Industrial robot joint fault prediction method, device and storage medium

Abstract

The present application provides an industrial robot joint fault prediction method, device and storage medium, including: S1, obtaining the original motor current signal; S2, filtering it to obtain a filtered current signal; S3, extracting the root mean square value from the filtered current signal as a characteristic index for characterization, and writing the characteristic index in the form of a data set Z; S4, establishing a degradation model under multiple working conditions, variable loads, and multi-stage cycles; S5, estimating the unknown parameters involved; S6, dividing the failure threshold according to the characteristics of each stage task, and establishing a threshold set oh ; S7. Based on S4 and S6, the expressions of probability density function and reliability function are obtained, and reliability evaluation is performed; This application establishes a degradation model suitable for multi-working conditions, variable loads and multi-stage cyclic task systems when an industrial robot periodically performs a task. The model established in this application can be directly applied under multiple working conditions and variable loads.

Description

Technical Field

[0001] The present application relates to the technical field, and in particular to an industrial robot joint fault prediction method, device and storage medium. Background Art

[0002] Industrial robots are automated equipment that integrates advanced technologies from multiple disciplines, such as mechanics, electronics, control, computers, sensors, and artificial intelligence. They have the characteristics of multiple degrees of freedom, complex structure, and strong independence, and are widely used in automobile manufacturing, parts processing, and electronic and electrical industries. Due to the relatively complex service environment, industrial robots are prone to failure due to the influence of variable loads and random loads in the environment, especially the precision reducers at the joints. In field tests, their failure rate is as high as 40%-70%. Among them, harmonic reducers are a type of precision reducer with the advantages of small size, light weight, large transmission ratio, high load capacity, high precision, and high efficiency. They are widely used in high-end mechanical equipment such as joints and robotic arms of compact and small industrial robots. They play a role in reducing speed and increasing torque while ensuring positioning accuracy and repeatability. Their working state directly affects the overall working performance and service life of industrial robots. Once a failure occurs, it will lead to insufficient transmission, transmission ratio deviation, and even the shutdown of the entire system, causing huge economic losses.

[0003] Most of the existing studies on the multi-task stage degradation process divide the complete degradation process of the system into multiple degradation stages for research. However, this multi-stage division is based on the speed of degradation of the system during its entire life cycle. For example, before the system fails, it can be divided into normal, slow degradation and rapid degradation processes. Industrial robots have the characteristics of multi-task and variable stress in the multi-task stage. The harmonic reducers at their joints have the characteristics of complex performance, time-varying and periodic working conditions. The existing degradation model only divides a single failure threshold for a single working condition and constant load. However, the single failure threshold cannot accurately evaluate the reliability of the harmonic reducer under the multi-stage degradation task conditions, and therefore cannot be directly used to describe the degradation process of multi-condition, variable load, and multi-stage cyclic mechanical systems. Summary of the invention

[0004] The purpose of this application is to provide an industrial robot joint fault prediction method, device and storage medium to address the above problems.

[0005] First aspect:

[0006] The present application provides an industrial robot joint fault prediction method, comprising:

[0007] S1, obtaining the current signal of the original motor connected to the industrial robot;

[0008] S2, filtering the original motor current signal to obtain a filtered current signal;

[0009] S3, extracting a root mean square value from the filtered current signal as a characteristic index to characterize the harmonic reducer at the joint of the industrial robot, and writing the characteristic index in the form of a data set Z;

[0010] S4. Establish a degradation model that characterizes the harmonic reducer at the joint of the industrial robot under multiple working conditions, variable loads, and multi-stage cycles, and the degradation model includes tasks in multiple stages.

[0011] S5. Estimate the unknown parameters contained in each stage task;

[0012] S6. Divide the failure threshold according to the characteristics of each stage task and form a threshold set oh ;

[0013] S7, based on the degradation model and the threshold set oh , the expressions of probability density function and reliability function are obtained, and reliability evaluation is performed.

[0014] According to the technical solution provided in the embodiment of the present application, in the step S2, the original motor current signal is processed by median filtering to obtain the filtered current signal.

