CN116787435A - Robot action intelligent monitoring system based on programming analysis - Google Patents
Robot action intelligent monitoring system based on programming analysis Download PDFInfo
- Publication number
- CN116787435A CN116787435A CN202310758765.0A CN202310758765A CN116787435A CN 116787435 A CN116787435 A CN 116787435A CN 202310758765 A CN202310758765 A CN 202310758765A CN 116787435 A CN116787435 A CN 116787435A
- Authority
- CN
- China
- Prior art keywords
- robot
- training
- value
- procedure
- analysis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 100
- 238000012544 monitoring process Methods 0.000 title claims abstract description 84
- 238000000034 method Methods 0.000 claims abstract description 319
- 238000012549 training Methods 0.000 claims abstract description 189
- 238000006243 chemical reaction Methods 0.000 claims abstract description 70
- 238000009776 industrial production Methods 0.000 claims abstract description 13
- 238000010276 construction Methods 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims description 39
- 238000011156 evaluation Methods 0.000 claims description 31
- 230000002159 abnormal effect Effects 0.000 claims description 28
- 238000004364 calculation method Methods 0.000 claims description 20
- 230000000903 blocking effect Effects 0.000 claims description 17
- 239000006185 dispersion Substances 0.000 claims description 11
- 230000001133 acceleration Effects 0.000 claims description 7
- 230000005764 inhibitory process Effects 0.000 claims description 7
- 238000006467 substitution reaction Methods 0.000 claims description 7
- 238000012854 evaluation process Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 abstract description 7
- 230000000875 corresponding effect Effects 0.000 description 160
- 230000009286 beneficial effect Effects 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1674—Programme controls characterised by safety, monitoring, diagnostic
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Numerical Control (AREA)
Abstract
The invention belongs to the technical field of robot supervision, in particular to a robot action intelligent monitoring system based on programming analysis, which comprises a monitoring analysis platform, a training procedure selection construction module, a robot training monitoring module, a robot auxiliary supervision module, a robot stability analysis module and an intelligent supervision terminal; according to the invention, the operation procedures in the corresponding industrial production are analyzed so that the procedure selection is more reasonable, the training operation is more targeted, the corresponding training procedure is monitored and marked as a non-conversion procedure, an examination procedure or a conversion procedure when the robot performs the corresponding training operation, the operation procedure suitable for the robot can be rapidly and accurately determined, the auxiliary supervision analysis is performed through the training operation process of the robot for the corresponding conversion procedure, the operation stability analysis is performed when the auxiliary supervision is judged to be normal, the operation quality of the robot can be comprehensively and accurately estimated, and the subsequent use and optimization of the robot are facilitated.
Description
Technical Field
The invention relates to the technical field of robot supervision, in particular to an intelligent robot action monitoring system based on programming analysis.
Background
The robot is an intelligent machine capable of semi-autonomous or fully autonomous working, the robot can perform tasks such as work or movement through programming and automatic control, with the development of artificial intelligence technology, the robot can understand the language of contexts and people, and becomes an important strength of the science and technology world, and the robot covers various fields such as production and manufacture, agriculture, medical treatment, service, traffic and military at present;
at present, when industrial production is carried out through robots, the robots are often directly subjected to corresponding programming programs to be put into corresponding working procedures for production operation, the corresponding operation working procedures are difficult to analyze and select before the robots are put into use, so that the robots are more reasonable and efficient to operate, the robots are not beneficial to carrying out targeted training operation, the operation quality of the robots cannot be comprehensively and accurately estimated when the training operation of the corresponding working procedures is carried out, and the subsequent put into use and optimization of the robots are not beneficial to the follow-up operation of the robots;
in view of the above technical drawbacks, a solution is now proposed.
Disclosure of Invention
The invention aims to provide a robot action intelligent monitoring system based on programming analysis, which solves the problems that the prior art is difficult to analyze and select corresponding operation procedures before the robot is put into use, the robot is not beneficial to carrying out targeted training operation, the operation quality of the robot cannot be comprehensively and accurately estimated during the training operation, and the follow-up use and optimization of the robot are not beneficial.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the intelligent robot action monitoring system based on programming analysis comprises a monitoring analysis platform, a training procedure selection construction module, a robot training monitoring module, a robot auxiliary supervision module, a robot stability analysis module and an intelligent supervision terminal;
the training procedure selection construction module analyzes the operation procedure in the corresponding industrial production to generate a procedure evaluation value of the corresponding operation procedure, compares the procedure evaluation value according to the procedure evaluation value, marks the corresponding operation procedure as a training procedure or a non-training procedure, constructs a training monitoring scene corresponding to the training procedure, and the monitoring analysis platform sends the training procedure and the corresponding training monitoring scene to the robot training monitoring module; the robot training monitoring module monitors the robot when the robot performs training operation of the corresponding training procedure, marks the corresponding training procedure as a non-conversion procedure, an examination procedure or a conversion procedure through analysis, generates a machine substitution signal corresponding to the conversion procedure and a signal to be optimized corresponding to the examination procedure, and sends the examination procedure and the signal to be optimized as well as the machine substitution signal and the corresponding conversion procedure to the intelligent supervision terminal through the monitoring analysis platform;
the robot auxiliary supervision module carries out auxiliary supervision analysis on the training operation process of the robot corresponding to the conversion process, judges whether the auxiliary supervision of the robot is abnormal or not through analysis, generates a robot improvement signal when judging that the auxiliary supervision is abnormal, generates a stability analysis signal when judging that the auxiliary supervision is normal, and sends the stability analysis signal to the robot stability analysis module through the monitoring analysis platform, and sends the robot improvement signal to the intelligent supervision terminal through the monitoring analysis platform; the robot operation stability analysis module carries out operation stability analysis on the training operation process of the robot corresponding to the conversion procedure after receiving the stability analysis signal, so as to judge whether the operation stability of the robot is abnormal, generate a robot improvement signal when judging that the operation stability is abnormal, generate an operation input signal when judging that the operation stability is normal, and send the robot improvement signal or the operation input signal to the intelligent supervision terminal through the monitoring analysis platform.
