WO2023248482A1 - データ復号化装置、誤差補正システム及びデータ復号化プログラム - Google Patents
データ復号化装置、誤差補正システム及びデータ復号化プログラム Download PDFInfo
- Publication number
- WO2023248482A1 WO2023248482A1 PCT/JP2022/025416 JP2022025416W WO2023248482A1 WO 2023248482 A1 WO2023248482 A1 WO 2023248482A1 JP 2022025416 W JP2022025416 W JP 2022025416W WO 2023248482 A1 WO2023248482 A1 WO 2023248482A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- axis
- data
- approximation
- model
- dependent data
- 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.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Program-control systems
- G05B19/02—Program-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of program data in numerical form
- G05B19/404—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of program data in numerical form characterised by control arrangements for compensation, e.g. for backlash, overshoot, tool offset, tool wear, temperature, machine construction errors, load, inertia
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/0751—Error or fault detection not based on redundancy
- G06F11/0754—Error or fault detection not based on redundancy by exceeding limits
- G06F11/076—Error or fault detection not based on redundancy by exceeding limits by exceeding a count or rate limit, e.g. word- or bit count limit
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/16—Program controls
- B25J9/1628—Program controls characterised by the control loop
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/0706—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation the processing taking place on a specific hardware platform or in a specific software environment
- G06F11/0736—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation the processing taking place on a specific hardware platform or in a specific software environment in functional embedded systems, i.e. in a data processing system designed as a combination of hardware and software dedicated to performing a certain function
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/0793—Remedial or corrective actions
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
- H03M7/60—General implementation details not specific to a particular type of compression
- H03M7/6041—Compression optimized for errors
Definitions
- the present disclosure relates to a data decoding device, an error correction system, and a data decoding program.
- axis-dependent data that depends on the coordinate values of each axis of an industrial machine, such as the above-mentioned error amount, may have a white noise-like property with a uniform appearance frequency as a whole.
- it is difficult to compress data using entropy encoding technology because the above-mentioned small information entropy cannot be utilized.
- An object of the present disclosure is to provide a data decoding technique that can decode axis-dependent data after encoding axis-dependent data that depends on the coordinate values of each axis of an industrial machine.
- One aspect of the present disclosure is a data decoding device that decodes encoded data, wherein axis-dependent data that depends on coordinate values of each axis of an industrial machine is processed as a linear combination of each axis data of the industrial machine. Based on the linear combination model to be approximated and the model approximate encoded axis-dependent data approximated by the linear combination model, model approximate decoded axis-dependent data obtained by decoding the model approximate encoded axis-dependent data.
- a data decoding device includes a decoding unit that generates data.
- Another aspect of the present disclosure is an error correction system that corrects errors in industrial machinery, including a correction section and a data decoding device according to one aspect of the present disclosure, wherein the correction section is configured to This is an error correction system that corrects errors in the industrial machine based on rear axis dependent data.
- FIG. 7 is a diagram showing an approximation error (vector ⁇ [X][Y]) including an exceptional point larger than a predetermined tolerance.
- FIG. 6 is a diagram showing exceptional points that are excluded and retained because the approximation error (vector ⁇ [X][Y]) is larger than a predetermined tolerance.
- It is a flowchart which shows the procedure of learning processing by a machine learning device.
- FIG. 1 is a diagram showing the configuration of a data decoding device 1 according to the first embodiment.
- the data decoding device 1 includes a decoding section 11.
- the decoding unit 11 generates model approximate decoded axis dependent data as decoded axis dependent data based on the model approximate encoded axis dependent data and the linear combination model.
- FIG. 5 is a diagram showing data in which the appearance frequency of each value is uniform. Similar to FIGS. 3 and 4, in FIG. 5, the horizontal axis indicates bit values, and the vertical axis indicates the frequency of appearance of each value.
- White noise-like data with a uniform appearance frequency as shown in FIG. 5 cannot take advantage of the small information entropy described above, so it is difficult to compress the data by entropy encoding.
- examples of static error correction for each axis of industrial machinery include pitch error correction, straightness error correction, and three-dimensional error correction.
- Pitch error correction is correction of errors in the direction along the axial direction.
- Straightness error correction is correction of errors in a direction perpendicular to the axial direction.
- Three-dimensional error correction is correction of three-dimensional spatial errors.
- FIG. 6 is a diagram showing each axis error on the X axis.
- Each axis error of the X axis is an error amount of each coordinate value measured when only the X axis is moved while the Y axis and the Z axis are fixed.
- the error amount of each coordinate value X 0 , X 1 , X 2 , and X 3 is represented by a vector having a different magnitude and direction.
- FIG. 7 is a diagram showing each axis error of the Y axis.
- Each Y-axis error is the amount of error in each coordinate value measured when only the Y-axis is moved while the X-axis and Z-axis are fixed.
- the error amount of each coordinate value Y 0 , Y 1 , and Y 2 is represented by a vector having a different size and direction.
- L represents the number of axes targeted for error correction.
- X l represents the lth correction target axis.
- FIG. 8 is a diagram showing the amount of error in the coordinate values (X 2 , Y 1 ).
- the error amount (vector E[X 2 ][Y 1 ]) in the coordinate value (X 2 , Y 1 ) is the error amount (vector E [X 2 ] ) in the coordinate value X 2 and the error amount (vector E Y [Y 1 ]) of the coordinate value Y 1 can be regarded as a linear combination, and is expressed as in the following equation (2).
- each axis error is not linearly independent, and the error amount (vector E[X 1 ]...[X L ]) may be determined by the correlation of multiple axes.
- the error amount (vector E[X 1 ]...[ XL ]) is the correlation term (vector ⁇ [X 1 ]...[ XL ]). In some cases, it may not be expressed as a linear combination of errors in each axis.
- FIG. 9 is a diagram showing the amount of error when it cannot be represented by a linear combination of the errors of each axis.
- the error amount expressed by the above formula (1) is used as the error amount (vector E[X 1 ]...[X L ]). Instead, it is necessary to set the error amount to include the correlation term (vector ⁇ [X 1 ]...[X L ]) expressed by the above formula (3).
- the error amount hereinafter referred to as spatial error
- the control device for each space that has a correlation with the error amount and is corrected, it is called error correction for each space.
- the spatial error has the property that although it cannot be expressed as a linear combination of the errors of each axis as a whole, it can be regarded as a linear combination of errors of each axis locally, just like the errors of each axis. This is what the inventor discovered.
- FIG. 10 is a partial enlarged view of FIG . 9, and in the local area surrounded by the broken line in FIG .
- the spatial error can be expressed as a linear combination of errors in each axis.
- the spatial error (vector E[ X ][Y]) is calculated by the error of each axis (vector E It is expressed as the sum of This means that the spatial error (vector E[X][Y]) is the error amount in one row in the X-axis direction (vector E This means that it is possible to take out the error amount (vector E Y [Y]) and the error amount (vector E Y [Y]) in a row in the Y-axis direction and approximate it as a linear combination of these.
- the local area includes, for example, the central area of the movable range of the industrial machine.
- FIG. 11 is a diagram showing a bitmap image that visualizes the error map when the target axes for error correction are the X axis and the Y axis, and the RGB values of each pixel correspond to the error amount vector E. are doing. Further, the error amount (vector E[X][Y]) of each pixel is expressed as the sum of the vector E X [X] and the vector E Y [Y] according to the above equation (4).