[0015] According to the technical solution provided in the embodiment of the present application, in step S3, the data set Z is written in the following matrix expression:

[0016]

[0017] Where: z ij The system is j The second cycle i Data of the mission phase;

[0018] i =1,2,3... m， m represents the number of task stages;

[0019] j =1,2,3... n， n represents the number of loops.

[0020] According to the technical solution provided in the embodiment of the present application, in step S4, when the industrial robot works under multi-stage cycle and variable load conditions, the task stages of the harmonic reducer at the joints of the industrial robot are continuous and periodic, and the harmonic reducer has different degradation rates in different task stages. The degradation model is established according to the degradation state changes of the harmonic reducer when performing multi-stage cycle tasks, and the degradation model is a nonlinear multi-stage task degradation model.

[0021] According to the technical solution provided in the embodiment of the present application, in step S5, the maximum likelihood estimation method is used to estimate the unknown parameters contained in each stage.

[0022] According to the technical solution provided in the embodiment of the present application, in step S6, the threshold value set oh The expression is as follows:

[0023]

[0024] Where: oh i is the threshold of the system in the i-th task stage, and the system has a total of m task stages.

[0025] According to the technical solution provided in the embodiment of the present application, in step S7, it is assumed that Z 1, Z 2, Z 3, …, Z m are independent random variables, then the probability density function expression is as follows:

[0026]

[0027] Where: oh 1, oh 2, oh 3, ..., oh m is the data in the threshold set;

[0028] β i ( i =1,2,… m ) indicates the i The degradation rate of each task stage;

[0029] t represents time;

[0030] s is the diffusion coefficient, which is used to describe the impact of external noise on product performance. Assuming that the product failure mechanism remains unchanged at different stress levels, s constant, σB ( t) is subject to N (0,σ 2 t);

[0031] The expression of the reliability function is as follows:

[0032]

[0033] Where: F ( oh 1, oh 2, …, oh i )for m dimensional random variable Z 1, Z 2, Z 3, …, Z m The joint distribution function of

[0034] oh 1, oh 2, oh 3, ..., oh m is the data in the threshold set.

[0035] In a second aspect, the present application further provides a terminal device, the terminal device comprising:

[0036] A memory, a processor, and a computer program stored in the memory and executable on the processor;

[0037] When the computer program is executed by the processor, the steps of the industrial robot joint fault prediction method described in any one of the above are implemented.

[0038] In a third aspect, the present application further provides a computer-readable storage medium, comprising:

[0039] The computer-readable storage medium stores an industrial robot joint fault prediction program, and when the industrial robot joint fault prediction program is executed by the processor, the steps of the industrial robot joint fault prediction method described in any one of the above are implemented.

[0040] Compared with the prior art, the present invention has the following beneficial effects: the present invention first obtains the motor current signal of the harmonic reducer directly connected to the motor at the joint of the industrial robot, extracts the characteristic index after filtering and writes it into a data set ZIn the form of a method, aiming at the operation of industrial robots under the actual working conditions of variable loads and multi-stage cycles, taking into account the different conditions of the harmonic reducer at the joints of industrial robots in each task stage under multiple working conditions, a degradation model is established to characterize the harmonic reducer at the joints of industrial robots under multiple working conditions, variable loads, and multi-stage cycle tasks, and the unknown parameters are estimated. In view of the fact that a single threshold value cannot accurately identify failure faults under the multi-stage cycle task conditions of industrial robots, different failure thresholds are divided considering the characteristics of each task stage to form a threshold set. oh , used to identify failures at different mission stages, and obtain probability density function and reliability function according to the established degradation model and threshold set under multiple working conditions to conduct reliability assessment;

[0041] During use, the original motor current signal of the harmonic reducer directly connected to the motor at the joint of the industrial robot is first obtained, and the characteristic indicators are extracted after filtering, and the characteristic indicators are written into a data set. Z In the form of, according to the actual working conditions of the industrial robot, a degradation model under multiple working conditions, variable loads, and multi-stage cycles is established, and parameter estimation is performed. According to the different task stages of the industrial robot, different failure thresholds are divided for the harmonic reducer at the joint of the industrial robot, and a threshold set is established. According to the established multi-working condition degradation model and threshold set, the probability density function and reliability function are obtained, and the reliability evaluation is performed.