Further, the specific operation process of the training procedure selection construction module comprises:
obtaining operation procedures in corresponding industrial production, and marking the corresponding operation procedures as u, u= {1,2, …, m }, wherein m represents the number of the operation procedures in the corresponding industrial production and m is a natural number greater than 1; acquiring operation average input cost, operation average time consumption and operation average error frequency of an operation procedure u in a manual operation process, and carrying out weighting summation calculation on the operation average input cost, the operation average time consumption and the operation average error frequency to acquire a procedure evaluation value;
comparing the procedure evaluation value with a preset procedure evaluation threshold value, marking the corresponding operation procedure u as a training procedure if the procedure evaluation value exceeds the preset procedure evaluation threshold value, and marking the corresponding operation procedure u as a non-training procedure if the procedure evaluation value does not exceed the preset procedure evaluation threshold value; and constructing training monitoring scenes corresponding to the training procedures, sending all the training procedures and the corresponding training monitoring scenes to a monitoring analysis platform for storage, and sending the training procedures and the corresponding training monitoring scenes to a robot training monitoring module by the monitoring analysis platform.
Further, the specific operation process of the robot training monitoring module comprises the following steps:
when the robot performs training operation corresponding to a training procedure, acquiring the jamming times and each jamming time of the robot in the operation process, marking the jamming process exceeding a threshold value corresponding to the preset jamming time as a super jamming process, calculating the ratio of the super jamming time to the jamming time to obtain a super jamming frequency occupation value, summing all the jamming time to obtain an operation delay value, calculating the jamming time, the super jamming frequency occupation value and the operation delay value of the robot in the operation process to obtain a training obstruction coefficient, and comparing the training obstruction coefficient with the threshold value corresponding to the preset training obstruction coefficient;
if the training blocking coefficient exceeds a preset training blocking coefficient threshold value, judging that the corresponding training process is a non-conversion process; if the training blocking coefficient does not exceed the preset training blocking coefficient threshold, marking the corresponding training process as a preliminary qualified process, and performing process disassembly analysis on the preliminary qualified process; judging whether the corresponding primary qualified process is a non-conversion process, an evaluation process or a conversion process through process disassembly analysis, generating a machine substitution signal corresponding to the conversion process, and generating a signal to be optimized corresponding to the evaluation process.
Further, the specific analysis procedure of the process disassembly analysis is as follows:
dividing the corresponding preliminary qualified process into a plurality of operation steps based on a training monitoring scene, marking the corresponding operation steps as e, e= {1,2, …, k }, wherein k represents the number of operation steps in the corresponding preliminary qualified process and k is a natural number greater than 1; acquiring the completion time length of the robot in the corresponding operation step e and the interval engagement time length of the next operation step after the current operation step is completed when the robot performs the training operation corresponding to the preliminary qualified process, and judging that the training operation of the robot in the operation step e is unqualified if the completion time length is not in the preset completion time length range or the interval engagement time length is not in the preset interval engagement time length range;
if the completion time is within the preset completion time range and the interval engagement time is within the preset interval engagement time range, acquiring a speed deviation value, an acceleration deviation value and an angle deviation value of a corresponding limb joint of the robot in the corresponding operation step e, and carrying out normalization calculation on the speed deviation value, the acceleration deviation value and the angle deviation value of the corresponding limb joint to acquire an operation deviation coefficient; comparing the running deviation coefficient with a corresponding preset running deviation coefficient threshold value, if the running deviation coefficient exceeds the preset running deviation coefficient threshold value, judging that the training operation of the robot in the operation step e is not qualified, otherwise, judging that the training operation of the robot in the operation step e is qualified;
if the operation steps with unqualified training operation do not exist in the corresponding preliminary qualified working procedures, marking the corresponding preliminary qualified working procedures as conversion working procedures, if the operation steps with unqualified training operation exist in the preliminary qualified working procedures, acquiring the number of the operation steps with unqualified training operation and marking the number as XY1, and carrying out ratio calculation on XY1 and a numerical value k to acquire a non-sum occupying value XY2; carrying out numerical calculation through a formula XY=a1 xY1+a2 xXY 2 to obtain a conversion inhibition coefficient XY, marking the corresponding preliminary qualified process as a non-conversion process if XY is more than or equal to XYmax, and marking the corresponding preliminary qualified process as an consideration process if XY is less than XYmax; wherein XYmax represents a preset judgment threshold value of the conversion inhibition coefficient, and the value of XYmax is larger than zero; a1 and a2 are preset weight coefficients, and a2 > a1 > 1.
Further, the specific operation process of the robot auxiliary supervision module comprises the following steps:
setting a plurality of detection time points in the training operation process of the corresponding conversion process, marking the corresponding detection time points as i, i= {1,2, …, n }, wherein n represents the number of detection time points and n is a natural number larger than 1; acquiring noise decibel values generated during the training operation of the robot at the detection time point i, establishing a noise set of the noise decibel values at all the detection time points, carrying out mean value calculation and variance calculation on the noise set to obtain a noise average value and a noise dispersion value, and judging that the auxiliary supervision is abnormal and generating a robot improvement signal if the noise average value exceeds a preset noise average threshold value and the noise dispersion value does not exceed the preset noise dispersion threshold value;
the other cases are that a rectangular coordinate system positioned in a first quadrant is established by taking time as an X axis and taking noise decibel values as a Y axis, and the noise decibel values of all detection time points are marked into the rectangular coordinate system according to time sequence to form a plurality of noise coordinate points; taking (0, zymax) as an endpoint in a rectangular coordinate system as a ray parallel to an X axis, marking the ray as a noise early-warning ray, marking a noise coordinate point below the noise early-warning ray as a noise positive coordinate point, and marking the noise coordinate point above the noise early-warning ray as a noise super coordinate point; taking the corresponding noise coordinate point as an endpoint to downwards make a line segment perpendicular to the noise early warning ray, marking the line segment as a sound super line segment, and marking the length of the sound super line segment as a sound super distance;
summing all the ultrasonic distances, taking an average value to obtain an ultrasonic coefficient TQ1, calculating the ratio of the number of the ultrasonic coordinate points to the number of the positive coordinate points to obtain a noise analysis value TQ2, and analyzing and calculating the noise analysis value TQ2 through a formula TQ=b1+b2 to obtain an auxiliary pipe coefficient TQ; if the TQ is more than or equal to TQmax, judging that the auxiliary supervision is abnormal and generating a robot improvement signal, if the TQ is less than TQmax, judging that the auxiliary supervision is normal and generating a stability analysis signal, and transmitting the stability analysis signal to a robot stability analysis module through a monitoring analysis platform; wherein TQmax is a preset judgment threshold value of the auxiliary pipe coefficient TQ, the value of TQmax is larger than zero, b1 and b2 are preset weight coefficients, and b2 is larger than b1 and larger than 0.