- the data encoding device 101 can be locally encoded. Specifically, it utilizes the property that can be regarded as a linear combination of errors in each axis, as expressed in the above-mentioned formula (1). This allows the data encoding device 101 to encode and compress axis-dependent data, which has been difficult in the past.
- each axis of an industrial machine means, for example, each axis of a machine tool, that is, the X axis, Y axis, and Z axis.
- axis-dependent data includes, for example, the installation error amount of relatively large workpieces whose displacement varies depending on the coordinate value due to the influence of deflection due to their own weight. It will be done.
- error amounts and workpiece installation error amounts are both data that depend on the coordinate values of each axis of the industrial machine.
- an approximate model (vector Ea[X 1 ]...[X L ]) as a linear combination model expressed by the following formula (5) is used.
- the amount of error can be expressed. That is, the error amount is approximated by taking out the error amount in one row in the X - axis direction (vector Ea can.
- each axis data (each axis error) after approximation has a total of N+M points, indicating that axis-dependent data can be compressed.
- X represents a one-dimensional axial space
- x represents an element belonging to the space.
- p is any value from 1 to L.
- x 3 means a certain possible value of axis X 3 .
- the data encoding device 101 by approximating a part of axis-dependent data as a linear combination of each axis data (each axis error), it is possible to encode axis-dependent data, which was difficult to compress in the past. can be compressed. Furthermore, according to the data encoding device 101, by using the encoded and compressed axis-dependent data, it is possible to reduce the amount of error that can be input to the control device of industrial machinery, etc., without increasing the storage capacity. Data can be increased, and errors in industrial machinery can be corrected with higher accuracy.
- FIG. 14 is a diagram showing the configuration of a second example of the data encoding device.
- the data encoding device 102 differs from the data encoding device 101 in that it includes an axis-dependent data dividing section 122.
- the model approximation encoding unit 121 performs model approximation encoding based on the divided axis-dependent data generated by dividing the axis-dependent data into a plurality of pieces and the linear combination model described above. This is different from the model approximation encoding unit 111 in the first example.
- the configuration other than these differences is the same as the first example.
- the data encoding device 101 described above assumes that a portion of the axis-dependent data, which has a uniform appearance frequency as a whole and may resemble white noise, can be regarded as a linear combination of each axis data (each axis error). , which executes model approximation coding of a linear combination model.
- the data encoding device 102 actively divides the axis-dependent data into multiple regions, thereby creating multiple regions that can be regarded as a linear combination of each axis data (each axis error). This makes it possible to more reliably execute model approximation coding of a linear combination model.
- the axis-dependent data dividing unit 122 divides the axis-dependent data and generates a plurality of divided axis-dependent data.
- FIG. 15 is a diagram showing axis-dependent data partitioned into a plurality of grid-like regions.
- the axis-dependent data input to the data encoding device 102 is divided into a plurality of grid-like regions according to each axis data (each axis error) on each coordinate value, for example. Ru.
- the axis-dependent data dividing unit 122 divides the axis-dependent data into a plurality of pieces, for example, along these sections.
- FIG. 16 is a diagram showing an example of axis-dependent data after division.
- the axis-dependent data input to the data encoding device 102 is divided into five division sections 1 to 5 by the axis-dependent data dividing section 122.
- each data within each of these five divided sections 1 to 5 corresponds to the axis-dependent data after division
- each of these axis-dependent data after division is regarded as a linear combination of each axis data (each axis error). It is possible to perform model approximation encoding of a linear combination model by the model approximation encoding unit 121, which will be described later.
- each axis error can be created.
- model approximation encoding of a linear combination model for each region By performing model approximation encoding of a linear combination model for each region, axis-dependent data, which has been difficult to compress in the past, can be more reliably compressed.
- FIG. 17 is a diagram showing the configuration of a third example of a data encoding device.
- the data encoding device 103 differs from the second example in that the configuration of the axis-dependent data dividing unit 132 is different from the axis-dependent data dividing unit 122 described above.
- the configuration other than this difference is the same as the second example.
- the method of dividing axis-dependent data is not particularly limited, but in the data encoding device 103, the axis-dependent data is divided using dynamic programming. That is, by using dynamic programming, it is possible to perform optimal division of axis-dependent data, and the axis-dependent data can be best approximated and compressed.
- the dynamic programming processing unit 133 also includes an axis-dependent data partial division unit 135 as a means for dividing the problem into partial problems.
- the axis-dependent data partial division unit 135 divides the axis-dependent data into a plurality of parts to generate partial axis-dependent data.
- the axis-dependent data partial division unit 135 divides the axis-dependent data into predetermined specified sections according to a predetermined division criterion stored in advance, and then divides the axis-dependent data into sections in the + direction or ⁇ direction of each axis such as the X axis or the Y axis.
- the axis-dependent data is divided into multiple parts by optimizing downscaling one point in each direction. The division of axis-dependent data by the axis-dependent data partial division unit 135 will be described in detail later.
- the dynamic programming processing unit 133 also includes a partial axis-dependent data optimization result combination unit 136 as a means for combining (combining) the optimization results of partial problems.
- the partial axis-dependent data optimization result combining unit 136 generates optimal post-division axis-dependent data by expanding and combining the partial axis-dependent data.
- the partial axis-dependent data optimization result combining unit 136 divides the partial axis-dependent data generated by dividing the axis-dependent data by the axis-dependent data partial dividing unit 135 into the X-axis, Y-axis, etc. Optimize by expanding one point in each axis in the + direction or - direction.
- the generation of optimal post-division axis-dependent data by the partial axis-dependent data optimization result combination unit 136 will be described in detail later.
- FIG. 18 is a flowchart showing the procedure for dividing axis-dependent data by the dynamic programming processing unit 133.
- the division of the axis-dependent data by the dynamic programming processing unit 133 is performed by recursively searching for an optimal division section of the axis-dependent data using dynamic programming.
- step S1 the axis-dependent data is divided into predetermined designated sections. However, if the area has already undergone division processing of axis-dependent data by the dynamic programming processing unit 133, the held processing results may be reflected in this step. After that, the process advances to step S2.
- step S2 an approximate model of the region within the designated section (designated region) divided into sections in step S1 is generated. Specifically, for each specified region, an approximate model (vector Ea[X 1 ]...[X L ]) as a linear combination model described in the first embodiment is generated. After that, the process advances to step S3.
- step S3 it is determined whether the approximate model of the designated area generated in step S2 satisfies the all-point constraint.
- the constraints include whether the approximation errors of all points are within the allowable value, or whether the points whose approximation errors are not within the allowable value are within the allowable number of points. If this determination is YES, it is assumed that the axis-dependent data has been optimally divided and that the optimal axis-dependent data after division has been obtained, and the process ends. On the other hand, if this determination is NO, the process advances to step S4.
- n is set to an initial value of 1.
- the value of n represents each axis.
- the process advances to step S5.
- step S5 it is determined whether n is greater than L.
- L is the number of axes in the designated section of axis-dependent data. For example, if there are two axes, the X axis and the Y axis, L is 2. If this determination is YES, the process advances to step S11. On the other hand, if this determination is NO, the process advances to step S6.