[0042] This application is based on the original motor current signal of the harmonic reducer directly connected to the motor at the joint of the industrial robot. According to the multiple working conditions and variable loads that exist when the industrial robot periodically performs a task, a degradation model for a multi-stage cyclic task system suitable for multiple working conditions and variable loads is established. Different failure thresholds are divided according to different task stages of the industrial robot, and a threshold set is established. According to the established multi-stage task nonlinear degradation model and threshold set, a probability density function and a reliability function are established to perform reliability evaluation. The degradation model and reliability function established in this application can be directly applied under multiple working conditions and variable loads. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of a flow chart of a method for predicting joint failures of an industrial robot provided in Example 1 of the present application;

[0044] Figure 2 The original motor current signal and the filtered current signal under three operating conditions provided in Example 1 of the present application;

[0045] Figure 3 This is the current signal when the industrial robot provided in Example 1 of the present application performs action 1;

[0046] Figure 4The current signal when the industrial robot provided in Example 1 of the present application performs action 2;

[0047] Figure 5 This is the current signal when the industrial robot provided in Example 1 of the present application performs action 3;

[0048] Figure 6 The life probability density curve provided in Example 1 of the present application;

[0049] Figure 7 A reliability curve provided in Example 1 of the present application;

[0050] Figure 8 A schematic diagram of the structure of the server provided in Example 4 of the present application.

[0051] The text annotations in the figure represent:

[0052] 400, server; 401, central processing unit (CPU); 402, read-only memory (ROM); 403, random access memory (RAM); 404, bus; 405, input / output (I / O) interface; 406, input part; 407, output part; 408, storage part; 409, communication part; 410, drive; 411, removable media. DETAILED DESCRIPTION

[0053] In order to enable those skilled in the art to better understand the technical solution of the present application, the present application is described in detail below in conjunction with the accompanying drawings. The description in this section is only exemplary and explanatory and should not have any limiting effect on the scope of protection of the present application.

[0054] Embodiment 1

[0055] This embodiment provides an industrial robot joint fault prediction method, the method comprising:

[0056] Please refer to Figure 1 , S1, obtain the original motor current signal of the motor directly connected to the harmonic reducer at the joint of the industrial robot;

[0057] This patent builds a harmonic reducer acceleration life test bench to simulate the working conditions of the harmonic reducer of the robot joint in sorting work. The test bench consists of a servo motor, a harmonic reducer, a torque sensor, a load motor and an industrial computer.

[0058] Experimental parameter settings:

[0059] 1: Test bench servo motor n = Running at a speed of 2000r / min;

[0060] 2: The test loading is cyclic step stress, the load change sequence is S1=2.6Nm (0.5 times rated load), S2=5.1Nm (rated load), S3=7.7Nm (1.5 times load), changing every 2 hours, cyclically.

[0061] Current signal acquisition: In this experiment, the Fluke-80i-110s current probe is connected in series to the single-phase current output line of the motor driver to collect dynamic current signals in real time, and is connected to a high-precision NIUSB-6281 data acquisition card to record current signals. The sampling frequency of the motor current data is set to 20kHz, and the sampling time is about 9 seconds. Each signal segment records the valid data of 6 cycles of the harmonic reducer.

[0062] Experimental process: The harmonic reducer is operated in a state of accelerated degradation until it fails completely. At the same time, the experiment is carried out by doubling the load torque and removing part of the grease to create unfavorable lubrication conditions to accelerate the life of the harmonic reducer. In the experiment, the full life cycle of the harmonic reducer is 62520min, and the wave generator and the flexible wheel-steel wheel after the experiment are severely worn.

[0063] S2, filtering the original motor current signal to obtain a filtered current signal;

[0064] The collected current signals are mostly nonlinear and non-stationary signals, which often have problems such as weak fault impact characteristics and severe background noise interference. They need to be filtered to eliminate the high-frequency noise components in the current signals. This scheme uses the median filtering method to process the original current signal, providing a high-quality source signal for subsequent analysis; the fault impact components in the signal are retained after low-frequency noise reduction processing. Figure 2 The raw motor current signal and the filtered current signal are shown for three operating conditions. Figure 3 It is the current signal when the industrial robot performs action 1. Figure 4 It is the current signal when the industrial robot performs action 2. Figure 5 is the current signal when the industrial robot performs action 3, and the actions 1, 2 and 3 are the three operating conditions; Figure 2 It can be seen that the amplitude of the current signal varies greatly under different operating conditions.