Further, the specific operation process of the robot stability analysis module comprises the following steps:
after receiving a stability analysis signal of the robot in a corresponding conversion procedure, acquiring a three-way fluctuation value of a body when the robot at a detection time point i trains and operates, wherein the three-way fluctuation value comprises an X-direction fluctuation value, a Y-direction fluctuation value and a Z-direction fluctuation value; if at least one line in the X-direction fluctuation value, the Y-direction fluctuation value and the Z-direction fluctuation value exceeds a corresponding preset fluctuation threshold value, a fluctuation judgment symbol BD-1 is given to a corresponding detection time point i; if the X-direction fluctuation value, the Y-direction fluctuation value and the Z-direction fluctuation value do not exceed the corresponding preset fluctuation threshold values, carrying out numerical calculation on the X-direction fluctuation value, the Y-direction fluctuation value and the Z-direction fluctuation value to obtain three-way fluctuation coefficients, carrying out numerical comparison on the three-way fluctuation coefficients and the corresponding preset three-way fluctuation coefficient threshold values, if the three-way fluctuation coefficients exceed the preset three-way fluctuation coefficient threshold values, giving a fluctuation judgment symbol BD-1 to the corresponding detection time point i, and if the three-way fluctuation coefficients do not exceed the preset three-way fluctuation coefficient threshold values, giving a fluctuation judgment symbol BD-2 to the corresponding detection time point i;
acquiring detection time points of all corresponding fluctuation judgment symbols BD-2, marking the detection time points as unstable time points, marking the maximum continuous quantity of the unstable time points as KQ1, and calculating the ratio of the quantity of the unstable time points to a numerical value n to acquire an unstable number occupation value KQ2; calculating and analyzing through a formula KQ=hp1, KQ 1+h2 and KQ2 to obtain a stability negative coefficient KQ, judging that the operation stability is abnormal and generating a robot improvement signal if KQ is more than or equal to KQmax, and judging that the operation stability is normal and generating a put-into-use signal if KQ is less than KQmax; wherein KQmax is a preset judgment threshold value of a stability negative coefficient KQ, the value of KQmax is larger than zero, hp1 and hp2 are preset weight coefficients, and h2 is larger than hp1 and larger than 0.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the invention, the operation procedures in the corresponding industrial production are analyzed to be marked as training procedures or non-training procedures, the robot is used for training operation of the corresponding training procedures, the procedure selection is more reasonable, and the training operation of the robot is more targeted; the robot is monitored when the robot performs training operation of the corresponding training process, and the corresponding training process is marked as a non-conversion process, an examination process or a conversion process through analysis, so that a machine replacement signal of the corresponding conversion process and a signal to be optimized of the corresponding examination process are generated, and the robot is preferably applied to the corresponding conversion process, so that the operation process suitable for the robot can be rapidly and accurately determined, and the follow-up robot is beneficial to the application and use of the robot;
2. according to the invention, the robot is subjected to auxiliary supervision analysis in the training operation process of the corresponding conversion process so as to judge whether the auxiliary supervision of the robot is abnormal, a robot improvement signal is generated when the auxiliary supervision is abnormal, and the robot is subjected to operation stability analysis in the training operation process of the corresponding conversion process when the auxiliary supervision is normal, so that whether the operation stability of the robot is abnormal is judged, the operation quality of the robot can be comprehensively and accurately evaluated when the robot is subjected to the training operation of the corresponding conversion process, the intelligent degree is high, and the subsequent use and optimization of the robot are facilitated.
Drawings
For the convenience of those skilled in the art, the present invention will be further described with reference to the accompanying drawings;
fig. 1 is an overall system block diagram of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment one: as shown in fig. 1, the intelligent robot action monitoring system based on programming analysis provided by the invention comprises a monitoring analysis platform, a training procedure selection building module, a robot training monitoring module and an intelligent supervision terminal, wherein the monitoring analysis platform is in communication connection with the training procedure selection building module, the robot training monitoring module and the intelligent supervision terminal;
the training procedure selection construction module analyzes the operation procedure in the corresponding industrial production to generate a procedure evaluation value of the corresponding operation procedure, compares the procedure evaluation value according to the procedure evaluation value, marks the corresponding operation procedure as a training procedure or a non-training procedure, constructs a training monitoring scene corresponding to the training procedure, programs the corresponding action of the robot, and sends the training procedure and the corresponding training monitoring scene to the robot training monitoring module; the specific operation process is as follows:
obtaining operation procedures in corresponding industrial production, and marking the corresponding operation procedures as u, u= {1,2, …, m }, wherein m represents the number of the operation procedures in the corresponding industrial production and m is a natural number greater than 1; the average operation input cost, the average operation time and the average operation error frequency of the operation procedure u in the manual operation process are collected, and the operation process is carried out according to the formulaThe operation average input cost CBu, the operation average time consumption HSu and the operation average error frequency CPu are weighted and calculated to obtain a procedure evaluation value GPu; fq1, fq2 and fq3 are preset weight coefficients, and fq3 is more than fq1 and more than fq2 and more than 0; the larger the number of the process evaluation value GPu corresponding to the operation process u, the more unsuitable the manual operation of the corresponding operation process u, and the more suitable the robot replacement;
numerical comparison is performed between the process evaluation value GPu of the corresponding operation process u and a preset process evaluation threshold, if the process evaluation value GPu exceeds the preset process evaluation threshold, the corresponding operation process u is marked as a training process, and if the process evaluation value GPu does not exceed the preset process evaluation threshold, the corresponding operation process u is marked as a non-training process; the training monitoring scenes are constructed corresponding to the training procedures, all the training procedures and the corresponding training monitoring scenes are sent to the monitoring analysis platform for storage, the monitoring analysis platform sends the training procedures and the corresponding training monitoring scenes to the robot training monitoring module, so that the robot is required to perform training operation corresponding to the training procedures, whether the corresponding robot can effectively complete production work of the corresponding procedures is judged, the procedure selection is more reasonable, and the training operation of the robot is more targeted.