- steps S6 to S10 is performed when n is less than or equal to L, and when there are two axes, the X and Y axes, if n is 1, it means processing for the X axis, and if n is 2, it means processing for the X axis. If it exists, it means processing for the Y axis.
- step S6 the axis-dependent data is divided into specified sections narrowed by one row of each axis data (each axis error) in the X n positive direction from the specified section in step S1. That is, a new section division is performed in which each axis data (each axis error) is reduced by one column in the Xn positive direction.
- the X n positive direction means the X-axis positive direction when n is 1.
- the result is output as the optimization result nP. When n is 1, the optimization result 1P is output.
- the process advances to step S7.
- step S7 the optimization result nP obtained in step S6 is expanded by one column of each axis data (each axis error) in the Xn positive direction. The result is output as the optimization result nP + .
- n 1
- the optimization result 1P + is output. Since n can range from 1 to L, this step yields optimization results 1P to LP + .
- the process advances to step S8.
- step S8 the axis-dependent data is divided into specified sections narrowed by one row of each axis data (each axis error) in the negative direction of Xn from the specified section in step S1. That is, a new section division is performed in which each axis data (each axis error) is reduced by one column in the negative direction of Xn .
- the X n negative direction means the negative direction of the X axis when n is 1.
- the result is output as an optimization result nM. When n is 1, an optimization result of 1M is output. After that, the process advances to step S9.
- step S9 the optimization result nM obtained in step S8 is expanded by one column of each axis data (each axis error) in the negative direction of Xn .
- the result is output as the optimization result nM + .
- n 1
- an optimization result of 1M + is output. Since n can range from 1 to L, this step results in optimization results of 1M to LM + .
- the process advances to step S10.
- step S10 n is increased by 1. After that, the process returns to step S5.
- step S11 is performed when n is larger than L, and when the number of axes is two, the X-axis and the Y-axis, after the processing for the X-axis and Y-axis is completed in steps S6 to S10. It is processing.
- step S11 among the optimization results 1P to LP + and 1M to LM + obtained in steps S6 to S10, the one with the smallest number of non-approximable points is output. That is, for each of the optimization results 1P to LP + and 1M to LM + , the number of unapproximable points where the approximate model generated in step S3 does not satisfy the above constraints is calculated, and the number of unapproximable points is the smallest and best approximated. The data with the most compressed data is output, and the process ends.
- FIG. 19 is a diagram showing divided sections before each axis data (each axis error) is expanded by one column in the positive X direction.
- FIG. 20 is a diagram showing a divided section after expanding each axis data (each axis error) by one column in the positive X direction. In FIGS. 19 and 20, different numbers are assigned to each divided section.
- sections 1 to 5 are extracted as continuous sections that appear at the end in the positive X direction of the section before expanding each axis data (each axis error) by one column.
- each of the extracted sections 1 to 5 is expanded by one column of each axis data (each axis error) to generate expanded sections 1 to 5 as shown in FIG.
- post-expansion sections 1 to 5 it is checked whether the above-mentioned approximate model satisfies the above-mentioned constraints. If the constraints are satisfied, the section after expansion is set as a new section. In the example shown in FIG. 20, post-expansion sections 1 and 4 satisfy the constraints and are therefore set as new sections.
- the undetermined section has a certain area (for example, 2 ⁇ 2) or more, it is checked whether the above-mentioned approximate model satisfies the above-mentioned constraints. In the example shown in FIG. 20, this determination is performed because the post-expansion section 3 is larger than a certain area (for example, 2 ⁇ 2). Until then, the expanded section will also be considered an undetermined section.
- a certain area for example, 2 ⁇ 2 or more
- the section before expansion is an NG section, that is, a section that does not satisfy the constraints and cannot be approximated
- the section for expansion is set as an undetermined section.
- post-expansion section 5 corresponds to this, and is therefore set as an undetermined section.
- the axis-dependent data can be divided into optimal divided axis-dependent data that can be compressed by reducing the number of data to the greatest extent possible, so that it is regarded as a linear combination of each axis data (each axis error).
- a linear combination of each axis data each axis error.
- the approximation error encoding unit 143 encodes the approximation error amount to generate an encoded approximation error amount.
- the approximation error amount calculated by the approximation error calculation unit 142 is biased in the appearance frequency of values in the data as described later, and the information entropy is often small. It is possible to compress.
- data may be compressed by encoding by model approximation encoding of a linear combination model executed by the model approximation encoding unit 141.
- vector E[X 1 ]...[ XL ] is the original error amount before model approximation
- vector Ea[X 1 ]...[ XL ] is the amount of error before model approximation. This is the amount of error after. From this formula (10), it can be seen that these differences are approximation errors (vector ⁇ [X 1 ]...[X L ]).
- FIG. 22 is a diagram showing the approximation error (vector ⁇ [X][Y]).
- the approximation error (vector ⁇ [X][Y]) has only small values unevenly distributed, and the frequency distribution of the values is also unevenly distributed. Therefore, data can be compressed by encoding the approximation errors (vectors ⁇ [X 1 ]...[X L ]).
- FIG. 23 is a diagram showing the configuration of a fifth example of a data encoding device.
- data encoding device 105 differs from data encoding device 104 described above in that it further includes an approximation error removal unit 153 with a predetermined tolerance or more.
- the approximation error encoding unit 154 is different from the approximation error encoding unit 143 described above in that the approximation error encoding unit 154 encodes an approximation error amount within a predetermined tolerance.
- the configuration other than these differences is the same as the fourth example.
- the approximation error removal unit 153 generates an approximation error amount within a predetermined tolerance by removing an approximation error amount that exceeds a predetermined tolerance from the approximation error amount.
- FIG. 24 is a diagram showing an approximation error (vector ⁇ [X][Y]) including an exceptional point larger than a predetermined tolerance.
- the approximation error (vector ⁇ [X][Y]) which is the difference between the original error amount before model approximation encoding and the error amount after model approximation encoding, has the following: Exception points larger than a predetermined tolerance may be included. In this embodiment, this exceptional point is removed by the approximation error removal unit 153.
- FIG. 25 is a diagram showing exceptional points that are excluded and retained because the approximation error (vector ⁇ [X][Y]) is larger than a predetermined tolerance.
- the approximation error removal unit 153 may separately retain the exceptional points where the approximation error is larger than a predetermined tolerance, that is, the approximation error amount that exceeds the predetermined tolerance, which is removed from the approximation error amount.
- axis-dependent data such as the original error amount can be compressed and reproduced without loss.
- the predetermined tolerance examples include an approximation error tolerance and a predetermined number of data points (tolerance) that exceed the approximation error tolerance.
- the approximation error removing unit 153 converts points exceeding a preset approximation error tolerance value or a predetermined number of points out of the points exceeding the approximation error tolerance value into an approximation error (vector ⁇ [X][Y]).
- the predetermined tolerance may include 0.
- the approximation error encoding unit 154 encodes the amount of approximation error within a predetermined tolerance to generate the amount of approximation error after encoding. That is, in encoding the approximation error (vector ⁇ [X 1 ]...[X L ]), the approximation error encoding unit 154 of this embodiment excludes points where the approximation error is larger than a predetermined tolerance, and then , perform the encoding.