[0065] S3, extracting the root mean square value from the filtered current signal as a characteristic index to characterize the harmonic reducer at the joint of the industrial robot, and writing the characteristic index into a data set Z form;

[0066] The RMS calculation method is used to process the data and the degradation indicators after RMS processing are sorted out.

[0067] During the life cycle of the harmonic reducer, the complete mission has m = 3 stages, the mission lasted nearly n = 174 cycles, divide the data according to each stage, and take one sample point in each cycle of each stage to form a data set Z , as shown in formula (1).

[0068] (1)

[0069] Where: z ij The system is j The second cycle i Data of the mission phase;

[0070] i =1,2,3... m， m represents the number of task stages;

[0071] j =1,2,3... n， n represents the number of loops.

[0072] S4. Establishing a degradation model for characterizing the harmonic reducer at the joint of the industrial robot under multiple working conditions, variable loads, and multiple-stage cycles, wherein the degradation model includes tasks at multiple stages;

[0073] 1. System Assumptions

[0074] This patent establishes a multi-stage task nonlinear degradation model and makes the following description and assumptions about the degradation model; it should be noted that the systems described in this application are all "industrial robot systems":

[0075] 1) The degradation process is irreversible, that is, the system performance is monotonic over time;

[0076] 2) The task consists of a series of consecutive stages, that is, the task stages are continuous and the order is fixed;

[0077] 3) The duration of the different phases is known;

[0078] 4) Within the failure threshold, the degradation rate is different under different load levels.

[0079] 2. Establishing a multi-stage task nonlinear degradation model

[0080] When an industrial robot works under multi-stage cycle and variable load conditions (i.e. in actual industrial production), the task stages of the harmonic reducer at the joints of the industrial robot are characterized by continuity and periodicity; when the harmonic reducer of the industrial robot is affected by sudden load changes, steering changes, start-stop and complex external environment, independent degradation increments will be generated; at different task stages, the degradation rate of the harmonic reducer will change with the change of the working conditions of the industrial robot; taking into account the multivariate time-varying working conditions, individual differences, nonlinearity, multi-stage and random stress conditions existing in the complex system of the industrial robot, the degradation model is established according to the degradation state transformation of the harmonic reducer when performing multi-stage cycle tasks, and the degradation model is a nonlinear multi-stage task degradation model; that is, the nonlinear multi-stage task degradation model can characterize the degradation model process of the harmonic reducer at the joints of the industrial robot under multi-conditions, variable loads and multi-stage cycle tasks.

[0081] The degradation amount of the harmonic reducer at time t can be expressed as:

[0082] (2)

[0083] Where: β is the drift coefficient, which characterizes the degradation rate;

[0084] x (0) is t = the initial degradation amount at time 0;

[0085] β (•) represents the functional relationship between the degradation rate and time, and there are different formulas for different parts;

[0086] B ( t ), t >0 conforms to the Wiener process, that is, the standard Brownian motion;

[0087] s is the diffusion coefficient, which is used to describe the impact of random factors such as external noise on product performance. Assuming that the product failure mechanism remains unchanged at different stress levels, s constant, σB ( t ) is subject to N (0, s 2 t ).

[0088] A system with m task stages runs for t time, and each task stage is cycled n times. Assuming that the duration of the i-th stage of the system is the same in each cycle, the overall degradation at time t is:

[0089]

[0090] Assuming that the degradation rate is constant at each stage in each cycle, formula (3) can be written as:

[0091]

[0092] Where: β i (i=1,2,…m) represents the degradation rate of the i-th task stage;

[0093] (t i-1 , t i ) represents a time interval;

[0094] β i =β(i),Δt i represents the duration of the i-th task stage;

[0095] (t (j-1)m+i-1 ,t (j-1)m+1 ) is the duration of the i-th task phase in the j-th cycle, and the duration of the i-th task phase is considered to be the same in each cycle;

[0096] x(0) is the initial degradation at time t = 0;

[0097] σ is the diffusion coefficient, which is used to describe the impact of random factors such as external noise on product performance. Assuming that the product failure mechanism remains unchanged under different stress levels, σ remains unchanged, and σB(t) obeys N(0, σ 2 t).