The robot training monitoring module monitors the corresponding training process when the robot performs training operation of the corresponding training process, marks the corresponding training process as a non-conversion process, an examination process or a conversion process through analysis, generates a machine replacement signal corresponding to the conversion process and a signal to be optimized corresponding to the examination process, sends the examination process and the signal to be optimized, the machine replacement signal and the corresponding conversion process to the intelligent monitoring terminal through the monitoring analysis platform, and the corresponding monitoring personnel can preferably apply the robot to the corresponding conversion process after receiving the machine replacement signal, correspondingly optimizes the program and the structure of the robot according to the need after receiving the signal to be optimized so as to effectively adapt to the corresponding examination process, and then puts the robot into the corresponding examination process according to the need to perform production work, so that the applicable operation process of the robot can be quickly and accurately determined, and the subsequent application of the robot is facilitated; the specific operation process of the robot training monitoring module is as follows:
when the robot performs training operation corresponding to the training procedure, the jamming times of the robot in the operation process and the jamming time of each time are collected, the jamming process exceeding the threshold value of the corresponding preset jamming time is marked as an overtaking process, the ratio of the overtaking process times to the jamming times is calculated to obtain an overtaking frequency occupation value, all the jamming time is summed to obtain an operation delay value, and a normalization analysis formula is adoptedCarrying out numerical calculation on the blocking times KDu, the super-blocking frequency occupation value KPu and the operation delay value YSu of the robot in the operation process to obtain a training blocking coefficient XZu, wherein up1, up2 and up3 are preset weight coefficients, and up2 is larger than up1 and larger than up3 and larger than 0;
the larger the value of the training inhibition coefficient XZu is, the larger the operation inhibition of the robot in the corresponding training procedure is, and the smoother the operation is; comparing the training blocking coefficient XZu with a corresponding preset training blocking coefficient threshold value, and judging that the corresponding training process is a non-conversion process if the training blocking coefficient XZu exceeds the preset training blocking coefficient threshold value, which indicates that the robot is difficult to effectively complete the production work of the corresponding training process; if the training blocking coefficient XZu does not exceed the preset training blocking coefficient threshold, marking the corresponding training process as a preliminary qualified process, and performing process disassembly analysis on the preliminary qualified process; the method comprises the following steps: dividing the corresponding preliminary qualified process into a plurality of operation steps based on a training monitoring scene, marking the corresponding operation steps as e, e= {1,2, …, k }, wherein k represents the number of operation steps in the corresponding preliminary qualified process and k is a natural number greater than 1;
acquiring the completion time length of the robot in the corresponding operation step e and the interval engagement time length of the next operation step after the current operation step is completed when the robot performs training operation corresponding to the preliminary qualified process, respectively performing numerical comparison on the completion time length and the interval engagement time length with corresponding preset completion time length threshold values and preset interval engagement time length threshold values, and judging that the training operation of the robot in the operation step e is unqualified if the completion time length is not in the preset completion time length range or the interval engagement time length is not in the preset interval engagement time length range; if the completion time is within the preset completion time range and the interval engagement time is within the preset interval engagement time range, acquiring a speed deviation value, an acceleration deviation value and an angle deviation value of a corresponding limb joint of the robot in the corresponding operation step e; the speed deviation value is a data value representing the speed deviation degree in the corresponding operation process, the smaller the speed deviation value is, the better the robot completes the action corresponding to the operation step, and the acceleration deviation value and the angle deviation value corresponding to the limb joint can be known in the same way;
carrying out normalization calculation on the speed deviation value WSue, the acceleration deviation value WJue and the angle deviation value WDue of the corresponding limb joint through a formula HYue=t1, WSue+t2, WJue+t3, and obtaining an operation deviation coefficient HYue; wherein t1, t2 and t3 are preset weight coefficients, and the values of t1, t2 and t3 are all larger than zero; and the larger the value of the running deviation coefficient HYue is, the better the running effect of the robot in the corresponding operation step e is; comparing the running deviation coefficient HYue with a corresponding preset running deviation coefficient threshold value, if the running deviation coefficient HYue exceeds the preset running deviation coefficient threshold value, judging that the training operation of the robot in the operation step e is unqualified, and if the running deviation coefficient HYue does not exceed the preset running deviation coefficient threshold value, judging that the training operation of the robot in the operation step e is qualified;
if the operation steps of unqualified training operation do not exist in the corresponding primary qualified working procedures, the robot can be well adapted to the corresponding primary qualified working procedures, the corresponding primary qualified working procedures are marked as conversion working procedures, and a machine substitution signal corresponding to the conversion working procedures is generated; if the operation steps with unqualified training operation exist in the primary qualified working procedure, the number of the operation steps with unqualified training operation is collected and marked as XY1, and the ratio of XY1 to the value k is calculated to obtain a non-composite number occupation value XY2; obtaining a conversion blocking coefficient XY through numerical calculation of a formula XY=a1 xXY 1+a2 xXY 2, wherein a1 and a2 are preset weight coefficients and a2 is larger than a1 and larger than 1; comparing XY with XYmax in value, wherein XYmax represents a preset judgment threshold value of the conversion inhibition coefficient, and the value of XYmax is larger than zero; if XY is more than or equal to XYmax, the robot is difficult to effectively adapt to the corresponding primary qualified process, and the corresponding primary qualified process is marked as a non-conversion process; and if XY is less than XYmax, marking the corresponding primary qualified process as the considered process and generating a signal to be optimized corresponding to the considered process.