- the approximation error after excluding points larger than the predetermined tolerance from the approximation error amount becomes more biased and the information entropy becomes smaller, so that the data compression effect becomes more effective by encoding. It increases. Further, for example, the data size after encoding can be further reduced by retaining only the points where the approximation error is larger than a predetermined tolerance and not retaining the other approximation error amounts. Even in that case, it is possible to guarantee that the entire approximation error falls within the tolerance.
- the data encoding device 105 it is possible to encode and compress axis-dependent data, which was conventionally difficult to compress, and also encode the approximate error amount after removing the approximate error amount exceeding a predetermined tolerance. By doing so, compression with loss can also be realized within the range of allowable amount of loss (predetermined tolerance, predetermined number of points), and in this case, data size can be reduced more than compression without loss.
- FIG. 26 is a diagram showing the configuration of a sixth example of a data encoding device.
- the data encoding device 106 differs from the above-described data encoding device 101 in that it further includes a model approximation-encoded data encoding unit 162.
- this example has the same configuration as the first example.
- the model approximation encoded data encoding unit 162 encodes the model approximation encoded axis-dependent data. That is, the model approximation-encoded data encoding unit 162 executes re-encoding of the axis-dependent data after model approximation encoding.
- the encoded axis-dependent data is further encoded by the model approximation encoded data encoder 162, so that the data size can be further reduced.
- FIG. 27 is a diagram showing the configuration of a seventh example of a data encoding device.
- the data encoding device 107 includes a learning result acquisition unit that acquires reinforcement learning results by the machine learning device 109 instead of dynamic programming, and uses the learning results to generate axis-dependent data. This differs from the data encoding device 103 described above in that it divides the data into sections. The configuration other than this difference is the same as the third example.
- the machine learning device 109 executes reinforcement learning for optimal division processing of axis-dependent data.
- the machine learning device 109 as an agent acquires axis-dependent data such as the amount of error of an industrial machine as the state of the environment, and selects certain axis-dependent data after division as an action. Then, the environment changes based on the action. With this change in environment, the number of unapproximable points and the amount of data after approximation, which are obtained by model approximation coding of the axis-dependent data after division, are obtained as determination data.
- the machine learning device 109 as an agent learns the optimal post-division axis-dependent data for selecting a better action, that is, making a decision.
- the machine learning device 109 as an agent learns to select an action that maximizes the total reward over the future.
- E[ ] represents the expected value
- t is time
- ⁇ is a parameter called a discount rate which will be described later
- r t is the reward at time t
- ⁇ is the sum at time t.
- the expected value in this equation is the expected value when the state changes according to the optimal action.
- reinforcement learning is performed while exploring by performing various actions.
- Such an update formula for the value Q(s, a) can be expressed, for example, as shown in Equation (11) below.
- s t represents the state of the environment at time t
- a t represents the behavior at time t. Due to the action a t , the state changes to s t+1 . r t+1 represents the reward obtained by changing the state.
- the term with max is the Q value when action a with the highest Q value known at that time is selected under state s t+1 multiplied by ⁇ .
- ⁇ is a parameter satisfying 0 ⁇ 1 and is called a discount rate.
- ⁇ is a learning coefficient and is in the range of 0 ⁇ 1.
- the above formula (11) represents a method of updating the value Q(s t , at ) of the action a t in the state s t based on the reward r t+1 returned as a result of the trial a t .
- This update formula shows that the value of the best action max a Q(s t +1 , a ) in the next state s t +1 due to action a t is greater than the value Q(s t , a t ) of action a t in state s t. If it is larger, Q(s t , a t ) is increased, and if it is smaller, Q(s t , at ) is decreased.
- Q learning there is a method of creating a table of Q(s, a) for all state-action pairs (s, a) and performing learning.
- the number of states is too large to obtain the values of Q(s, a) for all state-action pairs, and it may take a long time for Q-learning to converge.
- DQN Deep Q-Network
- the value of value Q (s, a) can be calculated by configuring value function Q using an appropriate neural network, adjusting the parameters of the neural network, and approximating value function Q with an appropriate neural network. It may be calculated.
- DQN it is possible to shorten the time required for Q learning to converge.
- non-patent literature "Human-level control through deep reinforcement learning", by Volodymyr Mnih1 [online], [searched on January 17, 2017], Internet ⁇ URL: http://files.davidqiu .com/research/nature14236.pdf> has a detailed description.
- the machine learning device 109 includes a state observation unit 191, a determination data acquisition unit 192, a learning unit 193, and a decision making unit 194, as shown in FIG. Be prepared. Further, the learning section 193 includes a reward calculation section 195 and a value function updating section 196.
- the state observation unit 191 acquires axis-dependent data as state data from the data encoding device 107. Further, the state observation unit 191 outputs the acquired axis-dependent data to the learning unit 193.
- the reward calculation unit 195 of the learning unit 193 calculates a reward based on the acquired axis-dependent data, the number of points that cannot be approximated, and the amount of data after approximation. Specifically, the reward calculation unit 195 increases the reward when the number of points that cannot be approximated decreases, and decreases the reward when the number of points that cannot be approximated increases. Further, the reward calculation unit 195 increases the reward when the amount of data after approximation decreases, and decreases the reward when the amount of data after approximation increases.
- the value function updating unit 196 of the learning unit 193 calculates the number of unapproximable points, the amount of data after approximation, and the reward value obtained by model approximation encoding of the axis-dependent data as state data and the axis-dependent data after division as judgment data.
- the stored value function is updated by performing the above-mentioned Q learning based on .
- the value function stored by the value function update unit 196 can be shared by, for example, a plurality of machine learning devices that are communicably connected to each other.
- the decision making unit 194 obtains the updated value function from the value function updating unit 196. Furthermore, the decision making unit 194 outputs the optimal post-division axis-dependent data to the data encoding device 107 as a behavioral output based on the acquired value function.
- FIG. 28 is a flowchart showing the procedure of learning processing by the machine learning device 109.
- step S21 first, the machine learning device 109 outputs post-division axis-dependent data to the data encoding device 107 as a behavioral output.
- the divided axis-dependent data output in this step is obtained by dividing the axis-dependent data into predetermined specified sections according to a predetermined division criterion stored in advance.
- the data encoding device 107 generates the number of non-approximable points and the amount of data after approximation by executing model approximation encoding on the axis-dependent data after division. After that, the process advances to step S22.
- step S22 the machine learning device 109 acquires axis-dependent data as state data from the data encoding device 107. After that, the process advances to step S23.
- step S23 the machine learning device 109 acquires the number of unapproximable points after model approximation encoding and the amount of data after approximation of the axis-dependent data after division, which were generated in step S21, from the data encoding device 107 as determination data. After that, the process advances to step S24.
- step S24 as determination condition 1, it is determined whether the number of non-approximation points has decreased when the data encoding device 107 executes model approximation encoding on the divided axis-dependent data. If this determination is YES, the process proceeds to step S25 and the reward is increased. On the other hand, if this determination is NO, the process proceeds to step S26 and the reward is decreased. After that, the process advances to step S27.
- step S27 as determination condition 2, it is determined whether the amount of data after model approximation encoding is reduced when the data encoding device 107 executes model approximation encoding on the axis-dependent data after division. . If this determination is YES, the process proceeds to step S28 and the reward is increased. On the other hand, if this determination is NO, the process proceeds to step S29 and the reward is decreased. After that, the process advances to step S30.