[0098] In the i-th task stage, the degradation amount generated after n cycles is formula (5):

[0099]

[0100] Where: x(0) is the initial degradation at time t = 0;

[0101] β i (i=1,2,…m) represents the degradation rate of the i-th task stage;

[0102] (t i-1 , t i ) represents a time interval;

[0103] β i =β(i),Δt i represents the duration of the i-th task stage;

[0104] (t (j-1)m+i-1 ,t (j-1)m+1) is the duration of the i-th task phase in the j-th cycle, and the duration of the i-th task phase is considered to be the same in each cycle;

[0105] σ is the diffusion coefficient, which is used to describe the impact of random factors such as external noise on product performance. Assuming that the product failure mechanism remains unchanged under different stress levels, σ remains unchanged, σB(t)

[0106] Subject to N(0,σ 2 t).

[0107] S5. estimating unknown parameters included in the tasks of each stage;

[0108] Assume that the system has m The tasks of the stage were run t moment, all stages passed n Loop through to get the data set Z , as shown in the above formula (1), the system i Stages at time t i1 , t i2 , …, t in The measured data is z i1 ,z i2 ,z i3 ,…, z in , that is, i The data set of each stage is {z i1 ,z i2 ,z i3 ,…, z in}, the incremental data set is ΔZ , as shown in formula (6):

[0109] (6)

[0110] (7)

[0111] Where: i =1,2,3,…, m ;

[0112] j =1,2,3,…, n ;

[0113] in z i0 =0;

[0114] t ij - t i(j-1)Executes once for all phases for a duration.

[0115] ΔZ It obeys the multivariate normal distribution and assumes that the failure mechanism of the product remains unchanged at different stress levels. s 2 constant; ΔZ obey N ( β i ( t ij - t i(j-1 )), s 2 ( t ij - t i(j-1) )); The maximum likelihood estimation method is used to estimate the unknown parameters of each task in the multi-stage task degradation model β i , s 2 :

[0116] (8)

[0117] (9)

[0118] in: and It only represents the result after the maximum likelihood function is calculated and has no special meaning;

[0119] According to the real-time data changes, the maximum likelihood estimation method is used to solve the unknown parameters in the degradation model through equations (8) and (9): β i , s 2 , the results are shown in Table 1:

[0120] Table 1 Degradation model parameters

[0121]

[0122] S6. Divide the failure threshold according to the characteristics of each stage task and form the threshold set oh ;

[0123] Industrial robots actually go through a cyclical task mode in service, and a single task usually includes several stages (for example, when a palletizing robot performs a single palletizing task, it mainly goes through the following four stages: quickly moving to the waiting working position, grabbing objects, moving the load to the waiting placement area, and placing objects; at the same time, in the continuous palletizing process, as the number of objects to be grabbed decreases, the height of the robot's rapid movement to the waiting working position is also decreasing, and the height of the waiting placement area is increasing. When working continuously, the working conditions experienced by the robot are in a changing process). The motor current of the motor directly connected to the harmonic reducer at the joint of the industrial robot has a large difference in amplitude at different task stages. In the task stage with a small current amplitude, the reliability assessment result of the harmonic reducer is too large, and in the task stage with a large current amplitude, the reliability assessment result of the harmonic reducer is small. The method of presetting a single failure threshold for reliability assessment or remaining life assessment is no longer applicable. Therefore, it is necessary to dynamically divide the threshold according to different task stages and obtain a threshold set. oh ;

[0124] (10)

[0125] In the formula oh i The system is i The system has a threshold of task stages. m A task phase.

[0126] During the life cycle of the harmonic reducer, the complete mission has m = 3 stages, the mission lasted nearly n = 174 cycles, divide the data according to each stage, and take one sample point in each cycle of each stage to form a data set Z , as shown in formula (1).

[0127] Assume that the failure threshold set of the harmonic reducer is {ω1,ω2,ω3} as {4,5,6.5} according to formula (2).