Embodiment two: as shown in fig. 1, the difference between the present embodiment and embodiment 1 is that the monitoring and analyzing platform is in communication connection with the robot auxiliary supervision module, the monitoring and analyzing platform sends the conversion procedure to the robot auxiliary supervision module, the robot auxiliary supervision module performs auxiliary supervision analysis on the training operation process of the robot corresponding to the conversion procedure, determines whether the auxiliary supervision of the robot is abnormal through the analysis, generates a robot improvement signal when the auxiliary supervision is abnormal, sends the robot improvement signal to the intelligent supervision terminal through the monitoring and analyzing platform, and should perform inspection optimization of the robot in time after receiving the robot improvement signal to ensure the smoothness of the put into operation; the specific operation process of the robot auxiliary supervision module is as follows:
setting a plurality of detection time points in the training operation process of the corresponding conversion process, marking the corresponding detection time points as i, i= {1,2, …, n }, wherein n represents the number of detection time points and n is a natural number larger than 1; the noise decibel value generated during the robot training operation at the detection time point i is collected, and the larger the value of the noise decibel value is, the greater the possibility of abnormal operation of the robot is indicated; establishing a noise set from the noise decibel values of all the detection time points, and carrying out mean value calculation and variance calculation on the noise set to obtain a noise mean value and a noise dispersion value, wherein the noise dispersion value is a data value representing the degree of deviation between the noise decibel values generated by each detection time point, and the smaller the value of the noise dispersion value is, the closer the noise condition generated by each detection time point is; if the average noise value exceeds the preset average noise threshold value and the noise dispersion value does not exceed the preset noise dispersion threshold value, indicating that the training running condition of the robot in the corresponding conversion process is poor as a whole, judging that the auxiliary supervision is abnormal and generating a robot improvement signal;
the other cases are that a rectangular coordinate system positioned in a first quadrant is established by taking time as an X axis and taking noise decibel values as a Y axis, and the noise decibel values of all detection time points are marked into the rectangular coordinate system according to time sequence to form a plurality of noise coordinate points; taking (0, zymax) as an endpoint in a rectangular coordinate system as a ray parallel to an X axis, marking the ray as a noise early-warning ray, marking a noise coordinate point below the noise early-warning ray as a noise positive coordinate point, and marking the noise coordinate point above the noise early-warning ray as a noise super coordinate point; taking the corresponding noise coordinate point as an endpoint to downwards make a line segment perpendicular to the noise early warning ray, marking the line segment as a sound super line segment, and marking the length of the sound super line segment as a sound super distance; the larger the value of the sound-to-sound distance is, the larger the noise deviation degree corresponding to the detection time point is, and the worse the generated noise condition is;
summing all the ultrasonic distances, taking an average value to obtain an ultrasonic coefficient TQ1, calculating the ratio of the number of the ultrasonic coordinate points to the number of the positive coordinate points to obtain a noise analysis value TQ2, and analyzing and calculating the noise analysis value TQ2 through a formula TQ=b1+b2 to obtain an auxiliary pipe coefficient TQ; wherein b1 and b2 are preset weight coefficients, and b2 is more than b1 and more than 0; the numerical value of the auxiliary pipe coefficient TQ is in a direct proportion relation with the ultrasonic coefficient TQ1 and the noise analysis value TQ2, and the larger the numerical value of the auxiliary pipe coefficient TQ is, the worse the training operation condition of the robot for carrying out the corresponding conversion process is indicated; and comparing the TQ with the TQmax in a numerical value, wherein the TQmax is a preset judging threshold value of the auxiliary pipe coefficient TQ, the value of the TQmax is larger than zero, if the TQ is larger than or equal to the TQmax, the auxiliary supervision is abnormal, a robot improvement signal is generated, and if the TQ is smaller than the TQmax, the auxiliary supervision is normal.
Embodiment III: as shown in fig. 1, the difference between the present embodiment and embodiments 1 and 2 is that the monitoring and analyzing platform is in communication connection with the robot operation stability analyzing module, the robot auxiliary monitoring module generates a stability analyzing signal when the auxiliary monitoring is normal, and sends the stability analyzing signal to the robot operation stability analyzing module through the monitoring and analyzing platform, the robot operation stability analyzing module carries out operation stability analysis on the training operation process of the robot corresponding to the conversion process after receiving the stability analyzing signal, so as to determine whether the operation stability of the robot is abnormal, generates a robot improvement signal when the operation stability is abnormal, generates an input operation signal when the operation stability is normal, sends the robot improvement signal or the input operation signal to the intelligent monitoring and analyzing terminal through the monitoring and analyzing platform, can select to input the robot into the corresponding conversion process for use after receiving the input operation signal, and should timely carry out inspection and optimization of the robot after receiving the robot improvement signal so as to ensure the stability of the input operation; the specific analysis process of the operation stability analysis is as follows:
after receiving a stability analysis signal of a robot in a corresponding conversion procedure, acquiring a three-way fluctuation value of a body when the robot at a detection time point i trains and operates, wherein the three-way fluctuation value comprises an X-direction fluctuation value, a Y-direction fluctuation value and a Z-direction fluctuation value, the fluctuation value is a data magnitude value representing the sum value of a corresponding direction shaking frequency and a shaking amplitude, and the larger the shaking amplitude and the shaking frequency, the larger the corresponding fluctuation value; respectively carrying out numerical comparison on the X-direction fluctuation value, the Y-direction fluctuation value and the Z-direction fluctuation value with corresponding preset X-direction fluctuation threshold, preset Y-direction fluctuation threshold and preset Z-direction fluctuation threshold, and if at least one line in the X-direction fluctuation value, the Y-direction fluctuation value and the Z-direction fluctuation value exceeds the corresponding preset fluctuation threshold, giving a fluctuation judgment symbol BD-1 to a corresponding detection time point i;
if the X-direction fluctuation value, the Y-direction fluctuation value and the Z-direction fluctuation value do not exceed the corresponding preset fluctuation threshold values, the method passes through the formulaCarrying out numerical calculation on an X-direction fluctuation value BTxi, a Y-direction fluctuation value BTyi and a Z-direction fluctuation value BTzi to obtain a three-way fluctuation coefficient SBi, wherein es1, es2 and es3 are preset weight coefficients, and the values of es1, es2 and es3 are all larger than zero; and, the larger the numerical value of the three-way fluctuation coefficient SBi is, the more unstable the robot operation is; numerical comparison is carried out on the three-way fluctuation coefficient SBi and a corresponding preset three-way fluctuation coefficient threshold value, if the three-way fluctuation coefficient SBi exceeds the preset three-way fluctuation coefficient threshold value, a fluctuation judgment symbol BD-1 is given to a corresponding detection time point i, and if the three-way fluctuation coefficient SBi does not exceed the preset three-way fluctuation coefficient threshold value, a fluctuation judgment symbol BD-2 is given to the corresponding detection time point i;
acquiring detection time points of all corresponding fluctuation judgment symbols BD-2, marking the detection time points as unstable time points, marking the maximum continuous quantity of the unstable time points as KQ1, and calculating the ratio of the quantity of the unstable time points to a numerical value n to acquire an unstable number occupation value KQ2; calculating and analyzing by a formula KQ=hp1 xKQ1+hp2 xKQ2 to obtain a stability negative coefficient KQ, wherein hp1 and hp2 are preset weight coefficients, h2 is larger than hp1 and larger the value of the stability negative coefficient KQ is, the worse the stability condition of the robot in the training operation process corresponding to the conversion procedure is; and comparing the KQ with KQmax, wherein KQmax is a preset judgment threshold value of the stability negative coefficient KQ, the KQmax is larger than zero, if KQ is larger than or equal to KQmax, the operation stability is judged to be abnormal, a robot improvement signal is generated, and if KQ is smaller than KQmax, the operation stability is judged to be normal, and a put-into-operation signal is generated.
