plurality of beat windows, wherein each beat window comprises historical beat data corresponding to a plurality of beats;

respectively taking a beat window as a target beat window, and determining historical beat data in different beats respectively corresponding to each joint axis in the target beat window;

determining effective values of torque beats of the joint shafts in different beats according to historical beat data in different beats corresponding to the joint shafts in the target beat window;

calculating to obtain linear regression models in the target beat window according to the torque beat effective values of the joint shafts in different beats so as to determine a plurality of linear regression models corresponding to the beat windows;

and determining the change trend of the effective value of the torque load according to the plurality of linear regression models so as to determine the predicted value of the effective value of the torque load in the next beat window, and performing fault early warning according to the predicted value.

2. The fault detection and alarm method according to claim 1, wherein the obtaining beat data corresponding to each joint axis in the plurality of joint axes in a beat comprises:

acquiring initial beat data;

3. The fault detection alarm method according to claim 1, wherein after obtaining the effective value of the torque load corresponding to each of the plurality of joint axes, the method further comprises:

acquiring first historical beat data corresponding to each joint shaft in the plurality of joint shafts within a first preset time period;

4. The fault detection warning method according to claim 1, wherein the determining whether the effective torque loading value reaches a preset warning condition includes:

and if the torque load effective value exceeds the early warning threshold value, judging whether the torque load effective value reaches a preset warning condition.

5. A fault detection warning device, characterized in that, applied to an industrial robot comprising a plurality of joint axes, the device comprises:

the acquisition module is used for acquiring beat data corresponding to each joint shaft in the plurality of joint shafts in a beat, wherein the beat data comprises speed data corresponding to each joint shaft in the plurality of joint shafts in a beat;

the computing module is used for determining single beat data corresponding to each joint axis in the plurality of joint axes in the beat data according to the speed data, wherein the single beat data is a torque load value corresponding to the corresponding joint axis in a single beat; taking any joint axis in the plurality of joint axes as a target joint axis; determining single beat data corresponding to the target joint axis; calculating the absolute mean value and standard deviation of the single beat data corresponding to the target joint axis; determining a torque load effective value corresponding to the target joint axis according to the absolute mean value and the standard deviation of the target single beat data corresponding to the target joint axis so as to obtain a torque load effective value corresponding to each joint axis in the plurality of joint axes;

the warning module is used for generating a warning corresponding to the torque load effective value if the preset warning condition is met;

6. A server, characterized in that the server comprises:

one or more processors;

a memory; and

one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the processor to implement the failure detection alarm method of any of claims 1-4.

7. A computer-readable storage medium, having stored thereon a computer program which is loaded by a processor for performing the steps of the fault detection alarm method as claimed in any one of claims 1 to 4.