[0128] S7, based on the multi-stage task degradation model and the threshold set oh , the expressions of probability density function and reliability function are obtained, and reliability evaluation is performed.

[0129] The maximum likelihood estimation method is used to estimate the unknown parameters of each task in the multi-stage task degradation model. β i , s 2 .

[0130] Threshold Set oh ={ω1,ω2,…,ω i}(i=1,2,…,m), cutofft All task stages of the moment system have passed n Second cycle.

[0131] Divide the task into stages according to the task phase. i The set of degradation data of the stage is recorded as Z i ,Right now Z i =( z i1 , z i2 , …, z ij ,…, z in ), as shown in formula (11), where z ij ( i =1,2,… m , j =1,2,… n ) indicates that the system is j The first task in the cycle i The degradation index of the stage is ( Z 1, Z 2, Z 3, …, Z m ) is a random variable on the same sample space, belonging to m dimensional random variable.

[0132] From formula (4), we can know Z 1, Z 2, Z 3, …, Z m All obey the Wiener process, and the failure threshold is oh i . (11)

[0133] Assumptions Z 1, Z 2, Z 3, …, Z m are independent random variables, and the probability density function (PDF) of the harmonic reducer life is as follows (12):

[0134] (12)

[0135] In the formula: ω1, ω2, ω3,…,ω m is the data in the threshold set.

[0136] β i (i=1,2,…m) represents the degradation rate of the i-th task stage;

[0137] t represents time;

[0138] s is the diffusion coefficient, which is used to describe the impact of product external noise (random factors are not limited to external noise) on product performance. Assuming that the product failure mechanism remains unchanged at different stress levels, s constant, σB ( t ) is subject to N(0,σ 2 t).

[0139] Its reliability function can be expressed as:

[0140] (13)

[0141] Where: F ( oh 1, oh 2, …, oh i )for m dimensional random variable Z 1, Z 2, Z 3, …, Z m The joint distribution function of

[0142] oh 1, oh 2, oh 3, …, oh m is the threshold vector;

[0143] β i ( i =1,2,… m ) indicates the i The degradation rate of each task stage;

[0144] t represents time;

[0145] s is the diffusion coefficient, which is used to describe the impact of random factors such as external noise on product performance. Assuming that the product failure mechanism remains unchanged at different stress levels, s constant, σB ( t ) is subject to N (0, s 2 t ).

[0146] According to the proposed degradation model and reliability function based on the Wiener process, the degradation model parameters in Table 1 are substituted into equations (14) and (15) to obtain the life probability density curve and reliability function curve of the harmonic reducer, as shown in the figure. Figure 6 and Figure 7 shown.

[0147] Embodiment 2

[0148] This embodiment provides a terminal device, wherein the industrial robot joint fault prediction device comprises:

[0149] A memory, a processor, and a computer program stored in the memory and executable on the processor;

[0150] When the computer program is executed by the processor, the following is achieved: Figure 1 The steps of any industrial robot joint fault prediction method.

[0151] Embodiment three:

[0152] This embodiment provides a computer-readable storage medium on which an industrial robot joint fault prediction program is stored. When the industrial robot joint fault prediction program is executed by a processor, the following is achieved: Figure 1 The steps of any industrial robot joint fault prediction method.

[0153] Embodiment 4:

[0154] This embodiment provides a server 400, such as Figure 8 As shown, the server 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part to the random access memory (RAM) 403. Various programs and data required for system operation are also stored in the RAM 403. The CPU 401, ROM 402 and RAM 403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0155] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.

[0156] In particular, according to an embodiment of the present invention, the above reference Figure 1 The described processes may be implemented as computer software programs. For example, an embodiment of the present invention includes a computer program product comprising a computer program carried on a computer readable medium, the computer program including a computer program for executing Figure 1 In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 409 and / or installed from the removable medium 411 .

[0157] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0158] The flow chart and block diagram in the accompanying drawings illustrate the possible implementation architecture, function and operation of the method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0159] The units involved in the embodiments of the present invention may be implemented by software or hardware, and the units described may also be arranged in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves. The units or modules described may also be arranged in a processor, for example, they may be described as: a processor includes a first generation module, an acquisition module, a search module, a second generation module, and a merging module. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves, for example, the acquisition module may also be described as "an acquisition module for acquiring multiple instances to be detected in the basic table."