When the robot is used, the operation procedures in corresponding industrial production are analyzed through the training procedure selection construction module to mark the corresponding operation procedures as training procedures or non-training procedures, and the standby robot is used for training operation of the corresponding training procedures, so that whether the corresponding robot can effectively finish production work of the corresponding procedures or not is judged, the procedure selection is more reasonable, and the training operation of the robot is more targeted; the robot training monitoring module monitors the robot when the robot performs training operation of the corresponding training process, and generates a machine replacing signal corresponding to the conversion process and a signal to be optimized corresponding to the conversion process by analyzing the corresponding training process to be marked as a non-conversion process, an examination process or a conversion process, preferably, the robot is applied to the corresponding conversion process, so that the operation process suitable for the robot can be rapidly and accurately determined, and the follow-up robot is beneficial to being put into use; and carrying out auxiliary supervision analysis on the training operation process of the robot corresponding to the conversion process through the robot auxiliary supervision module so as to judge whether the auxiliary supervision of the robot is abnormal, generating a robot improvement signal when the auxiliary supervision is abnormal, carrying out operation stability analysis on the training operation process of the robot corresponding to the conversion process through the robot operation stability analysis module when the auxiliary supervision is normal, judging whether the operation stability of the robot is abnormal and generating an operation input signal or a robot improvement signal according to the operation stability, and comprehensively and accurately evaluating the operation quality of the robot when the robot carries out the training operation corresponding to the conversion process, wherein the intelligent degree is high, so that the follow-up operation and optimization of the robot are more facilitated.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation. The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (6)
1. The intelligent robot action monitoring system based on programming analysis is characterized by comprising a monitoring analysis platform, a training procedure selection construction module, a robot training monitoring module, a robot auxiliary supervision module, a robot stability analysis module and an intelligent supervision terminal;
the training procedure selection construction module analyzes the operation procedure in the corresponding industrial production to generate a procedure evaluation value of the corresponding operation procedure, compares the procedure evaluation value according to the procedure evaluation value, marks the corresponding operation procedure as a training procedure or a non-training procedure, constructs a training monitoring scene corresponding to the training procedure, and the monitoring analysis platform sends the training procedure and the corresponding training monitoring scene to the robot training monitoring module; the robot training monitoring module monitors the robot when the robot performs training operation of the corresponding training procedure, marks the corresponding training procedure as a non-conversion procedure, an examination procedure or a conversion procedure through analysis, generates a machine substitution signal corresponding to the conversion procedure and a signal to be optimized corresponding to the examination procedure, and sends the examination procedure and the signal to be optimized as well as the machine substitution signal and the corresponding conversion procedure to the intelligent supervision terminal through the monitoring analysis platform;
the robot auxiliary supervision module carries out auxiliary supervision analysis on the training operation process of the robot corresponding to the conversion process, judges whether the auxiliary supervision of the robot is abnormal or not through analysis, generates a robot improvement signal when judging that the auxiliary supervision is abnormal, generates a stability analysis signal when judging that the auxiliary supervision is normal, and sends the stability analysis signal to the robot stability analysis module through the monitoring analysis platform, and sends the robot improvement signal to the intelligent supervision terminal through the monitoring analysis platform; the robot operation stability analysis module carries out operation stability analysis on the training operation process of the robot corresponding to the conversion procedure after receiving the stability analysis signal, so as to judge whether the operation stability of the robot is abnormal, generate a robot improvement signal when judging that the operation stability is abnormal, generate an operation input signal when judging that the operation stability is normal, and send the robot improvement signal or the operation input signal to the intelligent supervision terminal through the monitoring analysis platform.
2. The intelligent robot motion monitoring system based on programming analysis of claim 1, wherein the specific operation of the training process selection building block comprises:
obtaining operation procedures in corresponding industrial production, and marking the corresponding operation procedures as u, u= {1,2, …, m }, wherein m represents the number of the operation procedures in the corresponding industrial production and m is a natural number greater than 1; acquiring operation average input cost, operation average time consumption and operation average error frequency of an operation procedure u in a manual operation process, and carrying out weighting summation calculation on the operation average input cost, the operation average time consumption and the operation average error frequency to acquire a procedure evaluation value;
comparing the procedure evaluation value with a preset procedure evaluation threshold value, marking the corresponding operation procedure u as a training procedure if the procedure evaluation value exceeds the preset procedure evaluation threshold value, and marking the corresponding operation procedure u as a non-training procedure if the procedure evaluation value does not exceed the preset procedure evaluation threshold value; and constructing training monitoring scenes corresponding to the training procedures, sending all the training procedures and the corresponding training monitoring scenes to a monitoring analysis platform for storage, and sending the training procedures and the corresponding training monitoring scenes to a robot training monitoring module by the monitoring analysis platform.
3. The intelligent robot motion monitoring system based on programming analysis of claim 2, wherein the specific operation process of the robot training monitoring module comprises:
when the robot performs training operation corresponding to a training procedure, acquiring the jamming times and each jamming time of the robot in the operation process, marking the jamming process exceeding a threshold value corresponding to the preset jamming time as a super jamming process, calculating the ratio of the super jamming time to the jamming time to obtain a super jamming frequency occupation value, summing all the jamming time to obtain an operation delay value, calculating the jamming time, the super jamming frequency occupation value and the operation delay value of the robot in the operation process to obtain a training obstruction coefficient, and comparing the training obstruction coefficient with the threshold value corresponding to the preset training obstruction coefficient;
if the training blocking coefficient exceeds a preset training blocking coefficient threshold value, judging that the corresponding training process is a non-conversion process; if the training blocking coefficient does not exceed the preset training blocking coefficient threshold, marking the corresponding training process as a preliminary qualified process, and performing process disassembly analysis on the preliminary qualified process; judging whether the corresponding primary qualified process is a non-conversion process, an evaluation process or a conversion process through process disassembly analysis, generating a machine substitution signal corresponding to the conversion process, and generating a signal to be optimized corresponding to the evaluation process.