- step S30 the value function stored in the value function update unit 196 is updated.
- the value function update unit 196 performs model approximation encoding of the axis-dependent data as state data and the axis-dependent data after division as judgment data, and calculates the number of points that cannot be approximated, the amount of data after approximation, and the reward value.
- the stored value function is updated by performing the above-mentioned Q learning based on . After that, the process advances to step S31.
- step S31 it is determined whether or not to continue the main learning process. If this determination is YES, the process returns to step S21. On the other hand, if this determination is NO, this process ends.
- the axis-dependent data can be divided into optimal divided axis-dependent data that can be compressed by reducing the number of data through reinforcement learning by the machine learning device 109. It is possible to generate multiple optimal regions that can be regarded as a linear combination (axis error), and by performing model approximation coding of a linear combination model for each region, axis dependence, which was previously difficult to compress, can be generated. Data can be more compressed.
- the first data encoding program includes a part of the axis-dependent data that depends on the coordinate values of each axis of the industrial machine, and a linear combination model that approximates the axis-dependent data as a linear combination of the axis data of the industrial machine.
- a data encoding program for causing a computer to execute a model approximation encoding step of generating encoded axis-dependent data by encoding axis-dependent data it is possible to provide a data encoding program for causing a computer to execute a model approximation encoding step of generating encoded axis-dependent data by encoding axis-dependent data.
- the first data encoding program further includes an axis-dependent data division step of dividing the axis-dependent data to generate a plurality of divided axis-dependent data, and the model approximation encoding step generates a plurality of divided axis-dependent data.
- a second data encoding program that generates encoded axis-dependent data based on the linear combination model and the linear combination model can be provided.
- the second data encoding program includes a dynamic programming processing step for generating optimal divided axis-dependent data by executing dynamic programming, and evaluates the optimality of the encoded axis-dependent data.
- an optimality evaluation step a partial division step that generates partial axis-dependent data by dividing axis-dependent data into multiple parts, and optimal axis-dependent data after division by expanding and combining the partial axis-dependent data. It is possible to provide a third data encoding program for causing a computer to execute the optimization result combining step of generating.
- a fourth data encoding program for causing the computer to execute a step of generating optimal post-division axis-dependent data based on the reinforcement learning result by the machine learning device. can.
- a fifth data encoding program for causing a computer to execute an approximation error calculation step of calculating an approximation error amount, and a step of encoding the approximation error amount and generating an approximation error amount after encoding.
- a fifth data encoding program can be provided.
- the model approximation encoding unit 141 is configured to include the approximation error calculation unit 142, but for example, the model approximation encoded axis-dependent data encoded by the data encoding device 104 is The approximation error amount may be calculated based on the difference between the axis-dependent data that has been decoded and decoded by the data decoding device and the original axis-dependent data.
- the configuration including the approximation error calculation unit 142 is applied to the first example, but the configuration is not limited to this, and can be applied to the second example and the third example as well.
- the configuration including the model approximation encoded data encoding section 162 is applied to the first example, but the configuration is not limited to this and can be applied to other examples as well. In this way, the above-mentioned examples can be combined as appropriate as long as they do not interfere with each other's functions.
- the machine learning device 109 is provided separately from the data encoding device 107, but the invention is not limited to this, and a machine learning device may be provided inside the data encoding device 107. .
- the data decoding device 1 may be provided, for example, in a numerical control device (CNC) corresponding to a control device for industrial machinery such as a machine tool or a robot, a robot control device, or the like. Alternatively, it may be provided in an external computer or the like so as to be able to communicate with these control devices.
- CNC numerical control device
- the decoding unit 11 obtains, as input data, axis-dependent data after model approximation coding by linear combination of each axis data.
- This model approximation encoded axis-dependent data is generated by each of the above-mentioned data encoding devices.
- the axis-dependent data after model approximation encoding is the constant vector c expressed by the above formula (7).
- vector Ea X 1 [ X 1 ] to vector Ea Contains information on XL and XL .
- each axis data (each axis error) is assumed to be a vector arranged as many times as the number of elements, as expressed by the following formula (12).
- the data decoding device 1 uses a linear combination model that approximates axis-dependent data that depends on the coordinate values of each axis of an industrial machine as a linear combination of each axis data of the industrial machine, and model approximation using the linear combination model.
- a decoding unit 11 is provided which generates model approximate decoded axis dependent data by decoding the model approximate encoded axis dependent data based on the model approximate encoded axis dependent data.
- it is possible to increase the amount of data such as the amount of error that can be input to the control device of the industrial machine and the like without increasing the storage capacity, and it is possible to correct the error of the industrial machine with higher precision.
- the approximation error decoding unit 22 obtains an encoded approximation error amount obtained by encoding the approximation error amount obtained when axis-dependent data is approximated by a linear combination model. Further, the approximation error decoding unit 22 decodes the obtained encoded approximation error amount to generate a decoded approximation error amount.
- the post-encoding approximation error amount is generated by encoding the approximation error amount by the approximation error encoding unit 43 in the data encoding device 104 of the fourth example described above.
- FIG. 30 is a diagram showing the configuration of a data decoding device according to the third embodiment.
- the data decoding device 3 according to the third embodiment differs from the data decoding device 2 according to the second embodiment in that it includes an approximation error amount combining unit 34 exceeding a predetermined tolerance.
- this embodiment differs from the second embodiment in that decoded axis-dependent data is generated by combining an approximation error amount exceeding a predetermined tolerance with decoded axis-dependent data after approximation error amount combination.
- the configuration other than these differences is the same as the second embodiment.
- the approximation error amount after encoding decoded by the approximation error decoding unit 32 of this embodiment is within a predetermined tolerance by the approximation error encoding unit 154 in the data encoding device 105 of the fifth example described above. It is generated by encoding the approximation error amount. That is, the approximation error amount used in this embodiment is an approximation error amount within a predetermined tolerance from which the approximation error amount exceeding the predetermined tolerance is removed.
- the approximation error amount combining unit 34 that exceeds the predetermined tolerance acquires the approximation error amount that exceeds the predetermined tolerance, and combines the approximation error amount that exceeds the predetermined tolerance with the decoded axis-dependent data after the approximation error amount combination, thereby decoding the approximation error amount that exceeds the predetermined tolerance. Generate axis-dependent data after conversion.
- the coupling method is not particularly limited. For example, it may be addition, and the approximation error amount combining unit 34 that exceeds a predetermined tolerance adds the approximation error amount that exceeds a predetermined tolerance to the decoded axis-dependent data after the approximation error amount combination. Data can be generated.
- the amount of approximation error that exceeds a predetermined tolerance is generated by the approximation error removal unit 153 that exceeds a predetermined tolerance in the data encoding device 105 of the fifth example described above. That is, the approximation error amount exceeding the predetermined tolerance generated by subtracting the approximation error amount within the predetermined tolerance from the approximation error amount by the approximation error removal unit 153 is the approximation error amount combining unit 34 exceeding the predetermined tolerance of this embodiment. used in
- the approximation error amount is an approximation error amount within a predetermined tolerance from which an approximation error amount exceeding a predetermined tolerance is removed. Further, in the data decoding device 3 according to the present embodiment, by acquiring an approximation error amount exceeding a predetermined tolerance and combining the approximation error amount exceeding a predetermined tolerance with the decoded axis-dependent data after combining the approximation error amount, An approximation error amount coupling unit exceeding a predetermined tolerance is provided, which generates axis-dependent data after decoding.