[0160] As another aspect, the present application also provides a computer-readable medium, which may be included in the server described in the above embodiment; or may exist independently without being installed in the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the smart device rental method described in the above embodiment. For example, the electronic device can implement Figure 1 The steps shown in .

[0161] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0162] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and its core ideas of this application. The above is only the preferred implementation method of this application. It should be pointed out that due to the limitations of textual expression and the objective existence of infinite specific structures, ordinary technicians in this technical field can make several improvements, modifications or changes without departing from the principles of the present invention, and can also combine the above technical features in an appropriate manner; these improvements, modifications, changes or combinations, or the direct application of the inventive concept and technical solution to other occasions without improvement, should be regarded as the scope of protection of this application.

Claims

1. A method for predicting joint failure of an industrial robot, characterized in that: include: S1, obtaining the original motor current signal of the motor directly connected to the harmonic reducer at the joint of the industrial robot; S2, filtering the original motor current signal to obtain a filtered current signal; S3, extracting the root mean square value from the filtered current signal as a characteristic index to characterize the harmonic reducer at the joint of the industrial robot, and writing the characteristic index into a data set Z form; S4. Establishing a degradation model for characterizing the harmonic reducer at the joint of the industrial robot under multiple working conditions, variable loads, and multiple-stage cycles, wherein the degradation model includes tasks at multiple stages; S5. Estimate the unknown parameters contained in each stage task; S6. Divide the failure threshold according to the characteristics of each stage task and form a threshold set ω ; S7, based on the degradation model and the threshold set ω , the expressions of probability density function and reliability function are obtained, and reliability evaluation is performed.

2. The method for predicting joint failure of an industrial robot according to claim 1, characterized in that: In step S2, the original motor current signal is processed by median filtering to obtain the filtered current signal.

3. The method for predicting joint failure of an industrial robot according to claim 1, characterized in that: In step S3, the data set Z is written in the following matrix expression: Where: z ij The system is j The second cycle i Data of the mission phase; i =1,2,3... m， m represents the number of task stages; j =1,2,3... n， n represents the number of loops.

4. The method for predicting joint failure of an industrial robot according to claim 1, characterized in that: In step S4, when the industrial robot works under multi-stage cycle and variable load conditions, the task stages of the harmonic reducer at the joints of the industrial robot are continuous and periodic, and the harmonic reducer has different degradation rates in different task stages. According to the degradation state changes of the harmonic reducer when performing multi-stage cycle tasks, the degradation model is established, and the degradation model is a nonlinear multi-stage task degradation model.

5. The method for predicting joint failure of an industrial robot according to claim 1, characterized in that: In step S5, the maximum likelihood estimation method is used to estimate the unknown parameters included in each stage.

6. The method for predicting joint failure of an industrial robot according to claim 1, characterized in that: In step S6, the threshold value set ω The expression is as follows: Where: ω i The system is i The system has a threshold of task stages. m A task phase.

7. The method for predicting joint failure of an industrial robot according to claim 6, characterized in that: In step S7, it is assumed that Z 1, Z 2, Z 3, …, Z m are independent random variables, then the probability density function expression is as follows: Where: ω 1, ω 2, ω 3, ..., ω m is the data in the threshold set; β i ( i =1,2,… m ) indicates the i The degradation rate of each task stage; t represents time; σ is the diffusion coefficient, which is used to describe the impact of external noise on product performance. Assuming that the product failure mechanism remains unchanged at different stress levels, σ constant, σB ( t ) is subject to N (0, σ 2 t ); The expression of the reliability function is as follows: Where: F ( ω 1, ω 2, …, ω i )for m dimensional random variable Z 1, Z 2, Z 3, …, Z m The joint distribution function of ω 1, ω 2, ω 3, ..., ω m is the data in the threshold set.

8. A terminal device, characterized in that: The terminal device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor; When the computer program is executed by the processor, the steps of the industrial robot joint failure prediction method according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an industrial robot joint fault prediction program, which, when executed by a processor, implements the steps of the industrial robot joint fault prediction method according to any one of claims 1 to 7.

Images