4. A robot motion intelligent monitoring system based on programming analysis according to claim 3, wherein the specific analysis process of the process disassembly analysis is as follows:
dividing the corresponding preliminary qualified process into a plurality of operation steps based on a training monitoring scene, marking the corresponding operation steps as e, e= {1,2, …, k }, wherein k represents the number of operation steps in the corresponding preliminary qualified process and k is a natural number greater than 1; acquiring the completion time length of the robot in the corresponding operation step e and the interval engagement time length of the next operation step after the current operation step is completed when the robot performs the training operation corresponding to the preliminary qualified process, and judging that the training operation of the robot in the operation step e is unqualified if the completion time length is not in the preset completion time length range or the interval engagement time length is not in the preset interval engagement time length range;
if the completion time is within the preset completion time range and the interval engagement time is within the preset interval engagement time range, acquiring a speed deviation value, an acceleration deviation value and an angle deviation value of a corresponding limb joint of the robot in the corresponding operation step e, and carrying out normalization calculation on the speed deviation value, the acceleration deviation value and the angle deviation value of the corresponding limb joint to acquire an operation deviation coefficient; comparing the running deviation coefficient with a corresponding preset running deviation coefficient threshold value, if the running deviation coefficient exceeds the preset running deviation coefficient threshold value, judging that the training operation of the robot in the operation step e is not qualified, otherwise, judging that the training operation of the robot in the operation step e is qualified;
if the operation steps with unqualified training operation do not exist in the corresponding preliminary qualified working procedures, marking the corresponding preliminary qualified working procedures as conversion working procedures, if the operation steps with unqualified training operation exist in the preliminary qualified working procedures, acquiring the number of the operation steps with unqualified training operation and marking the number as XY1, and carrying out ratio calculation on XY1 and a numerical value k to acquire a non-sum occupying value XY2; carrying out numerical calculation through a formula XY=a1 xY1+a2 xXY 2 to obtain a conversion inhibition coefficient XY, marking the corresponding preliminary qualified process as a non-conversion process if XY is more than or equal to XYmax, and marking the corresponding preliminary qualified process as an consideration process if XY is less than XYmax; wherein XYmax represents a preset judgment threshold value of the conversion inhibition coefficient, and the value of XYmax is larger than zero; a1 and a2 are preset weight coefficients, and a2 > a1 > 1.
5. The intelligent robot motion monitoring system based on programming analysis of claim 1, wherein the specific operation process of the robot-assisted supervision module comprises:
setting a plurality of detection time points in the training operation process of the corresponding conversion process, marking the corresponding detection time points as i, i= {1,2, …, n }, wherein n represents the number of detection time points and n is a natural number larger than 1; acquiring noise decibel values generated during the training operation of the robot at the detection time point i, establishing a noise set of the noise decibel values at all the detection time points, carrying out mean value calculation and variance calculation on the noise set to obtain a noise average value and a noise dispersion value, and judging that the auxiliary supervision is abnormal and generating a robot improvement signal if the noise average value exceeds a preset noise average threshold value and the noise dispersion value does not exceed the preset noise dispersion threshold value;
the other cases are that a rectangular coordinate system positioned in a first quadrant is established by taking time as an X axis and taking noise decibel values as a Y axis, and the noise decibel values of all detection time points are marked into the rectangular coordinate system according to time sequence to form a plurality of noise coordinate points; taking (0, zymax) as an endpoint in a rectangular coordinate system as a ray parallel to an X axis, marking the ray as a noise early-warning ray, marking a noise coordinate point below the noise early-warning ray as a noise positive coordinate point, and marking the noise coordinate point above the noise early-warning ray as a noise super coordinate point; taking the corresponding noise coordinate point as an endpoint to downwards make a line segment perpendicular to the noise early warning ray, marking the line segment as a sound super line segment, and marking the length of the sound super line segment as a sound super distance;
summing all the ultrasonic distances, taking an average value to obtain an ultrasonic coefficient TQ1, calculating the ratio of the number of the ultrasonic coordinate points to the number of the positive coordinate points to obtain a noise analysis value TQ2, and analyzing and calculating the noise analysis value TQ2 through a formula TQ=b1+b2 to obtain an auxiliary pipe coefficient TQ; if the TQ is more than or equal to TQmax, judging that the auxiliary supervision is abnormal and generating a robot improvement signal, if the TQ is less than TQmax, judging that the auxiliary supervision is normal and generating a stability analysis signal, and transmitting the stability analysis signal to a robot stability analysis module through a monitoring analysis platform; wherein TQmax is a preset judgment threshold value of the auxiliary pipe coefficient TQ, the value of TQmax is larger than zero, b1 and b2 are preset weight coefficients, and b2 is larger than b1 and larger than 0.