- the encoded axis-dependent data can be decoded, the encoded approximation error amount can be decoded and combined, and the approximation error amount exceeding a predetermined tolerance can also be combined.
- Axis-dependent data such as the original error amount can be reproduced without loss.
- FIG. 31 is a diagram showing the configuration of an error correction system 200 including the data decoding device 1 according to the first embodiment.
- the error correction system 200 according to this embodiment corrects errors in industrial machinery using decoded axis-dependent data generated by the data decoding device 1.
- the error correction system 200 includes, for example, memories such as ROM (read only memory) and RAM (random access memory), a CPU (control processing unit), operating means such as a keyboard, a display, and the like, which are connected to each other via a bus. It is constructed using a computer equipped with a communication control section. The functions and operations of the functional units described below are achieved by the cooperation of a CPU installed in the computer, a memory, and a control program stored in the memory.
- the error correction system 200 may be provided, for example, in a numerical control device (CNC) corresponding to a control device for industrial machinery such as a machine tool or a robot, a robot control device, or the like. Alternatively, it may be provided in an external computer or the like so as to be able to communicate with these control devices.
- CNC numerical control device
- the error correction system 200 includes a data decoding device 1, a command analysis section 201, a correction section 202, an interpolation section 203, an X-axis acceleration/deceleration section 204, and a Y-axis acceleration/deceleration section 204. It includes a deceleration section 205, a Z-axis acceleration/deceleration section 206, an X-axis servo 207, a Y-axis servo 208, and a Z-axis servo 209. Details of the data decoding device 1 are as described above.
- the command analysis unit 201 reads and analyzes the machining program block by block, and generates movement command data that commands movement of each control axis of a machine tool, etc. based on the analysis results.
- the command analysis unit 201 transmits the generated movement command data to the correction unit 202, which will be described later.
- the correction unit 202 corrects the movement command data acquired from the command analysis unit 201 based on the decoded axis-dependent data generated by the data decoding device 1. The correction process by the correction unit 202 will be described in detail later.
- the interpolation unit 203 generates interpolation data by interpolating points on the command route at a predetermined interpolation cycle based on the movement command data generated by the command analysis unit 201 and corrected by the correction unit 202.
- the interpolation unit 203 distributes and transmits the generated interpolation data to an X-axis acceleration/deceleration unit 204, a Y-axis acceleration/deceleration unit 205, and a Z-axis acceleration/deceleration unit 206, which will be described later.
- the data decoding device 1 when the error correction system 200 includes, for example, three axes, X, Y, and Z, the data decoding device 1 generates the vector Ea[X][Y][ as axis-dependent data after decoding. Z] is generated.
- X, Y, and Z in the vector Ea[X][Y][Z] are the coordinate values of each axis X, Y, and Z provided in the error correction system 200, and the correction point spacing ⁇ X , ⁇ It is assumed that the index is quantized by Y and ⁇ Z .
- FIG. 32 is a diagram for explaining error correction by the correction unit 202, and more specifically, it is a diagram for explaining error correction when the value after quantization has a fraction below the decimal point.
- the quantization result is ( nX + fX , nY + fY , nZ + fZ ), for example.
- nX , nY , and nZ are integer values
- fX , fY , and fZ are decimal values of 0 or more and less than 1.
- the axis-dependent data after decoding of one point among the eight vertices of the cube is set as a vector Ea[ nX ][ nY ][ nZ ], and each of the remaining seven vertices is decoded.
- the axis-dependent data after conversion are converted into vector Ea [ n X +1][n Y ][ n Z ] , vector Ea[ n ] [n Z +1], vector Ea [ n X +1] [n Y +1] [n Z +1 ] , vector Ea[ n +1][n Z +1], and the vector Ea[n X ][n Y ][n Z +1].
- the error correction system 200 includes a correction unit 202 and a data decoding device 1, and the correction unit 202 is configured to correct errors in industrial machinery based on decoded axis-dependent data. .
- the correction unit 202 is configured to correct errors in industrial machinery based on decoded axis-dependent data.
- it is possible to decode encoded axis-dependent data obtained by encoding axis-dependent data that depends on the coordinate values of each axis of the industrial machine, and as a result, without increasing the storage capacity, It is possible to increase the data such as the amount of error that can be input into the control device of the industrial machine and the like, and it is possible to correct the error of the industrial machine with higher accuracy.
- the first data decoding program includes a linear combination model in which axis-dependent data that depends on the coordinate values of each axis of an industrial machine is approximated as a linear combination of each axis data of the industrial machine, and a model approximated by the linear combination model.
- a data decoding program for causing a computer to execute a step of generating model approximate decoding axis dependent data based on model approximate encoded axis dependent data and decoded model approximate encoded axis dependent data. can do.
- an encoded approximation error amount obtained by encoding the approximation error amount obtained when axis-dependent data is approximated by a linear combination model is obtained, and the encoded approximation error amount is decoded. and generating post-decoding axis-dependent data after combining the approximation error amounts by combining the approximate error amount after decoding with the model approximation decoding axis-dependent data.
- a second data decryption program can be provided for causing a computer to perform the steps.
- the approximation error amount is set as the approximation error amount within a predetermined tolerance from which the approximation error amount exceeding the predetermined tolerance is removed, the approximation error amount exceeding the predetermined tolerance is obtained, and the approximation error amount is combined.
- a third data decoding program for causing a computer to execute the step of generating decoded axis-dependent data by combining an approximation error amount exceeding a predetermined tolerance with subsequent decoded axis-dependent data. can do.
- an error correction program for causing the above-described error correction system 200 to execute the above-mentioned correction process, the error correction program for causing a computer to execute a step of correcting an error of an industrial machine based on decoded axis-dependent data. programs can be provided.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Automation & Control Theory (AREA)
- Image Processing (AREA)
Abstract
Description
産業機械の各軸の誤差補正に用いられる誤差量等の軸依存データは、全体として出現頻度が一様なホワイトノイズ的な性質を有する場合がある。そのため、データ上における値の出現頻度の偏り、即ち情報エントロピーの小ささを利用する従来のエントロピー符号化技術では、軸依存データを圧縮することが困難である。これに対して本実施形態に係るデータ復号化装置1は、産業機械の各軸の座標値に依存する軸依存データを符号化して圧縮したデータを復号化可能なデータ復号化装置である。
先ず、データ復号化装置1の構成を説明する前に、産業機械の各軸の座標値に依存する軸依存データを符号化して圧縮可能なデータ符号化装置について、従来のデータ符号化技術とともに詳しく説明する。
図2は、データ符号化装置の第1の例の構成を示す図である。図2に示されるように、データ符号化装置101は、モデル近似符号化部111を備える。モデル近似符号化部111は、軸依存データと、一次結合モデルと、に基づいて、軸依存データを符号化したモデル近似符号化後軸依存データ(以下、符号化後軸依存データともいう)を生成する。
図14は、データ符号化装置の第2の例の構成を示す図である。図14に示されるように、データ符号化装置102は、軸依存データ分割部122を備える点においてデータ符号化装置101と相違する。また、モデル近似符号化部121が、軸依存データを複数に分割して生成された分割後軸依存データと、上述の一次結合モデルと、に基づいてモデル近似符号化を実行する点において、上述の第1の例のモデル近似符号化部111と相違する。これら相違点以外の構成については、第1の例と共通である。
図17は、データ符号化装置の第3の例の構成を示す図である。図17に示されるように、データ符号化装置103は、軸依存データ分割部132の構成が上述の軸依存データ分割部122と相違する点において、第2の例と相違する。この相違点以外の構成については、第2の例と共通である。
図21は、データ符号化装置の第4の例の構成を示す図である。図21に示されるように、データ符号化装置104は、モデル近似符号化部141が近似誤差算出部142を備える点において、上述のモデル近似符号化部111と相違する。また、データ符号化装置104は近似誤差符号化部143を備える点において、上述のデータ符号化装置101と相違する。これら相違点以外の構成については、第1の例と共通である。
図23は、データ符号化装置の第5の例の構成を示す図である。図23に示されるように、データ符号化装置105は、所定トレランス以上の近似誤差除去部153をさらに備える点において、上述のデータ符号化装置104と相違する。また、近似誤差符号化部154が所定トレランス以内の近似誤差量を符号化する点において、上述の近似誤差符号化部143と相違する。これら相違点以外の構成については、第4の例と共通である。
図26は、データ符号化装置の第6の例の構成を示す図である。図26に示されるように、データ符号化装置106は、モデル近似符号化後データ符号化部162をさらに備える点において上述のデータ符号化装置101と相違する。この相違点以外は、第1の例と共通の構成である。
図27は、データ符号化装置の第7の例の構成を示す図である。図27に示されるように、データ符号化装置107は、動的計画法の代わりに機械学習装置109による強化学習結果を取得する学習結果取得部を備え、該学習結果を利用して軸依存データを区間分割する点において、上述のデータ符号化装置103と相違する。この相違点以外の構成については、第3の例と共通である。
図1に戻って、第1実施形態に係るデータ復号化装置1について説明する。
図29は、第2実施形態に係るデータ復号化装置の構成を示す図である。図29に示されるように、第2実施形態に係るデータ復号化装置2は、近似誤差復号化部22と、近似誤差量結合部23と、を備える点において第1実施形態に係るデータ復号化装置1と相違する。また、復号化部21で生成されるモデル近似復号化後軸依存データに、復号化後近似誤差量を結合することにより復号化後軸依存データを生成する点において、第1実施形態と相違する。これら相違点以外の構成については、第1実施形態と共通である。
図30は、第3実施形態に係るデータ復号化装置の構成を示す図である。図30に示されるように、第3実施形態に係るデータ復号化装置3は、所定トレランスを超える近似誤差量結合部34を備える点において第2実施形態に係るデータ復号化装置2と相違する。また、近似誤差量結合後の復号化後軸依存データに所定トレランスを超える近似誤差量を結合することにより復号化後軸依存データを生成する点において、第2実施形態と相違する。これら相違点以外の構成については、第2実施形態と共通である。
図31は、第1実施形態に係るデータ復号化装置1を備える誤差補正システム200の構成を示す図である。本実施形態に係る誤差補正システム200は、データ復号化装置1により生成される復号化後軸依存データを用いて、産業機械の誤差を補正するものである。
11,21,31 復号化部
22,32 近似誤差復号化部
23,33 近似誤差量結合部
34 所定トレランスを超える近似誤差量結合部
101,102,103,104,105,106,107 データ符号化装置
109 機械学習装置
111,121,131,141,151,161 モデル近似符号化部
122,132 軸依存データ分割部
133 動的計画法処理部
134 モデル近似符号化後の最適性評価部
135 軸依存データの部分分割部
136 部分的軸依存データの最適化結果結合部
142 近似誤差算出部
143 近似誤差符号化部
152 近似誤差算出部
153 所定トレランスを超える近似誤差除去部
154 近似誤差符号化部
162 モデル近似符号化後データ符号化部
200 誤差補正システム
201 指令解析部
202 補正部
203 補間部
204 X軸用加減速部
205 Y軸用加減速部
206 Z軸用加減速部
207 X軸サーボ
208 Y軸サーボ
209 Z軸サーボ
Claims (5)
- 符号化されたデータを復号化するデータ復号化装置であって、
産業機械の各軸の座標値に依存する軸依存データを前記産業機械の各軸データの一次結合として近似する一次結合モデルと、前記一次結合モデルによりモデル近似されたモデル近似符号化軸依存データと、に基づいて、前記モデル近似符号化軸依存データを復号化したモデル近似復号化後軸依存データを生成する復号化部を備える、データ復号化装置。 - 前記軸依存データを前記一次結合モデルによりモデル近似したときに得られる近似誤差量を符号化した符号化後近似誤差量を取得し、前記符号化後近似誤差量を復号化して復号化後近似誤差量を生成する近似誤差復号化部と、
前記モデル近似復号化後軸依存データに前記復号化後近似誤差量を結合することにより、近似誤差量結合後の復号化後軸依存データを生成する近似誤差量結合部と、をさらに備える、請求項1に記載のデータ復号化装置。 - 前記近似誤差量は、所定トレランスを超える近似誤差量が除去された所定トレランス以内の近似誤差量であり、
前記所定トレランスを超える近似誤差量を取得し、前記近似誤差量結合後の復号化後軸依存データに前記所定トレランスを超える近似誤差量を結合することにより、復号化後軸依存データを生成する所定トレランス超え近似誤差量結合部をさらに備える、請求項2に記載のデータ復号化装置。 - 産業機械の誤差を補正する誤差補正システムであって、
補正部と、請求項1から3いずれかに記載のデータ復号化装置と、を備え、
前記補正部は、前記復号化後軸依存データに基づいて前記産業機械の誤差を補正する、誤差補正システム。 - 符号化されたデータを復号化するデータ復号化プログラムであって、
産業機械の各軸の座標値に依存する軸依存データを前記産業機械の各軸データの一次結合として近似する一次結合モデルと、前記一次結合モデルによりモデル近似されたモデル近似符号化軸依存データと、に基づいて、前記モデル近似符号化軸依存データを復号化したモデル近似復号化後軸依存データを生成させるステップをコンピュータに実行させるためのデータ復号化プログラム。
Priority Applications (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US18/873,239 US20250370837A1 (en) | 2022-06-24 | 2022-06-24 | Data decoding device, error correction system, and non-transitory computer-readable medium storing a data decoding program |
| PCT/JP2022/025416 WO2023248482A1 (ja) | 2022-06-24 | 2022-06-24 | データ復号化装置、誤差補正システム及びデータ復号化プログラム |
| JP2024528259A JP7807544B2 (ja) | 2022-06-24 | 2022-06-24 | データ復号化装置、誤差補正システム及びデータ復号化プログラム |
| CN202280097202.5A CN119384649A (zh) | 2022-06-24 | 2022-06-24 | 数据解码装置、误差校正系统以及数据解码程序 |
| DE112022007085.4T DE112022007085T5 (de) | 2022-06-24 | 2022-06-24 | Datendecodiervorrichtung, Fehlerkorrektursystem, und Datendecodierprogramm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/JP2022/025416 WO2023248482A1 (ja) | 2022-06-24 | 2022-06-24 | データ復号化装置、誤差補正システム及びデータ復号化プログラム |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023248482A1 true WO2023248482A1 (ja) | 2023-12-28 |
Family
ID=89379325
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2022/025416 Ceased WO2023248482A1 (ja) | 2022-06-24 | 2022-06-24 | データ復号化装置、誤差補正システム及びデータ復号化プログラム |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US20250370837A1 (ja) |
| JP (1) | JP7807544B2 (ja) |
| CN (1) | CN119384649A (ja) |
| DE (1) | DE112022007085T5 (ja) |
| WO (1) | WO2023248482A1 (ja) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08339216A (ja) * | 1995-06-09 | 1996-12-24 | Mitsubishi Electric Corp | コンピュータ制御型数値制御装置のパラメータ設定方法およびコンピュータ制御型数値制御装置 |
| JP2000099123A (ja) * | 1998-09-22 | 2000-04-07 | Matsushita Electric Ind Co Ltd | 産業用ロボット |
| JP2011209897A (ja) * | 2010-03-29 | 2011-10-20 | Fanuc Ltd | 5軸加工機を制御する数値制御装置 |
| JP2014113674A (ja) * | 2012-12-12 | 2014-06-26 | Hirokiko Co Ltd | 補正プログラム及びその記憶媒体 |
| CN112558547A (zh) * | 2021-02-19 | 2021-03-26 | 成都飞机工业(集团)有限责任公司 | 一种五轴数控机床平动轴几何误差补偿数据快速优化方法 |
| JP2021092954A (ja) * | 2019-12-10 | 2021-06-17 | ファナック株式会社 | ワークモデルの修正量を学習する機械学習装置、制御装置、加工システム、及び機械学習方法 |
-
2022
- 2022-06-24 CN CN202280097202.5A patent/CN119384649A/zh active Pending
- 2022-06-24 WO PCT/JP2022/025416 patent/WO2023248482A1/ja not_active Ceased
- 2022-06-24 JP JP2024528259A patent/JP7807544B2/ja active Active
- 2022-06-24 US US18/873,239 patent/US20250370837A1/en active Pending
- 2022-06-24 DE DE112022007085.4T patent/DE112022007085T5/de active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08339216A (ja) * | 1995-06-09 | 1996-12-24 | Mitsubishi Electric Corp | コンピュータ制御型数値制御装置のパラメータ設定方法およびコンピュータ制御型数値制御装置 |
| JP2000099123A (ja) * | 1998-09-22 | 2000-04-07 | Matsushita Electric Ind Co Ltd | 産業用ロボット |
| JP2011209897A (ja) * | 2010-03-29 | 2011-10-20 | Fanuc Ltd | 5軸加工機を制御する数値制御装置 |
| JP2014113674A (ja) * | 2012-12-12 | 2014-06-26 | Hirokiko Co Ltd | 補正プログラム及びその記憶媒体 |
| JP2021092954A (ja) * | 2019-12-10 | 2021-06-17 | ファナック株式会社 | ワークモデルの修正量を学習する機械学習装置、制御装置、加工システム、及び機械学習方法 |
| CN112558547A (zh) * | 2021-02-19 | 2021-03-26 | 成都飞机工业(集团)有限责任公司 | 一种五轴数控机床平动轴几何误差补偿数据快速优化方法 |
Non-Patent Citations (1)
| Title |
|---|
| VOLODYMYR MNIH, KORAY KAVUKCUOGLU, DAVID SILVER, ANDREI A. RUSU, JOEL VENESS, MARC G. BELLEMARE, ALEX GRAVES, MARTIN RIEDMILLER, A: "Human-level control through deep reinforcement learning", NATURE, vol. 518, no. 7540, pages 529 - 533, XP055283401, DOI: 10.1038/nature14236 * |
Also Published As
| Publication number | Publication date |
|---|---|
| DE112022007085T5 (de) | 2025-04-24 |
| CN119384649A (zh) | 2025-01-28 |
| JP7807544B2 (ja) | 2026-01-27 |
| US20250370837A1 (en) | 2025-12-04 |
| JPWO2023248482A1 (ja) | 2023-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113706686A (zh) | 一种三维点云重建结果补全方法及相关组件 | |
| JP4210056B2 (ja) | 工具経路の作成装置及び方法 | |
| CN101925925A (zh) | 基于预测的图像处理 | |
| JP2017126890A (ja) | 符号化装置及びその制御方法 | |
| CN106157339A (zh) | 基于低秩顶点轨迹子空间提取的动画网格序列压缩算法 | |
| EP0822516B1 (en) | Shape data compression method and apparatus | |
| JP2007518367A (ja) | マッチング追跡を用いたデータ圧縮 | |
| JP7807543B2 (ja) | データ符号化装置及びデータ符号化プログラム | |
| JP2024086700A (ja) | 製造用センサデータのシーケンスモデリングを行うシステム及び方法 | |
| JP7807544B2 (ja) | データ復号化装置、誤差補正システム及びデータ復号化プログラム | |
| CN113065204B (zh) | 一种液压支架油缸参数化设计方法及系统 | |
| US6609045B1 (en) | File conversion apparatus for machining program of numerical control system and computer readable recording medium for storing program for computer to execute file conversion process | |
| CN112958313A (zh) | 使用距离矩阵加权特征的智能区域补偿喷漆参数控制方法 | |
| CN115091211B (zh) | 数控车磨复合机床及其生产控制方法 | |
| JP7807545B2 (ja) | 近似誤差検出装置及び近似誤差検出プログラム | |
| CN118484724B (zh) | 基于人工智能的系留固定索具的性能评估方法及装置 | |
| JP4524501B2 (ja) | 符号化システム、符号化方法、符号化プログラム、復号化システム、復号化方法および復号化プログラム | |
| CN117540517A (zh) | 一种基于两阶段深度概率模型的快速拓扑优化方法 | |
| CN106101731A (zh) | 图像无损压缩方法及装置 | |
| JP2022045615A (ja) | 演算装置及び演算方法 | |
| Parker et al. | Structural optimization of a force balance using a computational experiment design | |
| JPH1097645A (ja) | 形状データ圧縮方法,伸長方法、及び形状データ圧縮装置,伸長装置 | |
| CN121389731B (zh) | 一种地下场景中六自由度并联机构的位姿计算方法及装置 | |
| JP7649452B2 (ja) | 情報処理装置及びプログラム | |
| CN118537702B (zh) | 一种基于自适应拓扑结构的视觉或文本任务深度学习方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22948041 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2024528259 Country of ref document: JP Ref document number: 18873239 Country of ref document: US |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 112022007085 Country of ref document: DE Ref document number: 202280097202.5 Country of ref document: CN |
|
| WWP | Wipo information: published in national office |
Ref document number: 202280097202.5 Country of ref document: CN |
|
| WWP | Wipo information: published in national office |
Ref document number: 112022007085 Country of ref document: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 22948041 Country of ref document: EP Kind code of ref document: A1 |
|
| WWP | Wipo information: published in national office |
Ref document number: 18873239 Country of ref document: US |
