6. The intelligent robot motion monitoring system based on programming analysis of claim 5, wherein the specific operation process of the robot stability analysis module comprises:
after receiving a stability analysis signal of the robot in a corresponding conversion procedure, acquiring a three-way fluctuation value of a body when the robot at a detection time point i trains and operates, wherein the three-way fluctuation value comprises an X-direction fluctuation value, a Y-direction fluctuation value and a Z-direction fluctuation value; if at least one line in the X-direction fluctuation value, the Y-direction fluctuation value and the Z-direction fluctuation value exceeds a corresponding preset fluctuation threshold value, a fluctuation judgment symbol BD-1 is given to a corresponding detection time point i; if the X-direction fluctuation value, the Y-direction fluctuation value and the Z-direction fluctuation value do not exceed the corresponding preset fluctuation threshold values, carrying out numerical calculation on the X-direction fluctuation value, the Y-direction fluctuation value and the Z-direction fluctuation value to obtain three-way fluctuation coefficients, carrying out numerical comparison on the three-way fluctuation coefficients and the corresponding preset three-way fluctuation coefficient threshold values, if the three-way fluctuation coefficients exceed the preset three-way fluctuation coefficient threshold values, giving a fluctuation judgment symbol BD-1 to the corresponding detection time point i, and if the three-way fluctuation coefficients do not exceed the preset three-way fluctuation coefficient threshold values, giving a fluctuation judgment symbol BD-2 to the corresponding detection time point i;
acquiring detection time points of all corresponding fluctuation judgment symbols BD-2, marking the detection time points as unstable time points, marking the maximum continuous quantity of the unstable time points as KQ1, and calculating the ratio of the quantity of the unstable time points to a numerical value n to acquire an unstable number occupation value KQ2; calculating and analyzing through a formula KQ=hp1, KQ 1+h2 and KQ2 to obtain a stability negative coefficient KQ, judging that the operation stability is abnormal and generating a robot improvement signal if KQ is more than or equal to KQmax, and judging that the operation stability is normal and generating a put-into-use signal if KQ is less than KQmax; wherein KQmax is a preset judgment threshold value of a stability negative coefficient KQ, the value of KQmax is larger than zero, hp1 and hp2 are preset weight coefficients, and h2 is larger than hp1 and larger than 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310758765.0A CN116787435A (en) | 2023-06-26 | 2023-06-26 | Robot action intelligent monitoring system based on programming analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310758765.0A CN116787435A (en) | 2023-06-26 | 2023-06-26 | Robot action intelligent monitoring system based on programming analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116787435A true CN116787435A (en) | 2023-09-22 |
Family
ID=88035931
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310758765.0A Pending CN116787435A (en) | 2023-06-26 | 2023-06-26 | Robot action intelligent monitoring system based on programming analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116787435A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117713630A (en) * | 2024-02-06 | 2024-03-15 | 深圳威洛博机器人有限公司 | Control system for speed fluctuation of robot transmission motor |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20070087139A (en) * | 2007-07-18 | 2007-08-27 | 한국표준과학연구원 | A precision diagnostic method for the failure protection and predictive maintenance of a vacuum pump and a precision diagnostic system therefor |
| CN114330545A (en) * | 2021-12-28 | 2022-04-12 | 花脸数字技术(杭州)有限公司 | Digital human dynamic capture analysis system based on ik algorithm |
| WO2023040575A1 (en) * | 2021-09-17 | 2023-03-23 | 中通服和信科技有限公司 | Internet-of-things-based abnormality early warning analysis system and method for special operation site |
| CN115903707A (en) * | 2022-12-01 | 2023-04-04 | 苏州连讯电子有限公司 | Connecting line production optimization method and system based on station monitoring |
| CN116184926A (en) * | 2023-04-21 | 2023-05-30 | 山东力乐新材料有限公司 | Full-automatic intelligent production line flow detection system for plastic hollow plate |
-
2023
- 2023-06-26 CN CN202310758765.0A patent/CN116787435A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20070087139A (en) * | 2007-07-18 | 2007-08-27 | 한국표준과학연구원 | A precision diagnostic method for the failure protection and predictive maintenance of a vacuum pump and a precision diagnostic system therefor |
| WO2023040575A1 (en) * | 2021-09-17 | 2023-03-23 | 中通服和信科技有限公司 | Internet-of-things-based abnormality early warning analysis system and method for special operation site |
| CN114330545A (en) * | 2021-12-28 | 2022-04-12 | 花脸数字技术(杭州)有限公司 | Digital human dynamic capture analysis system based on ik algorithm |
| CN115903707A (en) * | 2022-12-01 | 2023-04-04 | 苏州连讯电子有限公司 | Connecting line production optimization method and system based on station monitoring |
| CN116184926A (en) * | 2023-04-21 | 2023-05-30 | 山东力乐新材料有限公司 | Full-automatic intelligent production line flow detection system for plastic hollow plate |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117713630A (en) * | 2024-02-06 | 2024-03-15 | 深圳威洛博机器人有限公司 | Control system for speed fluctuation of robot transmission motor |
| CN117713630B (en) * | 2024-02-06 | 2024-06-07 | 深圳威洛博机器人有限公司 | Control system for speed fluctuation of robot transmission motor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111913803B (en) | Service load fine granularity prediction method based on AKX hybrid model | |
| CN116787435A (en) | Robot action intelligent monitoring system based on programming analysis | |
| CN108090515B (en) | Data fusion-based environment grade evaluation method | |
| WO2021109180A1 (en) | Sewage treatment process fault monitoring method based on fuzzy width adaptive learning model | |
| CN106934242A (en) | The health degree appraisal procedure and system of equipment under multi-mode based on Cross-Entropy Method | |
| CN113033772A (en) | Multi-equipment state monitoring method based on federal learning | |
| CN113033624A (en) | Industrial image fault diagnosis method based on federal learning | |
| CN117557065B (en) | Building engineering construction progress supervisory systems based on BIM technique | |
| CN112187528A (en) | Industrial control system communication flow online monitoring method based on SARIMA | |
| CN112418682A (en) | Security assessment method fusing multi-source information | |
| CN116872206A (en) | Robot fault detection method and system based on industrial Internet | |
| CN116781560A (en) | Industrial computer remote intelligent control system based on artificial intelligence | |
| CN112333147B (en) | Nuclear power plant DCS platform network operation situation sensing method and system | |
| CN116300969B (en) | Path tracking method of mobile robot | |
| CN117093852A (en) | Early abnormality monitoring model and method for industrial robot | |
| CN117092953A (en) | Production data acquisition management and control system based on industrial Internet of things | |
| CN111045415A (en) | Multi-modal process fault detection method based on local probability density double subspace | |
| CN115640980A (en) | Power grid engineering cost dynamic management system based on target control | |
| CN116386128A (en) | Tunnel worker construction state detection method, system, medium and equipment | |
| CN114609969B (en) | Numerical control machine tool track error compensation method based on cloud computing | |
| CN111428345B (en) | Performance evaluation system and method of random load disturbance control system | |
| CN111158238B (en) | Force feedback equipment dynamics parameter estimation algorithm based on particle swarm optimization | |
| CN113608622A (en) | Human body posture real-time prediction method, system, medium and equipment | |
| CN111123890B (en) | Special equipment fault monitoring system | |
| Li et al. | Research on Robot Inspection Path Planning in Substation Based on Artificial Neural Network Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |